diff --git a/.gitignore b/.gitignore
index 5d947ca..bc90b94 100644
--- a/.gitignore
+++ b/.gitignore
@@ -16,3 +16,15 @@ bin-release/
# Project files, i.e. `.project`, `.actionScriptProperties` and `.flexProperties`
# should NOT be excluded as they contain compiler settings and other important
# information for Eclipse / Flash Builder.
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+.venv
+pip-selfcheck.json
diff --git a/.idea/StackOverflow-LiteAPI.iml b/.idea/StackOverflow-LiteAPI.iml
new file mode 100644
index 0000000..6711323
--- /dev/null
+++ b/.idea/StackOverflow-LiteAPI.iml
@@ -0,0 +1,20 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 0000000..8656114
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,7 @@
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..da05ddf
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..94a25f7
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
new file mode 100644
index 0000000..38c874e
--- /dev/null
+++ b/.idea/workspace.xml
@@ -0,0 +1,232 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ true
+ DEFINITION_ORDER
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 1534536454935
+
+
+ 1534536454935
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.pytest_cache/README.md b/.pytest_cache/README.md
new file mode 100644
index 0000000..bb78ba0
--- /dev/null
+++ b/.pytest_cache/README.md
@@ -0,0 +1,8 @@
+# pytest cache directory #
+
+This directory contains data from the pytest's cache plugin,
+which provides the `--lf` and `--ff` options, as well as the `cache` fixture.
+
+**Do not** commit this to version control.
+
+See [the docs](https://docs.pytest.org/en/latest/cache.html) for more information.
diff --git a/.pytest_cache/v/cache/lastfailed b/.pytest_cache/v/cache/lastfailed
new file mode 100644
index 0000000..324f1ce
--- /dev/null
+++ b/.pytest_cache/v/cache/lastfailed
@@ -0,0 +1,4 @@
+{
+ "Users/test_Users.py::test_dummy": true,
+ "Users/test_Users.py::test_new_user": true
+}
\ No newline at end of file
diff --git a/.pytest_cache/v/cache/nodeids b/.pytest_cache/v/cache/nodeids
new file mode 100644
index 0000000..26f1862
--- /dev/null
+++ b/.pytest_cache/v/cache/nodeids
@@ -0,0 +1,283 @@
+[
+ "Lib/site-packages/more_itertools/tests/test_more.py::CollateTests::test_alias",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CollateTests::test_default",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CollateTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CollateTests::test_key",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CollateTests::test_one",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CollateTests::test_reverse",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ChunkedTests::test_even",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ChunkedTests::test_odd",
+ "Lib/site-packages/more_itertools/tests/test_more.py::FirstTests::test_default",
+ "Lib/site-packages/more_itertools/tests/test_more.py::FirstTests::test_empty_stop_iteration",
+ "Lib/site-packages/more_itertools/tests/test_more.py::FirstTests::test_many",
+ "Lib/site-packages/more_itertools/tests/test_more.py::FirstTests::test_one",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_customrange",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_default_nonsliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_default_sliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_dict",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_empty_stop_iteration_nonsliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_empty_stop_iteration_sliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_many_nonsliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_many_sliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_one_nonsliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_one_sliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LastTests::test_ordereddict",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_indexing",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_multi_prepend",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_multi_prepend_peek",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_passthrough",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_peek_default",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_after_stop",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_indexing",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_iterable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_many",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_reversed",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_slicing",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_prepend_truthiness",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_simple_peeking",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_slicing",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_slicing_error",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_slicing_reset",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PeekableTests::test_truthiness",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ConsumerTests::test_consumer",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DistinctPermutationsTests::test_distinct_permutations",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DistinctPermutationsTests::test_other_iterables",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IlenTests::test_ilen",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WithIterTests::test_with_iter",
+ "Lib/site-packages/more_itertools/tests/test_more.py::OneTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::OneTests::test_too_long",
+ "Lib/site-packages/more_itertools/tests/test_more.py::OneTests::test_too_short",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IntersperseTest::test_even",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IntersperseTest::test_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IntersperseTest::test_n_zero",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IntersperseTest::test_nested",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IntersperseTest::test_not_iterable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IntersperseTest::test_odd",
+ "Lib/site-packages/more_itertools/tests/test_more.py::UniqueToEachTests::test_all_unique",
+ "Lib/site-packages/more_itertools/tests/test_more.py::UniqueToEachTests::test_duplicates",
+ "Lib/site-packages/more_itertools/tests/test_more.py::UniqueToEachTests::test_mixed",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WindowedTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WindowedTests::test_fillvalue",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WindowedTests::test_large_size",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WindowedTests::test_negative",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WindowedTests::test_step",
+ "Lib/site-packages/more_itertools/tests/test_more.py::WindowedTests::test_zero",
+ "Lib/site-packages/more_itertools/tests/test_more.py::BucketTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::BucketTests::test_in",
+ "Lib/site-packages/more_itertools/tests/test_more.py::BucketTests::test_validator",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SpyTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SpyTests::test_too_many",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SpyTests::test_unpacking",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SpyTests::test_zero",
+ "Lib/site-packages/more_itertools/tests/test_more.py::InterleaveTests::test_even",
+ "Lib/site-packages/more_itertools/tests/test_more.py::InterleaveTests::test_mixed_types",
+ "Lib/site-packages/more_itertools/tests/test_more.py::InterleaveTests::test_short",
+ "Lib/site-packages/more_itertools/tests/test_more.py::InterleaveLongestTests::test_even",
+ "Lib/site-packages/more_itertools/tests/test_more.py::InterleaveLongestTests::test_mixed_types",
+ "Lib/site-packages/more_itertools/tests/test_more.py::InterleaveLongestTests::test_short",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestCollapse::test_collapse",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestCollapse::test_collapse_flatten",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestCollapse::test_collapse_to_level",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestCollapse::test_collapse_to_list",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestCollapse::test_collapse_to_string",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SideEffectTests::test_before_after",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SideEffectTests::test_before_fails",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SideEffectTests::test_chunked",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SideEffectTests::test_individual",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SlicedTests::test_even",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SlicedTests::test_not_sliceable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SlicedTests::test_odd",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitAtTests::test_seperators",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitBeforeTest::test_ends_with_sep",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitBeforeTest::test_no_sep",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitBeforeTest::test_starts_with_sep",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitAfterTest::test_ends_with_sep",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitAfterTest::test_no_sep",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SplitAfterTest::test_starts_with_sep",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PaddedTest::test_invalid_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PaddedTest::test_next_multiple",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PaddedTest::test_no_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::PaddedTest::test_valid_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DistributeTest::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DistributeTest::test_invalid_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DistributeTest::test_large_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::StaggerTest::test_default",
+ "Lib/site-packages/more_itertools/tests/test_more.py::StaggerTest::test_longest",
+ "Lib/site-packages/more_itertools/tests/test_more.py::StaggerTest::test_offsets",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ZipOffsetTest::test_longest",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ZipOffsetTest::test_mismatch",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ZipOffsetTest::test_shortest",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SortTogetherTest::test_invalid_key_list",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SortTogetherTest::test_key_list",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SortTogetherTest::test_reverse",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SortTogetherTest::test_uneven_iterables",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DivideTest::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DivideTest::test_invalid_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DivideTest::test_large_n",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestAlwaysIterable::test_base_type",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestAlwaysIterable::test_generator",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestAlwaysIterable::test_iterables",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestAlwaysIterable::test_none",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestAlwaysIterable::test_single",
+ "Lib/site-packages/more_itertools/tests/test_more.py::TestAlwaysIterable::test_strings",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_call_once",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_consecutive_true",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_distance",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_empty_iterable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_grouping",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_large_distance",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_length_one",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_negative_distance",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_typical",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AdjacentTests::test_zero_distance",
+ "Lib/site-packages/more_itertools/tests/test_more.py::GroupByTransformTests::test_default_funcs",
+ "Lib/site-packages/more_itertools/tests/test_more.py::GroupByTransformTests::test_no_valuefunc",
+ "Lib/site-packages/more_itertools/tests/test_more.py::GroupByTransformTests::test_valuefunc",
+ "Lib/site-packages/more_itertools/tests/test_more.py::NumericRangeTests::test_arg_count",
+ "Lib/site-packages/more_itertools/tests/test_more.py::NumericRangeTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::NumericRangeTests::test_zero_step",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CountCycleTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CountCycleTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CountCycleTests::test_negative",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LocateTests::test_custom_pred",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LocateTests::test_default_pred",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LocateTests::test_no_matches",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LocateTests::test_window_size",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LocateTests::test_window_size_large",
+ "Lib/site-packages/more_itertools/tests/test_more.py::LocateTests::test_window_size_zero",
+ "Lib/site-packages/more_itertools/tests/test_more.py::StripFunctionTests::test_hashable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::StripFunctionTests::test_math",
+ "Lib/site-packages/more_itertools/tests/test_more.py::StripFunctionTests::test_not_hashable",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IsliceExtendedTests::test_all",
+ "Lib/site-packages/more_itertools/tests/test_more.py::IsliceExtendedTests::test_zero_step",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ConsecutiveGroupsTest::test_custom_ordering",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ConsecutiveGroupsTest::test_exotic_ordering",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ConsecutiveGroupsTest::test_numbers",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DifferenceTest::test_custom",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DifferenceTest::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DifferenceTest::test_normal",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DifferenceTest::test_one",
+ "Lib/site-packages/more_itertools/tests/test_more.py::DifferenceTest::test_roundtrip",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SeekableTest::test_elements",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SeekableTest::test_exhaustion_reset",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SeekableTest::test_forward",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SeekableTest::test_partial_reset",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SeekableTest::test_past_end",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SequenceViewTests::test_abc_methods",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SequenceViewTests::test_indexing",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SequenceViewTests::test_init",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SequenceViewTests::test_slicing",
+ "Lib/site-packages/more_itertools/tests/test_more.py::SequenceViewTests::test_update",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RunLengthTest::test_decode",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RunLengthTest::test_encode",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ExactlyNTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ExactlyNTests::test_false",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ExactlyNTests::test_true",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AlwaysReversibleTests::test_nonseq_reversed",
+ "Lib/site-packages/more_itertools/tests/test_more.py::AlwaysReversibleTests::test_regular_reversed",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CircularShiftsTests::test_duplicates",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CircularShiftsTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_more.py::CircularShiftsTests::test_simple_circular_shifts",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MakeDecoratorTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MakeDecoratorTests::test_result_index",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MakeDecoratorTests::test_wrap_class",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MapReduceTests::test_default",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MapReduceTests::test_reducefunc",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MapReduceTests::test_ret",
+ "Lib/site-packages/more_itertools/tests/test_more.py::MapReduceTests::test_valuefunc",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_custom_pred",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_default_pred",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_efficient_reversal",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_no_matches",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_window_size",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_window_size_large",
+ "Lib/site-packages/more_itertools/tests/test_more.py::RlocateTests::test_window_size_zero",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_count",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_iterable_substitutes",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_window_size",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_window_size_count",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_window_size_end",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_window_size_large",
+ "Lib/site-packages/more_itertools/tests/test_more.py::ReplaceTests::test_window_size_zero",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AccumulateTests::test_bogus_function",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AccumulateTests::test_custom_function",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AccumulateTests::test_default",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AccumulateTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TakeTests::test_negative_take",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TakeTests::test_null_take",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TakeTests::test_simple_take",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TakeTests::test_take_too_much",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TabulateTests::test_count",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TabulateTests::test_simple_tabulate",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TailTests::test_equal",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TailTests::test_greater",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::TailTests::test_less",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::ConsumeTests::test_negative_consume",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::ConsumeTests::test_null_consume",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::ConsumeTests::test_sanity",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::ConsumeTests::test_total_consume",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthTests::test_default",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthTests::test_negative_item_raises",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AllEqualTests::test_empty",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AllEqualTests::test_false",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AllEqualTests::test_one",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AllEqualTests::test_tricky",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::AllEqualTests::test_true",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::QuantifyTests::test_custom_predicate",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::QuantifyTests::test_happy_path",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PadnoneTests::test_happy_path",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NcyclesTests::test_happy_path",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NcyclesTests::test_null_case",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NcyclesTests::test_pathalogical_case",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::DotproductTests::test_happy_path",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::FlattenTests::test_basic_usage",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::FlattenTests::test_single_level",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RepeatfuncTests::test_added_arguments",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RepeatfuncTests::test_finite_repeat",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RepeatfuncTests::test_null_times",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RepeatfuncTests::test_simple_repeat",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PairwiseTests::test_base_case",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PairwiseTests::test_short_case",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::GrouperTests::test_even",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::GrouperTests::test_fill_value",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::GrouperTests::test_odd",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RoundrobinTests::test_even_groups",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RoundrobinTests::test_uneven_groups",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PartitionTests::test_arbitrary",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PartitionTests::test_bool",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PowersetTests::test_combinatorics",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::UniqueEverseenTests::test_custom_key",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::UniqueEverseenTests::test_everseen",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::UniqueEverseenTests::test_unhashable",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::UniqueEverseenTests::test_unhashable_key",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::UniqueJustseenTests::test_custom_key",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::UniqueJustseenTests::test_justseen",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::IterExceptTests::test_exact_exception",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::IterExceptTests::test_first",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::IterExceptTests::test_generic_exception",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::IterExceptTests::test_uncaught_exception_is_raised",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::FirstTrueTests::test_default",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::FirstTrueTests::test_nothing_true",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::FirstTrueTests::test_pred",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::FirstTrueTests::test_something_true",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomProductTests::test_list_with_repeat",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomProductTests::test_simple_lists",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomPermutationTests::test_full_permutation",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomPermutationTests::test_partial_permutation",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomCombinationTests::test_no_replacement",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomCombinationTests::test_psuedorandomness",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomCombinationWithReplacementTests::test_pseudorandomness",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::RandomCombinationWithReplacementTests::test_replacement",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthCombinationTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthCombinationTests::test_invalid_index",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthCombinationTests::test_invalid_r",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::NthCombinationTests::test_long",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PrependTests::test_basic",
+ "Lib/site-packages/more_itertools/tests/test_recipes.py::PrependTests::test_multiple",
+ "Users/test_Users.py::test_new_user",
+ "Users/test_Users.py::test_dummy"
+]
\ No newline at end of file
diff --git a/.travis.yml b/.travis.yml
new file mode 100644
index 0000000..2464d3a
--- /dev/null
+++ b/.travis.yml
@@ -0,0 +1,4 @@
+language: python
+rvm: 3.7.0
+
+sudo: enabled
diff --git a/Include/Python-ast.h b/Include/Python-ast.h
new file mode 100644
index 0000000..8e0f750
--- /dev/null
+++ b/Include/Python-ast.h
@@ -0,0 +1,637 @@
+/* File automatically generated by Parser/asdl_c.py. */
+
+#include "asdl.h"
+
+typedef struct _mod *mod_ty;
+
+typedef struct _stmt *stmt_ty;
+
+typedef struct _expr *expr_ty;
+
+typedef enum _expr_context { Load=1, Store=2, Del=3, AugLoad=4, AugStore=5,
+ Param=6 } expr_context_ty;
+
+typedef struct _slice *slice_ty;
+
+typedef enum _boolop { And=1, Or=2 } boolop_ty;
+
+typedef enum _operator { Add=1, Sub=2, Mult=3, MatMult=4, Div=5, Mod=6, Pow=7,
+ LShift=8, RShift=9, BitOr=10, BitXor=11, BitAnd=12,
+ FloorDiv=13 } operator_ty;
+
+typedef enum _unaryop { Invert=1, Not=2, UAdd=3, USub=4 } unaryop_ty;
+
+typedef enum _cmpop { Eq=1, NotEq=2, Lt=3, LtE=4, Gt=5, GtE=6, Is=7, IsNot=8,
+ In=9, NotIn=10 } cmpop_ty;
+
+typedef struct _comprehension *comprehension_ty;
+
+typedef struct _excepthandler *excepthandler_ty;
+
+typedef struct _arguments *arguments_ty;
+
+typedef struct _arg *arg_ty;
+
+typedef struct _keyword *keyword_ty;
+
+typedef struct _alias *alias_ty;
+
+typedef struct _withitem *withitem_ty;
+
+
+enum _mod_kind {Module_kind=1, Interactive_kind=2, Expression_kind=3,
+ Suite_kind=4};
+struct _mod {
+ enum _mod_kind kind;
+ union {
+ struct {
+ asdl_seq *body;
+ } Module;
+
+ struct {
+ asdl_seq *body;
+ } Interactive;
+
+ struct {
+ expr_ty body;
+ } Expression;
+
+ struct {
+ asdl_seq *body;
+ } Suite;
+
+ } v;
+};
+
+enum _stmt_kind {FunctionDef_kind=1, AsyncFunctionDef_kind=2, ClassDef_kind=3,
+ Return_kind=4, Delete_kind=5, Assign_kind=6,
+ AugAssign_kind=7, AnnAssign_kind=8, For_kind=9,
+ AsyncFor_kind=10, While_kind=11, If_kind=12, With_kind=13,
+ AsyncWith_kind=14, Raise_kind=15, Try_kind=16,
+ Assert_kind=17, Import_kind=18, ImportFrom_kind=19,
+ Global_kind=20, Nonlocal_kind=21, Expr_kind=22, Pass_kind=23,
+ Break_kind=24, Continue_kind=25};
+struct _stmt {
+ enum _stmt_kind kind;
+ union {
+ struct {
+ identifier name;
+ arguments_ty args;
+ asdl_seq *body;
+ asdl_seq *decorator_list;
+ expr_ty returns;
+ } FunctionDef;
+
+ struct {
+ identifier name;
+ arguments_ty args;
+ asdl_seq *body;
+ asdl_seq *decorator_list;
+ expr_ty returns;
+ } AsyncFunctionDef;
+
+ struct {
+ identifier name;
+ asdl_seq *bases;
+ asdl_seq *keywords;
+ asdl_seq *body;
+ asdl_seq *decorator_list;
+ } ClassDef;
+
+ struct {
+ expr_ty value;
+ } Return;
+
+ struct {
+ asdl_seq *targets;
+ } Delete;
+
+ struct {
+ asdl_seq *targets;
+ expr_ty value;
+ } Assign;
+
+ struct {
+ expr_ty target;
+ operator_ty op;
+ expr_ty value;
+ } AugAssign;
+
+ struct {
+ expr_ty target;
+ expr_ty annotation;
+ expr_ty value;
+ int simple;
+ } AnnAssign;
+
+ struct {
+ expr_ty target;
+ expr_ty iter;
+ asdl_seq *body;
+ asdl_seq *orelse;
+ } For;
+
+ struct {
+ expr_ty target;
+ expr_ty iter;
+ asdl_seq *body;
+ asdl_seq *orelse;
+ } AsyncFor;
+
+ struct {
+ expr_ty test;
+ asdl_seq *body;
+ asdl_seq *orelse;
+ } While;
+
+ struct {
+ expr_ty test;
+ asdl_seq *body;
+ asdl_seq *orelse;
+ } If;
+
+ struct {
+ asdl_seq *items;
+ asdl_seq *body;
+ } With;
+
+ struct {
+ asdl_seq *items;
+ asdl_seq *body;
+ } AsyncWith;
+
+ struct {
+ expr_ty exc;
+ expr_ty cause;
+ } Raise;
+
+ struct {
+ asdl_seq *body;
+ asdl_seq *handlers;
+ asdl_seq *orelse;
+ asdl_seq *finalbody;
+ } Try;
+
+ struct {
+ expr_ty test;
+ expr_ty msg;
+ } Assert;
+
+ struct {
+ asdl_seq *names;
+ } Import;
+
+ struct {
+ identifier module;
+ asdl_seq *names;
+ int level;
+ } ImportFrom;
+
+ struct {
+ asdl_seq *names;
+ } Global;
+
+ struct {
+ asdl_seq *names;
+ } Nonlocal;
+
+ struct {
+ expr_ty value;
+ } Expr;
+
+ } v;
+ int lineno;
+ int col_offset;
+};
+
+enum _expr_kind {BoolOp_kind=1, BinOp_kind=2, UnaryOp_kind=3, Lambda_kind=4,
+ IfExp_kind=5, Dict_kind=6, Set_kind=7, ListComp_kind=8,
+ SetComp_kind=9, DictComp_kind=10, GeneratorExp_kind=11,
+ Await_kind=12, Yield_kind=13, YieldFrom_kind=14,
+ Compare_kind=15, Call_kind=16, Num_kind=17, Str_kind=18,
+ FormattedValue_kind=19, JoinedStr_kind=20, Bytes_kind=21,
+ NameConstant_kind=22, Ellipsis_kind=23, Constant_kind=24,
+ Attribute_kind=25, Subscript_kind=26, Starred_kind=27,
+ Name_kind=28, List_kind=29, Tuple_kind=30};
+struct _expr {
+ enum _expr_kind kind;
+ union {
+ struct {
+ boolop_ty op;
+ asdl_seq *values;
+ } BoolOp;
+
+ struct {
+ expr_ty left;
+ operator_ty op;
+ expr_ty right;
+ } BinOp;
+
+ struct {
+ unaryop_ty op;
+ expr_ty operand;
+ } UnaryOp;
+
+ struct {
+ arguments_ty args;
+ expr_ty body;
+ } Lambda;
+
+ struct {
+ expr_ty test;
+ expr_ty body;
+ expr_ty orelse;
+ } IfExp;
+
+ struct {
+ asdl_seq *keys;
+ asdl_seq *values;
+ } Dict;
+
+ struct {
+ asdl_seq *elts;
+ } Set;
+
+ struct {
+ expr_ty elt;
+ asdl_seq *generators;
+ } ListComp;
+
+ struct {
+ expr_ty elt;
+ asdl_seq *generators;
+ } SetComp;
+
+ struct {
+ expr_ty key;
+ expr_ty value;
+ asdl_seq *generators;
+ } DictComp;
+
+ struct {
+ expr_ty elt;
+ asdl_seq *generators;
+ } GeneratorExp;
+
+ struct {
+ expr_ty value;
+ } Await;
+
+ struct {
+ expr_ty value;
+ } Yield;
+
+ struct {
+ expr_ty value;
+ } YieldFrom;
+
+ struct {
+ expr_ty left;
+ asdl_int_seq *ops;
+ asdl_seq *comparators;
+ } Compare;
+
+ struct {
+ expr_ty func;
+ asdl_seq *args;
+ asdl_seq *keywords;
+ } Call;
+
+ struct {
+ object n;
+ } Num;
+
+ struct {
+ string s;
+ } Str;
+
+ struct {
+ expr_ty value;
+ int conversion;
+ expr_ty format_spec;
+ } FormattedValue;
+
+ struct {
+ asdl_seq *values;
+ } JoinedStr;
+
+ struct {
+ bytes s;
+ } Bytes;
+
+ struct {
+ singleton value;
+ } NameConstant;
+
+ struct {
+ constant value;
+ } Constant;
+
+ struct {
+ expr_ty value;
+ identifier attr;
+ expr_context_ty ctx;
+ } Attribute;
+
+ struct {
+ expr_ty value;
+ slice_ty slice;
+ expr_context_ty ctx;
+ } Subscript;
+
+ struct {
+ expr_ty value;
+ expr_context_ty ctx;
+ } Starred;
+
+ struct {
+ identifier id;
+ expr_context_ty ctx;
+ } Name;
+
+ struct {
+ asdl_seq *elts;
+ expr_context_ty ctx;
+ } List;
+
+ struct {
+ asdl_seq *elts;
+ expr_context_ty ctx;
+ } Tuple;
+
+ } v;
+ int lineno;
+ int col_offset;
+};
+
+enum _slice_kind {Slice_kind=1, ExtSlice_kind=2, Index_kind=3};
+struct _slice {
+ enum _slice_kind kind;
+ union {
+ struct {
+ expr_ty lower;
+ expr_ty upper;
+ expr_ty step;
+ } Slice;
+
+ struct {
+ asdl_seq *dims;
+ } ExtSlice;
+
+ struct {
+ expr_ty value;
+ } Index;
+
+ } v;
+};
+
+struct _comprehension {
+ expr_ty target;
+ expr_ty iter;
+ asdl_seq *ifs;
+ int is_async;
+};
+
+enum _excepthandler_kind {ExceptHandler_kind=1};
+struct _excepthandler {
+ enum _excepthandler_kind kind;
+ union {
+ struct {
+ expr_ty type;
+ identifier name;
+ asdl_seq *body;
+ } ExceptHandler;
+
+ } v;
+ int lineno;
+ int col_offset;
+};
+
+struct _arguments {
+ asdl_seq *args;
+ arg_ty vararg;
+ asdl_seq *kwonlyargs;
+ asdl_seq *kw_defaults;
+ arg_ty kwarg;
+ asdl_seq *defaults;
+};
+
+struct _arg {
+ identifier arg;
+ expr_ty annotation;
+ int lineno;
+ int col_offset;
+};
+
+struct _keyword {
+ identifier arg;
+ expr_ty value;
+};
+
+struct _alias {
+ identifier name;
+ identifier asname;
+};
+
+struct _withitem {
+ expr_ty context_expr;
+ expr_ty optional_vars;
+};
+
+
+#define Module(a0, a1) _Py_Module(a0, a1)
+mod_ty _Py_Module(asdl_seq * body, PyArena *arena);
+#define Interactive(a0, a1) _Py_Interactive(a0, a1)
+mod_ty _Py_Interactive(asdl_seq * body, PyArena *arena);
+#define Expression(a0, a1) _Py_Expression(a0, a1)
+mod_ty _Py_Expression(expr_ty body, PyArena *arena);
+#define Suite(a0, a1) _Py_Suite(a0, a1)
+mod_ty _Py_Suite(asdl_seq * body, PyArena *arena);
+#define FunctionDef(a0, a1, a2, a3, a4, a5, a6, a7) _Py_FunctionDef(a0, a1, a2, a3, a4, a5, a6, a7)
+stmt_ty _Py_FunctionDef(identifier name, arguments_ty args, asdl_seq * body,
+ asdl_seq * decorator_list, expr_ty returns, int lineno,
+ int col_offset, PyArena *arena);
+#define AsyncFunctionDef(a0, a1, a2, a3, a4, a5, a6, a7) _Py_AsyncFunctionDef(a0, a1, a2, a3, a4, a5, a6, a7)
+stmt_ty _Py_AsyncFunctionDef(identifier name, arguments_ty args, asdl_seq *
+ body, asdl_seq * decorator_list, expr_ty returns,
+ int lineno, int col_offset, PyArena *arena);
+#define ClassDef(a0, a1, a2, a3, a4, a5, a6, a7) _Py_ClassDef(a0, a1, a2, a3, a4, a5, a6, a7)
+stmt_ty _Py_ClassDef(identifier name, asdl_seq * bases, asdl_seq * keywords,
+ asdl_seq * body, asdl_seq * decorator_list, int lineno,
+ int col_offset, PyArena *arena);
+#define Return(a0, a1, a2, a3) _Py_Return(a0, a1, a2, a3)
+stmt_ty _Py_Return(expr_ty value, int lineno, int col_offset, PyArena *arena);
+#define Delete(a0, a1, a2, a3) _Py_Delete(a0, a1, a2, a3)
+stmt_ty _Py_Delete(asdl_seq * targets, int lineno, int col_offset, PyArena
+ *arena);
+#define Assign(a0, a1, a2, a3, a4) _Py_Assign(a0, a1, a2, a3, a4)
+stmt_ty _Py_Assign(asdl_seq * targets, expr_ty value, int lineno, int
+ col_offset, PyArena *arena);
+#define AugAssign(a0, a1, a2, a3, a4, a5) _Py_AugAssign(a0, a1, a2, a3, a4, a5)
+stmt_ty _Py_AugAssign(expr_ty target, operator_ty op, expr_ty value, int
+ lineno, int col_offset, PyArena *arena);
+#define AnnAssign(a0, a1, a2, a3, a4, a5, a6) _Py_AnnAssign(a0, a1, a2, a3, a4, a5, a6)
+stmt_ty _Py_AnnAssign(expr_ty target, expr_ty annotation, expr_ty value, int
+ simple, int lineno, int col_offset, PyArena *arena);
+#define For(a0, a1, a2, a3, a4, a5, a6) _Py_For(a0, a1, a2, a3, a4, a5, a6)
+stmt_ty _Py_For(expr_ty target, expr_ty iter, asdl_seq * body, asdl_seq *
+ orelse, int lineno, int col_offset, PyArena *arena);
+#define AsyncFor(a0, a1, a2, a3, a4, a5, a6) _Py_AsyncFor(a0, a1, a2, a3, a4, a5, a6)
+stmt_ty _Py_AsyncFor(expr_ty target, expr_ty iter, asdl_seq * body, asdl_seq *
+ orelse, int lineno, int col_offset, PyArena *arena);
+#define While(a0, a1, a2, a3, a4, a5) _Py_While(a0, a1, a2, a3, a4, a5)
+stmt_ty _Py_While(expr_ty test, asdl_seq * body, asdl_seq * orelse, int lineno,
+ int col_offset, PyArena *arena);
+#define If(a0, a1, a2, a3, a4, a5) _Py_If(a0, a1, a2, a3, a4, a5)
+stmt_ty _Py_If(expr_ty test, asdl_seq * body, asdl_seq * orelse, int lineno,
+ int col_offset, PyArena *arena);
+#define With(a0, a1, a2, a3, a4) _Py_With(a0, a1, a2, a3, a4)
+stmt_ty _Py_With(asdl_seq * items, asdl_seq * body, int lineno, int col_offset,
+ PyArena *arena);
+#define AsyncWith(a0, a1, a2, a3, a4) _Py_AsyncWith(a0, a1, a2, a3, a4)
+stmt_ty _Py_AsyncWith(asdl_seq * items, asdl_seq * body, int lineno, int
+ col_offset, PyArena *arena);
+#define Raise(a0, a1, a2, a3, a4) _Py_Raise(a0, a1, a2, a3, a4)
+stmt_ty _Py_Raise(expr_ty exc, expr_ty cause, int lineno, int col_offset,
+ PyArena *arena);
+#define Try(a0, a1, a2, a3, a4, a5, a6) _Py_Try(a0, a1, a2, a3, a4, a5, a6)
+stmt_ty _Py_Try(asdl_seq * body, asdl_seq * handlers, asdl_seq * orelse,
+ asdl_seq * finalbody, int lineno, int col_offset, PyArena
+ *arena);
+#define Assert(a0, a1, a2, a3, a4) _Py_Assert(a0, a1, a2, a3, a4)
+stmt_ty _Py_Assert(expr_ty test, expr_ty msg, int lineno, int col_offset,
+ PyArena *arena);
+#define Import(a0, a1, a2, a3) _Py_Import(a0, a1, a2, a3)
+stmt_ty _Py_Import(asdl_seq * names, int lineno, int col_offset, PyArena
+ *arena);
+#define ImportFrom(a0, a1, a2, a3, a4, a5) _Py_ImportFrom(a0, a1, a2, a3, a4, a5)
+stmt_ty _Py_ImportFrom(identifier module, asdl_seq * names, int level, int
+ lineno, int col_offset, PyArena *arena);
+#define Global(a0, a1, a2, a3) _Py_Global(a0, a1, a2, a3)
+stmt_ty _Py_Global(asdl_seq * names, int lineno, int col_offset, PyArena
+ *arena);
+#define Nonlocal(a0, a1, a2, a3) _Py_Nonlocal(a0, a1, a2, a3)
+stmt_ty _Py_Nonlocal(asdl_seq * names, int lineno, int col_offset, PyArena
+ *arena);
+#define Expr(a0, a1, a2, a3) _Py_Expr(a0, a1, a2, a3)
+stmt_ty _Py_Expr(expr_ty value, int lineno, int col_offset, PyArena *arena);
+#define Pass(a0, a1, a2) _Py_Pass(a0, a1, a2)
+stmt_ty _Py_Pass(int lineno, int col_offset, PyArena *arena);
+#define Break(a0, a1, a2) _Py_Break(a0, a1, a2)
+stmt_ty _Py_Break(int lineno, int col_offset, PyArena *arena);
+#define Continue(a0, a1, a2) _Py_Continue(a0, a1, a2)
+stmt_ty _Py_Continue(int lineno, int col_offset, PyArena *arena);
+#define BoolOp(a0, a1, a2, a3, a4) _Py_BoolOp(a0, a1, a2, a3, a4)
+expr_ty _Py_BoolOp(boolop_ty op, asdl_seq * values, int lineno, int col_offset,
+ PyArena *arena);
+#define BinOp(a0, a1, a2, a3, a4, a5) _Py_BinOp(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_BinOp(expr_ty left, operator_ty op, expr_ty right, int lineno, int
+ col_offset, PyArena *arena);
+#define UnaryOp(a0, a1, a2, a3, a4) _Py_UnaryOp(a0, a1, a2, a3, a4)
+expr_ty _Py_UnaryOp(unaryop_ty op, expr_ty operand, int lineno, int col_offset,
+ PyArena *arena);
+#define Lambda(a0, a1, a2, a3, a4) _Py_Lambda(a0, a1, a2, a3, a4)
+expr_ty _Py_Lambda(arguments_ty args, expr_ty body, int lineno, int col_offset,
+ PyArena *arena);
+#define IfExp(a0, a1, a2, a3, a4, a5) _Py_IfExp(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_IfExp(expr_ty test, expr_ty body, expr_ty orelse, int lineno, int
+ col_offset, PyArena *arena);
+#define Dict(a0, a1, a2, a3, a4) _Py_Dict(a0, a1, a2, a3, a4)
+expr_ty _Py_Dict(asdl_seq * keys, asdl_seq * values, int lineno, int
+ col_offset, PyArena *arena);
+#define Set(a0, a1, a2, a3) _Py_Set(a0, a1, a2, a3)
+expr_ty _Py_Set(asdl_seq * elts, int lineno, int col_offset, PyArena *arena);
+#define ListComp(a0, a1, a2, a3, a4) _Py_ListComp(a0, a1, a2, a3, a4)
+expr_ty _Py_ListComp(expr_ty elt, asdl_seq * generators, int lineno, int
+ col_offset, PyArena *arena);
+#define SetComp(a0, a1, a2, a3, a4) _Py_SetComp(a0, a1, a2, a3, a4)
+expr_ty _Py_SetComp(expr_ty elt, asdl_seq * generators, int lineno, int
+ col_offset, PyArena *arena);
+#define DictComp(a0, a1, a2, a3, a4, a5) _Py_DictComp(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_DictComp(expr_ty key, expr_ty value, asdl_seq * generators, int
+ lineno, int col_offset, PyArena *arena);
+#define GeneratorExp(a0, a1, a2, a3, a4) _Py_GeneratorExp(a0, a1, a2, a3, a4)
+expr_ty _Py_GeneratorExp(expr_ty elt, asdl_seq * generators, int lineno, int
+ col_offset, PyArena *arena);
+#define Await(a0, a1, a2, a3) _Py_Await(a0, a1, a2, a3)
+expr_ty _Py_Await(expr_ty value, int lineno, int col_offset, PyArena *arena);
+#define Yield(a0, a1, a2, a3) _Py_Yield(a0, a1, a2, a3)
+expr_ty _Py_Yield(expr_ty value, int lineno, int col_offset, PyArena *arena);
+#define YieldFrom(a0, a1, a2, a3) _Py_YieldFrom(a0, a1, a2, a3)
+expr_ty _Py_YieldFrom(expr_ty value, int lineno, int col_offset, PyArena
+ *arena);
+#define Compare(a0, a1, a2, a3, a4, a5) _Py_Compare(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_Compare(expr_ty left, asdl_int_seq * ops, asdl_seq * comparators,
+ int lineno, int col_offset, PyArena *arena);
+#define Call(a0, a1, a2, a3, a4, a5) _Py_Call(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_Call(expr_ty func, asdl_seq * args, asdl_seq * keywords, int
+ lineno, int col_offset, PyArena *arena);
+#define Num(a0, a1, a2, a3) _Py_Num(a0, a1, a2, a3)
+expr_ty _Py_Num(object n, int lineno, int col_offset, PyArena *arena);
+#define Str(a0, a1, a2, a3) _Py_Str(a0, a1, a2, a3)
+expr_ty _Py_Str(string s, int lineno, int col_offset, PyArena *arena);
+#define FormattedValue(a0, a1, a2, a3, a4, a5) _Py_FormattedValue(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_FormattedValue(expr_ty value, int conversion, expr_ty format_spec,
+ int lineno, int col_offset, PyArena *arena);
+#define JoinedStr(a0, a1, a2, a3) _Py_JoinedStr(a0, a1, a2, a3)
+expr_ty _Py_JoinedStr(asdl_seq * values, int lineno, int col_offset, PyArena
+ *arena);
+#define Bytes(a0, a1, a2, a3) _Py_Bytes(a0, a1, a2, a3)
+expr_ty _Py_Bytes(bytes s, int lineno, int col_offset, PyArena *arena);
+#define NameConstant(a0, a1, a2, a3) _Py_NameConstant(a0, a1, a2, a3)
+expr_ty _Py_NameConstant(singleton value, int lineno, int col_offset, PyArena
+ *arena);
+#define Ellipsis(a0, a1, a2) _Py_Ellipsis(a0, a1, a2)
+expr_ty _Py_Ellipsis(int lineno, int col_offset, PyArena *arena);
+#define Constant(a0, a1, a2, a3) _Py_Constant(a0, a1, a2, a3)
+expr_ty _Py_Constant(constant value, int lineno, int col_offset, PyArena
+ *arena);
+#define Attribute(a0, a1, a2, a3, a4, a5) _Py_Attribute(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_Attribute(expr_ty value, identifier attr, expr_context_ty ctx, int
+ lineno, int col_offset, PyArena *arena);
+#define Subscript(a0, a1, a2, a3, a4, a5) _Py_Subscript(a0, a1, a2, a3, a4, a5)
+expr_ty _Py_Subscript(expr_ty value, slice_ty slice, expr_context_ty ctx, int
+ lineno, int col_offset, PyArena *arena);
+#define Starred(a0, a1, a2, a3, a4) _Py_Starred(a0, a1, a2, a3, a4)
+expr_ty _Py_Starred(expr_ty value, expr_context_ty ctx, int lineno, int
+ col_offset, PyArena *arena);
+#define Name(a0, a1, a2, a3, a4) _Py_Name(a0, a1, a2, a3, a4)
+expr_ty _Py_Name(identifier id, expr_context_ty ctx, int lineno, int
+ col_offset, PyArena *arena);
+#define List(a0, a1, a2, a3, a4) _Py_List(a0, a1, a2, a3, a4)
+expr_ty _Py_List(asdl_seq * elts, expr_context_ty ctx, int lineno, int
+ col_offset, PyArena *arena);
+#define Tuple(a0, a1, a2, a3, a4) _Py_Tuple(a0, a1, a2, a3, a4)
+expr_ty _Py_Tuple(asdl_seq * elts, expr_context_ty ctx, int lineno, int
+ col_offset, PyArena *arena);
+#define Slice(a0, a1, a2, a3) _Py_Slice(a0, a1, a2, a3)
+slice_ty _Py_Slice(expr_ty lower, expr_ty upper, expr_ty step, PyArena *arena);
+#define ExtSlice(a0, a1) _Py_ExtSlice(a0, a1)
+slice_ty _Py_ExtSlice(asdl_seq * dims, PyArena *arena);
+#define Index(a0, a1) _Py_Index(a0, a1)
+slice_ty _Py_Index(expr_ty value, PyArena *arena);
+#define comprehension(a0, a1, a2, a3, a4) _Py_comprehension(a0, a1, a2, a3, a4)
+comprehension_ty _Py_comprehension(expr_ty target, expr_ty iter, asdl_seq *
+ ifs, int is_async, PyArena *arena);
+#define ExceptHandler(a0, a1, a2, a3, a4, a5) _Py_ExceptHandler(a0, a1, a2, a3, a4, a5)
+excepthandler_ty _Py_ExceptHandler(expr_ty type, identifier name, asdl_seq *
+ body, int lineno, int col_offset, PyArena
+ *arena);
+#define arguments(a0, a1, a2, a3, a4, a5, a6) _Py_arguments(a0, a1, a2, a3, a4, a5, a6)
+arguments_ty _Py_arguments(asdl_seq * args, arg_ty vararg, asdl_seq *
+ kwonlyargs, asdl_seq * kw_defaults, arg_ty kwarg,
+ asdl_seq * defaults, PyArena *arena);
+#define arg(a0, a1, a2, a3, a4) _Py_arg(a0, a1, a2, a3, a4)
+arg_ty _Py_arg(identifier arg, expr_ty annotation, int lineno, int col_offset,
+ PyArena *arena);
+#define keyword(a0, a1, a2) _Py_keyword(a0, a1, a2)
+keyword_ty _Py_keyword(identifier arg, expr_ty value, PyArena *arena);
+#define alias(a0, a1, a2) _Py_alias(a0, a1, a2)
+alias_ty _Py_alias(identifier name, identifier asname, PyArena *arena);
+#define withitem(a0, a1, a2) _Py_withitem(a0, a1, a2)
+withitem_ty _Py_withitem(expr_ty context_expr, expr_ty optional_vars, PyArena
+ *arena);
+
+PyObject* PyAST_mod2obj(mod_ty t);
+mod_ty PyAST_obj2mod(PyObject* ast, PyArena* arena, int mode);
+int PyAST_Check(PyObject* obj);
diff --git a/Include/Python.h b/Include/Python.h
new file mode 100644
index 0000000..1feb153
--- /dev/null
+++ b/Include/Python.h
@@ -0,0 +1,140 @@
+#ifndef Py_PYTHON_H
+#define Py_PYTHON_H
+/* Since this is a "meta-include" file, no #ifdef __cplusplus / extern "C" { */
+
+/* Include nearly all Python header files */
+
+#include "patchlevel.h"
+#include "pyconfig.h"
+#include "pymacconfig.h"
+
+#include
+
+#ifndef UCHAR_MAX
+#error "Something's broken. UCHAR_MAX should be defined in limits.h."
+#endif
+
+#if UCHAR_MAX != 255
+#error "Python's source code assumes C's unsigned char is an 8-bit type."
+#endif
+
+#if defined(__sgi) && !defined(_SGI_MP_SOURCE)
+#define _SGI_MP_SOURCE
+#endif
+
+#include
+#ifndef NULL
+# error "Python.h requires that stdio.h define NULL."
+#endif
+
+#include
+#ifdef HAVE_ERRNO_H
+#include
+#endif
+#include
+#ifdef HAVE_UNISTD_H
+#include
+#endif
+#ifdef HAVE_CRYPT_H
+#include
+#endif
+
+/* For size_t? */
+#ifdef HAVE_STDDEF_H
+#include
+#endif
+
+/* CAUTION: Build setups should ensure that NDEBUG is defined on the
+ * compiler command line when building Python in release mode; else
+ * assert() calls won't be removed.
+ */
+#include
+
+#include "pyport.h"
+#include "pymacro.h"
+
+#include "pyatomic.h"
+
+/* Debug-mode build with pymalloc implies PYMALLOC_DEBUG.
+ * PYMALLOC_DEBUG is in error if pymalloc is not in use.
+ */
+#if defined(Py_DEBUG) && defined(WITH_PYMALLOC) && !defined(PYMALLOC_DEBUG)
+#define PYMALLOC_DEBUG
+#endif
+#if defined(PYMALLOC_DEBUG) && !defined(WITH_PYMALLOC)
+#error "PYMALLOC_DEBUG requires WITH_PYMALLOC"
+#endif
+#include "pymath.h"
+#include "pytime.h"
+#include "pymem.h"
+
+#include "object.h"
+#include "objimpl.h"
+#include "typeslots.h"
+#include "pyhash.h"
+
+#include "pydebug.h"
+
+#include "bytearrayobject.h"
+#include "bytesobject.h"
+#include "unicodeobject.h"
+#include "longobject.h"
+#include "longintrepr.h"
+#include "boolobject.h"
+#include "floatobject.h"
+#include "complexobject.h"
+#include "rangeobject.h"
+#include "memoryobject.h"
+#include "tupleobject.h"
+#include "listobject.h"
+#include "dictobject.h"
+#include "odictobject.h"
+#include "enumobject.h"
+#include "setobject.h"
+#include "methodobject.h"
+#include "moduleobject.h"
+#include "funcobject.h"
+#include "classobject.h"
+#include "fileobject.h"
+#include "pycapsule.h"
+#include "traceback.h"
+#include "sliceobject.h"
+#include "cellobject.h"
+#include "iterobject.h"
+#include "genobject.h"
+#include "descrobject.h"
+#include "warnings.h"
+#include "weakrefobject.h"
+#include "structseq.h"
+#include "namespaceobject.h"
+
+#include "codecs.h"
+#include "pyerrors.h"
+
+#include "pystate.h"
+#include "context.h"
+
+#include "pyarena.h"
+#include "modsupport.h"
+#include "compile.h"
+#include "pythonrun.h"
+#include "pylifecycle.h"
+#include "ceval.h"
+#include "sysmodule.h"
+#include "osmodule.h"
+#include "intrcheck.h"
+#include "import.h"
+
+#include "abstract.h"
+#include "bltinmodule.h"
+
+#include "eval.h"
+
+#include "pyctype.h"
+#include "pystrtod.h"
+#include "pystrcmp.h"
+#include "dtoa.h"
+#include "fileutils.h"
+#include "pyfpe.h"
+
+#endif /* !Py_PYTHON_H */
diff --git a/Include/abstract.h b/Include/abstract.h
new file mode 100644
index 0000000..4088f75
--- /dev/null
+++ b/Include/abstract.h
@@ -0,0 +1,1109 @@
+/* Abstract Object Interface (many thanks to Jim Fulton) */
+
+#ifndef Py_ABSTRACTOBJECT_H
+#define Py_ABSTRACTOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* === Object Protocol ================================================== */
+
+/* Implemented elsewhere:
+
+ int PyObject_Print(PyObject *o, FILE *fp, int flags);
+
+ Print an object 'o' on file 'fp'. Returns -1 on error. The flags argument
+ is used to enable certain printing options. The only option currently
+ supported is Py_Print_RAW.
+
+ (What should be said about Py_Print_RAW?). */
+
+
+/* Implemented elsewhere:
+
+ int PyObject_HasAttrString(PyObject *o, const char *attr_name);
+
+ Returns 1 if object 'o' has the attribute attr_name, and 0 otherwise.
+
+ This is equivalent to the Python expression: hasattr(o,attr_name).
+
+ This function always succeeds. */
+
+
+/* Implemented elsewhere:
+
+ PyObject* PyObject_GetAttrString(PyObject *o, const char *attr_name);
+
+ Retrieve an attributed named attr_name form object o.
+ Returns the attribute value on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: o.attr_name. */
+
+
+/* Implemented elsewhere:
+
+ int PyObject_HasAttr(PyObject *o, PyObject *attr_name);
+
+ Returns 1 if o has the attribute attr_name, and 0 otherwise.
+
+ This is equivalent to the Python expression: hasattr(o,attr_name).
+
+ This function always succeeds. */
+
+/* Implemented elsewhere:
+
+ PyObject* PyObject_GetAttr(PyObject *o, PyObject *attr_name);
+
+ Retrieve an attributed named 'attr_name' form object 'o'.
+ Returns the attribute value on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: o.attr_name. */
+
+
+/* Implemented elsewhere:
+
+ int PyObject_SetAttrString(PyObject *o, const char *attr_name, PyObject *v);
+
+ Set the value of the attribute named attr_name, for object 'o',
+ to the value 'v'. Raise an exception and return -1 on failure; return 0 on
+ success.
+
+ This is the equivalent of the Python statement o.attr_name=v. */
+
+
+/* Implemented elsewhere:
+
+ int PyObject_SetAttr(PyObject *o, PyObject *attr_name, PyObject *v);
+
+ Set the value of the attribute named attr_name, for object 'o', to the value
+ 'v'. an exception and return -1 on failure; return 0 on success.
+
+ This is the equivalent of the Python statement o.attr_name=v. */
+
+/* Implemented as a macro:
+
+ int PyObject_DelAttrString(PyObject *o, const char *attr_name);
+
+ Delete attribute named attr_name, for object o. Returns
+ -1 on failure.
+
+ This is the equivalent of the Python statement: del o.attr_name. */
+#define PyObject_DelAttrString(O,A) PyObject_SetAttrString((O),(A), NULL)
+
+
+/* Implemented as a macro:
+
+ int PyObject_DelAttr(PyObject *o, PyObject *attr_name);
+
+ Delete attribute named attr_name, for object o. Returns -1
+ on failure. This is the equivalent of the Python
+ statement: del o.attr_name. */
+#define PyObject_DelAttr(O,A) PyObject_SetAttr((O),(A), NULL)
+
+
+/* Implemented elsewhere:
+
+ PyObject *PyObject_Repr(PyObject *o);
+
+ Compute the string representation of object 'o'. Returns the
+ string representation on success, NULL on failure.
+
+ This is the equivalent of the Python expression: repr(o).
+
+ Called by the repr() built-in function. */
+
+
+/* Implemented elsewhere:
+
+ PyObject *PyObject_Str(PyObject *o);
+
+ Compute the string representation of object, o. Returns the
+ string representation on success, NULL on failure.
+
+ This is the equivalent of the Python expression: str(o).
+
+ Called by the str() and print() built-in functions. */
+
+
+/* Declared elsewhere
+
+ PyAPI_FUNC(int) PyCallable_Check(PyObject *o);
+
+ Determine if the object, o, is callable. Return 1 if the object is callable
+ and 0 otherwise.
+
+ This function always succeeds. */
+
+
+#ifdef PY_SSIZE_T_CLEAN
+# define PyObject_CallFunction _PyObject_CallFunction_SizeT
+# define PyObject_CallMethod _PyObject_CallMethod_SizeT
+# ifndef Py_LIMITED_API
+# define _PyObject_CallMethodId _PyObject_CallMethodId_SizeT
+# endif /* !Py_LIMITED_API */
+#endif
+
+
+/* Call a callable Python object 'callable' with arguments given by the
+ tuple 'args' and keywords arguments given by the dictionary 'kwargs'.
+
+ 'args' must not be *NULL*, use an empty tuple if no arguments are
+ needed. If no named arguments are needed, 'kwargs' can be NULL.
+
+ This is the equivalent of the Python expression:
+ callable(*args, **kwargs). */
+PyAPI_FUNC(PyObject *) PyObject_Call(PyObject *callable,
+ PyObject *args, PyObject *kwargs);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) _PyStack_AsTuple(
+ PyObject *const *stack,
+ Py_ssize_t nargs);
+
+PyAPI_FUNC(PyObject*) _PyStack_AsTupleSlice(
+ PyObject *const *stack,
+ Py_ssize_t nargs,
+ Py_ssize_t start,
+ Py_ssize_t end);
+
+/* Convert keyword arguments from the FASTCALL (stack: C array, kwnames: tuple)
+ format to a Python dictionary ("kwargs" dict).
+
+ The type of kwnames keys is not checked. The final function getting
+ arguments is responsible to check if all keys are strings, for example using
+ PyArg_ParseTupleAndKeywords() or PyArg_ValidateKeywordArguments().
+
+ Duplicate keys are merged using the last value. If duplicate keys must raise
+ an exception, the caller is responsible to implement an explicit keys on
+ kwnames. */
+PyAPI_FUNC(PyObject *) _PyStack_AsDict(
+ PyObject *const *values,
+ PyObject *kwnames);
+
+/* Convert (args, nargs, kwargs: dict) into a (stack, nargs, kwnames: tuple).
+
+ Return 0 on success, raise an exception and return -1 on error.
+
+ Write the new stack into *p_stack. If *p_stack is differen than args, it
+ must be released by PyMem_Free().
+
+ The stack uses borrowed references.
+
+ The type of keyword keys is not checked, these checks should be done
+ later (ex: _PyArg_ParseStackAndKeywords). */
+PyAPI_FUNC(int) _PyStack_UnpackDict(
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwargs,
+ PyObject *const **p_stack,
+ PyObject **p_kwnames);
+
+/* Suggested size (number of positional arguments) for arrays of PyObject*
+ allocated on a C stack to avoid allocating memory on the heap memory. Such
+ array is used to pass positional arguments to call functions of the
+ _PyObject_FastCall() family.
+
+ The size is chosen to not abuse the C stack and so limit the risk of stack
+ overflow. The size is also chosen to allow using the small stack for most
+ function calls of the Python standard library. On 64-bit CPU, it allocates
+ 40 bytes on the stack. */
+#define _PY_FASTCALL_SMALL_STACK 5
+
+/* Return 1 if callable supports FASTCALL calling convention for positional
+ arguments: see _PyObject_FastCallDict() and _PyObject_FastCallKeywords() */
+PyAPI_FUNC(int) _PyObject_HasFastCall(PyObject *callable);
+
+/* Call the callable object 'callable' with the "fast call" calling convention:
+ args is a C array for positional arguments (nargs is the number of
+ positional arguments), kwargs is a dictionary for keyword arguments.
+
+ If nargs is equal to zero, args can be NULL. kwargs can be NULL.
+ nargs must be greater or equal to zero.
+
+ Return the result on success. Raise an exception on return NULL on
+ error. */
+PyAPI_FUNC(PyObject *) _PyObject_FastCallDict(
+ PyObject *callable,
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwargs);
+
+/* Call the callable object 'callable' with the "fast call" calling convention:
+ args is a C array for positional arguments followed by values of
+ keyword arguments. Keys of keyword arguments are stored as a tuple
+ of strings in kwnames. nargs is the number of positional parameters at
+ the beginning of stack. The size of kwnames gives the number of keyword
+ values in the stack after positional arguments.
+
+ kwnames must only contains str strings, no subclass, and all keys must
+ be unique.
+
+ If nargs is equal to zero and there is no keyword argument (kwnames is
+ NULL or its size is zero), args can be NULL.
+
+ Return the result on success. Raise an exception and return NULL on
+ error. */
+PyAPI_FUNC(PyObject *) _PyObject_FastCallKeywords(
+ PyObject *callable,
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwnames);
+
+#define _PyObject_FastCall(func, args, nargs) \
+ _PyObject_FastCallDict((func), (args), (nargs), NULL)
+
+#define _PyObject_CallNoArg(func) \
+ _PyObject_FastCallDict((func), NULL, 0, NULL)
+
+PyAPI_FUNC(PyObject *) _PyObject_Call_Prepend(
+ PyObject *callable,
+ PyObject *obj,
+ PyObject *args,
+ PyObject *kwargs);
+
+PyAPI_FUNC(PyObject *) _PyObject_FastCall_Prepend(
+ PyObject *callable,
+ PyObject *obj,
+ PyObject *const *args,
+ Py_ssize_t nargs);
+
+PyAPI_FUNC(PyObject *) _Py_CheckFunctionResult(PyObject *callable,
+ PyObject *result,
+ const char *where);
+#endif /* Py_LIMITED_API */
+
+
+/* Call a callable Python object 'callable', with arguments given by the
+ tuple 'args'. If no arguments are needed, then 'args' can be *NULL*.
+
+ Returns the result of the call on success, or *NULL* on failure.
+
+ This is the equivalent of the Python expression:
+ callable(*args). */
+PyAPI_FUNC(PyObject *) PyObject_CallObject(PyObject *callable,
+ PyObject *args);
+
+/* Call a callable Python object, callable, with a variable number of C
+ arguments. The C arguments are described using a mkvalue-style format
+ string.
+
+ The format may be NULL, indicating that no arguments are provided.
+
+ Returns the result of the call on success, or NULL on failure.
+
+ This is the equivalent of the Python expression:
+ callable(arg1, arg2, ...). */
+PyAPI_FUNC(PyObject *) PyObject_CallFunction(PyObject *callable,
+ const char *format, ...);
+
+/* Call the method named 'name' of object 'obj' with a variable number of
+ C arguments. The C arguments are described by a mkvalue format string.
+
+ The format can be NULL, indicating that no arguments are provided.
+
+ Returns the result of the call on success, or NULL on failure.
+
+ This is the equivalent of the Python expression:
+ obj.name(arg1, arg2, ...). */
+PyAPI_FUNC(PyObject *) PyObject_CallMethod(PyObject *obj,
+ const char *name,
+ const char *format, ...);
+
+#ifndef Py_LIMITED_API
+/* Like PyObject_CallMethod(), but expect a _Py_Identifier*
+ as the method name. */
+PyAPI_FUNC(PyObject *) _PyObject_CallMethodId(PyObject *obj,
+ _Py_Identifier *name,
+ const char *format, ...);
+#endif /* !Py_LIMITED_API */
+
+PyAPI_FUNC(PyObject *) _PyObject_CallFunction_SizeT(PyObject *callable,
+ const char *format,
+ ...);
+
+PyAPI_FUNC(PyObject *) _PyObject_CallMethod_SizeT(PyObject *obj,
+ const char *name,
+ const char *format,
+ ...);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyObject_CallMethodId_SizeT(PyObject *obj,
+ _Py_Identifier *name,
+ const char *format,
+ ...);
+#endif /* !Py_LIMITED_API */
+
+/* Call a callable Python object 'callable' with a variable number of C
+ arguments. The C arguments are provided as PyObject* values, terminated
+ by a NULL.
+
+ Returns the result of the call on success, or NULL on failure.
+
+ This is the equivalent of the Python expression:
+ callable(arg1, arg2, ...). */
+PyAPI_FUNC(PyObject *) PyObject_CallFunctionObjArgs(PyObject *callable,
+ ...);
+
+/* Call the method named 'name' of object 'obj' with a variable number of
+ C arguments. The C arguments are provided as PyObject* values, terminated
+ by NULL.
+
+ Returns the result of the call on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: obj.name(*args). */
+
+PyAPI_FUNC(PyObject *) PyObject_CallMethodObjArgs(
+ PyObject *obj,
+ PyObject *name,
+ ...);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyObject_CallMethodIdObjArgs(
+ PyObject *obj,
+ struct _Py_Identifier *name,
+ ...);
+#endif /* !Py_LIMITED_API */
+
+
+/* Implemented elsewhere:
+
+ Py_hash_t PyObject_Hash(PyObject *o);
+
+ Compute and return the hash, hash_value, of an object, o. On
+ failure, return -1.
+
+ This is the equivalent of the Python expression: hash(o). */
+
+
+/* Implemented elsewhere:
+
+ int PyObject_IsTrue(PyObject *o);
+
+ Returns 1 if the object, o, is considered to be true, 0 if o is
+ considered to be false and -1 on failure.
+
+ This is equivalent to the Python expression: not not o. */
+
+
+/* Implemented elsewhere:
+
+ int PyObject_Not(PyObject *o);
+
+ Returns 0 if the object, o, is considered to be true, 1 if o is
+ considered to be false and -1 on failure.
+
+ This is equivalent to the Python expression: not o. */
+
+
+/* Get the type of an object.
+
+ On success, returns a type object corresponding to the object type of object
+ 'o'. On failure, returns NULL.
+
+ This is equivalent to the Python expression: type(o) */
+PyAPI_FUNC(PyObject *) PyObject_Type(PyObject *o);
+
+
+/* Return the size of object 'o'. If the object 'o' provides both sequence and
+ mapping protocols, the sequence size is returned.
+
+ On error, -1 is returned.
+
+ This is the equivalent to the Python expression: len(o) */
+PyAPI_FUNC(Py_ssize_t) PyObject_Size(PyObject *o);
+
+
+/* For DLL compatibility */
+#undef PyObject_Length
+PyAPI_FUNC(Py_ssize_t) PyObject_Length(PyObject *o);
+#define PyObject_Length PyObject_Size
+
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyObject_HasLen(PyObject *o);
+
+/* Guess the size of object 'o' using len(o) or o.__length_hint__().
+ If neither of those return a non-negative value, then return the default
+ value. If one of the calls fails, this function returns -1. */
+PyAPI_FUNC(Py_ssize_t) PyObject_LengthHint(PyObject *o, Py_ssize_t);
+#endif
+
+/* Return element of 'o' corresponding to the object 'key'. Return NULL
+ on failure.
+
+ This is the equivalent of the Python expression: o[key] */
+PyAPI_FUNC(PyObject *) PyObject_GetItem(PyObject *o, PyObject *key);
+
+
+/* Map the object 'key' to the value 'v' into 'o'.
+
+ Raise an exception and return -1 on failure; return 0 on success.
+
+ This is the equivalent of the Python statement: o[key]=v. */
+PyAPI_FUNC(int) PyObject_SetItem(PyObject *o, PyObject *key, PyObject *v);
+
+/* Remove the mapping for the string 'key' from the object 'o'.
+ Returns -1 on failure.
+
+ This is equivalent to the Python statement: del o[key]. */
+PyAPI_FUNC(int) PyObject_DelItemString(PyObject *o, const char *key);
+
+/* Delete the mapping for the object 'key' from the object 'o'.
+ Returns -1 on failure.
+
+ This is the equivalent of the Python statement: del o[key]. */
+PyAPI_FUNC(int) PyObject_DelItem(PyObject *o, PyObject *key);
+
+
+/* === Old Buffer API ============================================ */
+
+/* FIXME: usage of these should all be replaced in Python itself
+ but for backwards compatibility we will implement them.
+ Their usage without a corresponding "unlock" mechanism
+ may create issues (but they would already be there). */
+
+/* Takes an arbitrary object which must support the (character, single segment)
+ buffer interface and returns a pointer to a read-only memory location
+ useable as character based input for subsequent processing.
+
+ Return 0 on success. buffer and buffer_len are only set in case no error
+ occurs. Otherwise, -1 is returned and an exception set. */
+PyAPI_FUNC(int) PyObject_AsCharBuffer(PyObject *obj,
+ const char **buffer,
+ Py_ssize_t *buffer_len)
+ Py_DEPRECATED(3.0);
+
+/* Checks whether an arbitrary object supports the (character, single segment)
+ buffer interface.
+
+ Returns 1 on success, 0 on failure. */
+PyAPI_FUNC(int) PyObject_CheckReadBuffer(PyObject *obj)
+ Py_DEPRECATED(3.0);
+
+/* Same as PyObject_AsCharBuffer() except that this API expects (readable,
+ single segment) buffer interface and returns a pointer to a read-only memory
+ location which can contain arbitrary data.
+
+ 0 is returned on success. buffer and buffer_len are only set in case no
+ error occurs. Otherwise, -1 is returned and an exception set. */
+PyAPI_FUNC(int) PyObject_AsReadBuffer(PyObject *obj,
+ const void **buffer,
+ Py_ssize_t *buffer_len)
+ Py_DEPRECATED(3.0);
+
+/* Takes an arbitrary object which must support the (writable, single segment)
+ buffer interface and returns a pointer to a writable memory location in
+ buffer of size 'buffer_len'.
+
+ Return 0 on success. buffer and buffer_len are only set in case no error
+ occurs. Otherwise, -1 is returned and an exception set. */
+PyAPI_FUNC(int) PyObject_AsWriteBuffer(PyObject *obj,
+ void **buffer,
+ Py_ssize_t *buffer_len)
+ Py_DEPRECATED(3.0);
+
+
+/* === New Buffer API ============================================ */
+
+#ifndef Py_LIMITED_API
+
+/* Return 1 if the getbuffer function is available, otherwise return 0. */
+#define PyObject_CheckBuffer(obj) \
+ (((obj)->ob_type->tp_as_buffer != NULL) && \
+ ((obj)->ob_type->tp_as_buffer->bf_getbuffer != NULL))
+
+/* This is a C-API version of the getbuffer function call. It checks
+ to make sure object has the required function pointer and issues the
+ call.
+
+ Returns -1 and raises an error on failure and returns 0 on success. */
+PyAPI_FUNC(int) PyObject_GetBuffer(PyObject *obj, Py_buffer *view,
+ int flags);
+
+/* Get the memory area pointed to by the indices for the buffer given.
+ Note that view->ndim is the assumed size of indices. */
+PyAPI_FUNC(void *) PyBuffer_GetPointer(Py_buffer *view, Py_ssize_t *indices);
+
+/* Return the implied itemsize of the data-format area from a
+ struct-style description. */
+PyAPI_FUNC(int) PyBuffer_SizeFromFormat(const char *);
+
+/* Implementation in memoryobject.c */
+PyAPI_FUNC(int) PyBuffer_ToContiguous(void *buf, Py_buffer *view,
+ Py_ssize_t len, char order);
+
+PyAPI_FUNC(int) PyBuffer_FromContiguous(Py_buffer *view, void *buf,
+ Py_ssize_t len, char order);
+
+/* Copy len bytes of data from the contiguous chunk of memory
+ pointed to by buf into the buffer exported by obj. Return
+ 0 on success and return -1 and raise a PyBuffer_Error on
+ error (i.e. the object does not have a buffer interface or
+ it is not working).
+
+ If fort is 'F', then if the object is multi-dimensional,
+ then the data will be copied into the array in
+ Fortran-style (first dimension varies the fastest). If
+ fort is 'C', then the data will be copied into the array
+ in C-style (last dimension varies the fastest). If fort
+ is 'A', then it does not matter and the copy will be made
+ in whatever way is more efficient. */
+PyAPI_FUNC(int) PyObject_CopyData(PyObject *dest, PyObject *src);
+
+/* Copy the data from the src buffer to the buffer of destination. */
+PyAPI_FUNC(int) PyBuffer_IsContiguous(const Py_buffer *view, char fort);
+
+/*Fill the strides array with byte-strides of a contiguous
+ (Fortran-style if fort is 'F' or C-style otherwise)
+ array of the given shape with the given number of bytes
+ per element. */
+PyAPI_FUNC(void) PyBuffer_FillContiguousStrides(int ndims,
+ Py_ssize_t *shape,
+ Py_ssize_t *strides,
+ int itemsize,
+ char fort);
+
+/* Fills in a buffer-info structure correctly for an exporter
+ that can only share a contiguous chunk of memory of
+ "unsigned bytes" of the given length.
+
+ Returns 0 on success and -1 (with raising an error) on error. */
+PyAPI_FUNC(int) PyBuffer_FillInfo(Py_buffer *view, PyObject *o, void *buf,
+ Py_ssize_t len, int readonly,
+ int flags);
+
+/* Releases a Py_buffer obtained from getbuffer ParseTuple's "s*". */
+PyAPI_FUNC(void) PyBuffer_Release(Py_buffer *view);
+
+#endif /* Py_LIMITED_API */
+
+/* Takes an arbitrary object and returns the result of calling
+ obj.__format__(format_spec). */
+PyAPI_FUNC(PyObject *) PyObject_Format(PyObject *obj,
+ PyObject *format_spec);
+
+
+/* ==== Iterators ================================================ */
+
+/* Takes an object and returns an iterator for it.
+ This is typically a new iterator but if the argument is an iterator, this
+ returns itself. */
+PyAPI_FUNC(PyObject *) PyObject_GetIter(PyObject *);
+
+#define PyIter_Check(obj) \
+ ((obj)->ob_type->tp_iternext != NULL && \
+ (obj)->ob_type->tp_iternext != &_PyObject_NextNotImplemented)
+
+/* Takes an iterator object and calls its tp_iternext slot,
+ returning the next value.
+
+ If the iterator is exhausted, this returns NULL without setting an
+ exception.
+
+ NULL with an exception means an error occurred. */
+PyAPI_FUNC(PyObject *) PyIter_Next(PyObject *);
+
+
+/* === Number Protocol ================================================== */
+
+/* Returns 1 if the object 'o' provides numeric protocols, and 0 otherwise.
+
+ This function always succeeds. */
+PyAPI_FUNC(int) PyNumber_Check(PyObject *o);
+
+/* Returns the result of adding o1 and o2, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 + o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Add(PyObject *o1, PyObject *o2);
+
+/* Returns the result of subtracting o2 from o1, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 - o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Subtract(PyObject *o1, PyObject *o2);
+
+/* Returns the result of multiplying o1 and o2, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 * o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Multiply(PyObject *o1, PyObject *o2);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* This is the equivalent of the Python expression: o1 @ o2. */
+PyAPI_FUNC(PyObject *) PyNumber_MatrixMultiply(PyObject *o1, PyObject *o2);
+#endif
+
+/* Returns the result of dividing o1 by o2 giving an integral result,
+ or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 // o2. */
+PyAPI_FUNC(PyObject *) PyNumber_FloorDivide(PyObject *o1, PyObject *o2);
+
+/* Returns the result of dividing o1 by o2 giving a float result, or NULL on
+ failure.
+
+ This is the equivalent of the Python expression: o1 / o2. */
+PyAPI_FUNC(PyObject *) PyNumber_TrueDivide(PyObject *o1, PyObject *o2);
+
+/* Returns the remainder of dividing o1 by o2, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 % o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Remainder(PyObject *o1, PyObject *o2);
+
+/* See the built-in function divmod.
+
+ Returns NULL on failure.
+
+ This is the equivalent of the Python expression: divmod(o1, o2). */
+PyAPI_FUNC(PyObject *) PyNumber_Divmod(PyObject *o1, PyObject *o2);
+
+/* See the built-in function pow. Returns NULL on failure.
+
+ This is the equivalent of the Python expression: pow(o1, o2, o3),
+ where o3 is optional. */
+PyAPI_FUNC(PyObject *) PyNumber_Power(PyObject *o1, PyObject *o2,
+ PyObject *o3);
+
+/* Returns the negation of o on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: -o. */
+PyAPI_FUNC(PyObject *) PyNumber_Negative(PyObject *o);
+
+/* Returns the positive of o on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: +o. */
+PyAPI_FUNC(PyObject *) PyNumber_Positive(PyObject *o);
+
+/* Returns the absolute value of 'o', or NULL on failure.
+
+ This is the equivalent of the Python expression: abs(o). */
+PyAPI_FUNC(PyObject *) PyNumber_Absolute(PyObject *o);
+
+/* Returns the bitwise negation of 'o' on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: ~o. */
+PyAPI_FUNC(PyObject *) PyNumber_Invert(PyObject *o);
+
+/* Returns the result of left shifting o1 by o2 on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 << o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Lshift(PyObject *o1, PyObject *o2);
+
+/* Returns the result of right shifting o1 by o2 on success, or NULL on
+ failure.
+
+ This is the equivalent of the Python expression: o1 >> o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Rshift(PyObject *o1, PyObject *o2);
+
+/* Returns the result of bitwise and of o1 and o2 on success, or NULL on
+ failure.
+
+ This is the equivalent of the Python expression: o1 & o2. */
+PyAPI_FUNC(PyObject *) PyNumber_And(PyObject *o1, PyObject *o2);
+
+/* Returns the bitwise exclusive or of o1 by o2 on success, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 ^ o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Xor(PyObject *o1, PyObject *o2);
+
+/* Returns the result of bitwise or on o1 and o2 on success, or NULL on
+ failure.
+
+ This is the equivalent of the Python expression: o1 | o2. */
+PyAPI_FUNC(PyObject *) PyNumber_Or(PyObject *o1, PyObject *o2);
+
+#define PyIndex_Check(obj) \
+ ((obj)->ob_type->tp_as_number != NULL && \
+ (obj)->ob_type->tp_as_number->nb_index != NULL)
+
+/* Returns the object 'o' converted to a Python int, or NULL with an exception
+ raised on failure. */
+PyAPI_FUNC(PyObject *) PyNumber_Index(PyObject *o);
+
+/* Returns the object 'o' converted to Py_ssize_t by going through
+ PyNumber_Index() first.
+
+ If an overflow error occurs while converting the int to Py_ssize_t, then the
+ second argument 'exc' is the error-type to return. If it is NULL, then the
+ overflow error is cleared and the value is clipped. */
+PyAPI_FUNC(Py_ssize_t) PyNumber_AsSsize_t(PyObject *o, PyObject *exc);
+
+/* Returns the object 'o' converted to an integer object on success, or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: int(o). */
+PyAPI_FUNC(PyObject *) PyNumber_Long(PyObject *o);
+
+/* Returns the object 'o' converted to a float object on success, or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: float(o). */
+PyAPI_FUNC(PyObject *) PyNumber_Float(PyObject *o);
+
+
+/* --- In-place variants of (some of) the above number protocol functions -- */
+
+/* Returns the result of adding o2 to o1, possibly in-place, or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: o1 += o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceAdd(PyObject *o1, PyObject *o2);
+
+/* Returns the result of subtracting o2 from o1, possibly in-place or
+ NULL on failure.
+
+ This is the equivalent of the Python expression: o1 -= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceSubtract(PyObject *o1, PyObject *o2);
+
+/* Returns the result of multiplying o1 by o2, possibly in-place, or NULL on
+ failure.
+
+ This is the equivalent of the Python expression: o1 *= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceMultiply(PyObject *o1, PyObject *o2);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* This is the equivalent of the Python expression: o1 @= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceMatrixMultiply(PyObject *o1, PyObject *o2);
+#endif
+
+/* Returns the result of dividing o1 by o2 giving an integral result, possibly
+ in-place, or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 /= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceFloorDivide(PyObject *o1,
+ PyObject *o2);
+
+/* Returns the result of dividing o1 by o2 giving a float result, possibly
+ in-place, or null on failure.
+
+ This is the equivalent of the Python expression: o1 /= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceTrueDivide(PyObject *o1,
+ PyObject *o2);
+
+/* Returns the remainder of dividing o1 by o2, possibly in-place, or NULL on
+ failure.
+
+ This is the equivalent of the Python expression: o1 %= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceRemainder(PyObject *o1, PyObject *o2);
+
+/* Returns the result of raising o1 to the power of o2, possibly in-place,
+ or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 **= o2,
+ or o1 = pow(o1, o2, o3) if o3 is present. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlacePower(PyObject *o1, PyObject *o2,
+ PyObject *o3);
+
+/* Returns the result of left shifting o1 by o2, possibly in-place, or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: o1 <<= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceLshift(PyObject *o1, PyObject *o2);
+
+/* Returns the result of right shifting o1 by o2, possibly in-place or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: o1 >>= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceRshift(PyObject *o1, PyObject *o2);
+
+/* Returns the result of bitwise and of o1 and o2, possibly in-place, or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: o1 &= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceAnd(PyObject *o1, PyObject *o2);
+
+/* Returns the bitwise exclusive or of o1 by o2, possibly in-place, or NULL
+ on failure.
+
+ This is the equivalent of the Python expression: o1 ^= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceXor(PyObject *o1, PyObject *o2);
+
+/* Returns the result of bitwise or of o1 and o2, possibly in-place,
+ or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 |= o2. */
+PyAPI_FUNC(PyObject *) PyNumber_InPlaceOr(PyObject *o1, PyObject *o2);
+
+/* Returns the integer n converted to a string with a base, with a base
+ marker of 0b, 0o or 0x prefixed if applicable.
+
+ If n is not an int object, it is converted with PyNumber_Index first. */
+PyAPI_FUNC(PyObject *) PyNumber_ToBase(PyObject *n, int base);
+
+
+/* === Sequence protocol ================================================ */
+
+/* Return 1 if the object provides sequence protocol, and zero
+ otherwise.
+
+ This function always succeeds. */
+PyAPI_FUNC(int) PySequence_Check(PyObject *o);
+
+/* Return the size of sequence object o, or -1 on failure. */
+PyAPI_FUNC(Py_ssize_t) PySequence_Size(PyObject *o);
+
+/* For DLL compatibility */
+#undef PySequence_Length
+PyAPI_FUNC(Py_ssize_t) PySequence_Length(PyObject *o);
+#define PySequence_Length PySequence_Size
+
+
+/* Return the concatenation of o1 and o2 on success, and NULL on failure.
+
+ This is the equivalent of the Python expression: o1 + o2. */
+PyAPI_FUNC(PyObject *) PySequence_Concat(PyObject *o1, PyObject *o2);
+
+/* Return the result of repeating sequence object 'o' 'count' times,
+ or NULL on failure.
+
+ This is the equivalent of the Python expression: o * count. */
+PyAPI_FUNC(PyObject *) PySequence_Repeat(PyObject *o, Py_ssize_t count);
+
+/* Return the ith element of o, or NULL on failure.
+
+ This is the equivalent of the Python expression: o[i]. */
+PyAPI_FUNC(PyObject *) PySequence_GetItem(PyObject *o, Py_ssize_t i);
+
+/* Return the slice of sequence object o between i1 and i2, or NULL on failure.
+
+ This is the equivalent of the Python expression: o[i1:i2]. */
+PyAPI_FUNC(PyObject *) PySequence_GetSlice(PyObject *o, Py_ssize_t i1, Py_ssize_t i2);
+
+/* Assign object 'v' to the ith element of the sequence 'o'. Raise an exception
+ and return -1 on failure; return 0 on success.
+
+ This is the equivalent of the Python statement o[i] = v. */
+PyAPI_FUNC(int) PySequence_SetItem(PyObject *o, Py_ssize_t i, PyObject *v);
+
+/* Delete the 'i'-th element of the sequence 'v'. Returns -1 on failure.
+
+ This is the equivalent of the Python statement: del o[i]. */
+PyAPI_FUNC(int) PySequence_DelItem(PyObject *o, Py_ssize_t i);
+
+/* Assign the sequence object 'v' to the slice in sequence object 'o',
+ from 'i1' to 'i2'. Returns -1 on failure.
+
+ This is the equivalent of the Python statement: o[i1:i2] = v. */
+PyAPI_FUNC(int) PySequence_SetSlice(PyObject *o, Py_ssize_t i1, Py_ssize_t i2,
+ PyObject *v);
+
+/* Delete the slice in sequence object 'o' from 'i1' to 'i2'.
+ Returns -1 on failure.
+
+ This is the equivalent of the Python statement: del o[i1:i2]. */
+PyAPI_FUNC(int) PySequence_DelSlice(PyObject *o, Py_ssize_t i1, Py_ssize_t i2);
+
+/* Returns the sequence 'o' as a tuple on success, and NULL on failure.
+
+ This is equivalent to the Python expression: tuple(o). */
+PyAPI_FUNC(PyObject *) PySequence_Tuple(PyObject *o);
+
+/* Returns the sequence 'o' as a list on success, and NULL on failure.
+ This is equivalent to the Python expression: list(o) */
+PyAPI_FUNC(PyObject *) PySequence_List(PyObject *o);
+
+/* Return the sequence 'o' as a list, unless it's already a tuple or list.
+
+ Use PySequence_Fast_GET_ITEM to access the members of this list, and
+ PySequence_Fast_GET_SIZE to get its length.
+
+ Returns NULL on failure. If the object does not support iteration, raises a
+ TypeError exception with 'm' as the message text. */
+PyAPI_FUNC(PyObject *) PySequence_Fast(PyObject *o, const char* m);
+
+/* Return the size of the sequence 'o', assuming that 'o' was returned by
+ PySequence_Fast and is not NULL. */
+#define PySequence_Fast_GET_SIZE(o) \
+ (PyList_Check(o) ? PyList_GET_SIZE(o) : PyTuple_GET_SIZE(o))
+
+/* Return the 'i'-th element of the sequence 'o', assuming that o was returned
+ by PySequence_Fast, and that i is within bounds. */
+#define PySequence_Fast_GET_ITEM(o, i)\
+ (PyList_Check(o) ? PyList_GET_ITEM(o, i) : PyTuple_GET_ITEM(o, i))
+
+/* Assume tp_as_sequence and sq_item exist and that 'i' does not
+ need to be corrected for a negative index. */
+#define PySequence_ITEM(o, i)\
+ ( Py_TYPE(o)->tp_as_sequence->sq_item(o, i) )
+
+/* Return a pointer to the underlying item array for
+ an object retured by PySequence_Fast */
+#define PySequence_Fast_ITEMS(sf) \
+ (PyList_Check(sf) ? ((PyListObject *)(sf))->ob_item \
+ : ((PyTupleObject *)(sf))->ob_item)
+
+/* Return the number of occurrences on value on 'o', that is, return
+ the number of keys for which o[key] == value.
+
+ On failure, return -1. This is equivalent to the Python expression:
+ o.count(value). */
+PyAPI_FUNC(Py_ssize_t) PySequence_Count(PyObject *o, PyObject *value);
+
+/* Return 1 if 'ob' is in the sequence 'seq'; 0 if 'ob' is not in the sequence
+ 'seq'; -1 on error.
+
+ Use __contains__ if possible, else _PySequence_IterSearch(). */
+PyAPI_FUNC(int) PySequence_Contains(PyObject *seq, PyObject *ob);
+
+#ifndef Py_LIMITED_API
+#define PY_ITERSEARCH_COUNT 1
+#define PY_ITERSEARCH_INDEX 2
+#define PY_ITERSEARCH_CONTAINS 3
+
+/* Iterate over seq.
+
+ Result depends on the operation:
+
+ PY_ITERSEARCH_COUNT: return # of times obj appears in seq; -1 if
+ error.
+ PY_ITERSEARCH_INDEX: return 0-based index of first occurrence of
+ obj in seq; set ValueError and return -1 if none found;
+ also return -1 on error.
+ PY_ITERSEARCH_CONTAINS: return 1 if obj in seq, else 0; -1 on
+ error. */
+PyAPI_FUNC(Py_ssize_t) _PySequence_IterSearch(PyObject *seq,
+ PyObject *obj, int operation);
+#endif
+
+
+/* For DLL-level backwards compatibility */
+#undef PySequence_In
+/* Determine if the sequence 'o' contains 'value'. If an item in 'o' is equal
+ to 'value', return 1, otherwise return 0. On error, return -1.
+
+ This is equivalent to the Python expression: value in o. */
+PyAPI_FUNC(int) PySequence_In(PyObject *o, PyObject *value);
+
+/* For source-level backwards compatibility */
+#define PySequence_In PySequence_Contains
+
+
+/* Return the first index for which o[i] == value.
+ On error, return -1.
+
+ This is equivalent to the Python expression: o.index(value). */
+PyAPI_FUNC(Py_ssize_t) PySequence_Index(PyObject *o, PyObject *value);
+
+
+/* --- In-place versions of some of the above Sequence functions --- */
+
+/* Append sequence 'o2' to sequence 'o1', in-place when possible. Return the
+ resulting object, which could be 'o1', or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 += o2. */
+PyAPI_FUNC(PyObject *) PySequence_InPlaceConcat(PyObject *o1, PyObject *o2);
+
+/* Repeat sequence 'o' by 'count', in-place when possible. Return the resulting
+ object, which could be 'o', or NULL on failure.
+
+ This is the equivalent of the Python expression: o1 *= count. */
+PyAPI_FUNC(PyObject *) PySequence_InPlaceRepeat(PyObject *o, Py_ssize_t count);
+
+
+/* === Mapping protocol ================================================= */
+
+/* Return 1 if the object provides mapping protocol, and 0 otherwise.
+
+ This function always succeeds. */
+PyAPI_FUNC(int) PyMapping_Check(PyObject *o);
+
+/* Returns the number of keys in mapping object 'o' on success, and -1 on
+ failure. This is equivalent to the Python expression: len(o). */
+PyAPI_FUNC(Py_ssize_t) PyMapping_Size(PyObject *o);
+
+/* For DLL compatibility */
+#undef PyMapping_Length
+PyAPI_FUNC(Py_ssize_t) PyMapping_Length(PyObject *o);
+#define PyMapping_Length PyMapping_Size
+
+
+/* Implemented as a macro:
+
+ int PyMapping_DelItemString(PyObject *o, const char *key);
+
+ Remove the mapping for the string 'key' from the mapping 'o'. Returns -1 on
+ failure.
+
+ This is equivalent to the Python statement: del o[key]. */
+#define PyMapping_DelItemString(O,K) PyObject_DelItemString((O),(K))
+
+/* Implemented as a macro:
+
+ int PyMapping_DelItem(PyObject *o, PyObject *key);
+
+ Remove the mapping for the object 'key' from the mapping object 'o'.
+ Returns -1 on failure.
+
+ This is equivalent to the Python statement: del o[key]. */
+#define PyMapping_DelItem(O,K) PyObject_DelItem((O),(K))
+
+/* On success, return 1 if the mapping object 'o' has the key 'key',
+ and 0 otherwise.
+
+ This is equivalent to the Python expression: key in o.
+
+ This function always succeeds. */
+PyAPI_FUNC(int) PyMapping_HasKeyString(PyObject *o, const char *key);
+
+/* Return 1 if the mapping object has the key 'key', and 0 otherwise.
+
+ This is equivalent to the Python expression: key in o.
+
+ This function always succeeds. */
+PyAPI_FUNC(int) PyMapping_HasKey(PyObject *o, PyObject *key);
+
+/* On success, return a list or tuple of the keys in mapping object 'o'.
+ On failure, return NULL. */
+PyAPI_FUNC(PyObject *) PyMapping_Keys(PyObject *o);
+
+/* On success, return a list or tuple of the values in mapping object 'o'.
+ On failure, return NULL. */
+PyAPI_FUNC(PyObject *) PyMapping_Values(PyObject *o);
+
+/* On success, return a list or tuple of the items in mapping object 'o',
+ where each item is a tuple containing a key-value pair. On failure, return
+ NULL. */
+PyAPI_FUNC(PyObject *) PyMapping_Items(PyObject *o);
+
+/* Return element of 'o' corresponding to the string 'key' or NULL on failure.
+
+ This is the equivalent of the Python expression: o[key]. */
+PyAPI_FUNC(PyObject *) PyMapping_GetItemString(PyObject *o,
+ const char *key);
+
+/* Map the string 'key' to the value 'v' in the mapping 'o'.
+ Returns -1 on failure.
+
+ This is the equivalent of the Python statement: o[key]=v. */
+PyAPI_FUNC(int) PyMapping_SetItemString(PyObject *o, const char *key,
+ PyObject *value);
+
+/* isinstance(object, typeorclass) */
+PyAPI_FUNC(int) PyObject_IsInstance(PyObject *object, PyObject *typeorclass);
+
+/* issubclass(object, typeorclass) */
+PyAPI_FUNC(int) PyObject_IsSubclass(PyObject *object, PyObject *typeorclass);
+
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyObject_RealIsInstance(PyObject *inst, PyObject *cls);
+
+PyAPI_FUNC(int) _PyObject_RealIsSubclass(PyObject *derived, PyObject *cls);
+
+PyAPI_FUNC(char *const *) _PySequence_BytesToCharpArray(PyObject* self);
+
+PyAPI_FUNC(void) _Py_FreeCharPArray(char *const array[]);
+
+/* For internal use by buffer API functions */
+PyAPI_FUNC(void) _Py_add_one_to_index_F(int nd, Py_ssize_t *index,
+ const Py_ssize_t *shape);
+PyAPI_FUNC(void) _Py_add_one_to_index_C(int nd, Py_ssize_t *index,
+ const Py_ssize_t *shape);
+
+/* Convert Python int to Py_ssize_t. Do nothing if the argument is None. */
+PyAPI_FUNC(int) _Py_convert_optional_to_ssize_t(PyObject *, void *);
+#endif /* !Py_LIMITED_API */
+
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* Py_ABSTRACTOBJECT_H */
diff --git a/Include/accu.h b/Include/accu.h
new file mode 100644
index 0000000..3636ea6
--- /dev/null
+++ b/Include/accu.h
@@ -0,0 +1,37 @@
+#ifndef Py_LIMITED_API
+#ifndef Py_ACCU_H
+#define Py_ACCU_H
+
+/*** This is a private API for use by the interpreter and the stdlib.
+ *** Its definition may be changed or removed at any moment.
+ ***/
+
+/*
+ * A two-level accumulator of unicode objects that avoids both the overhead
+ * of keeping a huge number of small separate objects, and the quadratic
+ * behaviour of using a naive repeated concatenation scheme.
+ */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#undef small /* defined by some Windows headers */
+
+typedef struct {
+ PyObject *large; /* A list of previously accumulated large strings */
+ PyObject *small; /* Pending small strings */
+} _PyAccu;
+
+PyAPI_FUNC(int) _PyAccu_Init(_PyAccu *acc);
+PyAPI_FUNC(int) _PyAccu_Accumulate(_PyAccu *acc, PyObject *unicode);
+PyAPI_FUNC(PyObject *) _PyAccu_FinishAsList(_PyAccu *acc);
+PyAPI_FUNC(PyObject *) _PyAccu_Finish(_PyAccu *acc);
+PyAPI_FUNC(void) _PyAccu_Destroy(_PyAccu *acc);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* Py_ACCU_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/asdl.h b/Include/asdl.h
new file mode 100644
index 0000000..35e9fa1
--- /dev/null
+++ b/Include/asdl.h
@@ -0,0 +1,46 @@
+#ifndef Py_ASDL_H
+#define Py_ASDL_H
+
+typedef PyObject * identifier;
+typedef PyObject * string;
+typedef PyObject * bytes;
+typedef PyObject * object;
+typedef PyObject * singleton;
+typedef PyObject * constant;
+
+/* It would be nice if the code generated by asdl_c.py was completely
+ independent of Python, but it is a goal the requires too much work
+ at this stage. So, for example, I'll represent identifiers as
+ interned Python strings.
+*/
+
+/* XXX A sequence should be typed so that its use can be typechecked. */
+
+typedef struct {
+ Py_ssize_t size;
+ void *elements[1];
+} asdl_seq;
+
+typedef struct {
+ Py_ssize_t size;
+ int elements[1];
+} asdl_int_seq;
+
+asdl_seq *_Py_asdl_seq_new(Py_ssize_t size, PyArena *arena);
+asdl_int_seq *_Py_asdl_int_seq_new(Py_ssize_t size, PyArena *arena);
+
+#define asdl_seq_GET(S, I) (S)->elements[(I)]
+#define asdl_seq_LEN(S) ((S) == NULL ? 0 : (S)->size)
+#ifdef Py_DEBUG
+#define asdl_seq_SET(S, I, V) \
+ do { \
+ Py_ssize_t _asdl_i = (I); \
+ assert((S) != NULL); \
+ assert(_asdl_i < (S)->size); \
+ (S)->elements[_asdl_i] = (V); \
+ } while (0)
+#else
+#define asdl_seq_SET(S, I, V) (S)->elements[I] = (V)
+#endif
+
+#endif /* !Py_ASDL_H */
diff --git a/Include/ast.h b/Include/ast.h
new file mode 100644
index 0000000..5bc2b05
--- /dev/null
+++ b/Include/ast.h
@@ -0,0 +1,29 @@
+#ifndef Py_AST_H
+#define Py_AST_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(int) PyAST_Validate(mod_ty);
+PyAPI_FUNC(mod_ty) PyAST_FromNode(
+ const node *n,
+ PyCompilerFlags *flags,
+ const char *filename, /* decoded from the filesystem encoding */
+ PyArena *arena);
+PyAPI_FUNC(mod_ty) PyAST_FromNodeObject(
+ const node *n,
+ PyCompilerFlags *flags,
+ PyObject *filename,
+ PyArena *arena);
+
+#ifndef Py_LIMITED_API
+
+/* _PyAST_ExprAsUnicode is defined in ast_unparse.c */
+PyAPI_FUNC(PyObject *) _PyAST_ExprAsUnicode(expr_ty);
+
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_AST_H */
diff --git a/Include/bitset.h b/Include/bitset.h
new file mode 100644
index 0000000..b22fa77
--- /dev/null
+++ b/Include/bitset.h
@@ -0,0 +1,32 @@
+
+#ifndef Py_BITSET_H
+#define Py_BITSET_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Bitset interface */
+
+#define BYTE char
+
+typedef BYTE *bitset;
+
+bitset newbitset(int nbits);
+void delbitset(bitset bs);
+#define testbit(ss, ibit) (((ss)[BIT2BYTE(ibit)] & BIT2MASK(ibit)) != 0)
+int addbit(bitset bs, int ibit); /* Returns 0 if already set */
+int samebitset(bitset bs1, bitset bs2, int nbits);
+void mergebitset(bitset bs1, bitset bs2, int nbits);
+
+#define BITSPERBYTE (8*sizeof(BYTE))
+#define NBYTES(nbits) (((nbits) + BITSPERBYTE - 1) / BITSPERBYTE)
+
+#define BIT2BYTE(ibit) ((ibit) / BITSPERBYTE)
+#define BIT2SHIFT(ibit) ((ibit) % BITSPERBYTE)
+#define BIT2MASK(ibit) (1 << BIT2SHIFT(ibit))
+#define BYTE2BIT(ibyte) ((ibyte) * BITSPERBYTE)
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_BITSET_H */
diff --git a/Include/bltinmodule.h b/Include/bltinmodule.h
new file mode 100644
index 0000000..868c9e6
--- /dev/null
+++ b/Include/bltinmodule.h
@@ -0,0 +1,14 @@
+#ifndef Py_BLTINMODULE_H
+#define Py_BLTINMODULE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_DATA(PyTypeObject) PyFilter_Type;
+PyAPI_DATA(PyTypeObject) PyMap_Type;
+PyAPI_DATA(PyTypeObject) PyZip_Type;
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_BLTINMODULE_H */
diff --git a/Include/boolobject.h b/Include/boolobject.h
new file mode 100644
index 0000000..7cc2f1f
--- /dev/null
+++ b/Include/boolobject.h
@@ -0,0 +1,34 @@
+/* Boolean object interface */
+
+#ifndef Py_BOOLOBJECT_H
+#define Py_BOOLOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+PyAPI_DATA(PyTypeObject) PyBool_Type;
+
+#define PyBool_Check(x) (Py_TYPE(x) == &PyBool_Type)
+
+/* Py_False and Py_True are the only two bools in existence.
+Don't forget to apply Py_INCREF() when returning either!!! */
+
+/* Don't use these directly */
+PyAPI_DATA(struct _longobject) _Py_FalseStruct, _Py_TrueStruct;
+
+/* Use these macros */
+#define Py_False ((PyObject *) &_Py_FalseStruct)
+#define Py_True ((PyObject *) &_Py_TrueStruct)
+
+/* Macros for returning Py_True or Py_False, respectively */
+#define Py_RETURN_TRUE return Py_INCREF(Py_True), Py_True
+#define Py_RETURN_FALSE return Py_INCREF(Py_False), Py_False
+
+/* Function to return a bool from a C long */
+PyAPI_FUNC(PyObject *) PyBool_FromLong(long);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_BOOLOBJECT_H */
diff --git a/Include/bytearrayobject.h b/Include/bytearrayobject.h
new file mode 100644
index 0000000..a757b88
--- /dev/null
+++ b/Include/bytearrayobject.h
@@ -0,0 +1,62 @@
+/* ByteArray object interface */
+
+#ifndef Py_BYTEARRAYOBJECT_H
+#define Py_BYTEARRAYOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include
+
+/* Type PyByteArrayObject represents a mutable array of bytes.
+ * The Python API is that of a sequence;
+ * the bytes are mapped to ints in [0, 256).
+ * Bytes are not characters; they may be used to encode characters.
+ * The only way to go between bytes and str/unicode is via encoding
+ * and decoding.
+ * For the convenience of C programmers, the bytes type is considered
+ * to contain a char pointer, not an unsigned char pointer.
+ */
+
+/* Object layout */
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_VAR_HEAD
+ Py_ssize_t ob_alloc; /* How many bytes allocated in ob_bytes */
+ char *ob_bytes; /* Physical backing buffer */
+ char *ob_start; /* Logical start inside ob_bytes */
+ /* XXX(nnorwitz): should ob_exports be Py_ssize_t? */
+ int ob_exports; /* How many buffer exports */
+} PyByteArrayObject;
+#endif
+
+/* Type object */
+PyAPI_DATA(PyTypeObject) PyByteArray_Type;
+PyAPI_DATA(PyTypeObject) PyByteArrayIter_Type;
+
+/* Type check macros */
+#define PyByteArray_Check(self) PyObject_TypeCheck(self, &PyByteArray_Type)
+#define PyByteArray_CheckExact(self) (Py_TYPE(self) == &PyByteArray_Type)
+
+/* Direct API functions */
+PyAPI_FUNC(PyObject *) PyByteArray_FromObject(PyObject *);
+PyAPI_FUNC(PyObject *) PyByteArray_Concat(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyByteArray_FromStringAndSize(const char *, Py_ssize_t);
+PyAPI_FUNC(Py_ssize_t) PyByteArray_Size(PyObject *);
+PyAPI_FUNC(char *) PyByteArray_AsString(PyObject *);
+PyAPI_FUNC(int) PyByteArray_Resize(PyObject *, Py_ssize_t);
+
+/* Macros, trading safety for speed */
+#ifndef Py_LIMITED_API
+#define PyByteArray_AS_STRING(self) \
+ (assert(PyByteArray_Check(self)), \
+ Py_SIZE(self) ? ((PyByteArrayObject *)(self))->ob_start : _PyByteArray_empty_string)
+#define PyByteArray_GET_SIZE(self) (assert(PyByteArray_Check(self)), Py_SIZE(self))
+
+PyAPI_DATA(char) _PyByteArray_empty_string[];
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_BYTEARRAYOBJECT_H */
diff --git a/Include/bytes_methods.h b/Include/bytes_methods.h
new file mode 100644
index 0000000..8434a50
--- /dev/null
+++ b/Include/bytes_methods.h
@@ -0,0 +1,69 @@
+#ifndef Py_LIMITED_API
+#ifndef Py_BYTES_CTYPE_H
+#define Py_BYTES_CTYPE_H
+
+/*
+ * The internal implementation behind PyBytes (bytes) and PyByteArray (bytearray)
+ * methods of the given names, they operate on ASCII byte strings.
+ */
+extern PyObject* _Py_bytes_isspace(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_isalpha(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_isalnum(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_isascii(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_isdigit(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_islower(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_isupper(const char *cptr, Py_ssize_t len);
+extern PyObject* _Py_bytes_istitle(const char *cptr, Py_ssize_t len);
+
+/* These store their len sized answer in the given preallocated *result arg. */
+extern void _Py_bytes_lower(char *result, const char *cptr, Py_ssize_t len);
+extern void _Py_bytes_upper(char *result, const char *cptr, Py_ssize_t len);
+extern void _Py_bytes_title(char *result, const char *s, Py_ssize_t len);
+extern void _Py_bytes_capitalize(char *result, const char *s, Py_ssize_t len);
+extern void _Py_bytes_swapcase(char *result, const char *s, Py_ssize_t len);
+
+extern PyObject *_Py_bytes_find(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_index(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_rfind(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_rindex(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_count(const char *str, Py_ssize_t len, PyObject *args);
+extern int _Py_bytes_contains(const char *str, Py_ssize_t len, PyObject *arg);
+extern PyObject *_Py_bytes_startswith(const char *str, Py_ssize_t len, PyObject *args);
+extern PyObject *_Py_bytes_endswith(const char *str, Py_ssize_t len, PyObject *args);
+
+/* The maketrans() static method. */
+extern PyObject* _Py_bytes_maketrans(Py_buffer *frm, Py_buffer *to);
+
+/* Shared __doc__ strings. */
+extern const char _Py_isspace__doc__[];
+extern const char _Py_isalpha__doc__[];
+extern const char _Py_isalnum__doc__[];
+extern const char _Py_isascii__doc__[];
+extern const char _Py_isdigit__doc__[];
+extern const char _Py_islower__doc__[];
+extern const char _Py_isupper__doc__[];
+extern const char _Py_istitle__doc__[];
+extern const char _Py_lower__doc__[];
+extern const char _Py_upper__doc__[];
+extern const char _Py_title__doc__[];
+extern const char _Py_capitalize__doc__[];
+extern const char _Py_swapcase__doc__[];
+extern const char _Py_count__doc__[];
+extern const char _Py_find__doc__[];
+extern const char _Py_index__doc__[];
+extern const char _Py_rfind__doc__[];
+extern const char _Py_rindex__doc__[];
+extern const char _Py_startswith__doc__[];
+extern const char _Py_endswith__doc__[];
+extern const char _Py_maketrans__doc__[];
+extern const char _Py_expandtabs__doc__[];
+extern const char _Py_ljust__doc__[];
+extern const char _Py_rjust__doc__[];
+extern const char _Py_center__doc__[];
+extern const char _Py_zfill__doc__[];
+
+/* this is needed because some docs are shared from the .o, not static */
+#define PyDoc_STRVAR_shared(name,str) const char name[] = PyDoc_STR(str)
+
+#endif /* !Py_BYTES_CTYPE_H */
+#endif /* !Py_LIMITED_API */
diff --git a/Include/bytesobject.h b/Include/bytesobject.h
new file mode 100644
index 0000000..3fde4a2
--- /dev/null
+++ b/Include/bytesobject.h
@@ -0,0 +1,224 @@
+
+/* Bytes (String) object interface */
+
+#ifndef Py_BYTESOBJECT_H
+#define Py_BYTESOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include
+
+/*
+Type PyBytesObject represents a character string. An extra zero byte is
+reserved at the end to ensure it is zero-terminated, but a size is
+present so strings with null bytes in them can be represented. This
+is an immutable object type.
+
+There are functions to create new string objects, to test
+an object for string-ness, and to get the
+string value. The latter function returns a null pointer
+if the object is not of the proper type.
+There is a variant that takes an explicit size as well as a
+variant that assumes a zero-terminated string. Note that none of the
+functions should be applied to nil objects.
+*/
+
+/* Caching the hash (ob_shash) saves recalculation of a string's hash value.
+ This significantly speeds up dict lookups. */
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_VAR_HEAD
+ Py_hash_t ob_shash;
+ char ob_sval[1];
+
+ /* Invariants:
+ * ob_sval contains space for 'ob_size+1' elements.
+ * ob_sval[ob_size] == 0.
+ * ob_shash is the hash of the string or -1 if not computed yet.
+ */
+} PyBytesObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PyBytes_Type;
+PyAPI_DATA(PyTypeObject) PyBytesIter_Type;
+
+#define PyBytes_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_BYTES_SUBCLASS)
+#define PyBytes_CheckExact(op) (Py_TYPE(op) == &PyBytes_Type)
+
+PyAPI_FUNC(PyObject *) PyBytes_FromStringAndSize(const char *, Py_ssize_t);
+PyAPI_FUNC(PyObject *) PyBytes_FromString(const char *);
+PyAPI_FUNC(PyObject *) PyBytes_FromObject(PyObject *);
+PyAPI_FUNC(PyObject *) PyBytes_FromFormatV(const char*, va_list)
+ Py_GCC_ATTRIBUTE((format(printf, 1, 0)));
+PyAPI_FUNC(PyObject *) PyBytes_FromFormat(const char*, ...)
+ Py_GCC_ATTRIBUTE((format(printf, 1, 2)));
+PyAPI_FUNC(Py_ssize_t) PyBytes_Size(PyObject *);
+PyAPI_FUNC(char *) PyBytes_AsString(PyObject *);
+PyAPI_FUNC(PyObject *) PyBytes_Repr(PyObject *, int);
+PyAPI_FUNC(void) PyBytes_Concat(PyObject **, PyObject *);
+PyAPI_FUNC(void) PyBytes_ConcatAndDel(PyObject **, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyBytes_Resize(PyObject **, Py_ssize_t);
+PyAPI_FUNC(PyObject*) _PyBytes_FormatEx(
+ const char *format,
+ Py_ssize_t format_len,
+ PyObject *args,
+ int use_bytearray);
+PyAPI_FUNC(PyObject*) _PyBytes_FromHex(
+ PyObject *string,
+ int use_bytearray);
+#endif
+PyAPI_FUNC(PyObject *) PyBytes_DecodeEscape(const char *, Py_ssize_t,
+ const char *, Py_ssize_t,
+ const char *);
+#ifndef Py_LIMITED_API
+/* Helper for PyBytes_DecodeEscape that detects invalid escape chars. */
+PyAPI_FUNC(PyObject *) _PyBytes_DecodeEscape(const char *, Py_ssize_t,
+ const char *, Py_ssize_t,
+ const char *,
+ const char **);
+#endif
+
+/* Macro, trading safety for speed */
+#ifndef Py_LIMITED_API
+#define PyBytes_AS_STRING(op) (assert(PyBytes_Check(op)), \
+ (((PyBytesObject *)(op))->ob_sval))
+#define PyBytes_GET_SIZE(op) (assert(PyBytes_Check(op)),Py_SIZE(op))
+#endif
+
+/* _PyBytes_Join(sep, x) is like sep.join(x). sep must be PyBytesObject*,
+ x must be an iterable object. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyBytes_Join(PyObject *sep, PyObject *x);
+#endif
+
+/* Provides access to the internal data buffer and size of a string
+ object or the default encoded version of a Unicode object. Passing
+ NULL as *len parameter will force the string buffer to be
+ 0-terminated (passing a string with embedded NULL characters will
+ cause an exception). */
+PyAPI_FUNC(int) PyBytes_AsStringAndSize(
+ PyObject *obj, /* string or Unicode object */
+ char **s, /* pointer to buffer variable */
+ Py_ssize_t *len /* pointer to length variable or NULL
+ (only possible for 0-terminated
+ strings) */
+ );
+
+/* Using the current locale, insert the thousands grouping
+ into the string pointed to by buffer. For the argument descriptions,
+ see Objects/stringlib/localeutil.h */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) _PyBytes_InsertThousandsGroupingLocale(char *buffer,
+ Py_ssize_t n_buffer,
+ char *digits,
+ Py_ssize_t n_digits,
+ Py_ssize_t min_width);
+
+/* Using explicit passed-in values, insert the thousands grouping
+ into the string pointed to by buffer. For the argument descriptions,
+ see Objects/stringlib/localeutil.h */
+PyAPI_FUNC(Py_ssize_t) _PyBytes_InsertThousandsGrouping(char *buffer,
+ Py_ssize_t n_buffer,
+ char *digits,
+ Py_ssize_t n_digits,
+ Py_ssize_t min_width,
+ const char *grouping,
+ const char *thousands_sep);
+#endif
+
+/* Flags used by string formatting */
+#define F_LJUST (1<<0)
+#define F_SIGN (1<<1)
+#define F_BLANK (1<<2)
+#define F_ALT (1<<3)
+#define F_ZERO (1<<4)
+
+#ifndef Py_LIMITED_API
+/* The _PyBytesWriter structure is big: it contains an embedded "stack buffer".
+ A _PyBytesWriter variable must be declared at the end of variables in a
+ function to optimize the memory allocation on the stack. */
+typedef struct {
+ /* bytes, bytearray or NULL (when the small buffer is used) */
+ PyObject *buffer;
+
+ /* Number of allocated size. */
+ Py_ssize_t allocated;
+
+ /* Minimum number of allocated bytes,
+ incremented by _PyBytesWriter_Prepare() */
+ Py_ssize_t min_size;
+
+ /* If non-zero, use a bytearray instead of a bytes object for buffer. */
+ int use_bytearray;
+
+ /* If non-zero, overallocate the buffer (default: 0).
+ This flag must be zero if use_bytearray is non-zero. */
+ int overallocate;
+
+ /* Stack buffer */
+ int use_small_buffer;
+ char small_buffer[512];
+} _PyBytesWriter;
+
+/* Initialize a bytes writer
+
+ By default, the overallocation is disabled. Set the overallocate attribute
+ to control the allocation of the buffer. */
+PyAPI_FUNC(void) _PyBytesWriter_Init(_PyBytesWriter *writer);
+
+/* Get the buffer content and reset the writer.
+ Return a bytes object, or a bytearray object if use_bytearray is non-zero.
+ Raise an exception and return NULL on error. */
+PyAPI_FUNC(PyObject *) _PyBytesWriter_Finish(_PyBytesWriter *writer,
+ void *str);
+
+/* Deallocate memory of a writer (clear its internal buffer). */
+PyAPI_FUNC(void) _PyBytesWriter_Dealloc(_PyBytesWriter *writer);
+
+/* Allocate the buffer to write size bytes.
+ Return the pointer to the beginning of buffer data.
+ Raise an exception and return NULL on error. */
+PyAPI_FUNC(void*) _PyBytesWriter_Alloc(_PyBytesWriter *writer,
+ Py_ssize_t size);
+
+/* Ensure that the buffer is large enough to write *size* bytes.
+ Add size to the writer minimum size (min_size attribute).
+
+ str is the current pointer inside the buffer.
+ Return the updated current pointer inside the buffer.
+ Raise an exception and return NULL on error. */
+PyAPI_FUNC(void*) _PyBytesWriter_Prepare(_PyBytesWriter *writer,
+ void *str,
+ Py_ssize_t size);
+
+/* Resize the buffer to make it larger.
+ The new buffer may be larger than size bytes because of overallocation.
+ Return the updated current pointer inside the buffer.
+ Raise an exception and return NULL on error.
+
+ Note: size must be greater than the number of allocated bytes in the writer.
+
+ This function doesn't use the writer minimum size (min_size attribute).
+
+ See also _PyBytesWriter_Prepare().
+ */
+PyAPI_FUNC(void*) _PyBytesWriter_Resize(_PyBytesWriter *writer,
+ void *str,
+ Py_ssize_t size);
+
+/* Write bytes.
+ Raise an exception and return NULL on error. */
+PyAPI_FUNC(void*) _PyBytesWriter_WriteBytes(_PyBytesWriter *writer,
+ void *str,
+ const void *bytes,
+ Py_ssize_t size);
+#endif /* Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_BYTESOBJECT_H */
diff --git a/Include/cellobject.h b/Include/cellobject.h
new file mode 100644
index 0000000..2f9b5b7
--- /dev/null
+++ b/Include/cellobject.h
@@ -0,0 +1,29 @@
+/* Cell object interface */
+#ifndef Py_LIMITED_API
+#ifndef Py_CELLOBJECT_H
+#define Py_CELLOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ PyObject_HEAD
+ PyObject *ob_ref; /* Content of the cell or NULL when empty */
+} PyCellObject;
+
+PyAPI_DATA(PyTypeObject) PyCell_Type;
+
+#define PyCell_Check(op) (Py_TYPE(op) == &PyCell_Type)
+
+PyAPI_FUNC(PyObject *) PyCell_New(PyObject *);
+PyAPI_FUNC(PyObject *) PyCell_Get(PyObject *);
+PyAPI_FUNC(int) PyCell_Set(PyObject *, PyObject *);
+
+#define PyCell_GET(op) (((PyCellObject *)(op))->ob_ref)
+#define PyCell_SET(op, v) (((PyCellObject *)(op))->ob_ref = v)
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_TUPLEOBJECT_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/ceval.h b/Include/ceval.h
new file mode 100644
index 0000000..bce8a0b
--- /dev/null
+++ b/Include/ceval.h
@@ -0,0 +1,237 @@
+#ifndef Py_CEVAL_H
+#define Py_CEVAL_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Interface to random parts in ceval.c */
+
+/* PyEval_CallObjectWithKeywords(), PyEval_CallObject(), PyEval_CallFunction
+ * and PyEval_CallMethod are kept for backward compatibility: PyObject_Call(),
+ * PyObject_CallFunction() and PyObject_CallMethod() are recommended to call
+ * a callable object.
+ */
+
+PyAPI_FUNC(PyObject *) PyEval_CallObjectWithKeywords(
+ PyObject *callable,
+ PyObject *args,
+ PyObject *kwargs);
+
+/* Inline this */
+#define PyEval_CallObject(callable, arg) \
+ PyEval_CallObjectWithKeywords(callable, arg, (PyObject *)NULL)
+
+PyAPI_FUNC(PyObject *) PyEval_CallFunction(PyObject *callable,
+ const char *format, ...);
+PyAPI_FUNC(PyObject *) PyEval_CallMethod(PyObject *obj,
+ const char *name,
+ const char *format, ...);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) PyEval_SetProfile(Py_tracefunc, PyObject *);
+PyAPI_FUNC(void) PyEval_SetTrace(Py_tracefunc, PyObject *);
+PyAPI_FUNC(void) _PyEval_SetCoroutineOriginTrackingDepth(int new_depth);
+PyAPI_FUNC(int) _PyEval_GetCoroutineOriginTrackingDepth(void);
+PyAPI_FUNC(void) _PyEval_SetCoroutineWrapper(PyObject *);
+PyAPI_FUNC(PyObject *) _PyEval_GetCoroutineWrapper(void);
+PyAPI_FUNC(void) _PyEval_SetAsyncGenFirstiter(PyObject *);
+PyAPI_FUNC(PyObject *) _PyEval_GetAsyncGenFirstiter(void);
+PyAPI_FUNC(void) _PyEval_SetAsyncGenFinalizer(PyObject *);
+PyAPI_FUNC(PyObject *) _PyEval_GetAsyncGenFinalizer(void);
+#endif
+
+struct _frame; /* Avoid including frameobject.h */
+
+PyAPI_FUNC(PyObject *) PyEval_GetBuiltins(void);
+PyAPI_FUNC(PyObject *) PyEval_GetGlobals(void);
+PyAPI_FUNC(PyObject *) PyEval_GetLocals(void);
+PyAPI_FUNC(struct _frame *) PyEval_GetFrame(void);
+
+/* Look at the current frame's (if any) code's co_flags, and turn on
+ the corresponding compiler flags in cf->cf_flags. Return 1 if any
+ flag was set, else return 0. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) PyEval_MergeCompilerFlags(PyCompilerFlags *cf);
+#endif
+
+PyAPI_FUNC(int) Py_AddPendingCall(int (*func)(void *), void *arg);
+PyAPI_FUNC(void) _PyEval_SignalReceived(void);
+PyAPI_FUNC(int) Py_MakePendingCalls(void);
+
+/* Protection against deeply nested recursive calls
+
+ In Python 3.0, this protection has two levels:
+ * normal anti-recursion protection is triggered when the recursion level
+ exceeds the current recursion limit. It raises a RecursionError, and sets
+ the "overflowed" flag in the thread state structure. This flag
+ temporarily *disables* the normal protection; this allows cleanup code
+ to potentially outgrow the recursion limit while processing the
+ RecursionError.
+ * "last chance" anti-recursion protection is triggered when the recursion
+ level exceeds "current recursion limit + 50". By construction, this
+ protection can only be triggered when the "overflowed" flag is set. It
+ means the cleanup code has itself gone into an infinite loop, or the
+ RecursionError has been mistakingly ignored. When this protection is
+ triggered, the interpreter aborts with a Fatal Error.
+
+ In addition, the "overflowed" flag is automatically reset when the
+ recursion level drops below "current recursion limit - 50". This heuristic
+ is meant to ensure that the normal anti-recursion protection doesn't get
+ disabled too long.
+
+ Please note: this scheme has its own limitations. See:
+ http://mail.python.org/pipermail/python-dev/2008-August/082106.html
+ for some observations.
+*/
+PyAPI_FUNC(void) Py_SetRecursionLimit(int);
+PyAPI_FUNC(int) Py_GetRecursionLimit(void);
+
+#define Py_EnterRecursiveCall(where) \
+ (_Py_MakeRecCheck(PyThreadState_GET()->recursion_depth) && \
+ _Py_CheckRecursiveCall(where))
+#define Py_LeaveRecursiveCall() \
+ do{ if(_Py_MakeEndRecCheck(PyThreadState_GET()->recursion_depth)) \
+ PyThreadState_GET()->overflowed = 0; \
+ } while(0)
+PyAPI_FUNC(int) _Py_CheckRecursiveCall(const char *where);
+
+/* Due to the macros in which it's used, _Py_CheckRecursionLimit is in
+ the stable ABI. It should be removed therefrom when possible.
+*/
+PyAPI_DATA(int) _Py_CheckRecursionLimit;
+
+#ifdef USE_STACKCHECK
+/* With USE_STACKCHECK, trigger stack checks in _Py_CheckRecursiveCall()
+ on every 64th call to Py_EnterRecursiveCall.
+*/
+# define _Py_MakeRecCheck(x) \
+ (++(x) > _Py_CheckRecursionLimit || \
+ ++(PyThreadState_GET()->stackcheck_counter) > 64)
+#else
+# define _Py_MakeRecCheck(x) (++(x) > _Py_CheckRecursionLimit)
+#endif
+
+/* Compute the "lower-water mark" for a recursion limit. When
+ * Py_LeaveRecursiveCall() is called with a recursion depth below this mark,
+ * the overflowed flag is reset to 0. */
+#define _Py_RecursionLimitLowerWaterMark(limit) \
+ (((limit) > 200) \
+ ? ((limit) - 50) \
+ : (3 * ((limit) >> 2)))
+
+#define _Py_MakeEndRecCheck(x) \
+ (--(x) < _Py_RecursionLimitLowerWaterMark(_Py_CheckRecursionLimit))
+
+#define Py_ALLOW_RECURSION \
+ do { unsigned char _old = PyThreadState_GET()->recursion_critical;\
+ PyThreadState_GET()->recursion_critical = 1;
+
+#define Py_END_ALLOW_RECURSION \
+ PyThreadState_GET()->recursion_critical = _old; \
+ } while(0);
+
+PyAPI_FUNC(const char *) PyEval_GetFuncName(PyObject *);
+PyAPI_FUNC(const char *) PyEval_GetFuncDesc(PyObject *);
+
+PyAPI_FUNC(PyObject *) PyEval_EvalFrame(struct _frame *);
+PyAPI_FUNC(PyObject *) PyEval_EvalFrameEx(struct _frame *f, int exc);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyEval_EvalFrameDefault(struct _frame *f, int exc);
+#endif
+
+/* Interface for threads.
+
+ A module that plans to do a blocking system call (or something else
+ that lasts a long time and doesn't touch Python data) can allow other
+ threads to run as follows:
+
+ ...preparations here...
+ Py_BEGIN_ALLOW_THREADS
+ ...blocking system call here...
+ Py_END_ALLOW_THREADS
+ ...interpret result here...
+
+ The Py_BEGIN_ALLOW_THREADS/Py_END_ALLOW_THREADS pair expands to a
+ {}-surrounded block.
+ To leave the block in the middle (e.g., with return), you must insert
+ a line containing Py_BLOCK_THREADS before the return, e.g.
+
+ if (...premature_exit...) {
+ Py_BLOCK_THREADS
+ PyErr_SetFromErrno(PyExc_OSError);
+ return NULL;
+ }
+
+ An alternative is:
+
+ Py_BLOCK_THREADS
+ if (...premature_exit...) {
+ PyErr_SetFromErrno(PyExc_OSError);
+ return NULL;
+ }
+ Py_UNBLOCK_THREADS
+
+ For convenience, that the value of 'errno' is restored across
+ Py_END_ALLOW_THREADS and Py_BLOCK_THREADS.
+
+ WARNING: NEVER NEST CALLS TO Py_BEGIN_ALLOW_THREADS AND
+ Py_END_ALLOW_THREADS!!!
+
+ The function PyEval_InitThreads() should be called only from
+ init_thread() in "_threadmodule.c".
+
+ Note that not yet all candidates have been converted to use this
+ mechanism!
+*/
+
+PyAPI_FUNC(PyThreadState *) PyEval_SaveThread(void);
+PyAPI_FUNC(void) PyEval_RestoreThread(PyThreadState *);
+
+PyAPI_FUNC(int) PyEval_ThreadsInitialized(void);
+PyAPI_FUNC(void) PyEval_InitThreads(void);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyEval_FiniThreads(void);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(void) PyEval_AcquireLock(void) Py_DEPRECATED(3.2);
+PyAPI_FUNC(void) PyEval_ReleaseLock(void) /* Py_DEPRECATED(3.2) */;
+PyAPI_FUNC(void) PyEval_AcquireThread(PyThreadState *tstate);
+PyAPI_FUNC(void) PyEval_ReleaseThread(PyThreadState *tstate);
+PyAPI_FUNC(void) PyEval_ReInitThreads(void);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyEval_SetSwitchInterval(unsigned long microseconds);
+PyAPI_FUNC(unsigned long) _PyEval_GetSwitchInterval(void);
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) _PyEval_RequestCodeExtraIndex(freefunc);
+#endif
+
+#define Py_BEGIN_ALLOW_THREADS { \
+ PyThreadState *_save; \
+ _save = PyEval_SaveThread();
+#define Py_BLOCK_THREADS PyEval_RestoreThread(_save);
+#define Py_UNBLOCK_THREADS _save = PyEval_SaveThread();
+#define Py_END_ALLOW_THREADS PyEval_RestoreThread(_save); \
+ }
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyEval_SliceIndex(PyObject *, Py_ssize_t *);
+PyAPI_FUNC(int) _PyEval_SliceIndexNotNone(PyObject *, Py_ssize_t *);
+PyAPI_FUNC(void) _PyEval_SignalAsyncExc(void);
+#endif
+
+/* Masks and values used by FORMAT_VALUE opcode. */
+#define FVC_MASK 0x3
+#define FVC_NONE 0x0
+#define FVC_STR 0x1
+#define FVC_REPR 0x2
+#define FVC_ASCII 0x3
+#define FVS_MASK 0x4
+#define FVS_HAVE_SPEC 0x4
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_CEVAL_H */
diff --git a/Include/classobject.h b/Include/classobject.h
new file mode 100644
index 0000000..209f0f4
--- /dev/null
+++ b/Include/classobject.h
@@ -0,0 +1,58 @@
+/* Former class object interface -- now only bound methods are here */
+
+/* Revealing some structures (not for general use) */
+
+#ifndef Py_LIMITED_API
+#ifndef Py_CLASSOBJECT_H
+#define Py_CLASSOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ PyObject_HEAD
+ PyObject *im_func; /* The callable object implementing the method */
+ PyObject *im_self; /* The instance it is bound to */
+ PyObject *im_weakreflist; /* List of weak references */
+} PyMethodObject;
+
+PyAPI_DATA(PyTypeObject) PyMethod_Type;
+
+#define PyMethod_Check(op) ((op)->ob_type == &PyMethod_Type)
+
+PyAPI_FUNC(PyObject *) PyMethod_New(PyObject *, PyObject *);
+
+PyAPI_FUNC(PyObject *) PyMethod_Function(PyObject *);
+PyAPI_FUNC(PyObject *) PyMethod_Self(PyObject *);
+
+/* Macros for direct access to these values. Type checks are *not*
+ done, so use with care. */
+#define PyMethod_GET_FUNCTION(meth) \
+ (((PyMethodObject *)meth) -> im_func)
+#define PyMethod_GET_SELF(meth) \
+ (((PyMethodObject *)meth) -> im_self)
+
+PyAPI_FUNC(int) PyMethod_ClearFreeList(void);
+
+typedef struct {
+ PyObject_HEAD
+ PyObject *func;
+} PyInstanceMethodObject;
+
+PyAPI_DATA(PyTypeObject) PyInstanceMethod_Type;
+
+#define PyInstanceMethod_Check(op) ((op)->ob_type == &PyInstanceMethod_Type)
+
+PyAPI_FUNC(PyObject *) PyInstanceMethod_New(PyObject *);
+PyAPI_FUNC(PyObject *) PyInstanceMethod_Function(PyObject *);
+
+/* Macros for direct access to these values. Type checks are *not*
+ done, so use with care. */
+#define PyInstanceMethod_GET_FUNCTION(meth) \
+ (((PyInstanceMethodObject *)meth) -> func)
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_CLASSOBJECT_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/code.h b/Include/code.h
new file mode 100644
index 0000000..2e661e8
--- /dev/null
+++ b/Include/code.h
@@ -0,0 +1,157 @@
+/* Definitions for bytecode */
+
+#ifndef Py_LIMITED_API
+#ifndef Py_CODE_H
+#define Py_CODE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef uint16_t _Py_CODEUNIT;
+
+#ifdef WORDS_BIGENDIAN
+# define _Py_OPCODE(word) ((word) >> 8)
+# define _Py_OPARG(word) ((word) & 255)
+#else
+# define _Py_OPCODE(word) ((word) & 255)
+# define _Py_OPARG(word) ((word) >> 8)
+#endif
+
+/* Bytecode object */
+typedef struct {
+ PyObject_HEAD
+ int co_argcount; /* #arguments, except *args */
+ int co_kwonlyargcount; /* #keyword only arguments */
+ int co_nlocals; /* #local variables */
+ int co_stacksize; /* #entries needed for evaluation stack */
+ int co_flags; /* CO_..., see below */
+ int co_firstlineno; /* first source line number */
+ PyObject *co_code; /* instruction opcodes */
+ PyObject *co_consts; /* list (constants used) */
+ PyObject *co_names; /* list of strings (names used) */
+ PyObject *co_varnames; /* tuple of strings (local variable names) */
+ PyObject *co_freevars; /* tuple of strings (free variable names) */
+ PyObject *co_cellvars; /* tuple of strings (cell variable names) */
+ /* The rest aren't used in either hash or comparisons, except for co_name,
+ used in both. This is done to preserve the name and line number
+ for tracebacks and debuggers; otherwise, constant de-duplication
+ would collapse identical functions/lambdas defined on different lines.
+ */
+ Py_ssize_t *co_cell2arg; /* Maps cell vars which are arguments. */
+ PyObject *co_filename; /* unicode (where it was loaded from) */
+ PyObject *co_name; /* unicode (name, for reference) */
+ PyObject *co_lnotab; /* string (encoding addr<->lineno mapping) See
+ Objects/lnotab_notes.txt for details. */
+ void *co_zombieframe; /* for optimization only (see frameobject.c) */
+ PyObject *co_weakreflist; /* to support weakrefs to code objects */
+ /* Scratch space for extra data relating to the code object.
+ Type is a void* to keep the format private in codeobject.c to force
+ people to go through the proper APIs. */
+ void *co_extra;
+} PyCodeObject;
+
+/* Masks for co_flags above */
+#define CO_OPTIMIZED 0x0001
+#define CO_NEWLOCALS 0x0002
+#define CO_VARARGS 0x0004
+#define CO_VARKEYWORDS 0x0008
+#define CO_NESTED 0x0010
+#define CO_GENERATOR 0x0020
+/* The CO_NOFREE flag is set if there are no free or cell variables.
+ This information is redundant, but it allows a single flag test
+ to determine whether there is any extra work to be done when the
+ call frame it setup.
+*/
+#define CO_NOFREE 0x0040
+
+/* The CO_COROUTINE flag is set for coroutine functions (defined with
+ ``async def`` keywords) */
+#define CO_COROUTINE 0x0080
+#define CO_ITERABLE_COROUTINE 0x0100
+#define CO_ASYNC_GENERATOR 0x0200
+
+/* These are no longer used. */
+#if 0
+#define CO_GENERATOR_ALLOWED 0x1000
+#endif
+#define CO_FUTURE_DIVISION 0x2000
+#define CO_FUTURE_ABSOLUTE_IMPORT 0x4000 /* do absolute imports by default */
+#define CO_FUTURE_WITH_STATEMENT 0x8000
+#define CO_FUTURE_PRINT_FUNCTION 0x10000
+#define CO_FUTURE_UNICODE_LITERALS 0x20000
+
+#define CO_FUTURE_BARRY_AS_BDFL 0x40000
+#define CO_FUTURE_GENERATOR_STOP 0x80000
+#define CO_FUTURE_ANNOTATIONS 0x100000
+
+/* This value is found in the co_cell2arg array when the associated cell
+ variable does not correspond to an argument. */
+#define CO_CELL_NOT_AN_ARG (-1)
+
+/* This should be defined if a future statement modifies the syntax.
+ For example, when a keyword is added.
+*/
+#define PY_PARSER_REQUIRES_FUTURE_KEYWORD
+
+#define CO_MAXBLOCKS 20 /* Max static block nesting within a function */
+
+PyAPI_DATA(PyTypeObject) PyCode_Type;
+
+#define PyCode_Check(op) (Py_TYPE(op) == &PyCode_Type)
+#define PyCode_GetNumFree(op) (PyTuple_GET_SIZE((op)->co_freevars))
+
+/* Public interface */
+PyAPI_FUNC(PyCodeObject *) PyCode_New(
+ int, int, int, int, int, PyObject *, PyObject *,
+ PyObject *, PyObject *, PyObject *, PyObject *,
+ PyObject *, PyObject *, int, PyObject *);
+ /* same as struct above */
+
+/* Creates a new empty code object with the specified source location. */
+PyAPI_FUNC(PyCodeObject *)
+PyCode_NewEmpty(const char *filename, const char *funcname, int firstlineno);
+
+/* Return the line number associated with the specified bytecode index
+ in this code object. If you just need the line number of a frame,
+ use PyFrame_GetLineNumber() instead. */
+PyAPI_FUNC(int) PyCode_Addr2Line(PyCodeObject *, int);
+
+/* for internal use only */
+typedef struct _addr_pair {
+ int ap_lower;
+ int ap_upper;
+} PyAddrPair;
+
+#ifndef Py_LIMITED_API
+/* Update *bounds to describe the first and one-past-the-last instructions in the
+ same line as lasti. Return the number of that line.
+*/
+PyAPI_FUNC(int) _PyCode_CheckLineNumber(PyCodeObject* co,
+ int lasti, PyAddrPair *bounds);
+
+/* Create a comparable key used to compare constants taking in account the
+ * object type. It is used to make sure types are not coerced (e.g., float and
+ * complex) _and_ to distinguish 0.0 from -0.0 e.g. on IEEE platforms
+ *
+ * Return (type(obj), obj, ...): a tuple with variable size (at least 2 items)
+ * depending on the type and the value. The type is the first item to not
+ * compare bytes and str which can raise a BytesWarning exception. */
+PyAPI_FUNC(PyObject*) _PyCode_ConstantKey(PyObject *obj);
+#endif
+
+PyAPI_FUNC(PyObject*) PyCode_Optimize(PyObject *code, PyObject* consts,
+ PyObject *names, PyObject *lnotab);
+
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyCode_GetExtra(PyObject *code, Py_ssize_t index,
+ void **extra);
+PyAPI_FUNC(int) _PyCode_SetExtra(PyObject *code, Py_ssize_t index,
+ void *extra);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_CODE_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/codecs.h b/Include/codecs.h
new file mode 100644
index 0000000..3ad0f2b
--- /dev/null
+++ b/Include/codecs.h
@@ -0,0 +1,240 @@
+#ifndef Py_CODECREGISTRY_H
+#define Py_CODECREGISTRY_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* ------------------------------------------------------------------------
+
+ Python Codec Registry and support functions
+
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+Copyright (c) Corporation for National Research Initiatives.
+
+ ------------------------------------------------------------------------ */
+
+/* Register a new codec search function.
+
+ As side effect, this tries to load the encodings package, if not
+ yet done, to make sure that it is always first in the list of
+ search functions.
+
+ The search_function's refcount is incremented by this function. */
+
+PyAPI_FUNC(int) PyCodec_Register(
+ PyObject *search_function
+ );
+
+/* Codec registry lookup API.
+
+ Looks up the given encoding and returns a CodecInfo object with
+ function attributes which implement the different aspects of
+ processing the encoding.
+
+ The encoding string is looked up converted to all lower-case
+ characters. This makes encodings looked up through this mechanism
+ effectively case-insensitive.
+
+ If no codec is found, a KeyError is set and NULL returned.
+
+ As side effect, this tries to load the encodings package, if not
+ yet done. This is part of the lazy load strategy for the encodings
+ package.
+
+ */
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyCodec_Lookup(
+ const char *encoding
+ );
+
+PyAPI_FUNC(int) _PyCodec_Forget(
+ const char *encoding
+ );
+#endif
+
+/* Codec registry encoding check API.
+
+ Returns 1/0 depending on whether there is a registered codec for
+ the given encoding.
+
+*/
+
+PyAPI_FUNC(int) PyCodec_KnownEncoding(
+ const char *encoding
+ );
+
+/* Generic codec based encoding API.
+
+ object is passed through the encoder function found for the given
+ encoding using the error handling method defined by errors. errors
+ may be NULL to use the default method defined for the codec.
+
+ Raises a LookupError in case no encoder can be found.
+
+ */
+
+PyAPI_FUNC(PyObject *) PyCodec_Encode(
+ PyObject *object,
+ const char *encoding,
+ const char *errors
+ );
+
+/* Generic codec based decoding API.
+
+ object is passed through the decoder function found for the given
+ encoding using the error handling method defined by errors. errors
+ may be NULL to use the default method defined for the codec.
+
+ Raises a LookupError in case no encoder can be found.
+
+ */
+
+PyAPI_FUNC(PyObject *) PyCodec_Decode(
+ PyObject *object,
+ const char *encoding,
+ const char *errors
+ );
+
+#ifndef Py_LIMITED_API
+/* Text codec specific encoding and decoding API.
+
+ Checks the encoding against a list of codecs which do not
+ implement a str<->bytes encoding before attempting the
+ operation.
+
+ Please note that these APIs are internal and should not
+ be used in Python C extensions.
+
+ XXX (ncoghlan): should we make these, or something like them, public
+ in Python 3.5+?
+
+ */
+PyAPI_FUNC(PyObject *) _PyCodec_LookupTextEncoding(
+ const char *encoding,
+ const char *alternate_command
+ );
+
+PyAPI_FUNC(PyObject *) _PyCodec_EncodeText(
+ PyObject *object,
+ const char *encoding,
+ const char *errors
+ );
+
+PyAPI_FUNC(PyObject *) _PyCodec_DecodeText(
+ PyObject *object,
+ const char *encoding,
+ const char *errors
+ );
+
+/* These two aren't actually text encoding specific, but _io.TextIOWrapper
+ * is the only current API consumer.
+ */
+PyAPI_FUNC(PyObject *) _PyCodecInfo_GetIncrementalDecoder(
+ PyObject *codec_info,
+ const char *errors
+ );
+
+PyAPI_FUNC(PyObject *) _PyCodecInfo_GetIncrementalEncoder(
+ PyObject *codec_info,
+ const char *errors
+ );
+#endif
+
+
+
+/* --- Codec Lookup APIs --------------------------------------------------
+
+ All APIs return a codec object with incremented refcount and are
+ based on _PyCodec_Lookup(). The same comments w/r to the encoding
+ name also apply to these APIs.
+
+*/
+
+/* Get an encoder function for the given encoding. */
+
+PyAPI_FUNC(PyObject *) PyCodec_Encoder(
+ const char *encoding
+ );
+
+/* Get a decoder function for the given encoding. */
+
+PyAPI_FUNC(PyObject *) PyCodec_Decoder(
+ const char *encoding
+ );
+
+/* Get an IncrementalEncoder object for the given encoding. */
+
+PyAPI_FUNC(PyObject *) PyCodec_IncrementalEncoder(
+ const char *encoding,
+ const char *errors
+ );
+
+/* Get an IncrementalDecoder object function for the given encoding. */
+
+PyAPI_FUNC(PyObject *) PyCodec_IncrementalDecoder(
+ const char *encoding,
+ const char *errors
+ );
+
+/* Get a StreamReader factory function for the given encoding. */
+
+PyAPI_FUNC(PyObject *) PyCodec_StreamReader(
+ const char *encoding,
+ PyObject *stream,
+ const char *errors
+ );
+
+/* Get a StreamWriter factory function for the given encoding. */
+
+PyAPI_FUNC(PyObject *) PyCodec_StreamWriter(
+ const char *encoding,
+ PyObject *stream,
+ const char *errors
+ );
+
+/* Unicode encoding error handling callback registry API */
+
+/* Register the error handling callback function error under the given
+ name. This function will be called by the codec when it encounters
+ unencodable characters/undecodable bytes and doesn't know the
+ callback name, when name is specified as the error parameter
+ in the call to the encode/decode function.
+ Return 0 on success, -1 on error */
+PyAPI_FUNC(int) PyCodec_RegisterError(const char *name, PyObject *error);
+
+/* Lookup the error handling callback function registered under the given
+ name. As a special case NULL can be passed, in which case
+ the error handling callback for "strict" will be returned. */
+PyAPI_FUNC(PyObject *) PyCodec_LookupError(const char *name);
+
+/* raise exc as an exception */
+PyAPI_FUNC(PyObject *) PyCodec_StrictErrors(PyObject *exc);
+
+/* ignore the unicode error, skipping the faulty input */
+PyAPI_FUNC(PyObject *) PyCodec_IgnoreErrors(PyObject *exc);
+
+/* replace the unicode encode error with ? or U+FFFD */
+PyAPI_FUNC(PyObject *) PyCodec_ReplaceErrors(PyObject *exc);
+
+/* replace the unicode encode error with XML character references */
+PyAPI_FUNC(PyObject *) PyCodec_XMLCharRefReplaceErrors(PyObject *exc);
+
+/* replace the unicode encode error with backslash escapes (\x, \u and \U) */
+PyAPI_FUNC(PyObject *) PyCodec_BackslashReplaceErrors(PyObject *exc);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* replace the unicode encode error with backslash escapes (\N, \x, \u and \U) */
+PyAPI_FUNC(PyObject *) PyCodec_NameReplaceErrors(PyObject *exc);
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(const char *) Py_hexdigits;
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_CODECREGISTRY_H */
diff --git a/Include/compile.h b/Include/compile.h
new file mode 100644
index 0000000..edb961f
--- /dev/null
+++ b/Include/compile.h
@@ -0,0 +1,93 @@
+#ifndef Py_COMPILE_H
+#define Py_COMPILE_H
+
+#ifndef Py_LIMITED_API
+#include "code.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Public interface */
+struct _node; /* Declare the existence of this type */
+PyAPI_FUNC(PyCodeObject *) PyNode_Compile(struct _node *, const char *);
+/* XXX (ncoghlan): Unprefixed type name in a public API! */
+
+#define PyCF_MASK (CO_FUTURE_DIVISION | CO_FUTURE_ABSOLUTE_IMPORT | \
+ CO_FUTURE_WITH_STATEMENT | CO_FUTURE_PRINT_FUNCTION | \
+ CO_FUTURE_UNICODE_LITERALS | CO_FUTURE_BARRY_AS_BDFL | \
+ CO_FUTURE_GENERATOR_STOP | CO_FUTURE_ANNOTATIONS)
+#define PyCF_MASK_OBSOLETE (CO_NESTED)
+#define PyCF_SOURCE_IS_UTF8 0x0100
+#define PyCF_DONT_IMPLY_DEDENT 0x0200
+#define PyCF_ONLY_AST 0x0400
+#define PyCF_IGNORE_COOKIE 0x0800
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ int cf_flags; /* bitmask of CO_xxx flags relevant to future */
+} PyCompilerFlags;
+#endif
+
+/* Future feature support */
+
+typedef struct {
+ int ff_features; /* flags set by future statements */
+ int ff_lineno; /* line number of last future statement */
+} PyFutureFeatures;
+
+#define FUTURE_NESTED_SCOPES "nested_scopes"
+#define FUTURE_GENERATORS "generators"
+#define FUTURE_DIVISION "division"
+#define FUTURE_ABSOLUTE_IMPORT "absolute_import"
+#define FUTURE_WITH_STATEMENT "with_statement"
+#define FUTURE_PRINT_FUNCTION "print_function"
+#define FUTURE_UNICODE_LITERALS "unicode_literals"
+#define FUTURE_BARRY_AS_BDFL "barry_as_FLUFL"
+#define FUTURE_GENERATOR_STOP "generator_stop"
+#define FUTURE_ANNOTATIONS "annotations"
+
+struct _mod; /* Declare the existence of this type */
+#define PyAST_Compile(mod, s, f, ar) PyAST_CompileEx(mod, s, f, -1, ar)
+PyAPI_FUNC(PyCodeObject *) PyAST_CompileEx(
+ struct _mod *mod,
+ const char *filename, /* decoded from the filesystem encoding */
+ PyCompilerFlags *flags,
+ int optimize,
+ PyArena *arena);
+PyAPI_FUNC(PyCodeObject *) PyAST_CompileObject(
+ struct _mod *mod,
+ PyObject *filename,
+ PyCompilerFlags *flags,
+ int optimize,
+ PyArena *arena);
+PyAPI_FUNC(PyFutureFeatures *) PyFuture_FromAST(
+ struct _mod * mod,
+ const char *filename /* decoded from the filesystem encoding */
+ );
+PyAPI_FUNC(PyFutureFeatures *) PyFuture_FromASTObject(
+ struct _mod * mod,
+ PyObject *filename
+ );
+
+/* _Py_Mangle is defined in compile.c */
+PyAPI_FUNC(PyObject*) _Py_Mangle(PyObject *p, PyObject *name);
+
+#define PY_INVALID_STACK_EFFECT INT_MAX
+PyAPI_FUNC(int) PyCompile_OpcodeStackEffect(int opcode, int oparg);
+
+PyAPI_FUNC(int) _PyAST_Optimize(struct _mod *, PyArena *arena, int optimize);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_LIMITED_API */
+
+/* These definitions must match corresponding definitions in graminit.h.
+ There's code in compile.c that checks that they are the same. */
+#define Py_single_input 256
+#define Py_file_input 257
+#define Py_eval_input 258
+
+#endif /* !Py_COMPILE_H */
diff --git a/Include/complexobject.h b/Include/complexobject.h
new file mode 100644
index 0000000..cb8c52c
--- /dev/null
+++ b/Include/complexobject.h
@@ -0,0 +1,69 @@
+/* Complex number structure */
+
+#ifndef Py_COMPLEXOBJECT_H
+#define Py_COMPLEXOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ double real;
+ double imag;
+} Py_complex;
+
+/* Operations on complex numbers from complexmodule.c */
+
+PyAPI_FUNC(Py_complex) _Py_c_sum(Py_complex, Py_complex);
+PyAPI_FUNC(Py_complex) _Py_c_diff(Py_complex, Py_complex);
+PyAPI_FUNC(Py_complex) _Py_c_neg(Py_complex);
+PyAPI_FUNC(Py_complex) _Py_c_prod(Py_complex, Py_complex);
+PyAPI_FUNC(Py_complex) _Py_c_quot(Py_complex, Py_complex);
+PyAPI_FUNC(Py_complex) _Py_c_pow(Py_complex, Py_complex);
+PyAPI_FUNC(double) _Py_c_abs(Py_complex);
+#endif
+
+/* Complex object interface */
+
+/*
+PyComplexObject represents a complex number with double-precision
+real and imaginary parts.
+*/
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_HEAD
+ Py_complex cval;
+} PyComplexObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PyComplex_Type;
+
+#define PyComplex_Check(op) PyObject_TypeCheck(op, &PyComplex_Type)
+#define PyComplex_CheckExact(op) (Py_TYPE(op) == &PyComplex_Type)
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyComplex_FromCComplex(Py_complex);
+#endif
+PyAPI_FUNC(PyObject *) PyComplex_FromDoubles(double real, double imag);
+
+PyAPI_FUNC(double) PyComplex_RealAsDouble(PyObject *op);
+PyAPI_FUNC(double) PyComplex_ImagAsDouble(PyObject *op);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_complex) PyComplex_AsCComplex(PyObject *op);
+#endif
+
+/* Format the object based on the format_spec, as defined in PEP 3101
+ (Advanced String Formatting). */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyComplex_FormatAdvancedWriter(
+ _PyUnicodeWriter *writer,
+ PyObject *obj,
+ PyObject *format_spec,
+ Py_ssize_t start,
+ Py_ssize_t end);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_COMPLEXOBJECT_H */
diff --git a/Include/context.h b/Include/context.h
new file mode 100644
index 0000000..8b9f129
--- /dev/null
+++ b/Include/context.h
@@ -0,0 +1,86 @@
+#ifndef Py_CONTEXT_H
+#define Py_CONTEXT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+
+
+PyAPI_DATA(PyTypeObject) PyContext_Type;
+typedef struct _pycontextobject PyContext;
+
+PyAPI_DATA(PyTypeObject) PyContextVar_Type;
+typedef struct _pycontextvarobject PyContextVar;
+
+PyAPI_DATA(PyTypeObject) PyContextToken_Type;
+typedef struct _pycontexttokenobject PyContextToken;
+
+
+#define PyContext_CheckExact(o) (Py_TYPE(o) == &PyContext_Type)
+#define PyContextVar_CheckExact(o) (Py_TYPE(o) == &PyContextVar_Type)
+#define PyContextToken_CheckExact(o) (Py_TYPE(o) == &PyContextToken_Type)
+
+
+PyAPI_FUNC(PyContext *) PyContext_New(void);
+PyAPI_FUNC(PyContext *) PyContext_Copy(PyContext *);
+PyAPI_FUNC(PyContext *) PyContext_CopyCurrent(void);
+
+PyAPI_FUNC(int) PyContext_Enter(PyContext *);
+PyAPI_FUNC(int) PyContext_Exit(PyContext *);
+
+
+/* Create a new context variable.
+
+ default_value can be NULL.
+*/
+PyAPI_FUNC(PyContextVar *) PyContextVar_New(
+ const char *name, PyObject *default_value);
+
+
+/* Get a value for the variable.
+
+ Returns -1 if an error occurred during lookup.
+
+ Returns 0 if value either was or was not found.
+
+ If value was found, *value will point to it.
+ If not, it will point to:
+
+ - default_value, if not NULL;
+ - the default value of "var", if not NULL;
+ - NULL.
+
+ '*value' will be a new ref, if not NULL.
+*/
+PyAPI_FUNC(int) PyContextVar_Get(
+ PyContextVar *var, PyObject *default_value, PyObject **value);
+
+
+/* Set a new value for the variable.
+ Returns NULL if an error occurs.
+*/
+PyAPI_FUNC(PyContextToken *) PyContextVar_Set(
+ PyContextVar *var, PyObject *value);
+
+
+/* Reset a variable to its previous value.
+ Returns 0 on success, -1 on error.
+*/
+PyAPI_FUNC(int) PyContextVar_Reset(
+ PyContextVar *var, PyContextToken *token);
+
+
+/* This method is exposed only for CPython tests. Don not use it. */
+PyAPI_FUNC(PyObject *) _PyContext_NewHamtForTests(void);
+
+
+PyAPI_FUNC(int) PyContext_ClearFreeList(void);
+
+
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_CONTEXT_H */
diff --git a/Include/datetime.h b/Include/datetime.h
new file mode 100644
index 0000000..059d5ec
--- /dev/null
+++ b/Include/datetime.h
@@ -0,0 +1,273 @@
+/* datetime.h
+ */
+#ifndef Py_LIMITED_API
+#ifndef DATETIME_H
+#define DATETIME_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Fields are packed into successive bytes, each viewed as unsigned and
+ * big-endian, unless otherwise noted:
+ *
+ * byte offset
+ * 0 year 2 bytes, 1-9999
+ * 2 month 1 byte, 1-12
+ * 3 day 1 byte, 1-31
+ * 4 hour 1 byte, 0-23
+ * 5 minute 1 byte, 0-59
+ * 6 second 1 byte, 0-59
+ * 7 usecond 3 bytes, 0-999999
+ * 10
+ */
+
+/* # of bytes for year, month, and day. */
+#define _PyDateTime_DATE_DATASIZE 4
+
+/* # of bytes for hour, minute, second, and usecond. */
+#define _PyDateTime_TIME_DATASIZE 6
+
+/* # of bytes for year, month, day, hour, minute, second, and usecond. */
+#define _PyDateTime_DATETIME_DATASIZE 10
+
+
+typedef struct
+{
+ PyObject_HEAD
+ Py_hash_t hashcode; /* -1 when unknown */
+ int days; /* -MAX_DELTA_DAYS <= days <= MAX_DELTA_DAYS */
+ int seconds; /* 0 <= seconds < 24*3600 is invariant */
+ int microseconds; /* 0 <= microseconds < 1000000 is invariant */
+} PyDateTime_Delta;
+
+typedef struct
+{
+ PyObject_HEAD /* a pure abstract base class */
+} PyDateTime_TZInfo;
+
+
+/* The datetime and time types have hashcodes, and an optional tzinfo member,
+ * present if and only if hastzinfo is true.
+ */
+#define _PyTZINFO_HEAD \
+ PyObject_HEAD \
+ Py_hash_t hashcode; \
+ char hastzinfo; /* boolean flag */
+
+/* No _PyDateTime_BaseTZInfo is allocated; it's just to have something
+ * convenient to cast to, when getting at the hastzinfo member of objects
+ * starting with _PyTZINFO_HEAD.
+ */
+typedef struct
+{
+ _PyTZINFO_HEAD
+} _PyDateTime_BaseTZInfo;
+
+/* All time objects are of PyDateTime_TimeType, but that can be allocated
+ * in two ways, with or without a tzinfo member. Without is the same as
+ * tzinfo == None, but consumes less memory. _PyDateTime_BaseTime is an
+ * internal struct used to allocate the right amount of space for the
+ * "without" case.
+ */
+#define _PyDateTime_TIMEHEAD \
+ _PyTZINFO_HEAD \
+ unsigned char data[_PyDateTime_TIME_DATASIZE];
+
+typedef struct
+{
+ _PyDateTime_TIMEHEAD
+} _PyDateTime_BaseTime; /* hastzinfo false */
+
+typedef struct
+{
+ _PyDateTime_TIMEHEAD
+ unsigned char fold;
+ PyObject *tzinfo;
+} PyDateTime_Time; /* hastzinfo true */
+
+
+/* All datetime objects are of PyDateTime_DateTimeType, but that can be
+ * allocated in two ways too, just like for time objects above. In addition,
+ * the plain date type is a base class for datetime, so it must also have
+ * a hastzinfo member (although it's unused there).
+ */
+typedef struct
+{
+ _PyTZINFO_HEAD
+ unsigned char data[_PyDateTime_DATE_DATASIZE];
+} PyDateTime_Date;
+
+#define _PyDateTime_DATETIMEHEAD \
+ _PyTZINFO_HEAD \
+ unsigned char data[_PyDateTime_DATETIME_DATASIZE];
+
+typedef struct
+{
+ _PyDateTime_DATETIMEHEAD
+} _PyDateTime_BaseDateTime; /* hastzinfo false */
+
+typedef struct
+{
+ _PyDateTime_DATETIMEHEAD
+ unsigned char fold;
+ PyObject *tzinfo;
+} PyDateTime_DateTime; /* hastzinfo true */
+
+
+/* Apply for date and datetime instances. */
+#define PyDateTime_GET_YEAR(o) ((((PyDateTime_Date*)o)->data[0] << 8) | \
+ ((PyDateTime_Date*)o)->data[1])
+#define PyDateTime_GET_MONTH(o) (((PyDateTime_Date*)o)->data[2])
+#define PyDateTime_GET_DAY(o) (((PyDateTime_Date*)o)->data[3])
+
+#define PyDateTime_DATE_GET_HOUR(o) (((PyDateTime_DateTime*)o)->data[4])
+#define PyDateTime_DATE_GET_MINUTE(o) (((PyDateTime_DateTime*)o)->data[5])
+#define PyDateTime_DATE_GET_SECOND(o) (((PyDateTime_DateTime*)o)->data[6])
+#define PyDateTime_DATE_GET_MICROSECOND(o) \
+ ((((PyDateTime_DateTime*)o)->data[7] << 16) | \
+ (((PyDateTime_DateTime*)o)->data[8] << 8) | \
+ ((PyDateTime_DateTime*)o)->data[9])
+#define PyDateTime_DATE_GET_FOLD(o) (((PyDateTime_DateTime*)o)->fold)
+
+/* Apply for time instances. */
+#define PyDateTime_TIME_GET_HOUR(o) (((PyDateTime_Time*)o)->data[0])
+#define PyDateTime_TIME_GET_MINUTE(o) (((PyDateTime_Time*)o)->data[1])
+#define PyDateTime_TIME_GET_SECOND(o) (((PyDateTime_Time*)o)->data[2])
+#define PyDateTime_TIME_GET_MICROSECOND(o) \
+ ((((PyDateTime_Time*)o)->data[3] << 16) | \
+ (((PyDateTime_Time*)o)->data[4] << 8) | \
+ ((PyDateTime_Time*)o)->data[5])
+#define PyDateTime_TIME_GET_FOLD(o) (((PyDateTime_Time*)o)->fold)
+
+/* Apply for time delta instances */
+#define PyDateTime_DELTA_GET_DAYS(o) (((PyDateTime_Delta*)o)->days)
+#define PyDateTime_DELTA_GET_SECONDS(o) (((PyDateTime_Delta*)o)->seconds)
+#define PyDateTime_DELTA_GET_MICROSECONDS(o) \
+ (((PyDateTime_Delta*)o)->microseconds)
+
+
+/* Define structure for C API. */
+typedef struct {
+ /* type objects */
+ PyTypeObject *DateType;
+ PyTypeObject *DateTimeType;
+ PyTypeObject *TimeType;
+ PyTypeObject *DeltaType;
+ PyTypeObject *TZInfoType;
+
+ /* singletons */
+ PyObject *TimeZone_UTC;
+
+ /* constructors */
+ PyObject *(*Date_FromDate)(int, int, int, PyTypeObject*);
+ PyObject *(*DateTime_FromDateAndTime)(int, int, int, int, int, int, int,
+ PyObject*, PyTypeObject*);
+ PyObject *(*Time_FromTime)(int, int, int, int, PyObject*, PyTypeObject*);
+ PyObject *(*Delta_FromDelta)(int, int, int, int, PyTypeObject*);
+ PyObject *(*TimeZone_FromTimeZone)(PyObject *offset, PyObject *name);
+
+ /* constructors for the DB API */
+ PyObject *(*DateTime_FromTimestamp)(PyObject*, PyObject*, PyObject*);
+ PyObject *(*Date_FromTimestamp)(PyObject*, PyObject*);
+
+ /* PEP 495 constructors */
+ PyObject *(*DateTime_FromDateAndTimeAndFold)(int, int, int, int, int, int, int,
+ PyObject*, int, PyTypeObject*);
+ PyObject *(*Time_FromTimeAndFold)(int, int, int, int, PyObject*, int, PyTypeObject*);
+
+} PyDateTime_CAPI;
+
+#define PyDateTime_CAPSULE_NAME "datetime.datetime_CAPI"
+
+
+#ifdef Py_BUILD_CORE
+
+/* Macros for type checking when building the Python core. */
+#define PyDate_Check(op) PyObject_TypeCheck(op, &PyDateTime_DateType)
+#define PyDate_CheckExact(op) (Py_TYPE(op) == &PyDateTime_DateType)
+
+#define PyDateTime_Check(op) PyObject_TypeCheck(op, &PyDateTime_DateTimeType)
+#define PyDateTime_CheckExact(op) (Py_TYPE(op) == &PyDateTime_DateTimeType)
+
+#define PyTime_Check(op) PyObject_TypeCheck(op, &PyDateTime_TimeType)
+#define PyTime_CheckExact(op) (Py_TYPE(op) == &PyDateTime_TimeType)
+
+#define PyDelta_Check(op) PyObject_TypeCheck(op, &PyDateTime_DeltaType)
+#define PyDelta_CheckExact(op) (Py_TYPE(op) == &PyDateTime_DeltaType)
+
+#define PyTZInfo_Check(op) PyObject_TypeCheck(op, &PyDateTime_TZInfoType)
+#define PyTZInfo_CheckExact(op) (Py_TYPE(op) == &PyDateTime_TZInfoType)
+
+#else
+
+/* Define global variable for the C API and a macro for setting it. */
+static PyDateTime_CAPI *PyDateTimeAPI = NULL;
+
+#define PyDateTime_IMPORT \
+ PyDateTimeAPI = (PyDateTime_CAPI *)PyCapsule_Import(PyDateTime_CAPSULE_NAME, 0)
+
+/* Macro for access to the UTC singleton */
+#define PyDateTime_TimeZone_UTC PyDateTimeAPI->TimeZone_UTC
+
+/* Macros for type checking when not building the Python core. */
+#define PyDate_Check(op) PyObject_TypeCheck(op, PyDateTimeAPI->DateType)
+#define PyDate_CheckExact(op) (Py_TYPE(op) == PyDateTimeAPI->DateType)
+
+#define PyDateTime_Check(op) PyObject_TypeCheck(op, PyDateTimeAPI->DateTimeType)
+#define PyDateTime_CheckExact(op) (Py_TYPE(op) == PyDateTimeAPI->DateTimeType)
+
+#define PyTime_Check(op) PyObject_TypeCheck(op, PyDateTimeAPI->TimeType)
+#define PyTime_CheckExact(op) (Py_TYPE(op) == PyDateTimeAPI->TimeType)
+
+#define PyDelta_Check(op) PyObject_TypeCheck(op, PyDateTimeAPI->DeltaType)
+#define PyDelta_CheckExact(op) (Py_TYPE(op) == PyDateTimeAPI->DeltaType)
+
+#define PyTZInfo_Check(op) PyObject_TypeCheck(op, PyDateTimeAPI->TZInfoType)
+#define PyTZInfo_CheckExact(op) (Py_TYPE(op) == PyDateTimeAPI->TZInfoType)
+
+/* Macros for accessing constructors in a simplified fashion. */
+#define PyDate_FromDate(year, month, day) \
+ PyDateTimeAPI->Date_FromDate(year, month, day, PyDateTimeAPI->DateType)
+
+#define PyDateTime_FromDateAndTime(year, month, day, hour, min, sec, usec) \
+ PyDateTimeAPI->DateTime_FromDateAndTime(year, month, day, hour, \
+ min, sec, usec, Py_None, PyDateTimeAPI->DateTimeType)
+
+#define PyDateTime_FromDateAndTimeAndFold(year, month, day, hour, min, sec, usec, fold) \
+ PyDateTimeAPI->DateTime_FromDateAndTimeAndFold(year, month, day, hour, \
+ min, sec, usec, Py_None, fold, PyDateTimeAPI->DateTimeType)
+
+#define PyTime_FromTime(hour, minute, second, usecond) \
+ PyDateTimeAPI->Time_FromTime(hour, minute, second, usecond, \
+ Py_None, PyDateTimeAPI->TimeType)
+
+#define PyTime_FromTimeAndFold(hour, minute, second, usecond, fold) \
+ PyDateTimeAPI->Time_FromTimeAndFold(hour, minute, second, usecond, \
+ Py_None, fold, PyDateTimeAPI->TimeType)
+
+#define PyDelta_FromDSU(days, seconds, useconds) \
+ PyDateTimeAPI->Delta_FromDelta(days, seconds, useconds, 1, \
+ PyDateTimeAPI->DeltaType)
+
+#define PyTimeZone_FromOffset(offset) \
+ PyDateTimeAPI->TimeZone_FromTimeZone(offset, NULL)
+
+#define PyTimeZone_FromOffsetAndName(offset, name) \
+ PyDateTimeAPI->TimeZone_FromTimeZone(offset, name)
+
+/* Macros supporting the DB API. */
+#define PyDateTime_FromTimestamp(args) \
+ PyDateTimeAPI->DateTime_FromTimestamp( \
+ (PyObject*) (PyDateTimeAPI->DateTimeType), args, NULL)
+
+#define PyDate_FromTimestamp(args) \
+ PyDateTimeAPI->Date_FromTimestamp( \
+ (PyObject*) (PyDateTimeAPI->DateType), args)
+
+#endif /* Py_BUILD_CORE */
+
+#ifdef __cplusplus
+}
+#endif
+#endif
+#endif /* !Py_LIMITED_API */
diff --git a/Include/descrobject.h b/Include/descrobject.h
new file mode 100644
index 0000000..73bbb3f
--- /dev/null
+++ b/Include/descrobject.h
@@ -0,0 +1,110 @@
+/* Descriptors */
+#ifndef Py_DESCROBJECT_H
+#define Py_DESCROBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef PyObject *(*getter)(PyObject *, void *);
+typedef int (*setter)(PyObject *, PyObject *, void *);
+
+typedef struct PyGetSetDef {
+ const char *name;
+ getter get;
+ setter set;
+ const char *doc;
+ void *closure;
+} PyGetSetDef;
+
+#ifndef Py_LIMITED_API
+typedef PyObject *(*wrapperfunc)(PyObject *self, PyObject *args,
+ void *wrapped);
+
+typedef PyObject *(*wrapperfunc_kwds)(PyObject *self, PyObject *args,
+ void *wrapped, PyObject *kwds);
+
+struct wrapperbase {
+ const char *name;
+ int offset;
+ void *function;
+ wrapperfunc wrapper;
+ const char *doc;
+ int flags;
+ PyObject *name_strobj;
+};
+
+/* Flags for above struct */
+#define PyWrapperFlag_KEYWORDS 1 /* wrapper function takes keyword args */
+
+/* Various kinds of descriptor objects */
+
+typedef struct {
+ PyObject_HEAD
+ PyTypeObject *d_type;
+ PyObject *d_name;
+ PyObject *d_qualname;
+} PyDescrObject;
+
+#define PyDescr_COMMON PyDescrObject d_common
+
+#define PyDescr_TYPE(x) (((PyDescrObject *)(x))->d_type)
+#define PyDescr_NAME(x) (((PyDescrObject *)(x))->d_name)
+
+typedef struct {
+ PyDescr_COMMON;
+ PyMethodDef *d_method;
+} PyMethodDescrObject;
+
+typedef struct {
+ PyDescr_COMMON;
+ struct PyMemberDef *d_member;
+} PyMemberDescrObject;
+
+typedef struct {
+ PyDescr_COMMON;
+ PyGetSetDef *d_getset;
+} PyGetSetDescrObject;
+
+typedef struct {
+ PyDescr_COMMON;
+ struct wrapperbase *d_base;
+ void *d_wrapped; /* This can be any function pointer */
+} PyWrapperDescrObject;
+#endif /* Py_LIMITED_API */
+
+PyAPI_DATA(PyTypeObject) PyClassMethodDescr_Type;
+PyAPI_DATA(PyTypeObject) PyGetSetDescr_Type;
+PyAPI_DATA(PyTypeObject) PyMemberDescr_Type;
+PyAPI_DATA(PyTypeObject) PyMethodDescr_Type;
+PyAPI_DATA(PyTypeObject) PyWrapperDescr_Type;
+PyAPI_DATA(PyTypeObject) PyDictProxy_Type;
+#ifndef Py_LIMITED_API
+PyAPI_DATA(PyTypeObject) _PyMethodWrapper_Type;
+#endif /* Py_LIMITED_API */
+
+PyAPI_FUNC(PyObject *) PyDescr_NewMethod(PyTypeObject *, PyMethodDef *);
+PyAPI_FUNC(PyObject *) PyDescr_NewClassMethod(PyTypeObject *, PyMethodDef *);
+struct PyMemberDef; /* forward declaration for following prototype */
+PyAPI_FUNC(PyObject *) PyDescr_NewMember(PyTypeObject *,
+ struct PyMemberDef *);
+PyAPI_FUNC(PyObject *) PyDescr_NewGetSet(PyTypeObject *,
+ struct PyGetSetDef *);
+#ifndef Py_LIMITED_API
+
+PyAPI_FUNC(PyObject *) _PyMethodDescr_FastCallKeywords(
+ PyObject *descrobj, PyObject *const *stack, Py_ssize_t nargs, PyObject *kwnames);
+PyAPI_FUNC(PyObject *) PyDescr_NewWrapper(PyTypeObject *,
+ struct wrapperbase *, void *);
+#define PyDescr_IsData(d) (Py_TYPE(d)->tp_descr_set != NULL)
+#endif
+
+PyAPI_FUNC(PyObject *) PyDictProxy_New(PyObject *);
+PyAPI_FUNC(PyObject *) PyWrapper_New(PyObject *, PyObject *);
+
+
+PyAPI_DATA(PyTypeObject) PyProperty_Type;
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_DESCROBJECT_H */
+
diff --git a/Include/dictobject.h b/Include/dictobject.h
new file mode 100644
index 0000000..28930f4
--- /dev/null
+++ b/Include/dictobject.h
@@ -0,0 +1,179 @@
+#ifndef Py_DICTOBJECT_H
+#define Py_DICTOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Dictionary object type -- mapping from hashable object to object */
+
+/* The distribution includes a separate file, Objects/dictnotes.txt,
+ describing explorations into dictionary design and optimization.
+ It covers typical dictionary use patterns, the parameters for
+ tuning dictionaries, and several ideas for possible optimizations.
+*/
+
+#ifndef Py_LIMITED_API
+
+typedef struct _dictkeysobject PyDictKeysObject;
+
+/* The ma_values pointer is NULL for a combined table
+ * or points to an array of PyObject* for a split table
+ */
+typedef struct {
+ PyObject_HEAD
+
+ /* Number of items in the dictionary */
+ Py_ssize_t ma_used;
+
+ /* Dictionary version: globally unique, value change each time
+ the dictionary is modified */
+ uint64_t ma_version_tag;
+
+ PyDictKeysObject *ma_keys;
+
+ /* If ma_values is NULL, the table is "combined": keys and values
+ are stored in ma_keys.
+
+ If ma_values is not NULL, the table is splitted:
+ keys are stored in ma_keys and values are stored in ma_values */
+ PyObject **ma_values;
+} PyDictObject;
+
+typedef struct {
+ PyObject_HEAD
+ PyDictObject *dv_dict;
+} _PyDictViewObject;
+
+#endif /* Py_LIMITED_API */
+
+PyAPI_DATA(PyTypeObject) PyDict_Type;
+PyAPI_DATA(PyTypeObject) PyDictIterKey_Type;
+PyAPI_DATA(PyTypeObject) PyDictIterValue_Type;
+PyAPI_DATA(PyTypeObject) PyDictIterItem_Type;
+PyAPI_DATA(PyTypeObject) PyDictKeys_Type;
+PyAPI_DATA(PyTypeObject) PyDictItems_Type;
+PyAPI_DATA(PyTypeObject) PyDictValues_Type;
+
+#define PyDict_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_DICT_SUBCLASS)
+#define PyDict_CheckExact(op) (Py_TYPE(op) == &PyDict_Type)
+#define PyDictKeys_Check(op) PyObject_TypeCheck(op, &PyDictKeys_Type)
+#define PyDictItems_Check(op) PyObject_TypeCheck(op, &PyDictItems_Type)
+#define PyDictValues_Check(op) PyObject_TypeCheck(op, &PyDictValues_Type)
+/* This excludes Values, since they are not sets. */
+# define PyDictViewSet_Check(op) \
+ (PyDictKeys_Check(op) || PyDictItems_Check(op))
+
+
+PyAPI_FUNC(PyObject *) PyDict_New(void);
+PyAPI_FUNC(PyObject *) PyDict_GetItem(PyObject *mp, PyObject *key);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyDict_GetItem_KnownHash(PyObject *mp, PyObject *key,
+ Py_hash_t hash);
+#endif
+PyAPI_FUNC(PyObject *) PyDict_GetItemWithError(PyObject *mp, PyObject *key);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyDict_GetItemIdWithError(PyObject *dp,
+ struct _Py_Identifier *key);
+PyAPI_FUNC(PyObject *) PyDict_SetDefault(
+ PyObject *mp, PyObject *key, PyObject *defaultobj);
+#endif
+PyAPI_FUNC(int) PyDict_SetItem(PyObject *mp, PyObject *key, PyObject *item);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyDict_SetItem_KnownHash(PyObject *mp, PyObject *key,
+ PyObject *item, Py_hash_t hash);
+#endif
+PyAPI_FUNC(int) PyDict_DelItem(PyObject *mp, PyObject *key);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyDict_DelItem_KnownHash(PyObject *mp, PyObject *key,
+ Py_hash_t hash);
+PyAPI_FUNC(int) _PyDict_DelItemIf(PyObject *mp, PyObject *key,
+ int (*predicate)(PyObject *value));
+#endif
+PyAPI_FUNC(void) PyDict_Clear(PyObject *mp);
+PyAPI_FUNC(int) PyDict_Next(
+ PyObject *mp, Py_ssize_t *pos, PyObject **key, PyObject **value);
+#ifndef Py_LIMITED_API
+PyDictKeysObject *_PyDict_NewKeysForClass(void);
+PyAPI_FUNC(PyObject *) PyObject_GenericGetDict(PyObject *, void *);
+PyAPI_FUNC(int) _PyDict_Next(
+ PyObject *mp, Py_ssize_t *pos, PyObject **key, PyObject **value, Py_hash_t *hash);
+PyObject *_PyDictView_New(PyObject *, PyTypeObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyDict_Keys(PyObject *mp);
+PyAPI_FUNC(PyObject *) PyDict_Values(PyObject *mp);
+PyAPI_FUNC(PyObject *) PyDict_Items(PyObject *mp);
+PyAPI_FUNC(Py_ssize_t) PyDict_Size(PyObject *mp);
+PyAPI_FUNC(PyObject *) PyDict_Copy(PyObject *mp);
+PyAPI_FUNC(int) PyDict_Contains(PyObject *mp, PyObject *key);
+#ifndef Py_LIMITED_API
+/* Get the number of items of a dictionary. */
+#define PyDict_GET_SIZE(mp) (assert(PyDict_Check(mp)),((PyDictObject *)mp)->ma_used)
+PyAPI_FUNC(int) _PyDict_Contains(PyObject *mp, PyObject *key, Py_hash_t hash);
+PyAPI_FUNC(PyObject *) _PyDict_NewPresized(Py_ssize_t minused);
+PyAPI_FUNC(void) _PyDict_MaybeUntrack(PyObject *mp);
+PyAPI_FUNC(int) _PyDict_HasOnlyStringKeys(PyObject *mp);
+Py_ssize_t _PyDict_KeysSize(PyDictKeysObject *keys);
+PyAPI_FUNC(Py_ssize_t) _PyDict_SizeOf(PyDictObject *);
+PyAPI_FUNC(PyObject *) _PyDict_Pop(PyObject *, PyObject *, PyObject *);
+PyObject *_PyDict_Pop_KnownHash(PyObject *, PyObject *, Py_hash_t, PyObject *);
+PyObject *_PyDict_FromKeys(PyObject *, PyObject *, PyObject *);
+#define _PyDict_HasSplitTable(d) ((d)->ma_values != NULL)
+
+PyAPI_FUNC(int) PyDict_ClearFreeList(void);
+#endif
+
+/* PyDict_Update(mp, other) is equivalent to PyDict_Merge(mp, other, 1). */
+PyAPI_FUNC(int) PyDict_Update(PyObject *mp, PyObject *other);
+
+/* PyDict_Merge updates/merges from a mapping object (an object that
+ supports PyMapping_Keys() and PyObject_GetItem()). If override is true,
+ the last occurrence of a key wins, else the first. The Python
+ dict.update(other) is equivalent to PyDict_Merge(dict, other, 1).
+*/
+PyAPI_FUNC(int) PyDict_Merge(PyObject *mp,
+ PyObject *other,
+ int override);
+
+#ifndef Py_LIMITED_API
+/* Like PyDict_Merge, but override can be 0, 1 or 2. If override is 0,
+ the first occurrence of a key wins, if override is 1, the last occurrence
+ of a key wins, if override is 2, a KeyError with conflicting key as
+ argument is raised.
+*/
+PyAPI_FUNC(int) _PyDict_MergeEx(PyObject *mp, PyObject *other, int override);
+PyAPI_FUNC(PyObject *) _PyDictView_Intersect(PyObject* self, PyObject *other);
+#endif
+
+/* PyDict_MergeFromSeq2 updates/merges from an iterable object producing
+ iterable objects of length 2. If override is true, the last occurrence
+ of a key wins, else the first. The Python dict constructor dict(seq2)
+ is equivalent to dict={}; PyDict_MergeFromSeq(dict, seq2, 1).
+*/
+PyAPI_FUNC(int) PyDict_MergeFromSeq2(PyObject *d,
+ PyObject *seq2,
+ int override);
+
+PyAPI_FUNC(PyObject *) PyDict_GetItemString(PyObject *dp, const char *key);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyDict_GetItemId(PyObject *dp, struct _Py_Identifier *key);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(int) PyDict_SetItemString(PyObject *dp, const char *key, PyObject *item);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyDict_SetItemId(PyObject *dp, struct _Py_Identifier *key, PyObject *item);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(int) PyDict_DelItemString(PyObject *dp, const char *key);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyDict_DelItemId(PyObject *mp, struct _Py_Identifier *key);
+PyAPI_FUNC(void) _PyDict_DebugMallocStats(FILE *out);
+
+int _PyObjectDict_SetItem(PyTypeObject *tp, PyObject **dictptr, PyObject *name, PyObject *value);
+PyObject *_PyDict_LoadGlobal(PyDictObject *, PyDictObject *, PyObject *);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_DICTOBJECT_H */
diff --git a/Include/dtoa.h b/Include/dtoa.h
new file mode 100644
index 0000000..9bfb625
--- /dev/null
+++ b/Include/dtoa.h
@@ -0,0 +1,19 @@
+#ifndef Py_LIMITED_API
+#ifndef PY_NO_SHORT_FLOAT_REPR
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(double) _Py_dg_strtod(const char *str, char **ptr);
+PyAPI_FUNC(char *) _Py_dg_dtoa(double d, int mode, int ndigits,
+ int *decpt, int *sign, char **rve);
+PyAPI_FUNC(void) _Py_dg_freedtoa(char *s);
+PyAPI_FUNC(double) _Py_dg_stdnan(int sign);
+PyAPI_FUNC(double) _Py_dg_infinity(int sign);
+
+
+#ifdef __cplusplus
+}
+#endif
+#endif
+#endif
diff --git a/Include/dynamic_annotations.h b/Include/dynamic_annotations.h
new file mode 100644
index 0000000..0bd1a83
--- /dev/null
+++ b/Include/dynamic_annotations.h
@@ -0,0 +1,499 @@
+/* Copyright (c) 2008-2009, Google Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Neither the name of Google Inc. nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * ---
+ * Author: Kostya Serebryany
+ * Copied to CPython by Jeffrey Yasskin, with all macros renamed to
+ * start with _Py_ to avoid colliding with users embedding Python, and
+ * with deprecated macros removed.
+ */
+
+/* This file defines dynamic annotations for use with dynamic analysis
+ tool such as valgrind, PIN, etc.
+
+ Dynamic annotation is a source code annotation that affects
+ the generated code (that is, the annotation is not a comment).
+ Each such annotation is attached to a particular
+ instruction and/or to a particular object (address) in the program.
+
+ The annotations that should be used by users are macros in all upper-case
+ (e.g., _Py_ANNOTATE_NEW_MEMORY).
+
+ Actual implementation of these macros may differ depending on the
+ dynamic analysis tool being used.
+
+ See http://code.google.com/p/data-race-test/ for more information.
+
+ This file supports the following dynamic analysis tools:
+ - None (DYNAMIC_ANNOTATIONS_ENABLED is not defined or zero).
+ Macros are defined empty.
+ - ThreadSanitizer, Helgrind, DRD (DYNAMIC_ANNOTATIONS_ENABLED is 1).
+ Macros are defined as calls to non-inlinable empty functions
+ that are intercepted by Valgrind. */
+
+#ifndef __DYNAMIC_ANNOTATIONS_H__
+#define __DYNAMIC_ANNOTATIONS_H__
+
+#ifndef DYNAMIC_ANNOTATIONS_ENABLED
+# define DYNAMIC_ANNOTATIONS_ENABLED 0
+#endif
+
+#if DYNAMIC_ANNOTATIONS_ENABLED != 0
+
+ /* -------------------------------------------------------------
+ Annotations useful when implementing condition variables such as CondVar,
+ using conditional critical sections (Await/LockWhen) and when constructing
+ user-defined synchronization mechanisms.
+
+ The annotations _Py_ANNOTATE_HAPPENS_BEFORE() and
+ _Py_ANNOTATE_HAPPENS_AFTER() can be used to define happens-before arcs in
+ user-defined synchronization mechanisms: the race detector will infer an
+ arc from the former to the latter when they share the same argument
+ pointer.
+
+ Example 1 (reference counting):
+
+ void Unref() {
+ _Py_ANNOTATE_HAPPENS_BEFORE(&refcount_);
+ if (AtomicDecrementByOne(&refcount_) == 0) {
+ _Py_ANNOTATE_HAPPENS_AFTER(&refcount_);
+ delete this;
+ }
+ }
+
+ Example 2 (message queue):
+
+ void MyQueue::Put(Type *e) {
+ MutexLock lock(&mu_);
+ _Py_ANNOTATE_HAPPENS_BEFORE(e);
+ PutElementIntoMyQueue(e);
+ }
+
+ Type *MyQueue::Get() {
+ MutexLock lock(&mu_);
+ Type *e = GetElementFromMyQueue();
+ _Py_ANNOTATE_HAPPENS_AFTER(e);
+ return e;
+ }
+
+ Note: when possible, please use the existing reference counting and message
+ queue implementations instead of inventing new ones. */
+
+ /* Report that wait on the condition variable at address "cv" has succeeded
+ and the lock at address "lock" is held. */
+#define _Py_ANNOTATE_CONDVAR_LOCK_WAIT(cv, lock) \
+ AnnotateCondVarWait(__FILE__, __LINE__, cv, lock)
+
+ /* Report that wait on the condition variable at "cv" has succeeded. Variant
+ w/o lock. */
+#define _Py_ANNOTATE_CONDVAR_WAIT(cv) \
+ AnnotateCondVarWait(__FILE__, __LINE__, cv, NULL)
+
+ /* Report that we are about to signal on the condition variable at address
+ "cv". */
+#define _Py_ANNOTATE_CONDVAR_SIGNAL(cv) \
+ AnnotateCondVarSignal(__FILE__, __LINE__, cv)
+
+ /* Report that we are about to signal_all on the condition variable at "cv". */
+#define _Py_ANNOTATE_CONDVAR_SIGNAL_ALL(cv) \
+ AnnotateCondVarSignalAll(__FILE__, __LINE__, cv)
+
+ /* Annotations for user-defined synchronization mechanisms. */
+#define _Py_ANNOTATE_HAPPENS_BEFORE(obj) _Py_ANNOTATE_CONDVAR_SIGNAL(obj)
+#define _Py_ANNOTATE_HAPPENS_AFTER(obj) _Py_ANNOTATE_CONDVAR_WAIT(obj)
+
+ /* Report that the bytes in the range [pointer, pointer+size) are about
+ to be published safely. The race checker will create a happens-before
+ arc from the call _Py_ANNOTATE_PUBLISH_MEMORY_RANGE(pointer, size) to
+ subsequent accesses to this memory.
+ Note: this annotation may not work properly if the race detector uses
+ sampling, i.e. does not observe all memory accesses.
+ */
+#define _Py_ANNOTATE_PUBLISH_MEMORY_RANGE(pointer, size) \
+ AnnotatePublishMemoryRange(__FILE__, __LINE__, pointer, size)
+
+ /* Instruct the tool to create a happens-before arc between mu->Unlock() and
+ mu->Lock(). This annotation may slow down the race detector and hide real
+ races. Normally it is used only when it would be difficult to annotate each
+ of the mutex's critical sections individually using the annotations above.
+ This annotation makes sense only for hybrid race detectors. For pure
+ happens-before detectors this is a no-op. For more details see
+ http://code.google.com/p/data-race-test/wiki/PureHappensBeforeVsHybrid . */
+#define _Py_ANNOTATE_PURE_HAPPENS_BEFORE_MUTEX(mu) \
+ AnnotateMutexIsUsedAsCondVar(__FILE__, __LINE__, mu)
+
+ /* -------------------------------------------------------------
+ Annotations useful when defining memory allocators, or when memory that
+ was protected in one way starts to be protected in another. */
+
+ /* Report that a new memory at "address" of size "size" has been allocated.
+ This might be used when the memory has been retrieved from a free list and
+ is about to be reused, or when the locking discipline for a variable
+ changes. */
+#define _Py_ANNOTATE_NEW_MEMORY(address, size) \
+ AnnotateNewMemory(__FILE__, __LINE__, address, size)
+
+ /* -------------------------------------------------------------
+ Annotations useful when defining FIFO queues that transfer data between
+ threads. */
+
+ /* Report that the producer-consumer queue (such as ProducerConsumerQueue) at
+ address "pcq" has been created. The _Py_ANNOTATE_PCQ_* annotations should
+ be used only for FIFO queues. For non-FIFO queues use
+ _Py_ANNOTATE_HAPPENS_BEFORE (for put) and _Py_ANNOTATE_HAPPENS_AFTER (for
+ get). */
+#define _Py_ANNOTATE_PCQ_CREATE(pcq) \
+ AnnotatePCQCreate(__FILE__, __LINE__, pcq)
+
+ /* Report that the queue at address "pcq" is about to be destroyed. */
+#define _Py_ANNOTATE_PCQ_DESTROY(pcq) \
+ AnnotatePCQDestroy(__FILE__, __LINE__, pcq)
+
+ /* Report that we are about to put an element into a FIFO queue at address
+ "pcq". */
+#define _Py_ANNOTATE_PCQ_PUT(pcq) \
+ AnnotatePCQPut(__FILE__, __LINE__, pcq)
+
+ /* Report that we've just got an element from a FIFO queue at address "pcq". */
+#define _Py_ANNOTATE_PCQ_GET(pcq) \
+ AnnotatePCQGet(__FILE__, __LINE__, pcq)
+
+ /* -------------------------------------------------------------
+ Annotations that suppress errors. It is usually better to express the
+ program's synchronization using the other annotations, but these can
+ be used when all else fails. */
+
+ /* Report that we may have a benign race at "pointer", with size
+ "sizeof(*(pointer))". "pointer" must be a non-void* pointer. Insert at the
+ point where "pointer" has been allocated, preferably close to the point
+ where the race happens. See also _Py_ANNOTATE_BENIGN_RACE_STATIC. */
+#define _Py_ANNOTATE_BENIGN_RACE(pointer, description) \
+ AnnotateBenignRaceSized(__FILE__, __LINE__, pointer, \
+ sizeof(*(pointer)), description)
+
+ /* Same as _Py_ANNOTATE_BENIGN_RACE(address, description), but applies to
+ the memory range [address, address+size). */
+#define _Py_ANNOTATE_BENIGN_RACE_SIZED(address, size, description) \
+ AnnotateBenignRaceSized(__FILE__, __LINE__, address, size, description)
+
+ /* Request the analysis tool to ignore all reads in the current thread
+ until _Py_ANNOTATE_IGNORE_READS_END is called.
+ Useful to ignore intentional racey reads, while still checking
+ other reads and all writes.
+ See also _Py_ANNOTATE_UNPROTECTED_READ. */
+#define _Py_ANNOTATE_IGNORE_READS_BEGIN() \
+ AnnotateIgnoreReadsBegin(__FILE__, __LINE__)
+
+ /* Stop ignoring reads. */
+#define _Py_ANNOTATE_IGNORE_READS_END() \
+ AnnotateIgnoreReadsEnd(__FILE__, __LINE__)
+
+ /* Similar to _Py_ANNOTATE_IGNORE_READS_BEGIN, but ignore writes. */
+#define _Py_ANNOTATE_IGNORE_WRITES_BEGIN() \
+ AnnotateIgnoreWritesBegin(__FILE__, __LINE__)
+
+ /* Stop ignoring writes. */
+#define _Py_ANNOTATE_IGNORE_WRITES_END() \
+ AnnotateIgnoreWritesEnd(__FILE__, __LINE__)
+
+ /* Start ignoring all memory accesses (reads and writes). */
+#define _Py_ANNOTATE_IGNORE_READS_AND_WRITES_BEGIN() \
+ do {\
+ _Py_ANNOTATE_IGNORE_READS_BEGIN();\
+ _Py_ANNOTATE_IGNORE_WRITES_BEGIN();\
+ }while(0)\
+
+ /* Stop ignoring all memory accesses. */
+#define _Py_ANNOTATE_IGNORE_READS_AND_WRITES_END() \
+ do {\
+ _Py_ANNOTATE_IGNORE_WRITES_END();\
+ _Py_ANNOTATE_IGNORE_READS_END();\
+ }while(0)\
+
+ /* Similar to _Py_ANNOTATE_IGNORE_READS_BEGIN, but ignore synchronization events:
+ RWLOCK* and CONDVAR*. */
+#define _Py_ANNOTATE_IGNORE_SYNC_BEGIN() \
+ AnnotateIgnoreSyncBegin(__FILE__, __LINE__)
+
+ /* Stop ignoring sync events. */
+#define _Py_ANNOTATE_IGNORE_SYNC_END() \
+ AnnotateIgnoreSyncEnd(__FILE__, __LINE__)
+
+
+ /* Enable (enable!=0) or disable (enable==0) race detection for all threads.
+ This annotation could be useful if you want to skip expensive race analysis
+ during some period of program execution, e.g. during initialization. */
+#define _Py_ANNOTATE_ENABLE_RACE_DETECTION(enable) \
+ AnnotateEnableRaceDetection(__FILE__, __LINE__, enable)
+
+ /* -------------------------------------------------------------
+ Annotations useful for debugging. */
+
+ /* Request to trace every access to "address". */
+#define _Py_ANNOTATE_TRACE_MEMORY(address) \
+ AnnotateTraceMemory(__FILE__, __LINE__, address)
+
+ /* Report the current thread name to a race detector. */
+#define _Py_ANNOTATE_THREAD_NAME(name) \
+ AnnotateThreadName(__FILE__, __LINE__, name)
+
+ /* -------------------------------------------------------------
+ Annotations useful when implementing locks. They are not
+ normally needed by modules that merely use locks.
+ The "lock" argument is a pointer to the lock object. */
+
+ /* Report that a lock has been created at address "lock". */
+#define _Py_ANNOTATE_RWLOCK_CREATE(lock) \
+ AnnotateRWLockCreate(__FILE__, __LINE__, lock)
+
+ /* Report that the lock at address "lock" is about to be destroyed. */
+#define _Py_ANNOTATE_RWLOCK_DESTROY(lock) \
+ AnnotateRWLockDestroy(__FILE__, __LINE__, lock)
+
+ /* Report that the lock at address "lock" has been acquired.
+ is_w=1 for writer lock, is_w=0 for reader lock. */
+#define _Py_ANNOTATE_RWLOCK_ACQUIRED(lock, is_w) \
+ AnnotateRWLockAcquired(__FILE__, __LINE__, lock, is_w)
+
+ /* Report that the lock at address "lock" is about to be released. */
+#define _Py_ANNOTATE_RWLOCK_RELEASED(lock, is_w) \
+ AnnotateRWLockReleased(__FILE__, __LINE__, lock, is_w)
+
+ /* -------------------------------------------------------------
+ Annotations useful when implementing barriers. They are not
+ normally needed by modules that merely use barriers.
+ The "barrier" argument is a pointer to the barrier object. */
+
+ /* Report that the "barrier" has been initialized with initial "count".
+ If 'reinitialization_allowed' is true, initialization is allowed to happen
+ multiple times w/o calling barrier_destroy() */
+#define _Py_ANNOTATE_BARRIER_INIT(barrier, count, reinitialization_allowed) \
+ AnnotateBarrierInit(__FILE__, __LINE__, barrier, count, \
+ reinitialization_allowed)
+
+ /* Report that we are about to enter barrier_wait("barrier"). */
+#define _Py_ANNOTATE_BARRIER_WAIT_BEFORE(barrier) \
+ AnnotateBarrierWaitBefore(__FILE__, __LINE__, barrier)
+
+ /* Report that we just exited barrier_wait("barrier"). */
+#define _Py_ANNOTATE_BARRIER_WAIT_AFTER(barrier) \
+ AnnotateBarrierWaitAfter(__FILE__, __LINE__, barrier)
+
+ /* Report that the "barrier" has been destroyed. */
+#define _Py_ANNOTATE_BARRIER_DESTROY(barrier) \
+ AnnotateBarrierDestroy(__FILE__, __LINE__, barrier)
+
+ /* -------------------------------------------------------------
+ Annotations useful for testing race detectors. */
+
+ /* Report that we expect a race on the variable at "address".
+ Use only in unit tests for a race detector. */
+#define _Py_ANNOTATE_EXPECT_RACE(address, description) \
+ AnnotateExpectRace(__FILE__, __LINE__, address, description)
+
+ /* A no-op. Insert where you like to test the interceptors. */
+#define _Py_ANNOTATE_NO_OP(arg) \
+ AnnotateNoOp(__FILE__, __LINE__, arg)
+
+ /* Force the race detector to flush its state. The actual effect depends on
+ * the implementation of the detector. */
+#define _Py_ANNOTATE_FLUSH_STATE() \
+ AnnotateFlushState(__FILE__, __LINE__)
+
+
+#else /* DYNAMIC_ANNOTATIONS_ENABLED == 0 */
+
+#define _Py_ANNOTATE_RWLOCK_CREATE(lock) /* empty */
+#define _Py_ANNOTATE_RWLOCK_DESTROY(lock) /* empty */
+#define _Py_ANNOTATE_RWLOCK_ACQUIRED(lock, is_w) /* empty */
+#define _Py_ANNOTATE_RWLOCK_RELEASED(lock, is_w) /* empty */
+#define _Py_ANNOTATE_BARRIER_INIT(barrier, count, reinitialization_allowed) /* */
+#define _Py_ANNOTATE_BARRIER_WAIT_BEFORE(barrier) /* empty */
+#define _Py_ANNOTATE_BARRIER_WAIT_AFTER(barrier) /* empty */
+#define _Py_ANNOTATE_BARRIER_DESTROY(barrier) /* empty */
+#define _Py_ANNOTATE_CONDVAR_LOCK_WAIT(cv, lock) /* empty */
+#define _Py_ANNOTATE_CONDVAR_WAIT(cv) /* empty */
+#define _Py_ANNOTATE_CONDVAR_SIGNAL(cv) /* empty */
+#define _Py_ANNOTATE_CONDVAR_SIGNAL_ALL(cv) /* empty */
+#define _Py_ANNOTATE_HAPPENS_BEFORE(obj) /* empty */
+#define _Py_ANNOTATE_HAPPENS_AFTER(obj) /* empty */
+#define _Py_ANNOTATE_PUBLISH_MEMORY_RANGE(address, size) /* empty */
+#define _Py_ANNOTATE_UNPUBLISH_MEMORY_RANGE(address, size) /* empty */
+#define _Py_ANNOTATE_SWAP_MEMORY_RANGE(address, size) /* empty */
+#define _Py_ANNOTATE_PCQ_CREATE(pcq) /* empty */
+#define _Py_ANNOTATE_PCQ_DESTROY(pcq) /* empty */
+#define _Py_ANNOTATE_PCQ_PUT(pcq) /* empty */
+#define _Py_ANNOTATE_PCQ_GET(pcq) /* empty */
+#define _Py_ANNOTATE_NEW_MEMORY(address, size) /* empty */
+#define _Py_ANNOTATE_EXPECT_RACE(address, description) /* empty */
+#define _Py_ANNOTATE_BENIGN_RACE(address, description) /* empty */
+#define _Py_ANNOTATE_BENIGN_RACE_SIZED(address, size, description) /* empty */
+#define _Py_ANNOTATE_PURE_HAPPENS_BEFORE_MUTEX(mu) /* empty */
+#define _Py_ANNOTATE_MUTEX_IS_USED_AS_CONDVAR(mu) /* empty */
+#define _Py_ANNOTATE_TRACE_MEMORY(arg) /* empty */
+#define _Py_ANNOTATE_THREAD_NAME(name) /* empty */
+#define _Py_ANNOTATE_IGNORE_READS_BEGIN() /* empty */
+#define _Py_ANNOTATE_IGNORE_READS_END() /* empty */
+#define _Py_ANNOTATE_IGNORE_WRITES_BEGIN() /* empty */
+#define _Py_ANNOTATE_IGNORE_WRITES_END() /* empty */
+#define _Py_ANNOTATE_IGNORE_READS_AND_WRITES_BEGIN() /* empty */
+#define _Py_ANNOTATE_IGNORE_READS_AND_WRITES_END() /* empty */
+#define _Py_ANNOTATE_IGNORE_SYNC_BEGIN() /* empty */
+#define _Py_ANNOTATE_IGNORE_SYNC_END() /* empty */
+#define _Py_ANNOTATE_ENABLE_RACE_DETECTION(enable) /* empty */
+#define _Py_ANNOTATE_NO_OP(arg) /* empty */
+#define _Py_ANNOTATE_FLUSH_STATE() /* empty */
+
+#endif /* DYNAMIC_ANNOTATIONS_ENABLED */
+
+/* Use the macros above rather than using these functions directly. */
+#ifdef __cplusplus
+extern "C" {
+#endif
+void AnnotateRWLockCreate(const char *file, int line,
+ const volatile void *lock);
+void AnnotateRWLockDestroy(const char *file, int line,
+ const volatile void *lock);
+void AnnotateRWLockAcquired(const char *file, int line,
+ const volatile void *lock, long is_w);
+void AnnotateRWLockReleased(const char *file, int line,
+ const volatile void *lock, long is_w);
+void AnnotateBarrierInit(const char *file, int line,
+ const volatile void *barrier, long count,
+ long reinitialization_allowed);
+void AnnotateBarrierWaitBefore(const char *file, int line,
+ const volatile void *barrier);
+void AnnotateBarrierWaitAfter(const char *file, int line,
+ const volatile void *barrier);
+void AnnotateBarrierDestroy(const char *file, int line,
+ const volatile void *barrier);
+void AnnotateCondVarWait(const char *file, int line,
+ const volatile void *cv,
+ const volatile void *lock);
+void AnnotateCondVarSignal(const char *file, int line,
+ const volatile void *cv);
+void AnnotateCondVarSignalAll(const char *file, int line,
+ const volatile void *cv);
+void AnnotatePublishMemoryRange(const char *file, int line,
+ const volatile void *address,
+ long size);
+void AnnotateUnpublishMemoryRange(const char *file, int line,
+ const volatile void *address,
+ long size);
+void AnnotatePCQCreate(const char *file, int line,
+ const volatile void *pcq);
+void AnnotatePCQDestroy(const char *file, int line,
+ const volatile void *pcq);
+void AnnotatePCQPut(const char *file, int line,
+ const volatile void *pcq);
+void AnnotatePCQGet(const char *file, int line,
+ const volatile void *pcq);
+void AnnotateNewMemory(const char *file, int line,
+ const volatile void *address,
+ long size);
+void AnnotateExpectRace(const char *file, int line,
+ const volatile void *address,
+ const char *description);
+void AnnotateBenignRace(const char *file, int line,
+ const volatile void *address,
+ const char *description);
+void AnnotateBenignRaceSized(const char *file, int line,
+ const volatile void *address,
+ long size,
+ const char *description);
+void AnnotateMutexIsUsedAsCondVar(const char *file, int line,
+ const volatile void *mu);
+void AnnotateTraceMemory(const char *file, int line,
+ const volatile void *arg);
+void AnnotateThreadName(const char *file, int line,
+ const char *name);
+void AnnotateIgnoreReadsBegin(const char *file, int line);
+void AnnotateIgnoreReadsEnd(const char *file, int line);
+void AnnotateIgnoreWritesBegin(const char *file, int line);
+void AnnotateIgnoreWritesEnd(const char *file, int line);
+void AnnotateEnableRaceDetection(const char *file, int line, int enable);
+void AnnotateNoOp(const char *file, int line,
+ const volatile void *arg);
+void AnnotateFlushState(const char *file, int line);
+
+/* Return non-zero value if running under valgrind.
+
+ If "valgrind.h" is included into dynamic_annotations.c,
+ the regular valgrind mechanism will be used.
+ See http://valgrind.org/docs/manual/manual-core-adv.html about
+ RUNNING_ON_VALGRIND and other valgrind "client requests".
+ The file "valgrind.h" may be obtained by doing
+ svn co svn://svn.valgrind.org/valgrind/trunk/include
+
+ If for some reason you can't use "valgrind.h" or want to fake valgrind,
+ there are two ways to make this function return non-zero:
+ - Use environment variable: export RUNNING_ON_VALGRIND=1
+ - Make your tool intercept the function RunningOnValgrind() and
+ change its return value.
+ */
+int RunningOnValgrind(void);
+
+#ifdef __cplusplus
+}
+#endif
+
+#if DYNAMIC_ANNOTATIONS_ENABLED != 0 && defined(__cplusplus)
+
+ /* _Py_ANNOTATE_UNPROTECTED_READ is the preferred way to annotate racey reads.
+
+ Instead of doing
+ _Py_ANNOTATE_IGNORE_READS_BEGIN();
+ ... = x;
+ _Py_ANNOTATE_IGNORE_READS_END();
+ one can use
+ ... = _Py_ANNOTATE_UNPROTECTED_READ(x); */
+ template
+ inline T _Py_ANNOTATE_UNPROTECTED_READ(const volatile T &x) {
+ _Py_ANNOTATE_IGNORE_READS_BEGIN();
+ T res = x;
+ _Py_ANNOTATE_IGNORE_READS_END();
+ return res;
+ }
+ /* Apply _Py_ANNOTATE_BENIGN_RACE_SIZED to a static variable. */
+#define _Py_ANNOTATE_BENIGN_RACE_STATIC(static_var, description) \
+ namespace { \
+ class static_var ## _annotator { \
+ public: \
+ static_var ## _annotator() { \
+ _Py_ANNOTATE_BENIGN_RACE_SIZED(&static_var, \
+ sizeof(static_var), \
+ # static_var ": " description); \
+ } \
+ }; \
+ static static_var ## _annotator the ## static_var ## _annotator;\
+ }
+#else /* DYNAMIC_ANNOTATIONS_ENABLED == 0 */
+
+#define _Py_ANNOTATE_UNPROTECTED_READ(x) (x)
+#define _Py_ANNOTATE_BENIGN_RACE_STATIC(static_var, description) /* empty */
+
+#endif /* DYNAMIC_ANNOTATIONS_ENABLED */
+
+#endif /* __DYNAMIC_ANNOTATIONS_H__ */
diff --git a/Include/enumobject.h b/Include/enumobject.h
new file mode 100644
index 0000000..c14dbfc
--- /dev/null
+++ b/Include/enumobject.h
@@ -0,0 +1,17 @@
+#ifndef Py_ENUMOBJECT_H
+#define Py_ENUMOBJECT_H
+
+/* Enumerate Object */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_DATA(PyTypeObject) PyEnum_Type;
+PyAPI_DATA(PyTypeObject) PyReversed_Type;
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_ENUMOBJECT_H */
diff --git a/Include/errcode.h b/Include/errcode.h
new file mode 100644
index 0000000..b37cd26
--- /dev/null
+++ b/Include/errcode.h
@@ -0,0 +1,38 @@
+#ifndef Py_ERRCODE_H
+#define Py_ERRCODE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Error codes passed around between file input, tokenizer, parser and
+ interpreter. This is necessary so we can turn them into Python
+ exceptions at a higher level. Note that some errors have a
+ slightly different meaning when passed from the tokenizer to the
+ parser than when passed from the parser to the interpreter; e.g.
+ the parser only returns E_EOF when it hits EOF immediately, and it
+ never returns E_OK. */
+
+#define E_OK 10 /* No error */
+#define E_EOF 11 /* End Of File */
+#define E_INTR 12 /* Interrupted */
+#define E_TOKEN 13 /* Bad token */
+#define E_SYNTAX 14 /* Syntax error */
+#define E_NOMEM 15 /* Ran out of memory */
+#define E_DONE 16 /* Parsing complete */
+#define E_ERROR 17 /* Execution error */
+#define E_TABSPACE 18 /* Inconsistent mixing of tabs and spaces */
+#define E_OVERFLOW 19 /* Node had too many children */
+#define E_TOODEEP 20 /* Too many indentation levels */
+#define E_DEDENT 21 /* No matching outer block for dedent */
+#define E_DECODE 22 /* Error in decoding into Unicode */
+#define E_EOFS 23 /* EOF in triple-quoted string */
+#define E_EOLS 24 /* EOL in single-quoted string */
+#define E_LINECONT 25 /* Unexpected characters after a line continuation */
+#define E_IDENTIFIER 26 /* Invalid characters in identifier */
+#define E_BADSINGLE 27 /* Ill-formed single statement input */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_ERRCODE_H */
diff --git a/Include/eval.h b/Include/eval.h
new file mode 100644
index 0000000..2c1c2d0
--- /dev/null
+++ b/Include/eval.h
@@ -0,0 +1,37 @@
+
+/* Interface to execute compiled code */
+
+#ifndef Py_EVAL_H
+#define Py_EVAL_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(PyObject *) PyEval_EvalCode(PyObject *, PyObject *, PyObject *);
+
+PyAPI_FUNC(PyObject *) PyEval_EvalCodeEx(PyObject *co,
+ PyObject *globals,
+ PyObject *locals,
+ PyObject *const *args, int argc,
+ PyObject *const *kwds, int kwdc,
+ PyObject *const *defs, int defc,
+ PyObject *kwdefs, PyObject *closure);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyEval_EvalCodeWithName(
+ PyObject *co,
+ PyObject *globals, PyObject *locals,
+ PyObject *const *args, Py_ssize_t argcount,
+ PyObject *const *kwnames, PyObject *const *kwargs,
+ Py_ssize_t kwcount, int kwstep,
+ PyObject *const *defs, Py_ssize_t defcount,
+ PyObject *kwdefs, PyObject *closure,
+ PyObject *name, PyObject *qualname);
+
+PyAPI_FUNC(PyObject *) _PyEval_CallTracing(PyObject *func, PyObject *args);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_EVAL_H */
diff --git a/Include/fileobject.h b/Include/fileobject.h
new file mode 100644
index 0000000..89e8dd6
--- /dev/null
+++ b/Include/fileobject.h
@@ -0,0 +1,55 @@
+/* File object interface (what's left of it -- see io.py) */
+
+#ifndef Py_FILEOBJECT_H
+#define Py_FILEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define PY_STDIOTEXTMODE "b"
+
+PyAPI_FUNC(PyObject *) PyFile_FromFd(int, const char *, const char *, int,
+ const char *, const char *,
+ const char *, int);
+PyAPI_FUNC(PyObject *) PyFile_GetLine(PyObject *, int);
+PyAPI_FUNC(int) PyFile_WriteObject(PyObject *, PyObject *, int);
+PyAPI_FUNC(int) PyFile_WriteString(const char *, PyObject *);
+PyAPI_FUNC(int) PyObject_AsFileDescriptor(PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(char *) Py_UniversalNewlineFgets(char *, int, FILE*, PyObject *);
+#endif
+
+/* The default encoding used by the platform file system APIs
+ If non-NULL, this is different than the default encoding for strings
+*/
+PyAPI_DATA(const char *) Py_FileSystemDefaultEncoding;
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03060000
+PyAPI_DATA(const char *) Py_FileSystemDefaultEncodeErrors;
+#endif
+PyAPI_DATA(int) Py_HasFileSystemDefaultEncoding;
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
+PyAPI_DATA(int) Py_UTF8Mode;
+#endif
+
+/* Internal API
+
+ The std printer acts as a preliminary sys.stderr until the new io
+ infrastructure is in place. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyFile_NewStdPrinter(int);
+PyAPI_DATA(PyTypeObject) PyStdPrinter_Type;
+#endif /* Py_LIMITED_API */
+
+/* A routine to check if a file descriptor can be select()-ed. */
+#ifdef _MSC_VER
+ /* On Windows, any socket fd can be select()-ed, no matter how high */
+ #define _PyIsSelectable_fd(FD) (1)
+#else
+ #define _PyIsSelectable_fd(FD) ((unsigned int)(FD) < (unsigned int)FD_SETSIZE)
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_FILEOBJECT_H */
diff --git a/Include/fileutils.h b/Include/fileutils.h
new file mode 100644
index 0000000..e4bf6d4
--- /dev/null
+++ b/Include/fileutils.h
@@ -0,0 +1,177 @@
+#ifndef Py_FILEUTILS_H
+#define Py_FILEUTILS_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_FUNC(wchar_t *) Py_DecodeLocale(
+ const char *arg,
+ size_t *size);
+
+PyAPI_FUNC(char*) Py_EncodeLocale(
+ const wchar_t *text,
+ size_t *error_pos);
+
+PyAPI_FUNC(char*) _Py_EncodeLocaleRaw(
+ const wchar_t *text,
+ size_t *error_pos);
+#endif
+
+#ifdef Py_BUILD_CORE
+PyAPI_FUNC(int) _Py_DecodeUTF8Ex(
+ const char *arg,
+ Py_ssize_t arglen,
+ wchar_t **wstr,
+ size_t *wlen,
+ const char **reason,
+ int surrogateescape);
+
+PyAPI_FUNC(int) _Py_EncodeUTF8Ex(
+ const wchar_t *text,
+ char **str,
+ size_t *error_pos,
+ const char **reason,
+ int raw_malloc,
+ int surrogateescape);
+
+PyAPI_FUNC(wchar_t*) _Py_DecodeUTF8_surrogateescape(
+ const char *arg,
+ Py_ssize_t arglen);
+
+PyAPI_FUNC(int) _Py_DecodeLocaleEx(
+ const char *arg,
+ wchar_t **wstr,
+ size_t *wlen,
+ const char **reason,
+ int current_locale,
+ int surrogateescape);
+
+PyAPI_FUNC(int) _Py_EncodeLocaleEx(
+ const wchar_t *text,
+ char **str,
+ size_t *error_pos,
+ const char **reason,
+ int current_locale,
+ int surrogateescape);
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _Py_device_encoding(int);
+
+#ifdef MS_WINDOWS
+struct _Py_stat_struct {
+ unsigned long st_dev;
+ uint64_t st_ino;
+ unsigned short st_mode;
+ int st_nlink;
+ int st_uid;
+ int st_gid;
+ unsigned long st_rdev;
+ __int64 st_size;
+ time_t st_atime;
+ int st_atime_nsec;
+ time_t st_mtime;
+ int st_mtime_nsec;
+ time_t st_ctime;
+ int st_ctime_nsec;
+ unsigned long st_file_attributes;
+};
+#else
+# define _Py_stat_struct stat
+#endif
+
+PyAPI_FUNC(int) _Py_fstat(
+ int fd,
+ struct _Py_stat_struct *status);
+
+PyAPI_FUNC(int) _Py_fstat_noraise(
+ int fd,
+ struct _Py_stat_struct *status);
+
+PyAPI_FUNC(int) _Py_stat(
+ PyObject *path,
+ struct stat *status);
+
+PyAPI_FUNC(int) _Py_open(
+ const char *pathname,
+ int flags);
+
+PyAPI_FUNC(int) _Py_open_noraise(
+ const char *pathname,
+ int flags);
+
+PyAPI_FUNC(FILE *) _Py_wfopen(
+ const wchar_t *path,
+ const wchar_t *mode);
+
+PyAPI_FUNC(FILE*) _Py_fopen(
+ const char *pathname,
+ const char *mode);
+
+PyAPI_FUNC(FILE*) _Py_fopen_obj(
+ PyObject *path,
+ const char *mode);
+
+PyAPI_FUNC(Py_ssize_t) _Py_read(
+ int fd,
+ void *buf,
+ size_t count);
+
+PyAPI_FUNC(Py_ssize_t) _Py_write(
+ int fd,
+ const void *buf,
+ size_t count);
+
+PyAPI_FUNC(Py_ssize_t) _Py_write_noraise(
+ int fd,
+ const void *buf,
+ size_t count);
+
+#ifdef HAVE_READLINK
+PyAPI_FUNC(int) _Py_wreadlink(
+ const wchar_t *path,
+ wchar_t *buf,
+ size_t bufsiz);
+#endif
+
+#ifdef HAVE_REALPATH
+PyAPI_FUNC(wchar_t*) _Py_wrealpath(
+ const wchar_t *path,
+ wchar_t *resolved_path,
+ size_t resolved_path_size);
+#endif
+
+PyAPI_FUNC(wchar_t*) _Py_wgetcwd(
+ wchar_t *buf,
+ size_t size);
+
+PyAPI_FUNC(int) _Py_get_inheritable(int fd);
+
+PyAPI_FUNC(int) _Py_set_inheritable(int fd, int inheritable,
+ int *atomic_flag_works);
+
+PyAPI_FUNC(int) _Py_set_inheritable_async_safe(int fd, int inheritable,
+ int *atomic_flag_works);
+
+PyAPI_FUNC(int) _Py_dup(int fd);
+
+#ifndef MS_WINDOWS
+PyAPI_FUNC(int) _Py_get_blocking(int fd);
+
+PyAPI_FUNC(int) _Py_set_blocking(int fd, int blocking);
+#endif /* !MS_WINDOWS */
+
+PyAPI_FUNC(int) _Py_GetLocaleconvNumeric(
+ PyObject **decimal_point,
+ PyObject **thousands_sep,
+ const char **grouping);
+
+#endif /* Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_FILEUTILS_H */
diff --git a/Include/floatobject.h b/Include/floatobject.h
new file mode 100644
index 0000000..f1044d6
--- /dev/null
+++ b/Include/floatobject.h
@@ -0,0 +1,130 @@
+
+/* Float object interface */
+
+/*
+PyFloatObject represents a (double precision) floating point number.
+*/
+
+#ifndef Py_FLOATOBJECT_H
+#define Py_FLOATOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_HEAD
+ double ob_fval;
+} PyFloatObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PyFloat_Type;
+
+#define PyFloat_Check(op) PyObject_TypeCheck(op, &PyFloat_Type)
+#define PyFloat_CheckExact(op) (Py_TYPE(op) == &PyFloat_Type)
+
+#ifdef Py_NAN
+#define Py_RETURN_NAN return PyFloat_FromDouble(Py_NAN)
+#endif
+
+#define Py_RETURN_INF(sign) do \
+ if (copysign(1., sign) == 1.) { \
+ return PyFloat_FromDouble(Py_HUGE_VAL); \
+ } else { \
+ return PyFloat_FromDouble(-Py_HUGE_VAL); \
+ } while(0)
+
+PyAPI_FUNC(double) PyFloat_GetMax(void);
+PyAPI_FUNC(double) PyFloat_GetMin(void);
+PyAPI_FUNC(PyObject *) PyFloat_GetInfo(void);
+
+/* Return Python float from string PyObject. */
+PyAPI_FUNC(PyObject *) PyFloat_FromString(PyObject*);
+
+/* Return Python float from C double. */
+PyAPI_FUNC(PyObject *) PyFloat_FromDouble(double);
+
+/* Extract C double from Python float. The macro version trades safety for
+ speed. */
+PyAPI_FUNC(double) PyFloat_AsDouble(PyObject *);
+#ifndef Py_LIMITED_API
+#define PyFloat_AS_DOUBLE(op) (((PyFloatObject *)(op))->ob_fval)
+#endif
+
+#ifndef Py_LIMITED_API
+/* _PyFloat_{Pack,Unpack}{4,8}
+ *
+ * The struct and pickle (at least) modules need an efficient platform-
+ * independent way to store floating-point values as byte strings.
+ * The Pack routines produce a string from a C double, and the Unpack
+ * routines produce a C double from such a string. The suffix (4 or 8)
+ * specifies the number of bytes in the string.
+ *
+ * On platforms that appear to use (see _PyFloat_Init()) IEEE-754 formats
+ * these functions work by copying bits. On other platforms, the formats the
+ * 4- byte format is identical to the IEEE-754 single precision format, and
+ * the 8-byte format to the IEEE-754 double precision format, although the
+ * packing of INFs and NaNs (if such things exist on the platform) isn't
+ * handled correctly, and attempting to unpack a string containing an IEEE
+ * INF or NaN will raise an exception.
+ *
+ * On non-IEEE platforms with more precision, or larger dynamic range, than
+ * 754 supports, not all values can be packed; on non-IEEE platforms with less
+ * precision, or smaller dynamic range, not all values can be unpacked. What
+ * happens in such cases is partly accidental (alas).
+ */
+
+/* The pack routines write 2, 4 or 8 bytes, starting at p. le is a bool
+ * argument, true if you want the string in little-endian format (exponent
+ * last, at p+1, p+3 or p+7), false if you want big-endian format (exponent
+ * first, at p).
+ * Return value: 0 if all is OK, -1 if error (and an exception is
+ * set, most likely OverflowError).
+ * There are two problems on non-IEEE platforms:
+ * 1): What this does is undefined if x is a NaN or infinity.
+ * 2): -0.0 and +0.0 produce the same string.
+ */
+PyAPI_FUNC(int) _PyFloat_Pack2(double x, unsigned char *p, int le);
+PyAPI_FUNC(int) _PyFloat_Pack4(double x, unsigned char *p, int le);
+PyAPI_FUNC(int) _PyFloat_Pack8(double x, unsigned char *p, int le);
+
+/* Needed for the old way for marshal to store a floating point number.
+ Returns the string length copied into p, -1 on error.
+ */
+PyAPI_FUNC(int) _PyFloat_Repr(double x, char *p, size_t len);
+
+/* Used to get the important decimal digits of a double */
+PyAPI_FUNC(int) _PyFloat_Digits(char *buf, double v, int *signum);
+PyAPI_FUNC(void) _PyFloat_DigitsInit(void);
+
+/* The unpack routines read 2, 4 or 8 bytes, starting at p. le is a bool
+ * argument, true if the string is in little-endian format (exponent
+ * last, at p+1, p+3 or p+7), false if big-endian (exponent first, at p).
+ * Return value: The unpacked double. On error, this is -1.0 and
+ * PyErr_Occurred() is true (and an exception is set, most likely
+ * OverflowError). Note that on a non-IEEE platform this will refuse
+ * to unpack a string that represents a NaN or infinity.
+ */
+PyAPI_FUNC(double) _PyFloat_Unpack2(const unsigned char *p, int le);
+PyAPI_FUNC(double) _PyFloat_Unpack4(const unsigned char *p, int le);
+PyAPI_FUNC(double) _PyFloat_Unpack8(const unsigned char *p, int le);
+
+/* free list api */
+PyAPI_FUNC(int) PyFloat_ClearFreeList(void);
+
+PyAPI_FUNC(void) _PyFloat_DebugMallocStats(FILE* out);
+
+/* Format the object based on the format_spec, as defined in PEP 3101
+ (Advanced String Formatting). */
+PyAPI_FUNC(int) _PyFloat_FormatAdvancedWriter(
+ _PyUnicodeWriter *writer,
+ PyObject *obj,
+ PyObject *format_spec,
+ Py_ssize_t start,
+ Py_ssize_t end);
+#endif /* Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_FLOATOBJECT_H */
diff --git a/Include/frameobject.h b/Include/frameobject.h
new file mode 100644
index 0000000..a95baf8
--- /dev/null
+++ b/Include/frameobject.h
@@ -0,0 +1,93 @@
+
+/* Frame object interface */
+
+#ifndef Py_LIMITED_API
+#ifndef Py_FRAMEOBJECT_H
+#define Py_FRAMEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ int b_type; /* what kind of block this is */
+ int b_handler; /* where to jump to find handler */
+ int b_level; /* value stack level to pop to */
+} PyTryBlock;
+
+typedef struct _frame {
+ PyObject_VAR_HEAD
+ struct _frame *f_back; /* previous frame, or NULL */
+ PyCodeObject *f_code; /* code segment */
+ PyObject *f_builtins; /* builtin symbol table (PyDictObject) */
+ PyObject *f_globals; /* global symbol table (PyDictObject) */
+ PyObject *f_locals; /* local symbol table (any mapping) */
+ PyObject **f_valuestack; /* points after the last local */
+ /* Next free slot in f_valuestack. Frame creation sets to f_valuestack.
+ Frame evaluation usually NULLs it, but a frame that yields sets it
+ to the current stack top. */
+ PyObject **f_stacktop;
+ PyObject *f_trace; /* Trace function */
+ char f_trace_lines; /* Emit per-line trace events? */
+ char f_trace_opcodes; /* Emit per-opcode trace events? */
+
+ /* Borrowed reference to a generator, or NULL */
+ PyObject *f_gen;
+
+ int f_lasti; /* Last instruction if called */
+ /* Call PyFrame_GetLineNumber() instead of reading this field
+ directly. As of 2.3 f_lineno is only valid when tracing is
+ active (i.e. when f_trace is set). At other times we use
+ PyCode_Addr2Line to calculate the line from the current
+ bytecode index. */
+ int f_lineno; /* Current line number */
+ int f_iblock; /* index in f_blockstack */
+ char f_executing; /* whether the frame is still executing */
+ PyTryBlock f_blockstack[CO_MAXBLOCKS]; /* for try and loop blocks */
+ PyObject *f_localsplus[1]; /* locals+stack, dynamically sized */
+} PyFrameObject;
+
+
+/* Standard object interface */
+
+PyAPI_DATA(PyTypeObject) PyFrame_Type;
+
+#define PyFrame_Check(op) (Py_TYPE(op) == &PyFrame_Type)
+
+PyAPI_FUNC(PyFrameObject *) PyFrame_New(PyThreadState *, PyCodeObject *,
+ PyObject *, PyObject *);
+
+/* only internal use */
+PyFrameObject* _PyFrame_New_NoTrack(PyThreadState *, PyCodeObject *,
+ PyObject *, PyObject *);
+
+
+/* The rest of the interface is specific for frame objects */
+
+/* Block management functions */
+
+PyAPI_FUNC(void) PyFrame_BlockSetup(PyFrameObject *, int, int, int);
+PyAPI_FUNC(PyTryBlock *) PyFrame_BlockPop(PyFrameObject *);
+
+/* Extend the value stack */
+
+PyAPI_FUNC(PyObject **) PyFrame_ExtendStack(PyFrameObject *, int, int);
+
+/* Conversions between "fast locals" and locals in dictionary */
+
+PyAPI_FUNC(void) PyFrame_LocalsToFast(PyFrameObject *, int);
+
+PyAPI_FUNC(int) PyFrame_FastToLocalsWithError(PyFrameObject *f);
+PyAPI_FUNC(void) PyFrame_FastToLocals(PyFrameObject *);
+
+PyAPI_FUNC(int) PyFrame_ClearFreeList(void);
+
+PyAPI_FUNC(void) _PyFrame_DebugMallocStats(FILE *out);
+
+/* Return the line of code the frame is currently executing. */
+PyAPI_FUNC(int) PyFrame_GetLineNumber(PyFrameObject *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_FRAMEOBJECT_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/funcobject.h b/Include/funcobject.h
new file mode 100644
index 0000000..86674ac
--- /dev/null
+++ b/Include/funcobject.h
@@ -0,0 +1,103 @@
+
+/* Function object interface */
+#ifndef Py_LIMITED_API
+#ifndef Py_FUNCOBJECT_H
+#define Py_FUNCOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Function objects and code objects should not be confused with each other:
+ *
+ * Function objects are created by the execution of the 'def' statement.
+ * They reference a code object in their __code__ attribute, which is a
+ * purely syntactic object, i.e. nothing more than a compiled version of some
+ * source code lines. There is one code object per source code "fragment",
+ * but each code object can be referenced by zero or many function objects
+ * depending only on how many times the 'def' statement in the source was
+ * executed so far.
+ */
+
+typedef struct {
+ PyObject_HEAD
+ PyObject *func_code; /* A code object, the __code__ attribute */
+ PyObject *func_globals; /* A dictionary (other mappings won't do) */
+ PyObject *func_defaults; /* NULL or a tuple */
+ PyObject *func_kwdefaults; /* NULL or a dict */
+ PyObject *func_closure; /* NULL or a tuple of cell objects */
+ PyObject *func_doc; /* The __doc__ attribute, can be anything */
+ PyObject *func_name; /* The __name__ attribute, a string object */
+ PyObject *func_dict; /* The __dict__ attribute, a dict or NULL */
+ PyObject *func_weakreflist; /* List of weak references */
+ PyObject *func_module; /* The __module__ attribute, can be anything */
+ PyObject *func_annotations; /* Annotations, a dict or NULL */
+ PyObject *func_qualname; /* The qualified name */
+
+ /* Invariant:
+ * func_closure contains the bindings for func_code->co_freevars, so
+ * PyTuple_Size(func_closure) == PyCode_GetNumFree(func_code)
+ * (func_closure may be NULL if PyCode_GetNumFree(func_code) == 0).
+ */
+} PyFunctionObject;
+
+PyAPI_DATA(PyTypeObject) PyFunction_Type;
+
+#define PyFunction_Check(op) (Py_TYPE(op) == &PyFunction_Type)
+
+PyAPI_FUNC(PyObject *) PyFunction_New(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_NewWithQualName(PyObject *, PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetCode(PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetGlobals(PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetModule(PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetDefaults(PyObject *);
+PyAPI_FUNC(int) PyFunction_SetDefaults(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetKwDefaults(PyObject *);
+PyAPI_FUNC(int) PyFunction_SetKwDefaults(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetClosure(PyObject *);
+PyAPI_FUNC(int) PyFunction_SetClosure(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyFunction_GetAnnotations(PyObject *);
+PyAPI_FUNC(int) PyFunction_SetAnnotations(PyObject *, PyObject *);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyFunction_FastCallDict(
+ PyObject *func,
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwargs);
+
+PyAPI_FUNC(PyObject *) _PyFunction_FastCallKeywords(
+ PyObject *func,
+ PyObject *const *stack,
+ Py_ssize_t nargs,
+ PyObject *kwnames);
+#endif
+
+/* Macros for direct access to these values. Type checks are *not*
+ done, so use with care. */
+#define PyFunction_GET_CODE(func) \
+ (((PyFunctionObject *)func) -> func_code)
+#define PyFunction_GET_GLOBALS(func) \
+ (((PyFunctionObject *)func) -> func_globals)
+#define PyFunction_GET_MODULE(func) \
+ (((PyFunctionObject *)func) -> func_module)
+#define PyFunction_GET_DEFAULTS(func) \
+ (((PyFunctionObject *)func) -> func_defaults)
+#define PyFunction_GET_KW_DEFAULTS(func) \
+ (((PyFunctionObject *)func) -> func_kwdefaults)
+#define PyFunction_GET_CLOSURE(func) \
+ (((PyFunctionObject *)func) -> func_closure)
+#define PyFunction_GET_ANNOTATIONS(func) \
+ (((PyFunctionObject *)func) -> func_annotations)
+
+/* The classmethod and staticmethod types lives here, too */
+PyAPI_DATA(PyTypeObject) PyClassMethod_Type;
+PyAPI_DATA(PyTypeObject) PyStaticMethod_Type;
+
+PyAPI_FUNC(PyObject *) PyClassMethod_New(PyObject *);
+PyAPI_FUNC(PyObject *) PyStaticMethod_New(PyObject *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_FUNCOBJECT_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/genobject.h b/Include/genobject.h
new file mode 100644
index 0000000..16b9833
--- /dev/null
+++ b/Include/genobject.h
@@ -0,0 +1,105 @@
+
+/* Generator object interface */
+
+#ifndef Py_LIMITED_API
+#ifndef Py_GENOBJECT_H
+#define Py_GENOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct _frame; /* Avoid including frameobject.h */
+
+/* _PyGenObject_HEAD defines the initial segment of generator
+ and coroutine objects. */
+#define _PyGenObject_HEAD(prefix) \
+ PyObject_HEAD \
+ /* Note: gi_frame can be NULL if the generator is "finished" */ \
+ struct _frame *prefix##_frame; \
+ /* True if generator is being executed. */ \
+ char prefix##_running; \
+ /* The code object backing the generator */ \
+ PyObject *prefix##_code; \
+ /* List of weak reference. */ \
+ PyObject *prefix##_weakreflist; \
+ /* Name of the generator. */ \
+ PyObject *prefix##_name; \
+ /* Qualified name of the generator. */ \
+ PyObject *prefix##_qualname; \
+ _PyErr_StackItem prefix##_exc_state;
+
+typedef struct {
+ /* The gi_ prefix is intended to remind of generator-iterator. */
+ _PyGenObject_HEAD(gi)
+} PyGenObject;
+
+PyAPI_DATA(PyTypeObject) PyGen_Type;
+
+#define PyGen_Check(op) PyObject_TypeCheck(op, &PyGen_Type)
+#define PyGen_CheckExact(op) (Py_TYPE(op) == &PyGen_Type)
+
+PyAPI_FUNC(PyObject *) PyGen_New(struct _frame *);
+PyAPI_FUNC(PyObject *) PyGen_NewWithQualName(struct _frame *,
+ PyObject *name, PyObject *qualname);
+PyAPI_FUNC(int) PyGen_NeedsFinalizing(PyGenObject *);
+PyAPI_FUNC(int) _PyGen_SetStopIterationValue(PyObject *);
+PyAPI_FUNC(int) _PyGen_FetchStopIterationValue(PyObject **);
+PyAPI_FUNC(PyObject *) _PyGen_Send(PyGenObject *, PyObject *);
+PyObject *_PyGen_yf(PyGenObject *);
+PyAPI_FUNC(void) _PyGen_Finalize(PyObject *self);
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ _PyGenObject_HEAD(cr)
+ PyObject *cr_origin;
+} PyCoroObject;
+
+PyAPI_DATA(PyTypeObject) PyCoro_Type;
+PyAPI_DATA(PyTypeObject) _PyCoroWrapper_Type;
+
+PyAPI_DATA(PyTypeObject) _PyAIterWrapper_Type;
+
+#define PyCoro_CheckExact(op) (Py_TYPE(op) == &PyCoro_Type)
+PyObject *_PyCoro_GetAwaitableIter(PyObject *o);
+PyAPI_FUNC(PyObject *) PyCoro_New(struct _frame *,
+ PyObject *name, PyObject *qualname);
+
+/* Asynchronous Generators */
+
+typedef struct {
+ _PyGenObject_HEAD(ag)
+ PyObject *ag_finalizer;
+
+ /* Flag is set to 1 when hooks set up by sys.set_asyncgen_hooks
+ were called on the generator, to avoid calling them more
+ than once. */
+ int ag_hooks_inited;
+
+ /* Flag is set to 1 when aclose() is called for the first time, or
+ when a StopAsyncIteration exception is raised. */
+ int ag_closed;
+} PyAsyncGenObject;
+
+PyAPI_DATA(PyTypeObject) PyAsyncGen_Type;
+PyAPI_DATA(PyTypeObject) _PyAsyncGenASend_Type;
+PyAPI_DATA(PyTypeObject) _PyAsyncGenWrappedValue_Type;
+PyAPI_DATA(PyTypeObject) _PyAsyncGenAThrow_Type;
+
+PyAPI_FUNC(PyObject *) PyAsyncGen_New(struct _frame *,
+ PyObject *name, PyObject *qualname);
+
+#define PyAsyncGen_CheckExact(op) (Py_TYPE(op) == &PyAsyncGen_Type)
+
+PyObject *_PyAsyncGenValueWrapperNew(PyObject *);
+
+int PyAsyncGen_ClearFreeLists(void);
+
+#endif
+
+#undef _PyGenObject_HEAD
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_GENOBJECT_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/graminit.h b/Include/graminit.h
new file mode 100644
index 0000000..bdfe821
--- /dev/null
+++ b/Include/graminit.h
@@ -0,0 +1,89 @@
+/* Generated by Parser/pgen */
+
+#define single_input 256
+#define file_input 257
+#define eval_input 258
+#define decorator 259
+#define decorators 260
+#define decorated 261
+#define async_funcdef 262
+#define funcdef 263
+#define parameters 264
+#define typedargslist 265
+#define tfpdef 266
+#define varargslist 267
+#define vfpdef 268
+#define stmt 269
+#define simple_stmt 270
+#define small_stmt 271
+#define expr_stmt 272
+#define annassign 273
+#define testlist_star_expr 274
+#define augassign 275
+#define del_stmt 276
+#define pass_stmt 277
+#define flow_stmt 278
+#define break_stmt 279
+#define continue_stmt 280
+#define return_stmt 281
+#define yield_stmt 282
+#define raise_stmt 283
+#define import_stmt 284
+#define import_name 285
+#define import_from 286
+#define import_as_name 287
+#define dotted_as_name 288
+#define import_as_names 289
+#define dotted_as_names 290
+#define dotted_name 291
+#define global_stmt 292
+#define nonlocal_stmt 293
+#define assert_stmt 294
+#define compound_stmt 295
+#define async_stmt 296
+#define if_stmt 297
+#define while_stmt 298
+#define for_stmt 299
+#define try_stmt 300
+#define with_stmt 301
+#define with_item 302
+#define except_clause 303
+#define suite 304
+#define test 305
+#define test_nocond 306
+#define lambdef 307
+#define lambdef_nocond 308
+#define or_test 309
+#define and_test 310
+#define not_test 311
+#define comparison 312
+#define comp_op 313
+#define star_expr 314
+#define expr 315
+#define xor_expr 316
+#define and_expr 317
+#define shift_expr 318
+#define arith_expr 319
+#define term 320
+#define factor 321
+#define power 322
+#define atom_expr 323
+#define atom 324
+#define testlist_comp 325
+#define trailer 326
+#define subscriptlist 327
+#define subscript 328
+#define sliceop 329
+#define exprlist 330
+#define testlist 331
+#define dictorsetmaker 332
+#define classdef 333
+#define arglist 334
+#define argument 335
+#define comp_iter 336
+#define sync_comp_for 337
+#define comp_for 338
+#define comp_if 339
+#define encoding_decl 340
+#define yield_expr 341
+#define yield_arg 342
diff --git a/Include/grammar.h b/Include/grammar.h
new file mode 100644
index 0000000..e1703f4
--- /dev/null
+++ b/Include/grammar.h
@@ -0,0 +1,94 @@
+
+/* Grammar interface */
+
+#ifndef Py_GRAMMAR_H
+#define Py_GRAMMAR_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "bitset.h" /* Sigh... */
+
+/* A label of an arc */
+
+typedef struct {
+ int lb_type;
+ char *lb_str;
+} label;
+
+#define EMPTY 0 /* Label number 0 is by definition the empty label */
+
+/* A list of labels */
+
+typedef struct {
+ int ll_nlabels;
+ label *ll_label;
+} labellist;
+
+/* An arc from one state to another */
+
+typedef struct {
+ short a_lbl; /* Label of this arc */
+ short a_arrow; /* State where this arc goes to */
+} arc;
+
+/* A state in a DFA */
+
+typedef struct {
+ int s_narcs;
+ arc *s_arc; /* Array of arcs */
+
+ /* Optional accelerators */
+ int s_lower; /* Lowest label index */
+ int s_upper; /* Highest label index */
+ int *s_accel; /* Accelerator */
+ int s_accept; /* Nonzero for accepting state */
+} state;
+
+/* A DFA */
+
+typedef struct {
+ int d_type; /* Non-terminal this represents */
+ char *d_name; /* For printing */
+ int d_initial; /* Initial state */
+ int d_nstates;
+ state *d_state; /* Array of states */
+ bitset d_first;
+} dfa;
+
+/* A grammar */
+
+typedef struct {
+ int g_ndfas;
+ dfa *g_dfa; /* Array of DFAs */
+ labellist g_ll;
+ int g_start; /* Start symbol of the grammar */
+ int g_accel; /* Set if accelerators present */
+} grammar;
+
+/* FUNCTIONS */
+
+grammar *newgrammar(int start);
+void freegrammar(grammar *g);
+dfa *adddfa(grammar *g, int type, const char *name);
+int addstate(dfa *d);
+void addarc(dfa *d, int from, int to, int lbl);
+dfa *PyGrammar_FindDFA(grammar *g, int type);
+
+int addlabel(labellist *ll, int type, const char *str);
+int findlabel(labellist *ll, int type, const char *str);
+const char *PyGrammar_LabelRepr(label *lb);
+void translatelabels(grammar *g);
+
+void addfirstsets(grammar *g);
+
+void PyGrammar_AddAccelerators(grammar *g);
+void PyGrammar_RemoveAccelerators(grammar *);
+
+void printgrammar(grammar *g, FILE *fp);
+void printnonterminals(grammar *g, FILE *fp);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_GRAMMAR_H */
diff --git a/Include/import.h b/Include/import.h
new file mode 100644
index 0000000..13f32a1
--- /dev/null
+++ b/Include/import.h
@@ -0,0 +1,154 @@
+
+/* Module definition and import interface */
+
+#ifndef Py_IMPORT_H
+#define Py_IMPORT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(_PyInitError) _PyImportZip_Init(void);
+
+PyMODINIT_FUNC PyInit__imp(void);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(long) PyImport_GetMagicNumber(void);
+PyAPI_FUNC(const char *) PyImport_GetMagicTag(void);
+PyAPI_FUNC(PyObject *) PyImport_ExecCodeModule(
+ const char *name, /* UTF-8 encoded string */
+ PyObject *co
+ );
+PyAPI_FUNC(PyObject *) PyImport_ExecCodeModuleEx(
+ const char *name, /* UTF-8 encoded string */
+ PyObject *co,
+ const char *pathname /* decoded from the filesystem encoding */
+ );
+PyAPI_FUNC(PyObject *) PyImport_ExecCodeModuleWithPathnames(
+ const char *name, /* UTF-8 encoded string */
+ PyObject *co,
+ const char *pathname, /* decoded from the filesystem encoding */
+ const char *cpathname /* decoded from the filesystem encoding */
+ );
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject *) PyImport_ExecCodeModuleObject(
+ PyObject *name,
+ PyObject *co,
+ PyObject *pathname,
+ PyObject *cpathname
+ );
+#endif
+PyAPI_FUNC(PyObject *) PyImport_GetModuleDict(void);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
+PyAPI_FUNC(PyObject *) PyImport_GetModule(PyObject *name);
+#endif
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyImport_IsInitialized(PyInterpreterState *);
+PyAPI_FUNC(PyObject *) _PyImport_GetModuleId(struct _Py_Identifier *name);
+PyAPI_FUNC(PyObject *) _PyImport_AddModuleObject(PyObject *name,
+ PyObject *modules);
+PyAPI_FUNC(int) _PyImport_SetModule(PyObject *name, PyObject *module);
+PyAPI_FUNC(int) _PyImport_SetModuleString(const char *name, PyObject* module);
+#endif
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject *) PyImport_AddModuleObject(
+ PyObject *name
+ );
+#endif
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyImport_AddModuleObject(PyObject *, PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyImport_AddModule(
+ const char *name /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(PyObject *) PyImport_ImportModule(
+ const char *name /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(PyObject *) PyImport_ImportModuleNoBlock(
+ const char *name /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(PyObject *) PyImport_ImportModuleLevel(
+ const char *name, /* UTF-8 encoded string */
+ PyObject *globals,
+ PyObject *locals,
+ PyObject *fromlist,
+ int level
+ );
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_FUNC(PyObject *) PyImport_ImportModuleLevelObject(
+ PyObject *name,
+ PyObject *globals,
+ PyObject *locals,
+ PyObject *fromlist,
+ int level
+ );
+#endif
+
+#define PyImport_ImportModuleEx(n, g, l, f) \
+ PyImport_ImportModuleLevel(n, g, l, f, 0)
+
+PyAPI_FUNC(PyObject *) PyImport_GetImporter(PyObject *path);
+PyAPI_FUNC(PyObject *) PyImport_Import(PyObject *name);
+PyAPI_FUNC(PyObject *) PyImport_ReloadModule(PyObject *m);
+PyAPI_FUNC(void) PyImport_Cleanup(void);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(int) PyImport_ImportFrozenModuleObject(
+ PyObject *name
+ );
+#endif
+PyAPI_FUNC(int) PyImport_ImportFrozenModule(
+ const char *name /* UTF-8 encoded string */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyImport_AcquireLock(void);
+PyAPI_FUNC(int) _PyImport_ReleaseLock(void);
+
+PyAPI_FUNC(void) _PyImport_ReInitLock(void);
+
+PyAPI_FUNC(PyObject *) _PyImport_FindBuiltin(
+ const char *name, /* UTF-8 encoded string */
+ PyObject *modules
+ );
+PyAPI_FUNC(PyObject *) _PyImport_FindExtensionObject(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) _PyImport_FindExtensionObjectEx(PyObject *, PyObject *,
+ PyObject *);
+PyAPI_FUNC(int) _PyImport_FixupBuiltin(
+ PyObject *mod,
+ const char *name, /* UTF-8 encoded string */
+ PyObject *modules
+ );
+PyAPI_FUNC(int) _PyImport_FixupExtensionObject(PyObject*, PyObject *,
+ PyObject *, PyObject *);
+
+struct _inittab {
+ const char *name; /* ASCII encoded string */
+ PyObject* (*initfunc)(void);
+};
+PyAPI_DATA(struct _inittab *) PyImport_Inittab;
+PyAPI_FUNC(int) PyImport_ExtendInittab(struct _inittab *newtab);
+#endif /* Py_LIMITED_API */
+
+PyAPI_DATA(PyTypeObject) PyNullImporter_Type;
+
+PyAPI_FUNC(int) PyImport_AppendInittab(
+ const char *name, /* ASCII encoded string */
+ PyObject* (*initfunc)(void)
+ );
+
+#ifndef Py_LIMITED_API
+struct _frozen {
+ const char *name; /* ASCII encoded string */
+ const unsigned char *code;
+ int size;
+};
+
+/* Embedding apps may change this pointer to point to their favorite
+ collection of frozen modules: */
+
+PyAPI_DATA(const struct _frozen *) PyImport_FrozenModules;
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_IMPORT_H */
diff --git a/Include/intrcheck.h b/Include/intrcheck.h
new file mode 100644
index 0000000..2e17336
--- /dev/null
+++ b/Include/intrcheck.h
@@ -0,0 +1,33 @@
+
+#ifndef Py_INTRCHECK_H
+#define Py_INTRCHECK_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(int) PyOS_InterruptOccurred(void);
+PyAPI_FUNC(void) PyOS_InitInterrupts(void);
+#ifdef HAVE_FORK
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
+PyAPI_FUNC(void) PyOS_BeforeFork(void);
+PyAPI_FUNC(void) PyOS_AfterFork_Parent(void);
+PyAPI_FUNC(void) PyOS_AfterFork_Child(void);
+#endif
+#endif
+/* Deprecated, please use PyOS_AfterFork_Child() instead */
+PyAPI_FUNC(void) PyOS_AfterFork(void) Py_DEPRECATED(3.7);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyOS_IsMainThread(void);
+PyAPI_FUNC(void) _PySignal_AfterFork(void);
+
+#ifdef MS_WINDOWS
+/* windows.h is not included by Python.h so use void* instead of HANDLE */
+PyAPI_FUNC(void*) _PyOS_SigintEvent(void);
+#endif
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_INTRCHECK_H */
diff --git a/Include/iterobject.h b/Include/iterobject.h
new file mode 100644
index 0000000..f61726f
--- /dev/null
+++ b/Include/iterobject.h
@@ -0,0 +1,25 @@
+#ifndef Py_ITEROBJECT_H
+#define Py_ITEROBJECT_H
+/* Iterators (the basic kind, over a sequence) */
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_DATA(PyTypeObject) PySeqIter_Type;
+PyAPI_DATA(PyTypeObject) PyCallIter_Type;
+PyAPI_DATA(PyTypeObject) PyCmpWrapper_Type;
+
+#define PySeqIter_Check(op) (Py_TYPE(op) == &PySeqIter_Type)
+
+PyAPI_FUNC(PyObject *) PySeqIter_New(PyObject *);
+
+
+#define PyCallIter_Check(op) (Py_TYPE(op) == &PyCallIter_Type)
+
+PyAPI_FUNC(PyObject *) PyCallIter_New(PyObject *, PyObject *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_ITEROBJECT_H */
+
diff --git a/Include/listobject.h b/Include/listobject.h
new file mode 100644
index 0000000..6057279
--- /dev/null
+++ b/Include/listobject.h
@@ -0,0 +1,81 @@
+
+/* List object interface */
+
+/*
+Another generally useful object type is a list of object pointers.
+This is a mutable type: the list items can be changed, and items can be
+added or removed. Out-of-range indices or non-list objects are ignored.
+
+*** WARNING *** PyList_SetItem does not increment the new item's reference
+count, but does decrement the reference count of the item it replaces,
+if not nil. It does *decrement* the reference count if it is *not*
+inserted in the list. Similarly, PyList_GetItem does not increment the
+returned item's reference count.
+*/
+
+#ifndef Py_LISTOBJECT_H
+#define Py_LISTOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_VAR_HEAD
+ /* Vector of pointers to list elements. list[0] is ob_item[0], etc. */
+ PyObject **ob_item;
+
+ /* ob_item contains space for 'allocated' elements. The number
+ * currently in use is ob_size.
+ * Invariants:
+ * 0 <= ob_size <= allocated
+ * len(list) == ob_size
+ * ob_item == NULL implies ob_size == allocated == 0
+ * list.sort() temporarily sets allocated to -1 to detect mutations.
+ *
+ * Items must normally not be NULL, except during construction when
+ * the list is not yet visible outside the function that builds it.
+ */
+ Py_ssize_t allocated;
+} PyListObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PyList_Type;
+PyAPI_DATA(PyTypeObject) PyListIter_Type;
+PyAPI_DATA(PyTypeObject) PyListRevIter_Type;
+PyAPI_DATA(PyTypeObject) PySortWrapper_Type;
+
+#define PyList_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_LIST_SUBCLASS)
+#define PyList_CheckExact(op) (Py_TYPE(op) == &PyList_Type)
+
+PyAPI_FUNC(PyObject *) PyList_New(Py_ssize_t size);
+PyAPI_FUNC(Py_ssize_t) PyList_Size(PyObject *);
+PyAPI_FUNC(PyObject *) PyList_GetItem(PyObject *, Py_ssize_t);
+PyAPI_FUNC(int) PyList_SetItem(PyObject *, Py_ssize_t, PyObject *);
+PyAPI_FUNC(int) PyList_Insert(PyObject *, Py_ssize_t, PyObject *);
+PyAPI_FUNC(int) PyList_Append(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyList_GetSlice(PyObject *, Py_ssize_t, Py_ssize_t);
+PyAPI_FUNC(int) PyList_SetSlice(PyObject *, Py_ssize_t, Py_ssize_t, PyObject *);
+PyAPI_FUNC(int) PyList_Sort(PyObject *);
+PyAPI_FUNC(int) PyList_Reverse(PyObject *);
+PyAPI_FUNC(PyObject *) PyList_AsTuple(PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyList_Extend(PyListObject *, PyObject *);
+
+PyAPI_FUNC(int) PyList_ClearFreeList(void);
+PyAPI_FUNC(void) _PyList_DebugMallocStats(FILE *out);
+#endif
+
+/* Macro, trading safety for speed */
+#ifndef Py_LIMITED_API
+#define PyList_GET_ITEM(op, i) (((PyListObject *)(op))->ob_item[i])
+#define PyList_SET_ITEM(op, i, v) (((PyListObject *)(op))->ob_item[i] = (v))
+#define PyList_GET_SIZE(op) (assert(PyList_Check(op)),Py_SIZE(op))
+#define _PyList_ITEMS(op) (((PyListObject *)(op))->ob_item)
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_LISTOBJECT_H */
diff --git a/Include/longintrepr.h b/Include/longintrepr.h
new file mode 100644
index 0000000..ff4155f
--- /dev/null
+++ b/Include/longintrepr.h
@@ -0,0 +1,99 @@
+#ifndef Py_LIMITED_API
+#ifndef Py_LONGINTREPR_H
+#define Py_LONGINTREPR_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* This is published for the benefit of "friends" marshal.c and _decimal.c. */
+
+/* Parameters of the integer representation. There are two different
+ sets of parameters: one set for 30-bit digits, stored in an unsigned 32-bit
+ integer type, and one set for 15-bit digits with each digit stored in an
+ unsigned short. The value of PYLONG_BITS_IN_DIGIT, defined either at
+ configure time or in pyport.h, is used to decide which digit size to use.
+
+ Type 'digit' should be able to hold 2*PyLong_BASE-1, and type 'twodigits'
+ should be an unsigned integer type able to hold all integers up to
+ PyLong_BASE*PyLong_BASE-1. x_sub assumes that 'digit' is an unsigned type,
+ and that overflow is handled by taking the result modulo 2**N for some N >
+ PyLong_SHIFT. The majority of the code doesn't care about the precise
+ value of PyLong_SHIFT, but there are some notable exceptions:
+
+ - long_pow() requires that PyLong_SHIFT be divisible by 5
+
+ - PyLong_{As,From}ByteArray require that PyLong_SHIFT be at least 8
+
+ - long_hash() requires that PyLong_SHIFT is *strictly* less than the number
+ of bits in an unsigned long, as do the PyLong <-> long (or unsigned long)
+ conversion functions
+
+ - the Python int <-> size_t/Py_ssize_t conversion functions expect that
+ PyLong_SHIFT is strictly less than the number of bits in a size_t
+
+ - the marshal code currently expects that PyLong_SHIFT is a multiple of 15
+
+ - NSMALLNEGINTS and NSMALLPOSINTS should be small enough to fit in a single
+ digit; with the current values this forces PyLong_SHIFT >= 9
+
+ The values 15 and 30 should fit all of the above requirements, on any
+ platform.
+*/
+
+#if PYLONG_BITS_IN_DIGIT == 30
+typedef uint32_t digit;
+typedef int32_t sdigit; /* signed variant of digit */
+typedef uint64_t twodigits;
+typedef int64_t stwodigits; /* signed variant of twodigits */
+#define PyLong_SHIFT 30
+#define _PyLong_DECIMAL_SHIFT 9 /* max(e such that 10**e fits in a digit) */
+#define _PyLong_DECIMAL_BASE ((digit)1000000000) /* 10 ** DECIMAL_SHIFT */
+#elif PYLONG_BITS_IN_DIGIT == 15
+typedef unsigned short digit;
+typedef short sdigit; /* signed variant of digit */
+typedef unsigned long twodigits;
+typedef long stwodigits; /* signed variant of twodigits */
+#define PyLong_SHIFT 15
+#define _PyLong_DECIMAL_SHIFT 4 /* max(e such that 10**e fits in a digit) */
+#define _PyLong_DECIMAL_BASE ((digit)10000) /* 10 ** DECIMAL_SHIFT */
+#else
+#error "PYLONG_BITS_IN_DIGIT should be 15 or 30"
+#endif
+#define PyLong_BASE ((digit)1 << PyLong_SHIFT)
+#define PyLong_MASK ((digit)(PyLong_BASE - 1))
+
+#if PyLong_SHIFT % 5 != 0
+#error "longobject.c requires that PyLong_SHIFT be divisible by 5"
+#endif
+
+/* Long integer representation.
+ The absolute value of a number is equal to
+ SUM(for i=0 through abs(ob_size)-1) ob_digit[i] * 2**(SHIFT*i)
+ Negative numbers are represented with ob_size < 0;
+ zero is represented by ob_size == 0.
+ In a normalized number, ob_digit[abs(ob_size)-1] (the most significant
+ digit) is never zero. Also, in all cases, for all valid i,
+ 0 <= ob_digit[i] <= MASK.
+ The allocation function takes care of allocating extra memory
+ so that ob_digit[0] ... ob_digit[abs(ob_size)-1] are actually available.
+
+ CAUTION: Generic code manipulating subtypes of PyVarObject has to
+ aware that ints abuse ob_size's sign bit.
+*/
+
+struct _longobject {
+ PyObject_VAR_HEAD
+ digit ob_digit[1];
+};
+
+PyAPI_FUNC(PyLongObject *) _PyLong_New(Py_ssize_t);
+
+/* Return a copy of src. */
+PyAPI_FUNC(PyObject *) _PyLong_Copy(PyLongObject *src);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_LONGINTREPR_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/longobject.h b/Include/longobject.h
new file mode 100644
index 0000000..7bdd047
--- /dev/null
+++ b/Include/longobject.h
@@ -0,0 +1,220 @@
+#ifndef Py_LONGOBJECT_H
+#define Py_LONGOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Long (arbitrary precision) integer object interface */
+
+typedef struct _longobject PyLongObject; /* Revealed in longintrepr.h */
+
+PyAPI_DATA(PyTypeObject) PyLong_Type;
+
+#define PyLong_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_LONG_SUBCLASS)
+#define PyLong_CheckExact(op) (Py_TYPE(op) == &PyLong_Type)
+
+PyAPI_FUNC(PyObject *) PyLong_FromLong(long);
+PyAPI_FUNC(PyObject *) PyLong_FromUnsignedLong(unsigned long);
+PyAPI_FUNC(PyObject *) PyLong_FromSize_t(size_t);
+PyAPI_FUNC(PyObject *) PyLong_FromSsize_t(Py_ssize_t);
+PyAPI_FUNC(PyObject *) PyLong_FromDouble(double);
+PyAPI_FUNC(long) PyLong_AsLong(PyObject *);
+PyAPI_FUNC(long) PyLong_AsLongAndOverflow(PyObject *, int *);
+PyAPI_FUNC(Py_ssize_t) PyLong_AsSsize_t(PyObject *);
+PyAPI_FUNC(size_t) PyLong_AsSize_t(PyObject *);
+PyAPI_FUNC(unsigned long) PyLong_AsUnsignedLong(PyObject *);
+PyAPI_FUNC(unsigned long) PyLong_AsUnsignedLongMask(PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyLong_AsInt(PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyLong_GetInfo(void);
+
+/* It may be useful in the future. I've added it in the PyInt -> PyLong
+ cleanup to keep the extra information. [CH] */
+#define PyLong_AS_LONG(op) PyLong_AsLong(op)
+
+/* Issue #1983: pid_t can be longer than a C long on some systems */
+#if !defined(SIZEOF_PID_T) || SIZEOF_PID_T == SIZEOF_INT
+#define _Py_PARSE_PID "i"
+#define PyLong_FromPid PyLong_FromLong
+#define PyLong_AsPid PyLong_AsLong
+#elif SIZEOF_PID_T == SIZEOF_LONG
+#define _Py_PARSE_PID "l"
+#define PyLong_FromPid PyLong_FromLong
+#define PyLong_AsPid PyLong_AsLong
+#elif defined(SIZEOF_LONG_LONG) && SIZEOF_PID_T == SIZEOF_LONG_LONG
+#define _Py_PARSE_PID "L"
+#define PyLong_FromPid PyLong_FromLongLong
+#define PyLong_AsPid PyLong_AsLongLong
+#else
+#error "sizeof(pid_t) is neither sizeof(int), sizeof(long) or sizeof(long long)"
+#endif /* SIZEOF_PID_T */
+
+#if SIZEOF_VOID_P == SIZEOF_INT
+# define _Py_PARSE_INTPTR "i"
+# define _Py_PARSE_UINTPTR "I"
+#elif SIZEOF_VOID_P == SIZEOF_LONG
+# define _Py_PARSE_INTPTR "l"
+# define _Py_PARSE_UINTPTR "k"
+#elif defined(SIZEOF_LONG_LONG) && SIZEOF_VOID_P == SIZEOF_LONG_LONG
+# define _Py_PARSE_INTPTR "L"
+# define _Py_PARSE_UINTPTR "K"
+#else
+# error "void* different in size from int, long and long long"
+#endif /* SIZEOF_VOID_P */
+
+/* Used by Python/mystrtoul.c, _PyBytes_FromHex(),
+ _PyBytes_DecodeEscapeRecode(), etc. */
+#ifndef Py_LIMITED_API
+PyAPI_DATA(unsigned char) _PyLong_DigitValue[256];
+#endif
+
+/* _PyLong_Frexp returns a double x and an exponent e such that the
+ true value is approximately equal to x * 2**e. e is >= 0. x is
+ 0.0 if and only if the input is 0 (in which case, e and x are both
+ zeroes); otherwise, 0.5 <= abs(x) < 1.0. On overflow, which is
+ possible if the number of bits doesn't fit into a Py_ssize_t, sets
+ OverflowError and returns -1.0 for x, 0 for e. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(double) _PyLong_Frexp(PyLongObject *a, Py_ssize_t *e);
+#endif
+
+PyAPI_FUNC(double) PyLong_AsDouble(PyObject *);
+PyAPI_FUNC(PyObject *) PyLong_FromVoidPtr(void *);
+PyAPI_FUNC(void *) PyLong_AsVoidPtr(PyObject *);
+
+PyAPI_FUNC(PyObject *) PyLong_FromLongLong(long long);
+PyAPI_FUNC(PyObject *) PyLong_FromUnsignedLongLong(unsigned long long);
+PyAPI_FUNC(long long) PyLong_AsLongLong(PyObject *);
+PyAPI_FUNC(unsigned long long) PyLong_AsUnsignedLongLong(PyObject *);
+PyAPI_FUNC(unsigned long long) PyLong_AsUnsignedLongLongMask(PyObject *);
+PyAPI_FUNC(long long) PyLong_AsLongLongAndOverflow(PyObject *, int *);
+
+PyAPI_FUNC(PyObject *) PyLong_FromString(const char *, char **, int);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyLong_FromUnicode(Py_UNICODE*, Py_ssize_t, int) Py_DEPRECATED(3.3);
+PyAPI_FUNC(PyObject *) PyLong_FromUnicodeObject(PyObject *u, int base);
+PyAPI_FUNC(PyObject *) _PyLong_FromBytes(const char *, Py_ssize_t, int);
+#endif
+
+#ifndef Py_LIMITED_API
+/* _PyLong_Sign. Return 0 if v is 0, -1 if v < 0, +1 if v > 0.
+ v must not be NULL, and must be a normalized long.
+ There are no error cases.
+*/
+PyAPI_FUNC(int) _PyLong_Sign(PyObject *v);
+
+
+/* _PyLong_NumBits. Return the number of bits needed to represent the
+ absolute value of a long. For example, this returns 1 for 1 and -1, 2
+ for 2 and -2, and 2 for 3 and -3. It returns 0 for 0.
+ v must not be NULL, and must be a normalized long.
+ (size_t)-1 is returned and OverflowError set if the true result doesn't
+ fit in a size_t.
+*/
+PyAPI_FUNC(size_t) _PyLong_NumBits(PyObject *v);
+
+/* _PyLong_DivmodNear. Given integers a and b, compute the nearest
+ integer q to the exact quotient a / b, rounding to the nearest even integer
+ in the case of a tie. Return (q, r), where r = a - q*b. The remainder r
+ will satisfy abs(r) <= abs(b)/2, with equality possible only if q is
+ even.
+*/
+PyAPI_FUNC(PyObject *) _PyLong_DivmodNear(PyObject *, PyObject *);
+
+/* _PyLong_FromByteArray: View the n unsigned bytes as a binary integer in
+ base 256, and return a Python int with the same numeric value.
+ If n is 0, the integer is 0. Else:
+ If little_endian is 1/true, bytes[n-1] is the MSB and bytes[0] the LSB;
+ else (little_endian is 0/false) bytes[0] is the MSB and bytes[n-1] the
+ LSB.
+ If is_signed is 0/false, view the bytes as a non-negative integer.
+ If is_signed is 1/true, view the bytes as a 2's-complement integer,
+ non-negative if bit 0x80 of the MSB is clear, negative if set.
+ Error returns:
+ + Return NULL with the appropriate exception set if there's not
+ enough memory to create the Python int.
+*/
+PyAPI_FUNC(PyObject *) _PyLong_FromByteArray(
+ const unsigned char* bytes, size_t n,
+ int little_endian, int is_signed);
+
+/* _PyLong_AsByteArray: Convert the least-significant 8*n bits of long
+ v to a base-256 integer, stored in array bytes. Normally return 0,
+ return -1 on error.
+ If little_endian is 1/true, store the MSB at bytes[n-1] and the LSB at
+ bytes[0]; else (little_endian is 0/false) store the MSB at bytes[0] and
+ the LSB at bytes[n-1].
+ If is_signed is 0/false, it's an error if v < 0; else (v >= 0) n bytes
+ are filled and there's nothing special about bit 0x80 of the MSB.
+ If is_signed is 1/true, bytes is filled with the 2's-complement
+ representation of v's value. Bit 0x80 of the MSB is the sign bit.
+ Error returns (-1):
+ + is_signed is 0 and v < 0. TypeError is set in this case, and bytes
+ isn't altered.
+ + n isn't big enough to hold the full mathematical value of v. For
+ example, if is_signed is 0 and there are more digits in the v than
+ fit in n; or if is_signed is 1, v < 0, and n is just 1 bit shy of
+ being large enough to hold a sign bit. OverflowError is set in this
+ case, but bytes holds the least-significant n bytes of the true value.
+*/
+PyAPI_FUNC(int) _PyLong_AsByteArray(PyLongObject* v,
+ unsigned char* bytes, size_t n,
+ int little_endian, int is_signed);
+
+/* _PyLong_FromNbInt: Convert the given object to a PyLongObject
+ using the nb_int slot, if available. Raise TypeError if either the
+ nb_int slot is not available or the result of the call to nb_int
+ returns something not of type int.
+*/
+PyAPI_FUNC(PyLongObject *)_PyLong_FromNbInt(PyObject *);
+
+/* _PyLong_Format: Convert the long to a string object with given base,
+ appending a base prefix of 0[box] if base is 2, 8 or 16. */
+PyAPI_FUNC(PyObject *) _PyLong_Format(PyObject *obj, int base);
+
+PyAPI_FUNC(int) _PyLong_FormatWriter(
+ _PyUnicodeWriter *writer,
+ PyObject *obj,
+ int base,
+ int alternate);
+
+PyAPI_FUNC(char*) _PyLong_FormatBytesWriter(
+ _PyBytesWriter *writer,
+ char *str,
+ PyObject *obj,
+ int base,
+ int alternate);
+
+/* Format the object based on the format_spec, as defined in PEP 3101
+ (Advanced String Formatting). */
+PyAPI_FUNC(int) _PyLong_FormatAdvancedWriter(
+ _PyUnicodeWriter *writer,
+ PyObject *obj,
+ PyObject *format_spec,
+ Py_ssize_t start,
+ Py_ssize_t end);
+#endif /* Py_LIMITED_API */
+
+/* These aren't really part of the int object, but they're handy. The
+ functions are in Python/mystrtoul.c.
+ */
+PyAPI_FUNC(unsigned long) PyOS_strtoul(const char *, char **, int);
+PyAPI_FUNC(long) PyOS_strtol(const char *, char **, int);
+
+#ifndef Py_LIMITED_API
+/* For use by the gcd function in mathmodule.c */
+PyAPI_FUNC(PyObject *) _PyLong_GCD(PyObject *, PyObject *);
+#endif /* !Py_LIMITED_API */
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(PyObject *) _PyLong_Zero;
+PyAPI_DATA(PyObject *) _PyLong_One;
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_LONGOBJECT_H */
diff --git a/Include/marshal.h b/Include/marshal.h
new file mode 100644
index 0000000..09d9337
--- /dev/null
+++ b/Include/marshal.h
@@ -0,0 +1,28 @@
+
+/* Interface for marshal.c */
+
+#ifndef Py_MARSHAL_H
+#define Py_MARSHAL_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define Py_MARSHAL_VERSION 4
+
+PyAPI_FUNC(void) PyMarshal_WriteLongToFile(long, FILE *, int);
+PyAPI_FUNC(void) PyMarshal_WriteObjectToFile(PyObject *, FILE *, int);
+PyAPI_FUNC(PyObject *) PyMarshal_WriteObjectToString(PyObject *, int);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(long) PyMarshal_ReadLongFromFile(FILE *);
+PyAPI_FUNC(int) PyMarshal_ReadShortFromFile(FILE *);
+PyAPI_FUNC(PyObject *) PyMarshal_ReadObjectFromFile(FILE *);
+PyAPI_FUNC(PyObject *) PyMarshal_ReadLastObjectFromFile(FILE *);
+#endif
+PyAPI_FUNC(PyObject *) PyMarshal_ReadObjectFromString(const char *,
+ Py_ssize_t);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_MARSHAL_H */
diff --git a/Include/memoryobject.h b/Include/memoryobject.h
new file mode 100644
index 0000000..990a716
--- /dev/null
+++ b/Include/memoryobject.h
@@ -0,0 +1,72 @@
+/* Memory view object. In Python this is available as "memoryview". */
+
+#ifndef Py_MEMORYOBJECT_H
+#define Py_MEMORYOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(PyTypeObject) _PyManagedBuffer_Type;
+#endif
+PyAPI_DATA(PyTypeObject) PyMemoryView_Type;
+
+#define PyMemoryView_Check(op) (Py_TYPE(op) == &PyMemoryView_Type)
+
+#ifndef Py_LIMITED_API
+/* Get a pointer to the memoryview's private copy of the exporter's buffer. */
+#define PyMemoryView_GET_BUFFER(op) (&((PyMemoryViewObject *)(op))->view)
+/* Get a pointer to the exporting object (this may be NULL!). */
+#define PyMemoryView_GET_BASE(op) (((PyMemoryViewObject *)(op))->view.obj)
+#endif
+
+PyAPI_FUNC(PyObject *) PyMemoryView_FromObject(PyObject *base);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject *) PyMemoryView_FromMemory(char *mem, Py_ssize_t size,
+ int flags);
+#endif
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyMemoryView_FromBuffer(Py_buffer *info);
+#endif
+PyAPI_FUNC(PyObject *) PyMemoryView_GetContiguous(PyObject *base,
+ int buffertype,
+ char order);
+
+
+/* The structs are declared here so that macros can work, but they shouldn't
+ be considered public. Don't access their fields directly, use the macros
+ and functions instead! */
+#ifndef Py_LIMITED_API
+#define _Py_MANAGED_BUFFER_RELEASED 0x001 /* access to exporter blocked */
+#define _Py_MANAGED_BUFFER_FREE_FORMAT 0x002 /* free format */
+typedef struct {
+ PyObject_HEAD
+ int flags; /* state flags */
+ Py_ssize_t exports; /* number of direct memoryview exports */
+ Py_buffer master; /* snapshot buffer obtained from the original exporter */
+} _PyManagedBufferObject;
+
+
+/* memoryview state flags */
+#define _Py_MEMORYVIEW_RELEASED 0x001 /* access to master buffer blocked */
+#define _Py_MEMORYVIEW_C 0x002 /* C-contiguous layout */
+#define _Py_MEMORYVIEW_FORTRAN 0x004 /* Fortran contiguous layout */
+#define _Py_MEMORYVIEW_SCALAR 0x008 /* scalar: ndim = 0 */
+#define _Py_MEMORYVIEW_PIL 0x010 /* PIL-style layout */
+
+typedef struct {
+ PyObject_VAR_HEAD
+ _PyManagedBufferObject *mbuf; /* managed buffer */
+ Py_hash_t hash; /* hash value for read-only views */
+ int flags; /* state flags */
+ Py_ssize_t exports; /* number of buffer re-exports */
+ Py_buffer view; /* private copy of the exporter's view */
+ PyObject *weakreflist;
+ Py_ssize_t ob_array[1]; /* shape, strides, suboffsets */
+} PyMemoryViewObject;
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_MEMORYOBJECT_H */
diff --git a/Include/metagrammar.h b/Include/metagrammar.h
new file mode 100644
index 0000000..15c8ef8
--- /dev/null
+++ b/Include/metagrammar.h
@@ -0,0 +1,18 @@
+#ifndef Py_METAGRAMMAR_H
+#define Py_METAGRAMMAR_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+#define MSTART 256
+#define RULE 257
+#define RHS 258
+#define ALT 259
+#define ITEM 260
+#define ATOM 261
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_METAGRAMMAR_H */
diff --git a/Include/methodobject.h b/Include/methodobject.h
new file mode 100644
index 0000000..ea35d86
--- /dev/null
+++ b/Include/methodobject.h
@@ -0,0 +1,135 @@
+
+/* Method object interface */
+
+#ifndef Py_METHODOBJECT_H
+#define Py_METHODOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* This is about the type 'builtin_function_or_method',
+ not Python methods in user-defined classes. See classobject.h
+ for the latter. */
+
+PyAPI_DATA(PyTypeObject) PyCFunction_Type;
+
+#define PyCFunction_Check(op) (Py_TYPE(op) == &PyCFunction_Type)
+
+typedef PyObject *(*PyCFunction)(PyObject *, PyObject *);
+typedef PyObject *(*_PyCFunctionFast) (PyObject *, PyObject *const *, Py_ssize_t);
+typedef PyObject *(*PyCFunctionWithKeywords)(PyObject *, PyObject *,
+ PyObject *);
+typedef PyObject *(*_PyCFunctionFastWithKeywords) (PyObject *,
+ PyObject *const *, Py_ssize_t,
+ PyObject *);
+typedef PyObject *(*PyNoArgsFunction)(PyObject *);
+
+PyAPI_FUNC(PyCFunction) PyCFunction_GetFunction(PyObject *);
+PyAPI_FUNC(PyObject *) PyCFunction_GetSelf(PyObject *);
+PyAPI_FUNC(int) PyCFunction_GetFlags(PyObject *);
+
+/* Macros for direct access to these values. Type checks are *not*
+ done, so use with care. */
+#ifndef Py_LIMITED_API
+#define PyCFunction_GET_FUNCTION(func) \
+ (((PyCFunctionObject *)func) -> m_ml -> ml_meth)
+#define PyCFunction_GET_SELF(func) \
+ (((PyCFunctionObject *)func) -> m_ml -> ml_flags & METH_STATIC ? \
+ NULL : ((PyCFunctionObject *)func) -> m_self)
+#define PyCFunction_GET_FLAGS(func) \
+ (((PyCFunctionObject *)func) -> m_ml -> ml_flags)
+#endif
+PyAPI_FUNC(PyObject *) PyCFunction_Call(PyObject *, PyObject *, PyObject *);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyCFunction_FastCallDict(PyObject *func,
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwargs);
+
+PyAPI_FUNC(PyObject *) _PyCFunction_FastCallKeywords(PyObject *func,
+ PyObject *const *stack,
+ Py_ssize_t nargs,
+ PyObject *kwnames);
+#endif
+
+struct PyMethodDef {
+ const char *ml_name; /* The name of the built-in function/method */
+ PyCFunction ml_meth; /* The C function that implements it */
+ int ml_flags; /* Combination of METH_xxx flags, which mostly
+ describe the args expected by the C func */
+ const char *ml_doc; /* The __doc__ attribute, or NULL */
+};
+typedef struct PyMethodDef PyMethodDef;
+
+#define PyCFunction_New(ML, SELF) PyCFunction_NewEx((ML), (SELF), NULL)
+PyAPI_FUNC(PyObject *) PyCFunction_NewEx(PyMethodDef *, PyObject *,
+ PyObject *);
+
+/* Flag passed to newmethodobject */
+/* #define METH_OLDARGS 0x0000 -- unsupported now */
+#define METH_VARARGS 0x0001
+#define METH_KEYWORDS 0x0002
+/* METH_NOARGS and METH_O must not be combined with the flags above. */
+#define METH_NOARGS 0x0004
+#define METH_O 0x0008
+
+/* METH_CLASS and METH_STATIC are a little different; these control
+ the construction of methods for a class. These cannot be used for
+ functions in modules. */
+#define METH_CLASS 0x0010
+#define METH_STATIC 0x0020
+
+/* METH_COEXIST allows a method to be entered even though a slot has
+ already filled the entry. When defined, the flag allows a separate
+ method, "__contains__" for example, to coexist with a defined
+ slot like sq_contains. */
+
+#define METH_COEXIST 0x0040
+
+#ifndef Py_LIMITED_API
+#define METH_FASTCALL 0x0080
+#endif
+
+/* This bit is preserved for Stackless Python */
+#ifdef STACKLESS
+#define METH_STACKLESS 0x0100
+#else
+#define METH_STACKLESS 0x0000
+#endif
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_HEAD
+ PyMethodDef *m_ml; /* Description of the C function to call */
+ PyObject *m_self; /* Passed as 'self' arg to the C func, can be NULL */
+ PyObject *m_module; /* The __module__ attribute, can be anything */
+ PyObject *m_weakreflist; /* List of weak references */
+} PyCFunctionObject;
+
+PyAPI_FUNC(PyObject *) _PyMethodDef_RawFastCallDict(
+ PyMethodDef *method,
+ PyObject *self,
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwargs);
+
+PyAPI_FUNC(PyObject *) _PyMethodDef_RawFastCallKeywords(
+ PyMethodDef *method,
+ PyObject *self,
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwnames);
+#endif
+
+PyAPI_FUNC(int) PyCFunction_ClearFreeList(void);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyCFunction_DebugMallocStats(FILE *out);
+PyAPI_FUNC(void) _PyMethod_DebugMallocStats(FILE *out);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_METHODOBJECT_H */
diff --git a/Include/modsupport.h b/Include/modsupport.h
new file mode 100644
index 0000000..a238bef
--- /dev/null
+++ b/Include/modsupport.h
@@ -0,0 +1,229 @@
+
+#ifndef Py_MODSUPPORT_H
+#define Py_MODSUPPORT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Module support interface */
+
+#include
+
+/* If PY_SSIZE_T_CLEAN is defined, each functions treats #-specifier
+ to mean Py_ssize_t */
+#ifdef PY_SSIZE_T_CLEAN
+#define PyArg_Parse _PyArg_Parse_SizeT
+#define PyArg_ParseTuple _PyArg_ParseTuple_SizeT
+#define PyArg_ParseTupleAndKeywords _PyArg_ParseTupleAndKeywords_SizeT
+#define PyArg_VaParse _PyArg_VaParse_SizeT
+#define PyArg_VaParseTupleAndKeywords _PyArg_VaParseTupleAndKeywords_SizeT
+#define Py_BuildValue _Py_BuildValue_SizeT
+#define Py_VaBuildValue _Py_VaBuildValue_SizeT
+#ifndef Py_LIMITED_API
+#define _Py_VaBuildStack _Py_VaBuildStack_SizeT
+#endif
+#else
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _Py_VaBuildValue_SizeT(const char *, va_list);
+PyAPI_FUNC(PyObject **) _Py_VaBuildStack_SizeT(
+ PyObject **small_stack,
+ Py_ssize_t small_stack_len,
+ const char *format,
+ va_list va,
+ Py_ssize_t *p_nargs);
+#endif /* !Py_LIMITED_API */
+#endif
+
+/* Due to a glitch in 3.2, the _SizeT versions weren't exported from the DLL. */
+#if !defined(PY_SSIZE_T_CLEAN) || !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(int) PyArg_Parse(PyObject *, const char *, ...);
+PyAPI_FUNC(int) PyArg_ParseTuple(PyObject *, const char *, ...);
+PyAPI_FUNC(int) PyArg_ParseTupleAndKeywords(PyObject *, PyObject *,
+ const char *, char **, ...);
+PyAPI_FUNC(int) PyArg_VaParse(PyObject *, const char *, va_list);
+PyAPI_FUNC(int) PyArg_VaParseTupleAndKeywords(PyObject *, PyObject *,
+ const char *, char **, va_list);
+#endif
+PyAPI_FUNC(int) PyArg_ValidateKeywordArguments(PyObject *);
+PyAPI_FUNC(int) PyArg_UnpackTuple(PyObject *, const char *, Py_ssize_t, Py_ssize_t, ...);
+PyAPI_FUNC(PyObject *) Py_BuildValue(const char *, ...);
+PyAPI_FUNC(PyObject *) _Py_BuildValue_SizeT(const char *, ...);
+
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyArg_UnpackStack(
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ const char *name,
+ Py_ssize_t min,
+ Py_ssize_t max,
+ ...);
+
+PyAPI_FUNC(int) _PyArg_NoKeywords(const char *funcname, PyObject *kwargs);
+PyAPI_FUNC(int) _PyArg_NoPositional(const char *funcname, PyObject *args);
+#define _PyArg_NoKeywords(funcname, kwargs) \
+ ((kwargs) == NULL || _PyArg_NoKeywords((funcname), (kwargs)))
+#define _PyArg_NoPositional(funcname, args) \
+ ((args) == NULL || _PyArg_NoPositional((funcname), (args)))
+
+#endif
+
+PyAPI_FUNC(PyObject *) Py_VaBuildValue(const char *, va_list);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject **) _Py_VaBuildStack(
+ PyObject **small_stack,
+ Py_ssize_t small_stack_len,
+ const char *format,
+ va_list va,
+ Py_ssize_t *p_nargs);
+#endif
+
+#ifndef Py_LIMITED_API
+typedef struct _PyArg_Parser {
+ const char *format;
+ const char * const *keywords;
+ const char *fname;
+ const char *custom_msg;
+ int pos; /* number of positional-only arguments */
+ int min; /* minimal number of arguments */
+ int max; /* maximal number of positional arguments */
+ PyObject *kwtuple; /* tuple of keyword parameter names */
+ struct _PyArg_Parser *next;
+} _PyArg_Parser;
+#ifdef PY_SSIZE_T_CLEAN
+#define _PyArg_ParseTupleAndKeywordsFast _PyArg_ParseTupleAndKeywordsFast_SizeT
+#define _PyArg_ParseStack _PyArg_ParseStack_SizeT
+#define _PyArg_ParseStackAndKeywords _PyArg_ParseStackAndKeywords_SizeT
+#define _PyArg_VaParseTupleAndKeywordsFast _PyArg_VaParseTupleAndKeywordsFast_SizeT
+#endif
+PyAPI_FUNC(int) _PyArg_ParseTupleAndKeywordsFast(PyObject *, PyObject *,
+ struct _PyArg_Parser *, ...);
+PyAPI_FUNC(int) _PyArg_ParseStack(
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ const char *format,
+ ...);
+PyAPI_FUNC(int) _PyArg_ParseStackAndKeywords(
+ PyObject *const *args,
+ Py_ssize_t nargs,
+ PyObject *kwnames,
+ struct _PyArg_Parser *,
+ ...);
+PyAPI_FUNC(int) _PyArg_VaParseTupleAndKeywordsFast(PyObject *, PyObject *,
+ struct _PyArg_Parser *, va_list);
+void _PyArg_Fini(void);
+#endif /* Py_LIMITED_API */
+
+PyAPI_FUNC(int) PyModule_AddObject(PyObject *, const char *, PyObject *);
+PyAPI_FUNC(int) PyModule_AddIntConstant(PyObject *, const char *, long);
+PyAPI_FUNC(int) PyModule_AddStringConstant(PyObject *, const char *, const char *);
+#define PyModule_AddIntMacro(m, c) PyModule_AddIntConstant(m, #c, c)
+#define PyModule_AddStringMacro(m, c) PyModule_AddStringConstant(m, #c, c)
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* New in 3.5 */
+PyAPI_FUNC(int) PyModule_SetDocString(PyObject *, const char *);
+PyAPI_FUNC(int) PyModule_AddFunctions(PyObject *, PyMethodDef *);
+PyAPI_FUNC(int) PyModule_ExecDef(PyObject *module, PyModuleDef *def);
+#endif
+
+#define Py_CLEANUP_SUPPORTED 0x20000
+
+#define PYTHON_API_VERSION 1013
+#define PYTHON_API_STRING "1013"
+/* The API version is maintained (independently from the Python version)
+ so we can detect mismatches between the interpreter and dynamically
+ loaded modules. These are diagnosed by an error message but
+ the module is still loaded (because the mismatch can only be tested
+ after loading the module). The error message is intended to
+ explain the core dump a few seconds later.
+
+ The symbol PYTHON_API_STRING defines the same value as a string
+ literal. *** PLEASE MAKE SURE THE DEFINITIONS MATCH. ***
+
+ Please add a line or two to the top of this log for each API
+ version change:
+
+ 22-Feb-2006 MvL 1013 PEP 353 - long indices for sequence lengths
+
+ 19-Aug-2002 GvR 1012 Changes to string object struct for
+ interning changes, saving 3 bytes.
+
+ 17-Jul-2001 GvR 1011 Descr-branch, just to be on the safe side
+
+ 25-Jan-2001 FLD 1010 Parameters added to PyCode_New() and
+ PyFrame_New(); Python 2.1a2
+
+ 14-Mar-2000 GvR 1009 Unicode API added
+
+ 3-Jan-1999 GvR 1007 Decided to change back! (Don't reuse 1008!)
+
+ 3-Dec-1998 GvR 1008 Python 1.5.2b1
+
+ 18-Jan-1997 GvR 1007 string interning and other speedups
+
+ 11-Oct-1996 GvR renamed Py_Ellipses to Py_Ellipsis :-(
+
+ 30-Jul-1996 GvR Slice and ellipses syntax added
+
+ 23-Jul-1996 GvR For 1.4 -- better safe than sorry this time :-)
+
+ 7-Nov-1995 GvR Keyword arguments (should've been done at 1.3 :-( )
+
+ 10-Jan-1995 GvR Renamed globals to new naming scheme
+
+ 9-Jan-1995 GvR Initial version (incompatible with older API)
+*/
+
+/* The PYTHON_ABI_VERSION is introduced in PEP 384. For the lifetime of
+ Python 3, it will stay at the value of 3; changes to the limited API
+ must be performed in a strictly backwards-compatible manner. */
+#define PYTHON_ABI_VERSION 3
+#define PYTHON_ABI_STRING "3"
+
+#ifdef Py_TRACE_REFS
+ /* When we are tracing reference counts, rename module creation functions so
+ modules compiled with incompatible settings will generate a
+ link-time error. */
+ #define PyModule_Create2 PyModule_Create2TraceRefs
+ #define PyModule_FromDefAndSpec2 PyModule_FromDefAndSpec2TraceRefs
+#endif
+
+PyAPI_FUNC(PyObject *) PyModule_Create2(struct PyModuleDef*,
+ int apiver);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyModule_CreateInitialized(struct PyModuleDef*,
+ int apiver);
+#endif
+
+#ifdef Py_LIMITED_API
+#define PyModule_Create(module) \
+ PyModule_Create2(module, PYTHON_ABI_VERSION)
+#else
+#define PyModule_Create(module) \
+ PyModule_Create2(module, PYTHON_API_VERSION)
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* New in 3.5 */
+PyAPI_FUNC(PyObject *) PyModule_FromDefAndSpec2(PyModuleDef *def,
+ PyObject *spec,
+ int module_api_version);
+
+#ifdef Py_LIMITED_API
+#define PyModule_FromDefAndSpec(module, spec) \
+ PyModule_FromDefAndSpec2(module, spec, PYTHON_ABI_VERSION)
+#else
+#define PyModule_FromDefAndSpec(module, spec) \
+ PyModule_FromDefAndSpec2(module, spec, PYTHON_API_VERSION)
+#endif /* Py_LIMITED_API */
+#endif /* New in 3.5 */
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(const char *) _Py_PackageContext;
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_MODSUPPORT_H */
diff --git a/Include/moduleobject.h b/Include/moduleobject.h
new file mode 100644
index 0000000..1d8fe46
--- /dev/null
+++ b/Include/moduleobject.h
@@ -0,0 +1,89 @@
+
+/* Module object interface */
+
+#ifndef Py_MODULEOBJECT_H
+#define Py_MODULEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_DATA(PyTypeObject) PyModule_Type;
+
+#define PyModule_Check(op) PyObject_TypeCheck(op, &PyModule_Type)
+#define PyModule_CheckExact(op) (Py_TYPE(op) == &PyModule_Type)
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject *) PyModule_NewObject(
+ PyObject *name
+ );
+#endif
+PyAPI_FUNC(PyObject *) PyModule_New(
+ const char *name /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(PyObject *) PyModule_GetDict(PyObject *);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject *) PyModule_GetNameObject(PyObject *);
+#endif
+PyAPI_FUNC(const char *) PyModule_GetName(PyObject *);
+PyAPI_FUNC(const char *) PyModule_GetFilename(PyObject *) Py_DEPRECATED(3.2);
+PyAPI_FUNC(PyObject *) PyModule_GetFilenameObject(PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyModule_Clear(PyObject *);
+PyAPI_FUNC(void) _PyModule_ClearDict(PyObject *);
+#endif
+PyAPI_FUNC(struct PyModuleDef*) PyModule_GetDef(PyObject*);
+PyAPI_FUNC(void*) PyModule_GetState(PyObject*);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* New in 3.5 */
+PyAPI_FUNC(PyObject *) PyModuleDef_Init(struct PyModuleDef*);
+PyAPI_DATA(PyTypeObject) PyModuleDef_Type;
+#endif
+
+typedef struct PyModuleDef_Base {
+ PyObject_HEAD
+ PyObject* (*m_init)(void);
+ Py_ssize_t m_index;
+ PyObject* m_copy;
+} PyModuleDef_Base;
+
+#define PyModuleDef_HEAD_INIT { \
+ PyObject_HEAD_INIT(NULL) \
+ NULL, /* m_init */ \
+ 0, /* m_index */ \
+ NULL, /* m_copy */ \
+ }
+
+struct PyModuleDef_Slot;
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* New in 3.5 */
+typedef struct PyModuleDef_Slot{
+ int slot;
+ void *value;
+} PyModuleDef_Slot;
+
+#define Py_mod_create 1
+#define Py_mod_exec 2
+
+#ifndef Py_LIMITED_API
+#define _Py_mod_LAST_SLOT 2
+#endif
+
+#endif /* New in 3.5 */
+
+typedef struct PyModuleDef{
+ PyModuleDef_Base m_base;
+ const char* m_name;
+ const char* m_doc;
+ Py_ssize_t m_size;
+ PyMethodDef *m_methods;
+ struct PyModuleDef_Slot* m_slots;
+ traverseproc m_traverse;
+ inquiry m_clear;
+ freefunc m_free;
+} PyModuleDef;
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_MODULEOBJECT_H */
diff --git a/Include/namespaceobject.h b/Include/namespaceobject.h
new file mode 100644
index 0000000..0c8d95c
--- /dev/null
+++ b/Include/namespaceobject.h
@@ -0,0 +1,19 @@
+
+/* simple namespace object interface */
+
+#ifndef NAMESPACEOBJECT_H
+#define NAMESPACEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(PyTypeObject) _PyNamespace_Type;
+
+PyAPI_FUNC(PyObject *) _PyNamespace_New(PyObject *kwds);
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !NAMESPACEOBJECT_H */
diff --git a/Include/node.h b/Include/node.h
new file mode 100644
index 0000000..40596df
--- /dev/null
+++ b/Include/node.h
@@ -0,0 +1,44 @@
+
+/* Parse tree node interface */
+
+#ifndef Py_NODE_H
+#define Py_NODE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct _node {
+ short n_type;
+ char *n_str;
+ int n_lineno;
+ int n_col_offset;
+ int n_nchildren;
+ struct _node *n_child;
+} node;
+
+PyAPI_FUNC(node *) PyNode_New(int type);
+PyAPI_FUNC(int) PyNode_AddChild(node *n, int type,
+ char *str, int lineno, int col_offset);
+PyAPI_FUNC(void) PyNode_Free(node *n);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) _PyNode_SizeOf(node *n);
+#endif
+
+/* Node access functions */
+#define NCH(n) ((n)->n_nchildren)
+
+#define CHILD(n, i) (&(n)->n_child[i])
+#define RCHILD(n, i) (CHILD(n, NCH(n) + i))
+#define TYPE(n) ((n)->n_type)
+#define STR(n) ((n)->n_str)
+#define LINENO(n) ((n)->n_lineno)
+
+/* Assert that the type of a node is what we expect */
+#define REQ(n, type) assert(TYPE(n) == (type))
+
+PyAPI_FUNC(void) PyNode_ListTree(node *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_NODE_H */
diff --git a/Include/object.h b/Include/object.h
new file mode 100644
index 0000000..c772dea
--- /dev/null
+++ b/Include/object.h
@@ -0,0 +1,1104 @@
+#ifndef Py_OBJECT_H
+#define Py_OBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Object and type object interface */
+
+/*
+Objects are structures allocated on the heap. Special rules apply to
+the use of objects to ensure they are properly garbage-collected.
+Objects are never allocated statically or on the stack; they must be
+accessed through special macros and functions only. (Type objects are
+exceptions to the first rule; the standard types are represented by
+statically initialized type objects, although work on type/class unification
+for Python 2.2 made it possible to have heap-allocated type objects too).
+
+An object has a 'reference count' that is increased or decreased when a
+pointer to the object is copied or deleted; when the reference count
+reaches zero there are no references to the object left and it can be
+removed from the heap.
+
+An object has a 'type' that determines what it represents and what kind
+of data it contains. An object's type is fixed when it is created.
+Types themselves are represented as objects; an object contains a
+pointer to the corresponding type object. The type itself has a type
+pointer pointing to the object representing the type 'type', which
+contains a pointer to itself!).
+
+Objects do not float around in memory; once allocated an object keeps
+the same size and address. Objects that must hold variable-size data
+can contain pointers to variable-size parts of the object. Not all
+objects of the same type have the same size; but the size cannot change
+after allocation. (These restrictions are made so a reference to an
+object can be simply a pointer -- moving an object would require
+updating all the pointers, and changing an object's size would require
+moving it if there was another object right next to it.)
+
+Objects are always accessed through pointers of the type 'PyObject *'.
+The type 'PyObject' is a structure that only contains the reference count
+and the type pointer. The actual memory allocated for an object
+contains other data that can only be accessed after casting the pointer
+to a pointer to a longer structure type. This longer type must start
+with the reference count and type fields; the macro PyObject_HEAD should be
+used for this (to accommodate for future changes). The implementation
+of a particular object type can cast the object pointer to the proper
+type and back.
+
+A standard interface exists for objects that contain an array of items
+whose size is determined when the object is allocated.
+*/
+
+/* Py_DEBUG implies Py_TRACE_REFS. */
+#if defined(Py_DEBUG) && !defined(Py_TRACE_REFS)
+#define Py_TRACE_REFS
+#endif
+
+/* Py_TRACE_REFS implies Py_REF_DEBUG. */
+#if defined(Py_TRACE_REFS) && !defined(Py_REF_DEBUG)
+#define Py_REF_DEBUG
+#endif
+
+#if defined(Py_LIMITED_API) && defined(Py_REF_DEBUG)
+#error Py_LIMITED_API is incompatible with Py_DEBUG, Py_TRACE_REFS, and Py_REF_DEBUG
+#endif
+
+
+#ifdef Py_TRACE_REFS
+/* Define pointers to support a doubly-linked list of all live heap objects. */
+#define _PyObject_HEAD_EXTRA \
+ struct _object *_ob_next; \
+ struct _object *_ob_prev;
+
+#define _PyObject_EXTRA_INIT 0, 0,
+
+#else
+#define _PyObject_HEAD_EXTRA
+#define _PyObject_EXTRA_INIT
+#endif
+
+/* PyObject_HEAD defines the initial segment of every PyObject. */
+#define PyObject_HEAD PyObject ob_base;
+
+#define PyObject_HEAD_INIT(type) \
+ { _PyObject_EXTRA_INIT \
+ 1, type },
+
+#define PyVarObject_HEAD_INIT(type, size) \
+ { PyObject_HEAD_INIT(type) size },
+
+/* PyObject_VAR_HEAD defines the initial segment of all variable-size
+ * container objects. These end with a declaration of an array with 1
+ * element, but enough space is malloc'ed so that the array actually
+ * has room for ob_size elements. Note that ob_size is an element count,
+ * not necessarily a byte count.
+ */
+#define PyObject_VAR_HEAD PyVarObject ob_base;
+#define Py_INVALID_SIZE (Py_ssize_t)-1
+
+/* Nothing is actually declared to be a PyObject, but every pointer to
+ * a Python object can be cast to a PyObject*. This is inheritance built
+ * by hand. Similarly every pointer to a variable-size Python object can,
+ * in addition, be cast to PyVarObject*.
+ */
+typedef struct _object {
+ _PyObject_HEAD_EXTRA
+ Py_ssize_t ob_refcnt;
+ struct _typeobject *ob_type;
+} PyObject;
+
+typedef struct {
+ PyObject ob_base;
+ Py_ssize_t ob_size; /* Number of items in variable part */
+} PyVarObject;
+
+#define Py_REFCNT(ob) (((PyObject*)(ob))->ob_refcnt)
+#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
+#define Py_SIZE(ob) (((PyVarObject*)(ob))->ob_size)
+
+#ifndef Py_LIMITED_API
+/********************* String Literals ****************************************/
+/* This structure helps managing static strings. The basic usage goes like this:
+ Instead of doing
+
+ r = PyObject_CallMethod(o, "foo", "args", ...);
+
+ do
+
+ _Py_IDENTIFIER(foo);
+ ...
+ r = _PyObject_CallMethodId(o, &PyId_foo, "args", ...);
+
+ PyId_foo is a static variable, either on block level or file level. On first
+ usage, the string "foo" is interned, and the structures are linked. On interpreter
+ shutdown, all strings are released (through _PyUnicode_ClearStaticStrings).
+
+ Alternatively, _Py_static_string allows choosing the variable name.
+ _PyUnicode_FromId returns a borrowed reference to the interned string.
+ _PyObject_{Get,Set,Has}AttrId are __getattr__ versions using _Py_Identifier*.
+*/
+typedef struct _Py_Identifier {
+ struct _Py_Identifier *next;
+ const char* string;
+ PyObject *object;
+} _Py_Identifier;
+
+#define _Py_static_string_init(value) { .next = NULL, .string = value, .object = NULL }
+#define _Py_static_string(varname, value) static _Py_Identifier varname = _Py_static_string_init(value)
+#define _Py_IDENTIFIER(varname) _Py_static_string(PyId_##varname, #varname)
+
+#endif /* !Py_LIMITED_API */
+
+/*
+Type objects contain a string containing the type name (to help somewhat
+in debugging), the allocation parameters (see PyObject_New() and
+PyObject_NewVar()),
+and methods for accessing objects of the type. Methods are optional, a
+nil pointer meaning that particular kind of access is not available for
+this type. The Py_DECREF() macro uses the tp_dealloc method without
+checking for a nil pointer; it should always be implemented except if
+the implementation can guarantee that the reference count will never
+reach zero (e.g., for statically allocated type objects).
+
+NB: the methods for certain type groups are now contained in separate
+method blocks.
+*/
+
+typedef PyObject * (*unaryfunc)(PyObject *);
+typedef PyObject * (*binaryfunc)(PyObject *, PyObject *);
+typedef PyObject * (*ternaryfunc)(PyObject *, PyObject *, PyObject *);
+typedef int (*inquiry)(PyObject *);
+typedef Py_ssize_t (*lenfunc)(PyObject *);
+typedef PyObject *(*ssizeargfunc)(PyObject *, Py_ssize_t);
+typedef PyObject *(*ssizessizeargfunc)(PyObject *, Py_ssize_t, Py_ssize_t);
+typedef int(*ssizeobjargproc)(PyObject *, Py_ssize_t, PyObject *);
+typedef int(*ssizessizeobjargproc)(PyObject *, Py_ssize_t, Py_ssize_t, PyObject *);
+typedef int(*objobjargproc)(PyObject *, PyObject *, PyObject *);
+
+#ifndef Py_LIMITED_API
+/* buffer interface */
+typedef struct bufferinfo {
+ void *buf;
+ PyObject *obj; /* owned reference */
+ Py_ssize_t len;
+ Py_ssize_t itemsize; /* This is Py_ssize_t so it can be
+ pointed to by strides in simple case.*/
+ int readonly;
+ int ndim;
+ char *format;
+ Py_ssize_t *shape;
+ Py_ssize_t *strides;
+ Py_ssize_t *suboffsets;
+ void *internal;
+} Py_buffer;
+
+typedef int (*getbufferproc)(PyObject *, Py_buffer *, int);
+typedef void (*releasebufferproc)(PyObject *, Py_buffer *);
+
+/* Maximum number of dimensions */
+#define PyBUF_MAX_NDIM 64
+
+/* Flags for getting buffers */
+#define PyBUF_SIMPLE 0
+#define PyBUF_WRITABLE 0x0001
+/* we used to include an E, backwards compatible alias */
+#define PyBUF_WRITEABLE PyBUF_WRITABLE
+#define PyBUF_FORMAT 0x0004
+#define PyBUF_ND 0x0008
+#define PyBUF_STRIDES (0x0010 | PyBUF_ND)
+#define PyBUF_C_CONTIGUOUS (0x0020 | PyBUF_STRIDES)
+#define PyBUF_F_CONTIGUOUS (0x0040 | PyBUF_STRIDES)
+#define PyBUF_ANY_CONTIGUOUS (0x0080 | PyBUF_STRIDES)
+#define PyBUF_INDIRECT (0x0100 | PyBUF_STRIDES)
+
+#define PyBUF_CONTIG (PyBUF_ND | PyBUF_WRITABLE)
+#define PyBUF_CONTIG_RO (PyBUF_ND)
+
+#define PyBUF_STRIDED (PyBUF_STRIDES | PyBUF_WRITABLE)
+#define PyBUF_STRIDED_RO (PyBUF_STRIDES)
+
+#define PyBUF_RECORDS (PyBUF_STRIDES | PyBUF_WRITABLE | PyBUF_FORMAT)
+#define PyBUF_RECORDS_RO (PyBUF_STRIDES | PyBUF_FORMAT)
+
+#define PyBUF_FULL (PyBUF_INDIRECT | PyBUF_WRITABLE | PyBUF_FORMAT)
+#define PyBUF_FULL_RO (PyBUF_INDIRECT | PyBUF_FORMAT)
+
+
+#define PyBUF_READ 0x100
+#define PyBUF_WRITE 0x200
+
+/* End buffer interface */
+#endif /* Py_LIMITED_API */
+
+typedef int (*objobjproc)(PyObject *, PyObject *);
+typedef int (*visitproc)(PyObject *, void *);
+typedef int (*traverseproc)(PyObject *, visitproc, void *);
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ /* Number implementations must check *both*
+ arguments for proper type and implement the necessary conversions
+ in the slot functions themselves. */
+
+ binaryfunc nb_add;
+ binaryfunc nb_subtract;
+ binaryfunc nb_multiply;
+ binaryfunc nb_remainder;
+ binaryfunc nb_divmod;
+ ternaryfunc nb_power;
+ unaryfunc nb_negative;
+ unaryfunc nb_positive;
+ unaryfunc nb_absolute;
+ inquiry nb_bool;
+ unaryfunc nb_invert;
+ binaryfunc nb_lshift;
+ binaryfunc nb_rshift;
+ binaryfunc nb_and;
+ binaryfunc nb_xor;
+ binaryfunc nb_or;
+ unaryfunc nb_int;
+ void *nb_reserved; /* the slot formerly known as nb_long */
+ unaryfunc nb_float;
+
+ binaryfunc nb_inplace_add;
+ binaryfunc nb_inplace_subtract;
+ binaryfunc nb_inplace_multiply;
+ binaryfunc nb_inplace_remainder;
+ ternaryfunc nb_inplace_power;
+ binaryfunc nb_inplace_lshift;
+ binaryfunc nb_inplace_rshift;
+ binaryfunc nb_inplace_and;
+ binaryfunc nb_inplace_xor;
+ binaryfunc nb_inplace_or;
+
+ binaryfunc nb_floor_divide;
+ binaryfunc nb_true_divide;
+ binaryfunc nb_inplace_floor_divide;
+ binaryfunc nb_inplace_true_divide;
+
+ unaryfunc nb_index;
+
+ binaryfunc nb_matrix_multiply;
+ binaryfunc nb_inplace_matrix_multiply;
+} PyNumberMethods;
+
+typedef struct {
+ lenfunc sq_length;
+ binaryfunc sq_concat;
+ ssizeargfunc sq_repeat;
+ ssizeargfunc sq_item;
+ void *was_sq_slice;
+ ssizeobjargproc sq_ass_item;
+ void *was_sq_ass_slice;
+ objobjproc sq_contains;
+
+ binaryfunc sq_inplace_concat;
+ ssizeargfunc sq_inplace_repeat;
+} PySequenceMethods;
+
+typedef struct {
+ lenfunc mp_length;
+ binaryfunc mp_subscript;
+ objobjargproc mp_ass_subscript;
+} PyMappingMethods;
+
+typedef struct {
+ unaryfunc am_await;
+ unaryfunc am_aiter;
+ unaryfunc am_anext;
+} PyAsyncMethods;
+
+typedef struct {
+ getbufferproc bf_getbuffer;
+ releasebufferproc bf_releasebuffer;
+} PyBufferProcs;
+#endif /* Py_LIMITED_API */
+
+typedef void (*freefunc)(void *);
+typedef void (*destructor)(PyObject *);
+#ifndef Py_LIMITED_API
+/* We can't provide a full compile-time check that limited-API
+ users won't implement tp_print. However, not defining printfunc
+ and making tp_print of a different function pointer type
+ should at least cause a warning in most cases. */
+typedef int (*printfunc)(PyObject *, FILE *, int);
+#endif
+typedef PyObject *(*getattrfunc)(PyObject *, char *);
+typedef PyObject *(*getattrofunc)(PyObject *, PyObject *);
+typedef int (*setattrfunc)(PyObject *, char *, PyObject *);
+typedef int (*setattrofunc)(PyObject *, PyObject *, PyObject *);
+typedef PyObject *(*reprfunc)(PyObject *);
+typedef Py_hash_t (*hashfunc)(PyObject *);
+typedef PyObject *(*richcmpfunc) (PyObject *, PyObject *, int);
+typedef PyObject *(*getiterfunc) (PyObject *);
+typedef PyObject *(*iternextfunc) (PyObject *);
+typedef PyObject *(*descrgetfunc) (PyObject *, PyObject *, PyObject *);
+typedef int (*descrsetfunc) (PyObject *, PyObject *, PyObject *);
+typedef int (*initproc)(PyObject *, PyObject *, PyObject *);
+typedef PyObject *(*newfunc)(struct _typeobject *, PyObject *, PyObject *);
+typedef PyObject *(*allocfunc)(struct _typeobject *, Py_ssize_t);
+
+#ifdef Py_LIMITED_API
+typedef struct _typeobject PyTypeObject; /* opaque */
+#else
+typedef struct _typeobject {
+ PyObject_VAR_HEAD
+ const char *tp_name; /* For printing, in format "." */
+ Py_ssize_t tp_basicsize, tp_itemsize; /* For allocation */
+
+ /* Methods to implement standard operations */
+
+ destructor tp_dealloc;
+ printfunc tp_print;
+ getattrfunc tp_getattr;
+ setattrfunc tp_setattr;
+ PyAsyncMethods *tp_as_async; /* formerly known as tp_compare (Python 2)
+ or tp_reserved (Python 3) */
+ reprfunc tp_repr;
+
+ /* Method suites for standard classes */
+
+ PyNumberMethods *tp_as_number;
+ PySequenceMethods *tp_as_sequence;
+ PyMappingMethods *tp_as_mapping;
+
+ /* More standard operations (here for binary compatibility) */
+
+ hashfunc tp_hash;
+ ternaryfunc tp_call;
+ reprfunc tp_str;
+ getattrofunc tp_getattro;
+ setattrofunc tp_setattro;
+
+ /* Functions to access object as input/output buffer */
+ PyBufferProcs *tp_as_buffer;
+
+ /* Flags to define presence of optional/expanded features */
+ unsigned long tp_flags;
+
+ const char *tp_doc; /* Documentation string */
+
+ /* Assigned meaning in release 2.0 */
+ /* call function for all accessible objects */
+ traverseproc tp_traverse;
+
+ /* delete references to contained objects */
+ inquiry tp_clear;
+
+ /* Assigned meaning in release 2.1 */
+ /* rich comparisons */
+ richcmpfunc tp_richcompare;
+
+ /* weak reference enabler */
+ Py_ssize_t tp_weaklistoffset;
+
+ /* Iterators */
+ getiterfunc tp_iter;
+ iternextfunc tp_iternext;
+
+ /* Attribute descriptor and subclassing stuff */
+ struct PyMethodDef *tp_methods;
+ struct PyMemberDef *tp_members;
+ struct PyGetSetDef *tp_getset;
+ struct _typeobject *tp_base;
+ PyObject *tp_dict;
+ descrgetfunc tp_descr_get;
+ descrsetfunc tp_descr_set;
+ Py_ssize_t tp_dictoffset;
+ initproc tp_init;
+ allocfunc tp_alloc;
+ newfunc tp_new;
+ freefunc tp_free; /* Low-level free-memory routine */
+ inquiry tp_is_gc; /* For PyObject_IS_GC */
+ PyObject *tp_bases;
+ PyObject *tp_mro; /* method resolution order */
+ PyObject *tp_cache;
+ PyObject *tp_subclasses;
+ PyObject *tp_weaklist;
+ destructor tp_del;
+
+ /* Type attribute cache version tag. Added in version 2.6 */
+ unsigned int tp_version_tag;
+
+ destructor tp_finalize;
+
+#ifdef COUNT_ALLOCS
+ /* these must be last and never explicitly initialized */
+ Py_ssize_t tp_allocs;
+ Py_ssize_t tp_frees;
+ Py_ssize_t tp_maxalloc;
+ struct _typeobject *tp_prev;
+ struct _typeobject *tp_next;
+#endif
+} PyTypeObject;
+#endif
+
+typedef struct{
+ int slot; /* slot id, see below */
+ void *pfunc; /* function pointer */
+} PyType_Slot;
+
+typedef struct{
+ const char* name;
+ int basicsize;
+ int itemsize;
+ unsigned int flags;
+ PyType_Slot *slots; /* terminated by slot==0. */
+} PyType_Spec;
+
+PyAPI_FUNC(PyObject*) PyType_FromSpec(PyType_Spec*);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject*) PyType_FromSpecWithBases(PyType_Spec*, PyObject*);
+#endif
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03040000
+PyAPI_FUNC(void*) PyType_GetSlot(PyTypeObject*, int);
+#endif
+
+#ifndef Py_LIMITED_API
+/* The *real* layout of a type object when allocated on the heap */
+typedef struct _heaptypeobject {
+ /* Note: there's a dependency on the order of these members
+ in slotptr() in typeobject.c . */
+ PyTypeObject ht_type;
+ PyAsyncMethods as_async;
+ PyNumberMethods as_number;
+ PyMappingMethods as_mapping;
+ PySequenceMethods as_sequence; /* as_sequence comes after as_mapping,
+ so that the mapping wins when both
+ the mapping and the sequence define
+ a given operator (e.g. __getitem__).
+ see add_operators() in typeobject.c . */
+ PyBufferProcs as_buffer;
+ PyObject *ht_name, *ht_slots, *ht_qualname;
+ struct _dictkeysobject *ht_cached_keys;
+ /* here are optional user slots, followed by the members. */
+} PyHeapTypeObject;
+
+/* access macro to the members which are floating "behind" the object */
+#define PyHeapType_GET_MEMBERS(etype) \
+ ((PyMemberDef *)(((char *)etype) + Py_TYPE(etype)->tp_basicsize))
+#endif
+
+/* Generic type check */
+PyAPI_FUNC(int) PyType_IsSubtype(PyTypeObject *, PyTypeObject *);
+#define PyObject_TypeCheck(ob, tp) \
+ (Py_TYPE(ob) == (tp) || PyType_IsSubtype(Py_TYPE(ob), (tp)))
+
+PyAPI_DATA(PyTypeObject) PyType_Type; /* built-in 'type' */
+PyAPI_DATA(PyTypeObject) PyBaseObject_Type; /* built-in 'object' */
+PyAPI_DATA(PyTypeObject) PySuper_Type; /* built-in 'super' */
+
+PyAPI_FUNC(unsigned long) PyType_GetFlags(PyTypeObject*);
+
+#define PyType_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_TYPE_SUBCLASS)
+#define PyType_CheckExact(op) (Py_TYPE(op) == &PyType_Type)
+
+PyAPI_FUNC(int) PyType_Ready(PyTypeObject *);
+PyAPI_FUNC(PyObject *) PyType_GenericAlloc(PyTypeObject *, Py_ssize_t);
+PyAPI_FUNC(PyObject *) PyType_GenericNew(PyTypeObject *,
+ PyObject *, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(const char *) _PyType_Name(PyTypeObject *);
+PyAPI_FUNC(PyObject *) _PyType_Lookup(PyTypeObject *, PyObject *);
+PyAPI_FUNC(PyObject *) _PyType_LookupId(PyTypeObject *, _Py_Identifier *);
+PyAPI_FUNC(PyObject *) _PyObject_LookupSpecial(PyObject *, _Py_Identifier *);
+PyAPI_FUNC(PyTypeObject *) _PyType_CalculateMetaclass(PyTypeObject *, PyObject *);
+#endif
+PyAPI_FUNC(unsigned int) PyType_ClearCache(void);
+PyAPI_FUNC(void) PyType_Modified(PyTypeObject *);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyType_GetDocFromInternalDoc(const char *, const char *);
+PyAPI_FUNC(PyObject *) _PyType_GetTextSignatureFromInternalDoc(const char *, const char *);
+#endif
+
+/* Generic operations on objects */
+#ifndef Py_LIMITED_API
+struct _Py_Identifier;
+PyAPI_FUNC(int) PyObject_Print(PyObject *, FILE *, int);
+PyAPI_FUNC(void) _Py_BreakPoint(void);
+PyAPI_FUNC(void) _PyObject_Dump(PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyObject_Repr(PyObject *);
+PyAPI_FUNC(PyObject *) PyObject_Str(PyObject *);
+PyAPI_FUNC(PyObject *) PyObject_ASCII(PyObject *);
+PyAPI_FUNC(PyObject *) PyObject_Bytes(PyObject *);
+PyAPI_FUNC(PyObject *) PyObject_RichCompare(PyObject *, PyObject *, int);
+PyAPI_FUNC(int) PyObject_RichCompareBool(PyObject *, PyObject *, int);
+PyAPI_FUNC(PyObject *) PyObject_GetAttrString(PyObject *, const char *);
+PyAPI_FUNC(int) PyObject_SetAttrString(PyObject *, const char *, PyObject *);
+PyAPI_FUNC(int) PyObject_HasAttrString(PyObject *, const char *);
+PyAPI_FUNC(PyObject *) PyObject_GetAttr(PyObject *, PyObject *);
+PyAPI_FUNC(int) PyObject_SetAttr(PyObject *, PyObject *, PyObject *);
+PyAPI_FUNC(int) PyObject_HasAttr(PyObject *, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyObject_IsAbstract(PyObject *);
+PyAPI_FUNC(PyObject *) _PyObject_GetAttrId(PyObject *, struct _Py_Identifier *);
+PyAPI_FUNC(int) _PyObject_SetAttrId(PyObject *, struct _Py_Identifier *, PyObject *);
+PyAPI_FUNC(int) _PyObject_HasAttrId(PyObject *, struct _Py_Identifier *);
+/* Replacements of PyObject_GetAttr() and _PyObject_GetAttrId() which
+ don't raise AttributeError.
+
+ Return 1 and set *result != NULL if an attribute is found.
+ Return 0 and set *result == NULL if an attribute is not found;
+ an AttributeError is silenced.
+ Return -1 and set *result == NULL if an error other than AttributeError
+ is raised.
+*/
+PyAPI_FUNC(int) _PyObject_LookupAttr(PyObject *, PyObject *, PyObject **);
+PyAPI_FUNC(int) _PyObject_LookupAttrId(PyObject *, struct _Py_Identifier *, PyObject **);
+PyAPI_FUNC(PyObject **) _PyObject_GetDictPtr(PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyObject_SelfIter(PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyObject_NextNotImplemented(PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyObject_GenericGetAttr(PyObject *, PyObject *);
+PyAPI_FUNC(int) PyObject_GenericSetAttr(PyObject *,
+ PyObject *, PyObject *);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(int) PyObject_GenericSetDict(PyObject *, PyObject *, void *);
+#endif
+PyAPI_FUNC(Py_hash_t) PyObject_Hash(PyObject *);
+PyAPI_FUNC(Py_hash_t) PyObject_HashNotImplemented(PyObject *);
+PyAPI_FUNC(int) PyObject_IsTrue(PyObject *);
+PyAPI_FUNC(int) PyObject_Not(PyObject *);
+PyAPI_FUNC(int) PyCallable_Check(PyObject *);
+
+PyAPI_FUNC(void) PyObject_ClearWeakRefs(PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) PyObject_CallFinalizer(PyObject *);
+PyAPI_FUNC(int) PyObject_CallFinalizerFromDealloc(PyObject *);
+#endif
+
+#ifndef Py_LIMITED_API
+/* Same as PyObject_Generic{Get,Set}Attr, but passing the attributes
+ dict as the last parameter. */
+PyAPI_FUNC(PyObject *)
+_PyObject_GenericGetAttrWithDict(PyObject *, PyObject *, PyObject *, int);
+PyAPI_FUNC(int)
+_PyObject_GenericSetAttrWithDict(PyObject *, PyObject *,
+ PyObject *, PyObject *);
+#endif /* !Py_LIMITED_API */
+
+/* Helper to look up a builtin object */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *)
+_PyObject_GetBuiltin(const char *name);
+#endif
+
+/* PyObject_Dir(obj) acts like Python builtins.dir(obj), returning a
+ list of strings. PyObject_Dir(NULL) is like builtins.dir(),
+ returning the names of the current locals. In this case, if there are
+ no current locals, NULL is returned, and PyErr_Occurred() is false.
+*/
+PyAPI_FUNC(PyObject *) PyObject_Dir(PyObject *);
+
+
+/* Helpers for printing recursive container types */
+PyAPI_FUNC(int) Py_ReprEnter(PyObject *);
+PyAPI_FUNC(void) Py_ReprLeave(PyObject *);
+
+/* Flag bits for printing: */
+#define Py_PRINT_RAW 1 /* No string quotes etc. */
+
+/*
+`Type flags (tp_flags)
+
+These flags are used to extend the type structure in a backwards-compatible
+fashion. Extensions can use the flags to indicate (and test) when a given
+type structure contains a new feature. The Python core will use these when
+introducing new functionality between major revisions (to avoid mid-version
+changes in the PYTHON_API_VERSION).
+
+Arbitration of the flag bit positions will need to be coordinated among
+all extension writers who publicly release their extensions (this will
+be fewer than you might expect!)..
+
+Most flags were removed as of Python 3.0 to make room for new flags. (Some
+flags are not for backwards compatibility but to indicate the presence of an
+optional feature; these flags remain of course.)
+
+Type definitions should use Py_TPFLAGS_DEFAULT for their tp_flags value.
+
+Code can use PyType_HasFeature(type_ob, flag_value) to test whether the
+given type object has a specified feature.
+*/
+
+/* Set if the type object is dynamically allocated */
+#define Py_TPFLAGS_HEAPTYPE (1UL << 9)
+
+/* Set if the type allows subclassing */
+#define Py_TPFLAGS_BASETYPE (1UL << 10)
+
+/* Set if the type is 'ready' -- fully initialized */
+#define Py_TPFLAGS_READY (1UL << 12)
+
+/* Set while the type is being 'readied', to prevent recursive ready calls */
+#define Py_TPFLAGS_READYING (1UL << 13)
+
+/* Objects support garbage collection (see objimp.h) */
+#define Py_TPFLAGS_HAVE_GC (1UL << 14)
+
+/* These two bits are preserved for Stackless Python, next after this is 17 */
+#ifdef STACKLESS
+#define Py_TPFLAGS_HAVE_STACKLESS_EXTENSION (3UL << 15)
+#else
+#define Py_TPFLAGS_HAVE_STACKLESS_EXTENSION 0
+#endif
+
+/* Objects support type attribute cache */
+#define Py_TPFLAGS_HAVE_VERSION_TAG (1UL << 18)
+#define Py_TPFLAGS_VALID_VERSION_TAG (1UL << 19)
+
+/* Type is abstract and cannot be instantiated */
+#define Py_TPFLAGS_IS_ABSTRACT (1UL << 20)
+
+/* These flags are used to determine if a type is a subclass. */
+#define Py_TPFLAGS_LONG_SUBCLASS (1UL << 24)
+#define Py_TPFLAGS_LIST_SUBCLASS (1UL << 25)
+#define Py_TPFLAGS_TUPLE_SUBCLASS (1UL << 26)
+#define Py_TPFLAGS_BYTES_SUBCLASS (1UL << 27)
+#define Py_TPFLAGS_UNICODE_SUBCLASS (1UL << 28)
+#define Py_TPFLAGS_DICT_SUBCLASS (1UL << 29)
+#define Py_TPFLAGS_BASE_EXC_SUBCLASS (1UL << 30)
+#define Py_TPFLAGS_TYPE_SUBCLASS (1UL << 31)
+
+#define Py_TPFLAGS_DEFAULT ( \
+ Py_TPFLAGS_HAVE_STACKLESS_EXTENSION | \
+ Py_TPFLAGS_HAVE_VERSION_TAG | \
+ 0)
+
+/* NOTE: The following flags reuse lower bits (removed as part of the
+ * Python 3.0 transition). */
+
+/* Type structure has tp_finalize member (3.4) */
+#define Py_TPFLAGS_HAVE_FINALIZE (1UL << 0)
+
+#ifdef Py_LIMITED_API
+#define PyType_HasFeature(t,f) ((PyType_GetFlags(t) & (f)) != 0)
+#else
+#define PyType_HasFeature(t,f) (((t)->tp_flags & (f)) != 0)
+#endif
+#define PyType_FastSubclass(t,f) PyType_HasFeature(t,f)
+
+
+/*
+The macros Py_INCREF(op) and Py_DECREF(op) are used to increment or decrement
+reference counts. Py_DECREF calls the object's deallocator function when
+the refcount falls to 0; for
+objects that don't contain references to other objects or heap memory
+this can be the standard function free(). Both macros can be used
+wherever a void expression is allowed. The argument must not be a
+NULL pointer. If it may be NULL, use Py_XINCREF/Py_XDECREF instead.
+The macro _Py_NewReference(op) initialize reference counts to 1, and
+in special builds (Py_REF_DEBUG, Py_TRACE_REFS) performs additional
+bookkeeping appropriate to the special build.
+
+We assume that the reference count field can never overflow; this can
+be proven when the size of the field is the same as the pointer size, so
+we ignore the possibility. Provided a C int is at least 32 bits (which
+is implicitly assumed in many parts of this code), that's enough for
+about 2**31 references to an object.
+
+XXX The following became out of date in Python 2.2, but I'm not sure
+XXX what the full truth is now. Certainly, heap-allocated type objects
+XXX can and should be deallocated.
+Type objects should never be deallocated; the type pointer in an object
+is not considered to be a reference to the type object, to save
+complications in the deallocation function. (This is actually a
+decision that's up to the implementer of each new type so if you want,
+you can count such references to the type object.)
+*/
+
+/* First define a pile of simple helper macros, one set per special
+ * build symbol. These either expand to the obvious things, or to
+ * nothing at all when the special mode isn't in effect. The main
+ * macros can later be defined just once then, yet expand to different
+ * things depending on which special build options are and aren't in effect.
+ * Trust me : while painful, this is 20x easier to understand than,
+ * e.g, defining _Py_NewReference five different times in a maze of nested
+ * #ifdefs (we used to do that -- it was impenetrable).
+ */
+#ifdef Py_REF_DEBUG
+PyAPI_DATA(Py_ssize_t) _Py_RefTotal;
+PyAPI_FUNC(void) _Py_NegativeRefcount(const char *fname,
+ int lineno, PyObject *op);
+PyAPI_FUNC(Py_ssize_t) _Py_GetRefTotal(void);
+#define _Py_INC_REFTOTAL _Py_RefTotal++
+#define _Py_DEC_REFTOTAL _Py_RefTotal--
+#define _Py_REF_DEBUG_COMMA ,
+#define _Py_CHECK_REFCNT(OP) \
+{ if (((PyObject*)OP)->ob_refcnt < 0) \
+ _Py_NegativeRefcount(__FILE__, __LINE__, \
+ (PyObject *)(OP)); \
+}
+/* Py_REF_DEBUG also controls the display of refcounts and memory block
+ * allocations at the interactive prompt and at interpreter shutdown
+ */
+PyAPI_FUNC(void) _PyDebug_PrintTotalRefs(void);
+#else
+#define _Py_INC_REFTOTAL
+#define _Py_DEC_REFTOTAL
+#define _Py_REF_DEBUG_COMMA
+#define _Py_CHECK_REFCNT(OP) /* a semicolon */;
+#endif /* Py_REF_DEBUG */
+
+#ifdef COUNT_ALLOCS
+PyAPI_FUNC(void) inc_count(PyTypeObject *);
+PyAPI_FUNC(void) dec_count(PyTypeObject *);
+#define _Py_INC_TPALLOCS(OP) inc_count(Py_TYPE(OP))
+#define _Py_INC_TPFREES(OP) dec_count(Py_TYPE(OP))
+#define _Py_DEC_TPFREES(OP) Py_TYPE(OP)->tp_frees--
+#define _Py_COUNT_ALLOCS_COMMA ,
+#else
+#define _Py_INC_TPALLOCS(OP)
+#define _Py_INC_TPFREES(OP)
+#define _Py_DEC_TPFREES(OP)
+#define _Py_COUNT_ALLOCS_COMMA
+#endif /* COUNT_ALLOCS */
+
+#ifdef Py_TRACE_REFS
+/* Py_TRACE_REFS is such major surgery that we call external routines. */
+PyAPI_FUNC(void) _Py_NewReference(PyObject *);
+PyAPI_FUNC(void) _Py_ForgetReference(PyObject *);
+PyAPI_FUNC(void) _Py_Dealloc(PyObject *);
+PyAPI_FUNC(void) _Py_PrintReferences(FILE *);
+PyAPI_FUNC(void) _Py_PrintReferenceAddresses(FILE *);
+PyAPI_FUNC(void) _Py_AddToAllObjects(PyObject *, int force);
+
+#else
+/* Without Py_TRACE_REFS, there's little enough to do that we expand code
+ * inline.
+ */
+#define _Py_NewReference(op) ( \
+ _Py_INC_TPALLOCS(op) _Py_COUNT_ALLOCS_COMMA \
+ _Py_INC_REFTOTAL _Py_REF_DEBUG_COMMA \
+ Py_REFCNT(op) = 1)
+
+#define _Py_ForgetReference(op) _Py_INC_TPFREES(op)
+
+#ifdef Py_LIMITED_API
+PyAPI_FUNC(void) _Py_Dealloc(PyObject *);
+#else
+#define _Py_Dealloc(op) ( \
+ _Py_INC_TPFREES(op) _Py_COUNT_ALLOCS_COMMA \
+ (*Py_TYPE(op)->tp_dealloc)((PyObject *)(op)))
+#endif
+#endif /* !Py_TRACE_REFS */
+
+#define Py_INCREF(op) ( \
+ _Py_INC_REFTOTAL _Py_REF_DEBUG_COMMA \
+ ((PyObject *)(op))->ob_refcnt++)
+
+#define Py_DECREF(op) \
+ do { \
+ PyObject *_py_decref_tmp = (PyObject *)(op); \
+ if (_Py_DEC_REFTOTAL _Py_REF_DEBUG_COMMA \
+ --(_py_decref_tmp)->ob_refcnt != 0) \
+ _Py_CHECK_REFCNT(_py_decref_tmp) \
+ else \
+ _Py_Dealloc(_py_decref_tmp); \
+ } while (0)
+
+/* Safely decref `op` and set `op` to NULL, especially useful in tp_clear
+ * and tp_dealloc implementations.
+ *
+ * Note that "the obvious" code can be deadly:
+ *
+ * Py_XDECREF(op);
+ * op = NULL;
+ *
+ * Typically, `op` is something like self->containee, and `self` is done
+ * using its `containee` member. In the code sequence above, suppose
+ * `containee` is non-NULL with a refcount of 1. Its refcount falls to
+ * 0 on the first line, which can trigger an arbitrary amount of code,
+ * possibly including finalizers (like __del__ methods or weakref callbacks)
+ * coded in Python, which in turn can release the GIL and allow other threads
+ * to run, etc. Such code may even invoke methods of `self` again, or cause
+ * cyclic gc to trigger, but-- oops! --self->containee still points to the
+ * object being torn down, and it may be in an insane state while being torn
+ * down. This has in fact been a rich historic source of miserable (rare &
+ * hard-to-diagnose) segfaulting (and other) bugs.
+ *
+ * The safe way is:
+ *
+ * Py_CLEAR(op);
+ *
+ * That arranges to set `op` to NULL _before_ decref'ing, so that any code
+ * triggered as a side-effect of `op` getting torn down no longer believes
+ * `op` points to a valid object.
+ *
+ * There are cases where it's safe to use the naive code, but they're brittle.
+ * For example, if `op` points to a Python integer, you know that destroying
+ * one of those can't cause problems -- but in part that relies on that
+ * Python integers aren't currently weakly referencable. Best practice is
+ * to use Py_CLEAR() even if you can't think of a reason for why you need to.
+ */
+#define Py_CLEAR(op) \
+ do { \
+ PyObject *_py_tmp = (PyObject *)(op); \
+ if (_py_tmp != NULL) { \
+ (op) = NULL; \
+ Py_DECREF(_py_tmp); \
+ } \
+ } while (0)
+
+/* Macros to use in case the object pointer may be NULL: */
+#define Py_XINCREF(op) \
+ do { \
+ PyObject *_py_xincref_tmp = (PyObject *)(op); \
+ if (_py_xincref_tmp != NULL) \
+ Py_INCREF(_py_xincref_tmp); \
+ } while (0)
+
+#define Py_XDECREF(op) \
+ do { \
+ PyObject *_py_xdecref_tmp = (PyObject *)(op); \
+ if (_py_xdecref_tmp != NULL) \
+ Py_DECREF(_py_xdecref_tmp); \
+ } while (0)
+
+#ifndef Py_LIMITED_API
+/* Safely decref `op` and set `op` to `op2`.
+ *
+ * As in case of Py_CLEAR "the obvious" code can be deadly:
+ *
+ * Py_DECREF(op);
+ * op = op2;
+ *
+ * The safe way is:
+ *
+ * Py_SETREF(op, op2);
+ *
+ * That arranges to set `op` to `op2` _before_ decref'ing, so that any code
+ * triggered as a side-effect of `op` getting torn down no longer believes
+ * `op` points to a valid object.
+ *
+ * Py_XSETREF is a variant of Py_SETREF that uses Py_XDECREF instead of
+ * Py_DECREF.
+ */
+
+#define Py_SETREF(op, op2) \
+ do { \
+ PyObject *_py_tmp = (PyObject *)(op); \
+ (op) = (op2); \
+ Py_DECREF(_py_tmp); \
+ } while (0)
+
+#define Py_XSETREF(op, op2) \
+ do { \
+ PyObject *_py_tmp = (PyObject *)(op); \
+ (op) = (op2); \
+ Py_XDECREF(_py_tmp); \
+ } while (0)
+
+#endif /* ifndef Py_LIMITED_API */
+
+/*
+These are provided as conveniences to Python runtime embedders, so that
+they can have object code that is not dependent on Python compilation flags.
+*/
+PyAPI_FUNC(void) Py_IncRef(PyObject *);
+PyAPI_FUNC(void) Py_DecRef(PyObject *);
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(PyTypeObject) _PyNone_Type;
+PyAPI_DATA(PyTypeObject) _PyNotImplemented_Type;
+#endif /* !Py_LIMITED_API */
+
+/*
+_Py_NoneStruct is an object of undefined type which can be used in contexts
+where NULL (nil) is not suitable (since NULL often means 'error').
+
+Don't forget to apply Py_INCREF() when returning this value!!!
+*/
+PyAPI_DATA(PyObject) _Py_NoneStruct; /* Don't use this directly */
+#define Py_None (&_Py_NoneStruct)
+
+/* Macro for returning Py_None from a function */
+#define Py_RETURN_NONE return Py_INCREF(Py_None), Py_None
+
+/*
+Py_NotImplemented is a singleton used to signal that an operation is
+not implemented for a given type combination.
+*/
+PyAPI_DATA(PyObject) _Py_NotImplementedStruct; /* Don't use this directly */
+#define Py_NotImplemented (&_Py_NotImplementedStruct)
+
+/* Macro for returning Py_NotImplemented from a function */
+#define Py_RETURN_NOTIMPLEMENTED \
+ return Py_INCREF(Py_NotImplemented), Py_NotImplemented
+
+/* Rich comparison opcodes */
+#define Py_LT 0
+#define Py_LE 1
+#define Py_EQ 2
+#define Py_NE 3
+#define Py_GT 4
+#define Py_GE 5
+
+/*
+ * Macro for implementing rich comparisons
+ *
+ * Needs to be a macro because any C-comparable type can be used.
+ */
+#define Py_RETURN_RICHCOMPARE(val1, val2, op) \
+ do { \
+ switch (op) { \
+ case Py_EQ: if ((val1) == (val2)) Py_RETURN_TRUE; Py_RETURN_FALSE; \
+ case Py_NE: if ((val1) != (val2)) Py_RETURN_TRUE; Py_RETURN_FALSE; \
+ case Py_LT: if ((val1) < (val2)) Py_RETURN_TRUE; Py_RETURN_FALSE; \
+ case Py_GT: if ((val1) > (val2)) Py_RETURN_TRUE; Py_RETURN_FALSE; \
+ case Py_LE: if ((val1) <= (val2)) Py_RETURN_TRUE; Py_RETURN_FALSE; \
+ case Py_GE: if ((val1) >= (val2)) Py_RETURN_TRUE; Py_RETURN_FALSE; \
+ default: \
+ Py_UNREACHABLE(); \
+ } \
+ } while (0)
+
+#ifndef Py_LIMITED_API
+/* Maps Py_LT to Py_GT, ..., Py_GE to Py_LE.
+ * Defined in object.c.
+ */
+PyAPI_DATA(int) _Py_SwappedOp[];
+#endif /* !Py_LIMITED_API */
+
+
+/*
+More conventions
+================
+
+Argument Checking
+-----------------
+
+Functions that take objects as arguments normally don't check for nil
+arguments, but they do check the type of the argument, and return an
+error if the function doesn't apply to the type.
+
+Failure Modes
+-------------
+
+Functions may fail for a variety of reasons, including running out of
+memory. This is communicated to the caller in two ways: an error string
+is set (see errors.h), and the function result differs: functions that
+normally return a pointer return NULL for failure, functions returning
+an integer return -1 (which could be a legal return value too!), and
+other functions return 0 for success and -1 for failure.
+Callers should always check for errors before using the result. If
+an error was set, the caller must either explicitly clear it, or pass
+the error on to its caller.
+
+Reference Counts
+----------------
+
+It takes a while to get used to the proper usage of reference counts.
+
+Functions that create an object set the reference count to 1; such new
+objects must be stored somewhere or destroyed again with Py_DECREF().
+Some functions that 'store' objects, such as PyTuple_SetItem() and
+PyList_SetItem(),
+don't increment the reference count of the object, since the most
+frequent use is to store a fresh object. Functions that 'retrieve'
+objects, such as PyTuple_GetItem() and PyDict_GetItemString(), also
+don't increment
+the reference count, since most frequently the object is only looked at
+quickly. Thus, to retrieve an object and store it again, the caller
+must call Py_INCREF() explicitly.
+
+NOTE: functions that 'consume' a reference count, like
+PyList_SetItem(), consume the reference even if the object wasn't
+successfully stored, to simplify error handling.
+
+It seems attractive to make other functions that take an object as
+argument consume a reference count; however, this may quickly get
+confusing (even the current practice is already confusing). Consider
+it carefully, it may save lots of calls to Py_INCREF() and Py_DECREF() at
+times.
+*/
+
+
+/* Trashcan mechanism, thanks to Christian Tismer.
+
+When deallocating a container object, it's possible to trigger an unbounded
+chain of deallocations, as each Py_DECREF in turn drops the refcount on "the
+next" object in the chain to 0. This can easily lead to stack faults, and
+especially in threads (which typically have less stack space to work with).
+
+A container object that participates in cyclic gc can avoid this by
+bracketing the body of its tp_dealloc function with a pair of macros:
+
+static void
+mytype_dealloc(mytype *p)
+{
+ ... declarations go here ...
+
+ PyObject_GC_UnTrack(p); // must untrack first
+ Py_TRASHCAN_SAFE_BEGIN(p)
+ ... The body of the deallocator goes here, including all calls ...
+ ... to Py_DECREF on contained objects. ...
+ Py_TRASHCAN_SAFE_END(p)
+}
+
+CAUTION: Never return from the middle of the body! If the body needs to
+"get out early", put a label immediately before the Py_TRASHCAN_SAFE_END
+call, and goto it. Else the call-depth counter (see below) will stay
+above 0 forever, and the trashcan will never get emptied.
+
+How it works: The BEGIN macro increments a call-depth counter. So long
+as this counter is small, the body of the deallocator is run directly without
+further ado. But if the counter gets large, it instead adds p to a list of
+objects to be deallocated later, skips the body of the deallocator, and
+resumes execution after the END macro. The tp_dealloc routine then returns
+without deallocating anything (and so unbounded call-stack depth is avoided).
+
+When the call stack finishes unwinding again, code generated by the END macro
+notices this, and calls another routine to deallocate all the objects that
+may have been added to the list of deferred deallocations. In effect, a
+chain of N deallocations is broken into (N-1)/(PyTrash_UNWIND_LEVEL-1) pieces,
+with the call stack never exceeding a depth of PyTrash_UNWIND_LEVEL.
+*/
+
+#ifndef Py_LIMITED_API
+/* This is the old private API, invoked by the macros before 3.2.4.
+ Kept for binary compatibility of extensions using the stable ABI. */
+PyAPI_FUNC(void) _PyTrash_deposit_object(PyObject*);
+PyAPI_FUNC(void) _PyTrash_destroy_chain(void);
+#endif /* !Py_LIMITED_API */
+
+/* The new thread-safe private API, invoked by the macros below. */
+PyAPI_FUNC(void) _PyTrash_thread_deposit_object(PyObject*);
+PyAPI_FUNC(void) _PyTrash_thread_destroy_chain(void);
+
+#define PyTrash_UNWIND_LEVEL 50
+
+#define Py_TRASHCAN_SAFE_BEGIN(op) \
+ do { \
+ PyThreadState *_tstate = PyThreadState_GET(); \
+ if (_tstate->trash_delete_nesting < PyTrash_UNWIND_LEVEL) { \
+ ++_tstate->trash_delete_nesting;
+ /* The body of the deallocator is here. */
+#define Py_TRASHCAN_SAFE_END(op) \
+ --_tstate->trash_delete_nesting; \
+ if (_tstate->trash_delete_later && _tstate->trash_delete_nesting <= 0) \
+ _PyTrash_thread_destroy_chain(); \
+ } \
+ else \
+ _PyTrash_thread_deposit_object((PyObject*)op); \
+ } while (0);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void)
+_PyDebugAllocatorStats(FILE *out, const char *block_name, int num_blocks,
+ size_t sizeof_block);
+PyAPI_FUNC(void)
+_PyObject_DebugTypeStats(FILE *out);
+#endif /* ifndef Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_OBJECT_H */
diff --git a/Include/objimpl.h b/Include/objimpl.h
new file mode 100644
index 0000000..057bb50
--- /dev/null
+++ b/Include/objimpl.h
@@ -0,0 +1,370 @@
+/* The PyObject_ memory family: high-level object memory interfaces.
+ See pymem.h for the low-level PyMem_ family.
+*/
+
+#ifndef Py_OBJIMPL_H
+#define Py_OBJIMPL_H
+
+#include "pymem.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* BEWARE:
+
+ Each interface exports both functions and macros. Extension modules should
+ use the functions, to ensure binary compatibility across Python versions.
+ Because the Python implementation is free to change internal details, and
+ the macros may (or may not) expose details for speed, if you do use the
+ macros you must recompile your extensions with each Python release.
+
+ Never mix calls to PyObject_ memory functions with calls to the platform
+ malloc/realloc/ calloc/free, or with calls to PyMem_.
+*/
+
+/*
+Functions and macros for modules that implement new object types.
+
+ - PyObject_New(type, typeobj) allocates memory for a new object of the given
+ type, and initializes part of it. 'type' must be the C structure type used
+ to represent the object, and 'typeobj' the address of the corresponding
+ type object. Reference count and type pointer are filled in; the rest of
+ the bytes of the object are *undefined*! The resulting expression type is
+ 'type *'. The size of the object is determined by the tp_basicsize field
+ of the type object.
+
+ - PyObject_NewVar(type, typeobj, n) is similar but allocates a variable-size
+ object with room for n items. In addition to the refcount and type pointer
+ fields, this also fills in the ob_size field.
+
+ - PyObject_Del(op) releases the memory allocated for an object. It does not
+ run a destructor -- it only frees the memory. PyObject_Free is identical.
+
+ - PyObject_Init(op, typeobj) and PyObject_InitVar(op, typeobj, n) don't
+ allocate memory. Instead of a 'type' parameter, they take a pointer to a
+ new object (allocated by an arbitrary allocator), and initialize its object
+ header fields.
+
+Note that objects created with PyObject_{New, NewVar} are allocated using the
+specialized Python allocator (implemented in obmalloc.c), if WITH_PYMALLOC is
+enabled. In addition, a special debugging allocator is used if PYMALLOC_DEBUG
+is also #defined.
+
+In case a specific form of memory management is needed (for example, if you
+must use the platform malloc heap(s), or shared memory, or C++ local storage or
+operator new), you must first allocate the object with your custom allocator,
+then pass its pointer to PyObject_{Init, InitVar} for filling in its Python-
+specific fields: reference count, type pointer, possibly others. You should
+be aware that Python has no control over these objects because they don't
+cooperate with the Python memory manager. Such objects may not be eligible
+for automatic garbage collection and you have to make sure that they are
+released accordingly whenever their destructor gets called (cf. the specific
+form of memory management you're using).
+
+Unless you have specific memory management requirements, use
+PyObject_{New, NewVar, Del}.
+*/
+
+/*
+ * Raw object memory interface
+ * ===========================
+ */
+
+/* Functions to call the same malloc/realloc/free as used by Python's
+ object allocator. If WITH_PYMALLOC is enabled, these may differ from
+ the platform malloc/realloc/free. The Python object allocator is
+ designed for fast, cache-conscious allocation of many "small" objects,
+ and with low hidden memory overhead.
+
+ PyObject_Malloc(0) returns a unique non-NULL pointer if possible.
+
+ PyObject_Realloc(NULL, n) acts like PyObject_Malloc(n).
+ PyObject_Realloc(p != NULL, 0) does not return NULL, or free the memory
+ at p.
+
+ Returned pointers must be checked for NULL explicitly; no action is
+ performed on failure other than to return NULL (no warning it printed, no
+ exception is set, etc).
+
+ For allocating objects, use PyObject_{New, NewVar} instead whenever
+ possible. The PyObject_{Malloc, Realloc, Free} family is exposed
+ so that you can exploit Python's small-block allocator for non-object
+ uses. If you must use these routines to allocate object memory, make sure
+ the object gets initialized via PyObject_{Init, InitVar} after obtaining
+ the raw memory.
+*/
+PyAPI_FUNC(void *) PyObject_Malloc(size_t size);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_FUNC(void *) PyObject_Calloc(size_t nelem, size_t elsize);
+#endif
+PyAPI_FUNC(void *) PyObject_Realloc(void *ptr, size_t new_size);
+PyAPI_FUNC(void) PyObject_Free(void *ptr);
+
+#ifndef Py_LIMITED_API
+/* This function returns the number of allocated memory blocks, regardless of size */
+PyAPI_FUNC(Py_ssize_t) _Py_GetAllocatedBlocks(void);
+#endif /* !Py_LIMITED_API */
+
+/* Macros */
+#ifdef WITH_PYMALLOC
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyObject_DebugMallocStats(FILE *out);
+#endif /* #ifndef Py_LIMITED_API */
+#endif
+
+/* Macros */
+#define PyObject_MALLOC PyObject_Malloc
+#define PyObject_REALLOC PyObject_Realloc
+#define PyObject_FREE PyObject_Free
+#define PyObject_Del PyObject_Free
+#define PyObject_DEL PyObject_Free
+
+
+/*
+ * Generic object allocator interface
+ * ==================================
+ */
+
+/* Functions */
+PyAPI_FUNC(PyObject *) PyObject_Init(PyObject *, PyTypeObject *);
+PyAPI_FUNC(PyVarObject *) PyObject_InitVar(PyVarObject *,
+ PyTypeObject *, Py_ssize_t);
+PyAPI_FUNC(PyObject *) _PyObject_New(PyTypeObject *);
+PyAPI_FUNC(PyVarObject *) _PyObject_NewVar(PyTypeObject *, Py_ssize_t);
+
+#define PyObject_New(type, typeobj) \
+ ( (type *) _PyObject_New(typeobj) )
+#define PyObject_NewVar(type, typeobj, n) \
+ ( (type *) _PyObject_NewVar((typeobj), (n)) )
+
+/* Macros trading binary compatibility for speed. See also pymem.h.
+ Note that these macros expect non-NULL object pointers.*/
+#define PyObject_INIT(op, typeobj) \
+ ( Py_TYPE(op) = (typeobj), _Py_NewReference((PyObject *)(op)), (op) )
+#define PyObject_INIT_VAR(op, typeobj, size) \
+ ( Py_SIZE(op) = (size), PyObject_INIT((op), (typeobj)) )
+
+#define _PyObject_SIZE(typeobj) ( (typeobj)->tp_basicsize )
+
+/* _PyObject_VAR_SIZE returns the number of bytes (as size_t) allocated for a
+ vrbl-size object with nitems items, exclusive of gc overhead (if any). The
+ value is rounded up to the closest multiple of sizeof(void *), in order to
+ ensure that pointer fields at the end of the object are correctly aligned
+ for the platform (this is of special importance for subclasses of, e.g.,
+ str or int, so that pointers can be stored after the embedded data).
+
+ Note that there's no memory wastage in doing this, as malloc has to
+ return (at worst) pointer-aligned memory anyway.
+*/
+#if ((SIZEOF_VOID_P - 1) & SIZEOF_VOID_P) != 0
+# error "_PyObject_VAR_SIZE requires SIZEOF_VOID_P be a power of 2"
+#endif
+
+#define _PyObject_VAR_SIZE(typeobj, nitems) \
+ _Py_SIZE_ROUND_UP((typeobj)->tp_basicsize + \
+ (nitems)*(typeobj)->tp_itemsize, \
+ SIZEOF_VOID_P)
+
+#define PyObject_NEW(type, typeobj) \
+( (type *) PyObject_Init( \
+ (PyObject *) PyObject_MALLOC( _PyObject_SIZE(typeobj) ), (typeobj)) )
+
+#define PyObject_NEW_VAR(type, typeobj, n) \
+( (type *) PyObject_InitVar( \
+ (PyVarObject *) PyObject_MALLOC(_PyObject_VAR_SIZE((typeobj),(n)) ),\
+ (typeobj), (n)) )
+
+/* This example code implements an object constructor with a custom
+ allocator, where PyObject_New is inlined, and shows the important
+ distinction between two steps (at least):
+ 1) the actual allocation of the object storage;
+ 2) the initialization of the Python specific fields
+ in this storage with PyObject_{Init, InitVar}.
+
+ PyObject *
+ YourObject_New(...)
+ {
+ PyObject *op;
+
+ op = (PyObject *) Your_Allocator(_PyObject_SIZE(YourTypeStruct));
+ if (op == NULL)
+ return PyErr_NoMemory();
+
+ PyObject_Init(op, &YourTypeStruct);
+
+ op->ob_field = value;
+ ...
+ return op;
+ }
+
+ Note that in C++, the use of the new operator usually implies that
+ the 1st step is performed automatically for you, so in a C++ class
+ constructor you would start directly with PyObject_Init/InitVar
+*/
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ /* user context passed as the first argument to the 2 functions */
+ void *ctx;
+
+ /* allocate an arena of size bytes */
+ void* (*alloc) (void *ctx, size_t size);
+
+ /* free an arena */
+ void (*free) (void *ctx, void *ptr, size_t size);
+} PyObjectArenaAllocator;
+
+/* Get the arena allocator. */
+PyAPI_FUNC(void) PyObject_GetArenaAllocator(PyObjectArenaAllocator *allocator);
+
+/* Set the arena allocator. */
+PyAPI_FUNC(void) PyObject_SetArenaAllocator(PyObjectArenaAllocator *allocator);
+#endif
+
+
+/*
+ * Garbage Collection Support
+ * ==========================
+ */
+
+/* C equivalent of gc.collect() which ignores the state of gc.enabled. */
+PyAPI_FUNC(Py_ssize_t) PyGC_Collect(void);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) _PyGC_CollectNoFail(void);
+PyAPI_FUNC(Py_ssize_t) _PyGC_CollectIfEnabled(void);
+#endif
+
+/* Test if a type has a GC head */
+#define PyType_IS_GC(t) PyType_HasFeature((t), Py_TPFLAGS_HAVE_GC)
+
+/* Test if an object has a GC head */
+#define PyObject_IS_GC(o) (PyType_IS_GC(Py_TYPE(o)) && \
+ (Py_TYPE(o)->tp_is_gc == NULL || Py_TYPE(o)->tp_is_gc(o)))
+
+PyAPI_FUNC(PyVarObject *) _PyObject_GC_Resize(PyVarObject *, Py_ssize_t);
+#define PyObject_GC_Resize(type, op, n) \
+ ( (type *) _PyObject_GC_Resize((PyVarObject *)(op), (n)) )
+
+/* GC information is stored BEFORE the object structure. */
+#ifndef Py_LIMITED_API
+typedef union _gc_head {
+ struct {
+ union _gc_head *gc_next;
+ union _gc_head *gc_prev;
+ Py_ssize_t gc_refs;
+ } gc;
+ double dummy; /* force worst-case alignment */
+} PyGC_Head;
+
+extern PyGC_Head *_PyGC_generation0;
+
+#define _Py_AS_GC(o) ((PyGC_Head *)(o)-1)
+
+/* Bit 0 is set when tp_finalize is called */
+#define _PyGC_REFS_MASK_FINALIZED (1 << 0)
+/* The (N-1) most significant bits contain the gc state / refcount */
+#define _PyGC_REFS_SHIFT (1)
+#define _PyGC_REFS_MASK (((size_t) -1) << _PyGC_REFS_SHIFT)
+
+#define _PyGCHead_REFS(g) ((g)->gc.gc_refs >> _PyGC_REFS_SHIFT)
+#define _PyGCHead_SET_REFS(g, v) do { \
+ (g)->gc.gc_refs = ((g)->gc.gc_refs & ~_PyGC_REFS_MASK) \
+ | (((size_t)(v)) << _PyGC_REFS_SHIFT); \
+ } while (0)
+#define _PyGCHead_DECREF(g) ((g)->gc.gc_refs -= 1 << _PyGC_REFS_SHIFT)
+
+#define _PyGCHead_FINALIZED(g) (((g)->gc.gc_refs & _PyGC_REFS_MASK_FINALIZED) != 0)
+#define _PyGCHead_SET_FINALIZED(g, v) do { \
+ (g)->gc.gc_refs = ((g)->gc.gc_refs & ~_PyGC_REFS_MASK_FINALIZED) \
+ | (v != 0); \
+ } while (0)
+
+#define _PyGC_FINALIZED(o) _PyGCHead_FINALIZED(_Py_AS_GC(o))
+#define _PyGC_SET_FINALIZED(o, v) _PyGCHead_SET_FINALIZED(_Py_AS_GC(o), v)
+
+#define _PyGC_REFS(o) _PyGCHead_REFS(_Py_AS_GC(o))
+
+#define _PyGC_REFS_UNTRACKED (-2)
+#define _PyGC_REFS_REACHABLE (-3)
+#define _PyGC_REFS_TENTATIVELY_UNREACHABLE (-4)
+
+/* Tell the GC to track this object. NB: While the object is tracked the
+ * collector it must be safe to call the ob_traverse method. */
+#define _PyObject_GC_TRACK(o) do { \
+ PyGC_Head *g = _Py_AS_GC(o); \
+ if (_PyGCHead_REFS(g) != _PyGC_REFS_UNTRACKED) \
+ Py_FatalError("GC object already tracked"); \
+ _PyGCHead_SET_REFS(g, _PyGC_REFS_REACHABLE); \
+ g->gc.gc_next = _PyGC_generation0; \
+ g->gc.gc_prev = _PyGC_generation0->gc.gc_prev; \
+ g->gc.gc_prev->gc.gc_next = g; \
+ _PyGC_generation0->gc.gc_prev = g; \
+ } while (0);
+
+/* Tell the GC to stop tracking this object.
+ * gc_next doesn't need to be set to NULL, but doing so is a good
+ * way to provoke memory errors if calling code is confused.
+ */
+#define _PyObject_GC_UNTRACK(o) do { \
+ PyGC_Head *g = _Py_AS_GC(o); \
+ assert(_PyGCHead_REFS(g) != _PyGC_REFS_UNTRACKED); \
+ _PyGCHead_SET_REFS(g, _PyGC_REFS_UNTRACKED); \
+ g->gc.gc_prev->gc.gc_next = g->gc.gc_next; \
+ g->gc.gc_next->gc.gc_prev = g->gc.gc_prev; \
+ g->gc.gc_next = NULL; \
+ } while (0);
+
+/* True if the object is currently tracked by the GC. */
+#define _PyObject_GC_IS_TRACKED(o) \
+ (_PyGC_REFS(o) != _PyGC_REFS_UNTRACKED)
+
+/* True if the object may be tracked by the GC in the future, or already is.
+ This can be useful to implement some optimizations. */
+#define _PyObject_GC_MAY_BE_TRACKED(obj) \
+ (PyObject_IS_GC(obj) && \
+ (!PyTuple_CheckExact(obj) || _PyObject_GC_IS_TRACKED(obj)))
+#endif /* Py_LIMITED_API */
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyObject_GC_Malloc(size_t size);
+PyAPI_FUNC(PyObject *) _PyObject_GC_Calloc(size_t size);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(PyObject *) _PyObject_GC_New(PyTypeObject *);
+PyAPI_FUNC(PyVarObject *) _PyObject_GC_NewVar(PyTypeObject *, Py_ssize_t);
+PyAPI_FUNC(void) PyObject_GC_Track(void *);
+PyAPI_FUNC(void) PyObject_GC_UnTrack(void *);
+PyAPI_FUNC(void) PyObject_GC_Del(void *);
+
+#define PyObject_GC_New(type, typeobj) \
+ ( (type *) _PyObject_GC_New(typeobj) )
+#define PyObject_GC_NewVar(type, typeobj, n) \
+ ( (type *) _PyObject_GC_NewVar((typeobj), (n)) )
+
+
+/* Utility macro to help write tp_traverse functions.
+ * To use this macro, the tp_traverse function must name its arguments
+ * "visit" and "arg". This is intended to keep tp_traverse functions
+ * looking as much alike as possible.
+ */
+#define Py_VISIT(op) \
+ do { \
+ if (op) { \
+ int vret = visit((PyObject *)(op), arg); \
+ if (vret) \
+ return vret; \
+ } \
+ } while (0)
+
+
+/* Test if a type supports weak references */
+#define PyType_SUPPORTS_WEAKREFS(t) ((t)->tp_weaklistoffset > 0)
+
+#define PyObject_GET_WEAKREFS_LISTPTR(o) \
+ ((PyObject **) (((char *) (o)) + Py_TYPE(o)->tp_weaklistoffset))
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_OBJIMPL_H */
diff --git a/Include/odictobject.h b/Include/odictobject.h
new file mode 100644
index 0000000..8378dc4
--- /dev/null
+++ b/Include/odictobject.h
@@ -0,0 +1,43 @@
+#ifndef Py_ODICTOBJECT_H
+#define Py_ODICTOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* OrderedDict */
+/* This API is optional and mostly redundant. */
+
+#ifndef Py_LIMITED_API
+
+typedef struct _odictobject PyODictObject;
+
+PyAPI_DATA(PyTypeObject) PyODict_Type;
+PyAPI_DATA(PyTypeObject) PyODictIter_Type;
+PyAPI_DATA(PyTypeObject) PyODictKeys_Type;
+PyAPI_DATA(PyTypeObject) PyODictItems_Type;
+PyAPI_DATA(PyTypeObject) PyODictValues_Type;
+
+#define PyODict_Check(op) PyObject_TypeCheck(op, &PyODict_Type)
+#define PyODict_CheckExact(op) (Py_TYPE(op) == &PyODict_Type)
+#define PyODict_SIZE(op) PyDict_GET_SIZE((op))
+
+PyAPI_FUNC(PyObject *) PyODict_New(void);
+PyAPI_FUNC(int) PyODict_SetItem(PyObject *od, PyObject *key, PyObject *item);
+PyAPI_FUNC(int) PyODict_DelItem(PyObject *od, PyObject *key);
+
+/* wrappers around PyDict* functions */
+#define PyODict_GetItem(od, key) PyDict_GetItem((PyObject *)od, key)
+#define PyODict_GetItemWithError(od, key) \
+ PyDict_GetItemWithError((PyObject *)od, key)
+#define PyODict_Contains(od, key) PyDict_Contains((PyObject *)od, key)
+#define PyODict_Size(od) PyDict_Size((PyObject *)od)
+#define PyODict_GetItemString(od, key) \
+ PyDict_GetItemString((PyObject *)od, key)
+
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_ODICTOBJECT_H */
diff --git a/Include/opcode.h b/Include/opcode.h
new file mode 100644
index 0000000..fc6cbf3
--- /dev/null
+++ b/Include/opcode.h
@@ -0,0 +1,147 @@
+/* Auto-generated by Tools/scripts/generate_opcode_h.py */
+#ifndef Py_OPCODE_H
+#define Py_OPCODE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+ /* Instruction opcodes for compiled code */
+#define POP_TOP 1
+#define ROT_TWO 2
+#define ROT_THREE 3
+#define DUP_TOP 4
+#define DUP_TOP_TWO 5
+#define NOP 9
+#define UNARY_POSITIVE 10
+#define UNARY_NEGATIVE 11
+#define UNARY_NOT 12
+#define UNARY_INVERT 15
+#define BINARY_MATRIX_MULTIPLY 16
+#define INPLACE_MATRIX_MULTIPLY 17
+#define BINARY_POWER 19
+#define BINARY_MULTIPLY 20
+#define BINARY_MODULO 22
+#define BINARY_ADD 23
+#define BINARY_SUBTRACT 24
+#define BINARY_SUBSCR 25
+#define BINARY_FLOOR_DIVIDE 26
+#define BINARY_TRUE_DIVIDE 27
+#define INPLACE_FLOOR_DIVIDE 28
+#define INPLACE_TRUE_DIVIDE 29
+#define GET_AITER 50
+#define GET_ANEXT 51
+#define BEFORE_ASYNC_WITH 52
+#define INPLACE_ADD 55
+#define INPLACE_SUBTRACT 56
+#define INPLACE_MULTIPLY 57
+#define INPLACE_MODULO 59
+#define STORE_SUBSCR 60
+#define DELETE_SUBSCR 61
+#define BINARY_LSHIFT 62
+#define BINARY_RSHIFT 63
+#define BINARY_AND 64
+#define BINARY_XOR 65
+#define BINARY_OR 66
+#define INPLACE_POWER 67
+#define GET_ITER 68
+#define GET_YIELD_FROM_ITER 69
+#define PRINT_EXPR 70
+#define LOAD_BUILD_CLASS 71
+#define YIELD_FROM 72
+#define GET_AWAITABLE 73
+#define INPLACE_LSHIFT 75
+#define INPLACE_RSHIFT 76
+#define INPLACE_AND 77
+#define INPLACE_XOR 78
+#define INPLACE_OR 79
+#define BREAK_LOOP 80
+#define WITH_CLEANUP_START 81
+#define WITH_CLEANUP_FINISH 82
+#define RETURN_VALUE 83
+#define IMPORT_STAR 84
+#define SETUP_ANNOTATIONS 85
+#define YIELD_VALUE 86
+#define POP_BLOCK 87
+#define END_FINALLY 88
+#define POP_EXCEPT 89
+#define HAVE_ARGUMENT 90
+#define STORE_NAME 90
+#define DELETE_NAME 91
+#define UNPACK_SEQUENCE 92
+#define FOR_ITER 93
+#define UNPACK_EX 94
+#define STORE_ATTR 95
+#define DELETE_ATTR 96
+#define STORE_GLOBAL 97
+#define DELETE_GLOBAL 98
+#define LOAD_CONST 100
+#define LOAD_NAME 101
+#define BUILD_TUPLE 102
+#define BUILD_LIST 103
+#define BUILD_SET 104
+#define BUILD_MAP 105
+#define LOAD_ATTR 106
+#define COMPARE_OP 107
+#define IMPORT_NAME 108
+#define IMPORT_FROM 109
+#define JUMP_FORWARD 110
+#define JUMP_IF_FALSE_OR_POP 111
+#define JUMP_IF_TRUE_OR_POP 112
+#define JUMP_ABSOLUTE 113
+#define POP_JUMP_IF_FALSE 114
+#define POP_JUMP_IF_TRUE 115
+#define LOAD_GLOBAL 116
+#define CONTINUE_LOOP 119
+#define SETUP_LOOP 120
+#define SETUP_EXCEPT 121
+#define SETUP_FINALLY 122
+#define LOAD_FAST 124
+#define STORE_FAST 125
+#define DELETE_FAST 126
+#define RAISE_VARARGS 130
+#define CALL_FUNCTION 131
+#define MAKE_FUNCTION 132
+#define BUILD_SLICE 133
+#define LOAD_CLOSURE 135
+#define LOAD_DEREF 136
+#define STORE_DEREF 137
+#define DELETE_DEREF 138
+#define CALL_FUNCTION_KW 141
+#define CALL_FUNCTION_EX 142
+#define SETUP_WITH 143
+#define EXTENDED_ARG 144
+#define LIST_APPEND 145
+#define SET_ADD 146
+#define MAP_ADD 147
+#define LOAD_CLASSDEREF 148
+#define BUILD_LIST_UNPACK 149
+#define BUILD_MAP_UNPACK 150
+#define BUILD_MAP_UNPACK_WITH_CALL 151
+#define BUILD_TUPLE_UNPACK 152
+#define BUILD_SET_UNPACK 153
+#define SETUP_ASYNC_WITH 154
+#define FORMAT_VALUE 155
+#define BUILD_CONST_KEY_MAP 156
+#define BUILD_STRING 157
+#define BUILD_TUPLE_UNPACK_WITH_CALL 158
+#define LOAD_METHOD 160
+#define CALL_METHOD 161
+
+/* EXCEPT_HANDLER is a special, implicit block type which is created when
+ entering an except handler. It is not an opcode but we define it here
+ as we want it to be available to both frameobject.c and ceval.c, while
+ remaining private.*/
+#define EXCEPT_HANDLER 257
+
+
+enum cmp_op {PyCmp_LT=Py_LT, PyCmp_LE=Py_LE, PyCmp_EQ=Py_EQ, PyCmp_NE=Py_NE,
+ PyCmp_GT=Py_GT, PyCmp_GE=Py_GE, PyCmp_IN, PyCmp_NOT_IN,
+ PyCmp_IS, PyCmp_IS_NOT, PyCmp_EXC_MATCH, PyCmp_BAD};
+
+#define HAS_ARG(op) ((op) >= HAVE_ARGUMENT)
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_OPCODE_H */
diff --git a/Include/osdefs.h b/Include/osdefs.h
new file mode 100644
index 0000000..bd84c1c
--- /dev/null
+++ b/Include/osdefs.h
@@ -0,0 +1,47 @@
+#ifndef Py_OSDEFS_H
+#define Py_OSDEFS_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Operating system dependencies */
+
+#ifdef MS_WINDOWS
+#define SEP L'\\'
+#define ALTSEP L'/'
+#define MAXPATHLEN 256
+#define DELIM L';'
+#endif
+
+/* Filename separator */
+#ifndef SEP
+#define SEP L'/'
+#endif
+
+/* Max pathname length */
+#ifdef __hpux
+#include
+#include
+#ifndef PATH_MAX
+#define PATH_MAX MAXPATHLEN
+#endif
+#endif
+
+#ifndef MAXPATHLEN
+#if defined(PATH_MAX) && PATH_MAX > 1024
+#define MAXPATHLEN PATH_MAX
+#else
+#define MAXPATHLEN 1024
+#endif
+#endif
+
+/* Search path entry delimiter */
+#ifndef DELIM
+#define DELIM L':'
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_OSDEFS_H */
diff --git a/Include/osmodule.h b/Include/osmodule.h
new file mode 100644
index 0000000..9095c2f
--- /dev/null
+++ b/Include/osmodule.h
@@ -0,0 +1,17 @@
+
+/* os module interface */
+
+#ifndef Py_OSMODULE_H
+#define Py_OSMODULE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03060000
+PyAPI_FUNC(PyObject *) PyOS_FSPath(PyObject *path);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_OSMODULE_H */
diff --git a/Include/parsetok.h b/Include/parsetok.h
new file mode 100644
index 0000000..c9407a3
--- /dev/null
+++ b/Include/parsetok.h
@@ -0,0 +1,108 @@
+
+/* Parser-tokenizer link interface */
+#ifndef Py_LIMITED_API
+#ifndef Py_PARSETOK_H
+#define Py_PARSETOK_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+ int error;
+#ifndef PGEN
+ /* The filename is useless for pgen, see comment in tok_state structure */
+ PyObject *filename;
+#endif
+ int lineno;
+ int offset;
+ char *text; /* UTF-8-encoded string */
+ int token;
+ int expected;
+} perrdetail;
+
+#if 0
+#define PyPARSE_YIELD_IS_KEYWORD 0x0001
+#endif
+
+#define PyPARSE_DONT_IMPLY_DEDENT 0x0002
+
+#if 0
+#define PyPARSE_WITH_IS_KEYWORD 0x0003
+#define PyPARSE_PRINT_IS_FUNCTION 0x0004
+#define PyPARSE_UNICODE_LITERALS 0x0008
+#endif
+
+#define PyPARSE_IGNORE_COOKIE 0x0010
+#define PyPARSE_BARRY_AS_BDFL 0x0020
+
+PyAPI_FUNC(node *) PyParser_ParseString(const char *, grammar *, int,
+ perrdetail *);
+PyAPI_FUNC(node *) PyParser_ParseFile (FILE *, const char *, grammar *, int,
+ const char *, const char *,
+ perrdetail *);
+
+PyAPI_FUNC(node *) PyParser_ParseStringFlags(const char *, grammar *, int,
+ perrdetail *, int);
+PyAPI_FUNC(node *) PyParser_ParseFileFlags(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ const char *enc,
+ grammar *g,
+ int start,
+ const char *ps1,
+ const char *ps2,
+ perrdetail *err_ret,
+ int flags);
+PyAPI_FUNC(node *) PyParser_ParseFileFlagsEx(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ const char *enc,
+ grammar *g,
+ int start,
+ const char *ps1,
+ const char *ps2,
+ perrdetail *err_ret,
+ int *flags);
+PyAPI_FUNC(node *) PyParser_ParseFileObject(
+ FILE *fp,
+ PyObject *filename,
+ const char *enc,
+ grammar *g,
+ int start,
+ const char *ps1,
+ const char *ps2,
+ perrdetail *err_ret,
+ int *flags);
+
+PyAPI_FUNC(node *) PyParser_ParseStringFlagsFilename(
+ const char *s,
+ const char *filename, /* decoded from the filesystem encoding */
+ grammar *g,
+ int start,
+ perrdetail *err_ret,
+ int flags);
+PyAPI_FUNC(node *) PyParser_ParseStringFlagsFilenameEx(
+ const char *s,
+ const char *filename, /* decoded from the filesystem encoding */
+ grammar *g,
+ int start,
+ perrdetail *err_ret,
+ int *flags);
+PyAPI_FUNC(node *) PyParser_ParseStringObject(
+ const char *s,
+ PyObject *filename,
+ grammar *g,
+ int start,
+ perrdetail *err_ret,
+ int *flags);
+
+/* Note that the following functions are defined in pythonrun.c,
+ not in parsetok.c */
+PyAPI_FUNC(void) PyParser_SetError(perrdetail *);
+PyAPI_FUNC(void) PyParser_ClearError(perrdetail *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PARSETOK_H */
+#endif /* !Py_LIMITED_API */
diff --git a/Include/patchlevel.h b/Include/patchlevel.h
new file mode 100644
index 0000000..13876bd
--- /dev/null
+++ b/Include/patchlevel.h
@@ -0,0 +1,35 @@
+
+/* Python version identification scheme.
+
+ When the major or minor version changes, the VERSION variable in
+ configure.ac must also be changed.
+
+ There is also (independent) API version information in modsupport.h.
+*/
+
+/* Values for PY_RELEASE_LEVEL */
+#define PY_RELEASE_LEVEL_ALPHA 0xA
+#define PY_RELEASE_LEVEL_BETA 0xB
+#define PY_RELEASE_LEVEL_GAMMA 0xC /* For release candidates */
+#define PY_RELEASE_LEVEL_FINAL 0xF /* Serial should be 0 here */
+ /* Higher for patch releases */
+
+/* Version parsed out into numeric values */
+/*--start constants--*/
+#define PY_MAJOR_VERSION 3
+#define PY_MINOR_VERSION 7
+#define PY_MICRO_VERSION 0
+#define PY_RELEASE_LEVEL PY_RELEASE_LEVEL_FINAL
+#define PY_RELEASE_SERIAL 0
+
+/* Version as a string */
+#define PY_VERSION "3.7.0"
+/*--end constants--*/
+
+/* Version as a single 4-byte hex number, e.g. 0x010502B2 == 1.5.2b2.
+ Use this for numeric comparisons, e.g. #if PY_VERSION_HEX >= ... */
+#define PY_VERSION_HEX ((PY_MAJOR_VERSION << 24) | \
+ (PY_MINOR_VERSION << 16) | \
+ (PY_MICRO_VERSION << 8) | \
+ (PY_RELEASE_LEVEL << 4) | \
+ (PY_RELEASE_SERIAL << 0))
diff --git a/Include/pgen.h b/Include/pgen.h
new file mode 100644
index 0000000..8a325ed
--- /dev/null
+++ b/Include/pgen.h
@@ -0,0 +1,18 @@
+#ifndef Py_PGEN_H
+#define Py_PGEN_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Parser generator interface */
+
+extern grammar *meta_grammar(void);
+
+struct _node;
+extern grammar *pgen(struct _node *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PGEN_H */
diff --git a/Include/pgenheaders.h b/Include/pgenheaders.h
new file mode 100644
index 0000000..dbc5e0a
--- /dev/null
+++ b/Include/pgenheaders.h
@@ -0,0 +1,43 @@
+#ifndef Py_PGENHEADERS_H
+#define Py_PGENHEADERS_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Include files and extern declarations used by most of the parser. */
+
+#include "Python.h"
+
+PyAPI_FUNC(void) PySys_WriteStdout(const char *format, ...)
+ Py_GCC_ATTRIBUTE((format(printf, 1, 2)));
+PyAPI_FUNC(void) PySys_WriteStderr(const char *format, ...)
+ Py_GCC_ATTRIBUTE((format(printf, 1, 2)));
+
+#define addarc _Py_addarc
+#define addbit _Py_addbit
+#define adddfa _Py_adddfa
+#define addfirstsets _Py_addfirstsets
+#define addlabel _Py_addlabel
+#define addstate _Py_addstate
+#define delbitset _Py_delbitset
+#define dumptree _Py_dumptree
+#define findlabel _Py_findlabel
+#define freegrammar _Py_freegrammar
+#define mergebitset _Py_mergebitset
+#define meta_grammar _Py_meta_grammar
+#define newbitset _Py_newbitset
+#define newgrammar _Py_newgrammar
+#define pgen _Py_pgen
+#define printgrammar _Py_printgrammar
+#define printnonterminals _Py_printnonterminals
+#define printtree _Py_printtree
+#define samebitset _Py_samebitset
+#define showtree _Py_showtree
+#define tok_dump _Py_tok_dump
+#define translatelabels _Py_translatelabels
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PGENHEADERS_H */
diff --git a/Include/py_curses.h b/Include/py_curses.h
new file mode 100644
index 0000000..0eebc36
--- /dev/null
+++ b/Include/py_curses.h
@@ -0,0 +1,159 @@
+
+#ifndef Py_CURSES_H
+#define Py_CURSES_H
+
+#ifdef __APPLE__
+/*
+** On Mac OS X 10.2 [n]curses.h and stdlib.h use different guards
+** against multiple definition of wchar_t.
+*/
+#ifdef _BSD_WCHAR_T_DEFINED_
+#define _WCHAR_T
+#endif
+#endif /* __APPLE__ */
+
+/* On FreeBSD, [n]curses.h and stdlib.h/wchar.h use different guards
+ against multiple definition of wchar_t and wint_t. */
+#if defined(__FreeBSD__) && defined(_XOPEN_SOURCE_EXTENDED)
+# ifndef __wchar_t
+# define __wchar_t
+# endif
+# ifndef __wint_t
+# define __wint_t
+# endif
+#endif
+
+#if !defined(HAVE_CURSES_IS_PAD) && defined(WINDOW_HAS_FLAGS)
+/* The following definition is necessary for ncurses 5.7; without it,
+ some of [n]curses.h set NCURSES_OPAQUE to 1, and then Python
+ can't get at the WINDOW flags field. */
+#define NCURSES_OPAQUE 0
+#endif
+
+#ifdef HAVE_NCURSES_H
+#include
+#else
+#include
+#endif
+
+#ifdef HAVE_NCURSES_H
+/* configure was checking , but we will
+ use , which has some or all these features. */
+#if !defined(WINDOW_HAS_FLAGS) && !(NCURSES_OPAQUE+0)
+#define WINDOW_HAS_FLAGS 1
+#endif
+#if !defined(HAVE_CURSES_IS_PAD) && NCURSES_VERSION_PATCH+0 >= 20090906
+#define HAVE_CURSES_IS_PAD 1
+#endif
+#ifndef MVWDELCH_IS_EXPRESSION
+#define MVWDELCH_IS_EXPRESSION 1
+#endif
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#define PyCurses_API_pointers 4
+
+/* Type declarations */
+
+typedef struct {
+ PyObject_HEAD
+ WINDOW *win;
+ char *encoding;
+} PyCursesWindowObject;
+
+#define PyCursesWindow_Check(v) (Py_TYPE(v) == &PyCursesWindow_Type)
+
+#define PyCurses_CAPSULE_NAME "_curses._C_API"
+
+
+#ifdef CURSES_MODULE
+/* This section is used when compiling _cursesmodule.c */
+
+#else
+/* This section is used in modules that use the _cursesmodule API */
+
+static void **PyCurses_API;
+
+#define PyCursesWindow_Type (*(PyTypeObject *) PyCurses_API[0])
+#define PyCursesSetupTermCalled {if (! ((int (*)(void))PyCurses_API[1]) () ) return NULL;}
+#define PyCursesInitialised {if (! ((int (*)(void))PyCurses_API[2]) () ) return NULL;}
+#define PyCursesInitialisedColor {if (! ((int (*)(void))PyCurses_API[3]) () ) return NULL;}
+
+#define import_curses() \
+ PyCurses_API = (void **)PyCapsule_Import(PyCurses_CAPSULE_NAME, 1);
+
+#endif
+
+/* general error messages */
+static const char catchall_ERR[] = "curses function returned ERR";
+static const char catchall_NULL[] = "curses function returned NULL";
+
+/* Function Prototype Macros - They are ugly but very, very useful. ;-)
+
+ X - function name
+ TYPE - parameter Type
+ ERGSTR - format string for construction of the return value
+ PARSESTR - format string for argument parsing
+ */
+
+#define NoArgNoReturnFunction(X) \
+static PyObject *PyCurses_ ## X (PyObject *self) \
+{ \
+ PyCursesInitialised \
+ return PyCursesCheckERR(X(), # X); }
+
+#define NoArgOrFlagNoReturnFunction(X) \
+static PyObject *PyCurses_ ## X (PyObject *self, PyObject *args) \
+{ \
+ int flag = 0; \
+ PyCursesInitialised \
+ switch(PyTuple_Size(args)) { \
+ case 0: \
+ return PyCursesCheckERR(X(), # X); \
+ case 1: \
+ if (!PyArg_ParseTuple(args, "i;True(1) or False(0)", &flag)) return NULL; \
+ if (flag) return PyCursesCheckERR(X(), # X); \
+ else return PyCursesCheckERR(no ## X (), # X); \
+ default: \
+ PyErr_SetString(PyExc_TypeError, # X " requires 0 or 1 arguments"); \
+ return NULL; } }
+
+#define NoArgReturnIntFunction(X) \
+static PyObject *PyCurses_ ## X (PyObject *self) \
+{ \
+ PyCursesInitialised \
+ return PyLong_FromLong((long) X()); }
+
+
+#define NoArgReturnStringFunction(X) \
+static PyObject *PyCurses_ ## X (PyObject *self) \
+{ \
+ PyCursesInitialised \
+ return PyBytes_FromString(X()); }
+
+#define NoArgTrueFalseFunction(X) \
+static PyObject *PyCurses_ ## X (PyObject *self) \
+{ \
+ PyCursesInitialised \
+ if (X () == FALSE) { \
+ Py_RETURN_FALSE; \
+ } \
+ Py_RETURN_TRUE; }
+
+#define NoArgNoReturnVoidFunction(X) \
+static PyObject *PyCurses_ ## X (PyObject *self) \
+{ \
+ PyCursesInitialised \
+ X(); \
+ Py_RETURN_NONE; }
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !defined(Py_CURSES_H) */
+
+
diff --git a/Include/pyarena.h b/Include/pyarena.h
new file mode 100644
index 0000000..db3ad01
--- /dev/null
+++ b/Include/pyarena.h
@@ -0,0 +1,64 @@
+/* An arena-like memory interface for the compiler.
+ */
+
+#ifndef Py_LIMITED_API
+#ifndef Py_PYARENA_H
+#define Py_PYARENA_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+ typedef struct _arena PyArena;
+
+ /* PyArena_New() and PyArena_Free() create a new arena and free it,
+ respectively. Once an arena has been created, it can be used
+ to allocate memory via PyArena_Malloc(). Pointers to PyObject can
+ also be registered with the arena via PyArena_AddPyObject(), and the
+ arena will ensure that the PyObjects stay alive at least until
+ PyArena_Free() is called. When an arena is freed, all the memory it
+ allocated is freed, the arena releases internal references to registered
+ PyObject*, and none of its pointers are valid.
+ XXX (tim) What does "none of its pointers are valid" mean? Does it
+ XXX mean that pointers previously obtained via PyArena_Malloc() are
+ XXX no longer valid? (That's clearly true, but not sure that's what
+ XXX the text is trying to say.)
+
+ PyArena_New() returns an arena pointer. On error, it
+ returns a negative number and sets an exception.
+ XXX (tim): Not true. On error, PyArena_New() actually returns NULL,
+ XXX and looks like it may or may not set an exception (e.g., if the
+ XXX internal PyList_New(0) returns NULL, PyArena_New() passes that on
+ XXX and an exception is set; OTOH, if the internal
+ XXX block_new(DEFAULT_BLOCK_SIZE) returns NULL, that's passed on but
+ XXX an exception is not set in that case).
+ */
+ PyAPI_FUNC(PyArena *) PyArena_New(void);
+ PyAPI_FUNC(void) PyArena_Free(PyArena *);
+
+ /* Mostly like malloc(), return the address of a block of memory spanning
+ * `size` bytes, or return NULL (without setting an exception) if enough
+ * new memory can't be obtained. Unlike malloc(0), PyArena_Malloc() with
+ * size=0 does not guarantee to return a unique pointer (the pointer
+ * returned may equal one or more other pointers obtained from
+ * PyArena_Malloc()).
+ * Note that pointers obtained via PyArena_Malloc() must never be passed to
+ * the system free() or realloc(), or to any of Python's similar memory-
+ * management functions. PyArena_Malloc()-obtained pointers remain valid
+ * until PyArena_Free(ar) is called, at which point all pointers obtained
+ * from the arena `ar` become invalid simultaneously.
+ */
+ PyAPI_FUNC(void *) PyArena_Malloc(PyArena *, size_t size);
+
+ /* This routine isn't a proper arena allocation routine. It takes
+ * a PyObject* and records it so that it can be DECREFed when the
+ * arena is freed.
+ */
+ PyAPI_FUNC(int) PyArena_AddPyObject(PyArena *, PyObject *);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_PYARENA_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/pyatomic.h b/Include/pyatomic.h
new file mode 100644
index 0000000..9a497a6
--- /dev/null
+++ b/Include/pyatomic.h
@@ -0,0 +1,535 @@
+#ifndef Py_ATOMIC_H
+#define Py_ATOMIC_H
+#ifdef Py_BUILD_CORE
+
+#include "dynamic_annotations.h"
+
+#include "pyconfig.h"
+
+#if defined(HAVE_STD_ATOMIC)
+#include
+#endif
+
+
+#if defined(_MSC_VER)
+#include
+#include
+#endif
+
+/* This is modeled after the atomics interface from C1x, according to
+ * the draft at
+ * http://www.open-std.org/JTC1/SC22/wg14/www/docs/n1425.pdf.
+ * Operations and types are named the same except with a _Py_ prefix
+ * and have the same semantics.
+ *
+ * Beware, the implementations here are deep magic.
+ */
+
+#if defined(HAVE_STD_ATOMIC)
+
+typedef enum _Py_memory_order {
+ _Py_memory_order_relaxed = memory_order_relaxed,
+ _Py_memory_order_acquire = memory_order_acquire,
+ _Py_memory_order_release = memory_order_release,
+ _Py_memory_order_acq_rel = memory_order_acq_rel,
+ _Py_memory_order_seq_cst = memory_order_seq_cst
+} _Py_memory_order;
+
+typedef struct _Py_atomic_address {
+ atomic_uintptr_t _value;
+} _Py_atomic_address;
+
+typedef struct _Py_atomic_int {
+ atomic_int _value;
+} _Py_atomic_int;
+
+#define _Py_atomic_signal_fence(/*memory_order*/ ORDER) \
+ atomic_signal_fence(ORDER)
+
+#define _Py_atomic_thread_fence(/*memory_order*/ ORDER) \
+ atomic_thread_fence(ORDER)
+
+#define _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ atomic_store_explicit(&(ATOMIC_VAL)->_value, NEW_VAL, ORDER)
+
+#define _Py_atomic_load_explicit(ATOMIC_VAL, ORDER) \
+ atomic_load_explicit(&(ATOMIC_VAL)->_value, ORDER)
+
+/* Use builtin atomic operations in GCC >= 4.7 */
+#elif defined(HAVE_BUILTIN_ATOMIC)
+
+typedef enum _Py_memory_order {
+ _Py_memory_order_relaxed = __ATOMIC_RELAXED,
+ _Py_memory_order_acquire = __ATOMIC_ACQUIRE,
+ _Py_memory_order_release = __ATOMIC_RELEASE,
+ _Py_memory_order_acq_rel = __ATOMIC_ACQ_REL,
+ _Py_memory_order_seq_cst = __ATOMIC_SEQ_CST
+} _Py_memory_order;
+
+typedef struct _Py_atomic_address {
+ uintptr_t _value;
+} _Py_atomic_address;
+
+typedef struct _Py_atomic_int {
+ int _value;
+} _Py_atomic_int;
+
+#define _Py_atomic_signal_fence(/*memory_order*/ ORDER) \
+ __atomic_signal_fence(ORDER)
+
+#define _Py_atomic_thread_fence(/*memory_order*/ ORDER) \
+ __atomic_thread_fence(ORDER)
+
+#define _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ (assert((ORDER) == __ATOMIC_RELAXED \
+ || (ORDER) == __ATOMIC_SEQ_CST \
+ || (ORDER) == __ATOMIC_RELEASE), \
+ __atomic_store_n(&(ATOMIC_VAL)->_value, NEW_VAL, ORDER))
+
+#define _Py_atomic_load_explicit(ATOMIC_VAL, ORDER) \
+ (assert((ORDER) == __ATOMIC_RELAXED \
+ || (ORDER) == __ATOMIC_SEQ_CST \
+ || (ORDER) == __ATOMIC_ACQUIRE \
+ || (ORDER) == __ATOMIC_CONSUME), \
+ __atomic_load_n(&(ATOMIC_VAL)->_value, ORDER))
+
+/* Only support GCC (for expression statements) and x86 (for simple
+ * atomic semantics) and MSVC x86/x64/ARM */
+#elif defined(__GNUC__) && (defined(__i386__) || defined(__amd64))
+typedef enum _Py_memory_order {
+ _Py_memory_order_relaxed,
+ _Py_memory_order_acquire,
+ _Py_memory_order_release,
+ _Py_memory_order_acq_rel,
+ _Py_memory_order_seq_cst
+} _Py_memory_order;
+
+typedef struct _Py_atomic_address {
+ uintptr_t _value;
+} _Py_atomic_address;
+
+typedef struct _Py_atomic_int {
+ int _value;
+} _Py_atomic_int;
+
+
+static __inline__ void
+_Py_atomic_signal_fence(_Py_memory_order order)
+{
+ if (order != _Py_memory_order_relaxed)
+ __asm__ volatile("":::"memory");
+}
+
+static __inline__ void
+_Py_atomic_thread_fence(_Py_memory_order order)
+{
+ if (order != _Py_memory_order_relaxed)
+ __asm__ volatile("mfence":::"memory");
+}
+
+/* Tell the race checker about this operation's effects. */
+static __inline__ void
+_Py_ANNOTATE_MEMORY_ORDER(const volatile void *address, _Py_memory_order order)
+{
+ (void)address; /* shut up -Wunused-parameter */
+ switch(order) {
+ case _Py_memory_order_release:
+ case _Py_memory_order_acq_rel:
+ case _Py_memory_order_seq_cst:
+ _Py_ANNOTATE_HAPPENS_BEFORE(address);
+ break;
+ case _Py_memory_order_relaxed:
+ case _Py_memory_order_acquire:
+ break;
+ }
+ switch(order) {
+ case _Py_memory_order_acquire:
+ case _Py_memory_order_acq_rel:
+ case _Py_memory_order_seq_cst:
+ _Py_ANNOTATE_HAPPENS_AFTER(address);
+ break;
+ case _Py_memory_order_relaxed:
+ case _Py_memory_order_release:
+ break;
+ }
+}
+
+#define _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ __extension__ ({ \
+ __typeof__(ATOMIC_VAL) atomic_val = ATOMIC_VAL; \
+ __typeof__(atomic_val->_value) new_val = NEW_VAL;\
+ volatile __typeof__(new_val) *volatile_data = &atomic_val->_value; \
+ _Py_memory_order order = ORDER; \
+ _Py_ANNOTATE_MEMORY_ORDER(atomic_val, order); \
+ \
+ /* Perform the operation. */ \
+ _Py_ANNOTATE_IGNORE_WRITES_BEGIN(); \
+ switch(order) { \
+ case _Py_memory_order_release: \
+ _Py_atomic_signal_fence(_Py_memory_order_release); \
+ /* fallthrough */ \
+ case _Py_memory_order_relaxed: \
+ *volatile_data = new_val; \
+ break; \
+ \
+ case _Py_memory_order_acquire: \
+ case _Py_memory_order_acq_rel: \
+ case _Py_memory_order_seq_cst: \
+ __asm__ volatile("xchg %0, %1" \
+ : "+r"(new_val) \
+ : "m"(atomic_val->_value) \
+ : "memory"); \
+ break; \
+ } \
+ _Py_ANNOTATE_IGNORE_WRITES_END(); \
+ })
+
+#define _Py_atomic_load_explicit(ATOMIC_VAL, ORDER) \
+ __extension__ ({ \
+ __typeof__(ATOMIC_VAL) atomic_val = ATOMIC_VAL; \
+ __typeof__(atomic_val->_value) result; \
+ volatile __typeof__(result) *volatile_data = &atomic_val->_value; \
+ _Py_memory_order order = ORDER; \
+ _Py_ANNOTATE_MEMORY_ORDER(atomic_val, order); \
+ \
+ /* Perform the operation. */ \
+ _Py_ANNOTATE_IGNORE_READS_BEGIN(); \
+ switch(order) { \
+ case _Py_memory_order_release: \
+ case _Py_memory_order_acq_rel: \
+ case _Py_memory_order_seq_cst: \
+ /* Loads on x86 are not releases by default, so need a */ \
+ /* thread fence. */ \
+ _Py_atomic_thread_fence(_Py_memory_order_release); \
+ break; \
+ default: \
+ /* No fence */ \
+ break; \
+ } \
+ result = *volatile_data; \
+ switch(order) { \
+ case _Py_memory_order_acquire: \
+ case _Py_memory_order_acq_rel: \
+ case _Py_memory_order_seq_cst: \
+ /* Loads on x86 are automatically acquire operations so */ \
+ /* can get by with just a compiler fence. */ \
+ _Py_atomic_signal_fence(_Py_memory_order_acquire); \
+ break; \
+ default: \
+ /* No fence */ \
+ break; \
+ } \
+ _Py_ANNOTATE_IGNORE_READS_END(); \
+ result; \
+ })
+
+#elif defined(_MSC_VER)
+/* _Interlocked* functions provide a full memory barrier and are therefore
+ enough for acq_rel and seq_cst. If the HLE variants aren't available
+ in hardware they will fall back to a full memory barrier as well.
+
+ This might affect performance but likely only in some very specific and
+ hard to meassure scenario.
+*/
+#if defined(_M_IX86) || defined(_M_X64)
+typedef enum _Py_memory_order {
+ _Py_memory_order_relaxed,
+ _Py_memory_order_acquire,
+ _Py_memory_order_release,
+ _Py_memory_order_acq_rel,
+ _Py_memory_order_seq_cst
+} _Py_memory_order;
+
+typedef struct _Py_atomic_address {
+ volatile uintptr_t _value;
+} _Py_atomic_address;
+
+typedef struct _Py_atomic_int {
+ volatile int _value;
+} _Py_atomic_int;
+
+
+#if defined(_M_X64)
+#define _Py_atomic_store_64bit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ switch (ORDER) { \
+ case _Py_memory_order_acquire: \
+ _InterlockedExchange64_HLEAcquire((__int64 volatile*)ATOMIC_VAL, (__int64)NEW_VAL); \
+ break; \
+ case _Py_memory_order_release: \
+ _InterlockedExchange64_HLERelease((__int64 volatile*)ATOMIC_VAL, (__int64)NEW_VAL); \
+ break; \
+ default: \
+ _InterlockedExchange64((__int64 volatile*)ATOMIC_VAL, (__int64)NEW_VAL); \
+ break; \
+ }
+#else
+#define _Py_atomic_store_64bit(ATOMIC_VAL, NEW_VAL, ORDER) ((void)0);
+#endif
+
+#define _Py_atomic_store_32bit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ switch (ORDER) { \
+ case _Py_memory_order_acquire: \
+ _InterlockedExchange_HLEAcquire((volatile long*)ATOMIC_VAL, (int)NEW_VAL); \
+ break; \
+ case _Py_memory_order_release: \
+ _InterlockedExchange_HLERelease((volatile long*)ATOMIC_VAL, (int)NEW_VAL); \
+ break; \
+ default: \
+ _InterlockedExchange((volatile long*)ATOMIC_VAL, (int)NEW_VAL); \
+ break; \
+ }
+
+#if defined(_M_X64)
+/* This has to be an intptr_t for now.
+ gil_created() uses -1 as a sentinel value, if this returns
+ a uintptr_t it will do an unsigned compare and crash
+*/
+inline intptr_t _Py_atomic_load_64bit(volatile uintptr_t* value, int order) {
+ __int64 old;
+ switch (order) {
+ case _Py_memory_order_acquire:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange64_HLEAcquire((volatile __int64*)value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_release:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange64_HLERelease((volatile __int64*)value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_relaxed:
+ old = *value;
+ break;
+ default:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange64((volatile __int64*)value, old, old) != old);
+ break;
+ }
+ }
+ return old;
+}
+
+#else
+#define _Py_atomic_load_64bit(ATOMIC_VAL, ORDER) *ATOMIC_VAL
+#endif
+
+inline int _Py_atomic_load_32bit(volatile int* value, int order) {
+ long old;
+ switch (order) {
+ case _Py_memory_order_acquire:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange_HLEAcquire((volatile long*)value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_release:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange_HLERelease((volatile long*)value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_relaxed:
+ old = *value;
+ break;
+ default:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange((volatile long*)value, old, old) != old);
+ break;
+ }
+ }
+ return old;
+}
+
+#define _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ if (sizeof(*ATOMIC_VAL._value) == 8) { \
+ _Py_atomic_store_64bit((volatile long long*)ATOMIC_VAL._value, NEW_VAL, ORDER) } else { \
+ _Py_atomic_store_32bit((volatile long*)ATOMIC_VAL._value, NEW_VAL, ORDER) }
+
+#define _Py_atomic_load_explicit(ATOMIC_VAL, ORDER) \
+ ( \
+ sizeof(*(ATOMIC_VAL._value)) == 8 ? \
+ _Py_atomic_load_64bit((volatile long long*)ATOMIC_VAL._value, ORDER) : \
+ _Py_atomic_load_32bit((volatile long*)ATOMIC_VAL._value, ORDER) \
+ )
+#elif defined(_M_ARM) || defined(_M_ARM64)
+typedef enum _Py_memory_order {
+ _Py_memory_order_relaxed,
+ _Py_memory_order_acquire,
+ _Py_memory_order_release,
+ _Py_memory_order_acq_rel,
+ _Py_memory_order_seq_cst
+} _Py_memory_order;
+
+typedef struct _Py_atomic_address {
+ volatile uintptr_t _value;
+} _Py_atomic_address;
+
+typedef struct _Py_atomic_int {
+ volatile int _value;
+} _Py_atomic_int;
+
+
+#if defined(_M_ARM64)
+#define _Py_atomic_store_64bit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ switch (ORDER) { \
+ case _Py_memory_order_acquire: \
+ _InterlockedExchange64_acq((__int64 volatile*)ATOMIC_VAL, (__int64)NEW_VAL); \
+ break; \
+ case _Py_memory_order_release: \
+ _InterlockedExchange64_rel((__int64 volatile*)ATOMIC_VAL, (__int64)NEW_VAL); \
+ break; \
+ default: \
+ _InterlockedExchange64((__int64 volatile*)ATOMIC_VAL, (__int64)NEW_VAL); \
+ break; \
+ }
+#else
+#define _Py_atomic_store_64bit(ATOMIC_VAL, NEW_VAL, ORDER) ((void)0);
+#endif
+
+#define _Py_atomic_store_32bit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ switch (ORDER) { \
+ case _Py_memory_order_acquire: \
+ _InterlockedExchange_acq((volatile long*)ATOMIC_VAL, (int)NEW_VAL); \
+ break; \
+ case _Py_memory_order_release: \
+ _InterlockedExchange_rel((volatile long*)ATOMIC_VAL, (int)NEW_VAL); \
+ break; \
+ default: \
+ _InterlockedExchange((volatile long*)ATOMIC_VAL, (int)NEW_VAL); \
+ break; \
+ }
+
+#if defined(_M_ARM64)
+/* This has to be an intptr_t for now.
+ gil_created() uses -1 as a sentinel value, if this returns
+ a uintptr_t it will do an unsigned compare and crash
+*/
+inline intptr_t _Py_atomic_load_64bit(volatile uintptr_t* value, int order) {
+ uintptr_t old;
+ switch (order) {
+ case _Py_memory_order_acquire:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange64_acq(value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_release:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange64_rel(value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_relaxed:
+ old = *value;
+ break;
+ default:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange64(value, old, old) != old);
+ break;
+ }
+ }
+ return old;
+}
+
+#else
+#define _Py_atomic_load_64bit(ATOMIC_VAL, ORDER) *ATOMIC_VAL
+#endif
+
+inline int _Py_atomic_load_32bit(volatile int* value, int order) {
+ int old;
+ switch (order) {
+ case _Py_memory_order_acquire:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange_acq(value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_release:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange_rel(value, old, old) != old);
+ break;
+ }
+ case _Py_memory_order_relaxed:
+ old = *value;
+ break;
+ default:
+ {
+ do {
+ old = *value;
+ } while(_InterlockedCompareExchange(value, old, old) != old);
+ break;
+ }
+ }
+ return old;
+}
+
+#define _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ if (sizeof(*ATOMIC_VAL._value) == 8) { \
+ _Py_atomic_store_64bit(ATOMIC_VAL._value, NEW_VAL, ORDER) } else { \
+ _Py_atomic_store_32bit(ATOMIC_VAL._value, NEW_VAL, ORDER) }
+
+#define _Py_atomic_load_explicit(ATOMIC_VAL, ORDER) \
+ ( \
+ sizeof(*(ATOMIC_VAL._value)) == 8 ? \
+ _Py_atomic_load_64bit(ATOMIC_VAL._value, ORDER) : \
+ _Py_atomic_load_32bit(ATOMIC_VAL._value, ORDER) \
+ )
+#endif
+#else /* !gcc x86 !_msc_ver */
+typedef enum _Py_memory_order {
+ _Py_memory_order_relaxed,
+ _Py_memory_order_acquire,
+ _Py_memory_order_release,
+ _Py_memory_order_acq_rel,
+ _Py_memory_order_seq_cst
+} _Py_memory_order;
+
+typedef struct _Py_atomic_address {
+ uintptr_t _value;
+} _Py_atomic_address;
+
+typedef struct _Py_atomic_int {
+ int _value;
+} _Py_atomic_int;
+/* Fall back to other compilers and processors by assuming that simple
+ volatile accesses are atomic. This is false, so people should port
+ this. */
+#define _Py_atomic_signal_fence(/*memory_order*/ ORDER) ((void)0)
+#define _Py_atomic_thread_fence(/*memory_order*/ ORDER) ((void)0)
+#define _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, ORDER) \
+ ((ATOMIC_VAL)->_value = NEW_VAL)
+#define _Py_atomic_load_explicit(ATOMIC_VAL, ORDER) \
+ ((ATOMIC_VAL)->_value)
+#endif
+
+/* Standardized shortcuts. */
+#define _Py_atomic_store(ATOMIC_VAL, NEW_VAL) \
+ _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, _Py_memory_order_seq_cst)
+#define _Py_atomic_load(ATOMIC_VAL) \
+ _Py_atomic_load_explicit(ATOMIC_VAL, _Py_memory_order_seq_cst)
+
+/* Python-local extensions */
+
+#define _Py_atomic_store_relaxed(ATOMIC_VAL, NEW_VAL) \
+ _Py_atomic_store_explicit(ATOMIC_VAL, NEW_VAL, _Py_memory_order_relaxed)
+#define _Py_atomic_load_relaxed(ATOMIC_VAL) \
+ _Py_atomic_load_explicit(ATOMIC_VAL, _Py_memory_order_relaxed)
+#endif /* Py_BUILD_CORE */
+#endif /* Py_ATOMIC_H */
diff --git a/Include/pycapsule.h b/Include/pycapsule.h
new file mode 100644
index 0000000..d9ecda7
--- /dev/null
+++ b/Include/pycapsule.h
@@ -0,0 +1,59 @@
+
+/* Capsule objects let you wrap a C "void *" pointer in a Python
+ object. They're a way of passing data through the Python interpreter
+ without creating your own custom type.
+
+ Capsules are used for communication between extension modules.
+ They provide a way for an extension module to export a C interface
+ to other extension modules, so that extension modules can use the
+ Python import mechanism to link to one another.
+
+ For more information, please see "c-api/capsule.html" in the
+ documentation.
+*/
+
+#ifndef Py_CAPSULE_H
+#define Py_CAPSULE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_DATA(PyTypeObject) PyCapsule_Type;
+
+typedef void (*PyCapsule_Destructor)(PyObject *);
+
+#define PyCapsule_CheckExact(op) (Py_TYPE(op) == &PyCapsule_Type)
+
+
+PyAPI_FUNC(PyObject *) PyCapsule_New(
+ void *pointer,
+ const char *name,
+ PyCapsule_Destructor destructor);
+
+PyAPI_FUNC(void *) PyCapsule_GetPointer(PyObject *capsule, const char *name);
+
+PyAPI_FUNC(PyCapsule_Destructor) PyCapsule_GetDestructor(PyObject *capsule);
+
+PyAPI_FUNC(const char *) PyCapsule_GetName(PyObject *capsule);
+
+PyAPI_FUNC(void *) PyCapsule_GetContext(PyObject *capsule);
+
+PyAPI_FUNC(int) PyCapsule_IsValid(PyObject *capsule, const char *name);
+
+PyAPI_FUNC(int) PyCapsule_SetPointer(PyObject *capsule, void *pointer);
+
+PyAPI_FUNC(int) PyCapsule_SetDestructor(PyObject *capsule, PyCapsule_Destructor destructor);
+
+PyAPI_FUNC(int) PyCapsule_SetName(PyObject *capsule, const char *name);
+
+PyAPI_FUNC(int) PyCapsule_SetContext(PyObject *capsule, void *context);
+
+PyAPI_FUNC(void *) PyCapsule_Import(
+ const char *name, /* UTF-8 encoded string */
+ int no_block);
+
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_CAPSULE_H */
diff --git a/Include/pyconfig.h b/Include/pyconfig.h
new file mode 100644
index 0000000..d2a3f5d
--- /dev/null
+++ b/Include/pyconfig.h
@@ -0,0 +1,693 @@
+#ifndef Py_CONFIG_H
+#define Py_CONFIG_H
+
+/* pyconfig.h. NOT Generated automatically by configure.
+
+This is a manually maintained version used for the Watcom,
+Borland and Microsoft Visual C++ compilers. It is a
+standard part of the Python distribution.
+
+WINDOWS DEFINES:
+The code specific to Windows should be wrapped around one of
+the following #defines
+
+MS_WIN64 - Code specific to the MS Win64 API
+MS_WIN32 - Code specific to the MS Win32 (and Win64) API (obsolete, this covers all supported APIs)
+MS_WINDOWS - Code specific to Windows, but all versions.
+Py_ENABLE_SHARED - Code if the Python core is built as a DLL.
+
+Also note that neither "_M_IX86" or "_MSC_VER" should be used for
+any purpose other than "Windows Intel x86 specific" and "Microsoft
+compiler specific". Therefore, these should be very rare.
+
+
+NOTE: The following symbols are deprecated:
+NT, USE_DL_EXPORT, USE_DL_IMPORT, DL_EXPORT, DL_IMPORT
+MS_CORE_DLL.
+
+WIN32 is still required for the locale module.
+
+*/
+
+/* Deprecated USE_DL_EXPORT macro - please use Py_BUILD_CORE */
+#ifdef USE_DL_EXPORT
+# define Py_BUILD_CORE
+#endif /* USE_DL_EXPORT */
+
+/* Visual Studio 2005 introduces deprecation warnings for
+ "insecure" and POSIX functions. The insecure functions should
+ be replaced by *_s versions (according to Microsoft); the
+ POSIX functions by _* versions (which, according to Microsoft,
+ would be ISO C conforming). Neither renaming is feasible, so
+ we just silence the warnings. */
+
+#ifndef _CRT_SECURE_NO_DEPRECATE
+#define _CRT_SECURE_NO_DEPRECATE 1
+#endif
+#ifndef _CRT_NONSTDC_NO_DEPRECATE
+#define _CRT_NONSTDC_NO_DEPRECATE 1
+#endif
+
+#define HAVE_IO_H
+#define HAVE_SYS_UTIME_H
+#define HAVE_TEMPNAM
+#define HAVE_TMPFILE
+#define HAVE_TMPNAM
+#define HAVE_CLOCK
+#define HAVE_STRERROR
+
+#include
+
+#define HAVE_HYPOT
+#define HAVE_STRFTIME
+#define DONT_HAVE_SIG_ALARM
+#define DONT_HAVE_SIG_PAUSE
+#define LONG_BIT 32
+#define WORD_BIT 32
+
+#define MS_WIN32 /* only support win32 and greater. */
+#define MS_WINDOWS
+#ifndef PYTHONPATH
+# define PYTHONPATH L".\\DLLs;.\\lib"
+#endif
+#define NT_THREADS
+#define WITH_THREAD
+#ifndef NETSCAPE_PI
+#define USE_SOCKET
+#endif
+
+
+/* Compiler specific defines */
+
+/* ------------------------------------------------------------------------*/
+/* Microsoft C defines _MSC_VER */
+#ifdef _MSC_VER
+
+/* We want COMPILER to expand to a string containing _MSC_VER's *value*.
+ * This is horridly tricky, because the stringization operator only works
+ * on macro arguments, and doesn't evaluate macros passed *as* arguments.
+ * Attempts simpler than the following appear doomed to produce "_MSC_VER"
+ * literally in the string.
+ */
+#define _Py_PASTE_VERSION(SUFFIX) \
+ ("[MSC v." _Py_STRINGIZE(_MSC_VER) " " SUFFIX "]")
+/* e.g., this produces, after compile-time string catenation,
+ * ("[MSC v.1200 32 bit (Intel)]")
+ *
+ * _Py_STRINGIZE(_MSC_VER) expands to
+ * _Py_STRINGIZE1((_MSC_VER)) expands to
+ * _Py_STRINGIZE2(_MSC_VER) but as this call is the result of token-pasting
+ * it's scanned again for macros and so further expands to (under MSVC 6)
+ * _Py_STRINGIZE2(1200) which then expands to
+ * "1200"
+ */
+#define _Py_STRINGIZE(X) _Py_STRINGIZE1((X))
+#define _Py_STRINGIZE1(X) _Py_STRINGIZE2 ## X
+#define _Py_STRINGIZE2(X) #X
+
+/* MSVC defines _WINxx to differentiate the windows platform types
+
+ Note that for compatibility reasons _WIN32 is defined on Win32
+ *and* on Win64. For the same reasons, in Python, MS_WIN32 is
+ defined on Win32 *and* Win64. Win32 only code must therefore be
+ guarded as follows:
+ #if defined(MS_WIN32) && !defined(MS_WIN64)
+*/
+#ifdef _WIN64
+#define MS_WIN64
+#endif
+
+/* set the COMPILER */
+#ifdef MS_WIN64
+#if defined(_M_X64) || defined(_M_AMD64)
+#if defined(__INTEL_COMPILER)
+#define COMPILER ("[ICC v." _Py_STRINGIZE(__INTEL_COMPILER) " 64 bit (amd64) with MSC v." _Py_STRINGIZE(_MSC_VER) " CRT]")
+#else
+#define COMPILER _Py_PASTE_VERSION("64 bit (AMD64)")
+#endif /* __INTEL_COMPILER */
+#define PYD_PLATFORM_TAG "win_amd64"
+#else
+#define COMPILER _Py_PASTE_VERSION("64 bit (Unknown)")
+#endif
+#endif /* MS_WIN64 */
+
+/* set the version macros for the windows headers */
+/* Python 3.5+ requires Windows Vista or greater */
+#define Py_WINVER 0x0600 /* _WIN32_WINNT_VISTA */
+#define Py_NTDDI NTDDI_VISTA
+
+/* We only set these values when building Python - we don't want to force
+ these values on extensions, as that will affect the prototypes and
+ structures exposed in the Windows headers. Even when building Python, we
+ allow a single source file to override this - they may need access to
+ structures etc so it can optionally use new Windows features if it
+ determines at runtime they are available.
+*/
+#if defined(Py_BUILD_CORE) || defined(Py_BUILD_CORE_BUILTIN) || defined(Py_BUILD_CORE_MODULE)
+#ifndef NTDDI_VERSION
+#define NTDDI_VERSION Py_NTDDI
+#endif
+#ifndef WINVER
+#define WINVER Py_WINVER
+#endif
+#ifndef _WIN32_WINNT
+#define _WIN32_WINNT Py_WINVER
+#endif
+#endif
+
+/* _W64 is not defined for VC6 or eVC4 */
+#ifndef _W64
+#define _W64
+#endif
+
+/* Define like size_t, omitting the "unsigned" */
+#ifdef MS_WIN64
+typedef __int64 ssize_t;
+#else
+typedef _W64 int ssize_t;
+#endif
+#define HAVE_SSIZE_T 1
+
+#if defined(MS_WIN32) && !defined(MS_WIN64)
+#if defined(_M_IX86)
+#if defined(__INTEL_COMPILER)
+#define COMPILER ("[ICC v." _Py_STRINGIZE(__INTEL_COMPILER) " 32 bit (Intel) with MSC v." _Py_STRINGIZE(_MSC_VER) " CRT]")
+#else
+#define COMPILER _Py_PASTE_VERSION("32 bit (Intel)")
+#endif /* __INTEL_COMPILER */
+#define PYD_PLATFORM_TAG "win32"
+#elif defined(_M_ARM)
+#define COMPILER _Py_PASTE_VERSION("32 bit (ARM)")
+#define PYD_PLATFORM_TAG "win_arm"
+#else
+#define COMPILER _Py_PASTE_VERSION("32 bit (Unknown)")
+#endif
+#endif /* MS_WIN32 && !MS_WIN64 */
+
+typedef int pid_t;
+
+#include
+#define Py_IS_NAN _isnan
+#define Py_IS_INFINITY(X) (!_finite(X) && !_isnan(X))
+#define Py_IS_FINITE(X) _finite(X)
+#define copysign _copysign
+
+/* VS 2010 and above already defines hypot as _hypot */
+#if _MSC_VER < 1600
+#define hypot _hypot
+#endif
+
+/* VS 2015 defines these names with a leading underscore */
+#if _MSC_VER >= 1900
+#define timezone _timezone
+#define daylight _daylight
+#define tzname _tzname
+#endif
+
+/* Side by Side assemblies supported in VS 2005 and VS 2008 but not 2010*/
+#if _MSC_VER >= 1400 && _MSC_VER < 1600
+#define HAVE_SXS 1
+#endif
+
+/* define some ANSI types that are not defined in earlier Win headers */
+#if _MSC_VER >= 1200
+/* This file only exists in VC 6.0 or higher */
+#include
+#endif
+
+#endif /* _MSC_VER */
+
+/* ------------------------------------------------------------------------*/
+/* egcs/gnu-win32 defines __GNUC__ and _WIN32 */
+#if defined(__GNUC__) && defined(_WIN32)
+/* XXX These defines are likely incomplete, but should be easy to fix.
+ They should be complete enough to build extension modules. */
+/* Suggested by Rene Liebscher to avoid a GCC 2.91.*
+ bug that requires structure imports. More recent versions of the
+ compiler don't exhibit this bug.
+*/
+#if (__GNUC__==2) && (__GNUC_MINOR__<=91)
+#warning "Please use an up-to-date version of gcc! (>2.91 recommended)"
+#endif
+
+#define COMPILER "[gcc]"
+#define hypot _hypot
+#define PY_LONG_LONG long long
+#define PY_LLONG_MIN LLONG_MIN
+#define PY_LLONG_MAX LLONG_MAX
+#define PY_ULLONG_MAX ULLONG_MAX
+#endif /* GNUC */
+
+/* ------------------------------------------------------------------------*/
+/* lcc-win32 defines __LCC__ */
+#if defined(__LCC__)
+/* XXX These defines are likely incomplete, but should be easy to fix.
+ They should be complete enough to build extension modules. */
+
+#define COMPILER "[lcc-win32]"
+typedef int pid_t;
+/* __declspec() is supported here too - do nothing to get the defaults */
+
+#endif /* LCC */
+
+/* ------------------------------------------------------------------------*/
+/* End of compilers - finish up */
+
+#ifndef NO_STDIO_H
+# include
+#endif
+
+/* 64 bit ints are usually spelt __int64 unless compiler has overridden */
+#ifndef PY_LONG_LONG
+# define PY_LONG_LONG __int64
+# define PY_LLONG_MAX _I64_MAX
+# define PY_LLONG_MIN _I64_MIN
+# define PY_ULLONG_MAX _UI64_MAX
+#endif
+
+/* For Windows the Python core is in a DLL by default. Test
+Py_NO_ENABLE_SHARED to find out. Also support MS_NO_COREDLL for b/w compat */
+#if !defined(MS_NO_COREDLL) && !defined(Py_NO_ENABLE_SHARED)
+# define Py_ENABLE_SHARED 1 /* standard symbol for shared library */
+# define MS_COREDLL /* deprecated old symbol */
+#endif /* !MS_NO_COREDLL && ... */
+
+/* All windows compilers that use this header support __declspec */
+#define HAVE_DECLSPEC_DLL
+
+/* For an MSVC DLL, we can nominate the .lib files used by extensions */
+#ifdef MS_COREDLL
+# if !defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_BUILTIN)
+ /* not building the core - must be an ext */
+# if defined(_MSC_VER)
+ /* So MSVC users need not specify the .lib
+ file in their Makefile (other compilers are
+ generally taken care of by distutils.) */
+# if defined(_DEBUG)
+# pragma comment(lib,"python37_d.lib")
+# elif defined(Py_LIMITED_API)
+# pragma comment(lib,"python3.lib")
+# else
+# pragma comment(lib,"python37.lib")
+# endif /* _DEBUG */
+# endif /* _MSC_VER */
+# endif /* Py_BUILD_CORE */
+#endif /* MS_COREDLL */
+
+#if defined(MS_WIN64)
+/* maintain "win32" sys.platform for backward compatibility of Python code,
+ the Win64 API should be close enough to the Win32 API to make this
+ preferable */
+# define PLATFORM "win32"
+# define SIZEOF_VOID_P 8
+# define SIZEOF_TIME_T 8
+# define SIZEOF_OFF_T 4
+# define SIZEOF_FPOS_T 8
+# define SIZEOF_HKEY 8
+# define SIZEOF_SIZE_T 8
+/* configure.ac defines HAVE_LARGEFILE_SUPPORT iff HAVE_LONG_LONG,
+ sizeof(off_t) > sizeof(long), and sizeof(PY_LONG_LONG) >= sizeof(off_t).
+ On Win64 the second condition is not true, but if fpos_t replaces off_t
+ then this is true. The uses of HAVE_LARGEFILE_SUPPORT imply that Win64
+ should define this. */
+# define HAVE_LARGEFILE_SUPPORT
+#elif defined(MS_WIN32)
+# define PLATFORM "win32"
+# define HAVE_LARGEFILE_SUPPORT
+# define SIZEOF_VOID_P 4
+# define SIZEOF_OFF_T 4
+# define SIZEOF_FPOS_T 8
+# define SIZEOF_HKEY 4
+# define SIZEOF_SIZE_T 4
+ /* MS VS2005 changes time_t to a 64-bit type on all platforms */
+# if defined(_MSC_VER) && _MSC_VER >= 1400
+# define SIZEOF_TIME_T 8
+# else
+# define SIZEOF_TIME_T 4
+# endif
+#endif
+
+#ifdef _DEBUG
+# define Py_DEBUG
+#endif
+
+
+#ifdef MS_WIN32
+
+#define SIZEOF_SHORT 2
+#define SIZEOF_INT 4
+#define SIZEOF_LONG 4
+#define SIZEOF_LONG_LONG 8
+#define SIZEOF_DOUBLE 8
+#define SIZEOF_FLOAT 4
+
+/* VC 7.1 has them and VC 6.0 does not. VC 6.0 has a version number of 1200.
+ Microsoft eMbedded Visual C++ 4.0 has a version number of 1201 and doesn't
+ define these.
+ If some compiler does not provide them, modify the #if appropriately. */
+#if defined(_MSC_VER)
+#if _MSC_VER > 1300
+#define HAVE_UINTPTR_T 1
+#define HAVE_INTPTR_T 1
+#else
+/* VC6, VS 2002 and eVC4 don't support the C99 LL suffix for 64-bit integer literals */
+#define Py_LL(x) x##I64
+#endif /* _MSC_VER > 1300 */
+#endif /* _MSC_VER */
+
+#endif
+
+/* define signed and unsigned exact-width 32-bit and 64-bit types, used in the
+ implementation of Python integers. */
+#define PY_UINT32_T uint32_t
+#define PY_UINT64_T uint64_t
+#define PY_INT32_T int32_t
+#define PY_INT64_T int64_t
+
+/* Fairly standard from here! */
+
+/* Define to 1 if you have the `copysign' function. */
+#define HAVE_COPYSIGN 1
+
+/* Define to 1 if you have the `round' function. */
+#if _MSC_VER >= 1800
+#define HAVE_ROUND 1
+#endif
+
+/* Define to 1 if you have the `isinf' macro. */
+#define HAVE_DECL_ISINF 1
+
+/* Define to 1 if you have the `isnan' function. */
+#define HAVE_DECL_ISNAN 1
+
+/* Define if on AIX 3.
+ System headers sometimes define this.
+ We just want to avoid a redefinition error message. */
+#ifndef _ALL_SOURCE
+/* #undef _ALL_SOURCE */
+#endif
+
+/* Define to empty if the keyword does not work. */
+/* #define const */
+
+/* Define to 1 if you have the header file. */
+#define HAVE_CONIO_H 1
+
+/* Define to 1 if you have the header file. */
+#define HAVE_DIRECT_H 1
+
+/* Define if you have dirent.h. */
+/* #define DIRENT 1 */
+
+/* Define to the type of elements in the array set by `getgroups'.
+ Usually this is either `int' or `gid_t'. */
+/* #undef GETGROUPS_T */
+
+/* Define to `int' if doesn't define. */
+/* #undef gid_t */
+
+/* Define if your struct tm has tm_zone. */
+/* #undef HAVE_TM_ZONE */
+
+/* Define if you don't have tm_zone but do have the external array
+ tzname. */
+#define HAVE_TZNAME
+
+/* Define to `int' if doesn't define. */
+/* #undef mode_t */
+
+/* Define if you don't have dirent.h, but have ndir.h. */
+/* #undef NDIR */
+
+/* Define to `long' if doesn't define. */
+/* #undef off_t */
+
+/* Define to `int' if doesn't define. */
+/* #undef pid_t */
+
+/* Define if the system does not provide POSIX.1 features except
+ with this defined. */
+/* #undef _POSIX_1_SOURCE */
+
+/* Define if you need to in order for stat and other things to work. */
+/* #undef _POSIX_SOURCE */
+
+/* Define as the return type of signal handlers (int or void). */
+#define RETSIGTYPE void
+
+/* Define to `unsigned' if doesn't define. */
+/* #undef size_t */
+
+/* Define if you have the ANSI C header files. */
+#define STDC_HEADERS 1
+
+/* Define if you don't have dirent.h, but have sys/dir.h. */
+/* #undef SYSDIR */
+
+/* Define if you don't have dirent.h, but have sys/ndir.h. */
+/* #undef SYSNDIR */
+
+/* Define if you can safely include both and . */
+/* #undef TIME_WITH_SYS_TIME */
+
+/* Define if your declares struct tm. */
+/* #define TM_IN_SYS_TIME 1 */
+
+/* Define to `int' if doesn't define. */
+/* #undef uid_t */
+
+/* Define if the closedir function returns void instead of int. */
+/* #undef VOID_CLOSEDIR */
+
+/* Define if getpgrp() must be called as getpgrp(0)
+ and (consequently) setpgrp() as setpgrp(0, 0). */
+/* #undef GETPGRP_HAVE_ARGS */
+
+/* Define this if your time.h defines altzone */
+/* #define HAVE_ALTZONE */
+
+/* Define if you have the putenv function. */
+#define HAVE_PUTENV
+
+/* Define if your compiler supports function prototypes */
+#define HAVE_PROTOTYPES
+
+/* Define if you can safely include both and
+ (which you can't on SCO ODT 3.0). */
+/* #undef SYS_SELECT_WITH_SYS_TIME */
+
+/* Define if you want documentation strings in extension modules */
+#define WITH_DOC_STRINGS 1
+
+/* Define if you want to compile in rudimentary thread support */
+/* #undef WITH_THREAD */
+
+/* Define if you want to use the GNU readline library */
+/* #define WITH_READLINE 1 */
+
+/* Use Python's own small-block memory-allocator. */
+#define WITH_PYMALLOC 1
+
+/* Define if you have clock. */
+/* #define HAVE_CLOCK */
+
+/* Define when any dynamic module loading is enabled */
+#define HAVE_DYNAMIC_LOADING
+
+/* Define if you have ftime. */
+#define HAVE_FTIME
+
+/* Define if you have getpeername. */
+#define HAVE_GETPEERNAME
+
+/* Define if you have getpgrp. */
+/* #undef HAVE_GETPGRP */
+
+/* Define if you have getpid. */
+#define HAVE_GETPID
+
+/* Define if you have gettimeofday. */
+/* #undef HAVE_GETTIMEOFDAY */
+
+/* Define if you have getwd. */
+/* #undef HAVE_GETWD */
+
+/* Define if you have lstat. */
+/* #undef HAVE_LSTAT */
+
+/* Define if you have the mktime function. */
+#define HAVE_MKTIME
+
+/* Define if you have nice. */
+/* #undef HAVE_NICE */
+
+/* Define if you have readlink. */
+/* #undef HAVE_READLINK */
+
+/* Define if you have setpgid. */
+/* #undef HAVE_SETPGID */
+
+/* Define if you have setpgrp. */
+/* #undef HAVE_SETPGRP */
+
+/* Define if you have setsid. */
+/* #undef HAVE_SETSID */
+
+/* Define if you have setvbuf. */
+#define HAVE_SETVBUF
+
+/* Define if you have siginterrupt. */
+/* #undef HAVE_SIGINTERRUPT */
+
+/* Define if you have symlink. */
+/* #undef HAVE_SYMLINK */
+
+/* Define if you have tcgetpgrp. */
+/* #undef HAVE_TCGETPGRP */
+
+/* Define if you have tcsetpgrp. */
+/* #undef HAVE_TCSETPGRP */
+
+/* Define if you have times. */
+/* #undef HAVE_TIMES */
+
+/* Define if you have uname. */
+/* #undef HAVE_UNAME */
+
+/* Define if you have waitpid. */
+/* #undef HAVE_WAITPID */
+
+/* Define to 1 if you have the `wcsftime' function. */
+#if defined(_MSC_VER) && _MSC_VER >= 1310
+#define HAVE_WCSFTIME 1
+#endif
+
+/* Define to 1 if you have the `wcscoll' function. */
+#define HAVE_WCSCOLL 1
+
+/* Define to 1 if you have the `wcsxfrm' function. */
+#define HAVE_WCSXFRM 1
+
+/* Define if the zlib library has inflateCopy */
+#define HAVE_ZLIB_COPY 1
+
+/* Define if you have the header file. */
+/* #undef HAVE_DLFCN_H */
+
+/* Define to 1 if you have the header file. */
+#define HAVE_ERRNO_H 1
+
+/* Define if you have the header file. */
+#define HAVE_FCNTL_H 1
+
+/* Define to 1 if you have the header file. */
+#define HAVE_PROCESS_H 1
+
+/* Define to 1 if you have the header file. */
+#define HAVE_SIGNAL_H 1
+
+/* Define if you have the prototypes. */
+#define HAVE_STDARG_PROTOTYPES
+
+/* Define if you have the header file. */
+#define HAVE_STDDEF_H 1
+
+/* Define if you have the header file. */
+/* #undef HAVE_SYS_AUDIOIO_H */
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_PARAM_H 1 */
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_SELECT_H 1 */
+
+/* Define to 1 if you have the header file. */
+#define HAVE_SYS_STAT_H 1
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_TIME_H 1 */
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_TIMES_H 1 */
+
+/* Define to 1 if you have the header file. */
+#define HAVE_SYS_TYPES_H 1
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_UN_H 1 */
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_UTIME_H 1 */
+
+/* Define if you have the header file. */
+/* #define HAVE_SYS_UTSNAME_H 1 */
+
+/* Define if you have the header file. */
+/* #define HAVE_UNISTD_H 1 */
+
+/* Define if you have the header file. */
+/* #define HAVE_UTIME_H 1 */
+
+/* Define if the compiler provides a wchar.h header file. */
+#define HAVE_WCHAR_H 1
+
+/* The size of `wchar_t', as computed by sizeof. */
+#define SIZEOF_WCHAR_T 2
+
+/* The size of `_Bool', as computed by sizeof. */
+#define SIZEOF__BOOL 1
+
+/* The size of `pid_t', as computed by sizeof. */
+#define SIZEOF_PID_T SIZEOF_INT
+
+/* Define if you have the dl library (-ldl). */
+/* #undef HAVE_LIBDL */
+
+/* Define if you have the mpc library (-lmpc). */
+/* #undef HAVE_LIBMPC */
+
+/* Define if you have the nsl library (-lnsl). */
+#define HAVE_LIBNSL 1
+
+/* Define if you have the seq library (-lseq). */
+/* #undef HAVE_LIBSEQ */
+
+/* Define if you have the socket library (-lsocket). */
+#define HAVE_LIBSOCKET 1
+
+/* Define if you have the sun library (-lsun). */
+/* #undef HAVE_LIBSUN */
+
+/* Define if you have the termcap library (-ltermcap). */
+/* #undef HAVE_LIBTERMCAP */
+
+/* Define if you have the termlib library (-ltermlib). */
+/* #undef HAVE_LIBTERMLIB */
+
+/* Define if you have the thread library (-lthread). */
+/* #undef HAVE_LIBTHREAD */
+
+/* WinSock does not use a bitmask in select, and uses
+ socket handles greater than FD_SETSIZE */
+#define Py_SOCKET_FD_CAN_BE_GE_FD_SETSIZE
+
+/* Define if C doubles are 64-bit IEEE 754 binary format, stored with the
+ least significant byte first */
+#define DOUBLE_IS_LITTLE_ENDIAN_IEEE754 1
+
+/* Define to 1 if you have the `erf' function. */
+#define HAVE_ERF 1
+
+/* Define to 1 if you have the `erfc' function. */
+#define HAVE_ERFC 1
+
+/* Define if you have the 'inet_pton' function. */
+#define HAVE_INET_PTON 1
+
+/* framework name */
+#define _PYTHONFRAMEWORK ""
+
+/* Define if libssl has X509_VERIFY_PARAM_set1_host and related function */
+#define HAVE_X509_VERIFY_PARAM_SET1_HOST 1
+
+#endif /* !Py_CONFIG_H */
diff --git a/Include/pyctype.h b/Include/pyctype.h
new file mode 100644
index 0000000..6bce63e
--- /dev/null
+++ b/Include/pyctype.h
@@ -0,0 +1,33 @@
+#ifndef Py_LIMITED_API
+#ifndef PYCTYPE_H
+#define PYCTYPE_H
+
+#define PY_CTF_LOWER 0x01
+#define PY_CTF_UPPER 0x02
+#define PY_CTF_ALPHA (PY_CTF_LOWER|PY_CTF_UPPER)
+#define PY_CTF_DIGIT 0x04
+#define PY_CTF_ALNUM (PY_CTF_ALPHA|PY_CTF_DIGIT)
+#define PY_CTF_SPACE 0x08
+#define PY_CTF_XDIGIT 0x10
+
+PyAPI_DATA(const unsigned int) _Py_ctype_table[256];
+
+/* Unlike their C counterparts, the following macros are not meant to
+ * handle an int with any of the values [EOF, 0-UCHAR_MAX]. The argument
+ * must be a signed/unsigned char. */
+#define Py_ISLOWER(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_LOWER)
+#define Py_ISUPPER(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_UPPER)
+#define Py_ISALPHA(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_ALPHA)
+#define Py_ISDIGIT(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_DIGIT)
+#define Py_ISXDIGIT(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_XDIGIT)
+#define Py_ISALNUM(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_ALNUM)
+#define Py_ISSPACE(c) (_Py_ctype_table[Py_CHARMASK(c)] & PY_CTF_SPACE)
+
+PyAPI_DATA(const unsigned char) _Py_ctype_tolower[256];
+PyAPI_DATA(const unsigned char) _Py_ctype_toupper[256];
+
+#define Py_TOLOWER(c) (_Py_ctype_tolower[Py_CHARMASK(c)])
+#define Py_TOUPPER(c) (_Py_ctype_toupper[Py_CHARMASK(c)])
+
+#endif /* !PYCTYPE_H */
+#endif /* !Py_LIMITED_API */
diff --git a/Include/pydebug.h b/Include/pydebug.h
new file mode 100644
index 0000000..bd4aafe
--- /dev/null
+++ b/Include/pydebug.h
@@ -0,0 +1,40 @@
+#ifndef Py_LIMITED_API
+#ifndef Py_PYDEBUG_H
+#define Py_PYDEBUG_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* These global variable are defined in pylifecycle.c */
+/* XXX (ncoghlan): move these declarations to pylifecycle.h? */
+PyAPI_DATA(int) Py_DebugFlag;
+PyAPI_DATA(int) Py_VerboseFlag;
+PyAPI_DATA(int) Py_QuietFlag;
+PyAPI_DATA(int) Py_InteractiveFlag;
+PyAPI_DATA(int) Py_InspectFlag;
+PyAPI_DATA(int) Py_OptimizeFlag;
+PyAPI_DATA(int) Py_NoSiteFlag;
+PyAPI_DATA(int) Py_BytesWarningFlag;
+PyAPI_DATA(int) Py_FrozenFlag;
+PyAPI_DATA(int) Py_IgnoreEnvironmentFlag;
+PyAPI_DATA(int) Py_DontWriteBytecodeFlag;
+PyAPI_DATA(int) Py_NoUserSiteDirectory;
+PyAPI_DATA(int) Py_UnbufferedStdioFlag;
+PyAPI_DATA(int) Py_HashRandomizationFlag;
+PyAPI_DATA(int) Py_IsolatedFlag;
+
+#ifdef MS_WINDOWS
+PyAPI_DATA(int) Py_LegacyWindowsFSEncodingFlag;
+PyAPI_DATA(int) Py_LegacyWindowsStdioFlag;
+#endif
+
+/* this is a wrapper around getenv() that pays attention to
+ Py_IgnoreEnvironmentFlag. It should be used for getting variables like
+ PYTHONPATH and PYTHONHOME from the environment */
+#define Py_GETENV(s) (Py_IgnoreEnvironmentFlag ? NULL : getenv(s))
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PYDEBUG_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/pydtrace.h b/Include/pydtrace.h
new file mode 100644
index 0000000..037961d
--- /dev/null
+++ b/Include/pydtrace.h
@@ -0,0 +1,57 @@
+/* Static DTrace probes interface */
+
+#ifndef Py_DTRACE_H
+#define Py_DTRACE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifdef WITH_DTRACE
+
+#include "pydtrace_probes.h"
+
+/* pydtrace_probes.h, on systems with DTrace, is auto-generated to include
+ `PyDTrace_{PROBE}` and `PyDTrace_{PROBE}_ENABLED()` macros for every probe
+ defined in pydtrace_provider.d.
+
+ Calling these functions must be guarded by a `PyDTrace_{PROBE}_ENABLED()`
+ check to minimize performance impact when probing is off. For example:
+
+ if (PyDTrace_FUNCTION_ENTRY_ENABLED())
+ PyDTrace_FUNCTION_ENTRY(f);
+*/
+
+#else
+
+/* Without DTrace, compile to nothing. */
+
+static inline void PyDTrace_LINE(const char *arg0, const char *arg1, int arg2) {}
+static inline void PyDTrace_FUNCTION_ENTRY(const char *arg0, const char *arg1, int arg2) {}
+static inline void PyDTrace_FUNCTION_RETURN(const char *arg0, const char *arg1, int arg2) {}
+static inline void PyDTrace_GC_START(int arg0) {}
+static inline void PyDTrace_GC_DONE(int arg0) {}
+static inline void PyDTrace_INSTANCE_NEW_START(int arg0) {}
+static inline void PyDTrace_INSTANCE_NEW_DONE(int arg0) {}
+static inline void PyDTrace_INSTANCE_DELETE_START(int arg0) {}
+static inline void PyDTrace_INSTANCE_DELETE_DONE(int arg0) {}
+static inline void PyDTrace_IMPORT_FIND_LOAD_START(const char *arg0) {}
+static inline void PyDTrace_IMPORT_FIND_LOAD_DONE(const char *arg0, int arg1) {}
+
+static inline int PyDTrace_LINE_ENABLED(void) { return 0; }
+static inline int PyDTrace_FUNCTION_ENTRY_ENABLED(void) { return 0; }
+static inline int PyDTrace_FUNCTION_RETURN_ENABLED(void) { return 0; }
+static inline int PyDTrace_GC_START_ENABLED(void) { return 0; }
+static inline int PyDTrace_GC_DONE_ENABLED(void) { return 0; }
+static inline int PyDTrace_INSTANCE_NEW_START_ENABLED(void) { return 0; }
+static inline int PyDTrace_INSTANCE_NEW_DONE_ENABLED(void) { return 0; }
+static inline int PyDTrace_INSTANCE_DELETE_START_ENABLED(void) { return 0; }
+static inline int PyDTrace_INSTANCE_DELETE_DONE_ENABLED(void) { return 0; }
+static inline int PyDTrace_IMPORT_FIND_LOAD_START_ENABLED(void) { return 0; }
+static inline int PyDTrace_IMPORT_FIND_LOAD_DONE_ENABLED(void) { return 0; }
+
+#endif /* !WITH_DTRACE */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_DTRACE_H */
diff --git a/Include/pyerrors.h b/Include/pyerrors.h
new file mode 100644
index 0000000..f289471
--- /dev/null
+++ b/Include/pyerrors.h
@@ -0,0 +1,504 @@
+#ifndef Py_ERRORS_H
+#define Py_ERRORS_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Error objects */
+
+#ifndef Py_LIMITED_API
+/* PyException_HEAD defines the initial segment of every exception class. */
+#define PyException_HEAD PyObject_HEAD PyObject *dict;\
+ PyObject *args; PyObject *traceback;\
+ PyObject *context; PyObject *cause;\
+ char suppress_context;
+
+typedef struct {
+ PyException_HEAD
+} PyBaseExceptionObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *msg;
+ PyObject *filename;
+ PyObject *lineno;
+ PyObject *offset;
+ PyObject *text;
+ PyObject *print_file_and_line;
+} PySyntaxErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *msg;
+ PyObject *name;
+ PyObject *path;
+} PyImportErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *encoding;
+ PyObject *object;
+ Py_ssize_t start;
+ Py_ssize_t end;
+ PyObject *reason;
+} PyUnicodeErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *code;
+} PySystemExitObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *myerrno;
+ PyObject *strerror;
+ PyObject *filename;
+ PyObject *filename2;
+#ifdef MS_WINDOWS
+ PyObject *winerror;
+#endif
+ Py_ssize_t written; /* only for BlockingIOError, -1 otherwise */
+} PyOSErrorObject;
+
+typedef struct {
+ PyException_HEAD
+ PyObject *value;
+} PyStopIterationObject;
+
+/* Compatibility typedefs */
+typedef PyOSErrorObject PyEnvironmentErrorObject;
+#ifdef MS_WINDOWS
+typedef PyOSErrorObject PyWindowsErrorObject;
+#endif
+#endif /* !Py_LIMITED_API */
+
+/* Error handling definitions */
+
+PyAPI_FUNC(void) PyErr_SetNone(PyObject *);
+PyAPI_FUNC(void) PyErr_SetObject(PyObject *, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyErr_SetKeyError(PyObject *);
+_PyErr_StackItem *_PyErr_GetTopmostException(PyThreadState *tstate);
+#endif
+PyAPI_FUNC(void) PyErr_SetString(
+ PyObject *exception,
+ const char *string /* decoded from utf-8 */
+ );
+PyAPI_FUNC(PyObject *) PyErr_Occurred(void);
+PyAPI_FUNC(void) PyErr_Clear(void);
+PyAPI_FUNC(void) PyErr_Fetch(PyObject **, PyObject **, PyObject **);
+PyAPI_FUNC(void) PyErr_Restore(PyObject *, PyObject *, PyObject *);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(void) PyErr_GetExcInfo(PyObject **, PyObject **, PyObject **);
+PyAPI_FUNC(void) PyErr_SetExcInfo(PyObject *, PyObject *, PyObject *);
+#endif
+
+#if defined(__clang__) || \
+ (defined(__GNUC_MAJOR__) && \
+ ((__GNUC_MAJOR__ >= 3) || \
+ (__GNUC_MAJOR__ == 2) && (__GNUC_MINOR__ >= 5)))
+#define _Py_NO_RETURN __attribute__((__noreturn__))
+#else
+#define _Py_NO_RETURN
+#endif
+
+/* Defined in Python/pylifecycle.c */
+PyAPI_FUNC(void) Py_FatalError(const char *message) _Py_NO_RETURN;
+
+#if defined(Py_DEBUG) || defined(Py_LIMITED_API)
+#define _PyErr_OCCURRED() PyErr_Occurred()
+#else
+#define _PyErr_OCCURRED() (PyThreadState_GET()->curexc_type)
+#endif
+
+/* Error testing and normalization */
+PyAPI_FUNC(int) PyErr_GivenExceptionMatches(PyObject *, PyObject *);
+PyAPI_FUNC(int) PyErr_ExceptionMatches(PyObject *);
+PyAPI_FUNC(void) PyErr_NormalizeException(PyObject**, PyObject**, PyObject**);
+
+/* Traceback manipulation (PEP 3134) */
+PyAPI_FUNC(int) PyException_SetTraceback(PyObject *, PyObject *);
+PyAPI_FUNC(PyObject *) PyException_GetTraceback(PyObject *);
+
+/* Cause manipulation (PEP 3134) */
+PyAPI_FUNC(PyObject *) PyException_GetCause(PyObject *);
+PyAPI_FUNC(void) PyException_SetCause(PyObject *, PyObject *);
+
+/* Context manipulation (PEP 3134) */
+PyAPI_FUNC(PyObject *) PyException_GetContext(PyObject *);
+PyAPI_FUNC(void) PyException_SetContext(PyObject *, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyErr_ChainExceptions(PyObject *, PyObject *, PyObject *);
+#endif
+
+/* */
+
+#define PyExceptionClass_Check(x) \
+ (PyType_Check((x)) && \
+ PyType_FastSubclass((PyTypeObject*)(x), Py_TPFLAGS_BASE_EXC_SUBCLASS))
+
+#define PyExceptionInstance_Check(x) \
+ PyType_FastSubclass((x)->ob_type, Py_TPFLAGS_BASE_EXC_SUBCLASS)
+
+#define PyExceptionClass_Name(x) \
+ ((char *)(((PyTypeObject*)(x))->tp_name))
+
+#define PyExceptionInstance_Class(x) ((PyObject*)((x)->ob_type))
+
+
+/* Predefined exceptions */
+
+PyAPI_DATA(PyObject *) PyExc_BaseException;
+PyAPI_DATA(PyObject *) PyExc_Exception;
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_DATA(PyObject *) PyExc_StopAsyncIteration;
+#endif
+PyAPI_DATA(PyObject *) PyExc_StopIteration;
+PyAPI_DATA(PyObject *) PyExc_GeneratorExit;
+PyAPI_DATA(PyObject *) PyExc_ArithmeticError;
+PyAPI_DATA(PyObject *) PyExc_LookupError;
+
+PyAPI_DATA(PyObject *) PyExc_AssertionError;
+PyAPI_DATA(PyObject *) PyExc_AttributeError;
+PyAPI_DATA(PyObject *) PyExc_BufferError;
+PyAPI_DATA(PyObject *) PyExc_EOFError;
+PyAPI_DATA(PyObject *) PyExc_FloatingPointError;
+PyAPI_DATA(PyObject *) PyExc_OSError;
+PyAPI_DATA(PyObject *) PyExc_ImportError;
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03060000
+PyAPI_DATA(PyObject *) PyExc_ModuleNotFoundError;
+#endif
+PyAPI_DATA(PyObject *) PyExc_IndexError;
+PyAPI_DATA(PyObject *) PyExc_KeyError;
+PyAPI_DATA(PyObject *) PyExc_KeyboardInterrupt;
+PyAPI_DATA(PyObject *) PyExc_MemoryError;
+PyAPI_DATA(PyObject *) PyExc_NameError;
+PyAPI_DATA(PyObject *) PyExc_OverflowError;
+PyAPI_DATA(PyObject *) PyExc_RuntimeError;
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_DATA(PyObject *) PyExc_RecursionError;
+#endif
+PyAPI_DATA(PyObject *) PyExc_NotImplementedError;
+PyAPI_DATA(PyObject *) PyExc_SyntaxError;
+PyAPI_DATA(PyObject *) PyExc_IndentationError;
+PyAPI_DATA(PyObject *) PyExc_TabError;
+PyAPI_DATA(PyObject *) PyExc_ReferenceError;
+PyAPI_DATA(PyObject *) PyExc_SystemError;
+PyAPI_DATA(PyObject *) PyExc_SystemExit;
+PyAPI_DATA(PyObject *) PyExc_TypeError;
+PyAPI_DATA(PyObject *) PyExc_UnboundLocalError;
+PyAPI_DATA(PyObject *) PyExc_UnicodeError;
+PyAPI_DATA(PyObject *) PyExc_UnicodeEncodeError;
+PyAPI_DATA(PyObject *) PyExc_UnicodeDecodeError;
+PyAPI_DATA(PyObject *) PyExc_UnicodeTranslateError;
+PyAPI_DATA(PyObject *) PyExc_ValueError;
+PyAPI_DATA(PyObject *) PyExc_ZeroDivisionError;
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_DATA(PyObject *) PyExc_BlockingIOError;
+PyAPI_DATA(PyObject *) PyExc_BrokenPipeError;
+PyAPI_DATA(PyObject *) PyExc_ChildProcessError;
+PyAPI_DATA(PyObject *) PyExc_ConnectionError;
+PyAPI_DATA(PyObject *) PyExc_ConnectionAbortedError;
+PyAPI_DATA(PyObject *) PyExc_ConnectionRefusedError;
+PyAPI_DATA(PyObject *) PyExc_ConnectionResetError;
+PyAPI_DATA(PyObject *) PyExc_FileExistsError;
+PyAPI_DATA(PyObject *) PyExc_FileNotFoundError;
+PyAPI_DATA(PyObject *) PyExc_InterruptedError;
+PyAPI_DATA(PyObject *) PyExc_IsADirectoryError;
+PyAPI_DATA(PyObject *) PyExc_NotADirectoryError;
+PyAPI_DATA(PyObject *) PyExc_PermissionError;
+PyAPI_DATA(PyObject *) PyExc_ProcessLookupError;
+PyAPI_DATA(PyObject *) PyExc_TimeoutError;
+#endif
+
+
+/* Compatibility aliases */
+PyAPI_DATA(PyObject *) PyExc_EnvironmentError;
+PyAPI_DATA(PyObject *) PyExc_IOError;
+#ifdef MS_WINDOWS
+PyAPI_DATA(PyObject *) PyExc_WindowsError;
+#endif
+
+/* Predefined warning categories */
+PyAPI_DATA(PyObject *) PyExc_Warning;
+PyAPI_DATA(PyObject *) PyExc_UserWarning;
+PyAPI_DATA(PyObject *) PyExc_DeprecationWarning;
+PyAPI_DATA(PyObject *) PyExc_PendingDeprecationWarning;
+PyAPI_DATA(PyObject *) PyExc_SyntaxWarning;
+PyAPI_DATA(PyObject *) PyExc_RuntimeWarning;
+PyAPI_DATA(PyObject *) PyExc_FutureWarning;
+PyAPI_DATA(PyObject *) PyExc_ImportWarning;
+PyAPI_DATA(PyObject *) PyExc_UnicodeWarning;
+PyAPI_DATA(PyObject *) PyExc_BytesWarning;
+PyAPI_DATA(PyObject *) PyExc_ResourceWarning;
+
+
+/* Convenience functions */
+
+PyAPI_FUNC(int) PyErr_BadArgument(void);
+PyAPI_FUNC(PyObject *) PyErr_NoMemory(void);
+PyAPI_FUNC(PyObject *) PyErr_SetFromErrno(PyObject *);
+PyAPI_FUNC(PyObject *) PyErr_SetFromErrnoWithFilenameObject(
+ PyObject *, PyObject *);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03040000
+PyAPI_FUNC(PyObject *) PyErr_SetFromErrnoWithFilenameObjects(
+ PyObject *, PyObject *, PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyErr_SetFromErrnoWithFilename(
+ PyObject *exc,
+ const char *filename /* decoded from the filesystem encoding */
+ );
+#if defined(MS_WINDOWS) && !defined(Py_LIMITED_API)
+PyAPI_FUNC(PyObject *) PyErr_SetFromErrnoWithUnicodeFilename(
+ PyObject *, const Py_UNICODE *) Py_DEPRECATED(3.3);
+#endif /* MS_WINDOWS */
+
+PyAPI_FUNC(PyObject *) PyErr_Format(
+ PyObject *exception,
+ const char *format, /* ASCII-encoded string */
+ ...
+ );
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_FUNC(PyObject *) PyErr_FormatV(
+ PyObject *exception,
+ const char *format,
+ va_list vargs);
+#endif
+
+#ifndef Py_LIMITED_API
+/* Like PyErr_Format(), but saves current exception as __context__ and
+ __cause__.
+ */
+PyAPI_FUNC(PyObject *) _PyErr_FormatFromCause(
+ PyObject *exception,
+ const char *format, /* ASCII-encoded string */
+ ...
+ );
+#endif
+
+#ifdef MS_WINDOWS
+PyAPI_FUNC(PyObject *) PyErr_SetFromWindowsErrWithFilename(
+ int ierr,
+ const char *filename /* decoded from the filesystem encoding */
+ );
+#ifndef Py_LIMITED_API
+/* XXX redeclare to use WSTRING */
+PyAPI_FUNC(PyObject *) PyErr_SetFromWindowsErrWithUnicodeFilename(
+ int, const Py_UNICODE *) Py_DEPRECATED(3.3);
+#endif
+PyAPI_FUNC(PyObject *) PyErr_SetFromWindowsErr(int);
+PyAPI_FUNC(PyObject *) PyErr_SetExcFromWindowsErrWithFilenameObject(
+ PyObject *,int, PyObject *);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03040000
+PyAPI_FUNC(PyObject *) PyErr_SetExcFromWindowsErrWithFilenameObjects(
+ PyObject *,int, PyObject *, PyObject *);
+#endif
+PyAPI_FUNC(PyObject *) PyErr_SetExcFromWindowsErrWithFilename(
+ PyObject *exc,
+ int ierr,
+ const char *filename /* decoded from the filesystem encoding */
+ );
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyErr_SetExcFromWindowsErrWithUnicodeFilename(
+ PyObject *,int, const Py_UNICODE *) Py_DEPRECATED(3.3);
+#endif
+PyAPI_FUNC(PyObject *) PyErr_SetExcFromWindowsErr(PyObject *, int);
+#endif /* MS_WINDOWS */
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03060000
+PyAPI_FUNC(PyObject *) PyErr_SetImportErrorSubclass(PyObject *, PyObject *,
+ PyObject *, PyObject *);
+#endif
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject *) PyErr_SetImportError(PyObject *, PyObject *,
+ PyObject *);
+#endif
+
+/* Export the old function so that the existing API remains available: */
+PyAPI_FUNC(void) PyErr_BadInternalCall(void);
+PyAPI_FUNC(void) _PyErr_BadInternalCall(const char *filename, int lineno);
+/* Mask the old API with a call to the new API for code compiled under
+ Python 2.0: */
+#define PyErr_BadInternalCall() _PyErr_BadInternalCall(__FILE__, __LINE__)
+
+/* Function to create a new exception */
+PyAPI_FUNC(PyObject *) PyErr_NewException(
+ const char *name, PyObject *base, PyObject *dict);
+PyAPI_FUNC(PyObject *) PyErr_NewExceptionWithDoc(
+ const char *name, const char *doc, PyObject *base, PyObject *dict);
+PyAPI_FUNC(void) PyErr_WriteUnraisable(PyObject *);
+
+/* In exceptions.c */
+#ifndef Py_LIMITED_API
+/* Helper that attempts to replace the current exception with one of the
+ * same type but with a prefix added to the exception text. The resulting
+ * exception description looks like:
+ *
+ * prefix (exc_type: original_exc_str)
+ *
+ * Only some exceptions can be safely replaced. If the function determines
+ * it isn't safe to perform the replacement, it will leave the original
+ * unmodified exception in place.
+ *
+ * Returns a borrowed reference to the new exception (if any), NULL if the
+ * existing exception was left in place.
+ */
+PyAPI_FUNC(PyObject *) _PyErr_TrySetFromCause(
+ const char *prefix_format, /* ASCII-encoded string */
+ ...
+ );
+#endif
+
+
+/* In signalmodule.c */
+PyAPI_FUNC(int) PyErr_CheckSignals(void);
+PyAPI_FUNC(void) PyErr_SetInterrupt(void);
+
+/* In signalmodule.c */
+#ifndef Py_LIMITED_API
+int PySignal_SetWakeupFd(int fd);
+#endif
+
+/* Support for adding program text to SyntaxErrors */
+PyAPI_FUNC(void) PyErr_SyntaxLocation(
+ const char *filename, /* decoded from the filesystem encoding */
+ int lineno);
+PyAPI_FUNC(void) PyErr_SyntaxLocationEx(
+ const char *filename, /* decoded from the filesystem encoding */
+ int lineno,
+ int col_offset);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) PyErr_SyntaxLocationObject(
+ PyObject *filename,
+ int lineno,
+ int col_offset);
+#endif
+PyAPI_FUNC(PyObject *) PyErr_ProgramText(
+ const char *filename, /* decoded from the filesystem encoding */
+ int lineno);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyErr_ProgramTextObject(
+ PyObject *filename,
+ int lineno);
+#endif
+
+/* The following functions are used to create and modify unicode
+ exceptions from C */
+
+/* create a UnicodeDecodeError object */
+PyAPI_FUNC(PyObject *) PyUnicodeDecodeError_Create(
+ const char *encoding, /* UTF-8 encoded string */
+ const char *object,
+ Py_ssize_t length,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ );
+
+/* create a UnicodeEncodeError object */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyUnicodeEncodeError_Create(
+ const char *encoding, /* UTF-8 encoded string */
+ const Py_UNICODE *object,
+ Py_ssize_t length,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* create a UnicodeTranslateError object */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyUnicodeTranslateError_Create(
+ const Py_UNICODE *object,
+ Py_ssize_t length,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ ) Py_DEPRECATED(3.3);
+PyAPI_FUNC(PyObject *) _PyUnicodeTranslateError_Create(
+ PyObject *object,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ const char *reason /* UTF-8 encoded string */
+ );
+#endif
+
+/* get the encoding attribute */
+PyAPI_FUNC(PyObject *) PyUnicodeEncodeError_GetEncoding(PyObject *);
+PyAPI_FUNC(PyObject *) PyUnicodeDecodeError_GetEncoding(PyObject *);
+
+/* get the object attribute */
+PyAPI_FUNC(PyObject *) PyUnicodeEncodeError_GetObject(PyObject *);
+PyAPI_FUNC(PyObject *) PyUnicodeDecodeError_GetObject(PyObject *);
+PyAPI_FUNC(PyObject *) PyUnicodeTranslateError_GetObject(PyObject *);
+
+/* get the value of the start attribute (the int * may not be NULL)
+ return 0 on success, -1 on failure */
+PyAPI_FUNC(int) PyUnicodeEncodeError_GetStart(PyObject *, Py_ssize_t *);
+PyAPI_FUNC(int) PyUnicodeDecodeError_GetStart(PyObject *, Py_ssize_t *);
+PyAPI_FUNC(int) PyUnicodeTranslateError_GetStart(PyObject *, Py_ssize_t *);
+
+/* assign a new value to the start attribute
+ return 0 on success, -1 on failure */
+PyAPI_FUNC(int) PyUnicodeEncodeError_SetStart(PyObject *, Py_ssize_t);
+PyAPI_FUNC(int) PyUnicodeDecodeError_SetStart(PyObject *, Py_ssize_t);
+PyAPI_FUNC(int) PyUnicodeTranslateError_SetStart(PyObject *, Py_ssize_t);
+
+/* get the value of the end attribute (the int *may not be NULL)
+ return 0 on success, -1 on failure */
+PyAPI_FUNC(int) PyUnicodeEncodeError_GetEnd(PyObject *, Py_ssize_t *);
+PyAPI_FUNC(int) PyUnicodeDecodeError_GetEnd(PyObject *, Py_ssize_t *);
+PyAPI_FUNC(int) PyUnicodeTranslateError_GetEnd(PyObject *, Py_ssize_t *);
+
+/* assign a new value to the end attribute
+ return 0 on success, -1 on failure */
+PyAPI_FUNC(int) PyUnicodeEncodeError_SetEnd(PyObject *, Py_ssize_t);
+PyAPI_FUNC(int) PyUnicodeDecodeError_SetEnd(PyObject *, Py_ssize_t);
+PyAPI_FUNC(int) PyUnicodeTranslateError_SetEnd(PyObject *, Py_ssize_t);
+
+/* get the value of the reason attribute */
+PyAPI_FUNC(PyObject *) PyUnicodeEncodeError_GetReason(PyObject *);
+PyAPI_FUNC(PyObject *) PyUnicodeDecodeError_GetReason(PyObject *);
+PyAPI_FUNC(PyObject *) PyUnicodeTranslateError_GetReason(PyObject *);
+
+/* assign a new value to the reason attribute
+ return 0 on success, -1 on failure */
+PyAPI_FUNC(int) PyUnicodeEncodeError_SetReason(
+ PyObject *exc,
+ const char *reason /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(int) PyUnicodeDecodeError_SetReason(
+ PyObject *exc,
+ const char *reason /* UTF-8 encoded string */
+ );
+PyAPI_FUNC(int) PyUnicodeTranslateError_SetReason(
+ PyObject *exc,
+ const char *reason /* UTF-8 encoded string */
+ );
+
+/* These APIs aren't really part of the error implementation, but
+ often needed to format error messages; the native C lib APIs are
+ not available on all platforms, which is why we provide emulations
+ for those platforms in Python/mysnprintf.c,
+ WARNING: The return value of snprintf varies across platforms; do
+ not rely on any particular behavior; eventually the C99 defn may
+ be reliable.
+*/
+#if defined(MS_WIN32) && !defined(HAVE_SNPRINTF)
+# define HAVE_SNPRINTF
+# define snprintf _snprintf
+# define vsnprintf _vsnprintf
+#endif
+
+#include
+PyAPI_FUNC(int) PyOS_snprintf(char *str, size_t size, const char *format, ...)
+ Py_GCC_ATTRIBUTE((format(printf, 3, 4)));
+PyAPI_FUNC(int) PyOS_vsnprintf(char *str, size_t size, const char *format, va_list va)
+ Py_GCC_ATTRIBUTE((format(printf, 3, 0)));
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_ERRORS_H */
diff --git a/Include/pyexpat.h b/Include/pyexpat.h
new file mode 100644
index 0000000..44259bf
--- /dev/null
+++ b/Include/pyexpat.h
@@ -0,0 +1,53 @@
+/* Stuff to export relevant 'expat' entry points from pyexpat to other
+ * parser modules, such as cElementTree. */
+
+/* note: you must import expat.h before importing this module! */
+
+#define PyExpat_CAPI_MAGIC "pyexpat.expat_CAPI 1.0"
+#define PyExpat_CAPSULE_NAME "pyexpat.expat_CAPI"
+
+struct PyExpat_CAPI
+{
+ char* magic; /* set to PyExpat_CAPI_MAGIC */
+ int size; /* set to sizeof(struct PyExpat_CAPI) */
+ int MAJOR_VERSION;
+ int MINOR_VERSION;
+ int MICRO_VERSION;
+ /* pointers to selected expat functions. add new functions at
+ the end, if needed */
+ const XML_LChar * (*ErrorString)(enum XML_Error code);
+ enum XML_Error (*GetErrorCode)(XML_Parser parser);
+ XML_Size (*GetErrorColumnNumber)(XML_Parser parser);
+ XML_Size (*GetErrorLineNumber)(XML_Parser parser);
+ enum XML_Status (*Parse)(
+ XML_Parser parser, const char *s, int len, int isFinal);
+ XML_Parser (*ParserCreate_MM)(
+ const XML_Char *encoding, const XML_Memory_Handling_Suite *memsuite,
+ const XML_Char *namespaceSeparator);
+ void (*ParserFree)(XML_Parser parser);
+ void (*SetCharacterDataHandler)(
+ XML_Parser parser, XML_CharacterDataHandler handler);
+ void (*SetCommentHandler)(
+ XML_Parser parser, XML_CommentHandler handler);
+ void (*SetDefaultHandlerExpand)(
+ XML_Parser parser, XML_DefaultHandler handler);
+ void (*SetElementHandler)(
+ XML_Parser parser, XML_StartElementHandler start,
+ XML_EndElementHandler end);
+ void (*SetNamespaceDeclHandler)(
+ XML_Parser parser, XML_StartNamespaceDeclHandler start,
+ XML_EndNamespaceDeclHandler end);
+ void (*SetProcessingInstructionHandler)(
+ XML_Parser parser, XML_ProcessingInstructionHandler handler);
+ void (*SetUnknownEncodingHandler)(
+ XML_Parser parser, XML_UnknownEncodingHandler handler,
+ void *encodingHandlerData);
+ void (*SetUserData)(XML_Parser parser, void *userData);
+ void (*SetStartDoctypeDeclHandler)(XML_Parser parser,
+ XML_StartDoctypeDeclHandler start);
+ enum XML_Status (*SetEncoding)(XML_Parser parser, const XML_Char *encoding);
+ int (*DefaultUnknownEncodingHandler)(
+ void *encodingHandlerData, const XML_Char *name, XML_Encoding *info);
+ /* always add new stuff to the end! */
+};
+
diff --git a/Include/pyfpe.h b/Include/pyfpe.h
new file mode 100644
index 0000000..5a99e39
--- /dev/null
+++ b/Include/pyfpe.h
@@ -0,0 +1,12 @@
+#ifndef Py_PYFPE_H
+#define Py_PYFPE_H
+
+/* These macros used to do something when Python was built with --with-fpectl,
+ * but support for that was dropped in 3.7. We continue to define them though,
+ * to avoid breaking API users.
+ */
+
+#define PyFPE_START_PROTECT(err_string, leave_stmt)
+#define PyFPE_END_PROTECT(v)
+
+#endif /* !Py_PYFPE_H */
diff --git a/Include/pyhash.h b/Include/pyhash.h
new file mode 100644
index 0000000..9cfd071
--- /dev/null
+++ b/Include/pyhash.h
@@ -0,0 +1,145 @@
+#ifndef Py_HASH_H
+
+#define Py_HASH_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Helpers for hash functions */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_hash_t) _Py_HashDouble(double);
+PyAPI_FUNC(Py_hash_t) _Py_HashPointer(void*);
+PyAPI_FUNC(Py_hash_t) _Py_HashBytes(const void*, Py_ssize_t);
+#endif
+
+/* Prime multiplier used in string and various other hashes. */
+#define _PyHASH_MULTIPLIER 1000003UL /* 0xf4243 */
+
+/* Parameters used for the numeric hash implementation. See notes for
+ _Py_HashDouble in Python/pyhash.c. Numeric hashes are based on
+ reduction modulo the prime 2**_PyHASH_BITS - 1. */
+
+#if SIZEOF_VOID_P >= 8
+# define _PyHASH_BITS 61
+#else
+# define _PyHASH_BITS 31
+#endif
+
+#define _PyHASH_MODULUS (((size_t)1 << _PyHASH_BITS) - 1)
+#define _PyHASH_INF 314159
+#define _PyHASH_NAN 0
+#define _PyHASH_IMAG _PyHASH_MULTIPLIER
+
+
+/* hash secret
+ *
+ * memory layout on 64 bit systems
+ * cccccccc cccccccc cccccccc uc -- unsigned char[24]
+ * pppppppp ssssssss ........ fnv -- two Py_hash_t
+ * k0k0k0k0 k1k1k1k1 ........ siphash -- two uint64_t
+ * ........ ........ ssssssss djbx33a -- 16 bytes padding + one Py_hash_t
+ * ........ ........ eeeeeeee pyexpat XML hash salt
+ *
+ * memory layout on 32 bit systems
+ * cccccccc cccccccc cccccccc uc
+ * ppppssss ........ ........ fnv -- two Py_hash_t
+ * k0k0k0k0 k1k1k1k1 ........ siphash -- two uint64_t (*)
+ * ........ ........ ssss.... djbx33a -- 16 bytes padding + one Py_hash_t
+ * ........ ........ eeee.... pyexpat XML hash salt
+ *
+ * (*) The siphash member may not be available on 32 bit platforms without
+ * an unsigned int64 data type.
+ */
+#ifndef Py_LIMITED_API
+typedef union {
+ /* ensure 24 bytes */
+ unsigned char uc[24];
+ /* two Py_hash_t for FNV */
+ struct {
+ Py_hash_t prefix;
+ Py_hash_t suffix;
+ } fnv;
+ /* two uint64 for SipHash24 */
+ struct {
+ uint64_t k0;
+ uint64_t k1;
+ } siphash;
+ /* a different (!) Py_hash_t for small string optimization */
+ struct {
+ unsigned char padding[16];
+ Py_hash_t suffix;
+ } djbx33a;
+ struct {
+ unsigned char padding[16];
+ Py_hash_t hashsalt;
+ } expat;
+} _Py_HashSecret_t;
+PyAPI_DATA(_Py_HashSecret_t) _Py_HashSecret;
+#endif
+
+#ifdef Py_DEBUG
+PyAPI_DATA(int) _Py_HashSecret_Initialized;
+#endif
+
+
+/* hash function definition */
+#ifndef Py_LIMITED_API
+typedef struct {
+ Py_hash_t (*const hash)(const void *, Py_ssize_t);
+ const char *name;
+ const int hash_bits;
+ const int seed_bits;
+} PyHash_FuncDef;
+
+PyAPI_FUNC(PyHash_FuncDef*) PyHash_GetFuncDef(void);
+#endif
+
+
+/* cutoff for small string DJBX33A optimization in range [1, cutoff).
+ *
+ * About 50% of the strings in a typical Python application are smaller than
+ * 6 to 7 chars. However DJBX33A is vulnerable to hash collision attacks.
+ * NEVER use DJBX33A for long strings!
+ *
+ * A Py_HASH_CUTOFF of 0 disables small string optimization. 32 bit platforms
+ * should use a smaller cutoff because it is easier to create colliding
+ * strings. A cutoff of 7 on 64bit platforms and 5 on 32bit platforms should
+ * provide a decent safety margin.
+ */
+#ifndef Py_HASH_CUTOFF
+# define Py_HASH_CUTOFF 0
+#elif (Py_HASH_CUTOFF > 7 || Py_HASH_CUTOFF < 0)
+# error Py_HASH_CUTOFF must in range 0...7.
+#endif /* Py_HASH_CUTOFF */
+
+
+/* hash algorithm selection
+ *
+ * The values for Py_HASH_SIPHASH24 and Py_HASH_FNV are hard-coded in the
+ * configure script.
+ *
+ * - FNV is available on all platforms and architectures.
+ * - SIPHASH24 only works on plaforms that don't require aligned memory for integers.
+ * - With EXTERNAL embedders can provide an alternative implementation with::
+ *
+ * PyHash_FuncDef PyHash_Func = {...};
+ *
+ * XXX: Figure out __declspec() for extern PyHash_FuncDef.
+ */
+#define Py_HASH_EXTERNAL 0
+#define Py_HASH_SIPHASH24 1
+#define Py_HASH_FNV 2
+
+#ifndef Py_HASH_ALGORITHM
+# ifndef HAVE_ALIGNED_REQUIRED
+# define Py_HASH_ALGORITHM Py_HASH_SIPHASH24
+# else
+# define Py_HASH_ALGORITHM Py_HASH_FNV
+# endif /* uint64_t && uint32_t && aligned */
+#endif /* Py_HASH_ALGORITHM */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_HASH_H */
diff --git a/Include/pylifecycle.h b/Include/pylifecycle.h
new file mode 100644
index 0000000..659c6df
--- /dev/null
+++ b/Include/pylifecycle.h
@@ -0,0 +1,214 @@
+
+/* Interfaces to configure, query, create & destroy the Python runtime */
+
+#ifndef Py_PYLIFECYCLE_H
+#define Py_PYLIFECYCLE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ const char *prefix;
+ const char *msg;
+ int user_err;
+} _PyInitError;
+
+/* Almost all errors causing Python initialization to fail */
+#ifdef _MSC_VER
+ /* Visual Studio 2015 doesn't implement C99 __func__ in C */
+# define _Py_INIT_GET_FUNC() __FUNCTION__
+#else
+# define _Py_INIT_GET_FUNC() __func__
+#endif
+
+#define _Py_INIT_OK() \
+ (_PyInitError){.prefix = NULL, .msg = NULL, .user_err = 0}
+#define _Py_INIT_ERR(MSG) \
+ (_PyInitError){.prefix = _Py_INIT_GET_FUNC(), .msg = (MSG), .user_err = 0}
+/* Error that can be fixed by the user like invalid input parameter.
+ Don't abort() the process on such error. */
+#define _Py_INIT_USER_ERR(MSG) \
+ (_PyInitError){.prefix = _Py_INIT_GET_FUNC(), .msg = (MSG), .user_err = 1}
+#define _Py_INIT_NO_MEMORY() _Py_INIT_USER_ERR("memory allocation failed")
+#define _Py_INIT_FAILED(err) \
+ (err.msg != NULL)
+
+#endif
+
+
+PyAPI_FUNC(void) Py_SetProgramName(const wchar_t *);
+PyAPI_FUNC(wchar_t *) Py_GetProgramName(void);
+
+PyAPI_FUNC(void) Py_SetPythonHome(const wchar_t *);
+PyAPI_FUNC(wchar_t *) Py_GetPythonHome(void);
+
+#ifndef Py_LIMITED_API
+/* Only used by applications that embed the interpreter and need to
+ * override the standard encoding determination mechanism
+ */
+PyAPI_FUNC(int) Py_SetStandardStreamEncoding(const char *encoding,
+ const char *errors);
+
+/* PEP 432 Multi-phase initialization API (Private while provisional!) */
+PyAPI_FUNC(_PyInitError) _Py_InitializeCore(const _PyCoreConfig *);
+PyAPI_FUNC(int) _Py_IsCoreInitialized(void);
+
+PyAPI_FUNC(_PyInitError) _PyCoreConfig_Read(_PyCoreConfig *);
+PyAPI_FUNC(void) _PyCoreConfig_Clear(_PyCoreConfig *);
+PyAPI_FUNC(int) _PyCoreConfig_Copy(
+ _PyCoreConfig *config,
+ const _PyCoreConfig *config2);
+
+PyAPI_FUNC(_PyInitError) _PyMainInterpreterConfig_Read(
+ _PyMainInterpreterConfig *config,
+ const _PyCoreConfig *core_config);
+PyAPI_FUNC(void) _PyMainInterpreterConfig_Clear(_PyMainInterpreterConfig *);
+PyAPI_FUNC(int) _PyMainInterpreterConfig_Copy(
+ _PyMainInterpreterConfig *config,
+ const _PyMainInterpreterConfig *config2);
+
+PyAPI_FUNC(_PyInitError) _Py_InitializeMainInterpreter(const _PyMainInterpreterConfig *);
+#endif
+
+/* Initialization and finalization */
+PyAPI_FUNC(void) Py_Initialize(void);
+PyAPI_FUNC(void) Py_InitializeEx(int);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(_PyInitError) _Py_InitializeEx_Private(int, int);
+PyAPI_FUNC(void) _Py_FatalInitError(_PyInitError err) _Py_NO_RETURN;
+#endif
+PyAPI_FUNC(void) Py_Finalize(void);
+PyAPI_FUNC(int) Py_FinalizeEx(void);
+PyAPI_FUNC(int) Py_IsInitialized(void);
+
+/* Subinterpreter support */
+PyAPI_FUNC(PyThreadState *) Py_NewInterpreter(void);
+PyAPI_FUNC(void) Py_EndInterpreter(PyThreadState *);
+
+
+/* Py_PyAtExit is for the atexit module, Py_AtExit is for low-level
+ * exit functions.
+ */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _Py_PyAtExit(void (*func)(PyObject *), PyObject *);
+#endif
+PyAPI_FUNC(int) Py_AtExit(void (*func)(void));
+
+PyAPI_FUNC(void) Py_Exit(int) _Py_NO_RETURN;
+
+/* Restore signals that the interpreter has called SIG_IGN on to SIG_DFL. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _Py_RestoreSignals(void);
+
+PyAPI_FUNC(int) Py_FdIsInteractive(FILE *, const char *);
+#endif
+
+/* Bootstrap __main__ (defined in Modules/main.c) */
+PyAPI_FUNC(int) Py_Main(int argc, wchar_t **argv);
+#ifdef Py_BUILD_CORE
+PyAPI_FUNC(int) _Py_UnixMain(int argc, char **argv);
+#endif
+
+/* In getpath.c */
+PyAPI_FUNC(wchar_t *) Py_GetProgramFullPath(void);
+PyAPI_FUNC(wchar_t *) Py_GetPrefix(void);
+PyAPI_FUNC(wchar_t *) Py_GetExecPrefix(void);
+PyAPI_FUNC(wchar_t *) Py_GetPath(void);
+#ifdef Py_BUILD_CORE
+PyAPI_FUNC(_PyInitError) _PyPathConfig_Init(const _PyCoreConfig *core_config);
+PyAPI_FUNC(PyObject*) _PyPathConfig_ComputeArgv0(int argc, wchar_t **argv);
+PyAPI_FUNC(int) _Py_FindEnvConfigValue(
+ FILE *env_file,
+ const wchar_t *key,
+ wchar_t *value,
+ size_t value_size);
+#endif
+PyAPI_FUNC(void) Py_SetPath(const wchar_t *);
+#ifdef MS_WINDOWS
+int _Py_CheckPython3(void);
+#endif
+
+/* In their own files */
+PyAPI_FUNC(const char *) Py_GetVersion(void);
+PyAPI_FUNC(const char *) Py_GetPlatform(void);
+PyAPI_FUNC(const char *) Py_GetCopyright(void);
+PyAPI_FUNC(const char *) Py_GetCompiler(void);
+PyAPI_FUNC(const char *) Py_GetBuildInfo(void);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(const char *) _Py_gitidentifier(void);
+PyAPI_FUNC(const char *) _Py_gitversion(void);
+#endif
+
+/* Internal -- various one-time initializations */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyBuiltin_Init(void);
+PyAPI_FUNC(_PyInitError) _PySys_BeginInit(PyObject **sysmod);
+PyAPI_FUNC(int) _PySys_EndInit(PyObject *sysdict, _PyMainInterpreterConfig *config);
+PyAPI_FUNC(_PyInitError) _PyImport_Init(PyInterpreterState *interp);
+PyAPI_FUNC(void) _PyExc_Init(PyObject * bltinmod);
+PyAPI_FUNC(_PyInitError) _PyImportHooks_Init(void);
+PyAPI_FUNC(int) _PyFrame_Init(void);
+PyAPI_FUNC(int) _PyFloat_Init(void);
+PyAPI_FUNC(int) PyByteArray_Init(void);
+PyAPI_FUNC(_PyInitError) _Py_HashRandomization_Init(const _PyCoreConfig *);
+#endif
+#ifdef Py_BUILD_CORE
+PyAPI_FUNC(int) _Py_ReadHashSeed(
+ const char *seed_text,
+ int *use_hash_seed,
+ unsigned long *hash_seed);
+#endif
+
+/* Various internal finalizers */
+
+#ifdef Py_BUILD_CORE
+PyAPI_FUNC(void) _PyExc_Fini(void);
+PyAPI_FUNC(void) _PyImport_Fini(void);
+PyAPI_FUNC(void) _PyImport_Fini2(void);
+PyAPI_FUNC(void) _PyGC_DumpShutdownStats(void);
+PyAPI_FUNC(void) _PyGC_Fini(void);
+PyAPI_FUNC(void) _PyType_Fini(void);
+PyAPI_FUNC(void) _Py_HashRandomization_Fini(void);
+#endif /* Py_BUILD_CORE */
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) PyMethod_Fini(void);
+PyAPI_FUNC(void) PyFrame_Fini(void);
+PyAPI_FUNC(void) PyCFunction_Fini(void);
+PyAPI_FUNC(void) PyDict_Fini(void);
+PyAPI_FUNC(void) PyTuple_Fini(void);
+PyAPI_FUNC(void) PyList_Fini(void);
+PyAPI_FUNC(void) PySet_Fini(void);
+PyAPI_FUNC(void) PyBytes_Fini(void);
+PyAPI_FUNC(void) PyByteArray_Fini(void);
+PyAPI_FUNC(void) PyFloat_Fini(void);
+PyAPI_FUNC(void) PyOS_FiniInterrupts(void);
+PyAPI_FUNC(void) PySlice_Fini(void);
+PyAPI_FUNC(void) PyAsyncGen_Fini(void);
+
+PyAPI_FUNC(int) _Py_IsFinalizing(void);
+#endif /* !Py_LIMITED_API */
+
+/* Signals */
+typedef void (*PyOS_sighandler_t)(int);
+PyAPI_FUNC(PyOS_sighandler_t) PyOS_getsig(int);
+PyAPI_FUNC(PyOS_sighandler_t) PyOS_setsig(int, PyOS_sighandler_t);
+
+#ifndef Py_LIMITED_API
+/* Random */
+PyAPI_FUNC(int) _PyOS_URandom(void *buffer, Py_ssize_t size);
+PyAPI_FUNC(int) _PyOS_URandomNonblock(void *buffer, Py_ssize_t size);
+#endif /* !Py_LIMITED_API */
+
+/* Legacy locale support */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _Py_CoerceLegacyLocale(const _PyCoreConfig *config);
+PyAPI_FUNC(int) _Py_LegacyLocaleDetected(void);
+PyAPI_FUNC(char *) _Py_SetLocaleFromEnv(int category);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PYLIFECYCLE_H */
diff --git a/Include/pymacconfig.h b/Include/pymacconfig.h
new file mode 100644
index 0000000..9dde11b
--- /dev/null
+++ b/Include/pymacconfig.h
@@ -0,0 +1,102 @@
+#ifndef PYMACCONFIG_H
+#define PYMACCONFIG_H
+ /*
+ * This file moves some of the autoconf magic to compile-time
+ * when building on MacOSX. This is needed for building 4-way
+ * universal binaries and for 64-bit universal binaries because
+ * the values redefined below aren't configure-time constant but
+ * only compile-time constant in these scenarios.
+ */
+
+#if defined(__APPLE__)
+
+# undef SIZEOF_LONG
+# undef SIZEOF_PTHREAD_T
+# undef SIZEOF_SIZE_T
+# undef SIZEOF_TIME_T
+# undef SIZEOF_VOID_P
+# undef SIZEOF__BOOL
+# undef SIZEOF_UINTPTR_T
+# undef SIZEOF_PTHREAD_T
+# undef WORDS_BIGENDIAN
+# undef DOUBLE_IS_ARM_MIXED_ENDIAN_IEEE754
+# undef DOUBLE_IS_BIG_ENDIAN_IEEE754
+# undef DOUBLE_IS_LITTLE_ENDIAN_IEEE754
+# undef HAVE_GCC_ASM_FOR_X87
+
+# undef VA_LIST_IS_ARRAY
+# if defined(__LP64__) && defined(__x86_64__)
+# define VA_LIST_IS_ARRAY 1
+# endif
+
+# undef HAVE_LARGEFILE_SUPPORT
+# ifndef __LP64__
+# define HAVE_LARGEFILE_SUPPORT 1
+# endif
+
+# undef SIZEOF_LONG
+# ifdef __LP64__
+# define SIZEOF__BOOL 1
+# define SIZEOF__BOOL 1
+# define SIZEOF_LONG 8
+# define SIZEOF_PTHREAD_T 8
+# define SIZEOF_SIZE_T 8
+# define SIZEOF_TIME_T 8
+# define SIZEOF_VOID_P 8
+# define SIZEOF_UINTPTR_T 8
+# define SIZEOF_PTHREAD_T 8
+# else
+# ifdef __ppc__
+# define SIZEOF__BOOL 4
+# else
+# define SIZEOF__BOOL 1
+# endif
+# define SIZEOF_LONG 4
+# define SIZEOF_PTHREAD_T 4
+# define SIZEOF_SIZE_T 4
+# define SIZEOF_TIME_T 4
+# define SIZEOF_VOID_P 4
+# define SIZEOF_UINTPTR_T 4
+# define SIZEOF_PTHREAD_T 4
+# endif
+
+# if defined(__LP64__)
+ /* MacOSX 10.4 (the first release to support 64-bit code
+ * at all) only supports 64-bit in the UNIX layer.
+ * Therefore suppress the toolbox-glue in 64-bit mode.
+ */
+
+ /* In 64-bit mode setpgrp always has no arguments, in 32-bit
+ * mode that depends on the compilation environment
+ */
+# undef SETPGRP_HAVE_ARG
+
+# endif
+
+#ifdef __BIG_ENDIAN__
+#define WORDS_BIGENDIAN 1
+#define DOUBLE_IS_BIG_ENDIAN_IEEE754
+#else
+#define DOUBLE_IS_LITTLE_ENDIAN_IEEE754
+#endif /* __BIG_ENDIAN */
+
+#ifdef __i386__
+# define HAVE_GCC_ASM_FOR_X87
+#endif
+
+ /*
+ * The definition in pyconfig.h is only valid on the OS release
+ * where configure ran on and not necessarily for all systems where
+ * the executable can be used on.
+ *
+ * Specifically: OSX 10.4 has limited supported for '%zd', while
+ * 10.5 has full support for '%zd'. A binary built on 10.5 won't
+ * work properly on 10.4 unless we suppress the definition
+ * of PY_FORMAT_SIZE_T
+ */
+#undef PY_FORMAT_SIZE_T
+
+
+#endif /* defined(_APPLE__) */
+
+#endif /* PYMACCONFIG_H */
diff --git a/Include/pymacro.h b/Include/pymacro.h
new file mode 100644
index 0000000..3f6ddbe
--- /dev/null
+++ b/Include/pymacro.h
@@ -0,0 +1,100 @@
+#ifndef Py_PYMACRO_H
+#define Py_PYMACRO_H
+
+/* Minimum value between x and y */
+#define Py_MIN(x, y) (((x) > (y)) ? (y) : (x))
+
+/* Maximum value between x and y */
+#define Py_MAX(x, y) (((x) > (y)) ? (x) : (y))
+
+/* Absolute value of the number x */
+#define Py_ABS(x) ((x) < 0 ? -(x) : (x))
+
+#define _Py_XSTRINGIFY(x) #x
+
+/* Convert the argument to a string. For example, Py_STRINGIFY(123) is replaced
+ with "123" by the preprocessor. Defines are also replaced by their value.
+ For example Py_STRINGIFY(__LINE__) is replaced by the line number, not
+ by "__LINE__". */
+#define Py_STRINGIFY(x) _Py_XSTRINGIFY(x)
+
+/* Get the size of a structure member in bytes */
+#define Py_MEMBER_SIZE(type, member) sizeof(((type *)0)->member)
+
+/* Argument must be a char or an int in [-128, 127] or [0, 255]. */
+#define Py_CHARMASK(c) ((unsigned char)((c) & 0xff))
+
+/* Assert a build-time dependency, as an expression.
+
+ Your compile will fail if the condition isn't true, or can't be evaluated
+ by the compiler. This can be used in an expression: its value is 0.
+
+ Example:
+
+ #define foo_to_char(foo) \
+ ((char *)(foo) \
+ + Py_BUILD_ASSERT_EXPR(offsetof(struct foo, string) == 0))
+
+ Written by Rusty Russell, public domain, http://ccodearchive.net/ */
+#define Py_BUILD_ASSERT_EXPR(cond) \
+ (sizeof(char [1 - 2*!(cond)]) - 1)
+
+#define Py_BUILD_ASSERT(cond) do { \
+ (void)Py_BUILD_ASSERT_EXPR(cond); \
+ } while(0)
+
+/* Get the number of elements in a visible array
+
+ This does not work on pointers, or arrays declared as [], or function
+ parameters. With correct compiler support, such usage will cause a build
+ error (see Py_BUILD_ASSERT_EXPR).
+
+ Written by Rusty Russell, public domain, http://ccodearchive.net/
+
+ Requires at GCC 3.1+ */
+#if (defined(__GNUC__) && !defined(__STRICT_ANSI__) && \
+ (((__GNUC__ == 3) && (__GNUC_MINOR__ >= 1)) || (__GNUC__ >= 4)))
+/* Two gcc extensions.
+ &a[0] degrades to a pointer: a different type from an array */
+#define Py_ARRAY_LENGTH(array) \
+ (sizeof(array) / sizeof((array)[0]) \
+ + Py_BUILD_ASSERT_EXPR(!__builtin_types_compatible_p(typeof(array), \
+ typeof(&(array)[0]))))
+#else
+#define Py_ARRAY_LENGTH(array) \
+ (sizeof(array) / sizeof((array)[0]))
+#endif
+
+
+/* Define macros for inline documentation. */
+#define PyDoc_VAR(name) static char name[]
+#define PyDoc_STRVAR(name,str) PyDoc_VAR(name) = PyDoc_STR(str)
+#ifdef WITH_DOC_STRINGS
+#define PyDoc_STR(str) str
+#else
+#define PyDoc_STR(str) ""
+#endif
+
+/* Below "a" is a power of 2. */
+/* Round down size "n" to be a multiple of "a". */
+#define _Py_SIZE_ROUND_DOWN(n, a) ((size_t)(n) & ~(size_t)((a) - 1))
+/* Round up size "n" to be a multiple of "a". */
+#define _Py_SIZE_ROUND_UP(n, a) (((size_t)(n) + \
+ (size_t)((a) - 1)) & ~(size_t)((a) - 1))
+/* Round pointer "p" down to the closest "a"-aligned address <= "p". */
+#define _Py_ALIGN_DOWN(p, a) ((void *)((uintptr_t)(p) & ~(uintptr_t)((a) - 1)))
+/* Round pointer "p" up to the closest "a"-aligned address >= "p". */
+#define _Py_ALIGN_UP(p, a) ((void *)(((uintptr_t)(p) + \
+ (uintptr_t)((a) - 1)) & ~(uintptr_t)((a) - 1)))
+/* Check if pointer "p" is aligned to "a"-bytes boundary. */
+#define _Py_IS_ALIGNED(p, a) (!((uintptr_t)(p) & (uintptr_t)((a) - 1)))
+
+#ifdef __GNUC__
+#define Py_UNUSED(name) _unused_ ## name __attribute__((unused))
+#else
+#define Py_UNUSED(name) _unused_ ## name
+#endif
+
+#define Py_UNREACHABLE() abort()
+
+#endif /* Py_PYMACRO_H */
diff --git a/Include/pymath.h b/Include/pymath.h
new file mode 100644
index 0000000..6cf69f9
--- /dev/null
+++ b/Include/pymath.h
@@ -0,0 +1,230 @@
+#ifndef Py_PYMATH_H
+#define Py_PYMATH_H
+
+#include "pyconfig.h" /* include for defines */
+
+/**************************************************************************
+Symbols and macros to supply platform-independent interfaces to mathematical
+functions and constants
+**************************************************************************/
+
+/* Python provides implementations for copysign, round and hypot in
+ * Python/pymath.c just in case your math library doesn't provide the
+ * functions.
+ *
+ *Note: PC/pyconfig.h defines copysign as _copysign
+ */
+#ifndef HAVE_COPYSIGN
+extern double copysign(double, double);
+#endif
+
+#ifndef HAVE_ROUND
+extern double round(double);
+#endif
+
+#ifndef HAVE_HYPOT
+extern double hypot(double, double);
+#endif
+
+/* extra declarations */
+#ifndef _MSC_VER
+#ifndef __STDC__
+extern double fmod (double, double);
+extern double frexp (double, int *);
+extern double ldexp (double, int);
+extern double modf (double, double *);
+extern double pow(double, double);
+#endif /* __STDC__ */
+#endif /* _MSC_VER */
+
+/* High precision definition of pi and e (Euler)
+ * The values are taken from libc6's math.h.
+ */
+#ifndef Py_MATH_PIl
+#define Py_MATH_PIl 3.1415926535897932384626433832795029L
+#endif
+#ifndef Py_MATH_PI
+#define Py_MATH_PI 3.14159265358979323846
+#endif
+
+#ifndef Py_MATH_El
+#define Py_MATH_El 2.7182818284590452353602874713526625L
+#endif
+
+#ifndef Py_MATH_E
+#define Py_MATH_E 2.7182818284590452354
+#endif
+
+/* Tau (2pi) to 40 digits, taken from tauday.com/tau-digits. */
+#ifndef Py_MATH_TAU
+#define Py_MATH_TAU 6.2831853071795864769252867665590057683943L
+#endif
+
+
+/* On x86, Py_FORCE_DOUBLE forces a floating-point number out of an x87 FPU
+ register and into a 64-bit memory location, rounding from extended
+ precision to double precision in the process. On other platforms it does
+ nothing. */
+
+/* we take double rounding as evidence of x87 usage */
+#ifndef Py_LIMITED_API
+#ifndef Py_FORCE_DOUBLE
+# ifdef X87_DOUBLE_ROUNDING
+PyAPI_FUNC(double) _Py_force_double(double);
+# define Py_FORCE_DOUBLE(X) (_Py_force_double(X))
+# else
+# define Py_FORCE_DOUBLE(X) (X)
+# endif
+#endif
+#endif
+
+#ifndef Py_LIMITED_API
+#ifdef HAVE_GCC_ASM_FOR_X87
+PyAPI_FUNC(unsigned short) _Py_get_387controlword(void);
+PyAPI_FUNC(void) _Py_set_387controlword(unsigned short);
+#endif
+#endif
+
+/* Py_IS_NAN(X)
+ * Return 1 if float or double arg is a NaN, else 0.
+ * Caution:
+ * X is evaluated more than once.
+ * This may not work on all platforms. Each platform has *some*
+ * way to spell this, though -- override in pyconfig.h if you have
+ * a platform where it doesn't work.
+ * Note: PC/pyconfig.h defines Py_IS_NAN as _isnan
+ */
+#ifndef Py_IS_NAN
+#if defined HAVE_DECL_ISNAN && HAVE_DECL_ISNAN == 1
+#define Py_IS_NAN(X) isnan(X)
+#else
+#define Py_IS_NAN(X) ((X) != (X))
+#endif
+#endif
+
+/* Py_IS_INFINITY(X)
+ * Return 1 if float or double arg is an infinity, else 0.
+ * Caution:
+ * X is evaluated more than once.
+ * This implementation may set the underflow flag if |X| is very small;
+ * it really can't be implemented correctly (& easily) before C99.
+ * Override in pyconfig.h if you have a better spelling on your platform.
+ * Py_FORCE_DOUBLE is used to avoid getting false negatives from a
+ * non-infinite value v sitting in an 80-bit x87 register such that
+ * v becomes infinite when spilled from the register to 64-bit memory.
+ * Note: PC/pyconfig.h defines Py_IS_INFINITY as _isinf
+ */
+#ifndef Py_IS_INFINITY
+# if defined HAVE_DECL_ISINF && HAVE_DECL_ISINF == 1
+# define Py_IS_INFINITY(X) isinf(X)
+# else
+# define Py_IS_INFINITY(X) ((X) && \
+ (Py_FORCE_DOUBLE(X)*0.5 == Py_FORCE_DOUBLE(X)))
+# endif
+#endif
+
+/* Py_IS_FINITE(X)
+ * Return 1 if float or double arg is neither infinite nor NAN, else 0.
+ * Some compilers (e.g. VisualStudio) have intrisics for this, so a special
+ * macro for this particular test is useful
+ * Note: PC/pyconfig.h defines Py_IS_FINITE as _finite
+ */
+#ifndef Py_IS_FINITE
+#if defined HAVE_DECL_ISFINITE && HAVE_DECL_ISFINITE == 1
+#define Py_IS_FINITE(X) isfinite(X)
+#elif defined HAVE_FINITE
+#define Py_IS_FINITE(X) finite(X)
+#else
+#define Py_IS_FINITE(X) (!Py_IS_INFINITY(X) && !Py_IS_NAN(X))
+#endif
+#endif
+
+/* HUGE_VAL is supposed to expand to a positive double infinity. Python
+ * uses Py_HUGE_VAL instead because some platforms are broken in this
+ * respect. We used to embed code in pyport.h to try to worm around that,
+ * but different platforms are broken in conflicting ways. If you're on
+ * a platform where HUGE_VAL is defined incorrectly, fiddle your Python
+ * config to #define Py_HUGE_VAL to something that works on your platform.
+ */
+#ifndef Py_HUGE_VAL
+#define Py_HUGE_VAL HUGE_VAL
+#endif
+
+/* Py_NAN
+ * A value that evaluates to a NaN. On IEEE 754 platforms INF*0 or
+ * INF/INF works. Define Py_NO_NAN in pyconfig.h if your platform
+ * doesn't support NaNs.
+ */
+#if !defined(Py_NAN) && !defined(Py_NO_NAN)
+#if !defined(__INTEL_COMPILER)
+ #define Py_NAN (Py_HUGE_VAL * 0.)
+#else /* __INTEL_COMPILER */
+ #if defined(ICC_NAN_STRICT)
+ #pragma float_control(push)
+ #pragma float_control(precise, on)
+ #pragma float_control(except, on)
+ #if defined(_MSC_VER)
+ __declspec(noinline)
+ #else /* Linux */
+ __attribute__((noinline))
+ #endif /* _MSC_VER */
+ static double __icc_nan()
+ {
+ return sqrt(-1.0);
+ }
+ #pragma float_control (pop)
+ #define Py_NAN __icc_nan()
+ #else /* ICC_NAN_RELAXED as default for Intel Compiler */
+ static const union { unsigned char buf[8]; double __icc_nan; } __nan_store = {0,0,0,0,0,0,0xf8,0x7f};
+ #define Py_NAN (__nan_store.__icc_nan)
+ #endif /* ICC_NAN_STRICT */
+#endif /* __INTEL_COMPILER */
+#endif
+
+/* Py_OVERFLOWED(X)
+ * Return 1 iff a libm function overflowed. Set errno to 0 before calling
+ * a libm function, and invoke this macro after, passing the function
+ * result.
+ * Caution:
+ * This isn't reliable. C99 no longer requires libm to set errno under
+ * any exceptional condition, but does require +- HUGE_VAL return
+ * values on overflow. A 754 box *probably* maps HUGE_VAL to a
+ * double infinity, and we're cool if that's so, unless the input
+ * was an infinity and an infinity is the expected result. A C89
+ * system sets errno to ERANGE, so we check for that too. We're
+ * out of luck if a C99 754 box doesn't map HUGE_VAL to +Inf, or
+ * if the returned result is a NaN, or if a C89 box returns HUGE_VAL
+ * in non-overflow cases.
+ * X is evaluated more than once.
+ * Some platforms have better way to spell this, so expect some #ifdef'ery.
+ *
+ * OpenBSD uses 'isinf()' because a compiler bug on that platform causes
+ * the longer macro version to be mis-compiled. This isn't optimal, and
+ * should be removed once a newer compiler is available on that platform.
+ * The system that had the failure was running OpenBSD 3.2 on Intel, with
+ * gcc 2.95.3.
+ *
+ * According to Tim's checkin, the FreeBSD systems use isinf() to work
+ * around a FPE bug on that platform.
+ */
+#if defined(__FreeBSD__) || defined(__OpenBSD__)
+#define Py_OVERFLOWED(X) isinf(X)
+#else
+#define Py_OVERFLOWED(X) ((X) != 0.0 && (errno == ERANGE || \
+ (X) == Py_HUGE_VAL || \
+ (X) == -Py_HUGE_VAL))
+#endif
+
+/* Return whether integral type *type* is signed or not. */
+#define _Py_IntegralTypeSigned(type) ((type)(-1) < 0)
+/* Return the maximum value of integral type *type*. */
+#define _Py_IntegralTypeMax(type) ((_Py_IntegralTypeSigned(type)) ? (((((type)1 << (sizeof(type)*CHAR_BIT - 2)) - 1) << 1) + 1) : ~(type)0)
+/* Return the minimum value of integral type *type*. */
+#define _Py_IntegralTypeMin(type) ((_Py_IntegralTypeSigned(type)) ? -_Py_IntegralTypeMax(type) - 1 : 0)
+/* Check whether *v* is in the range of integral type *type*. This is most
+ * useful if *v* is floating-point, since demoting a floating-point *v* to an
+ * integral type that cannot represent *v*'s integral part is undefined
+ * behavior. */
+#define _Py_InIntegralTypeRange(type, v) (_Py_IntegralTypeMin(type) <= v && v <= _Py_IntegralTypeMax(type))
+
+#endif /* Py_PYMATH_H */
diff --git a/Include/pymem.h b/Include/pymem.h
new file mode 100644
index 0000000..8ee0efd
--- /dev/null
+++ b/Include/pymem.h
@@ -0,0 +1,244 @@
+/* The PyMem_ family: low-level memory allocation interfaces.
+ See objimpl.h for the PyObject_ memory family.
+*/
+
+#ifndef Py_PYMEM_H
+#define Py_PYMEM_H
+
+#include "pyport.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void *) PyMem_RawMalloc(size_t size);
+PyAPI_FUNC(void *) PyMem_RawCalloc(size_t nelem, size_t elsize);
+PyAPI_FUNC(void *) PyMem_RawRealloc(void *ptr, size_t new_size);
+PyAPI_FUNC(void) PyMem_RawFree(void *ptr);
+
+/* Configure the Python memory allocators. Pass NULL to use default
+ allocators. */
+PyAPI_FUNC(int) _PyMem_SetupAllocators(const char *opt);
+
+/* Try to get the allocators name set by _PyMem_SetupAllocators(). */
+PyAPI_FUNC(const char*) _PyMem_GetAllocatorsName(void);
+
+/* Track an allocated memory block in the tracemalloc module.
+ Return 0 on success, return -1 on error (failed to allocate memory to store
+ the trace).
+
+ Return -2 if tracemalloc is disabled.
+
+ If memory block is already tracked, update the existing trace. */
+PyAPI_FUNC(int) PyTraceMalloc_Track(
+ unsigned int domain,
+ uintptr_t ptr,
+ size_t size);
+
+/* Untrack an allocated memory block in the tracemalloc module.
+ Do nothing if the block was not tracked.
+
+ Return -2 if tracemalloc is disabled, otherwise return 0. */
+PyAPI_FUNC(int) PyTraceMalloc_Untrack(
+ unsigned int domain,
+ uintptr_t ptr);
+
+/* Get the traceback where a memory block was allocated.
+
+ Return a tuple of (filename: str, lineno: int) tuples.
+
+ Return None if the tracemalloc module is disabled or if the memory block
+ is not tracked by tracemalloc.
+
+ Raise an exception and return NULL on error. */
+PyAPI_FUNC(PyObject*) _PyTraceMalloc_GetTraceback(
+ unsigned int domain,
+ uintptr_t ptr);
+#endif /* !Py_LIMITED_API */
+
+
+/* BEWARE:
+
+ Each interface exports both functions and macros. Extension modules should
+ use the functions, to ensure binary compatibility across Python versions.
+ Because the Python implementation is free to change internal details, and
+ the macros may (or may not) expose details for speed, if you do use the
+ macros you must recompile your extensions with each Python release.
+
+ Never mix calls to PyMem_ with calls to the platform malloc/realloc/
+ calloc/free. For example, on Windows different DLLs may end up using
+ different heaps, and if you use PyMem_Malloc you'll get the memory from the
+ heap used by the Python DLL; it could be a disaster if you free()'ed that
+ directly in your own extension. Using PyMem_Free instead ensures Python
+ can return the memory to the proper heap. As another example, in
+ PYMALLOC_DEBUG mode, Python wraps all calls to all PyMem_ and PyObject_
+ memory functions in special debugging wrappers that add additional
+ debugging info to dynamic memory blocks. The system routines have no idea
+ what to do with that stuff, and the Python wrappers have no idea what to do
+ with raw blocks obtained directly by the system routines then.
+
+ The GIL must be held when using these APIs.
+*/
+
+/*
+ * Raw memory interface
+ * ====================
+ */
+
+/* Functions
+
+ Functions supplying platform-independent semantics for malloc/realloc/
+ free. These functions make sure that allocating 0 bytes returns a distinct
+ non-NULL pointer (whenever possible -- if we're flat out of memory, NULL
+ may be returned), even if the platform malloc and realloc don't.
+ Returned pointers must be checked for NULL explicitly. No action is
+ performed on failure (no exception is set, no warning is printed, etc).
+*/
+
+PyAPI_FUNC(void *) PyMem_Malloc(size_t size);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+PyAPI_FUNC(void *) PyMem_Calloc(size_t nelem, size_t elsize);
+#endif
+PyAPI_FUNC(void *) PyMem_Realloc(void *ptr, size_t new_size);
+PyAPI_FUNC(void) PyMem_Free(void *ptr);
+
+#ifndef Py_LIMITED_API
+/* strdup() using PyMem_RawMalloc() */
+PyAPI_FUNC(char *) _PyMem_RawStrdup(const char *str);
+
+/* strdup() using PyMem_Malloc() */
+PyAPI_FUNC(char *) _PyMem_Strdup(const char *str);
+
+/* wcsdup() using PyMem_RawMalloc() */
+PyAPI_FUNC(wchar_t*) _PyMem_RawWcsdup(const wchar_t *str);
+#endif
+
+/* Macros. */
+
+/* PyMem_MALLOC(0) means malloc(1). Some systems would return NULL
+ for malloc(0), which would be treated as an error. Some platforms
+ would return a pointer with no memory behind it, which would break
+ pymalloc. To solve these problems, allocate an extra byte. */
+/* Returns NULL to indicate error if a negative size or size larger than
+ Py_ssize_t can represent is supplied. Helps prevents security holes. */
+#define PyMem_MALLOC(n) PyMem_Malloc(n)
+#define PyMem_REALLOC(p, n) PyMem_Realloc(p, n)
+#define PyMem_FREE(p) PyMem_Free(p)
+
+/*
+ * Type-oriented memory interface
+ * ==============================
+ *
+ * Allocate memory for n objects of the given type. Returns a new pointer
+ * or NULL if the request was too large or memory allocation failed. Use
+ * these macros rather than doing the multiplication yourself so that proper
+ * overflow checking is always done.
+ */
+
+#define PyMem_New(type, n) \
+ ( ((size_t)(n) > PY_SSIZE_T_MAX / sizeof(type)) ? NULL : \
+ ( (type *) PyMem_Malloc((n) * sizeof(type)) ) )
+#define PyMem_NEW(type, n) \
+ ( ((size_t)(n) > PY_SSIZE_T_MAX / sizeof(type)) ? NULL : \
+ ( (type *) PyMem_MALLOC((n) * sizeof(type)) ) )
+
+/*
+ * The value of (p) is always clobbered by this macro regardless of success.
+ * The caller MUST check if (p) is NULL afterwards and deal with the memory
+ * error if so. This means the original value of (p) MUST be saved for the
+ * caller's memory error handler to not lose track of it.
+ */
+#define PyMem_Resize(p, type, n) \
+ ( (p) = ((size_t)(n) > PY_SSIZE_T_MAX / sizeof(type)) ? NULL : \
+ (type *) PyMem_Realloc((p), (n) * sizeof(type)) )
+#define PyMem_RESIZE(p, type, n) \
+ ( (p) = ((size_t)(n) > PY_SSIZE_T_MAX / sizeof(type)) ? NULL : \
+ (type *) PyMem_REALLOC((p), (n) * sizeof(type)) )
+
+/* PyMem{Del,DEL} are left over from ancient days, and shouldn't be used
+ * anymore. They're just confusing aliases for PyMem_{Free,FREE} now.
+ */
+#define PyMem_Del PyMem_Free
+#define PyMem_DEL PyMem_FREE
+
+#ifndef Py_LIMITED_API
+typedef enum {
+ /* PyMem_RawMalloc(), PyMem_RawRealloc() and PyMem_RawFree() */
+ PYMEM_DOMAIN_RAW,
+
+ /* PyMem_Malloc(), PyMem_Realloc() and PyMem_Free() */
+ PYMEM_DOMAIN_MEM,
+
+ /* PyObject_Malloc(), PyObject_Realloc() and PyObject_Free() */
+ PYMEM_DOMAIN_OBJ
+} PyMemAllocatorDomain;
+
+typedef struct {
+ /* user context passed as the first argument to the 4 functions */
+ void *ctx;
+
+ /* allocate a memory block */
+ void* (*malloc) (void *ctx, size_t size);
+
+ /* allocate a memory block initialized by zeros */
+ void* (*calloc) (void *ctx, size_t nelem, size_t elsize);
+
+ /* allocate or resize a memory block */
+ void* (*realloc) (void *ctx, void *ptr, size_t new_size);
+
+ /* release a memory block */
+ void (*free) (void *ctx, void *ptr);
+} PyMemAllocatorEx;
+
+/* Get the memory block allocator of the specified domain. */
+PyAPI_FUNC(void) PyMem_GetAllocator(PyMemAllocatorDomain domain,
+ PyMemAllocatorEx *allocator);
+
+/* Set the memory block allocator of the specified domain.
+
+ The new allocator must return a distinct non-NULL pointer when requesting
+ zero bytes.
+
+ For the PYMEM_DOMAIN_RAW domain, the allocator must be thread-safe: the GIL
+ is not held when the allocator is called.
+
+ If the new allocator is not a hook (don't call the previous allocator), the
+ PyMem_SetupDebugHooks() function must be called to reinstall the debug hooks
+ on top on the new allocator. */
+PyAPI_FUNC(void) PyMem_SetAllocator(PyMemAllocatorDomain domain,
+ PyMemAllocatorEx *allocator);
+
+/* Setup hooks to detect bugs in the following Python memory allocator
+ functions:
+
+ - PyMem_RawMalloc(), PyMem_RawRealloc(), PyMem_RawFree()
+ - PyMem_Malloc(), PyMem_Realloc(), PyMem_Free()
+ - PyObject_Malloc(), PyObject_Realloc() and PyObject_Free()
+
+ Newly allocated memory is filled with the byte 0xCB, freed memory is filled
+ with the byte 0xDB. Additional checks:
+
+ - detect API violations, ex: PyObject_Free() called on a buffer allocated
+ by PyMem_Malloc()
+ - detect write before the start of the buffer (buffer underflow)
+ - detect write after the end of the buffer (buffer overflow)
+
+ The function does nothing if Python is not compiled is debug mode. */
+PyAPI_FUNC(void) PyMem_SetupDebugHooks(void);
+#endif
+
+#ifdef Py_BUILD_CORE
+/* Set the memory allocator of the specified domain to the default.
+ Save the old allocator into *old_alloc if it's non-NULL.
+ Return on success, or return -1 if the domain is unknown. */
+PyAPI_FUNC(int) _PyMem_SetDefaultAllocator(
+ PyMemAllocatorDomain domain,
+ PyMemAllocatorEx *old_alloc);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_PYMEM_H */
diff --git a/Include/pyport.h b/Include/pyport.h
new file mode 100644
index 0000000..c1f4c7f
--- /dev/null
+++ b/Include/pyport.h
@@ -0,0 +1,793 @@
+#ifndef Py_PYPORT_H
+#define Py_PYPORT_H
+
+#include "pyconfig.h" /* include for defines */
+
+#include
+
+/**************************************************************************
+Symbols and macros to supply platform-independent interfaces to basic
+C language & library operations whose spellings vary across platforms.
+
+Please try to make documentation here as clear as possible: by definition,
+the stuff here is trying to illuminate C's darkest corners.
+
+Config #defines referenced here:
+
+SIGNED_RIGHT_SHIFT_ZERO_FILLS
+Meaning: To be defined iff i>>j does not extend the sign bit when i is a
+ signed integral type and i < 0.
+Used in: Py_ARITHMETIC_RIGHT_SHIFT
+
+Py_DEBUG
+Meaning: Extra checks compiled in for debug mode.
+Used in: Py_SAFE_DOWNCAST
+
+**************************************************************************/
+
+/* typedefs for some C9X-defined synonyms for integral types.
+ *
+ * The names in Python are exactly the same as the C9X names, except with a
+ * Py_ prefix. Until C9X is universally implemented, this is the only way
+ * to ensure that Python gets reliable names that don't conflict with names
+ * in non-Python code that are playing their own tricks to define the C9X
+ * names.
+ *
+ * NOTE: don't go nuts here! Python has no use for *most* of the C9X
+ * integral synonyms. Only define the ones we actually need.
+ */
+
+/* long long is required. Ensure HAVE_LONG_LONG is defined for compatibility. */
+#ifndef HAVE_LONG_LONG
+#define HAVE_LONG_LONG 1
+#endif
+#ifndef PY_LONG_LONG
+#define PY_LONG_LONG long long
+/* If LLONG_MAX is defined in limits.h, use that. */
+#define PY_LLONG_MIN LLONG_MIN
+#define PY_LLONG_MAX LLONG_MAX
+#define PY_ULLONG_MAX ULLONG_MAX
+#endif
+
+#define PY_UINT32_T uint32_t
+#define PY_UINT64_T uint64_t
+
+/* Signed variants of the above */
+#define PY_INT32_T int32_t
+#define PY_INT64_T int64_t
+
+/* If PYLONG_BITS_IN_DIGIT is not defined then we'll use 30-bit digits if all
+ the necessary integer types are available, and we're on a 64-bit platform
+ (as determined by SIZEOF_VOID_P); otherwise we use 15-bit digits. */
+
+#ifndef PYLONG_BITS_IN_DIGIT
+#if SIZEOF_VOID_P >= 8
+#define PYLONG_BITS_IN_DIGIT 30
+#else
+#define PYLONG_BITS_IN_DIGIT 15
+#endif
+#endif
+
+/* uintptr_t is the C9X name for an unsigned integral type such that a
+ * legitimate void* can be cast to uintptr_t and then back to void* again
+ * without loss of information. Similarly for intptr_t, wrt a signed
+ * integral type.
+ */
+typedef uintptr_t Py_uintptr_t;
+typedef intptr_t Py_intptr_t;
+
+/* Py_ssize_t is a signed integral type such that sizeof(Py_ssize_t) ==
+ * sizeof(size_t). C99 doesn't define such a thing directly (size_t is an
+ * unsigned integral type). See PEP 353 for details.
+ */
+#ifdef HAVE_SSIZE_T
+typedef ssize_t Py_ssize_t;
+#elif SIZEOF_VOID_P == SIZEOF_SIZE_T
+typedef Py_intptr_t Py_ssize_t;
+#else
+# error "Python needs a typedef for Py_ssize_t in pyport.h."
+#endif
+
+/* Py_hash_t is the same size as a pointer. */
+#define SIZEOF_PY_HASH_T SIZEOF_SIZE_T
+typedef Py_ssize_t Py_hash_t;
+/* Py_uhash_t is the unsigned equivalent needed to calculate numeric hash. */
+#define SIZEOF_PY_UHASH_T SIZEOF_SIZE_T
+typedef size_t Py_uhash_t;
+
+/* Only used for compatibility with code that may not be PY_SSIZE_T_CLEAN. */
+#ifdef PY_SSIZE_T_CLEAN
+typedef Py_ssize_t Py_ssize_clean_t;
+#else
+typedef int Py_ssize_clean_t;
+#endif
+
+/* Largest possible value of size_t. */
+#define PY_SIZE_MAX SIZE_MAX
+
+/* Largest positive value of type Py_ssize_t. */
+#define PY_SSIZE_T_MAX ((Py_ssize_t)(((size_t)-1)>>1))
+/* Smallest negative value of type Py_ssize_t. */
+#define PY_SSIZE_T_MIN (-PY_SSIZE_T_MAX-1)
+
+/* PY_FORMAT_SIZE_T is a platform-specific modifier for use in a printf
+ * format to convert an argument with the width of a size_t or Py_ssize_t.
+ * C99 introduced "z" for this purpose, but not all platforms support that;
+ * e.g., MS compilers use "I" instead.
+ *
+ * These "high level" Python format functions interpret "z" correctly on
+ * all platforms (Python interprets the format string itself, and does whatever
+ * the platform C requires to convert a size_t/Py_ssize_t argument):
+ *
+ * PyBytes_FromFormat
+ * PyErr_Format
+ * PyBytes_FromFormatV
+ * PyUnicode_FromFormatV
+ *
+ * Lower-level uses require that you interpolate the correct format modifier
+ * yourself (e.g., calling printf, fprintf, sprintf, PyOS_snprintf); for
+ * example,
+ *
+ * Py_ssize_t index;
+ * fprintf(stderr, "index %" PY_FORMAT_SIZE_T "d sucks\n", index);
+ *
+ * That will expand to %ld, or %Id, or to something else correct for a
+ * Py_ssize_t on the platform.
+ */
+#ifndef PY_FORMAT_SIZE_T
+# if SIZEOF_SIZE_T == SIZEOF_INT && !defined(__APPLE__)
+# define PY_FORMAT_SIZE_T ""
+# elif SIZEOF_SIZE_T == SIZEOF_LONG
+# define PY_FORMAT_SIZE_T "l"
+# elif defined(MS_WINDOWS)
+# define PY_FORMAT_SIZE_T "I"
+# else
+# error "This platform's pyconfig.h needs to define PY_FORMAT_SIZE_T"
+# endif
+#endif
+
+/* Py_LOCAL can be used instead of static to get the fastest possible calling
+ * convention for functions that are local to a given module.
+ *
+ * Py_LOCAL_INLINE does the same thing, and also explicitly requests inlining,
+ * for platforms that support that.
+ *
+ * If PY_LOCAL_AGGRESSIVE is defined before python.h is included, more
+ * "aggressive" inlining/optimization is enabled for the entire module. This
+ * may lead to code bloat, and may slow things down for those reasons. It may
+ * also lead to errors, if the code relies on pointer aliasing. Use with
+ * care.
+ *
+ * NOTE: You can only use this for functions that are entirely local to a
+ * module; functions that are exported via method tables, callbacks, etc,
+ * should keep using static.
+ */
+
+#if defined(_MSC_VER)
+#if defined(PY_LOCAL_AGGRESSIVE)
+/* enable more aggressive optimization for visual studio */
+#pragma optimize("agtw", on)
+#endif
+/* ignore warnings if the compiler decides not to inline a function */
+#pragma warning(disable: 4710)
+/* fastest possible local call under MSVC */
+#define Py_LOCAL(type) static type __fastcall
+#define Py_LOCAL_INLINE(type) static __inline type __fastcall
+#else
+#define Py_LOCAL(type) static type
+#define Py_LOCAL_INLINE(type) static inline type
+#endif
+
+/* Py_MEMCPY is kept for backwards compatibility,
+ * see https://bugs.python.org/issue28126 */
+#define Py_MEMCPY memcpy
+
+#include
+
+#ifdef HAVE_IEEEFP_H
+#include /* needed for 'finite' declaration on some platforms */
+#endif
+
+#include /* Moved here from the math section, before extern "C" */
+
+/********************************************
+ * WRAPPER FOR and/or *
+ ********************************************/
+
+#ifdef TIME_WITH_SYS_TIME
+#include
+#include
+#else /* !TIME_WITH_SYS_TIME */
+#ifdef HAVE_SYS_TIME_H
+#include
+#else /* !HAVE_SYS_TIME_H */
+#include
+#endif /* !HAVE_SYS_TIME_H */
+#endif /* !TIME_WITH_SYS_TIME */
+
+
+/******************************
+ * WRAPPER FOR *
+ ******************************/
+
+/* NB caller must include */
+
+#ifdef HAVE_SYS_SELECT_H
+#include
+#endif /* !HAVE_SYS_SELECT_H */
+
+/*******************************
+ * stat() and fstat() fiddling *
+ *******************************/
+
+#ifdef HAVE_SYS_STAT_H
+#include
+#elif defined(HAVE_STAT_H)
+#include
+#endif
+
+#ifndef S_IFMT
+/* VisualAge C/C++ Failed to Define MountType Field in sys/stat.h */
+#define S_IFMT 0170000
+#endif
+
+#ifndef S_IFLNK
+/* Windows doesn't define S_IFLNK but posixmodule.c maps
+ * IO_REPARSE_TAG_SYMLINK to S_IFLNK */
+# define S_IFLNK 0120000
+#endif
+
+#ifndef S_ISREG
+#define S_ISREG(x) (((x) & S_IFMT) == S_IFREG)
+#endif
+
+#ifndef S_ISDIR
+#define S_ISDIR(x) (((x) & S_IFMT) == S_IFDIR)
+#endif
+
+#ifndef S_ISCHR
+#define S_ISCHR(x) (((x) & S_IFMT) == S_IFCHR)
+#endif
+
+#ifdef __cplusplus
+/* Move this down here since some C++ #include's don't like to be included
+ inside an extern "C" */
+extern "C" {
+#endif
+
+
+/* Py_ARITHMETIC_RIGHT_SHIFT
+ * C doesn't define whether a right-shift of a signed integer sign-extends
+ * or zero-fills. Here a macro to force sign extension:
+ * Py_ARITHMETIC_RIGHT_SHIFT(TYPE, I, J)
+ * Return I >> J, forcing sign extension. Arithmetically, return the
+ * floor of I/2**J.
+ * Requirements:
+ * I should have signed integer type. In the terminology of C99, this can
+ * be either one of the five standard signed integer types (signed char,
+ * short, int, long, long long) or an extended signed integer type.
+ * J is an integer >= 0 and strictly less than the number of bits in the
+ * type of I (because C doesn't define what happens for J outside that
+ * range either).
+ * TYPE used to specify the type of I, but is now ignored. It's been left
+ * in for backwards compatibility with versions <= 2.6 or 3.0.
+ * Caution:
+ * I may be evaluated more than once.
+ */
+#ifdef SIGNED_RIGHT_SHIFT_ZERO_FILLS
+#define Py_ARITHMETIC_RIGHT_SHIFT(TYPE, I, J) \
+ ((I) < 0 ? -1-((-1-(I)) >> (J)) : (I) >> (J))
+#else
+#define Py_ARITHMETIC_RIGHT_SHIFT(TYPE, I, J) ((I) >> (J))
+#endif
+
+/* Py_FORCE_EXPANSION(X)
+ * "Simply" returns its argument. However, macro expansions within the
+ * argument are evaluated. This unfortunate trickery is needed to get
+ * token-pasting to work as desired in some cases.
+ */
+#define Py_FORCE_EXPANSION(X) X
+
+/* Py_SAFE_DOWNCAST(VALUE, WIDE, NARROW)
+ * Cast VALUE to type NARROW from type WIDE. In Py_DEBUG mode, this
+ * assert-fails if any information is lost.
+ * Caution:
+ * VALUE may be evaluated more than once.
+ */
+#ifdef Py_DEBUG
+#define Py_SAFE_DOWNCAST(VALUE, WIDE, NARROW) \
+ (assert((WIDE)(NARROW)(VALUE) == (VALUE)), (NARROW)(VALUE))
+#else
+#define Py_SAFE_DOWNCAST(VALUE, WIDE, NARROW) (NARROW)(VALUE)
+#endif
+
+/* Py_SET_ERRNO_ON_MATH_ERROR(x)
+ * If a libm function did not set errno, but it looks like the result
+ * overflowed or not-a-number, set errno to ERANGE or EDOM. Set errno
+ * to 0 before calling a libm function, and invoke this macro after,
+ * passing the function result.
+ * Caution:
+ * This isn't reliable. See Py_OVERFLOWED comments.
+ * X is evaluated more than once.
+ */
+#if defined(__FreeBSD__) || defined(__OpenBSD__) || (defined(__hpux) && defined(__ia64))
+#define _Py_SET_EDOM_FOR_NAN(X) if (isnan(X)) errno = EDOM;
+#else
+#define _Py_SET_EDOM_FOR_NAN(X) ;
+#endif
+#define Py_SET_ERRNO_ON_MATH_ERROR(X) \
+ do { \
+ if (errno == 0) { \
+ if ((X) == Py_HUGE_VAL || (X) == -Py_HUGE_VAL) \
+ errno = ERANGE; \
+ else _Py_SET_EDOM_FOR_NAN(X) \
+ } \
+ } while(0)
+
+/* Py_SET_ERANGE_ON_OVERFLOW(x)
+ * An alias of Py_SET_ERRNO_ON_MATH_ERROR for backward-compatibility.
+ */
+#define Py_SET_ERANGE_IF_OVERFLOW(X) Py_SET_ERRNO_ON_MATH_ERROR(X)
+
+/* Py_ADJUST_ERANGE1(x)
+ * Py_ADJUST_ERANGE2(x, y)
+ * Set errno to 0 before calling a libm function, and invoke one of these
+ * macros after, passing the function result(s) (Py_ADJUST_ERANGE2 is useful
+ * for functions returning complex results). This makes two kinds of
+ * adjustments to errno: (A) If it looks like the platform libm set
+ * errno=ERANGE due to underflow, clear errno. (B) If it looks like the
+ * platform libm overflowed but didn't set errno, force errno to ERANGE. In
+ * effect, we're trying to force a useful implementation of C89 errno
+ * behavior.
+ * Caution:
+ * This isn't reliable. See Py_OVERFLOWED comments.
+ * X and Y may be evaluated more than once.
+ */
+#define Py_ADJUST_ERANGE1(X) \
+ do { \
+ if (errno == 0) { \
+ if ((X) == Py_HUGE_VAL || (X) == -Py_HUGE_VAL) \
+ errno = ERANGE; \
+ } \
+ else if (errno == ERANGE && (X) == 0.0) \
+ errno = 0; \
+ } while(0)
+
+#define Py_ADJUST_ERANGE2(X, Y) \
+ do { \
+ if ((X) == Py_HUGE_VAL || (X) == -Py_HUGE_VAL || \
+ (Y) == Py_HUGE_VAL || (Y) == -Py_HUGE_VAL) { \
+ if (errno == 0) \
+ errno = ERANGE; \
+ } \
+ else if (errno == ERANGE) \
+ errno = 0; \
+ } while(0)
+
+/* The functions _Py_dg_strtod and _Py_dg_dtoa in Python/dtoa.c (which are
+ * required to support the short float repr introduced in Python 3.1) require
+ * that the floating-point unit that's being used for arithmetic operations
+ * on C doubles is set to use 53-bit precision. It also requires that the
+ * FPU rounding mode is round-half-to-even, but that's less often an issue.
+ *
+ * If your FPU isn't already set to 53-bit precision/round-half-to-even, and
+ * you want to make use of _Py_dg_strtod and _Py_dg_dtoa, then you should
+ *
+ * #define HAVE_PY_SET_53BIT_PRECISION 1
+ *
+ * and also give appropriate definitions for the following three macros:
+ *
+ * _PY_SET_53BIT_PRECISION_START : store original FPU settings, and
+ * set FPU to 53-bit precision/round-half-to-even
+ * _PY_SET_53BIT_PRECISION_END : restore original FPU settings
+ * _PY_SET_53BIT_PRECISION_HEADER : any variable declarations needed to
+ * use the two macros above.
+ *
+ * The macros are designed to be used within a single C function: see
+ * Python/pystrtod.c for an example of their use.
+ */
+
+/* get and set x87 control word for gcc/x86 */
+#ifdef HAVE_GCC_ASM_FOR_X87
+#define HAVE_PY_SET_53BIT_PRECISION 1
+/* _Py_get/set_387controlword functions are defined in Python/pymath.c */
+#define _Py_SET_53BIT_PRECISION_HEADER \
+ unsigned short old_387controlword, new_387controlword
+#define _Py_SET_53BIT_PRECISION_START \
+ do { \
+ old_387controlword = _Py_get_387controlword(); \
+ new_387controlword = (old_387controlword & ~0x0f00) | 0x0200; \
+ if (new_387controlword != old_387controlword) \
+ _Py_set_387controlword(new_387controlword); \
+ } while (0)
+#define _Py_SET_53BIT_PRECISION_END \
+ if (new_387controlword != old_387controlword) \
+ _Py_set_387controlword(old_387controlword)
+#endif
+
+/* get and set x87 control word for VisualStudio/x86 */
+#if defined(_MSC_VER) && !defined(_WIN64) /* x87 not supported in 64-bit */
+#define HAVE_PY_SET_53BIT_PRECISION 1
+#define _Py_SET_53BIT_PRECISION_HEADER \
+ unsigned int old_387controlword, new_387controlword, out_387controlword
+/* We use the __control87_2 function to set only the x87 control word.
+ The SSE control word is unaffected. */
+#define _Py_SET_53BIT_PRECISION_START \
+ do { \
+ __control87_2(0, 0, &old_387controlword, NULL); \
+ new_387controlword = \
+ (old_387controlword & ~(_MCW_PC | _MCW_RC)) | (_PC_53 | _RC_NEAR); \
+ if (new_387controlword != old_387controlword) \
+ __control87_2(new_387controlword, _MCW_PC | _MCW_RC, \
+ &out_387controlword, NULL); \
+ } while (0)
+#define _Py_SET_53BIT_PRECISION_END \
+ do { \
+ if (new_387controlword != old_387controlword) \
+ __control87_2(old_387controlword, _MCW_PC | _MCW_RC, \
+ &out_387controlword, NULL); \
+ } while (0)
+#endif
+
+#ifdef HAVE_GCC_ASM_FOR_MC68881
+#define HAVE_PY_SET_53BIT_PRECISION 1
+#define _Py_SET_53BIT_PRECISION_HEADER \
+ unsigned int old_fpcr, new_fpcr
+#define _Py_SET_53BIT_PRECISION_START \
+ do { \
+ __asm__ ("fmove.l %%fpcr,%0" : "=g" (old_fpcr)); \
+ /* Set double precision / round to nearest. */ \
+ new_fpcr = (old_fpcr & ~0xf0) | 0x80; \
+ if (new_fpcr != old_fpcr) \
+ __asm__ volatile ("fmove.l %0,%%fpcr" : : "g" (new_fpcr)); \
+ } while (0)
+#define _Py_SET_53BIT_PRECISION_END \
+ do { \
+ if (new_fpcr != old_fpcr) \
+ __asm__ volatile ("fmove.l %0,%%fpcr" : : "g" (old_fpcr)); \
+ } while (0)
+#endif
+
+/* default definitions are empty */
+#ifndef HAVE_PY_SET_53BIT_PRECISION
+#define _Py_SET_53BIT_PRECISION_HEADER
+#define _Py_SET_53BIT_PRECISION_START
+#define _Py_SET_53BIT_PRECISION_END
+#endif
+
+/* If we can't guarantee 53-bit precision, don't use the code
+ in Python/dtoa.c, but fall back to standard code. This
+ means that repr of a float will be long (17 sig digits).
+
+ Realistically, there are two things that could go wrong:
+
+ (1) doubles aren't IEEE 754 doubles, or
+ (2) we're on x86 with the rounding precision set to 64-bits
+ (extended precision), and we don't know how to change
+ the rounding precision.
+ */
+
+#if !defined(DOUBLE_IS_LITTLE_ENDIAN_IEEE754) && \
+ !defined(DOUBLE_IS_BIG_ENDIAN_IEEE754) && \
+ !defined(DOUBLE_IS_ARM_MIXED_ENDIAN_IEEE754)
+#define PY_NO_SHORT_FLOAT_REPR
+#endif
+
+/* double rounding is symptomatic of use of extended precision on x86. If
+ we're seeing double rounding, and we don't have any mechanism available for
+ changing the FPU rounding precision, then don't use Python/dtoa.c. */
+#if defined(X87_DOUBLE_ROUNDING) && !defined(HAVE_PY_SET_53BIT_PRECISION)
+#define PY_NO_SHORT_FLOAT_REPR
+#endif
+
+
+/* Py_DEPRECATED(version)
+ * Declare a variable, type, or function deprecated.
+ * Usage:
+ * extern int old_var Py_DEPRECATED(2.3);
+ * typedef int T1 Py_DEPRECATED(2.4);
+ * extern int x() Py_DEPRECATED(2.5);
+ */
+#if defined(__GNUC__) \
+ && ((__GNUC__ >= 4) || (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1))
+#define Py_DEPRECATED(VERSION_UNUSED) __attribute__((__deprecated__))
+#else
+#define Py_DEPRECATED(VERSION_UNUSED)
+#endif
+
+
+/* _Py_HOT_FUNCTION
+ * The hot attribute on a function is used to inform the compiler that the
+ * function is a hot spot of the compiled program. The function is optimized
+ * more aggressively and on many target it is placed into special subsection of
+ * the text section so all hot functions appears close together improving
+ * locality.
+ *
+ * Usage:
+ * int _Py_HOT_FUNCTION x(void) { return 3; }
+ *
+ * Issue #28618: This attribute must not be abused, otherwise it can have a
+ * negative effect on performance. Only the functions were Python spend most of
+ * its time must use it. Use a profiler when running performance benchmark
+ * suite to find these functions.
+ */
+#if defined(__GNUC__) \
+ && ((__GNUC__ >= 5) || (__GNUC__ == 4) && (__GNUC_MINOR__ >= 3))
+#define _Py_HOT_FUNCTION __attribute__((hot))
+#else
+#define _Py_HOT_FUNCTION
+#endif
+
+/* _Py_NO_INLINE
+ * Disable inlining on a function. For example, it helps to reduce the C stack
+ * consumption.
+ *
+ * Usage:
+ * int _Py_NO_INLINE x(void) { return 3; }
+ */
+#if defined(__GNUC__) || defined(__clang__)
+# define _Py_NO_INLINE __attribute__((noinline))
+#else
+# define _Py_NO_INLINE
+#endif
+
+/**************************************************************************
+Prototypes that are missing from the standard include files on some systems
+(and possibly only some versions of such systems.)
+
+Please be conservative with adding new ones, document them and enclose them
+in platform-specific #ifdefs.
+**************************************************************************/
+
+#ifdef SOLARIS
+/* Unchecked */
+extern int gethostname(char *, int);
+#endif
+
+#ifdef HAVE__GETPTY
+#include /* we need to import mode_t */
+extern char * _getpty(int *, int, mode_t, int);
+#endif
+
+/* On QNX 6, struct termio must be declared by including sys/termio.h
+ if TCGETA, TCSETA, TCSETAW, or TCSETAF are used. sys/termio.h must
+ be included before termios.h or it will generate an error. */
+#if defined(HAVE_SYS_TERMIO_H) && !defined(__hpux)
+#include
+#endif
+
+
+/* On 4.4BSD-descendants, ctype functions serves the whole range of
+ * wchar_t character set rather than single byte code points only.
+ * This characteristic can break some operations of string object
+ * including str.upper() and str.split() on UTF-8 locales. This
+ * workaround was provided by Tim Robbins of FreeBSD project.
+ */
+
+#if defined(__APPLE__)
+# define _PY_PORT_CTYPE_UTF8_ISSUE
+#endif
+
+#ifdef _PY_PORT_CTYPE_UTF8_ISSUE
+#ifndef __cplusplus
+ /* The workaround below is unsafe in C++ because
+ * the defines these symbols as real functions,
+ * with a slightly different signature.
+ * See issue #10910
+ */
+#include
+#include
+#undef isalnum
+#define isalnum(c) iswalnum(btowc(c))
+#undef isalpha
+#define isalpha(c) iswalpha(btowc(c))
+#undef islower
+#define islower(c) iswlower(btowc(c))
+#undef isspace
+#define isspace(c) iswspace(btowc(c))
+#undef isupper
+#define isupper(c) iswupper(btowc(c))
+#undef tolower
+#define tolower(c) towlower(btowc(c))
+#undef toupper
+#define toupper(c) towupper(btowc(c))
+#endif
+#endif
+
+
+/* Declarations for symbol visibility.
+
+ PyAPI_FUNC(type): Declares a public Python API function and return type
+ PyAPI_DATA(type): Declares public Python data and its type
+ PyMODINIT_FUNC: A Python module init function. If these functions are
+ inside the Python core, they are private to the core.
+ If in an extension module, it may be declared with
+ external linkage depending on the platform.
+
+ As a number of platforms support/require "__declspec(dllimport/dllexport)",
+ we support a HAVE_DECLSPEC_DLL macro to save duplication.
+*/
+
+/*
+ All windows ports, except cygwin, are handled in PC/pyconfig.h.
+
+ Cygwin is the only other autoconf platform requiring special
+ linkage handling and it uses __declspec().
+*/
+#if defined(__CYGWIN__)
+# define HAVE_DECLSPEC_DLL
+#endif
+
+/* only get special linkage if built as shared or platform is Cygwin */
+#if defined(Py_ENABLE_SHARED) || defined(__CYGWIN__)
+# if defined(HAVE_DECLSPEC_DLL)
+# if defined(Py_BUILD_CORE) || defined(Py_BUILD_CORE_BUILTIN)
+# define PyAPI_FUNC(RTYPE) __declspec(dllexport) RTYPE
+# define PyAPI_DATA(RTYPE) extern __declspec(dllexport) RTYPE
+ /* module init functions inside the core need no external linkage */
+ /* except for Cygwin to handle embedding */
+# if defined(__CYGWIN__)
+# define PyMODINIT_FUNC __declspec(dllexport) PyObject*
+# else /* __CYGWIN__ */
+# define PyMODINIT_FUNC PyObject*
+# endif /* __CYGWIN__ */
+# else /* Py_BUILD_CORE */
+ /* Building an extension module, or an embedded situation */
+ /* public Python functions and data are imported */
+ /* Under Cygwin, auto-import functions to prevent compilation */
+ /* failures similar to those described at the bottom of 4.1: */
+ /* http://docs.python.org/extending/windows.html#a-cookbook-approach */
+# if !defined(__CYGWIN__)
+# define PyAPI_FUNC(RTYPE) __declspec(dllimport) RTYPE
+# endif /* !__CYGWIN__ */
+# define PyAPI_DATA(RTYPE) extern __declspec(dllimport) RTYPE
+ /* module init functions outside the core must be exported */
+# if defined(__cplusplus)
+# define PyMODINIT_FUNC extern "C" __declspec(dllexport) PyObject*
+# else /* __cplusplus */
+# define PyMODINIT_FUNC __declspec(dllexport) PyObject*
+# endif /* __cplusplus */
+# endif /* Py_BUILD_CORE */
+# endif /* HAVE_DECLSPEC_DLL */
+#endif /* Py_ENABLE_SHARED */
+
+/* If no external linkage macros defined by now, create defaults */
+#ifndef PyAPI_FUNC
+# define PyAPI_FUNC(RTYPE) RTYPE
+#endif
+#ifndef PyAPI_DATA
+# define PyAPI_DATA(RTYPE) extern RTYPE
+#endif
+#ifndef PyMODINIT_FUNC
+# if defined(__cplusplus)
+# define PyMODINIT_FUNC extern "C" PyObject*
+# else /* __cplusplus */
+# define PyMODINIT_FUNC PyObject*
+# endif /* __cplusplus */
+#endif
+
+/* limits.h constants that may be missing */
+
+#ifndef INT_MAX
+#define INT_MAX 2147483647
+#endif
+
+#ifndef LONG_MAX
+#if SIZEOF_LONG == 4
+#define LONG_MAX 0X7FFFFFFFL
+#elif SIZEOF_LONG == 8
+#define LONG_MAX 0X7FFFFFFFFFFFFFFFL
+#else
+#error "could not set LONG_MAX in pyport.h"
+#endif
+#endif
+
+#ifndef LONG_MIN
+#define LONG_MIN (-LONG_MAX-1)
+#endif
+
+#ifndef LONG_BIT
+#define LONG_BIT (8 * SIZEOF_LONG)
+#endif
+
+#if LONG_BIT != 8 * SIZEOF_LONG
+/* 04-Oct-2000 LONG_BIT is apparently (mis)defined as 64 on some recent
+ * 32-bit platforms using gcc. We try to catch that here at compile-time
+ * rather than waiting for integer multiplication to trigger bogus
+ * overflows.
+ */
+#error "LONG_BIT definition appears wrong for platform (bad gcc/glibc config?)."
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+/*
+ * Hide GCC attributes from compilers that don't support them.
+ */
+#if (!defined(__GNUC__) || __GNUC__ < 2 || \
+ (__GNUC__ == 2 && __GNUC_MINOR__ < 7) )
+#define Py_GCC_ATTRIBUTE(x)
+#else
+#define Py_GCC_ATTRIBUTE(x) __attribute__(x)
+#endif
+
+/*
+ * Specify alignment on compilers that support it.
+ */
+#if defined(__GNUC__) && __GNUC__ >= 3
+#define Py_ALIGNED(x) __attribute__((aligned(x)))
+#else
+#define Py_ALIGNED(x)
+#endif
+
+/* Eliminate end-of-loop code not reached warnings from SunPro C
+ * when using do{...}while(0) macros
+ */
+#ifdef __SUNPRO_C
+#pragma error_messages (off,E_END_OF_LOOP_CODE_NOT_REACHED)
+#endif
+
+#ifndef Py_LL
+#define Py_LL(x) x##LL
+#endif
+
+#ifndef Py_ULL
+#define Py_ULL(x) Py_LL(x##U)
+#endif
+
+#define Py_VA_COPY va_copy
+
+/*
+ * Convenient macros to deal with endianness of the platform. WORDS_BIGENDIAN is
+ * detected by configure and defined in pyconfig.h. The code in pyconfig.h
+ * also takes care of Apple's universal builds.
+ */
+
+#ifdef WORDS_BIGENDIAN
+#define PY_BIG_ENDIAN 1
+#define PY_LITTLE_ENDIAN 0
+#else
+#define PY_BIG_ENDIAN 0
+#define PY_LITTLE_ENDIAN 1
+#endif
+
+#if defined(Py_BUILD_CORE) || defined(Py_BUILD_CORE_BUILTIN)
+/*
+ * Macros to protect CRT calls against instant termination when passed an
+ * invalid parameter (issue23524).
+ */
+#if defined _MSC_VER && _MSC_VER >= 1900
+
+extern _invalid_parameter_handler _Py_silent_invalid_parameter_handler;
+#define _Py_BEGIN_SUPPRESS_IPH { _invalid_parameter_handler _Py_old_handler = \
+ _set_thread_local_invalid_parameter_handler(_Py_silent_invalid_parameter_handler);
+#define _Py_END_SUPPRESS_IPH _set_thread_local_invalid_parameter_handler(_Py_old_handler); }
+
+#else
+
+#define _Py_BEGIN_SUPPRESS_IPH
+#define _Py_END_SUPPRESS_IPH
+
+#endif /* _MSC_VER >= 1900 */
+#endif /* Py_BUILD_CORE */
+
+#ifdef __ANDROID__
+/* The Android langinfo.h header is not used. */
+#undef HAVE_LANGINFO_H
+#undef CODESET
+#endif
+
+/* Maximum value of the Windows DWORD type */
+#define PY_DWORD_MAX 4294967295U
+
+/* This macro used to tell whether Python was built with multithreading
+ * enabled. Now multithreading is always enabled, but keep the macro
+ * for compatibility.
+ */
+#ifndef WITH_THREAD
+#define WITH_THREAD
+#endif
+
+#endif /* Py_PYPORT_H */
diff --git a/Include/pystate.h b/Include/pystate.h
new file mode 100644
index 0000000..29d7148
--- /dev/null
+++ b/Include/pystate.h
@@ -0,0 +1,452 @@
+
+/* Thread and interpreter state structures and their interfaces */
+
+
+#ifndef Py_PYSTATE_H
+#define Py_PYSTATE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "pythread.h"
+
+/* This limitation is for performance and simplicity. If needed it can be
+removed (with effort). */
+#define MAX_CO_EXTRA_USERS 255
+
+/* State shared between threads */
+
+struct _ts; /* Forward */
+struct _is; /* Forward */
+struct _frame; /* Forward declaration for PyFrameObject. */
+
+#ifdef Py_LIMITED_API
+typedef struct _is PyInterpreterState;
+#else
+typedef PyObject* (*_PyFrameEvalFunction)(struct _frame *, int);
+
+
+typedef struct {
+ int install_signal_handlers; /* Install signal handlers? -1 means unset */
+
+ int ignore_environment; /* -E, Py_IgnoreEnvironmentFlag */
+ int use_hash_seed; /* PYTHONHASHSEED=x */
+ unsigned long hash_seed;
+ const char *allocator; /* Memory allocator: _PyMem_SetupAllocators() */
+ int dev_mode; /* PYTHONDEVMODE, -X dev */
+ int faulthandler; /* PYTHONFAULTHANDLER, -X faulthandler */
+ int tracemalloc; /* PYTHONTRACEMALLOC, -X tracemalloc=N */
+ int import_time; /* PYTHONPROFILEIMPORTTIME, -X importtime */
+ int show_ref_count; /* -X showrefcount */
+ int show_alloc_count; /* -X showalloccount */
+ int dump_refs; /* PYTHONDUMPREFS */
+ int malloc_stats; /* PYTHONMALLOCSTATS */
+ int coerce_c_locale; /* PYTHONCOERCECLOCALE, -1 means unknown */
+ int coerce_c_locale_warn; /* PYTHONCOERCECLOCALE=warn */
+ int utf8_mode; /* PYTHONUTF8, -X utf8; -1 means unknown */
+
+ wchar_t *program_name; /* Program name, see also Py_GetProgramName() */
+ int argc; /* Number of command line arguments,
+ -1 means unset */
+ wchar_t **argv; /* Command line arguments */
+ wchar_t *program; /* argv[0] or "" */
+
+ int nxoption; /* Number of -X options */
+ wchar_t **xoptions; /* -X options */
+
+ int nwarnoption; /* Number of warnings options */
+ wchar_t **warnoptions; /* Warnings options */
+
+ /* Path configuration inputs */
+ wchar_t *module_search_path_env; /* PYTHONPATH environment variable */
+ wchar_t *home; /* PYTHONHOME environment variable,
+ see also Py_SetPythonHome(). */
+
+ /* Path configuration outputs */
+ int nmodule_search_path; /* Number of sys.path paths,
+ -1 means unset */
+ wchar_t **module_search_paths; /* sys.path paths */
+ wchar_t *executable; /* sys.executable */
+ wchar_t *prefix; /* sys.prefix */
+ wchar_t *base_prefix; /* sys.base_prefix */
+ wchar_t *exec_prefix; /* sys.exec_prefix */
+ wchar_t *base_exec_prefix; /* sys.base_exec_prefix */
+
+ /* Private fields */
+ int _disable_importlib; /* Needed by freeze_importlib */
+} _PyCoreConfig;
+
+#define _PyCoreConfig_INIT \
+ (_PyCoreConfig){ \
+ .install_signal_handlers = -1, \
+ .use_hash_seed = -1, \
+ .coerce_c_locale = -1, \
+ .utf8_mode = -1, \
+ .argc = -1, \
+ .nmodule_search_path = -1}
+/* Note: _PyCoreConfig_INIT sets other fields to 0/NULL */
+
+/* Placeholders while working on the new configuration API
+ *
+ * See PEP 432 for final anticipated contents
+ */
+typedef struct {
+ int install_signal_handlers; /* Install signal handlers? -1 means unset */
+ PyObject *argv; /* sys.argv list, can be NULL */
+ PyObject *executable; /* sys.executable str */
+ PyObject *prefix; /* sys.prefix str */
+ PyObject *base_prefix; /* sys.base_prefix str, can be NULL */
+ PyObject *exec_prefix; /* sys.exec_prefix str */
+ PyObject *base_exec_prefix; /* sys.base_exec_prefix str, can be NULL */
+ PyObject *warnoptions; /* sys.warnoptions list, can be NULL */
+ PyObject *xoptions; /* sys._xoptions dict, can be NULL */
+ PyObject *module_search_path; /* sys.path list */
+} _PyMainInterpreterConfig;
+
+#define _PyMainInterpreterConfig_INIT \
+ (_PyMainInterpreterConfig){.install_signal_handlers = -1}
+/* Note: _PyMainInterpreterConfig_INIT sets other fields to 0/NULL */
+
+typedef struct _is {
+
+ struct _is *next;
+ struct _ts *tstate_head;
+
+ int64_t id;
+ int64_t id_refcount;
+ PyThread_type_lock id_mutex;
+
+ PyObject *modules;
+ PyObject *modules_by_index;
+ PyObject *sysdict;
+ PyObject *builtins;
+ PyObject *importlib;
+
+ /* Used in Python/sysmodule.c. */
+ int check_interval;
+
+ /* Used in Modules/_threadmodule.c. */
+ long num_threads;
+ /* Support for runtime thread stack size tuning.
+ A value of 0 means using the platform's default stack size
+ or the size specified by the THREAD_STACK_SIZE macro. */
+ /* Used in Python/thread.c. */
+ size_t pythread_stacksize;
+
+ PyObject *codec_search_path;
+ PyObject *codec_search_cache;
+ PyObject *codec_error_registry;
+ int codecs_initialized;
+ int fscodec_initialized;
+
+ _PyCoreConfig core_config;
+ _PyMainInterpreterConfig config;
+#ifdef HAVE_DLOPEN
+ int dlopenflags;
+#endif
+
+ PyObject *builtins_copy;
+ PyObject *import_func;
+ /* Initialized to PyEval_EvalFrameDefault(). */
+ _PyFrameEvalFunction eval_frame;
+
+ Py_ssize_t co_extra_user_count;
+ freefunc co_extra_freefuncs[MAX_CO_EXTRA_USERS];
+
+#ifdef HAVE_FORK
+ PyObject *before_forkers;
+ PyObject *after_forkers_parent;
+ PyObject *after_forkers_child;
+#endif
+ /* AtExit module */
+ void (*pyexitfunc)(PyObject *);
+ PyObject *pyexitmodule;
+
+ uint64_t tstate_next_unique_id;
+} PyInterpreterState;
+#endif /* !Py_LIMITED_API */
+
+
+/* State unique per thread */
+
+#ifndef Py_LIMITED_API
+/* Py_tracefunc return -1 when raising an exception, or 0 for success. */
+typedef int (*Py_tracefunc)(PyObject *, struct _frame *, int, PyObject *);
+
+/* The following values are used for 'what' for tracefunc functions
+ *
+ * To add a new kind of trace event, also update "trace_init" in
+ * Python/sysmodule.c to define the Python level event name
+ */
+#define PyTrace_CALL 0
+#define PyTrace_EXCEPTION 1
+#define PyTrace_LINE 2
+#define PyTrace_RETURN 3
+#define PyTrace_C_CALL 4
+#define PyTrace_C_EXCEPTION 5
+#define PyTrace_C_RETURN 6
+#define PyTrace_OPCODE 7
+#endif /* Py_LIMITED_API */
+
+#ifdef Py_LIMITED_API
+typedef struct _ts PyThreadState;
+#else
+
+typedef struct _err_stackitem {
+ /* This struct represents an entry on the exception stack, which is a
+ * per-coroutine state. (Coroutine in the computer science sense,
+ * including the thread and generators).
+ * This ensures that the exception state is not impacted by "yields"
+ * from an except handler.
+ */
+ PyObject *exc_type, *exc_value, *exc_traceback;
+
+ struct _err_stackitem *previous_item;
+
+} _PyErr_StackItem;
+
+
+typedef struct _ts {
+ /* See Python/ceval.c for comments explaining most fields */
+
+ struct _ts *prev;
+ struct _ts *next;
+ PyInterpreterState *interp;
+
+ struct _frame *frame;
+ int recursion_depth;
+ char overflowed; /* The stack has overflowed. Allow 50 more calls
+ to handle the runtime error. */
+ char recursion_critical; /* The current calls must not cause
+ a stack overflow. */
+ int stackcheck_counter;
+
+ /* 'tracing' keeps track of the execution depth when tracing/profiling.
+ This is to prevent the actual trace/profile code from being recorded in
+ the trace/profile. */
+ int tracing;
+ int use_tracing;
+
+ Py_tracefunc c_profilefunc;
+ Py_tracefunc c_tracefunc;
+ PyObject *c_profileobj;
+ PyObject *c_traceobj;
+
+ /* The exception currently being raised */
+ PyObject *curexc_type;
+ PyObject *curexc_value;
+ PyObject *curexc_traceback;
+
+ /* The exception currently being handled, if no coroutines/generators
+ * are present. Always last element on the stack referred to be exc_info.
+ */
+ _PyErr_StackItem exc_state;
+
+ /* Pointer to the top of the stack of the exceptions currently
+ * being handled */
+ _PyErr_StackItem *exc_info;
+
+ PyObject *dict; /* Stores per-thread state */
+
+ int gilstate_counter;
+
+ PyObject *async_exc; /* Asynchronous exception to raise */
+ unsigned long thread_id; /* Thread id where this tstate was created */
+
+ int trash_delete_nesting;
+ PyObject *trash_delete_later;
+
+ /* Called when a thread state is deleted normally, but not when it
+ * is destroyed after fork().
+ * Pain: to prevent rare but fatal shutdown errors (issue 18808),
+ * Thread.join() must wait for the join'ed thread's tstate to be unlinked
+ * from the tstate chain. That happens at the end of a thread's life,
+ * in pystate.c.
+ * The obvious way doesn't quite work: create a lock which the tstate
+ * unlinking code releases, and have Thread.join() wait to acquire that
+ * lock. The problem is that we _are_ at the end of the thread's life:
+ * if the thread holds the last reference to the lock, decref'ing the
+ * lock will delete the lock, and that may trigger arbitrary Python code
+ * if there's a weakref, with a callback, to the lock. But by this time
+ * _PyThreadState_Current is already NULL, so only the simplest of C code
+ * can be allowed to run (in particular it must not be possible to
+ * release the GIL).
+ * So instead of holding the lock directly, the tstate holds a weakref to
+ * the lock: that's the value of on_delete_data below. Decref'ing a
+ * weakref is harmless.
+ * on_delete points to _threadmodule.c's static release_sentinel() function.
+ * After the tstate is unlinked, release_sentinel is called with the
+ * weakref-to-lock (on_delete_data) argument, and release_sentinel releases
+ * the indirectly held lock.
+ */
+ void (*on_delete)(void *);
+ void *on_delete_data;
+
+ int coroutine_origin_tracking_depth;
+
+ PyObject *coroutine_wrapper;
+ int in_coroutine_wrapper;
+
+ PyObject *async_gen_firstiter;
+ PyObject *async_gen_finalizer;
+
+ PyObject *context;
+ uint64_t context_ver;
+
+ /* Unique thread state id. */
+ uint64_t id;
+
+ /* XXX signal handlers should also be here */
+
+} PyThreadState;
+#endif /* !Py_LIMITED_API */
+
+
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_New(void);
+PyAPI_FUNC(void) PyInterpreterState_Clear(PyInterpreterState *);
+PyAPI_FUNC(void) PyInterpreterState_Delete(PyInterpreterState *);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
+/* New in 3.7 */
+PyAPI_FUNC(int64_t) PyInterpreterState_GetID(PyInterpreterState *);
+#endif
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyState_AddModule(PyObject*, struct PyModuleDef*);
+#endif /* !Py_LIMITED_API */
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+/* New in 3.3 */
+PyAPI_FUNC(int) PyState_AddModule(PyObject*, struct PyModuleDef*);
+PyAPI_FUNC(int) PyState_RemoveModule(struct PyModuleDef*);
+#endif
+PyAPI_FUNC(PyObject*) PyState_FindModule(struct PyModuleDef*);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyState_ClearModules(void);
+#endif
+
+PyAPI_FUNC(PyThreadState *) PyThreadState_New(PyInterpreterState *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyThreadState *) _PyThreadState_Prealloc(PyInterpreterState *);
+PyAPI_FUNC(void) _PyThreadState_Init(PyThreadState *);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(void) PyThreadState_Clear(PyThreadState *);
+PyAPI_FUNC(void) PyThreadState_Delete(PyThreadState *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyThreadState_DeleteExcept(PyThreadState *tstate);
+#endif /* !Py_LIMITED_API */
+PyAPI_FUNC(void) PyThreadState_DeleteCurrent(void);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyGILState_Reinit(void);
+#endif /* !Py_LIMITED_API */
+
+/* Return the current thread state. The global interpreter lock must be held.
+ * When the current thread state is NULL, this issues a fatal error (so that
+ * the caller needn't check for NULL). */
+PyAPI_FUNC(PyThreadState *) PyThreadState_Get(void);
+
+#ifndef Py_LIMITED_API
+/* Similar to PyThreadState_Get(), but don't issue a fatal error
+ * if it is NULL. */
+PyAPI_FUNC(PyThreadState *) _PyThreadState_UncheckedGet(void);
+#endif /* !Py_LIMITED_API */
+
+PyAPI_FUNC(PyThreadState *) PyThreadState_Swap(PyThreadState *);
+PyAPI_FUNC(PyObject *) PyThreadState_GetDict(void);
+PyAPI_FUNC(int) PyThreadState_SetAsyncExc(unsigned long, PyObject *);
+
+
+/* Variable and macro for in-line access to current thread state */
+
+/* Assuming the current thread holds the GIL, this is the
+ PyThreadState for the current thread. */
+#ifdef Py_BUILD_CORE
+# define _PyThreadState_Current _PyRuntime.gilstate.tstate_current
+# define PyThreadState_GET() \
+ ((PyThreadState*)_Py_atomic_load_relaxed(&_PyThreadState_Current))
+#else
+# define PyThreadState_GET() PyThreadState_Get()
+#endif
+
+typedef
+ enum {PyGILState_LOCKED, PyGILState_UNLOCKED}
+ PyGILState_STATE;
+
+
+/* Ensure that the current thread is ready to call the Python
+ C API, regardless of the current state of Python, or of its
+ thread lock. This may be called as many times as desired
+ by a thread so long as each call is matched with a call to
+ PyGILState_Release(). In general, other thread-state APIs may
+ be used between _Ensure() and _Release() calls, so long as the
+ thread-state is restored to its previous state before the Release().
+ For example, normal use of the Py_BEGIN_ALLOW_THREADS/
+ Py_END_ALLOW_THREADS macros are acceptable.
+
+ The return value is an opaque "handle" to the thread state when
+ PyGILState_Ensure() was called, and must be passed to
+ PyGILState_Release() to ensure Python is left in the same state. Even
+ though recursive calls are allowed, these handles can *not* be shared -
+ each unique call to PyGILState_Ensure must save the handle for its
+ call to PyGILState_Release.
+
+ When the function returns, the current thread will hold the GIL.
+
+ Failure is a fatal error.
+*/
+PyAPI_FUNC(PyGILState_STATE) PyGILState_Ensure(void);
+
+/* Release any resources previously acquired. After this call, Python's
+ state will be the same as it was prior to the corresponding
+ PyGILState_Ensure() call (but generally this state will be unknown to
+ the caller, hence the use of the GILState API.)
+
+ Every call to PyGILState_Ensure must be matched by a call to
+ PyGILState_Release on the same thread.
+*/
+PyAPI_FUNC(void) PyGILState_Release(PyGILState_STATE);
+
+/* Helper/diagnostic function - get the current thread state for
+ this thread. May return NULL if no GILState API has been used
+ on the current thread. Note that the main thread always has such a
+ thread-state, even if no auto-thread-state call has been made
+ on the main thread.
+*/
+PyAPI_FUNC(PyThreadState *) PyGILState_GetThisThreadState(void);
+
+#ifndef Py_LIMITED_API
+/* Helper/diagnostic function - return 1 if the current thread
+ currently holds the GIL, 0 otherwise.
+
+ The function returns 1 if _PyGILState_check_enabled is non-zero. */
+PyAPI_FUNC(int) PyGILState_Check(void);
+
+/* Unsafe function to get the single PyInterpreterState used by this process'
+ GILState implementation.
+
+ Return NULL before _PyGILState_Init() is called and after _PyGILState_Fini()
+ is called. */
+PyAPI_FUNC(PyInterpreterState *) _PyGILState_GetInterpreterStateUnsafe(void);
+#endif /* !Py_LIMITED_API */
+
+
+/* The implementation of sys._current_frames() Returns a dict mapping
+ thread id to that thread's current frame.
+*/
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyThread_CurrentFrames(void);
+#endif
+
+/* Routines for advanced debuggers, requested by David Beazley.
+ Don't use unless you know what you are doing! */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_Main(void);
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_Head(void);
+PyAPI_FUNC(PyInterpreterState *) PyInterpreterState_Next(PyInterpreterState *);
+PyAPI_FUNC(PyThreadState *) PyInterpreterState_ThreadHead(PyInterpreterState *);
+PyAPI_FUNC(PyThreadState *) PyThreadState_Next(PyThreadState *);
+
+typedef struct _frame *(*PyThreadFrameGetter)(PyThreadState *self_);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PYSTATE_H */
diff --git a/Include/pystrcmp.h b/Include/pystrcmp.h
new file mode 100644
index 0000000..edb1239
--- /dev/null
+++ b/Include/pystrcmp.h
@@ -0,0 +1,23 @@
+#ifndef Py_STRCMP_H
+#define Py_STRCMP_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(int) PyOS_mystrnicmp(const char *, const char *, Py_ssize_t);
+PyAPI_FUNC(int) PyOS_mystricmp(const char *, const char *);
+
+#ifdef MS_WINDOWS
+#define PyOS_strnicmp strnicmp
+#define PyOS_stricmp stricmp
+#else
+#define PyOS_strnicmp PyOS_mystrnicmp
+#define PyOS_stricmp PyOS_mystricmp
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_STRCMP_H */
diff --git a/Include/pystrhex.h b/Include/pystrhex.h
new file mode 100644
index 0000000..66a30e2
--- /dev/null
+++ b/Include/pystrhex.h
@@ -0,0 +1,19 @@
+#ifndef Py_STRHEX_H
+#define Py_STRHEX_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+/* Returns a str() containing the hex representation of argbuf. */
+PyAPI_FUNC(PyObject*) _Py_strhex(const char* argbuf, const Py_ssize_t arglen);
+/* Returns a bytes() containing the ASCII hex representation of argbuf. */
+PyAPI_FUNC(PyObject*) _Py_strhex_bytes(const char* argbuf, const Py_ssize_t arglen);
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_STRHEX_H */
diff --git a/Include/pystrtod.h b/Include/pystrtod.h
new file mode 100644
index 0000000..c1e84de
--- /dev/null
+++ b/Include/pystrtod.h
@@ -0,0 +1,45 @@
+#ifndef Py_STRTOD_H
+#define Py_STRTOD_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+PyAPI_FUNC(double) PyOS_string_to_double(const char *str,
+ char **endptr,
+ PyObject *overflow_exception);
+
+/* The caller is responsible for calling PyMem_Free to free the buffer
+ that's is returned. */
+PyAPI_FUNC(char *) PyOS_double_to_string(double val,
+ char format_code,
+ int precision,
+ int flags,
+ int *type);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _Py_string_to_number_with_underscores(
+ const char *str, Py_ssize_t len, const char *what, PyObject *obj, void *arg,
+ PyObject *(*innerfunc)(const char *, Py_ssize_t, void *));
+
+PyAPI_FUNC(double) _Py_parse_inf_or_nan(const char *p, char **endptr);
+#endif
+
+
+/* PyOS_double_to_string's "flags" parameter can be set to 0 or more of: */
+#define Py_DTSF_SIGN 0x01 /* always add the sign */
+#define Py_DTSF_ADD_DOT_0 0x02 /* if the result is an integer add ".0" */
+#define Py_DTSF_ALT 0x04 /* "alternate" formatting. it's format_code
+ specific */
+
+/* PyOS_double_to_string's "type", if non-NULL, will be set to one of: */
+#define Py_DTST_FINITE 0
+#define Py_DTST_INFINITE 1
+#define Py_DTST_NAN 2
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_STRTOD_H */
diff --git a/Include/pythonrun.h b/Include/pythonrun.h
new file mode 100644
index 0000000..6f0c6fc
--- /dev/null
+++ b/Include/pythonrun.h
@@ -0,0 +1,181 @@
+
+/* Interfaces to parse and execute pieces of python code */
+
+#ifndef Py_PYTHONRUN_H
+#define Py_PYTHONRUN_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) PyRun_SimpleStringFlags(const char *, PyCompilerFlags *);
+PyAPI_FUNC(int) PyRun_AnyFileFlags(FILE *, const char *, PyCompilerFlags *);
+PyAPI_FUNC(int) PyRun_AnyFileExFlags(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ int closeit,
+ PyCompilerFlags *flags);
+PyAPI_FUNC(int) PyRun_SimpleFileExFlags(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ int closeit,
+ PyCompilerFlags *flags);
+PyAPI_FUNC(int) PyRun_InteractiveOneFlags(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ PyCompilerFlags *flags);
+PyAPI_FUNC(int) PyRun_InteractiveOneObject(
+ FILE *fp,
+ PyObject *filename,
+ PyCompilerFlags *flags);
+PyAPI_FUNC(int) PyRun_InteractiveLoopFlags(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ PyCompilerFlags *flags);
+
+PyAPI_FUNC(struct _mod *) PyParser_ASTFromString(
+ const char *s,
+ const char *filename, /* decoded from the filesystem encoding */
+ int start,
+ PyCompilerFlags *flags,
+ PyArena *arena);
+PyAPI_FUNC(struct _mod *) PyParser_ASTFromStringObject(
+ const char *s,
+ PyObject *filename,
+ int start,
+ PyCompilerFlags *flags,
+ PyArena *arena);
+PyAPI_FUNC(struct _mod *) PyParser_ASTFromFile(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ const char* enc,
+ int start,
+ const char *ps1,
+ const char *ps2,
+ PyCompilerFlags *flags,
+ int *errcode,
+ PyArena *arena);
+PyAPI_FUNC(struct _mod *) PyParser_ASTFromFileObject(
+ FILE *fp,
+ PyObject *filename,
+ const char* enc,
+ int start,
+ const char *ps1,
+ const char *ps2,
+ PyCompilerFlags *flags,
+ int *errcode,
+ PyArena *arena);
+#endif
+
+#ifndef PyParser_SimpleParseString
+#define PyParser_SimpleParseString(S, B) \
+ PyParser_SimpleParseStringFlags(S, B, 0)
+#define PyParser_SimpleParseFile(FP, S, B) \
+ PyParser_SimpleParseFileFlags(FP, S, B, 0)
+#endif
+PyAPI_FUNC(struct _node *) PyParser_SimpleParseStringFlags(const char *, int,
+ int);
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(struct _node *) PyParser_SimpleParseStringFlagsFilename(const char *,
+ const char *,
+ int, int);
+#endif
+PyAPI_FUNC(struct _node *) PyParser_SimpleParseFileFlags(FILE *, const char *,
+ int, int);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyRun_StringFlags(const char *, int, PyObject *,
+ PyObject *, PyCompilerFlags *);
+
+PyAPI_FUNC(PyObject *) PyRun_FileExFlags(
+ FILE *fp,
+ const char *filename, /* decoded from the filesystem encoding */
+ int start,
+ PyObject *globals,
+ PyObject *locals,
+ int closeit,
+ PyCompilerFlags *flags);
+#endif
+
+#ifdef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) Py_CompileString(const char *, const char *, int);
+#else
+#define Py_CompileString(str, p, s) Py_CompileStringExFlags(str, p, s, NULL, -1)
+#define Py_CompileStringFlags(str, p, s, f) Py_CompileStringExFlags(str, p, s, f, -1)
+PyAPI_FUNC(PyObject *) Py_CompileStringExFlags(
+ const char *str,
+ const char *filename, /* decoded from the filesystem encoding */
+ int start,
+ PyCompilerFlags *flags,
+ int optimize);
+PyAPI_FUNC(PyObject *) Py_CompileStringObject(
+ const char *str,
+ PyObject *filename, int start,
+ PyCompilerFlags *flags,
+ int optimize);
+#endif
+PyAPI_FUNC(struct symtable *) Py_SymtableString(
+ const char *str,
+ const char *filename, /* decoded from the filesystem encoding */
+ int start);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(struct symtable *) Py_SymtableStringObject(
+ const char *str,
+ PyObject *filename,
+ int start);
+#endif
+
+PyAPI_FUNC(void) PyErr_Print(void);
+PyAPI_FUNC(void) PyErr_PrintEx(int);
+PyAPI_FUNC(void) PyErr_Display(PyObject *, PyObject *, PyObject *);
+
+#ifndef Py_LIMITED_API
+/* Use macros for a bunch of old variants */
+#define PyRun_String(str, s, g, l) PyRun_StringFlags(str, s, g, l, NULL)
+#define PyRun_AnyFile(fp, name) PyRun_AnyFileExFlags(fp, name, 0, NULL)
+#define PyRun_AnyFileEx(fp, name, closeit) \
+ PyRun_AnyFileExFlags(fp, name, closeit, NULL)
+#define PyRun_AnyFileFlags(fp, name, flags) \
+ PyRun_AnyFileExFlags(fp, name, 0, flags)
+#define PyRun_SimpleString(s) PyRun_SimpleStringFlags(s, NULL)
+#define PyRun_SimpleFile(f, p) PyRun_SimpleFileExFlags(f, p, 0, NULL)
+#define PyRun_SimpleFileEx(f, p, c) PyRun_SimpleFileExFlags(f, p, c, NULL)
+#define PyRun_InteractiveOne(f, p) PyRun_InteractiveOneFlags(f, p, NULL)
+#define PyRun_InteractiveLoop(f, p) PyRun_InteractiveLoopFlags(f, p, NULL)
+#define PyRun_File(fp, p, s, g, l) \
+ PyRun_FileExFlags(fp, p, s, g, l, 0, NULL)
+#define PyRun_FileEx(fp, p, s, g, l, c) \
+ PyRun_FileExFlags(fp, p, s, g, l, c, NULL)
+#define PyRun_FileFlags(fp, p, s, g, l, flags) \
+ PyRun_FileExFlags(fp, p, s, g, l, 0, flags)
+#endif
+
+/* Stuff with no proper home (yet) */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(char *) PyOS_Readline(FILE *, FILE *, const char *);
+#endif
+PyAPI_DATA(int) (*PyOS_InputHook)(void);
+PyAPI_DATA(char) *(*PyOS_ReadlineFunctionPointer)(FILE *, FILE *, const char *);
+#ifndef Py_LIMITED_API
+PyAPI_DATA(PyThreadState*) _PyOS_ReadlineTState;
+#endif
+
+/* Stack size, in "pointers" (so we get extra safety margins
+ on 64-bit platforms). On a 32-bit platform, this translates
+ to an 8k margin. */
+#define PYOS_STACK_MARGIN 2048
+
+#if defined(WIN32) && !defined(MS_WIN64) && defined(_MSC_VER) && _MSC_VER >= 1300
+/* Enable stack checking under Microsoft C */
+#define USE_STACKCHECK
+#endif
+
+#ifdef USE_STACKCHECK
+/* Check that we aren't overflowing our stack */
+PyAPI_FUNC(int) PyOS_CheckStack(void);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_PYTHONRUN_H */
diff --git a/Include/pythread.h b/Include/pythread.h
new file mode 100644
index 0000000..eb61033
--- /dev/null
+++ b/Include/pythread.h
@@ -0,0 +1,155 @@
+
+#ifndef Py_PYTHREAD_H
+#define Py_PYTHREAD_H
+
+typedef void *PyThread_type_lock;
+typedef void *PyThread_type_sema;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Return status codes for Python lock acquisition. Chosen for maximum
+ * backwards compatibility, ie failure -> 0, success -> 1. */
+typedef enum PyLockStatus {
+ PY_LOCK_FAILURE = 0,
+ PY_LOCK_ACQUIRED = 1,
+ PY_LOCK_INTR
+} PyLockStatus;
+
+#ifndef Py_LIMITED_API
+#define PYTHREAD_INVALID_THREAD_ID ((unsigned long)-1)
+#endif
+
+PyAPI_FUNC(void) PyThread_init_thread(void);
+PyAPI_FUNC(unsigned long) PyThread_start_new_thread(void (*)(void *), void *);
+PyAPI_FUNC(void) PyThread_exit_thread(void);
+PyAPI_FUNC(unsigned long) PyThread_get_thread_ident(void);
+
+PyAPI_FUNC(PyThread_type_lock) PyThread_allocate_lock(void);
+PyAPI_FUNC(void) PyThread_free_lock(PyThread_type_lock);
+PyAPI_FUNC(int) PyThread_acquire_lock(PyThread_type_lock, int);
+#define WAIT_LOCK 1
+#define NOWAIT_LOCK 0
+
+/* PY_TIMEOUT_T is the integral type used to specify timeouts when waiting
+ on a lock (see PyThread_acquire_lock_timed() below).
+ PY_TIMEOUT_MAX is the highest usable value (in microseconds) of that
+ type, and depends on the system threading API.
+
+ NOTE: this isn't the same value as `_thread.TIMEOUT_MAX`. The _thread
+ module exposes a higher-level API, with timeouts expressed in seconds
+ and floating-point numbers allowed.
+*/
+#define PY_TIMEOUT_T long long
+
+#if defined(_POSIX_THREADS)
+ /* PyThread_acquire_lock_timed() uses _PyTime_FromNanoseconds(us * 1000),
+ convert microseconds to nanoseconds. */
+# define PY_TIMEOUT_MAX (PY_LLONG_MAX / 1000)
+#elif defined (NT_THREADS)
+ /* In the NT API, the timeout is a DWORD and is expressed in milliseconds */
+# if 0xFFFFFFFFLL * 1000 < PY_LLONG_MAX
+# define PY_TIMEOUT_MAX (0xFFFFFFFFLL * 1000)
+# else
+# define PY_TIMEOUT_MAX PY_LLONG_MAX
+# endif
+#else
+# define PY_TIMEOUT_MAX PY_LLONG_MAX
+#endif
+
+
+/* If microseconds == 0, the call is non-blocking: it returns immediately
+ even when the lock can't be acquired.
+ If microseconds > 0, the call waits up to the specified duration.
+ If microseconds < 0, the call waits until success (or abnormal failure)
+
+ microseconds must be less than PY_TIMEOUT_MAX. Behaviour otherwise is
+ undefined.
+
+ If intr_flag is true and the acquire is interrupted by a signal, then the
+ call will return PY_LOCK_INTR. The caller may reattempt to acquire the
+ lock.
+*/
+PyAPI_FUNC(PyLockStatus) PyThread_acquire_lock_timed(PyThread_type_lock,
+ PY_TIMEOUT_T microseconds,
+ int intr_flag);
+
+PyAPI_FUNC(void) PyThread_release_lock(PyThread_type_lock);
+
+PyAPI_FUNC(size_t) PyThread_get_stacksize(void);
+PyAPI_FUNC(int) PyThread_set_stacksize(size_t);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject*) PyThread_GetInfo(void);
+#endif
+
+
+/* Thread Local Storage (TLS) API
+ TLS API is DEPRECATED. Use Thread Specific Storage (TSS) API.
+
+ The existing TLS API has used int to represent TLS keys across all
+ platforms, but it is not POSIX-compliant. Therefore, the new TSS API uses
+ opaque data type to represent TSS keys to be compatible (see PEP 539).
+*/
+PyAPI_FUNC(int) PyThread_create_key(void) Py_DEPRECATED(3.7);
+PyAPI_FUNC(void) PyThread_delete_key(int key) Py_DEPRECATED(3.7);
+PyAPI_FUNC(int) PyThread_set_key_value(int key, void *value) Py_DEPRECATED(3.7);
+PyAPI_FUNC(void *) PyThread_get_key_value(int key) Py_DEPRECATED(3.7);
+PyAPI_FUNC(void) PyThread_delete_key_value(int key) Py_DEPRECATED(3.7);
+
+/* Cleanup after a fork */
+PyAPI_FUNC(void) PyThread_ReInitTLS(void) Py_DEPRECATED(3.7);
+
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03070000
+/* New in 3.7 */
+/* Thread Specific Storage (TSS) API */
+
+typedef struct _Py_tss_t Py_tss_t; /* opaque */
+
+#ifndef Py_LIMITED_API
+#if defined(_POSIX_THREADS)
+ /* Darwin needs pthread.h to know type name the pthread_key_t. */
+# include
+# define NATIVE_TSS_KEY_T pthread_key_t
+#elif defined(NT_THREADS)
+ /* In Windows, native TSS key type is DWORD,
+ but hardcode the unsigned long to avoid errors for include directive.
+ */
+# define NATIVE_TSS_KEY_T unsigned long
+#else
+# error "Require native threads. See https://bugs.python.org/issue31370"
+#endif
+
+/* When Py_LIMITED_API is not defined, the type layout of Py_tss_t is
+ exposed to allow static allocation in the API clients. Even in this case,
+ you must handle TSS keys through API functions due to compatibility.
+*/
+struct _Py_tss_t {
+ int _is_initialized;
+ NATIVE_TSS_KEY_T _key;
+};
+
+#undef NATIVE_TSS_KEY_T
+
+/* When static allocation, you must initialize with Py_tss_NEEDS_INIT. */
+#define Py_tss_NEEDS_INIT {0}
+#endif /* !Py_LIMITED_API */
+
+PyAPI_FUNC(Py_tss_t *) PyThread_tss_alloc(void);
+PyAPI_FUNC(void) PyThread_tss_free(Py_tss_t *key);
+
+/* The parameter key must not be NULL. */
+PyAPI_FUNC(int) PyThread_tss_is_created(Py_tss_t *key);
+PyAPI_FUNC(int) PyThread_tss_create(Py_tss_t *key);
+PyAPI_FUNC(void) PyThread_tss_delete(Py_tss_t *key);
+PyAPI_FUNC(int) PyThread_tss_set(Py_tss_t *key, void *value);
+PyAPI_FUNC(void *) PyThread_tss_get(Py_tss_t *key);
+#endif /* New in 3.7 */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* !Py_PYTHREAD_H */
diff --git a/Include/pytime.h b/Include/pytime.h
new file mode 100644
index 0000000..4870a9d
--- /dev/null
+++ b/Include/pytime.h
@@ -0,0 +1,246 @@
+#ifndef Py_LIMITED_API
+#ifndef Py_PYTIME_H
+#define Py_PYTIME_H
+
+#include "pyconfig.h" /* include for defines */
+#include "object.h"
+
+/**************************************************************************
+Symbols and macros to supply platform-independent interfaces to time related
+functions and constants
+**************************************************************************/
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* _PyTime_t: Python timestamp with subsecond precision. It can be used to
+ store a duration, and so indirectly a date (related to another date, like
+ UNIX epoch). */
+typedef int64_t _PyTime_t;
+#define _PyTime_MIN PY_LLONG_MIN
+#define _PyTime_MAX PY_LLONG_MAX
+
+typedef enum {
+ /* Round towards minus infinity (-inf).
+ For example, used to read a clock. */
+ _PyTime_ROUND_FLOOR=0,
+ /* Round towards infinity (+inf).
+ For example, used for timeout to wait "at least" N seconds. */
+ _PyTime_ROUND_CEILING=1,
+ /* Round to nearest with ties going to nearest even integer.
+ For example, used to round from a Python float. */
+ _PyTime_ROUND_HALF_EVEN=2,
+ /* Round away from zero
+ For example, used for timeout. _PyTime_ROUND_CEILING rounds
+ -1e-9 to 0 milliseconds which causes bpo-31786 issue.
+ _PyTime_ROUND_UP rounds -1e-9 to -1 millisecond which keeps
+ the timeout sign as expected. select.poll(timeout) must block
+ for negative values." */
+ _PyTime_ROUND_UP=3,
+ /* _PyTime_ROUND_TIMEOUT (an alias for _PyTime_ROUND_UP) should be
+ used for timeouts. */
+ _PyTime_ROUND_TIMEOUT = _PyTime_ROUND_UP
+} _PyTime_round_t;
+
+
+/* Convert a time_t to a PyLong. */
+PyAPI_FUNC(PyObject *) _PyLong_FromTime_t(
+ time_t sec);
+
+/* Convert a PyLong to a time_t. */
+PyAPI_FUNC(time_t) _PyLong_AsTime_t(
+ PyObject *obj);
+
+/* Convert a number of seconds, int or float, to time_t. */
+PyAPI_FUNC(int) _PyTime_ObjectToTime_t(
+ PyObject *obj,
+ time_t *sec,
+ _PyTime_round_t);
+
+/* Convert a number of seconds, int or float, to a timeval structure.
+ usec is in the range [0; 999999] and rounded towards zero.
+ For example, -1.2 is converted to (-2, 800000). */
+PyAPI_FUNC(int) _PyTime_ObjectToTimeval(
+ PyObject *obj,
+ time_t *sec,
+ long *usec,
+ _PyTime_round_t);
+
+/* Convert a number of seconds, int or float, to a timespec structure.
+ nsec is in the range [0; 999999999] and rounded towards zero.
+ For example, -1.2 is converted to (-2, 800000000). */
+PyAPI_FUNC(int) _PyTime_ObjectToTimespec(
+ PyObject *obj,
+ time_t *sec,
+ long *nsec,
+ _PyTime_round_t);
+
+
+/* Create a timestamp from a number of seconds. */
+PyAPI_FUNC(_PyTime_t) _PyTime_FromSeconds(int seconds);
+
+/* Macro to create a timestamp from a number of seconds, no integer overflow.
+ Only use the macro for small values, prefer _PyTime_FromSeconds(). */
+#define _PYTIME_FROMSECONDS(seconds) \
+ ((_PyTime_t)(seconds) * (1000 * 1000 * 1000))
+
+/* Create a timestamp from a number of nanoseconds. */
+PyAPI_FUNC(_PyTime_t) _PyTime_FromNanoseconds(_PyTime_t ns);
+
+/* Create a timestamp from nanoseconds (Python int). */
+PyAPI_FUNC(int) _PyTime_FromNanosecondsObject(_PyTime_t *t,
+ PyObject *obj);
+
+/* Convert a number of seconds (Python float or int) to a timetamp.
+ Raise an exception and return -1 on error, return 0 on success. */
+PyAPI_FUNC(int) _PyTime_FromSecondsObject(_PyTime_t *t,
+ PyObject *obj,
+ _PyTime_round_t round);
+
+/* Convert a number of milliseconds (Python float or int, 10^-3) to a timetamp.
+ Raise an exception and return -1 on error, return 0 on success. */
+PyAPI_FUNC(int) _PyTime_FromMillisecondsObject(_PyTime_t *t,
+ PyObject *obj,
+ _PyTime_round_t round);
+
+/* Convert a timestamp to a number of seconds as a C double. */
+PyAPI_FUNC(double) _PyTime_AsSecondsDouble(_PyTime_t t);
+
+/* Convert timestamp to a number of milliseconds (10^-3 seconds). */
+PyAPI_FUNC(_PyTime_t) _PyTime_AsMilliseconds(_PyTime_t t,
+ _PyTime_round_t round);
+
+/* Convert timestamp to a number of microseconds (10^-6 seconds). */
+PyAPI_FUNC(_PyTime_t) _PyTime_AsMicroseconds(_PyTime_t t,
+ _PyTime_round_t round);
+
+/* Convert timestamp to a number of nanoseconds (10^-9 seconds) as a Python int
+ object. */
+PyAPI_FUNC(PyObject *) _PyTime_AsNanosecondsObject(_PyTime_t t);
+
+/* Create a timestamp from a timeval structure.
+ Raise an exception and return -1 on overflow, return 0 on success. */
+PyAPI_FUNC(int) _PyTime_FromTimeval(_PyTime_t *tp, struct timeval *tv);
+
+/* Convert a timestamp to a timeval structure (microsecond resolution).
+ tv_usec is always positive.
+ Raise an exception and return -1 if the conversion overflowed,
+ return 0 on success. */
+PyAPI_FUNC(int) _PyTime_AsTimeval(_PyTime_t t,
+ struct timeval *tv,
+ _PyTime_round_t round);
+
+/* Similar to _PyTime_AsTimeval(), but don't raise an exception on error. */
+PyAPI_FUNC(int) _PyTime_AsTimeval_noraise(_PyTime_t t,
+ struct timeval *tv,
+ _PyTime_round_t round);
+
+/* Convert a timestamp to a number of seconds (secs) and microseconds (us).
+ us is always positive. This function is similar to _PyTime_AsTimeval()
+ except that secs is always a time_t type, whereas the timeval structure
+ uses a C long for tv_sec on Windows.
+ Raise an exception and return -1 if the conversion overflowed,
+ return 0 on success. */
+PyAPI_FUNC(int) _PyTime_AsTimevalTime_t(
+ _PyTime_t t,
+ time_t *secs,
+ int *us,
+ _PyTime_round_t round);
+
+#if defined(HAVE_CLOCK_GETTIME) || defined(HAVE_KQUEUE)
+/* Create a timestamp from a timespec structure.
+ Raise an exception and return -1 on overflow, return 0 on success. */
+PyAPI_FUNC(int) _PyTime_FromTimespec(_PyTime_t *tp, struct timespec *ts);
+
+/* Convert a timestamp to a timespec structure (nanosecond resolution).
+ tv_nsec is always positive.
+ Raise an exception and return -1 on error, return 0 on success. */
+PyAPI_FUNC(int) _PyTime_AsTimespec(_PyTime_t t, struct timespec *ts);
+#endif
+
+/* Compute ticks * mul / div.
+ The caller must ensure that ((div - 1) * mul) cannot overflow. */
+PyAPI_FUNC(_PyTime_t) _PyTime_MulDiv(_PyTime_t ticks,
+ _PyTime_t mul,
+ _PyTime_t div);
+
+/* Get the current time from the system clock.
+
+ The function cannot fail. _PyTime_Init() ensures that the system clock
+ works. */
+PyAPI_FUNC(_PyTime_t) _PyTime_GetSystemClock(void);
+
+/* Get the time of a monotonic clock, i.e. a clock that cannot go backwards.
+ The clock is not affected by system clock updates. The reference point of
+ the returned value is undefined, so that only the difference between the
+ results of consecutive calls is valid.
+
+ The function cannot fail. _PyTime_Init() ensures that a monotonic clock
+ is available and works. */
+PyAPI_FUNC(_PyTime_t) _PyTime_GetMonotonicClock(void);
+
+
+/* Structure used by time.get_clock_info() */
+typedef struct {
+ const char *implementation;
+ int monotonic;
+ int adjustable;
+ double resolution;
+} _Py_clock_info_t;
+
+/* Get the current time from the system clock.
+ * Fill clock information if info is not NULL.
+ * Raise an exception and return -1 on error, return 0 on success.
+ */
+PyAPI_FUNC(int) _PyTime_GetSystemClockWithInfo(
+ _PyTime_t *t,
+ _Py_clock_info_t *info);
+
+/* Get the time of a monotonic clock, i.e. a clock that cannot go backwards.
+ The clock is not affected by system clock updates. The reference point of
+ the returned value is undefined, so that only the difference between the
+ results of consecutive calls is valid.
+
+ Fill info (if set) with information of the function used to get the time.
+
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int) _PyTime_GetMonotonicClockWithInfo(
+ _PyTime_t *t,
+ _Py_clock_info_t *info);
+
+
+/* Initialize time.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int) _PyTime_Init(void);
+
+/* Converts a timestamp to the Gregorian time, using the local time zone.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int) _PyTime_localtime(time_t t, struct tm *tm);
+
+/* Converts a timestamp to the Gregorian time, assuming UTC.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int) _PyTime_gmtime(time_t t, struct tm *tm);
+
+/* Get the performance counter: clock with the highest available resolution to
+ measure a short duration.
+
+ The function cannot fail. _PyTime_Init() ensures that the system clock
+ works. */
+PyAPI_FUNC(_PyTime_t) _PyTime_GetPerfCounter(void);
+
+/* Get the performance counter: clock with the highest available resolution to
+ measure a short duration.
+
+ Fill info (if set) with information of the function used to get the time.
+
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int) _PyTime_GetPerfCounterWithInfo(
+ _PyTime_t *t,
+ _Py_clock_info_t *info);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* Py_PYTIME_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/rangeobject.h b/Include/rangeobject.h
new file mode 100644
index 0000000..7e4dc28
--- /dev/null
+++ b/Include/rangeobject.h
@@ -0,0 +1,27 @@
+
+/* Range object interface */
+
+#ifndef Py_RANGEOBJECT_H
+#define Py_RANGEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+A range object represents an integer range. This is an immutable object;
+a range cannot change its value after creation.
+
+Range objects behave like the corresponding tuple objects except that
+they are represented by a start, stop, and step datamembers.
+*/
+
+PyAPI_DATA(PyTypeObject) PyRange_Type;
+PyAPI_DATA(PyTypeObject) PyRangeIter_Type;
+PyAPI_DATA(PyTypeObject) PyLongRangeIter_Type;
+
+#define PyRange_Check(op) (Py_TYPE(op) == &PyRange_Type)
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_RANGEOBJECT_H */
diff --git a/Include/setobject.h b/Include/setobject.h
new file mode 100644
index 0000000..fc0ea83
--- /dev/null
+++ b/Include/setobject.h
@@ -0,0 +1,108 @@
+/* Set object interface */
+
+#ifndef Py_SETOBJECT_H
+#define Py_SETOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+
+/* There are three kinds of entries in the table:
+
+1. Unused: key == NULL and hash == 0
+2. Dummy: key == dummy and hash == -1
+3. Active: key != NULL and key != dummy and hash != -1
+
+The hash field of Unused slots is always zero.
+
+The hash field of Dummy slots are set to -1
+meaning that dummy entries can be detected by
+either entry->key==dummy or by entry->hash==-1.
+*/
+
+#define PySet_MINSIZE 8
+
+typedef struct {
+ PyObject *key;
+ Py_hash_t hash; /* Cached hash code of the key */
+} setentry;
+
+/* The SetObject data structure is shared by set and frozenset objects.
+
+Invariant for sets:
+ - hash is -1
+
+Invariants for frozensets:
+ - data is immutable.
+ - hash is the hash of the frozenset or -1 if not computed yet.
+
+*/
+
+typedef struct {
+ PyObject_HEAD
+
+ Py_ssize_t fill; /* Number active and dummy entries*/
+ Py_ssize_t used; /* Number active entries */
+
+ /* The table contains mask + 1 slots, and that's a power of 2.
+ * We store the mask instead of the size because the mask is more
+ * frequently needed.
+ */
+ Py_ssize_t mask;
+
+ /* The table points to a fixed-size smalltable for small tables
+ * or to additional malloc'ed memory for bigger tables.
+ * The table pointer is never NULL which saves us from repeated
+ * runtime null-tests.
+ */
+ setentry *table;
+ Py_hash_t hash; /* Only used by frozenset objects */
+ Py_ssize_t finger; /* Search finger for pop() */
+
+ setentry smalltable[PySet_MINSIZE];
+ PyObject *weakreflist; /* List of weak references */
+} PySetObject;
+
+#define PySet_GET_SIZE(so) (assert(PyAnySet_Check(so)),(((PySetObject *)(so))->used))
+
+PyAPI_DATA(PyObject *) _PySet_Dummy;
+
+PyAPI_FUNC(int) _PySet_NextEntry(PyObject *set, Py_ssize_t *pos, PyObject **key, Py_hash_t *hash);
+PyAPI_FUNC(int) _PySet_Update(PyObject *set, PyObject *iterable);
+PyAPI_FUNC(int) PySet_ClearFreeList(void);
+
+#endif /* Section excluded by Py_LIMITED_API */
+
+PyAPI_DATA(PyTypeObject) PySet_Type;
+PyAPI_DATA(PyTypeObject) PyFrozenSet_Type;
+PyAPI_DATA(PyTypeObject) PySetIter_Type;
+
+PyAPI_FUNC(PyObject *) PySet_New(PyObject *);
+PyAPI_FUNC(PyObject *) PyFrozenSet_New(PyObject *);
+
+PyAPI_FUNC(int) PySet_Add(PyObject *set, PyObject *key);
+PyAPI_FUNC(int) PySet_Clear(PyObject *set);
+PyAPI_FUNC(int) PySet_Contains(PyObject *anyset, PyObject *key);
+PyAPI_FUNC(int) PySet_Discard(PyObject *set, PyObject *key);
+PyAPI_FUNC(PyObject *) PySet_Pop(PyObject *set);
+PyAPI_FUNC(Py_ssize_t) PySet_Size(PyObject *anyset);
+
+#define PyFrozenSet_CheckExact(ob) (Py_TYPE(ob) == &PyFrozenSet_Type)
+#define PyAnySet_CheckExact(ob) \
+ (Py_TYPE(ob) == &PySet_Type || Py_TYPE(ob) == &PyFrozenSet_Type)
+#define PyAnySet_Check(ob) \
+ (Py_TYPE(ob) == &PySet_Type || Py_TYPE(ob) == &PyFrozenSet_Type || \
+ PyType_IsSubtype(Py_TYPE(ob), &PySet_Type) || \
+ PyType_IsSubtype(Py_TYPE(ob), &PyFrozenSet_Type))
+#define PySet_Check(ob) \
+ (Py_TYPE(ob) == &PySet_Type || \
+ PyType_IsSubtype(Py_TYPE(ob), &PySet_Type))
+#define PyFrozenSet_Check(ob) \
+ (Py_TYPE(ob) == &PyFrozenSet_Type || \
+ PyType_IsSubtype(Py_TYPE(ob), &PyFrozenSet_Type))
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_SETOBJECT_H */
diff --git a/Include/sliceobject.h b/Include/sliceobject.h
new file mode 100644
index 0000000..c238b09
--- /dev/null
+++ b/Include/sliceobject.h
@@ -0,0 +1,63 @@
+#ifndef Py_SLICEOBJECT_H
+#define Py_SLICEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* The unique ellipsis object "..." */
+
+PyAPI_DATA(PyObject) _Py_EllipsisObject; /* Don't use this directly */
+
+#define Py_Ellipsis (&_Py_EllipsisObject)
+
+/* Slice object interface */
+
+/*
+
+A slice object containing start, stop, and step data members (the
+names are from range). After much talk with Guido, it was decided to
+let these be any arbitrary python type. Py_None stands for omitted values.
+*/
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_HEAD
+ PyObject *start, *stop, *step; /* not NULL */
+} PySliceObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PySlice_Type;
+PyAPI_DATA(PyTypeObject) PyEllipsis_Type;
+
+#define PySlice_Check(op) (Py_TYPE(op) == &PySlice_Type)
+
+PyAPI_FUNC(PyObject *) PySlice_New(PyObject* start, PyObject* stop,
+ PyObject* step);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PySlice_FromIndices(Py_ssize_t start, Py_ssize_t stop);
+PyAPI_FUNC(int) _PySlice_GetLongIndices(PySliceObject *self, PyObject *length,
+ PyObject **start_ptr, PyObject **stop_ptr,
+ PyObject **step_ptr);
+#endif
+PyAPI_FUNC(int) PySlice_GetIndices(PyObject *r, Py_ssize_t length,
+ Py_ssize_t *start, Py_ssize_t *stop, Py_ssize_t *step);
+PyAPI_FUNC(int) PySlice_GetIndicesEx(PyObject *r, Py_ssize_t length,
+ Py_ssize_t *start, Py_ssize_t *stop,
+ Py_ssize_t *step, Py_ssize_t *slicelength) Py_DEPRECATED(3.7);
+
+#if !defined(Py_LIMITED_API) || (Py_LIMITED_API+0 >= 0x03050400 && Py_LIMITED_API+0 < 0x03060000) || Py_LIMITED_API+0 >= 0x03060100
+#define PySlice_GetIndicesEx(slice, length, start, stop, step, slicelen) ( \
+ PySlice_Unpack((slice), (start), (stop), (step)) < 0 ? \
+ ((*(slicelen) = 0), -1) : \
+ ((*(slicelen) = PySlice_AdjustIndices((length), (start), (stop), *(step))), \
+ 0))
+PyAPI_FUNC(int) PySlice_Unpack(PyObject *slice,
+ Py_ssize_t *start, Py_ssize_t *stop, Py_ssize_t *step);
+PyAPI_FUNC(Py_ssize_t) PySlice_AdjustIndices(Py_ssize_t length,
+ Py_ssize_t *start, Py_ssize_t *stop,
+ Py_ssize_t step);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_SLICEOBJECT_H */
diff --git a/Include/structmember.h b/Include/structmember.h
new file mode 100644
index 0000000..b54f708
--- /dev/null
+++ b/Include/structmember.h
@@ -0,0 +1,74 @@
+#ifndef Py_STRUCTMEMBER_H
+#define Py_STRUCTMEMBER_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Interface to map C struct members to Python object attributes */
+
+#include /* For offsetof */
+
+/* An array of PyMemberDef structures defines the name, type and offset
+ of selected members of a C structure. These can be read by
+ PyMember_GetOne() and set by PyMember_SetOne() (except if their READONLY
+ flag is set). The array must be terminated with an entry whose name
+ pointer is NULL. */
+
+typedef struct PyMemberDef {
+ const char *name;
+ int type;
+ Py_ssize_t offset;
+ int flags;
+ const char *doc;
+} PyMemberDef;
+
+/* Types */
+#define T_SHORT 0
+#define T_INT 1
+#define T_LONG 2
+#define T_FLOAT 3
+#define T_DOUBLE 4
+#define T_STRING 5
+#define T_OBJECT 6
+/* XXX the ordering here is weird for binary compatibility */
+#define T_CHAR 7 /* 1-character string */
+#define T_BYTE 8 /* 8-bit signed int */
+/* unsigned variants: */
+#define T_UBYTE 9
+#define T_USHORT 10
+#define T_UINT 11
+#define T_ULONG 12
+
+/* Added by Jack: strings contained in the structure */
+#define T_STRING_INPLACE 13
+
+/* Added by Lillo: bools contained in the structure (assumed char) */
+#define T_BOOL 14
+
+#define T_OBJECT_EX 16 /* Like T_OBJECT, but raises AttributeError
+ when the value is NULL, instead of
+ converting to None. */
+#define T_LONGLONG 17
+#define T_ULONGLONG 18
+
+#define T_PYSSIZET 19 /* Py_ssize_t */
+#define T_NONE 20 /* Value is always None */
+
+
+/* Flags */
+#define READONLY 1
+#define READ_RESTRICTED 2
+#define PY_WRITE_RESTRICTED 4
+#define RESTRICTED (READ_RESTRICTED | PY_WRITE_RESTRICTED)
+
+
+/* Current API, use this */
+PyAPI_FUNC(PyObject *) PyMember_GetOne(const char *, struct PyMemberDef *);
+PyAPI_FUNC(int) PyMember_SetOne(char *, struct PyMemberDef *, PyObject *);
+
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_STRUCTMEMBER_H */
diff --git a/Include/structseq.h b/Include/structseq.h
new file mode 100644
index 0000000..e5e5d5c
--- /dev/null
+++ b/Include/structseq.h
@@ -0,0 +1,49 @@
+
+/* Named tuple object interface */
+
+#ifndef Py_STRUCTSEQ_H
+#define Py_STRUCTSEQ_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct PyStructSequence_Field {
+ const char *name;
+ const char *doc;
+} PyStructSequence_Field;
+
+typedef struct PyStructSequence_Desc {
+ const char *name;
+ const char *doc;
+ struct PyStructSequence_Field *fields;
+ int n_in_sequence;
+} PyStructSequence_Desc;
+
+extern char* PyStructSequence_UnnamedField;
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) PyStructSequence_InitType(PyTypeObject *type,
+ PyStructSequence_Desc *desc);
+PyAPI_FUNC(int) PyStructSequence_InitType2(PyTypeObject *type,
+ PyStructSequence_Desc *desc);
+#endif
+PyAPI_FUNC(PyTypeObject*) PyStructSequence_NewType(PyStructSequence_Desc *desc);
+
+PyAPI_FUNC(PyObject *) PyStructSequence_New(PyTypeObject* type);
+
+#ifndef Py_LIMITED_API
+typedef PyTupleObject PyStructSequence;
+
+/* Macro, *only* to be used to fill in brand new objects */
+#define PyStructSequence_SET_ITEM(op, i, v) PyTuple_SET_ITEM(op, i, v)
+
+#define PyStructSequence_GET_ITEM(op, i) PyTuple_GET_ITEM(op, i)
+#endif
+
+PyAPI_FUNC(void) PyStructSequence_SetItem(PyObject*, Py_ssize_t, PyObject*);
+PyAPI_FUNC(PyObject*) PyStructSequence_GetItem(PyObject*, Py_ssize_t);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_STRUCTSEQ_H */
diff --git a/Include/symtable.h b/Include/symtable.h
new file mode 100644
index 0000000..007f88d
--- /dev/null
+++ b/Include/symtable.h
@@ -0,0 +1,118 @@
+#ifndef Py_LIMITED_API
+#ifndef Py_SYMTABLE_H
+#define Py_SYMTABLE_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* XXX(ncoghlan): This is a weird mix of public names and interpreter internal
+ * names.
+ */
+
+typedef enum _block_type { FunctionBlock, ClassBlock, ModuleBlock }
+ _Py_block_ty;
+
+struct _symtable_entry;
+
+struct symtable {
+ PyObject *st_filename; /* name of file being compiled,
+ decoded from the filesystem encoding */
+ struct _symtable_entry *st_cur; /* current symbol table entry */
+ struct _symtable_entry *st_top; /* symbol table entry for module */
+ PyObject *st_blocks; /* dict: map AST node addresses
+ * to symbol table entries */
+ PyObject *st_stack; /* list: stack of namespace info */
+ PyObject *st_global; /* borrowed ref to st_top->ste_symbols */
+ int st_nblocks; /* number of blocks used. kept for
+ consistency with the corresponding
+ compiler structure */
+ PyObject *st_private; /* name of current class or NULL */
+ PyFutureFeatures *st_future; /* module's future features that affect
+ the symbol table */
+ int recursion_depth; /* current recursion depth */
+ int recursion_limit; /* recursion limit */
+};
+
+typedef struct _symtable_entry {
+ PyObject_HEAD
+ PyObject *ste_id; /* int: key in ste_table->st_blocks */
+ PyObject *ste_symbols; /* dict: variable names to flags */
+ PyObject *ste_name; /* string: name of current block */
+ PyObject *ste_varnames; /* list of function parameters */
+ PyObject *ste_children; /* list of child blocks */
+ PyObject *ste_directives;/* locations of global and nonlocal statements */
+ _Py_block_ty ste_type; /* module, class, or function */
+ int ste_nested; /* true if block is nested */
+ unsigned ste_free : 1; /* true if block has free variables */
+ unsigned ste_child_free : 1; /* true if a child block has free vars,
+ including free refs to globals */
+ unsigned ste_generator : 1; /* true if namespace is a generator */
+ unsigned ste_coroutine : 1; /* true if namespace is a coroutine */
+ unsigned ste_varargs : 1; /* true if block has varargs */
+ unsigned ste_varkeywords : 1; /* true if block has varkeywords */
+ unsigned ste_returns_value : 1; /* true if namespace uses return with
+ an argument */
+ unsigned ste_needs_class_closure : 1; /* for class scopes, true if a
+ closure over __class__
+ should be created */
+ int ste_lineno; /* first line of block */
+ int ste_col_offset; /* offset of first line of block */
+ int ste_opt_lineno; /* lineno of last exec or import * */
+ int ste_opt_col_offset; /* offset of last exec or import * */
+ struct symtable *ste_table;
+} PySTEntryObject;
+
+PyAPI_DATA(PyTypeObject) PySTEntry_Type;
+
+#define PySTEntry_Check(op) (Py_TYPE(op) == &PySTEntry_Type)
+
+PyAPI_FUNC(int) PyST_GetScope(PySTEntryObject *, PyObject *);
+
+PyAPI_FUNC(struct symtable *) PySymtable_Build(
+ mod_ty mod,
+ const char *filename, /* decoded from the filesystem encoding */
+ PyFutureFeatures *future);
+PyAPI_FUNC(struct symtable *) PySymtable_BuildObject(
+ mod_ty mod,
+ PyObject *filename,
+ PyFutureFeatures *future);
+PyAPI_FUNC(PySTEntryObject *) PySymtable_Lookup(struct symtable *, void *);
+
+PyAPI_FUNC(void) PySymtable_Free(struct symtable *);
+
+/* Flags for def-use information */
+
+#define DEF_GLOBAL 1 /* global stmt */
+#define DEF_LOCAL 2 /* assignment in code block */
+#define DEF_PARAM 2<<1 /* formal parameter */
+#define DEF_NONLOCAL 2<<2 /* nonlocal stmt */
+#define USE 2<<3 /* name is used */
+#define DEF_FREE 2<<4 /* name used but not defined in nested block */
+#define DEF_FREE_CLASS 2<<5 /* free variable from class's method */
+#define DEF_IMPORT 2<<6 /* assignment occurred via import */
+#define DEF_ANNOT 2<<7 /* this name is annotated */
+
+#define DEF_BOUND (DEF_LOCAL | DEF_PARAM | DEF_IMPORT)
+
+/* GLOBAL_EXPLICIT and GLOBAL_IMPLICIT are used internally by the symbol
+ table. GLOBAL is returned from PyST_GetScope() for either of them.
+ It is stored in ste_symbols at bits 12-15.
+*/
+#define SCOPE_OFFSET 11
+#define SCOPE_MASK (DEF_GLOBAL | DEF_LOCAL | DEF_PARAM | DEF_NONLOCAL)
+
+#define LOCAL 1
+#define GLOBAL_EXPLICIT 2
+#define GLOBAL_IMPLICIT 3
+#define FREE 4
+#define CELL 5
+
+#define GENERATOR 1
+#define GENERATOR_EXPRESSION 2
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_SYMTABLE_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/sysmodule.h b/Include/sysmodule.h
new file mode 100644
index 0000000..719ecfc
--- /dev/null
+++ b/Include/sysmodule.h
@@ -0,0 +1,48 @@
+
+/* System module interface */
+
+#ifndef Py_SYSMODULE_H
+#define Py_SYSMODULE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+PyAPI_FUNC(PyObject *) PySys_GetObject(const char *);
+PyAPI_FUNC(int) PySys_SetObject(const char *, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PySys_GetObjectId(_Py_Identifier *key);
+PyAPI_FUNC(int) _PySys_SetObjectId(_Py_Identifier *key, PyObject *);
+#endif
+
+PyAPI_FUNC(void) PySys_SetArgv(int, wchar_t **);
+PyAPI_FUNC(void) PySys_SetArgvEx(int, wchar_t **, int);
+PyAPI_FUNC(void) PySys_SetPath(const wchar_t *);
+
+PyAPI_FUNC(void) PySys_WriteStdout(const char *format, ...)
+ Py_GCC_ATTRIBUTE((format(printf, 1, 2)));
+PyAPI_FUNC(void) PySys_WriteStderr(const char *format, ...)
+ Py_GCC_ATTRIBUTE((format(printf, 1, 2)));
+PyAPI_FUNC(void) PySys_FormatStdout(const char *format, ...);
+PyAPI_FUNC(void) PySys_FormatStderr(const char *format, ...);
+
+PyAPI_FUNC(void) PySys_ResetWarnOptions(void);
+PyAPI_FUNC(void) PySys_AddWarnOption(const wchar_t *);
+PyAPI_FUNC(void) PySys_AddWarnOptionUnicode(PyObject *);
+PyAPI_FUNC(int) PySys_HasWarnOptions(void);
+
+PyAPI_FUNC(void) PySys_AddXOption(const wchar_t *);
+PyAPI_FUNC(PyObject *) PySys_GetXOptions(void);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(size_t) _PySys_GetSizeOf(PyObject *);
+#endif
+
+#ifdef Py_BUILD_CORE
+PyAPI_FUNC(int) _PySys_AddXOptionWithError(const wchar_t *s);
+PyAPI_FUNC(int) _PySys_AddWarnOptionWithError(PyObject *option);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_SYSMODULE_H */
diff --git a/Include/token.h b/Include/token.h
new file mode 100644
index 0000000..cd1cd00
--- /dev/null
+++ b/Include/token.h
@@ -0,0 +1,92 @@
+
+/* Token types */
+#ifndef Py_LIMITED_API
+#ifndef Py_TOKEN_H
+#define Py_TOKEN_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#undef TILDE /* Prevent clash of our definition with system macro. Ex AIX, ioctl.h */
+
+#define ENDMARKER 0
+#define NAME 1
+#define NUMBER 2
+#define STRING 3
+#define NEWLINE 4
+#define INDENT 5
+#define DEDENT 6
+#define LPAR 7
+#define RPAR 8
+#define LSQB 9
+#define RSQB 10
+#define COLON 11
+#define COMMA 12
+#define SEMI 13
+#define PLUS 14
+#define MINUS 15
+#define STAR 16
+#define SLASH 17
+#define VBAR 18
+#define AMPER 19
+#define LESS 20
+#define GREATER 21
+#define EQUAL 22
+#define DOT 23
+#define PERCENT 24
+#define LBRACE 25
+#define RBRACE 26
+#define EQEQUAL 27
+#define NOTEQUAL 28
+#define LESSEQUAL 29
+#define GREATEREQUAL 30
+#define TILDE 31
+#define CIRCUMFLEX 32
+#define LEFTSHIFT 33
+#define RIGHTSHIFT 34
+#define DOUBLESTAR 35
+#define PLUSEQUAL 36
+#define MINEQUAL 37
+#define STAREQUAL 38
+#define SLASHEQUAL 39
+#define PERCENTEQUAL 40
+#define AMPEREQUAL 41
+#define VBAREQUAL 42
+#define CIRCUMFLEXEQUAL 43
+#define LEFTSHIFTEQUAL 44
+#define RIGHTSHIFTEQUAL 45
+#define DOUBLESTAREQUAL 46
+#define DOUBLESLASH 47
+#define DOUBLESLASHEQUAL 48
+#define AT 49
+#define ATEQUAL 50
+#define RARROW 51
+#define ELLIPSIS 52
+/* Don't forget to update the table _PyParser_TokenNames in tokenizer.c! */
+#define OP 53
+#define ERRORTOKEN 54
+/* These aren't used by the C tokenizer but are needed for tokenize.py */
+#define COMMENT 55
+#define NL 56
+#define ENCODING 57
+#define N_TOKENS 58
+
+/* Special definitions for cooperation with parser */
+
+#define NT_OFFSET 256
+
+#define ISTERMINAL(x) ((x) < NT_OFFSET)
+#define ISNONTERMINAL(x) ((x) >= NT_OFFSET)
+#define ISEOF(x) ((x) == ENDMARKER)
+
+
+PyAPI_DATA(const char *) _PyParser_TokenNames[]; /* Token names */
+PyAPI_FUNC(int) PyToken_OneChar(int);
+PyAPI_FUNC(int) PyToken_TwoChars(int, int);
+PyAPI_FUNC(int) PyToken_ThreeChars(int, int, int);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_TOKEN_H */
+#endif /* Py_LIMITED_API */
diff --git a/Include/traceback.h b/Include/traceback.h
new file mode 100644
index 0000000..b587410
--- /dev/null
+++ b/Include/traceback.h
@@ -0,0 +1,119 @@
+
+#ifndef Py_TRACEBACK_H
+#define Py_TRACEBACK_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "pystate.h"
+
+struct _frame;
+
+/* Traceback interface */
+#ifndef Py_LIMITED_API
+typedef struct _traceback {
+ PyObject_HEAD
+ struct _traceback *tb_next;
+ struct _frame *tb_frame;
+ int tb_lasti;
+ int tb_lineno;
+} PyTracebackObject;
+#endif
+
+PyAPI_FUNC(int) PyTraceBack_Here(struct _frame *);
+PyAPI_FUNC(int) PyTraceBack_Print(PyObject *, PyObject *);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _Py_DisplaySourceLine(PyObject *, PyObject *, int, int);
+PyAPI_FUNC(void) _PyTraceback_Add(const char *, const char *, int);
+#endif
+
+/* Reveal traceback type so we can typecheck traceback objects */
+PyAPI_DATA(PyTypeObject) PyTraceBack_Type;
+#define PyTraceBack_Check(v) (Py_TYPE(v) == &PyTraceBack_Type)
+
+#ifndef Py_LIMITED_API
+/* Write the Python traceback into the file 'fd'. For example:
+
+ Traceback (most recent call first):
+ File "xxx", line xxx in
+ File "xxx", line xxx in
+ ...
+ File "xxx", line xxx in
+
+ This function is written for debug purpose only, to dump the traceback in
+ the worst case: after a segmentation fault, at fatal error, etc. That's why,
+ it is very limited. Strings are truncated to 100 characters and encoded to
+ ASCII with backslashreplace. It doesn't write the source code, only the
+ function name, filename and line number of each frame. Write only the first
+ 100 frames: if the traceback is truncated, write the line " ...".
+
+ This function is signal safe. */
+
+PyAPI_FUNC(void) _Py_DumpTraceback(
+ int fd,
+ PyThreadState *tstate);
+
+/* Write the traceback of all threads into the file 'fd'. current_thread can be
+ NULL.
+
+ Return NULL on success, or an error message on error.
+
+ This function is written for debug purpose only. It calls
+ _Py_DumpTraceback() for each thread, and so has the same limitations. It
+ only write the traceback of the first 100 threads: write "..." if there are
+ more threads.
+
+ If current_tstate is NULL, the function tries to get the Python thread state
+ of the current thread. It is not an error if the function is unable to get
+ the current Python thread state.
+
+ If interp is NULL, the function tries to get the interpreter state from
+ the current Python thread state, or from
+ _PyGILState_GetInterpreterStateUnsafe() in last resort.
+
+ It is better to pass NULL to interp and current_tstate, the function tries
+ different options to retrieve these informations.
+
+ This function is signal safe. */
+
+PyAPI_FUNC(const char*) _Py_DumpTracebackThreads(
+ int fd,
+ PyInterpreterState *interp,
+ PyThreadState *current_tstate);
+#endif /* !Py_LIMITED_API */
+
+#ifndef Py_LIMITED_API
+
+/* Write a Unicode object into the file descriptor fd. Encode the string to
+ ASCII using the backslashreplace error handler.
+
+ Do nothing if text is not a Unicode object. The function accepts Unicode
+ string which is not ready (PyUnicode_WCHAR_KIND).
+
+ This function is signal safe. */
+PyAPI_FUNC(void) _Py_DumpASCII(int fd, PyObject *text);
+
+/* Format an integer as decimal into the file descriptor fd.
+
+ This function is signal safe. */
+PyAPI_FUNC(void) _Py_DumpDecimal(
+ int fd,
+ unsigned long value);
+
+/* Format an integer as hexadecimal into the file descriptor fd with at least
+ width digits.
+
+ The maximum width is sizeof(unsigned long)*2 digits.
+
+ This function is signal safe. */
+PyAPI_FUNC(void) _Py_DumpHexadecimal(
+ int fd,
+ unsigned long value,
+ Py_ssize_t width);
+
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_TRACEBACK_H */
diff --git a/Include/tupleobject.h b/Include/tupleobject.h
new file mode 100644
index 0000000..72a7d8d
--- /dev/null
+++ b/Include/tupleobject.h
@@ -0,0 +1,73 @@
+
+/* Tuple object interface */
+
+#ifndef Py_TUPLEOBJECT_H
+#define Py_TUPLEOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+Another generally useful object type is a tuple of object pointers.
+For Python, this is an immutable type. C code can change the tuple items
+(but not their number), and even use tuples as general-purpose arrays of
+object references, but in general only brand new tuples should be mutated,
+not ones that might already have been exposed to Python code.
+
+*** WARNING *** PyTuple_SetItem does not increment the new item's reference
+count, but does decrement the reference count of the item it replaces,
+if not nil. It does *decrement* the reference count if it is *not*
+inserted in the tuple. Similarly, PyTuple_GetItem does not increment the
+returned item's reference count.
+*/
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject_VAR_HEAD
+ PyObject *ob_item[1];
+
+ /* ob_item contains space for 'ob_size' elements.
+ * Items must normally not be NULL, except during construction when
+ * the tuple is not yet visible outside the function that builds it.
+ */
+} PyTupleObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PyTuple_Type;
+PyAPI_DATA(PyTypeObject) PyTupleIter_Type;
+
+#define PyTuple_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_TUPLE_SUBCLASS)
+#define PyTuple_CheckExact(op) (Py_TYPE(op) == &PyTuple_Type)
+
+PyAPI_FUNC(PyObject *) PyTuple_New(Py_ssize_t size);
+PyAPI_FUNC(Py_ssize_t) PyTuple_Size(PyObject *);
+PyAPI_FUNC(PyObject *) PyTuple_GetItem(PyObject *, Py_ssize_t);
+PyAPI_FUNC(int) PyTuple_SetItem(PyObject *, Py_ssize_t, PyObject *);
+PyAPI_FUNC(PyObject *) PyTuple_GetSlice(PyObject *, Py_ssize_t, Py_ssize_t);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyTuple_Resize(PyObject **, Py_ssize_t);
+#endif
+PyAPI_FUNC(PyObject *) PyTuple_Pack(Py_ssize_t, ...);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyTuple_MaybeUntrack(PyObject *);
+#endif
+
+/* Macro, trading safety for speed */
+#ifndef Py_LIMITED_API
+#define PyTuple_GET_ITEM(op, i) (((PyTupleObject *)(op))->ob_item[i])
+#define PyTuple_GET_SIZE(op) (assert(PyTuple_Check(op)),Py_SIZE(op))
+
+/* Macro, *only* to be used to fill in brand new tuples */
+#define PyTuple_SET_ITEM(op, i, v) (((PyTupleObject *)(op))->ob_item[i] = v)
+#endif
+
+PyAPI_FUNC(int) PyTuple_ClearFreeList(void);
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _PyTuple_DebugMallocStats(FILE *out);
+#endif /* Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_TUPLEOBJECT_H */
diff --git a/Include/typeslots.h b/Include/typeslots.h
new file mode 100644
index 0000000..0ce6a37
--- /dev/null
+++ b/Include/typeslots.h
@@ -0,0 +1,85 @@
+/* Do not renumber the file; these numbers are part of the stable ABI. */
+/* Disabled, see #10181 */
+#undef Py_bf_getbuffer
+#undef Py_bf_releasebuffer
+#define Py_mp_ass_subscript 3
+#define Py_mp_length 4
+#define Py_mp_subscript 5
+#define Py_nb_absolute 6
+#define Py_nb_add 7
+#define Py_nb_and 8
+#define Py_nb_bool 9
+#define Py_nb_divmod 10
+#define Py_nb_float 11
+#define Py_nb_floor_divide 12
+#define Py_nb_index 13
+#define Py_nb_inplace_add 14
+#define Py_nb_inplace_and 15
+#define Py_nb_inplace_floor_divide 16
+#define Py_nb_inplace_lshift 17
+#define Py_nb_inplace_multiply 18
+#define Py_nb_inplace_or 19
+#define Py_nb_inplace_power 20
+#define Py_nb_inplace_remainder 21
+#define Py_nb_inplace_rshift 22
+#define Py_nb_inplace_subtract 23
+#define Py_nb_inplace_true_divide 24
+#define Py_nb_inplace_xor 25
+#define Py_nb_int 26
+#define Py_nb_invert 27
+#define Py_nb_lshift 28
+#define Py_nb_multiply 29
+#define Py_nb_negative 30
+#define Py_nb_or 31
+#define Py_nb_positive 32
+#define Py_nb_power 33
+#define Py_nb_remainder 34
+#define Py_nb_rshift 35
+#define Py_nb_subtract 36
+#define Py_nb_true_divide 37
+#define Py_nb_xor 38
+#define Py_sq_ass_item 39
+#define Py_sq_concat 40
+#define Py_sq_contains 41
+#define Py_sq_inplace_concat 42
+#define Py_sq_inplace_repeat 43
+#define Py_sq_item 44
+#define Py_sq_length 45
+#define Py_sq_repeat 46
+#define Py_tp_alloc 47
+#define Py_tp_base 48
+#define Py_tp_bases 49
+#define Py_tp_call 50
+#define Py_tp_clear 51
+#define Py_tp_dealloc 52
+#define Py_tp_del 53
+#define Py_tp_descr_get 54
+#define Py_tp_descr_set 55
+#define Py_tp_doc 56
+#define Py_tp_getattr 57
+#define Py_tp_getattro 58
+#define Py_tp_hash 59
+#define Py_tp_init 60
+#define Py_tp_is_gc 61
+#define Py_tp_iter 62
+#define Py_tp_iternext 63
+#define Py_tp_methods 64
+#define Py_tp_new 65
+#define Py_tp_repr 66
+#define Py_tp_richcompare 67
+#define Py_tp_setattr 68
+#define Py_tp_setattro 69
+#define Py_tp_str 70
+#define Py_tp_traverse 71
+#define Py_tp_members 72
+#define Py_tp_getset 73
+#define Py_tp_free 74
+#define Py_nb_matrix_multiply 75
+#define Py_nb_inplace_matrix_multiply 76
+#define Py_am_await 77
+#define Py_am_aiter 78
+#define Py_am_anext 79
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03050000
+/* New in 3.5 */
+#define Py_tp_finalize 80
+#endif
diff --git a/Include/ucnhash.h b/Include/ucnhash.h
new file mode 100644
index 0000000..45362e9
--- /dev/null
+++ b/Include/ucnhash.h
@@ -0,0 +1,36 @@
+/* Unicode name database interface */
+#ifndef Py_LIMITED_API
+#ifndef Py_UCNHASH_H
+#define Py_UCNHASH_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* revised ucnhash CAPI interface (exported through a "wrapper") */
+
+#define PyUnicodeData_CAPSULE_NAME "unicodedata.ucnhash_CAPI"
+
+typedef struct {
+
+ /* Size of this struct */
+ int size;
+
+ /* Get name for a given character code. Returns non-zero if
+ success, zero if not. Does not set Python exceptions.
+ If self is NULL, data come from the default version of the database.
+ If it is not NULL, it should be a unicodedata.ucd_X_Y_Z object */
+ int (*getname)(PyObject *self, Py_UCS4 code, char* buffer, int buflen,
+ int with_alias_and_seq);
+
+ /* Get character code for a given name. Same error handling
+ as for getname. */
+ int (*getcode)(PyObject *self, const char* name, int namelen, Py_UCS4* code,
+ int with_named_seq);
+
+} _PyUnicode_Name_CAPI;
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_UCNHASH_H */
+#endif /* !Py_LIMITED_API */
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
new file mode 100644
index 0000000..0274de6
--- /dev/null
+++ b/Include/unicodeobject.h
@@ -0,0 +1,2334 @@
+#ifndef Py_UNICODEOBJECT_H
+#define Py_UNICODEOBJECT_H
+
+#include
+
+/*
+
+Unicode implementation based on original code by Fredrik Lundh,
+modified by Marc-Andre Lemburg (mal@lemburg.com) according to the
+Unicode Integration Proposal. (See
+http://www.egenix.com/files/python/unicode-proposal.txt).
+
+Copyright (c) Corporation for National Research Initiatives.
+
+
+ Original header:
+ --------------------------------------------------------------------
+
+ * Yet another Unicode string type for Python. This type supports the
+ * 16-bit Basic Multilingual Plane (BMP) only.
+ *
+ * Written by Fredrik Lundh, January 1999.
+ *
+ * Copyright (c) 1999 by Secret Labs AB.
+ * Copyright (c) 1999 by Fredrik Lundh.
+ *
+ * fredrik@pythonware.com
+ * http://www.pythonware.com
+ *
+ * --------------------------------------------------------------------
+ * This Unicode String Type is
+ *
+ * Copyright (c) 1999 by Secret Labs AB
+ * Copyright (c) 1999 by Fredrik Lundh
+ *
+ * By obtaining, using, and/or copying this software and/or its
+ * associated documentation, you agree that you have read, understood,
+ * and will comply with the following terms and conditions:
+ *
+ * Permission to use, copy, modify, and distribute this software and its
+ * associated documentation for any purpose and without fee is hereby
+ * granted, provided that the above copyright notice appears in all
+ * copies, and that both that copyright notice and this permission notice
+ * appear in supporting documentation, and that the name of Secret Labs
+ * AB or the author not be used in advertising or publicity pertaining to
+ * distribution of the software without specific, written prior
+ * permission.
+ *
+ * SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO
+ * THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+ * FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
+ * OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ * -------------------------------------------------------------------- */
+
+#include
+
+/* === Internal API ======================================================= */
+
+/* --- Internal Unicode Format -------------------------------------------- */
+
+/* Python 3.x requires unicode */
+#define Py_USING_UNICODE
+
+#ifndef SIZEOF_WCHAR_T
+#error Must define SIZEOF_WCHAR_T
+#endif
+
+#define Py_UNICODE_SIZE SIZEOF_WCHAR_T
+
+/* If wchar_t can be used for UCS-4 storage, set Py_UNICODE_WIDE.
+ Otherwise, Unicode strings are stored as UCS-2 (with limited support
+ for UTF-16) */
+
+#if Py_UNICODE_SIZE >= 4
+#define Py_UNICODE_WIDE
+#endif
+
+/* Set these flags if the platform has "wchar.h" and the
+ wchar_t type is a 16-bit unsigned type */
+/* #define HAVE_WCHAR_H */
+/* #define HAVE_USABLE_WCHAR_T */
+
+/* Py_UNICODE was the native Unicode storage format (code unit) used by
+ Python and represents a single Unicode element in the Unicode type.
+ With PEP 393, Py_UNICODE is deprecated and replaced with a
+ typedef to wchar_t. */
+
+#ifndef Py_LIMITED_API
+#define PY_UNICODE_TYPE wchar_t
+typedef wchar_t Py_UNICODE /* Py_DEPRECATED(3.3) */;
+#endif
+
+/* If the compiler provides a wchar_t type we try to support it
+ through the interface functions PyUnicode_FromWideChar(),
+ PyUnicode_AsWideChar() and PyUnicode_AsWideCharString(). */
+
+#ifdef HAVE_USABLE_WCHAR_T
+# ifndef HAVE_WCHAR_H
+# define HAVE_WCHAR_H
+# endif
+#endif
+
+#ifdef HAVE_WCHAR_H
+# include
+#endif
+
+/* Py_UCS4 and Py_UCS2 are typedefs for the respective
+ unicode representations. */
+typedef uint32_t Py_UCS4;
+typedef uint16_t Py_UCS2;
+typedef uint8_t Py_UCS1;
+
+/* --- Internal Unicode Operations ---------------------------------------- */
+
+/* Since splitting on whitespace is an important use case, and
+ whitespace in most situations is solely ASCII whitespace, we
+ optimize for the common case by using a quick look-up table
+ _Py_ascii_whitespace (see below) with an inlined check.
+
+ */
+#ifndef Py_LIMITED_API
+#define Py_UNICODE_ISSPACE(ch) \
+ ((ch) < 128U ? _Py_ascii_whitespace[(ch)] : _PyUnicode_IsWhitespace(ch))
+
+#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
+#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
+#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
+#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
+
+#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
+#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
+#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
+
+#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
+#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
+#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
+#define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)
+
+#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
+#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
+#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
+
+#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
+
+#define Py_UNICODE_ISALNUM(ch) \
+ (Py_UNICODE_ISALPHA(ch) || \
+ Py_UNICODE_ISDECIMAL(ch) || \
+ Py_UNICODE_ISDIGIT(ch) || \
+ Py_UNICODE_ISNUMERIC(ch))
+
+#define Py_UNICODE_COPY(target, source, length) \
+ memcpy((target), (source), (length)*sizeof(Py_UNICODE))
+
+#define Py_UNICODE_FILL(target, value, length) \
+ do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
+ for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
+ } while (0)
+
+/* macros to work with surrogates */
+#define Py_UNICODE_IS_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDFFF)
+#define Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDBFF)
+#define Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= (ch) && (ch) <= 0xDFFF)
+/* Join two surrogate characters and return a single Py_UCS4 value. */
+#define Py_UNICODE_JOIN_SURROGATES(high, low) \
+ (((((Py_UCS4)(high) & 0x03FF) << 10) | \
+ ((Py_UCS4)(low) & 0x03FF)) + 0x10000)
+/* high surrogate = top 10 bits added to D800 */
+#define Py_UNICODE_HIGH_SURROGATE(ch) (0xD800 - (0x10000 >> 10) + ((ch) >> 10))
+/* low surrogate = bottom 10 bits added to DC00 */
+#define Py_UNICODE_LOW_SURROGATE(ch) (0xDC00 + ((ch) & 0x3FF))
+
+/* Check if substring matches at given offset. The offset must be
+ valid, and the substring must not be empty. */
+
+#define Py_UNICODE_MATCH(string, offset, substring) \
+ ((*((string)->wstr + (offset)) == *((substring)->wstr)) && \
+ ((*((string)->wstr + (offset) + (substring)->wstr_length-1) == *((substring)->wstr + (substring)->wstr_length-1))) && \
+ !memcmp((string)->wstr + (offset), (substring)->wstr, (substring)->wstr_length*sizeof(Py_UNICODE)))
+
+#endif /* Py_LIMITED_API */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* --- Unicode Type ------------------------------------------------------- */
+
+#ifndef Py_LIMITED_API
+
+/* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
+ structure. state.ascii and state.compact are set, and the data
+ immediately follow the structure. utf8_length and wstr_length can be found
+ in the length field; the utf8 pointer is equal to the data pointer. */
+typedef struct {
+ /* There are 4 forms of Unicode strings:
+
+ - compact ascii:
+
+ * structure = PyASCIIObject
+ * test: PyUnicode_IS_COMPACT_ASCII(op)
+ * kind = PyUnicode_1BYTE_KIND
+ * compact = 1
+ * ascii = 1
+ * ready = 1
+ * (length is the length of the utf8 and wstr strings)
+ * (data starts just after the structure)
+ * (since ASCII is decoded from UTF-8, the utf8 string are the data)
+
+ - compact:
+
+ * structure = PyCompactUnicodeObject
+ * test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
+ * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
+ PyUnicode_4BYTE_KIND
+ * compact = 1
+ * ready = 1
+ * ascii = 0
+ * utf8 is not shared with data
+ * utf8_length = 0 if utf8 is NULL
+ * wstr is shared with data and wstr_length=length
+ if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
+ or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
+ * wstr_length = 0 if wstr is NULL
+ * (data starts just after the structure)
+
+ - legacy string, not ready:
+
+ * structure = PyUnicodeObject
+ * test: kind == PyUnicode_WCHAR_KIND
+ * length = 0 (use wstr_length)
+ * hash = -1
+ * kind = PyUnicode_WCHAR_KIND
+ * compact = 0
+ * ascii = 0
+ * ready = 0
+ * interned = SSTATE_NOT_INTERNED
+ * wstr is not NULL
+ * data.any is NULL
+ * utf8 is NULL
+ * utf8_length = 0
+
+ - legacy string, ready:
+
+ * structure = PyUnicodeObject structure
+ * test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
+ * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
+ PyUnicode_4BYTE_KIND
+ * compact = 0
+ * ready = 1
+ * data.any is not NULL
+ * utf8 is shared and utf8_length = length with data.any if ascii = 1
+ * utf8_length = 0 if utf8 is NULL
+ * wstr is shared with data.any and wstr_length = length
+ if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
+ or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
+ * wstr_length = 0 if wstr is NULL
+
+ Compact strings use only one memory block (structure + characters),
+ whereas legacy strings use one block for the structure and one block
+ for characters.
+
+ Legacy strings are created by PyUnicode_FromUnicode() and
+ PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
+ when PyUnicode_READY() is called.
+
+ See also _PyUnicode_CheckConsistency().
+ */
+ PyObject_HEAD
+ Py_ssize_t length; /* Number of code points in the string */
+ Py_hash_t hash; /* Hash value; -1 if not set */
+ struct {
+ /*
+ SSTATE_NOT_INTERNED (0)
+ SSTATE_INTERNED_MORTAL (1)
+ SSTATE_INTERNED_IMMORTAL (2)
+
+ If interned != SSTATE_NOT_INTERNED, the two references from the
+ dictionary to this object are *not* counted in ob_refcnt.
+ */
+ unsigned int interned:2;
+ /* Character size:
+
+ - PyUnicode_WCHAR_KIND (0):
+
+ * character type = wchar_t (16 or 32 bits, depending on the
+ platform)
+
+ - PyUnicode_1BYTE_KIND (1):
+
+ * character type = Py_UCS1 (8 bits, unsigned)
+ * all characters are in the range U+0000-U+00FF (latin1)
+ * if ascii is set, all characters are in the range U+0000-U+007F
+ (ASCII), otherwise at least one character is in the range
+ U+0080-U+00FF
+
+ - PyUnicode_2BYTE_KIND (2):
+
+ * character type = Py_UCS2 (16 bits, unsigned)
+ * all characters are in the range U+0000-U+FFFF (BMP)
+ * at least one character is in the range U+0100-U+FFFF
+
+ - PyUnicode_4BYTE_KIND (4):
+
+ * character type = Py_UCS4 (32 bits, unsigned)
+ * all characters are in the range U+0000-U+10FFFF
+ * at least one character is in the range U+10000-U+10FFFF
+ */
+ unsigned int kind:3;
+ /* Compact is with respect to the allocation scheme. Compact unicode
+ objects only require one memory block while non-compact objects use
+ one block for the PyUnicodeObject struct and another for its data
+ buffer. */
+ unsigned int compact:1;
+ /* The string only contains characters in the range U+0000-U+007F (ASCII)
+ and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
+ set, use the PyASCIIObject structure. */
+ unsigned int ascii:1;
+ /* The ready flag indicates whether the object layout is initialized
+ completely. This means that this is either a compact object, or
+ the data pointer is filled out. The bit is redundant, and helps
+ to minimize the test in PyUnicode_IS_READY(). */
+ unsigned int ready:1;
+ /* Padding to ensure that PyUnicode_DATA() is always aligned to
+ 4 bytes (see issue #19537 on m68k). */
+ unsigned int :24;
+ } state;
+ wchar_t *wstr; /* wchar_t representation (null-terminated) */
+} PyASCIIObject;
+
+/* Non-ASCII strings allocated through PyUnicode_New use the
+ PyCompactUnicodeObject structure. state.compact is set, and the data
+ immediately follow the structure. */
+typedef struct {
+ PyASCIIObject _base;
+ Py_ssize_t utf8_length; /* Number of bytes in utf8, excluding the
+ * terminating \0. */
+ char *utf8; /* UTF-8 representation (null-terminated) */
+ Py_ssize_t wstr_length; /* Number of code points in wstr, possible
+ * surrogates count as two code points. */
+} PyCompactUnicodeObject;
+
+/* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
+ PyUnicodeObject structure. The actual string data is initially in the wstr
+ block, and copied into the data block using _PyUnicode_Ready. */
+typedef struct {
+ PyCompactUnicodeObject _base;
+ union {
+ void *any;
+ Py_UCS1 *latin1;
+ Py_UCS2 *ucs2;
+ Py_UCS4 *ucs4;
+ } data; /* Canonical, smallest-form Unicode buffer */
+} PyUnicodeObject;
+#endif
+
+PyAPI_DATA(PyTypeObject) PyUnicode_Type;
+PyAPI_DATA(PyTypeObject) PyUnicodeIter_Type;
+
+#define PyUnicode_Check(op) \
+ PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_UNICODE_SUBCLASS)
+#define PyUnicode_CheckExact(op) (Py_TYPE(op) == &PyUnicode_Type)
+
+/* Fast access macros */
+#ifndef Py_LIMITED_API
+
+#define PyUnicode_WSTR_LENGTH(op) \
+ (PyUnicode_IS_COMPACT_ASCII(op) ? \
+ ((PyASCIIObject*)op)->length : \
+ ((PyCompactUnicodeObject*)op)->wstr_length)
+
+/* Returns the deprecated Py_UNICODE representation's size in code units
+ (this includes surrogate pairs as 2 units).
+ If the Py_UNICODE representation is not available, it will be computed
+ on request. Use PyUnicode_GET_LENGTH() for the length in code points. */
+
+#define PyUnicode_GET_SIZE(op) \
+ (assert(PyUnicode_Check(op)), \
+ (((PyASCIIObject *)(op))->wstr) ? \
+ PyUnicode_WSTR_LENGTH(op) : \
+ ((void)PyUnicode_AsUnicode((PyObject *)(op)), \
+ assert(((PyASCIIObject *)(op))->wstr), \
+ PyUnicode_WSTR_LENGTH(op)))
+ /* Py_DEPRECATED(3.3) */
+
+#define PyUnicode_GET_DATA_SIZE(op) \
+ (PyUnicode_GET_SIZE(op) * Py_UNICODE_SIZE)
+ /* Py_DEPRECATED(3.3) */
+
+/* Alias for PyUnicode_AsUnicode(). This will create a wchar_t/Py_UNICODE
+ representation on demand. Using this macro is very inefficient now,
+ try to port your code to use the new PyUnicode_*BYTE_DATA() macros or
+ use PyUnicode_WRITE() and PyUnicode_READ(). */
+
+#define PyUnicode_AS_UNICODE(op) \
+ (assert(PyUnicode_Check(op)), \
+ (((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
+ PyUnicode_AsUnicode((PyObject *)(op)))
+ /* Py_DEPRECATED(3.3) */
+
+#define PyUnicode_AS_DATA(op) \
+ ((const char *)(PyUnicode_AS_UNICODE(op)))
+ /* Py_DEPRECATED(3.3) */
+
+
+/* --- Flexible String Representation Helper Macros (PEP 393) -------------- */
+
+/* Values for PyASCIIObject.state: */
+
+/* Interning state. */
+#define SSTATE_NOT_INTERNED 0
+#define SSTATE_INTERNED_MORTAL 1
+#define SSTATE_INTERNED_IMMORTAL 2
+
+/* Return true if the string contains only ASCII characters, or 0 if not. The
+ string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
+ ready. */
+#define PyUnicode_IS_ASCII(op) \
+ (assert(PyUnicode_Check(op)), \
+ assert(PyUnicode_IS_READY(op)), \
+ ((PyASCIIObject*)op)->state.ascii)
+
+/* Return true if the string is compact or 0 if not.
+ No type checks or Ready calls are performed. */
+#define PyUnicode_IS_COMPACT(op) \
+ (((PyASCIIObject*)(op))->state.compact)
+
+/* Return true if the string is a compact ASCII string (use PyASCIIObject
+ structure), or 0 if not. No type checks or Ready calls are performed. */
+#define PyUnicode_IS_COMPACT_ASCII(op) \
+ (((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))
+
+enum PyUnicode_Kind {
+/* String contains only wstr byte characters. This is only possible
+ when the string was created with a legacy API and _PyUnicode_Ready()
+ has not been called yet. */
+ PyUnicode_WCHAR_KIND = 0,
+/* Return values of the PyUnicode_KIND() macro: */
+ PyUnicode_1BYTE_KIND = 1,
+ PyUnicode_2BYTE_KIND = 2,
+ PyUnicode_4BYTE_KIND = 4
+};
+
+/* Return pointers to the canonical representation cast to unsigned char,
+ Py_UCS2, or Py_UCS4 for direct character access.
+ No checks are performed, use PyUnicode_KIND() before to ensure
+ these will work correctly. */
+
+#define PyUnicode_1BYTE_DATA(op) ((Py_UCS1*)PyUnicode_DATA(op))
+#define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
+#define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))
+
+/* Return one of the PyUnicode_*_KIND values defined above. */
+#define PyUnicode_KIND(op) \
+ (assert(PyUnicode_Check(op)), \
+ assert(PyUnicode_IS_READY(op)), \
+ ((PyASCIIObject *)(op))->state.kind)
+
+/* Return a void pointer to the raw unicode buffer. */
+#define _PyUnicode_COMPACT_DATA(op) \
+ (PyUnicode_IS_ASCII(op) ? \
+ ((void*)((PyASCIIObject*)(op) + 1)) : \
+ ((void*)((PyCompactUnicodeObject*)(op) + 1)))
+
+#define _PyUnicode_NONCOMPACT_DATA(op) \
+ (assert(((PyUnicodeObject*)(op))->data.any), \
+ ((((PyUnicodeObject *)(op))->data.any)))
+
+#define PyUnicode_DATA(op) \
+ (assert(PyUnicode_Check(op)), \
+ PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) : \
+ _PyUnicode_NONCOMPACT_DATA(op))
+
+/* In the access macros below, "kind" may be evaluated more than once.
+ All other macro parameters are evaluated exactly once, so it is safe
+ to put side effects into them (such as increasing the index). */
+
+/* Write into the canonical representation, this macro does not do any sanity
+ checks and is intended for usage in loops. The caller should cache the
+ kind and data pointers obtained from other macro calls.
+ index is the index in the string (starts at 0) and value is the new
+ code point value which should be written to that location. */
+#define PyUnicode_WRITE(kind, data, index, value) \
+ do { \
+ switch ((kind)) { \
+ case PyUnicode_1BYTE_KIND: { \
+ ((Py_UCS1 *)(data))[(index)] = (Py_UCS1)(value); \
+ break; \
+ } \
+ case PyUnicode_2BYTE_KIND: { \
+ ((Py_UCS2 *)(data))[(index)] = (Py_UCS2)(value); \
+ break; \
+ } \
+ default: { \
+ assert((kind) == PyUnicode_4BYTE_KIND); \
+ ((Py_UCS4 *)(data))[(index)] = (Py_UCS4)(value); \
+ } \
+ } \
+ } while (0)
+
+/* Read a code point from the string's canonical representation. No checks
+ or ready calls are performed. */
+#define PyUnicode_READ(kind, data, index) \
+ ((Py_UCS4) \
+ ((kind) == PyUnicode_1BYTE_KIND ? \
+ ((const Py_UCS1 *)(data))[(index)] : \
+ ((kind) == PyUnicode_2BYTE_KIND ? \
+ ((const Py_UCS2 *)(data))[(index)] : \
+ ((const Py_UCS4 *)(data))[(index)] \
+ ) \
+ ))
+
+/* PyUnicode_READ_CHAR() is less efficient than PyUnicode_READ() because it
+ calls PyUnicode_KIND() and might call it twice. For single reads, use
+ PyUnicode_READ_CHAR, for multiple consecutive reads callers should
+ cache kind and use PyUnicode_READ instead. */
+#define PyUnicode_READ_CHAR(unicode, index) \
+ (assert(PyUnicode_Check(unicode)), \
+ assert(PyUnicode_IS_READY(unicode)), \
+ (Py_UCS4) \
+ (PyUnicode_KIND((unicode)) == PyUnicode_1BYTE_KIND ? \
+ ((const Py_UCS1 *)(PyUnicode_DATA((unicode))))[(index)] : \
+ (PyUnicode_KIND((unicode)) == PyUnicode_2BYTE_KIND ? \
+ ((const Py_UCS2 *)(PyUnicode_DATA((unicode))))[(index)] : \
+ ((const Py_UCS4 *)(PyUnicode_DATA((unicode))))[(index)] \
+ ) \
+ ))
+
+/* Returns the length of the unicode string. The caller has to make sure that
+ the string has it's canonical representation set before calling
+ this macro. Call PyUnicode_(FAST_)Ready to ensure that. */
+#define PyUnicode_GET_LENGTH(op) \
+ (assert(PyUnicode_Check(op)), \
+ assert(PyUnicode_IS_READY(op)), \
+ ((PyASCIIObject *)(op))->length)
+
+
+/* Fast check to determine whether an object is ready. Equivalent to
+ PyUnicode_IS_COMPACT(op) || ((PyUnicodeObject*)(op))->data.any) */
+
+#define PyUnicode_IS_READY(op) (((PyASCIIObject*)op)->state.ready)
+
+/* PyUnicode_READY() does less work than _PyUnicode_Ready() in the best
+ case. If the canonical representation is not yet set, it will still call
+ _PyUnicode_Ready().
+ Returns 0 on success and -1 on errors. */
+#define PyUnicode_READY(op) \
+ (assert(PyUnicode_Check(op)), \
+ (PyUnicode_IS_READY(op) ? \
+ 0 : _PyUnicode_Ready((PyObject *)(op))))
+
+/* Return a maximum character value which is suitable for creating another
+ string based on op. This is always an approximation but more efficient
+ than iterating over the string. */
+#define PyUnicode_MAX_CHAR_VALUE(op) \
+ (assert(PyUnicode_IS_READY(op)), \
+ (PyUnicode_IS_ASCII(op) ? \
+ (0x7f) : \
+ (PyUnicode_KIND(op) == PyUnicode_1BYTE_KIND ? \
+ (0xffU) : \
+ (PyUnicode_KIND(op) == PyUnicode_2BYTE_KIND ? \
+ (0xffffU) : \
+ (0x10ffffU)))))
+
+#endif
+
+/* --- Constants ---------------------------------------------------------- */
+
+/* This Unicode character will be used as replacement character during
+ decoding if the errors argument is set to "replace". Note: the
+ Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
+ Unicode 3.0. */
+
+#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UCS4) 0xFFFD)
+
+/* === Public API ========================================================= */
+
+/* --- Plain Py_UNICODE --------------------------------------------------- */
+
+/* With PEP 393, this is the recommended way to allocate a new unicode object.
+ This function will allocate the object and its buffer in a single memory
+ block. Objects created using this function are not resizable. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_New(
+ Py_ssize_t size, /* Number of code points in the new string */
+ Py_UCS4 maxchar /* maximum code point value in the string */
+ );
+#endif
+
+/* Initializes the canonical string representation from the deprecated
+ wstr/Py_UNICODE representation. This function is used to convert Unicode
+ objects which were created using the old API to the new flexible format
+ introduced with PEP 393.
+
+ Don't call this function directly, use the public PyUnicode_READY() macro
+ instead. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) _PyUnicode_Ready(
+ PyObject *unicode /* Unicode object */
+ );
+#endif
+
+/* Get a copy of a Unicode string. */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) _PyUnicode_Copy(
+ PyObject *unicode
+ );
+#endif
+
+/* Copy character from one unicode object into another, this function performs
+ character conversion when necessary and falls back to memcpy() if possible.
+
+ Fail if to is too small (smaller than *how_many* or smaller than
+ len(from)-from_start), or if kind(from[from_start:from_start+how_many]) >
+ kind(to), or if *to* has more than 1 reference.
+
+ Return the number of written character, or return -1 and raise an exception
+ on error.
+
+ Pseudo-code:
+
+ how_many = min(how_many, len(from) - from_start)
+ to[to_start:to_start+how_many] = from[from_start:from_start+how_many]
+ return how_many
+
+ Note: The function doesn't write a terminating null character.
+ */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) PyUnicode_CopyCharacters(
+ PyObject *to,
+ Py_ssize_t to_start,
+ PyObject *from,
+ Py_ssize_t from_start,
+ Py_ssize_t how_many
+ );
+
+/* Unsafe version of PyUnicode_CopyCharacters(): don't check arguments and so
+ may crash if parameters are invalid (e.g. if the output string
+ is too short). */
+PyAPI_FUNC(void) _PyUnicode_FastCopyCharacters(
+ PyObject *to,
+ Py_ssize_t to_start,
+ PyObject *from,
+ Py_ssize_t from_start,
+ Py_ssize_t how_many
+ );
+#endif
+
+#ifndef Py_LIMITED_API
+/* Fill a string with a character: write fill_char into
+ unicode[start:start+length].
+
+ Fail if fill_char is bigger than the string maximum character, or if the
+ string has more than 1 reference.
+
+ Return the number of written character, or return -1 and raise an exception
+ on error. */
+PyAPI_FUNC(Py_ssize_t) PyUnicode_Fill(
+ PyObject *unicode,
+ Py_ssize_t start,
+ Py_ssize_t length,
+ Py_UCS4 fill_char
+ );
+
+/* Unsafe version of PyUnicode_Fill(): don't check arguments and so may crash
+ if parameters are invalid (e.g. if length is longer than the string). */
+PyAPI_FUNC(void) _PyUnicode_FastFill(
+ PyObject *unicode,
+ Py_ssize_t start,
+ Py_ssize_t length,
+ Py_UCS4 fill_char
+ );
+#endif
+
+/* Create a Unicode Object from the Py_UNICODE buffer u of the given
+ size.
+
+ u may be NULL which causes the contents to be undefined. It is the
+ user's responsibility to fill in the needed data afterwards. Note
+ that modifying the Unicode object contents after construction is
+ only allowed if u was set to NULL.
+
+ The buffer is copied into the new object. */
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
+ const Py_UNICODE *u, /* Unicode buffer */
+ Py_ssize_t size /* size of buffer */
+ ) /* Py_DEPRECATED(3.3) */;
+#endif
+
+/* Similar to PyUnicode_FromUnicode(), but u points to UTF-8 encoded bytes */
+PyAPI_FUNC(PyObject*) PyUnicode_FromStringAndSize(
+ const char *u, /* UTF-8 encoded string */
+ Py_ssize_t size /* size of buffer */
+ );
+
+/* Similar to PyUnicode_FromUnicode(), but u points to null-terminated
+ UTF-8 encoded bytes. The size is determined with strlen(). */
+PyAPI_FUNC(PyObject*) PyUnicode_FromString(
+ const char *u /* UTF-8 encoded string */
+ );
+
+#ifndef Py_LIMITED_API
+/* Create a new string from a buffer of Py_UCS1, Py_UCS2 or Py_UCS4 characters.
+ Scan the string to find the maximum character. */
+PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
+ int kind,
+ const void *buffer,
+ Py_ssize_t size);
+
+/* Create a new string from a buffer of ASCII characters.
+ WARNING: Don't check if the string contains any non-ASCII character. */
+PyAPI_FUNC(PyObject*) _PyUnicode_FromASCII(
+ const char *buffer,
+ Py_ssize_t size);
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject*) PyUnicode_Substring(
+ PyObject *str,
+ Py_ssize_t start,
+ Py_ssize_t end);
+#endif
+
+#ifndef Py_LIMITED_API
+/* Compute the maximum character of the substring unicode[start:end].
+ Return 127 for an empty string. */
+PyAPI_FUNC(Py_UCS4) _PyUnicode_FindMaxChar (
+ PyObject *unicode,
+ Py_ssize_t start,
+ Py_ssize_t end);
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+/* Copy the string into a UCS4 buffer including the null character if copy_null
+ is set. Return NULL and raise an exception on error. Raise a SystemError if
+ the buffer is smaller than the string. Return buffer on success.
+
+ buflen is the length of the buffer in (Py_UCS4) characters. */
+PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4(
+ PyObject *unicode,
+ Py_UCS4* buffer,
+ Py_ssize_t buflen,
+ int copy_null);
+
+/* Copy the string into a UCS4 buffer. A new buffer is allocated using
+ * PyMem_Malloc; if this fails, NULL is returned with a memory error
+ exception set. */
+PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4Copy(PyObject *unicode);
+#endif
+
+#ifndef Py_LIMITED_API
+/* Return a read-only pointer to the Unicode object's internal
+ Py_UNICODE buffer.
+ If the wchar_t/Py_UNICODE representation is not yet available, this
+ function will calculate it. */
+
+PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
+ PyObject *unicode /* Unicode object */
+ ) /* Py_DEPRECATED(3.3) */;
+
+/* Similar to PyUnicode_AsUnicode(), but raises a ValueError if the string
+ contains null characters. */
+PyAPI_FUNC(const Py_UNICODE *) _PyUnicode_AsUnicode(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* Return a read-only pointer to the Unicode object's internal
+ Py_UNICODE buffer and save the length at size.
+ If the wchar_t/Py_UNICODE representation is not yet available, this
+ function will calculate it. */
+
+PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicodeAndSize(
+ PyObject *unicode, /* Unicode object */
+ Py_ssize_t *size /* location where to save the length */
+ ) /* Py_DEPRECATED(3.3) */;
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+/* Get the length of the Unicode object. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_GetLength(
+ PyObject *unicode
+);
+#endif
+
+/* Get the number of Py_UNICODE units in the
+ string representation. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
+ PyObject *unicode /* Unicode object */
+ ) Py_DEPRECATED(3.3);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+/* Read a character from the string. */
+
+PyAPI_FUNC(Py_UCS4) PyUnicode_ReadChar(
+ PyObject *unicode,
+ Py_ssize_t index
+ );
+
+/* Write a character to the string. The string must have been created through
+ PyUnicode_New, must not be shared, and must not have been hashed yet.
+
+ Return 0 on success, -1 on error. */
+
+PyAPI_FUNC(int) PyUnicode_WriteChar(
+ PyObject *unicode,
+ Py_ssize_t index,
+ Py_UCS4 character
+ );
+#endif
+
+#ifndef Py_LIMITED_API
+/* Get the maximum ordinal for a Unicode character. */
+PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void) Py_DEPRECATED(3.3);
+#endif
+
+/* Resize a Unicode object. The length is the number of characters, except
+ if the kind of the string is PyUnicode_WCHAR_KIND: in this case, the length
+ is the number of Py_UNICODE characters.
+
+ *unicode is modified to point to the new (resized) object and 0
+ returned on success.
+
+ Try to resize the string in place (which is usually faster than allocating
+ a new string and copy characters), or create a new string.
+
+ Error handling is implemented as follows: an exception is set, -1
+ is returned and *unicode left untouched.
+
+ WARNING: The function doesn't check string content, the result may not be a
+ string in canonical representation. */
+
+PyAPI_FUNC(int) PyUnicode_Resize(
+ PyObject **unicode, /* Pointer to the Unicode object */
+ Py_ssize_t length /* New length */
+ );
+
+/* Decode obj to a Unicode object.
+
+ bytes, bytearray and other bytes-like objects are decoded according to the
+ given encoding and error handler. The encoding and error handler can be
+ NULL to have the interface use UTF-8 and "strict".
+
+ All other objects (including Unicode objects) raise an exception.
+
+ The API returns NULL in case of an error. The caller is responsible
+ for decref'ing the returned objects.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
+ PyObject *obj, /* Object */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ );
+
+/* Copy an instance of a Unicode subtype to a new true Unicode object if
+ necessary. If obj is already a true Unicode object (not a subtype), return
+ the reference with *incremented* refcount.
+
+ The API returns NULL in case of an error. The caller is responsible
+ for decref'ing the returned objects.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
+ PyObject *obj /* Object */
+ );
+
+PyAPI_FUNC(PyObject *) PyUnicode_FromFormatV(
+ const char *format, /* ASCII-encoded string */
+ va_list vargs
+ );
+PyAPI_FUNC(PyObject *) PyUnicode_FromFormat(
+ const char *format, /* ASCII-encoded string */
+ ...
+ );
+
+#ifndef Py_LIMITED_API
+typedef struct {
+ PyObject *buffer;
+ void *data;
+ enum PyUnicode_Kind kind;
+ Py_UCS4 maxchar;
+ Py_ssize_t size;
+ Py_ssize_t pos;
+
+ /* minimum number of allocated characters (default: 0) */
+ Py_ssize_t min_length;
+
+ /* minimum character (default: 127, ASCII) */
+ Py_UCS4 min_char;
+
+ /* If non-zero, overallocate the buffer (default: 0). */
+ unsigned char overallocate;
+
+ /* If readonly is 1, buffer is a shared string (cannot be modified)
+ and size is set to 0. */
+ unsigned char readonly;
+} _PyUnicodeWriter ;
+
+/* Initialize a Unicode writer.
+ *
+ * By default, the minimum buffer size is 0 character and overallocation is
+ * disabled. Set min_length, min_char and overallocate attributes to control
+ * the allocation of the buffer. */
+PyAPI_FUNC(void)
+_PyUnicodeWriter_Init(_PyUnicodeWriter *writer);
+
+/* Prepare the buffer to write 'length' characters
+ with the specified maximum character.
+
+ Return 0 on success, raise an exception and return -1 on error. */
+#define _PyUnicodeWriter_Prepare(WRITER, LENGTH, MAXCHAR) \
+ (((MAXCHAR) <= (WRITER)->maxchar \
+ && (LENGTH) <= (WRITER)->size - (WRITER)->pos) \
+ ? 0 \
+ : (((LENGTH) == 0) \
+ ? 0 \
+ : _PyUnicodeWriter_PrepareInternal((WRITER), (LENGTH), (MAXCHAR))))
+
+/* Don't call this function directly, use the _PyUnicodeWriter_Prepare() macro
+ instead. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
+ Py_ssize_t length, Py_UCS4 maxchar);
+
+/* Prepare the buffer to have at least the kind KIND.
+ For example, kind=PyUnicode_2BYTE_KIND ensures that the writer will
+ support characters in range U+000-U+FFFF.
+
+ Return 0 on success, raise an exception and return -1 on error. */
+#define _PyUnicodeWriter_PrepareKind(WRITER, KIND) \
+ (assert((KIND) != PyUnicode_WCHAR_KIND), \
+ (KIND) <= (WRITER)->kind \
+ ? 0 \
+ : _PyUnicodeWriter_PrepareKindInternal((WRITER), (KIND)))
+
+/* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind()
+ macro instead. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
+ enum PyUnicode_Kind kind);
+
+/* Append a Unicode character.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteChar(_PyUnicodeWriter *writer,
+ Py_UCS4 ch
+ );
+
+/* Append a Unicode string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer,
+ PyObject *str /* Unicode string */
+ );
+
+/* Append a substring of a Unicode string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteSubstring(_PyUnicodeWriter *writer,
+ PyObject *str, /* Unicode string */
+ Py_ssize_t start,
+ Py_ssize_t end
+ );
+
+/* Append an ASCII-encoded byte string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteASCIIString(_PyUnicodeWriter *writer,
+ const char *str, /* ASCII-encoded byte string */
+ Py_ssize_t len /* number of bytes, or -1 if unknown */
+ );
+
+/* Append a latin1-encoded byte string.
+ Return 0 on success, raise an exception and return -1 on error. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
+ const char *str, /* latin1-encoded byte string */
+ Py_ssize_t len /* length in bytes */
+ );
+
+/* Get the value of the writer as a Unicode string. Clear the
+ buffer of the writer. Raise an exception and return NULL
+ on error. */
+PyAPI_FUNC(PyObject *)
+_PyUnicodeWriter_Finish(_PyUnicodeWriter *writer);
+
+/* Deallocate memory of a writer (clear its internal buffer). */
+PyAPI_FUNC(void)
+_PyUnicodeWriter_Dealloc(_PyUnicodeWriter *writer);
+#endif
+
+#ifndef Py_LIMITED_API
+/* Format the object based on the format_spec, as defined in PEP 3101
+ (Advanced String Formatting). */
+PyAPI_FUNC(int) _PyUnicode_FormatAdvancedWriter(
+ _PyUnicodeWriter *writer,
+ PyObject *obj,
+ PyObject *format_spec,
+ Py_ssize_t start,
+ Py_ssize_t end);
+#endif
+
+PyAPI_FUNC(void) PyUnicode_InternInPlace(PyObject **);
+PyAPI_FUNC(void) PyUnicode_InternImmortal(PyObject **);
+PyAPI_FUNC(PyObject *) PyUnicode_InternFromString(
+ const char *u /* UTF-8 encoded string */
+ );
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void) _Py_ReleaseInternedUnicodeStrings(void);
+#endif
+
+/* Use only if you know it's a string */
+#define PyUnicode_CHECK_INTERNED(op) \
+ (((PyASCIIObject *)(op))->state.interned)
+
+/* --- wchar_t support for platforms which support it --------------------- */
+
+#ifdef HAVE_WCHAR_H
+
+/* Create a Unicode Object from the wchar_t buffer w of the given
+ size.
+
+ The buffer is copied into the new object. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar(
+ const wchar_t *w, /* wchar_t buffer */
+ Py_ssize_t size /* size of buffer */
+ );
+
+/* Copies the Unicode Object contents into the wchar_t buffer w. At
+ most size wchar_t characters are copied.
+
+ Note that the resulting wchar_t string may or may not be
+ 0-terminated. It is the responsibility of the caller to make sure
+ that the wchar_t string is 0-terminated in case this is required by
+ the application.
+
+ Returns the number of wchar_t characters copied (excluding a
+ possibly trailing 0-termination character) or -1 in case of an
+ error. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
+ PyObject *unicode, /* Unicode object */
+ wchar_t *w, /* wchar_t buffer */
+ Py_ssize_t size /* size of buffer */
+ );
+
+/* Convert the Unicode object to a wide character string. The output string
+ always ends with a nul character. If size is not NULL, write the number of
+ wide characters (excluding the null character) into *size.
+
+ Returns a buffer allocated by PyMem_Malloc() (use PyMem_Free() to free it)
+ on success. On error, returns NULL, *size is undefined and raises a
+ MemoryError. */
+
+PyAPI_FUNC(wchar_t*) PyUnicode_AsWideCharString(
+ PyObject *unicode, /* Unicode object */
+ Py_ssize_t *size /* number of characters of the result */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(void*) _PyUnicode_AsKind(PyObject *s, unsigned int kind);
+#endif
+
+#endif
+
+/* --- Unicode ordinals --------------------------------------------------- */
+
+/* Create a Unicode Object from the given Unicode code point ordinal.
+
+ The ordinal must be in range(0x110000). A ValueError is
+ raised in case it is not.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);
+
+/* --- Free-list management ----------------------------------------------- */
+
+/* Clear the free list used by the Unicode implementation.
+
+ This can be used to release memory used for objects on the free
+ list back to the Python memory allocator.
+
+*/
+
+PyAPI_FUNC(int) PyUnicode_ClearFreeList(void);
+
+/* === Builtin Codecs =====================================================
+
+ Many of these APIs take two arguments encoding and errors. These
+ parameters encoding and errors have the same semantics as the ones
+ of the builtin str() API.
+
+ Setting encoding to NULL causes the default encoding (UTF-8) to be used.
+
+ Error handling is set by errors which may also be set to NULL
+ meaning to use the default handling defined for the codec. Default
+ error handling for all builtin codecs is "strict" (ValueErrors are
+ raised).
+
+ The codecs all use a similar interface. Only deviation from the
+ generic ones are documented.
+
+*/
+
+/* --- Manage the default encoding ---------------------------------------- */
+
+/* Returns a pointer to the default encoding (UTF-8) of the
+ Unicode object unicode and the size of the encoded representation
+ in bytes stored in *size.
+
+ In case of an error, no *size is set.
+
+ This function caches the UTF-8 encoded string in the unicodeobject
+ and subsequent calls will return the same string. The memory is released
+ when the unicodeobject is deallocated.
+
+ _PyUnicode_AsStringAndSize is a #define for PyUnicode_AsUTF8AndSize to
+ support the previous internal function with the same behaviour.
+
+ *** This API is for interpreter INTERNAL USE ONLY and will likely
+ *** be removed or changed in the future.
+
+ *** If you need to access the Unicode object as UTF-8 bytes string,
+ *** please use PyUnicode_AsUTF8String() instead.
+*/
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
+ PyObject *unicode,
+ Py_ssize_t *size);
+#define _PyUnicode_AsStringAndSize PyUnicode_AsUTF8AndSize
+#endif
+
+/* Returns a pointer to the default encoding (UTF-8) of the
+ Unicode object unicode.
+
+ Like PyUnicode_AsUTF8AndSize(), this also caches the UTF-8 representation
+ in the unicodeobject.
+
+ _PyUnicode_AsString is a #define for PyUnicode_AsUTF8 to
+ support the previous internal function with the same behaviour.
+
+ Use of this API is DEPRECATED since no size information can be
+ extracted from the returned data.
+
+ *** This API is for interpreter INTERNAL USE ONLY and will likely
+ *** be removed or changed for Python 3.1.
+
+ *** If you need to access the Unicode object as UTF-8 bytes string,
+ *** please use PyUnicode_AsUTF8String() instead.
+
+*/
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);
+#define _PyUnicode_AsString PyUnicode_AsUTF8
+#endif
+
+/* Returns "utf-8". */
+
+PyAPI_FUNC(const char*) PyUnicode_GetDefaultEncoding(void);
+
+/* --- Generic Codecs ----------------------------------------------------- */
+
+/* Create a Unicode object by decoding the encoded string s of the
+ given size. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_Decode(
+ const char *s, /* encoded string */
+ Py_ssize_t size, /* size of buffer */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ );
+
+/* Decode a Unicode object unicode and return the result as Python
+ object.
+
+ This API is DEPRECATED. The only supported standard encoding is rot13.
+ Use PyCodec_Decode() to decode with rot13 and non-standard codecs
+ that decode from str. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsDecodedObject(
+ PyObject *unicode, /* Unicode object */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.6);
+
+/* Decode a Unicode object unicode and return the result as Unicode
+ object.
+
+ This API is DEPRECATED. The only supported standard encoding is rot13.
+ Use PyCodec_Decode() to decode with rot13 and non-standard codecs
+ that decode from str to str. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsDecodedUnicode(
+ PyObject *unicode, /* Unicode object */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.6);
+
+/* Encodes a Py_UNICODE buffer of the given size and returns a
+ Python string object. */
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_Encode(
+ const Py_UNICODE *s, /* Unicode char buffer */
+ Py_ssize_t size, /* number of Py_UNICODE chars to encode */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* Encodes a Unicode object and returns the result as Python
+ object.
+
+ This API is DEPRECATED. It is superseded by PyUnicode_AsEncodedString()
+ since all standard encodings (except rot13) encode str to bytes.
+ Use PyCodec_Encode() for encoding with rot13 and non-standard codecs
+ that encode form str to non-bytes. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedObject(
+ PyObject *unicode, /* Unicode object */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.6);
+
+/* Encodes a Unicode object and returns the result as Python string
+ object. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString(
+ PyObject *unicode, /* Unicode object */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ );
+
+/* Encodes a Unicode object and returns the result as Unicode
+ object.
+
+ This API is DEPRECATED. The only supported standard encodings is rot13.
+ Use PyCodec_Encode() to encode with rot13 and non-standard codecs
+ that encode from str to str. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedUnicode(
+ PyObject *unicode, /* Unicode object */
+ const char *encoding, /* encoding */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.6);
+
+/* Build an encoding map. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_BuildEncodingMap(
+ PyObject* string /* 256 character map */
+ );
+
+/* --- UTF-7 Codecs ------------------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
+ const char *string, /* UTF-7 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7Stateful(
+ const char *string, /* UTF-7 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ Py_ssize_t *consumed /* bytes consumed */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ int base64SetO, /* Encode RFC2152 Set O characters in base64 */
+ int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF7(
+ PyObject *unicode, /* Unicode object */
+ int base64SetO, /* Encode RFC2152 Set O characters in base64 */
+ int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
+ const char *errors /* error handling */
+ );
+#endif
+
+/* --- UTF-8 Codecs ------------------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8(
+ const char *string, /* UTF-8 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8Stateful(
+ const char *string, /* UTF-8 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ Py_ssize_t *consumed /* bytes consumed */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
+ PyObject *unicode /* Unicode object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) _PyUnicode_AsUTF8String(
+ PyObject *unicode,
+ const char *errors);
+
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* --- UTF-32 Codecs ------------------------------------------------------ */
+
+/* Decodes length bytes from a UTF-32 encoded buffer string and returns
+ the corresponding Unicode object.
+
+ errors (if non-NULL) defines the error handling. It defaults
+ to "strict".
+
+ If byteorder is non-NULL, the decoder starts decoding using the
+ given byte order:
+
+ *byteorder == -1: little endian
+ *byteorder == 0: native order
+ *byteorder == 1: big endian
+
+ In native mode, the first four bytes of the stream are checked for a
+ BOM mark. If found, the BOM mark is analysed, the byte order
+ adjusted and the BOM skipped. In the other modes, no BOM mark
+ interpretation is done. After completion, *byteorder is set to the
+ current byte order at the end of input data.
+
+ If byteorder is NULL, the codec starts in native order mode.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF32(
+ const char *string, /* UTF-32 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ int *byteorder /* pointer to byteorder to use
+ 0=native;-1=LE,1=BE; updated on
+ exit */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF32Stateful(
+ const char *string, /* UTF-32 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ int *byteorder, /* pointer to byteorder to use
+ 0=native;-1=LE,1=BE; updated on
+ exit */
+ Py_ssize_t *consumed /* bytes consumed */
+ );
+
+/* Returns a Python string using the UTF-32 encoding in native byte
+ order. The string always starts with a BOM mark. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsUTF32String(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* Returns a Python string object holding the UTF-32 encoded value of
+ the Unicode data.
+
+ If byteorder is not 0, output is written according to the following
+ byte order:
+
+ byteorder == -1: little endian
+ byteorder == 0: native byte order (writes a BOM mark)
+ byteorder == 1: big endian
+
+ If byteorder is 0, the output string will always start with the
+ Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
+ prepended.
+
+*/
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF32(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ ) Py_DEPRECATED(3.3);
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF32(
+ PyObject *object, /* Unicode object */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ );
+#endif
+
+/* --- UTF-16 Codecs ------------------------------------------------------ */
+
+/* Decodes length bytes from a UTF-16 encoded buffer string and returns
+ the corresponding Unicode object.
+
+ errors (if non-NULL) defines the error handling. It defaults
+ to "strict".
+
+ If byteorder is non-NULL, the decoder starts decoding using the
+ given byte order:
+
+ *byteorder == -1: little endian
+ *byteorder == 0: native order
+ *byteorder == 1: big endian
+
+ In native mode, the first two bytes of the stream are checked for a
+ BOM mark. If found, the BOM mark is analysed, the byte order
+ adjusted and the BOM skipped. In the other modes, no BOM mark
+ interpretation is done. After completion, *byteorder is set to the
+ current byte order at the end of input data.
+
+ If byteorder is NULL, the codec starts in native order mode.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16(
+ const char *string, /* UTF-16 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ int *byteorder /* pointer to byteorder to use
+ 0=native;-1=LE,1=BE; updated on
+ exit */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16Stateful(
+ const char *string, /* UTF-16 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ int *byteorder, /* pointer to byteorder to use
+ 0=native;-1=LE,1=BE; updated on
+ exit */
+ Py_ssize_t *consumed /* bytes consumed */
+ );
+
+/* Returns a Python string using the UTF-16 encoding in native byte
+ order. The string always starts with a BOM mark. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsUTF16String(
+ PyObject *unicode /* Unicode object */
+ );
+
+/* Returns a Python string object holding the UTF-16 encoded value of
+ the Unicode data.
+
+ If byteorder is not 0, output is written according to the following
+ byte order:
+
+ byteorder == -1: little endian
+ byteorder == 0: native byte order (writes a BOM mark)
+ byteorder == 1: big endian
+
+ If byteorder is 0, the output string will always start with the
+ Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
+ prepended.
+
+ Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
+ UCS-2. This trick makes it possible to add full UTF-16 capabilities
+ at a later point without compromising the APIs.
+
+*/
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ ) Py_DEPRECATED(3.3);
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF16(
+ PyObject* unicode, /* Unicode object */
+ const char *errors, /* error handling */
+ int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
+ );
+#endif
+
+/* --- Unicode-Escape Codecs ---------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeUnicodeEscape(
+ const char *string, /* Unicode-Escape encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+#ifndef Py_LIMITED_API
+/* Helper for PyUnicode_DecodeUnicodeEscape that detects invalid escape
+ chars. */
+PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscape(
+ const char *string, /* Unicode-Escape encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ const char **first_invalid_escape /* on return, points to first
+ invalid escaped char in
+ string. */
+);
+#endif
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsUnicodeEscapeString(
+ PyObject *unicode /* Unicode object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length /* Number of Py_UNICODE chars to encode */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeRawUnicodeEscape(
+ const char *string, /* Raw-Unicode-Escape encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsRawUnicodeEscapeString(
+ PyObject *unicode /* Unicode object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length /* Number of Py_UNICODE chars to encode */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* --- Unicode Internal Codec ---------------------------------------------
+
+ Only for internal use in _codecsmodule.c */
+
+#ifndef Py_LIMITED_API
+PyObject *_PyUnicode_DecodeUnicodeInternal(
+ const char *string,
+ Py_ssize_t length,
+ const char *errors
+ );
+#endif
+
+/* --- Latin-1 Codecs -----------------------------------------------------
+
+ Note: Latin-1 corresponds to the first 256 Unicode ordinals.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeLatin1(
+ const char *string, /* Latin-1 encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsLatin1String(
+ PyObject *unicode /* Unicode object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) _PyUnicode_AsLatin1String(
+ PyObject* unicode,
+ const char* errors);
+
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* --- ASCII Codecs -------------------------------------------------------
+
+ Only 7-bit ASCII data is excepted. All other codes generate errors.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeASCII(
+ const char *string, /* ASCII encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsASCIIString(
+ PyObject *unicode /* Unicode object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) _PyUnicode_AsASCIIString(
+ PyObject* unicode,
+ const char* errors);
+
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+/* --- Character Map Codecs -----------------------------------------------
+
+ This codec uses mappings to encode and decode characters.
+
+ Decoding mappings must map byte ordinals (integers in the range from 0 to
+ 255) to Unicode strings, integers (which are then interpreted as Unicode
+ ordinals) or None. Unmapped data bytes (ones which cause a LookupError)
+ as well as mapped to None, 0xFFFE or '\ufffe' are treated as "undefined
+ mapping" and cause an error.
+
+ Encoding mappings must map Unicode ordinal integers to bytes objects,
+ integers in the range from 0 to 255 or None. Unmapped character
+ ordinals (ones which cause a LookupError) as well as mapped to
+ None are treated as "undefined mapping" and cause an error.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeCharmap(
+ const char *string, /* Encoded string */
+ Py_ssize_t length, /* size of string */
+ PyObject *mapping, /* decoding mapping */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsCharmapString(
+ PyObject *unicode, /* Unicode object */
+ PyObject *mapping /* encoding mapping */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ PyObject *mapping, /* encoding mapping */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+PyAPI_FUNC(PyObject*) _PyUnicode_EncodeCharmap(
+ PyObject *unicode, /* Unicode object */
+ PyObject *mapping, /* encoding mapping */
+ const char *errors /* error handling */
+ );
+#endif
+
+/* Translate a Py_UNICODE buffer of the given length by applying a
+ character mapping table to it and return the resulting Unicode
+ object.
+
+ The mapping table must map Unicode ordinal integers to Unicode strings,
+ Unicode ordinal integers or None (causing deletion of the character).
+
+ Mapping tables may be dictionaries or sequences. Unmapped character
+ ordinals (ones which cause a LookupError) are left untouched and
+ are copied as-is.
+
+*/
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ PyObject *table, /* Translate table */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+#ifdef MS_WINDOWS
+
+/* --- MBCS codecs for Windows -------------------------------------------- */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCS(
+ const char *string, /* MBCS encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors /* error handling */
+ );
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCSStateful(
+ const char *string, /* MBCS encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ Py_ssize_t *consumed /* bytes consumed */
+ );
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeCodePageStateful(
+ int code_page, /* code page number */
+ const char *string, /* encoded string */
+ Py_ssize_t length, /* size of string */
+ const char *errors, /* error handling */
+ Py_ssize_t *consumed /* bytes consumed */
+ );
+#endif
+
+PyAPI_FUNC(PyObject*) PyUnicode_AsMBCSString(
+ PyObject *unicode /* Unicode object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS(
+ const Py_UNICODE *data, /* Unicode char buffer */
+ Py_ssize_t length, /* number of Py_UNICODE chars to encode */
+ const char *errors /* error handling */
+ ) Py_DEPRECATED(3.3);
+#endif
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeCodePage(
+ int code_page, /* code page number */
+ PyObject *unicode, /* Unicode object */
+ const char *errors /* error handling */
+ );
+#endif
+
+#endif /* MS_WINDOWS */
+
+#ifndef Py_LIMITED_API
+/* --- Decimal Encoder ---------------------------------------------------- */
+
+/* Takes a Unicode string holding a decimal value and writes it into
+ an output buffer using standard ASCII digit codes.
+
+ The output buffer has to provide at least length+1 bytes of storage
+ area. The output string is 0-terminated.
+
+ The encoder converts whitespace to ' ', decimal characters to their
+ corresponding ASCII digit and all other Latin-1 characters except
+ \0 as-is. Characters outside this range (Unicode ordinals 1-256)
+ are treated as errors. This includes embedded NULL bytes.
+
+ Error handling is defined by the errors argument:
+
+ NULL or "strict": raise a ValueError
+ "ignore": ignore the wrong characters (these are not copied to the
+ output buffer)
+ "replace": replaces illegal characters with '?'
+
+ Returns 0 on success, -1 on failure.
+
+*/
+
+PyAPI_FUNC(int) PyUnicode_EncodeDecimal(
+ Py_UNICODE *s, /* Unicode buffer */
+ Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
+ char *output, /* Output buffer; must have size >= length */
+ const char *errors /* error handling */
+ ) /* Py_DEPRECATED(3.3) */;
+
+/* Transforms code points that have decimal digit property to the
+ corresponding ASCII digit code points.
+
+ Returns a new Unicode string on success, NULL on failure.
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_TransformDecimalToASCII(
+ Py_UNICODE *s, /* Unicode buffer */
+ Py_ssize_t length /* Number of Py_UNICODE chars to transform */
+ ) /* Py_DEPRECATED(3.3) */;
+
+/* Coverts a Unicode object holding a decimal value to an ASCII string
+ for using in int, float and complex parsers.
+ Transforms code points that have decimal digit property to the
+ corresponding ASCII digit code points. Transforms spaces to ASCII.
+ Transforms code points starting from the first non-ASCII code point that
+ is neither a decimal digit nor a space to the end into '?'. */
+
+PyAPI_FUNC(PyObject*) _PyUnicode_TransformDecimalAndSpaceToASCII(
+ PyObject *unicode /* Unicode object */
+ );
+#endif
+
+/* --- Locale encoding --------------------------------------------------- */
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+/* Decode a string from the current locale encoding. The decoder is strict if
+ *surrogateescape* is equal to zero, otherwise it uses the 'surrogateescape'
+ error handler (PEP 383) to escape undecodable bytes. If a byte sequence can
+ be decoded as a surrogate character and *surrogateescape* is not equal to
+ zero, the byte sequence is escaped using the 'surrogateescape' error handler
+ instead of being decoded. *str* must end with a null character but cannot
+ contain embedded null characters. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeLocaleAndSize(
+ const char *str,
+ Py_ssize_t len,
+ const char *errors);
+
+/* Similar to PyUnicode_DecodeLocaleAndSize(), but compute the string
+ length using strlen(). */
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeLocale(
+ const char *str,
+ const char *errors);
+
+/* Encode a Unicode object to the current locale encoding. The encoder is
+ strict is *surrogateescape* is equal to zero, otherwise the
+ "surrogateescape" error handler is used. Return a bytes object. The string
+ cannot contain embedded null characters. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeLocale(
+ PyObject *unicode,
+ const char *errors
+ );
+#endif
+
+/* --- File system encoding ---------------------------------------------- */
+
+/* ParseTuple converter: encode str objects to bytes using
+ PyUnicode_EncodeFSDefault(); bytes objects are output as-is. */
+
+PyAPI_FUNC(int) PyUnicode_FSConverter(PyObject*, void*);
+
+/* ParseTuple converter: decode bytes objects to unicode using
+ PyUnicode_DecodeFSDefaultAndSize(); str objects are output as-is. */
+
+PyAPI_FUNC(int) PyUnicode_FSDecoder(PyObject*, void*);
+
+/* Decode a null-terminated string using Py_FileSystemDefaultEncoding
+ and the "surrogateescape" error handler.
+
+ If Py_FileSystemDefaultEncoding is not set, fall back to the locale
+ encoding.
+
+ Use PyUnicode_DecodeFSDefaultAndSize() if the string length is known.
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeFSDefault(
+ const char *s /* encoded string */
+ );
+
+/* Decode a string using Py_FileSystemDefaultEncoding
+ and the "surrogateescape" error handler.
+
+ If Py_FileSystemDefaultEncoding is not set, fall back to the locale
+ encoding.
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_DecodeFSDefaultAndSize(
+ const char *s, /* encoded string */
+ Py_ssize_t size /* size */
+ );
+
+/* Encode a Unicode object to Py_FileSystemDefaultEncoding with the
+ "surrogateescape" error handler, and return bytes.
+
+ If Py_FileSystemDefaultEncoding is not set, fall back to the locale
+ encoding.
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_EncodeFSDefault(
+ PyObject *unicode
+ );
+
+/* --- Methods & Slots ----------------------------------------------------
+
+ These are capable of handling Unicode objects and strings on input
+ (we refer to them as strings in the descriptions) and return
+ Unicode objects or integers as appropriate. */
+
+/* Concat two strings giving a new Unicode string. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_Concat(
+ PyObject *left, /* Left string */
+ PyObject *right /* Right string */
+ );
+
+/* Concat two strings and put the result in *pleft
+ (sets *pleft to NULL on error) */
+
+PyAPI_FUNC(void) PyUnicode_Append(
+ PyObject **pleft, /* Pointer to left string */
+ PyObject *right /* Right string */
+ );
+
+/* Concat two strings, put the result in *pleft and drop the right object
+ (sets *pleft to NULL on error) */
+
+PyAPI_FUNC(void) PyUnicode_AppendAndDel(
+ PyObject **pleft, /* Pointer to left string */
+ PyObject *right /* Right string */
+ );
+
+/* Split a string giving a list of Unicode strings.
+
+ If sep is NULL, splitting will be done at all whitespace
+ substrings. Otherwise, splits occur at the given separator.
+
+ At most maxsplit splits will be done. If negative, no limit is set.
+
+ Separators are not included in the resulting list.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_Split(
+ PyObject *s, /* String to split */
+ PyObject *sep, /* String separator */
+ Py_ssize_t maxsplit /* Maxsplit count */
+ );
+
+/* Dito, but split at line breaks.
+
+ CRLF is considered to be one line break. Line breaks are not
+ included in the resulting list. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_Splitlines(
+ PyObject *s, /* String to split */
+ int keepends /* If true, line end markers are included */
+ );
+
+/* Partition a string using a given separator. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_Partition(
+ PyObject *s, /* String to partition */
+ PyObject *sep /* String separator */
+ );
+
+/* Partition a string using a given separator, searching from the end of the
+ string. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_RPartition(
+ PyObject *s, /* String to partition */
+ PyObject *sep /* String separator */
+ );
+
+/* Split a string giving a list of Unicode strings.
+
+ If sep is NULL, splitting will be done at all whitespace
+ substrings. Otherwise, splits occur at the given separator.
+
+ At most maxsplit splits will be done. But unlike PyUnicode_Split
+ PyUnicode_RSplit splits from the end of the string. If negative,
+ no limit is set.
+
+ Separators are not included in the resulting list.
+
+*/
+
+PyAPI_FUNC(PyObject*) PyUnicode_RSplit(
+ PyObject *s, /* String to split */
+ PyObject *sep, /* String separator */
+ Py_ssize_t maxsplit /* Maxsplit count */
+ );
+
+/* Translate a string by applying a character mapping table to it and
+ return the resulting Unicode object.
+
+ The mapping table must map Unicode ordinal integers to Unicode strings,
+ Unicode ordinal integers or None (causing deletion of the character).
+
+ Mapping tables may be dictionaries or sequences. Unmapped character
+ ordinals (ones which cause a LookupError) are left untouched and
+ are copied as-is.
+
+*/
+
+PyAPI_FUNC(PyObject *) PyUnicode_Translate(
+ PyObject *str, /* String */
+ PyObject *table, /* Translate table */
+ const char *errors /* error handling */
+ );
+
+/* Join a sequence of strings using the given separator and return
+ the resulting Unicode string. */
+
+PyAPI_FUNC(PyObject*) PyUnicode_Join(
+ PyObject *separator, /* Separator string */
+ PyObject *seq /* Sequence object */
+ );
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyUnicode_JoinArray(
+ PyObject *separator,
+ PyObject *const *items,
+ Py_ssize_t seqlen
+ );
+#endif /* Py_LIMITED_API */
+
+/* Return 1 if substr matches str[start:end] at the given tail end, 0
+ otherwise. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_Tailmatch(
+ PyObject *str, /* String */
+ PyObject *substr, /* Prefix or Suffix string */
+ Py_ssize_t start, /* Start index */
+ Py_ssize_t end, /* Stop index */
+ int direction /* Tail end: -1 prefix, +1 suffix */
+ );
+
+/* Return the first position of substr in str[start:end] using the
+ given search direction or -1 if not found. -2 is returned in case
+ an error occurred and an exception is set. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_Find(
+ PyObject *str, /* String */
+ PyObject *substr, /* Substring to find */
+ Py_ssize_t start, /* Start index */
+ Py_ssize_t end, /* Stop index */
+ int direction /* Find direction: +1 forward, -1 backward */
+ );
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
+/* Like PyUnicode_Find, but search for single character only. */
+PyAPI_FUNC(Py_ssize_t) PyUnicode_FindChar(
+ PyObject *str,
+ Py_UCS4 ch,
+ Py_ssize_t start,
+ Py_ssize_t end,
+ int direction
+ );
+#endif
+
+/* Count the number of occurrences of substr in str[start:end]. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_Count(
+ PyObject *str, /* String */
+ PyObject *substr, /* Substring to count */
+ Py_ssize_t start, /* Start index */
+ Py_ssize_t end /* Stop index */
+ );
+
+/* Replace at most maxcount occurrences of substr in str with replstr
+ and return the resulting Unicode object. */
+
+PyAPI_FUNC(PyObject *) PyUnicode_Replace(
+ PyObject *str, /* String */
+ PyObject *substr, /* Substring to find */
+ PyObject *replstr, /* Substring to replace */
+ Py_ssize_t maxcount /* Max. number of replacements to apply;
+ -1 = all */
+ );
+
+/* Compare two strings and return -1, 0, 1 for less than, equal,
+ greater than resp.
+ Raise an exception and return -1 on error. */
+
+PyAPI_FUNC(int) PyUnicode_Compare(
+ PyObject *left, /* Left string */
+ PyObject *right /* Right string */
+ );
+
+#ifndef Py_LIMITED_API
+/* Test whether a unicode is equal to ASCII identifier. Return 1 if true,
+ 0 otherwise. The right argument must be ASCII identifier.
+ Any error occurs inside will be cleared before return. */
+
+PyAPI_FUNC(int) _PyUnicode_EqualToASCIIId(
+ PyObject *left, /* Left string */
+ _Py_Identifier *right /* Right identifier */
+ );
+#endif
+
+/* Compare a Unicode object with C string and return -1, 0, 1 for less than,
+ equal, and greater than, respectively. It is best to pass only
+ ASCII-encoded strings, but the function interprets the input string as
+ ISO-8859-1 if it contains non-ASCII characters.
+ This function does not raise exceptions. */
+
+PyAPI_FUNC(int) PyUnicode_CompareWithASCIIString(
+ PyObject *left,
+ const char *right /* ASCII-encoded string */
+ );
+
+#ifndef Py_LIMITED_API
+/* Test whether a unicode is equal to ASCII string. Return 1 if true,
+ 0 otherwise. The right argument must be ASCII-encoded string.
+ Any error occurs inside will be cleared before return. */
+
+PyAPI_FUNC(int) _PyUnicode_EqualToASCIIString(
+ PyObject *left,
+ const char *right /* ASCII-encoded string */
+ );
+#endif
+
+/* Rich compare two strings and return one of the following:
+
+ - NULL in case an exception was raised
+ - Py_True or Py_False for successful comparisons
+ - Py_NotImplemented in case the type combination is unknown
+
+ Possible values for op:
+
+ Py_GT, Py_GE, Py_EQ, Py_NE, Py_LT, Py_LE
+
+*/
+
+PyAPI_FUNC(PyObject *) PyUnicode_RichCompare(
+ PyObject *left, /* Left string */
+ PyObject *right, /* Right string */
+ int op /* Operation: Py_EQ, Py_NE, Py_GT, etc. */
+ );
+
+/* Apply an argument tuple or dictionary to a format string and return
+ the resulting Unicode string. */
+
+PyAPI_FUNC(PyObject *) PyUnicode_Format(
+ PyObject *format, /* Format string */
+ PyObject *args /* Argument tuple or dictionary */
+ );
+
+/* Checks whether element is contained in container and return 1/0
+ accordingly.
+
+ element has to coerce to a one element Unicode string. -1 is
+ returned in case of an error. */
+
+PyAPI_FUNC(int) PyUnicode_Contains(
+ PyObject *container, /* Container string */
+ PyObject *element /* Element string */
+ );
+
+/* Checks whether argument is a valid identifier. */
+
+PyAPI_FUNC(int) PyUnicode_IsIdentifier(PyObject *s);
+
+#ifndef Py_LIMITED_API
+/* Externally visible for str.strip(unicode) */
+PyAPI_FUNC(PyObject *) _PyUnicode_XStrip(
+ PyObject *self,
+ int striptype,
+ PyObject *sepobj
+ );
+#endif
+
+/* Using explicit passed-in values, insert the thousands grouping
+ into the string pointed to by buffer. For the argument descriptions,
+ see Objects/stringlib/localeutil.h */
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) _PyUnicode_InsertThousandsGrouping(
+ PyObject *unicode,
+ Py_ssize_t index,
+ Py_ssize_t n_buffer,
+ void *digits,
+ Py_ssize_t n_digits,
+ Py_ssize_t min_width,
+ const char *grouping,
+ PyObject *thousands_sep,
+ Py_UCS4 *maxchar);
+#endif
+/* === Characters Type APIs =============================================== */
+
+/* Helper array used by Py_UNICODE_ISSPACE(). */
+
+#ifndef Py_LIMITED_API
+PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];
+
+/* These should not be used directly. Use the Py_UNICODE_IS* and
+ Py_UNICODE_TO* macros instead.
+
+ These APIs are implemented in Objects/unicodectype.c.
+
+*/
+
+PyAPI_FUNC(int) _PyUnicode_IsLowercase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsUppercase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsTitlecase(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsXidStart(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsXidContinue(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsWhitespace(
+ const Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
+ const Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(Py_UCS4) _PyUnicode_ToLowercase(
+ Py_UCS4 ch /* Unicode character */
+ ) /* Py_DEPRECATED(3.3) */;
+
+PyAPI_FUNC(Py_UCS4) _PyUnicode_ToUppercase(
+ Py_UCS4 ch /* Unicode character */
+ ) /* Py_DEPRECATED(3.3) */;
+
+PyAPI_FUNC(Py_UCS4) _PyUnicode_ToTitlecase(
+ Py_UCS4 ch /* Unicode character */
+ ) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(int) _PyUnicode_ToLowerFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToTitleFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToUpperFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToFoldedFull(
+ Py_UCS4 ch, /* Unicode character */
+ Py_UCS4 *res
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsCaseIgnorable(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsCased(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_ToDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(double) _PyUnicode_ToNumeric(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsDigit(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsNumeric(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsPrintable(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(int) _PyUnicode_IsAlpha(
+ Py_UCS4 ch /* Unicode character */
+ );
+
+PyAPI_FUNC(size_t) Py_UNICODE_strlen(
+ const Py_UNICODE *u
+ ) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcpy(
+ Py_UNICODE *s1,
+ const Py_UNICODE *s2) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcat(
+ Py_UNICODE *s1, const Py_UNICODE *s2) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strncpy(
+ Py_UNICODE *s1,
+ const Py_UNICODE *s2,
+ size_t n) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(int) Py_UNICODE_strcmp(
+ const Py_UNICODE *s1,
+ const Py_UNICODE *s2
+ ) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(int) Py_UNICODE_strncmp(
+ const Py_UNICODE *s1,
+ const Py_UNICODE *s2,
+ size_t n
+ ) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strchr(
+ const Py_UNICODE *s,
+ Py_UNICODE c
+ ) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strrchr(
+ const Py_UNICODE *s,
+ Py_UNICODE c
+ ) Py_DEPRECATED(3.3);
+
+PyAPI_FUNC(PyObject*) _PyUnicode_FormatLong(PyObject *, int, int, int);
+
+/* Create a copy of a unicode string ending with a nul character. Return NULL
+ and raise a MemoryError exception on memory allocation failure, otherwise
+ return a new allocated buffer (use PyMem_Free() to free the buffer). */
+
+PyAPI_FUNC(Py_UNICODE*) PyUnicode_AsUnicodeCopy(
+ PyObject *unicode
+ ) Py_DEPRECATED(3.3);
+#endif /* Py_LIMITED_API */
+
+#if defined(Py_DEBUG) && !defined(Py_LIMITED_API)
+PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
+ PyObject *op,
+ int check_content);
+#elif !defined(NDEBUG)
+/* For asserts that call _PyUnicode_CheckConsistency(), which would
+ * otherwise be a problem when building with asserts but without Py_DEBUG. */
+#define _PyUnicode_CheckConsistency(op, check_content) PyUnicode_Check(op)
+#endif
+
+#ifndef Py_LIMITED_API
+/* Return an interned Unicode object for an Identifier; may fail if there is no memory.*/
+PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
+/* Clear all static strings. */
+PyAPI_FUNC(void) _PyUnicode_ClearStaticStrings(void);
+
+/* Fast equality check when the inputs are known to be exact unicode types
+ and where the hash values are equal (i.e. a very probable match) */
+PyAPI_FUNC(int) _PyUnicode_EQ(PyObject *, PyObject *);
+#endif /* !Py_LIMITED_API */
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_UNICODEOBJECT_H */
diff --git a/Include/warnings.h b/Include/warnings.h
new file mode 100644
index 0000000..a675bb5
--- /dev/null
+++ b/Include/warnings.h
@@ -0,0 +1,67 @@
+#ifndef Py_WARNINGS_H
+#define Py_WARNINGS_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject*) _PyWarnings_Init(void);
+#endif
+
+PyAPI_FUNC(int) PyErr_WarnEx(
+ PyObject *category,
+ const char *message, /* UTF-8 encoded string */
+ Py_ssize_t stack_level);
+PyAPI_FUNC(int) PyErr_WarnFormat(
+ PyObject *category,
+ Py_ssize_t stack_level,
+ const char *format, /* ASCII-encoded string */
+ ...);
+
+#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03060000
+/* Emit a ResourceWarning warning */
+PyAPI_FUNC(int) PyErr_ResourceWarning(
+ PyObject *source,
+ Py_ssize_t stack_level,
+ const char *format, /* ASCII-encoded string */
+ ...);
+#endif
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int) PyErr_WarnExplicitObject(
+ PyObject *category,
+ PyObject *message,
+ PyObject *filename,
+ int lineno,
+ PyObject *module,
+ PyObject *registry);
+#endif
+PyAPI_FUNC(int) PyErr_WarnExplicit(
+ PyObject *category,
+ const char *message, /* UTF-8 encoded string */
+ const char *filename, /* decoded from the filesystem encoding */
+ int lineno,
+ const char *module, /* UTF-8 encoded string */
+ PyObject *registry);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(int)
+PyErr_WarnExplicitFormat(PyObject *category,
+ const char *filename, int lineno,
+ const char *module, PyObject *registry,
+ const char *format, ...);
+#endif
+
+/* DEPRECATED: Use PyErr_WarnEx() instead. */
+#ifndef Py_LIMITED_API
+#define PyErr_Warn(category, msg) PyErr_WarnEx(category, msg, 1)
+#endif
+
+#ifndef Py_LIMITED_API
+void _PyErr_WarnUnawaitedCoroutine(PyObject *coro);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_WARNINGS_H */
+
diff --git a/Include/weakrefobject.h b/Include/weakrefobject.h
new file mode 100644
index 0000000..1705156
--- /dev/null
+++ b/Include/weakrefobject.h
@@ -0,0 +1,86 @@
+/* Weak references objects for Python. */
+
+#ifndef Py_WEAKREFOBJECT_H
+#define Py_WEAKREFOBJECT_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+typedef struct _PyWeakReference PyWeakReference;
+
+/* PyWeakReference is the base struct for the Python ReferenceType, ProxyType,
+ * and CallableProxyType.
+ */
+#ifndef Py_LIMITED_API
+struct _PyWeakReference {
+ PyObject_HEAD
+
+ /* The object to which this is a weak reference, or Py_None if none.
+ * Note that this is a stealth reference: wr_object's refcount is
+ * not incremented to reflect this pointer.
+ */
+ PyObject *wr_object;
+
+ /* A callable to invoke when wr_object dies, or NULL if none. */
+ PyObject *wr_callback;
+
+ /* A cache for wr_object's hash code. As usual for hashes, this is -1
+ * if the hash code isn't known yet.
+ */
+ Py_hash_t hash;
+
+ /* If wr_object is weakly referenced, wr_object has a doubly-linked NULL-
+ * terminated list of weak references to it. These are the list pointers.
+ * If wr_object goes away, wr_object is set to Py_None, and these pointers
+ * have no meaning then.
+ */
+ PyWeakReference *wr_prev;
+ PyWeakReference *wr_next;
+};
+#endif
+
+PyAPI_DATA(PyTypeObject) _PyWeakref_RefType;
+PyAPI_DATA(PyTypeObject) _PyWeakref_ProxyType;
+PyAPI_DATA(PyTypeObject) _PyWeakref_CallableProxyType;
+
+#define PyWeakref_CheckRef(op) PyObject_TypeCheck(op, &_PyWeakref_RefType)
+#define PyWeakref_CheckRefExact(op) \
+ (Py_TYPE(op) == &_PyWeakref_RefType)
+#define PyWeakref_CheckProxy(op) \
+ ((Py_TYPE(op) == &_PyWeakref_ProxyType) || \
+ (Py_TYPE(op) == &_PyWeakref_CallableProxyType))
+
+#define PyWeakref_Check(op) \
+ (PyWeakref_CheckRef(op) || PyWeakref_CheckProxy(op))
+
+
+PyAPI_FUNC(PyObject *) PyWeakref_NewRef(PyObject *ob,
+ PyObject *callback);
+PyAPI_FUNC(PyObject *) PyWeakref_NewProxy(PyObject *ob,
+ PyObject *callback);
+PyAPI_FUNC(PyObject *) PyWeakref_GetObject(PyObject *ref);
+
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(Py_ssize_t) _PyWeakref_GetWeakrefCount(PyWeakReference *head);
+
+PyAPI_FUNC(void) _PyWeakref_ClearRef(PyWeakReference *self);
+#endif
+
+/* Explanation for the Py_REFCNT() check: when a weakref's target is part
+ of a long chain of deallocations which triggers the trashcan mechanism,
+ clearing the weakrefs can be delayed long after the target's refcount
+ has dropped to zero. In the meantime, code accessing the weakref will
+ be able to "see" the target object even though it is supposed to be
+ unreachable. See issue #16602. */
+
+#define PyWeakref_GET_OBJECT(ref) \
+ (Py_REFCNT(((PyWeakReference *)(ref))->wr_object) > 0 \
+ ? ((PyWeakReference *)(ref))->wr_object \
+ : Py_None)
+
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_WEAKREFOBJECT_H */
diff --git a/Lib/__future__.py b/Lib/__future__.py
new file mode 100644
index 0000000..ce8bed7
--- /dev/null
+++ b/Lib/__future__.py
@@ -0,0 +1,146 @@
+"""Record of phased-in incompatible language changes.
+
+Each line is of the form:
+
+ FeatureName = "_Feature(" OptionalRelease "," MandatoryRelease ","
+ CompilerFlag ")"
+
+where, normally, OptionalRelease < MandatoryRelease, and both are 5-tuples
+of the same form as sys.version_info:
+
+ (PY_MAJOR_VERSION, # the 2 in 2.1.0a3; an int
+ PY_MINOR_VERSION, # the 1; an int
+ PY_MICRO_VERSION, # the 0; an int
+ PY_RELEASE_LEVEL, # "alpha", "beta", "candidate" or "final"; string
+ PY_RELEASE_SERIAL # the 3; an int
+ )
+
+OptionalRelease records the first release in which
+
+ from __future__ import FeatureName
+
+was accepted.
+
+In the case of MandatoryReleases that have not yet occurred,
+MandatoryRelease predicts the release in which the feature will become part
+of the language.
+
+Else MandatoryRelease records when the feature became part of the language;
+in releases at or after that, modules no longer need
+
+ from __future__ import FeatureName
+
+to use the feature in question, but may continue to use such imports.
+
+MandatoryRelease may also be None, meaning that a planned feature got
+dropped.
+
+Instances of class _Feature have two corresponding methods,
+.getOptionalRelease() and .getMandatoryRelease().
+
+CompilerFlag is the (bitfield) flag that should be passed in the fourth
+argument to the builtin function compile() to enable the feature in
+dynamically compiled code. This flag is stored in the .compiler_flag
+attribute on _Future instances. These values must match the appropriate
+#defines of CO_xxx flags in Include/compile.h.
+
+No feature line is ever to be deleted from this file.
+"""
+
+all_feature_names = [
+ "nested_scopes",
+ "generators",
+ "division",
+ "absolute_import",
+ "with_statement",
+ "print_function",
+ "unicode_literals",
+ "barry_as_FLUFL",
+ "generator_stop",
+ "annotations",
+]
+
+__all__ = ["all_feature_names"] + all_feature_names
+
+# The CO_xxx symbols are defined here under the same names defined in
+# code.h and used by compile.h, so that an editor search will find them here.
+# However, they're not exported in __all__, because they don't really belong to
+# this module.
+CO_NESTED = 0x0010 # nested_scopes
+CO_GENERATOR_ALLOWED = 0 # generators (obsolete, was 0x1000)
+CO_FUTURE_DIVISION = 0x2000 # division
+CO_FUTURE_ABSOLUTE_IMPORT = 0x4000 # perform absolute imports by default
+CO_FUTURE_WITH_STATEMENT = 0x8000 # with statement
+CO_FUTURE_PRINT_FUNCTION = 0x10000 # print function
+CO_FUTURE_UNICODE_LITERALS = 0x20000 # unicode string literals
+CO_FUTURE_BARRY_AS_BDFL = 0x40000
+CO_FUTURE_GENERATOR_STOP = 0x80000 # StopIteration becomes RuntimeError in generators
+CO_FUTURE_ANNOTATIONS = 0x100000 # annotations become strings at runtime
+
+class _Feature:
+ def __init__(self, optionalRelease, mandatoryRelease, compiler_flag):
+ self.optional = optionalRelease
+ self.mandatory = mandatoryRelease
+ self.compiler_flag = compiler_flag
+
+ def getOptionalRelease(self):
+ """Return first release in which this feature was recognized.
+
+ This is a 5-tuple, of the same form as sys.version_info.
+ """
+
+ return self.optional
+
+ def getMandatoryRelease(self):
+ """Return release in which this feature will become mandatory.
+
+ This is a 5-tuple, of the same form as sys.version_info, or, if
+ the feature was dropped, is None.
+ """
+
+ return self.mandatory
+
+ def __repr__(self):
+ return "_Feature" + repr((self.optional,
+ self.mandatory,
+ self.compiler_flag))
+
+nested_scopes = _Feature((2, 1, 0, "beta", 1),
+ (2, 2, 0, "alpha", 0),
+ CO_NESTED)
+
+generators = _Feature((2, 2, 0, "alpha", 1),
+ (2, 3, 0, "final", 0),
+ CO_GENERATOR_ALLOWED)
+
+division = _Feature((2, 2, 0, "alpha", 2),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_DIVISION)
+
+absolute_import = _Feature((2, 5, 0, "alpha", 1),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_ABSOLUTE_IMPORT)
+
+with_statement = _Feature((2, 5, 0, "alpha", 1),
+ (2, 6, 0, "alpha", 0),
+ CO_FUTURE_WITH_STATEMENT)
+
+print_function = _Feature((2, 6, 0, "alpha", 2),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_PRINT_FUNCTION)
+
+unicode_literals = _Feature((2, 6, 0, "alpha", 2),
+ (3, 0, 0, "alpha", 0),
+ CO_FUTURE_UNICODE_LITERALS)
+
+barry_as_FLUFL = _Feature((3, 1, 0, "alpha", 2),
+ (3, 9, 0, "alpha", 0),
+ CO_FUTURE_BARRY_AS_BDFL)
+
+generator_stop = _Feature((3, 5, 0, "beta", 1),
+ (3, 7, 0, "alpha", 0),
+ CO_FUTURE_GENERATOR_STOP)
+
+annotations = _Feature((3, 7, 0, "beta", 1),
+ (4, 0, 0, "alpha", 0),
+ CO_FUTURE_ANNOTATIONS)
diff --git a/Lib/__pycache__/__future__.cpython-37.pyc b/Lib/__pycache__/__future__.cpython-37.pyc
new file mode 100644
index 0000000..1abffea
Binary files /dev/null and b/Lib/__pycache__/__future__.cpython-37.pyc differ
diff --git a/Lib/__pycache__/_bootlocale.cpython-37.pyc b/Lib/__pycache__/_bootlocale.cpython-37.pyc
new file mode 100644
index 0000000..25c4a80
Binary files /dev/null and b/Lib/__pycache__/_bootlocale.cpython-37.pyc differ
diff --git a/Lib/__pycache__/_collections_abc.cpython-37.pyc b/Lib/__pycache__/_collections_abc.cpython-37.pyc
new file mode 100644
index 0000000..c8a1019
Binary files /dev/null and b/Lib/__pycache__/_collections_abc.cpython-37.pyc differ
diff --git a/Lib/__pycache__/_weakrefset.cpython-37.pyc b/Lib/__pycache__/_weakrefset.cpython-37.pyc
new file mode 100644
index 0000000..d7fa2ff
Binary files /dev/null and b/Lib/__pycache__/_weakrefset.cpython-37.pyc differ
diff --git a/Lib/__pycache__/abc.cpython-37.pyc b/Lib/__pycache__/abc.cpython-37.pyc
new file mode 100644
index 0000000..ff8efe2
Binary files /dev/null and b/Lib/__pycache__/abc.cpython-37.pyc differ
diff --git a/Lib/__pycache__/base64.cpython-37.pyc b/Lib/__pycache__/base64.cpython-37.pyc
new file mode 100644
index 0000000..365994c
Binary files /dev/null and b/Lib/__pycache__/base64.cpython-37.pyc differ
diff --git a/Lib/__pycache__/bisect.cpython-37.pyc b/Lib/__pycache__/bisect.cpython-37.pyc
new file mode 100644
index 0000000..c0c7823
Binary files /dev/null and b/Lib/__pycache__/bisect.cpython-37.pyc differ
diff --git a/Lib/__pycache__/codecs.cpython-37.pyc b/Lib/__pycache__/codecs.cpython-37.pyc
new file mode 100644
index 0000000..43bce67
Binary files /dev/null and b/Lib/__pycache__/codecs.cpython-37.pyc differ
diff --git a/Lib/__pycache__/copy.cpython-37.pyc b/Lib/__pycache__/copy.cpython-37.pyc
new file mode 100644
index 0000000..cf4d18d
Binary files /dev/null and b/Lib/__pycache__/copy.cpython-37.pyc differ
diff --git a/Lib/__pycache__/copyreg.cpython-37.pyc b/Lib/__pycache__/copyreg.cpython-37.pyc
new file mode 100644
index 0000000..5e198c6
Binary files /dev/null and b/Lib/__pycache__/copyreg.cpython-37.pyc differ
diff --git a/Lib/__pycache__/enum.cpython-37.pyc b/Lib/__pycache__/enum.cpython-37.pyc
new file mode 100644
index 0000000..2f055cb
Binary files /dev/null and b/Lib/__pycache__/enum.cpython-37.pyc differ
diff --git a/Lib/__pycache__/fnmatch.cpython-37.pyc b/Lib/__pycache__/fnmatch.cpython-37.pyc
new file mode 100644
index 0000000..dc38c9d
Binary files /dev/null and b/Lib/__pycache__/fnmatch.cpython-37.pyc differ
diff --git a/Lib/__pycache__/functools.cpython-37.pyc b/Lib/__pycache__/functools.cpython-37.pyc
new file mode 100644
index 0000000..28b2e09
Binary files /dev/null and b/Lib/__pycache__/functools.cpython-37.pyc differ
diff --git a/Lib/__pycache__/genericpath.cpython-37.pyc b/Lib/__pycache__/genericpath.cpython-37.pyc
new file mode 100644
index 0000000..a82bd18
Binary files /dev/null and b/Lib/__pycache__/genericpath.cpython-37.pyc differ
diff --git a/Lib/__pycache__/hashlib.cpython-37.pyc b/Lib/__pycache__/hashlib.cpython-37.pyc
new file mode 100644
index 0000000..6aec5e3
Binary files /dev/null and b/Lib/__pycache__/hashlib.cpython-37.pyc differ
diff --git a/Lib/__pycache__/heapq.cpython-37.pyc b/Lib/__pycache__/heapq.cpython-37.pyc
new file mode 100644
index 0000000..7dc5bd7
Binary files /dev/null and b/Lib/__pycache__/heapq.cpython-37.pyc differ
diff --git a/Lib/__pycache__/hmac.cpython-37.pyc b/Lib/__pycache__/hmac.cpython-37.pyc
new file mode 100644
index 0000000..4e755e0
Binary files /dev/null and b/Lib/__pycache__/hmac.cpython-37.pyc differ
diff --git a/Lib/__pycache__/imp.cpython-37.pyc b/Lib/__pycache__/imp.cpython-37.pyc
new file mode 100644
index 0000000..e26fe20
Binary files /dev/null and b/Lib/__pycache__/imp.cpython-37.pyc differ
diff --git a/Lib/__pycache__/io.cpython-37.pyc b/Lib/__pycache__/io.cpython-37.pyc
new file mode 100644
index 0000000..81aaaa0
Binary files /dev/null and b/Lib/__pycache__/io.cpython-37.pyc differ
diff --git a/Lib/__pycache__/keyword.cpython-37.pyc b/Lib/__pycache__/keyword.cpython-37.pyc
new file mode 100644
index 0000000..a1abc38
Binary files /dev/null and b/Lib/__pycache__/keyword.cpython-37.pyc differ
diff --git a/Lib/__pycache__/linecache.cpython-37.pyc b/Lib/__pycache__/linecache.cpython-37.pyc
new file mode 100644
index 0000000..79c769a
Binary files /dev/null and b/Lib/__pycache__/linecache.cpython-37.pyc differ
diff --git a/Lib/__pycache__/locale.cpython-37.pyc b/Lib/__pycache__/locale.cpython-37.pyc
new file mode 100644
index 0000000..a9f75f0
Binary files /dev/null and b/Lib/__pycache__/locale.cpython-37.pyc differ
diff --git a/Lib/__pycache__/ntpath.cpython-37.pyc b/Lib/__pycache__/ntpath.cpython-37.pyc
new file mode 100644
index 0000000..afc6a5f
Binary files /dev/null and b/Lib/__pycache__/ntpath.cpython-37.pyc differ
diff --git a/Lib/__pycache__/operator.cpython-37.pyc b/Lib/__pycache__/operator.cpython-37.pyc
new file mode 100644
index 0000000..f083885
Binary files /dev/null and b/Lib/__pycache__/operator.cpython-37.pyc differ
diff --git a/Lib/__pycache__/os.cpython-37.pyc b/Lib/__pycache__/os.cpython-37.pyc
new file mode 100644
index 0000000..a7b779b
Binary files /dev/null and b/Lib/__pycache__/os.cpython-37.pyc differ
diff --git a/Lib/__pycache__/posixpath.cpython-37.pyc b/Lib/__pycache__/posixpath.cpython-37.pyc
new file mode 100644
index 0000000..101a720
Binary files /dev/null and b/Lib/__pycache__/posixpath.cpython-37.pyc differ
diff --git a/Lib/__pycache__/random.cpython-37.pyc b/Lib/__pycache__/random.cpython-37.pyc
new file mode 100644
index 0000000..195fa8c
Binary files /dev/null and b/Lib/__pycache__/random.cpython-37.pyc differ
diff --git a/Lib/__pycache__/re.cpython-37.pyc b/Lib/__pycache__/re.cpython-37.pyc
new file mode 100644
index 0000000..ae68c9c
Binary files /dev/null and b/Lib/__pycache__/re.cpython-37.pyc differ
diff --git a/Lib/__pycache__/reprlib.cpython-37.pyc b/Lib/__pycache__/reprlib.cpython-37.pyc
new file mode 100644
index 0000000..474c453
Binary files /dev/null and b/Lib/__pycache__/reprlib.cpython-37.pyc differ
diff --git a/Lib/__pycache__/shutil.cpython-37.pyc b/Lib/__pycache__/shutil.cpython-37.pyc
new file mode 100644
index 0000000..3fa7edc
Binary files /dev/null and b/Lib/__pycache__/shutil.cpython-37.pyc differ
diff --git a/Lib/__pycache__/site.cpython-37.pyc b/Lib/__pycache__/site.cpython-37.pyc
new file mode 100644
index 0000000..74d86a6
Binary files /dev/null and b/Lib/__pycache__/site.cpython-37.pyc differ
diff --git a/Lib/__pycache__/sre_compile.cpython-37.pyc b/Lib/__pycache__/sre_compile.cpython-37.pyc
new file mode 100644
index 0000000..dbce73c
Binary files /dev/null and b/Lib/__pycache__/sre_compile.cpython-37.pyc differ
diff --git a/Lib/__pycache__/sre_constants.cpython-37.pyc b/Lib/__pycache__/sre_constants.cpython-37.pyc
new file mode 100644
index 0000000..a792c7c
Binary files /dev/null and b/Lib/__pycache__/sre_constants.cpython-37.pyc differ
diff --git a/Lib/__pycache__/sre_parse.cpython-37.pyc b/Lib/__pycache__/sre_parse.cpython-37.pyc
new file mode 100644
index 0000000..e4948b1
Binary files /dev/null and b/Lib/__pycache__/sre_parse.cpython-37.pyc differ
diff --git a/Lib/__pycache__/stat.cpython-37.pyc b/Lib/__pycache__/stat.cpython-37.pyc
new file mode 100644
index 0000000..1ea7605
Binary files /dev/null and b/Lib/__pycache__/stat.cpython-37.pyc differ
diff --git a/Lib/__pycache__/struct.cpython-37.pyc b/Lib/__pycache__/struct.cpython-37.pyc
new file mode 100644
index 0000000..c73be5e
Binary files /dev/null and b/Lib/__pycache__/struct.cpython-37.pyc differ
diff --git a/Lib/__pycache__/tarfile.cpython-37.pyc b/Lib/__pycache__/tarfile.cpython-37.pyc
new file mode 100644
index 0000000..766d083
Binary files /dev/null and b/Lib/__pycache__/tarfile.cpython-37.pyc differ
diff --git a/Lib/__pycache__/tempfile.cpython-37.pyc b/Lib/__pycache__/tempfile.cpython-37.pyc
new file mode 100644
index 0000000..e08fe81
Binary files /dev/null and b/Lib/__pycache__/tempfile.cpython-37.pyc differ
diff --git a/Lib/__pycache__/token.cpython-37.pyc b/Lib/__pycache__/token.cpython-37.pyc
new file mode 100644
index 0000000..d9fde3a
Binary files /dev/null and b/Lib/__pycache__/token.cpython-37.pyc differ
diff --git a/Lib/__pycache__/tokenize.cpython-37.pyc b/Lib/__pycache__/tokenize.cpython-37.pyc
new file mode 100644
index 0000000..32bd177
Binary files /dev/null and b/Lib/__pycache__/tokenize.cpython-37.pyc differ
diff --git a/Lib/__pycache__/types.cpython-37.pyc b/Lib/__pycache__/types.cpython-37.pyc
new file mode 100644
index 0000000..10ca70a
Binary files /dev/null and b/Lib/__pycache__/types.cpython-37.pyc differ
diff --git a/Lib/__pycache__/warnings.cpython-37.pyc b/Lib/__pycache__/warnings.cpython-37.pyc
new file mode 100644
index 0000000..87b6633
Binary files /dev/null and b/Lib/__pycache__/warnings.cpython-37.pyc differ
diff --git a/Lib/__pycache__/weakref.cpython-37.pyc b/Lib/__pycache__/weakref.cpython-37.pyc
new file mode 100644
index 0000000..7a9bae9
Binary files /dev/null and b/Lib/__pycache__/weakref.cpython-37.pyc differ
diff --git a/Lib/_bootlocale.py b/Lib/_bootlocale.py
new file mode 100644
index 0000000..3273a3b
--- /dev/null
+++ b/Lib/_bootlocale.py
@@ -0,0 +1,46 @@
+"""A minimal subset of the locale module used at interpreter startup
+(imported by the _io module), in order to reduce startup time.
+
+Don't import directly from third-party code; use the `locale` module instead!
+"""
+
+import sys
+import _locale
+
+if sys.platform.startswith("win"):
+ def getpreferredencoding(do_setlocale=True):
+ if sys.flags.utf8_mode:
+ return 'UTF-8'
+ return _locale._getdefaultlocale()[1]
+else:
+ try:
+ _locale.CODESET
+ except AttributeError:
+ if hasattr(sys, 'getandroidapilevel'):
+ # On Android langinfo.h and CODESET are missing, and UTF-8 is
+ # always used in mbstowcs() and wcstombs().
+ def getpreferredencoding(do_setlocale=True):
+ return 'UTF-8'
+ else:
+ def getpreferredencoding(do_setlocale=True):
+ if sys.flags.utf8_mode:
+ return 'UTF-8'
+ # This path for legacy systems needs the more complex
+ # getdefaultlocale() function, import the full locale module.
+ import locale
+ return locale.getpreferredencoding(do_setlocale)
+ else:
+ def getpreferredencoding(do_setlocale=True):
+ assert not do_setlocale
+ if sys.flags.utf8_mode:
+ return 'UTF-8'
+ result = _locale.nl_langinfo(_locale.CODESET)
+ if not result and sys.platform == 'darwin':
+ # nl_langinfo can return an empty string
+ # when the setting has an invalid value.
+ # Default to UTF-8 in that case because
+ # UTF-8 is the default charset on OSX and
+ # returning nothing will crash the
+ # interpreter.
+ result = 'UTF-8'
+ return result
diff --git a/Lib/_collections_abc.py b/Lib/_collections_abc.py
new file mode 100644
index 0000000..dbe30df
--- /dev/null
+++ b/Lib/_collections_abc.py
@@ -0,0 +1,1011 @@
+# Copyright 2007 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+"""Abstract Base Classes (ABCs) for collections, according to PEP 3119.
+
+Unit tests are in test_collections.
+"""
+
+from abc import ABCMeta, abstractmethod
+import sys
+
+__all__ = ["Awaitable", "Coroutine",
+ "AsyncIterable", "AsyncIterator", "AsyncGenerator",
+ "Hashable", "Iterable", "Iterator", "Generator", "Reversible",
+ "Sized", "Container", "Callable", "Collection",
+ "Set", "MutableSet",
+ "Mapping", "MutableMapping",
+ "MappingView", "KeysView", "ItemsView", "ValuesView",
+ "Sequence", "MutableSequence",
+ "ByteString",
+ ]
+
+# This module has been renamed from collections.abc to _collections_abc to
+# speed up interpreter startup. Some of the types such as MutableMapping are
+# required early but collections module imports a lot of other modules.
+# See issue #19218
+__name__ = "collections.abc"
+
+# Private list of types that we want to register with the various ABCs
+# so that they will pass tests like:
+# it = iter(somebytearray)
+# assert isinstance(it, Iterable)
+# Note: in other implementations, these types might not be distinct
+# and they may have their own implementation specific types that
+# are not included on this list.
+bytes_iterator = type(iter(b''))
+bytearray_iterator = type(iter(bytearray()))
+#callable_iterator = ???
+dict_keyiterator = type(iter({}.keys()))
+dict_valueiterator = type(iter({}.values()))
+dict_itemiterator = type(iter({}.items()))
+list_iterator = type(iter([]))
+list_reverseiterator = type(iter(reversed([])))
+range_iterator = type(iter(range(0)))
+longrange_iterator = type(iter(range(1 << 1000)))
+set_iterator = type(iter(set()))
+str_iterator = type(iter(""))
+tuple_iterator = type(iter(()))
+zip_iterator = type(iter(zip()))
+## views ##
+dict_keys = type({}.keys())
+dict_values = type({}.values())
+dict_items = type({}.items())
+## misc ##
+mappingproxy = type(type.__dict__)
+generator = type((lambda: (yield))())
+## coroutine ##
+async def _coro(): pass
+_coro = _coro()
+coroutine = type(_coro)
+_coro.close() # Prevent ResourceWarning
+del _coro
+## asynchronous generator ##
+async def _ag(): yield
+_ag = _ag()
+async_generator = type(_ag)
+del _ag
+
+
+### ONE-TRICK PONIES ###
+
+def _check_methods(C, *methods):
+ mro = C.__mro__
+ for method in methods:
+ for B in mro:
+ if method in B.__dict__:
+ if B.__dict__[method] is None:
+ return NotImplemented
+ break
+ else:
+ return NotImplemented
+ return True
+
+class Hashable(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __hash__(self):
+ return 0
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Hashable:
+ return _check_methods(C, "__hash__")
+ return NotImplemented
+
+
+class Awaitable(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __await__(self):
+ yield
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Awaitable:
+ return _check_methods(C, "__await__")
+ return NotImplemented
+
+
+class Coroutine(Awaitable):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def send(self, value):
+ """Send a value into the coroutine.
+ Return next yielded value or raise StopIteration.
+ """
+ raise StopIteration
+
+ @abstractmethod
+ def throw(self, typ, val=None, tb=None):
+ """Raise an exception in the coroutine.
+ Return next yielded value or raise StopIteration.
+ """
+ if val is None:
+ if tb is None:
+ raise typ
+ val = typ()
+ if tb is not None:
+ val = val.with_traceback(tb)
+ raise val
+
+ def close(self):
+ """Raise GeneratorExit inside coroutine.
+ """
+ try:
+ self.throw(GeneratorExit)
+ except (GeneratorExit, StopIteration):
+ pass
+ else:
+ raise RuntimeError("coroutine ignored GeneratorExit")
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Coroutine:
+ return _check_methods(C, '__await__', 'send', 'throw', 'close')
+ return NotImplemented
+
+
+Coroutine.register(coroutine)
+
+
+class AsyncIterable(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __aiter__(self):
+ return AsyncIterator()
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is AsyncIterable:
+ return _check_methods(C, "__aiter__")
+ return NotImplemented
+
+
+class AsyncIterator(AsyncIterable):
+
+ __slots__ = ()
+
+ @abstractmethod
+ async def __anext__(self):
+ """Return the next item or raise StopAsyncIteration when exhausted."""
+ raise StopAsyncIteration
+
+ def __aiter__(self):
+ return self
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is AsyncIterator:
+ return _check_methods(C, "__anext__", "__aiter__")
+ return NotImplemented
+
+
+class AsyncGenerator(AsyncIterator):
+
+ __slots__ = ()
+
+ async def __anext__(self):
+ """Return the next item from the asynchronous generator.
+ When exhausted, raise StopAsyncIteration.
+ """
+ return await self.asend(None)
+
+ @abstractmethod
+ async def asend(self, value):
+ """Send a value into the asynchronous generator.
+ Return next yielded value or raise StopAsyncIteration.
+ """
+ raise StopAsyncIteration
+
+ @abstractmethod
+ async def athrow(self, typ, val=None, tb=None):
+ """Raise an exception in the asynchronous generator.
+ Return next yielded value or raise StopAsyncIteration.
+ """
+ if val is None:
+ if tb is None:
+ raise typ
+ val = typ()
+ if tb is not None:
+ val = val.with_traceback(tb)
+ raise val
+
+ async def aclose(self):
+ """Raise GeneratorExit inside coroutine.
+ """
+ try:
+ await self.athrow(GeneratorExit)
+ except (GeneratorExit, StopAsyncIteration):
+ pass
+ else:
+ raise RuntimeError("asynchronous generator ignored GeneratorExit")
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is AsyncGenerator:
+ return _check_methods(C, '__aiter__', '__anext__',
+ 'asend', 'athrow', 'aclose')
+ return NotImplemented
+
+
+AsyncGenerator.register(async_generator)
+
+
+class Iterable(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __iter__(self):
+ while False:
+ yield None
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Iterable:
+ return _check_methods(C, "__iter__")
+ return NotImplemented
+
+
+class Iterator(Iterable):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __next__(self):
+ 'Return the next item from the iterator. When exhausted, raise StopIteration'
+ raise StopIteration
+
+ def __iter__(self):
+ return self
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Iterator:
+ return _check_methods(C, '__iter__', '__next__')
+ return NotImplemented
+
+Iterator.register(bytes_iterator)
+Iterator.register(bytearray_iterator)
+#Iterator.register(callable_iterator)
+Iterator.register(dict_keyiterator)
+Iterator.register(dict_valueiterator)
+Iterator.register(dict_itemiterator)
+Iterator.register(list_iterator)
+Iterator.register(list_reverseiterator)
+Iterator.register(range_iterator)
+Iterator.register(longrange_iterator)
+Iterator.register(set_iterator)
+Iterator.register(str_iterator)
+Iterator.register(tuple_iterator)
+Iterator.register(zip_iterator)
+
+
+class Reversible(Iterable):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __reversed__(self):
+ while False:
+ yield None
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Reversible:
+ return _check_methods(C, "__reversed__", "__iter__")
+ return NotImplemented
+
+
+class Generator(Iterator):
+
+ __slots__ = ()
+
+ def __next__(self):
+ """Return the next item from the generator.
+ When exhausted, raise StopIteration.
+ """
+ return self.send(None)
+
+ @abstractmethod
+ def send(self, value):
+ """Send a value into the generator.
+ Return next yielded value or raise StopIteration.
+ """
+ raise StopIteration
+
+ @abstractmethod
+ def throw(self, typ, val=None, tb=None):
+ """Raise an exception in the generator.
+ Return next yielded value or raise StopIteration.
+ """
+ if val is None:
+ if tb is None:
+ raise typ
+ val = typ()
+ if tb is not None:
+ val = val.with_traceback(tb)
+ raise val
+
+ def close(self):
+ """Raise GeneratorExit inside generator.
+ """
+ try:
+ self.throw(GeneratorExit)
+ except (GeneratorExit, StopIteration):
+ pass
+ else:
+ raise RuntimeError("generator ignored GeneratorExit")
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Generator:
+ return _check_methods(C, '__iter__', '__next__',
+ 'send', 'throw', 'close')
+ return NotImplemented
+
+Generator.register(generator)
+
+
+class Sized(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __len__(self):
+ return 0
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Sized:
+ return _check_methods(C, "__len__")
+ return NotImplemented
+
+
+class Container(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __contains__(self, x):
+ return False
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Container:
+ return _check_methods(C, "__contains__")
+ return NotImplemented
+
+class Collection(Sized, Iterable, Container):
+
+ __slots__ = ()
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Collection:
+ return _check_methods(C, "__len__", "__iter__", "__contains__")
+ return NotImplemented
+
+class Callable(metaclass=ABCMeta):
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __call__(self, *args, **kwds):
+ return False
+
+ @classmethod
+ def __subclasshook__(cls, C):
+ if cls is Callable:
+ return _check_methods(C, "__call__")
+ return NotImplemented
+
+
+### SETS ###
+
+
+class Set(Collection):
+
+ """A set is a finite, iterable container.
+
+ This class provides concrete generic implementations of all
+ methods except for __contains__, __iter__ and __len__.
+
+ To override the comparisons (presumably for speed, as the
+ semantics are fixed), redefine __le__ and __ge__,
+ then the other operations will automatically follow suit.
+ """
+
+ __slots__ = ()
+
+ def __le__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ if len(self) > len(other):
+ return False
+ for elem in self:
+ if elem not in other:
+ return False
+ return True
+
+ def __lt__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return len(self) < len(other) and self.__le__(other)
+
+ def __gt__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return len(self) > len(other) and self.__ge__(other)
+
+ def __ge__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ if len(self) < len(other):
+ return False
+ for elem in other:
+ if elem not in self:
+ return False
+ return True
+
+ def __eq__(self, other):
+ if not isinstance(other, Set):
+ return NotImplemented
+ return len(self) == len(other) and self.__le__(other)
+
+ @classmethod
+ def _from_iterable(cls, it):
+ '''Construct an instance of the class from any iterable input.
+
+ Must override this method if the class constructor signature
+ does not accept an iterable for an input.
+ '''
+ return cls(it)
+
+ def __and__(self, other):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ return self._from_iterable(value for value in other if value in self)
+
+ __rand__ = __and__
+
+ def isdisjoint(self, other):
+ 'Return True if two sets have a null intersection.'
+ for value in other:
+ if value in self:
+ return False
+ return True
+
+ def __or__(self, other):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ chain = (e for s in (self, other) for e in s)
+ return self._from_iterable(chain)
+
+ __ror__ = __or__
+
+ def __sub__(self, other):
+ if not isinstance(other, Set):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ other = self._from_iterable(other)
+ return self._from_iterable(value for value in self
+ if value not in other)
+
+ def __rsub__(self, other):
+ if not isinstance(other, Set):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ other = self._from_iterable(other)
+ return self._from_iterable(value for value in other
+ if value not in self)
+
+ def __xor__(self, other):
+ if not isinstance(other, Set):
+ if not isinstance(other, Iterable):
+ return NotImplemented
+ other = self._from_iterable(other)
+ return (self - other) | (other - self)
+
+ __rxor__ = __xor__
+
+ def _hash(self):
+ """Compute the hash value of a set.
+
+ Note that we don't define __hash__: not all sets are hashable.
+ But if you define a hashable set type, its __hash__ should
+ call this function.
+
+ This must be compatible __eq__.
+
+ All sets ought to compare equal if they contain the same
+ elements, regardless of how they are implemented, and
+ regardless of the order of the elements; so there's not much
+ freedom for __eq__ or __hash__. We match the algorithm used
+ by the built-in frozenset type.
+ """
+ MAX = sys.maxsize
+ MASK = 2 * MAX + 1
+ n = len(self)
+ h = 1927868237 * (n + 1)
+ h &= MASK
+ for x in self:
+ hx = hash(x)
+ h ^= (hx ^ (hx << 16) ^ 89869747) * 3644798167
+ h &= MASK
+ h = h * 69069 + 907133923
+ h &= MASK
+ if h > MAX:
+ h -= MASK + 1
+ if h == -1:
+ h = 590923713
+ return h
+
+Set.register(frozenset)
+
+
+class MutableSet(Set):
+ """A mutable set is a finite, iterable container.
+
+ This class provides concrete generic implementations of all
+ methods except for __contains__, __iter__, __len__,
+ add(), and discard().
+
+ To override the comparisons (presumably for speed, as the
+ semantics are fixed), all you have to do is redefine __le__ and
+ then the other operations will automatically follow suit.
+ """
+
+ __slots__ = ()
+
+ @abstractmethod
+ def add(self, value):
+ """Add an element."""
+ raise NotImplementedError
+
+ @abstractmethod
+ def discard(self, value):
+ """Remove an element. Do not raise an exception if absent."""
+ raise NotImplementedError
+
+ def remove(self, value):
+ """Remove an element. If not a member, raise a KeyError."""
+ if value not in self:
+ raise KeyError(value)
+ self.discard(value)
+
+ def pop(self):
+ """Return the popped value. Raise KeyError if empty."""
+ it = iter(self)
+ try:
+ value = next(it)
+ except StopIteration:
+ raise KeyError from None
+ self.discard(value)
+ return value
+
+ def clear(self):
+ """This is slow (creates N new iterators!) but effective."""
+ try:
+ while True:
+ self.pop()
+ except KeyError:
+ pass
+
+ def __ior__(self, it):
+ for value in it:
+ self.add(value)
+ return self
+
+ def __iand__(self, it):
+ for value in (self - it):
+ self.discard(value)
+ return self
+
+ def __ixor__(self, it):
+ if it is self:
+ self.clear()
+ else:
+ if not isinstance(it, Set):
+ it = self._from_iterable(it)
+ for value in it:
+ if value in self:
+ self.discard(value)
+ else:
+ self.add(value)
+ return self
+
+ def __isub__(self, it):
+ if it is self:
+ self.clear()
+ else:
+ for value in it:
+ self.discard(value)
+ return self
+
+MutableSet.register(set)
+
+
+### MAPPINGS ###
+
+
+class Mapping(Collection):
+
+ __slots__ = ()
+
+ """A Mapping is a generic container for associating key/value
+ pairs.
+
+ This class provides concrete generic implementations of all
+ methods except for __getitem__, __iter__, and __len__.
+
+ """
+
+ @abstractmethod
+ def __getitem__(self, key):
+ raise KeyError
+
+ def get(self, key, default=None):
+ 'D.get(k[,d]) -> D[k] if k in D, else d. d defaults to None.'
+ try:
+ return self[key]
+ except KeyError:
+ return default
+
+ def __contains__(self, key):
+ try:
+ self[key]
+ except KeyError:
+ return False
+ else:
+ return True
+
+ def keys(self):
+ "D.keys() -> a set-like object providing a view on D's keys"
+ return KeysView(self)
+
+ def items(self):
+ "D.items() -> a set-like object providing a view on D's items"
+ return ItemsView(self)
+
+ def values(self):
+ "D.values() -> an object providing a view on D's values"
+ return ValuesView(self)
+
+ def __eq__(self, other):
+ if not isinstance(other, Mapping):
+ return NotImplemented
+ return dict(self.items()) == dict(other.items())
+
+ __reversed__ = None
+
+Mapping.register(mappingproxy)
+
+
+class MappingView(Sized):
+
+ __slots__ = '_mapping',
+
+ def __init__(self, mapping):
+ self._mapping = mapping
+
+ def __len__(self):
+ return len(self._mapping)
+
+ def __repr__(self):
+ return '{0.__class__.__name__}({0._mapping!r})'.format(self)
+
+
+class KeysView(MappingView, Set):
+
+ __slots__ = ()
+
+ @classmethod
+ def _from_iterable(self, it):
+ return set(it)
+
+ def __contains__(self, key):
+ return key in self._mapping
+
+ def __iter__(self):
+ yield from self._mapping
+
+KeysView.register(dict_keys)
+
+
+class ItemsView(MappingView, Set):
+
+ __slots__ = ()
+
+ @classmethod
+ def _from_iterable(self, it):
+ return set(it)
+
+ def __contains__(self, item):
+ key, value = item
+ try:
+ v = self._mapping[key]
+ except KeyError:
+ return False
+ else:
+ return v is value or v == value
+
+ def __iter__(self):
+ for key in self._mapping:
+ yield (key, self._mapping[key])
+
+ItemsView.register(dict_items)
+
+
+class ValuesView(MappingView, Collection):
+
+ __slots__ = ()
+
+ def __contains__(self, value):
+ for key in self._mapping:
+ v = self._mapping[key]
+ if v is value or v == value:
+ return True
+ return False
+
+ def __iter__(self):
+ for key in self._mapping:
+ yield self._mapping[key]
+
+ValuesView.register(dict_values)
+
+
+class MutableMapping(Mapping):
+
+ __slots__ = ()
+
+ """A MutableMapping is a generic container for associating
+ key/value pairs.
+
+ This class provides concrete generic implementations of all
+ methods except for __getitem__, __setitem__, __delitem__,
+ __iter__, and __len__.
+
+ """
+
+ @abstractmethod
+ def __setitem__(self, key, value):
+ raise KeyError
+
+ @abstractmethod
+ def __delitem__(self, key):
+ raise KeyError
+
+ __marker = object()
+
+ def pop(self, key, default=__marker):
+ '''D.pop(k[,d]) -> v, remove specified key and return the corresponding value.
+ If key is not found, d is returned if given, otherwise KeyError is raised.
+ '''
+ try:
+ value = self[key]
+ except KeyError:
+ if default is self.__marker:
+ raise
+ return default
+ else:
+ del self[key]
+ return value
+
+ def popitem(self):
+ '''D.popitem() -> (k, v), remove and return some (key, value) pair
+ as a 2-tuple; but raise KeyError if D is empty.
+ '''
+ try:
+ key = next(iter(self))
+ except StopIteration:
+ raise KeyError from None
+ value = self[key]
+ del self[key]
+ return key, value
+
+ def clear(self):
+ 'D.clear() -> None. Remove all items from D.'
+ try:
+ while True:
+ self.popitem()
+ except KeyError:
+ pass
+
+ def update(*args, **kwds):
+ ''' D.update([E, ]**F) -> None. Update D from mapping/iterable E and F.
+ If E present and has a .keys() method, does: for k in E: D[k] = E[k]
+ If E present and lacks .keys() method, does: for (k, v) in E: D[k] = v
+ In either case, this is followed by: for k, v in F.items(): D[k] = v
+ '''
+ if not args:
+ raise TypeError("descriptor 'update' of 'MutableMapping' object "
+ "needs an argument")
+ self, *args = args
+ if len(args) > 1:
+ raise TypeError('update expected at most 1 arguments, got %d' %
+ len(args))
+ if args:
+ other = args[0]
+ if isinstance(other, Mapping):
+ for key in other:
+ self[key] = other[key]
+ elif hasattr(other, "keys"):
+ for key in other.keys():
+ self[key] = other[key]
+ else:
+ for key, value in other:
+ self[key] = value
+ for key, value in kwds.items():
+ self[key] = value
+
+ def setdefault(self, key, default=None):
+ 'D.setdefault(k[,d]) -> D.get(k,d), also set D[k]=d if k not in D'
+ try:
+ return self[key]
+ except KeyError:
+ self[key] = default
+ return default
+
+MutableMapping.register(dict)
+
+
+### SEQUENCES ###
+
+
+class Sequence(Reversible, Collection):
+
+ """All the operations on a read-only sequence.
+
+ Concrete subclasses must override __new__ or __init__,
+ __getitem__, and __len__.
+ """
+
+ __slots__ = ()
+
+ @abstractmethod
+ def __getitem__(self, index):
+ raise IndexError
+
+ def __iter__(self):
+ i = 0
+ try:
+ while True:
+ v = self[i]
+ yield v
+ i += 1
+ except IndexError:
+ return
+
+ def __contains__(self, value):
+ for v in self:
+ if v is value or v == value:
+ return True
+ return False
+
+ def __reversed__(self):
+ for i in reversed(range(len(self))):
+ yield self[i]
+
+ def index(self, value, start=0, stop=None):
+ '''S.index(value, [start, [stop]]) -> integer -- return first index of value.
+ Raises ValueError if the value is not present.
+
+ Supporting start and stop arguments is optional, but
+ recommended.
+ '''
+ if start is not None and start < 0:
+ start = max(len(self) + start, 0)
+ if stop is not None and stop < 0:
+ stop += len(self)
+
+ i = start
+ while stop is None or i < stop:
+ try:
+ v = self[i]
+ if v is value or v == value:
+ return i
+ except IndexError:
+ break
+ i += 1
+ raise ValueError
+
+ def count(self, value):
+ 'S.count(value) -> integer -- return number of occurrences of value'
+ return sum(1 for v in self if v is value or v == value)
+
+Sequence.register(tuple)
+Sequence.register(str)
+Sequence.register(range)
+Sequence.register(memoryview)
+
+
+class ByteString(Sequence):
+
+ """This unifies bytes and bytearray.
+
+ XXX Should add all their methods.
+ """
+
+ __slots__ = ()
+
+ByteString.register(bytes)
+ByteString.register(bytearray)
+
+
+class MutableSequence(Sequence):
+
+ __slots__ = ()
+
+ """All the operations on a read-write sequence.
+
+ Concrete subclasses must provide __new__ or __init__,
+ __getitem__, __setitem__, __delitem__, __len__, and insert().
+
+ """
+
+ @abstractmethod
+ def __setitem__(self, index, value):
+ raise IndexError
+
+ @abstractmethod
+ def __delitem__(self, index):
+ raise IndexError
+
+ @abstractmethod
+ def insert(self, index, value):
+ 'S.insert(index, value) -- insert value before index'
+ raise IndexError
+
+ def append(self, value):
+ 'S.append(value) -- append value to the end of the sequence'
+ self.insert(len(self), value)
+
+ def clear(self):
+ 'S.clear() -> None -- remove all items from S'
+ try:
+ while True:
+ self.pop()
+ except IndexError:
+ pass
+
+ def reverse(self):
+ 'S.reverse() -- reverse *IN PLACE*'
+ n = len(self)
+ for i in range(n//2):
+ self[i], self[n-i-1] = self[n-i-1], self[i]
+
+ def extend(self, values):
+ 'S.extend(iterable) -- extend sequence by appending elements from the iterable'
+ for v in values:
+ self.append(v)
+
+ def pop(self, index=-1):
+ '''S.pop([index]) -> item -- remove and return item at index (default last).
+ Raise IndexError if list is empty or index is out of range.
+ '''
+ v = self[index]
+ del self[index]
+ return v
+
+ def remove(self, value):
+ '''S.remove(value) -- remove first occurrence of value.
+ Raise ValueError if the value is not present.
+ '''
+ del self[self.index(value)]
+
+ def __iadd__(self, values):
+ self.extend(values)
+ return self
+
+MutableSequence.register(list)
+MutableSequence.register(bytearray) # Multiply inheriting, see ByteString
diff --git a/Lib/_dummy_thread.py b/Lib/_dummy_thread.py
new file mode 100644
index 0000000..a2cae54
--- /dev/null
+++ b/Lib/_dummy_thread.py
@@ -0,0 +1,163 @@
+"""Drop-in replacement for the thread module.
+
+Meant to be used as a brain-dead substitute so that threaded code does
+not need to be rewritten for when the thread module is not present.
+
+Suggested usage is::
+
+ try:
+ import _thread
+ except ImportError:
+ import _dummy_thread as _thread
+
+"""
+# Exports only things specified by thread documentation;
+# skipping obsolete synonyms allocate(), start_new(), exit_thread().
+__all__ = ['error', 'start_new_thread', 'exit', 'get_ident', 'allocate_lock',
+ 'interrupt_main', 'LockType']
+
+# A dummy value
+TIMEOUT_MAX = 2**31
+
+# NOTE: this module can be imported early in the extension building process,
+# and so top level imports of other modules should be avoided. Instead, all
+# imports are done when needed on a function-by-function basis. Since threads
+# are disabled, the import lock should not be an issue anyway (??).
+
+error = RuntimeError
+
+def start_new_thread(function, args, kwargs={}):
+ """Dummy implementation of _thread.start_new_thread().
+
+ Compatibility is maintained by making sure that ``args`` is a
+ tuple and ``kwargs`` is a dictionary. If an exception is raised
+ and it is SystemExit (which can be done by _thread.exit()) it is
+ caught and nothing is done; all other exceptions are printed out
+ by using traceback.print_exc().
+
+ If the executed function calls interrupt_main the KeyboardInterrupt will be
+ raised when the function returns.
+
+ """
+ if type(args) != type(tuple()):
+ raise TypeError("2nd arg must be a tuple")
+ if type(kwargs) != type(dict()):
+ raise TypeError("3rd arg must be a dict")
+ global _main
+ _main = False
+ try:
+ function(*args, **kwargs)
+ except SystemExit:
+ pass
+ except:
+ import traceback
+ traceback.print_exc()
+ _main = True
+ global _interrupt
+ if _interrupt:
+ _interrupt = False
+ raise KeyboardInterrupt
+
+def exit():
+ """Dummy implementation of _thread.exit()."""
+ raise SystemExit
+
+def get_ident():
+ """Dummy implementation of _thread.get_ident().
+
+ Since this module should only be used when _threadmodule is not
+ available, it is safe to assume that the current process is the
+ only thread. Thus a constant can be safely returned.
+ """
+ return 1
+
+def allocate_lock():
+ """Dummy implementation of _thread.allocate_lock()."""
+ return LockType()
+
+def stack_size(size=None):
+ """Dummy implementation of _thread.stack_size()."""
+ if size is not None:
+ raise error("setting thread stack size not supported")
+ return 0
+
+def _set_sentinel():
+ """Dummy implementation of _thread._set_sentinel()."""
+ return LockType()
+
+class LockType(object):
+ """Class implementing dummy implementation of _thread.LockType.
+
+ Compatibility is maintained by maintaining self.locked_status
+ which is a boolean that stores the state of the lock. Pickling of
+ the lock, though, should not be done since if the _thread module is
+ then used with an unpickled ``lock()`` from here problems could
+ occur from this class not having atomic methods.
+
+ """
+
+ def __init__(self):
+ self.locked_status = False
+
+ def acquire(self, waitflag=None, timeout=-1):
+ """Dummy implementation of acquire().
+
+ For blocking calls, self.locked_status is automatically set to
+ True and returned appropriately based on value of
+ ``waitflag``. If it is non-blocking, then the value is
+ actually checked and not set if it is already acquired. This
+ is all done so that threading.Condition's assert statements
+ aren't triggered and throw a little fit.
+
+ """
+ if waitflag is None or waitflag:
+ self.locked_status = True
+ return True
+ else:
+ if not self.locked_status:
+ self.locked_status = True
+ return True
+ else:
+ if timeout > 0:
+ import time
+ time.sleep(timeout)
+ return False
+
+ __enter__ = acquire
+
+ def __exit__(self, typ, val, tb):
+ self.release()
+
+ def release(self):
+ """Release the dummy lock."""
+ # XXX Perhaps shouldn't actually bother to test? Could lead
+ # to problems for complex, threaded code.
+ if not self.locked_status:
+ raise error
+ self.locked_status = False
+ return True
+
+ def locked(self):
+ return self.locked_status
+
+ def __repr__(self):
+ return "<%s %s.%s object at %s>" % (
+ "locked" if self.locked_status else "unlocked",
+ self.__class__.__module__,
+ self.__class__.__qualname__,
+ hex(id(self))
+ )
+
+# Used to signal that interrupt_main was called in a "thread"
+_interrupt = False
+# True when not executing in a "thread"
+_main = True
+
+def interrupt_main():
+ """Set _interrupt flag to True to have start_new_thread raise
+ KeyboardInterrupt upon exiting."""
+ if _main:
+ raise KeyboardInterrupt
+ else:
+ global _interrupt
+ _interrupt = True
diff --git a/Lib/_weakrefset.py b/Lib/_weakrefset.py
new file mode 100644
index 0000000..304c66f
--- /dev/null
+++ b/Lib/_weakrefset.py
@@ -0,0 +1,196 @@
+# Access WeakSet through the weakref module.
+# This code is separated-out because it is needed
+# by abc.py to load everything else at startup.
+
+from _weakref import ref
+
+__all__ = ['WeakSet']
+
+
+class _IterationGuard:
+ # This context manager registers itself in the current iterators of the
+ # weak container, such as to delay all removals until the context manager
+ # exits.
+ # This technique should be relatively thread-safe (since sets are).
+
+ def __init__(self, weakcontainer):
+ # Don't create cycles
+ self.weakcontainer = ref(weakcontainer)
+
+ def __enter__(self):
+ w = self.weakcontainer()
+ if w is not None:
+ w._iterating.add(self)
+ return self
+
+ def __exit__(self, e, t, b):
+ w = self.weakcontainer()
+ if w is not None:
+ s = w._iterating
+ s.remove(self)
+ if not s:
+ w._commit_removals()
+
+
+class WeakSet:
+ def __init__(self, data=None):
+ self.data = set()
+ def _remove(item, selfref=ref(self)):
+ self = selfref()
+ if self is not None:
+ if self._iterating:
+ self._pending_removals.append(item)
+ else:
+ self.data.discard(item)
+ self._remove = _remove
+ # A list of keys to be removed
+ self._pending_removals = []
+ self._iterating = set()
+ if data is not None:
+ self.update(data)
+
+ def _commit_removals(self):
+ l = self._pending_removals
+ discard = self.data.discard
+ while l:
+ discard(l.pop())
+
+ def __iter__(self):
+ with _IterationGuard(self):
+ for itemref in self.data:
+ item = itemref()
+ if item is not None:
+ # Caveat: the iterator will keep a strong reference to
+ # `item` until it is resumed or closed.
+ yield item
+
+ def __len__(self):
+ return len(self.data) - len(self._pending_removals)
+
+ def __contains__(self, item):
+ try:
+ wr = ref(item)
+ except TypeError:
+ return False
+ return wr in self.data
+
+ def __reduce__(self):
+ return (self.__class__, (list(self),),
+ getattr(self, '__dict__', None))
+
+ def add(self, item):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.add(ref(item, self._remove))
+
+ def clear(self):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.clear()
+
+ def copy(self):
+ return self.__class__(self)
+
+ def pop(self):
+ if self._pending_removals:
+ self._commit_removals()
+ while True:
+ try:
+ itemref = self.data.pop()
+ except KeyError:
+ raise KeyError('pop from empty WeakSet') from None
+ item = itemref()
+ if item is not None:
+ return item
+
+ def remove(self, item):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.remove(ref(item))
+
+ def discard(self, item):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.discard(ref(item))
+
+ def update(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ for element in other:
+ self.add(element)
+
+ def __ior__(self, other):
+ self.update(other)
+ return self
+
+ def difference(self, other):
+ newset = self.copy()
+ newset.difference_update(other)
+ return newset
+ __sub__ = difference
+
+ def difference_update(self, other):
+ self.__isub__(other)
+ def __isub__(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if self is other:
+ self.data.clear()
+ else:
+ self.data.difference_update(ref(item) for item in other)
+ return self
+
+ def intersection(self, other):
+ return self.__class__(item for item in other if item in self)
+ __and__ = intersection
+
+ def intersection_update(self, other):
+ self.__iand__(other)
+ def __iand__(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ self.data.intersection_update(ref(item) for item in other)
+ return self
+
+ def issubset(self, other):
+ return self.data.issubset(ref(item) for item in other)
+ __le__ = issubset
+
+ def __lt__(self, other):
+ return self.data < set(map(ref, other))
+
+ def issuperset(self, other):
+ return self.data.issuperset(ref(item) for item in other)
+ __ge__ = issuperset
+
+ def __gt__(self, other):
+ return self.data > set(map(ref, other))
+
+ def __eq__(self, other):
+ if not isinstance(other, self.__class__):
+ return NotImplemented
+ return self.data == set(map(ref, other))
+
+ def symmetric_difference(self, other):
+ newset = self.copy()
+ newset.symmetric_difference_update(other)
+ return newset
+ __xor__ = symmetric_difference
+
+ def symmetric_difference_update(self, other):
+ self.__ixor__(other)
+ def __ixor__(self, other):
+ if self._pending_removals:
+ self._commit_removals()
+ if self is other:
+ self.data.clear()
+ else:
+ self.data.symmetric_difference_update(ref(item, self._remove) for item in other)
+ return self
+
+ def union(self, other):
+ return self.__class__(e for s in (self, other) for e in s)
+ __or__ = union
+
+ def isdisjoint(self, other):
+ return len(self.intersection(other)) == 0
diff --git a/Lib/abc.py b/Lib/abc.py
new file mode 100644
index 0000000..7094141
--- /dev/null
+++ b/Lib/abc.py
@@ -0,0 +1,170 @@
+# Copyright 2007 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+"""Abstract Base Classes (ABCs) according to PEP 3119."""
+
+
+def abstractmethod(funcobj):
+ """A decorator indicating abstract methods.
+
+ Requires that the metaclass is ABCMeta or derived from it. A
+ class that has a metaclass derived from ABCMeta cannot be
+ instantiated unless all of its abstract methods are overridden.
+ The abstract methods can be called using any of the normal
+ 'super' call mechanisms.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractmethod
+ def my_abstract_method(self, ...):
+ ...
+ """
+ funcobj.__isabstractmethod__ = True
+ return funcobj
+
+
+class abstractclassmethod(classmethod):
+ """A decorator indicating abstract classmethods.
+
+ Similar to abstractmethod.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractclassmethod
+ def my_abstract_classmethod(cls, ...):
+ ...
+
+ 'abstractclassmethod' is deprecated. Use 'classmethod' with
+ 'abstractmethod' instead.
+ """
+
+ __isabstractmethod__ = True
+
+ def __init__(self, callable):
+ callable.__isabstractmethod__ = True
+ super().__init__(callable)
+
+
+class abstractstaticmethod(staticmethod):
+ """A decorator indicating abstract staticmethods.
+
+ Similar to abstractmethod.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractstaticmethod
+ def my_abstract_staticmethod(...):
+ ...
+
+ 'abstractstaticmethod' is deprecated. Use 'staticmethod' with
+ 'abstractmethod' instead.
+ """
+
+ __isabstractmethod__ = True
+
+ def __init__(self, callable):
+ callable.__isabstractmethod__ = True
+ super().__init__(callable)
+
+
+class abstractproperty(property):
+ """A decorator indicating abstract properties.
+
+ Requires that the metaclass is ABCMeta or derived from it. A
+ class that has a metaclass derived from ABCMeta cannot be
+ instantiated unless all of its abstract properties are overridden.
+ The abstract properties can be called using any of the normal
+ 'super' call mechanisms.
+
+ Usage:
+
+ class C(metaclass=ABCMeta):
+ @abstractproperty
+ def my_abstract_property(self):
+ ...
+
+ This defines a read-only property; you can also define a read-write
+ abstract property using the 'long' form of property declaration:
+
+ class C(metaclass=ABCMeta):
+ def getx(self): ...
+ def setx(self, value): ...
+ x = abstractproperty(getx, setx)
+
+ 'abstractproperty' is deprecated. Use 'property' with 'abstractmethod'
+ instead.
+ """
+
+ __isabstractmethod__ = True
+
+
+try:
+ from _abc import (get_cache_token, _abc_init, _abc_register,
+ _abc_instancecheck, _abc_subclasscheck, _get_dump,
+ _reset_registry, _reset_caches)
+except ImportError:
+ from _py_abc import ABCMeta, get_cache_token
+ ABCMeta.__module__ = 'abc'
+else:
+ class ABCMeta(type):
+ """Metaclass for defining Abstract Base Classes (ABCs).
+
+ Use this metaclass to create an ABC. An ABC can be subclassed
+ directly, and then acts as a mix-in class. You can also register
+ unrelated concrete classes (even built-in classes) and unrelated
+ ABCs as 'virtual subclasses' -- these and their descendants will
+ be considered subclasses of the registering ABC by the built-in
+ issubclass() function, but the registering ABC won't show up in
+ their MRO (Method Resolution Order) nor will method
+ implementations defined by the registering ABC be callable (not
+ even via super()).
+ """
+ def __new__(mcls, name, bases, namespace, **kwargs):
+ cls = super().__new__(mcls, name, bases, namespace, **kwargs)
+ _abc_init(cls)
+ return cls
+
+ def register(cls, subclass):
+ """Register a virtual subclass of an ABC.
+
+ Returns the subclass, to allow usage as a class decorator.
+ """
+ return _abc_register(cls, subclass)
+
+ def __instancecheck__(cls, instance):
+ """Override for isinstance(instance, cls)."""
+ return _abc_instancecheck(cls, instance)
+
+ def __subclasscheck__(cls, subclass):
+ """Override for issubclass(subclass, cls)."""
+ return _abc_subclasscheck(cls, subclass)
+
+ def _dump_registry(cls, file=None):
+ """Debug helper to print the ABC registry."""
+ print(f"Class: {cls.__module__}.{cls.__qualname__}", file=file)
+ print(f"Inv. counter: {get_cache_token()}", file=file)
+ (_abc_registry, _abc_cache, _abc_negative_cache,
+ _abc_negative_cache_version) = _get_dump(cls)
+ print(f"_abc_registry: {_abc_registry!r}", file=file)
+ print(f"_abc_cache: {_abc_cache!r}", file=file)
+ print(f"_abc_negative_cache: {_abc_negative_cache!r}", file=file)
+ print(f"_abc_negative_cache_version: {_abc_negative_cache_version!r}",
+ file=file)
+
+ def _abc_registry_clear(cls):
+ """Clear the registry (for debugging or testing)."""
+ _reset_registry(cls)
+
+ def _abc_caches_clear(cls):
+ """Clear the caches (for debugging or testing)."""
+ _reset_caches(cls)
+
+
+class ABC(metaclass=ABCMeta):
+ """Helper class that provides a standard way to create an ABC using
+ inheritance.
+ """
+ __slots__ = ()
diff --git a/Lib/base64.py b/Lib/base64.py
new file mode 100644
index 0000000..eb8f258
--- /dev/null
+++ b/Lib/base64.py
@@ -0,0 +1,602 @@
+#! /usr/bin/env python3
+
+"""Base16, Base32, Base64 (RFC 3548), Base85 and Ascii85 data encodings"""
+
+# Modified 04-Oct-1995 by Jack Jansen to use binascii module
+# Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support
+# Modified 22-May-2007 by Guido van Rossum to use bytes everywhere
+
+import re
+import struct
+import binascii
+
+
+__all__ = [
+ # Legacy interface exports traditional RFC 2045 Base64 encodings
+ 'encode', 'decode', 'encodebytes', 'decodebytes',
+ # Generalized interface for other encodings
+ 'b64encode', 'b64decode', 'b32encode', 'b32decode',
+ 'b16encode', 'b16decode',
+ # Base85 and Ascii85 encodings
+ 'b85encode', 'b85decode', 'a85encode', 'a85decode',
+ # Standard Base64 encoding
+ 'standard_b64encode', 'standard_b64decode',
+ # Some common Base64 alternatives. As referenced by RFC 3458, see thread
+ # starting at:
+ #
+ # http://zgp.org/pipermail/p2p-hackers/2001-September/000316.html
+ 'urlsafe_b64encode', 'urlsafe_b64decode',
+ ]
+
+
+bytes_types = (bytes, bytearray) # Types acceptable as binary data
+
+def _bytes_from_decode_data(s):
+ if isinstance(s, str):
+ try:
+ return s.encode('ascii')
+ except UnicodeEncodeError:
+ raise ValueError('string argument should contain only ASCII characters')
+ if isinstance(s, bytes_types):
+ return s
+ try:
+ return memoryview(s).tobytes()
+ except TypeError:
+ raise TypeError("argument should be a bytes-like object or ASCII "
+ "string, not %r" % s.__class__.__name__) from None
+
+
+# Base64 encoding/decoding uses binascii
+
+def b64encode(s, altchars=None):
+ """Encode the bytes-like object s using Base64 and return a bytes object.
+
+ Optional altchars should be a byte string of length 2 which specifies an
+ alternative alphabet for the '+' and '/' characters. This allows an
+ application to e.g. generate url or filesystem safe Base64 strings.
+ """
+ encoded = binascii.b2a_base64(s, newline=False)
+ if altchars is not None:
+ assert len(altchars) == 2, repr(altchars)
+ return encoded.translate(bytes.maketrans(b'+/', altchars))
+ return encoded
+
+
+def b64decode(s, altchars=None, validate=False):
+ """Decode the Base64 encoded bytes-like object or ASCII string s.
+
+ Optional altchars must be a bytes-like object or ASCII string of length 2
+ which specifies the alternative alphabet used instead of the '+' and '/'
+ characters.
+
+ The result is returned as a bytes object. A binascii.Error is raised if
+ s is incorrectly padded.
+
+ If validate is False (the default), characters that are neither in the
+ normal base-64 alphabet nor the alternative alphabet are discarded prior
+ to the padding check. If validate is True, these non-alphabet characters
+ in the input result in a binascii.Error.
+ """
+ s = _bytes_from_decode_data(s)
+ if altchars is not None:
+ altchars = _bytes_from_decode_data(altchars)
+ assert len(altchars) == 2, repr(altchars)
+ s = s.translate(bytes.maketrans(altchars, b'+/'))
+ if validate and not re.match(b'^[A-Za-z0-9+/]*={0,2}$', s):
+ raise binascii.Error('Non-base64 digit found')
+ return binascii.a2b_base64(s)
+
+
+def standard_b64encode(s):
+ """Encode bytes-like object s using the standard Base64 alphabet.
+
+ The result is returned as a bytes object.
+ """
+ return b64encode(s)
+
+def standard_b64decode(s):
+ """Decode bytes encoded with the standard Base64 alphabet.
+
+ Argument s is a bytes-like object or ASCII string to decode. The result
+ is returned as a bytes object. A binascii.Error is raised if the input
+ is incorrectly padded. Characters that are not in the standard alphabet
+ are discarded prior to the padding check.
+ """
+ return b64decode(s)
+
+
+_urlsafe_encode_translation = bytes.maketrans(b'+/', b'-_')
+_urlsafe_decode_translation = bytes.maketrans(b'-_', b'+/')
+
+def urlsafe_b64encode(s):
+ """Encode bytes using the URL- and filesystem-safe Base64 alphabet.
+
+ Argument s is a bytes-like object to encode. The result is returned as a
+ bytes object. The alphabet uses '-' instead of '+' and '_' instead of
+ '/'.
+ """
+ return b64encode(s).translate(_urlsafe_encode_translation)
+
+def urlsafe_b64decode(s):
+ """Decode bytes using the URL- and filesystem-safe Base64 alphabet.
+
+ Argument s is a bytes-like object or ASCII string to decode. The result
+ is returned as a bytes object. A binascii.Error is raised if the input
+ is incorrectly padded. Characters that are not in the URL-safe base-64
+ alphabet, and are not a plus '+' or slash '/', are discarded prior to the
+ padding check.
+
+ The alphabet uses '-' instead of '+' and '_' instead of '/'.
+ """
+ s = _bytes_from_decode_data(s)
+ s = s.translate(_urlsafe_decode_translation)
+ return b64decode(s)
+
+
+
+# Base32 encoding/decoding must be done in Python
+_b32alphabet = b'ABCDEFGHIJKLMNOPQRSTUVWXYZ234567'
+_b32tab2 = None
+_b32rev = None
+
+def b32encode(s):
+ """Encode the bytes-like object s using Base32 and return a bytes object.
+ """
+ global _b32tab2
+ # Delay the initialization of the table to not waste memory
+ # if the function is never called
+ if _b32tab2 is None:
+ b32tab = [bytes((i,)) for i in _b32alphabet]
+ _b32tab2 = [a + b for a in b32tab for b in b32tab]
+ b32tab = None
+
+ if not isinstance(s, bytes_types):
+ s = memoryview(s).tobytes()
+ leftover = len(s) % 5
+ # Pad the last quantum with zero bits if necessary
+ if leftover:
+ s = s + b'\0' * (5 - leftover) # Don't use += !
+ encoded = bytearray()
+ from_bytes = int.from_bytes
+ b32tab2 = _b32tab2
+ for i in range(0, len(s), 5):
+ c = from_bytes(s[i: i + 5], 'big')
+ encoded += (b32tab2[c >> 30] + # bits 1 - 10
+ b32tab2[(c >> 20) & 0x3ff] + # bits 11 - 20
+ b32tab2[(c >> 10) & 0x3ff] + # bits 21 - 30
+ b32tab2[c & 0x3ff] # bits 31 - 40
+ )
+ # Adjust for any leftover partial quanta
+ if leftover == 1:
+ encoded[-6:] = b'======'
+ elif leftover == 2:
+ encoded[-4:] = b'===='
+ elif leftover == 3:
+ encoded[-3:] = b'==='
+ elif leftover == 4:
+ encoded[-1:] = b'='
+ return bytes(encoded)
+
+def b32decode(s, casefold=False, map01=None):
+ """Decode the Base32 encoded bytes-like object or ASCII string s.
+
+ Optional casefold is a flag specifying whether a lowercase alphabet is
+ acceptable as input. For security purposes, the default is False.
+
+ RFC 3548 allows for optional mapping of the digit 0 (zero) to the
+ letter O (oh), and for optional mapping of the digit 1 (one) to
+ either the letter I (eye) or letter L (el). The optional argument
+ map01 when not None, specifies which letter the digit 1 should be
+ mapped to (when map01 is not None, the digit 0 is always mapped to
+ the letter O). For security purposes the default is None, so that
+ 0 and 1 are not allowed in the input.
+
+ The result is returned as a bytes object. A binascii.Error is raised if
+ the input is incorrectly padded or if there are non-alphabet
+ characters present in the input.
+ """
+ global _b32rev
+ # Delay the initialization of the table to not waste memory
+ # if the function is never called
+ if _b32rev is None:
+ _b32rev = {v: k for k, v in enumerate(_b32alphabet)}
+ s = _bytes_from_decode_data(s)
+ if len(s) % 8:
+ raise binascii.Error('Incorrect padding')
+ # Handle section 2.4 zero and one mapping. The flag map01 will be either
+ # False, or the character to map the digit 1 (one) to. It should be
+ # either L (el) or I (eye).
+ if map01 is not None:
+ map01 = _bytes_from_decode_data(map01)
+ assert len(map01) == 1, repr(map01)
+ s = s.translate(bytes.maketrans(b'01', b'O' + map01))
+ if casefold:
+ s = s.upper()
+ # Strip off pad characters from the right. We need to count the pad
+ # characters because this will tell us how many null bytes to remove from
+ # the end of the decoded string.
+ l = len(s)
+ s = s.rstrip(b'=')
+ padchars = l - len(s)
+ # Now decode the full quanta
+ decoded = bytearray()
+ b32rev = _b32rev
+ for i in range(0, len(s), 8):
+ quanta = s[i: i + 8]
+ acc = 0
+ try:
+ for c in quanta:
+ acc = (acc << 5) + b32rev[c]
+ except KeyError:
+ raise binascii.Error('Non-base32 digit found') from None
+ decoded += acc.to_bytes(5, 'big')
+ # Process the last, partial quanta
+ if padchars:
+ acc <<= 5 * padchars
+ last = acc.to_bytes(5, 'big')
+ if padchars == 1:
+ decoded[-5:] = last[:-1]
+ elif padchars == 3:
+ decoded[-5:] = last[:-2]
+ elif padchars == 4:
+ decoded[-5:] = last[:-3]
+ elif padchars == 6:
+ decoded[-5:] = last[:-4]
+ else:
+ raise binascii.Error('Incorrect padding')
+ return bytes(decoded)
+
+
+
+# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
+# lowercase. The RFC also recommends against accepting input case
+# insensitively.
+def b16encode(s):
+ """Encode the bytes-like object s using Base16 and return a bytes object.
+ """
+ return binascii.hexlify(s).upper()
+
+
+def b16decode(s, casefold=False):
+ """Decode the Base16 encoded bytes-like object or ASCII string s.
+
+ Optional casefold is a flag specifying whether a lowercase alphabet is
+ acceptable as input. For security purposes, the default is False.
+
+ The result is returned as a bytes object. A binascii.Error is raised if
+ s is incorrectly padded or if there are non-alphabet characters present
+ in the input.
+ """
+ s = _bytes_from_decode_data(s)
+ if casefold:
+ s = s.upper()
+ if re.search(b'[^0-9A-F]', s):
+ raise binascii.Error('Non-base16 digit found')
+ return binascii.unhexlify(s)
+
+#
+# Ascii85 encoding/decoding
+#
+
+_a85chars = None
+_a85chars2 = None
+_A85START = b"<~"
+_A85END = b"~>"
+
+def _85encode(b, chars, chars2, pad=False, foldnuls=False, foldspaces=False):
+ # Helper function for a85encode and b85encode
+ if not isinstance(b, bytes_types):
+ b = memoryview(b).tobytes()
+
+ padding = (-len(b)) % 4
+ if padding:
+ b = b + b'\0' * padding
+ words = struct.Struct('!%dI' % (len(b) // 4)).unpack(b)
+
+ chunks = [b'z' if foldnuls and not word else
+ b'y' if foldspaces and word == 0x20202020 else
+ (chars2[word // 614125] +
+ chars2[word // 85 % 7225] +
+ chars[word % 85])
+ for word in words]
+
+ if padding and not pad:
+ if chunks[-1] == b'z':
+ chunks[-1] = chars[0] * 5
+ chunks[-1] = chunks[-1][:-padding]
+
+ return b''.join(chunks)
+
+def a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False):
+ """Encode bytes-like object b using Ascii85 and return a bytes object.
+
+ foldspaces is an optional flag that uses the special short sequence 'y'
+ instead of 4 consecutive spaces (ASCII 0x20) as supported by 'btoa'. This
+ feature is not supported by the "standard" Adobe encoding.
+
+ wrapcol controls whether the output should have newline (b'\\n') characters
+ added to it. If this is non-zero, each output line will be at most this
+ many characters long.
+
+ pad controls whether the input is padded to a multiple of 4 before
+ encoding. Note that the btoa implementation always pads.
+
+ adobe controls whether the encoded byte sequence is framed with <~ and ~>,
+ which is used by the Adobe implementation.
+ """
+ global _a85chars, _a85chars2
+ # Delay the initialization of tables to not waste memory
+ # if the function is never called
+ if _a85chars is None:
+ _a85chars = [bytes((i,)) for i in range(33, 118)]
+ _a85chars2 = [(a + b) for a in _a85chars for b in _a85chars]
+
+ result = _85encode(b, _a85chars, _a85chars2, pad, True, foldspaces)
+
+ if adobe:
+ result = _A85START + result
+ if wrapcol:
+ wrapcol = max(2 if adobe else 1, wrapcol)
+ chunks = [result[i: i + wrapcol]
+ for i in range(0, len(result), wrapcol)]
+ if adobe:
+ if len(chunks[-1]) + 2 > wrapcol:
+ chunks.append(b'')
+ result = b'\n'.join(chunks)
+ if adobe:
+ result += _A85END
+
+ return result
+
+def a85decode(b, *, foldspaces=False, adobe=False, ignorechars=b' \t\n\r\v'):
+ """Decode the Ascii85 encoded bytes-like object or ASCII string b.
+
+ foldspaces is a flag that specifies whether the 'y' short sequence should be
+ accepted as shorthand for 4 consecutive spaces (ASCII 0x20). This feature is
+ not supported by the "standard" Adobe encoding.
+
+ adobe controls whether the input sequence is in Adobe Ascii85 format (i.e.
+ is framed with <~ and ~>).
+
+ ignorechars should be a byte string containing characters to ignore from the
+ input. This should only contain whitespace characters, and by default
+ contains all whitespace characters in ASCII.
+
+ The result is returned as a bytes object.
+ """
+ b = _bytes_from_decode_data(b)
+ if adobe:
+ if not b.endswith(_A85END):
+ raise ValueError(
+ "Ascii85 encoded byte sequences must end "
+ "with {!r}".format(_A85END)
+ )
+ if b.startswith(_A85START):
+ b = b[2:-2] # Strip off start/end markers
+ else:
+ b = b[:-2]
+ #
+ # We have to go through this stepwise, so as to ignore spaces and handle
+ # special short sequences
+ #
+ packI = struct.Struct('!I').pack
+ decoded = []
+ decoded_append = decoded.append
+ curr = []
+ curr_append = curr.append
+ curr_clear = curr.clear
+ for x in b + b'u' * 4:
+ if b'!'[0] <= x <= b'u'[0]:
+ curr_append(x)
+ if len(curr) == 5:
+ acc = 0
+ for x in curr:
+ acc = 85 * acc + (x - 33)
+ try:
+ decoded_append(packI(acc))
+ except struct.error:
+ raise ValueError('Ascii85 overflow') from None
+ curr_clear()
+ elif x == b'z'[0]:
+ if curr:
+ raise ValueError('z inside Ascii85 5-tuple')
+ decoded_append(b'\0\0\0\0')
+ elif foldspaces and x == b'y'[0]:
+ if curr:
+ raise ValueError('y inside Ascii85 5-tuple')
+ decoded_append(b'\x20\x20\x20\x20')
+ elif x in ignorechars:
+ # Skip whitespace
+ continue
+ else:
+ raise ValueError('Non-Ascii85 digit found: %c' % x)
+
+ result = b''.join(decoded)
+ padding = 4 - len(curr)
+ if padding:
+ # Throw away the extra padding
+ result = result[:-padding]
+ return result
+
+# The following code is originally taken (with permission) from Mercurial
+
+_b85alphabet = (b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+ b"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~")
+_b85chars = None
+_b85chars2 = None
+_b85dec = None
+
+def b85encode(b, pad=False):
+ """Encode bytes-like object b in base85 format and return a bytes object.
+
+ If pad is true, the input is padded with b'\\0' so its length is a multiple of
+ 4 bytes before encoding.
+ """
+ global _b85chars, _b85chars2
+ # Delay the initialization of tables to not waste memory
+ # if the function is never called
+ if _b85chars is None:
+ _b85chars = [bytes((i,)) for i in _b85alphabet]
+ _b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
+ return _85encode(b, _b85chars, _b85chars2, pad)
+
+def b85decode(b):
+ """Decode the base85-encoded bytes-like object or ASCII string b
+
+ The result is returned as a bytes object.
+ """
+ global _b85dec
+ # Delay the initialization of tables to not waste memory
+ # if the function is never called
+ if _b85dec is None:
+ _b85dec = [None] * 256
+ for i, c in enumerate(_b85alphabet):
+ _b85dec[c] = i
+
+ b = _bytes_from_decode_data(b)
+ padding = (-len(b)) % 5
+ b = b + b'~' * padding
+ out = []
+ packI = struct.Struct('!I').pack
+ for i in range(0, len(b), 5):
+ chunk = b[i:i + 5]
+ acc = 0
+ try:
+ for c in chunk:
+ acc = acc * 85 + _b85dec[c]
+ except TypeError:
+ for j, c in enumerate(chunk):
+ if _b85dec[c] is None:
+ raise ValueError('bad base85 character at position %d'
+ % (i + j)) from None
+ raise
+ try:
+ out.append(packI(acc))
+ except struct.error:
+ raise ValueError('base85 overflow in hunk starting at byte %d'
+ % i) from None
+
+ result = b''.join(out)
+ if padding:
+ result = result[:-padding]
+ return result
+
+# Legacy interface. This code could be cleaned up since I don't believe
+# binascii has any line length limitations. It just doesn't seem worth it
+# though. The files should be opened in binary mode.
+
+MAXLINESIZE = 76 # Excluding the CRLF
+MAXBINSIZE = (MAXLINESIZE//4)*3
+
+def encode(input, output):
+ """Encode a file; input and output are binary files."""
+ while True:
+ s = input.read(MAXBINSIZE)
+ if not s:
+ break
+ while len(s) < MAXBINSIZE:
+ ns = input.read(MAXBINSIZE-len(s))
+ if not ns:
+ break
+ s += ns
+ line = binascii.b2a_base64(s)
+ output.write(line)
+
+
+def decode(input, output):
+ """Decode a file; input and output are binary files."""
+ while True:
+ line = input.readline()
+ if not line:
+ break
+ s = binascii.a2b_base64(line)
+ output.write(s)
+
+def _input_type_check(s):
+ try:
+ m = memoryview(s)
+ except TypeError as err:
+ msg = "expected bytes-like object, not %s" % s.__class__.__name__
+ raise TypeError(msg) from err
+ if m.format not in ('c', 'b', 'B'):
+ msg = ("expected single byte elements, not %r from %s" %
+ (m.format, s.__class__.__name__))
+ raise TypeError(msg)
+ if m.ndim != 1:
+ msg = ("expected 1-D data, not %d-D data from %s" %
+ (m.ndim, s.__class__.__name__))
+ raise TypeError(msg)
+
+
+def encodebytes(s):
+ """Encode a bytestring into a bytes object containing multiple lines
+ of base-64 data."""
+ _input_type_check(s)
+ pieces = []
+ for i in range(0, len(s), MAXBINSIZE):
+ chunk = s[i : i + MAXBINSIZE]
+ pieces.append(binascii.b2a_base64(chunk))
+ return b"".join(pieces)
+
+def encodestring(s):
+ """Legacy alias of encodebytes()."""
+ import warnings
+ warnings.warn("encodestring() is a deprecated alias since 3.1, "
+ "use encodebytes()",
+ DeprecationWarning, 2)
+ return encodebytes(s)
+
+
+def decodebytes(s):
+ """Decode a bytestring of base-64 data into a bytes object."""
+ _input_type_check(s)
+ return binascii.a2b_base64(s)
+
+def decodestring(s):
+ """Legacy alias of decodebytes()."""
+ import warnings
+ warnings.warn("decodestring() is a deprecated alias since Python 3.1, "
+ "use decodebytes()",
+ DeprecationWarning, 2)
+ return decodebytes(s)
+
+
+# Usable as a script...
+def main():
+ """Small main program"""
+ import sys, getopt
+ try:
+ opts, args = getopt.getopt(sys.argv[1:], 'deut')
+ except getopt.error as msg:
+ sys.stdout = sys.stderr
+ print(msg)
+ print("""usage: %s [-d|-e|-u|-t] [file|-]
+ -d, -u: decode
+ -e: encode (default)
+ -t: encode and decode string 'Aladdin:open sesame'"""%sys.argv[0])
+ sys.exit(2)
+ func = encode
+ for o, a in opts:
+ if o == '-e': func = encode
+ if o == '-d': func = decode
+ if o == '-u': func = decode
+ if o == '-t': test(); return
+ if args and args[0] != '-':
+ with open(args[0], 'rb') as f:
+ func(f, sys.stdout.buffer)
+ else:
+ func(sys.stdin.buffer, sys.stdout.buffer)
+
+
+def test():
+ s0 = b"Aladdin:open sesame"
+ print(repr(s0))
+ s1 = encodebytes(s0)
+ print(repr(s1))
+ s2 = decodebytes(s1)
+ print(repr(s2))
+ assert s0 == s2
+
+
+if __name__ == '__main__':
+ main()
diff --git a/Lib/bisect.py b/Lib/bisect.py
new file mode 100644
index 0000000..7732c63
--- /dev/null
+++ b/Lib/bisect.py
@@ -0,0 +1,92 @@
+"""Bisection algorithms."""
+
+def insort_right(a, x, lo=0, hi=None):
+ """Insert item x in list a, and keep it sorted assuming a is sorted.
+
+ If x is already in a, insert it to the right of the rightmost x.
+
+ Optional args lo (default 0) and hi (default len(a)) bound the
+ slice of a to be searched.
+ """
+
+ if lo < 0:
+ raise ValueError('lo must be non-negative')
+ if hi is None:
+ hi = len(a)
+ while lo < hi:
+ mid = (lo+hi)//2
+ if x < a[mid]: hi = mid
+ else: lo = mid+1
+ a.insert(lo, x)
+
+def bisect_right(a, x, lo=0, hi=None):
+ """Return the index where to insert item x in list a, assuming a is sorted.
+
+ The return value i is such that all e in a[:i] have e <= x, and all e in
+ a[i:] have e > x. So if x already appears in the list, a.insert(x) will
+ insert just after the rightmost x already there.
+
+ Optional args lo (default 0) and hi (default len(a)) bound the
+ slice of a to be searched.
+ """
+
+ if lo < 0:
+ raise ValueError('lo must be non-negative')
+ if hi is None:
+ hi = len(a)
+ while lo < hi:
+ mid = (lo+hi)//2
+ if x < a[mid]: hi = mid
+ else: lo = mid+1
+ return lo
+
+def insort_left(a, x, lo=0, hi=None):
+ """Insert item x in list a, and keep it sorted assuming a is sorted.
+
+ If x is already in a, insert it to the left of the leftmost x.
+
+ Optional args lo (default 0) and hi (default len(a)) bound the
+ slice of a to be searched.
+ """
+
+ if lo < 0:
+ raise ValueError('lo must be non-negative')
+ if hi is None:
+ hi = len(a)
+ while lo < hi:
+ mid = (lo+hi)//2
+ if a[mid] < x: lo = mid+1
+ else: hi = mid
+ a.insert(lo, x)
+
+
+def bisect_left(a, x, lo=0, hi=None):
+ """Return the index where to insert item x in list a, assuming a is sorted.
+
+ The return value i is such that all e in a[:i] have e < x, and all e in
+ a[i:] have e >= x. So if x already appears in the list, a.insert(x) will
+ insert just before the leftmost x already there.
+
+ Optional args lo (default 0) and hi (default len(a)) bound the
+ slice of a to be searched.
+ """
+
+ if lo < 0:
+ raise ValueError('lo must be non-negative')
+ if hi is None:
+ hi = len(a)
+ while lo < hi:
+ mid = (lo+hi)//2
+ if a[mid] < x: lo = mid+1
+ else: hi = mid
+ return lo
+
+# Overwrite above definitions with a fast C implementation
+try:
+ from _bisect import *
+except ImportError:
+ pass
+
+# Create aliases
+bisect = bisect_right
+insort = insort_right
diff --git a/Lib/codecs.py b/Lib/codecs.py
new file mode 100644
index 0000000..a70ed20
--- /dev/null
+++ b/Lib/codecs.py
@@ -0,0 +1,1114 @@
+""" codecs -- Python Codec Registry, API and helpers.
+
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
+
+"""
+
+import builtins
+import sys
+
+### Registry and builtin stateless codec functions
+
+try:
+ from _codecs import *
+except ImportError as why:
+ raise SystemError('Failed to load the builtin codecs: %s' % why)
+
+__all__ = ["register", "lookup", "open", "EncodedFile", "BOM", "BOM_BE",
+ "BOM_LE", "BOM32_BE", "BOM32_LE", "BOM64_BE", "BOM64_LE",
+ "BOM_UTF8", "BOM_UTF16", "BOM_UTF16_LE", "BOM_UTF16_BE",
+ "BOM_UTF32", "BOM_UTF32_LE", "BOM_UTF32_BE",
+ "CodecInfo", "Codec", "IncrementalEncoder", "IncrementalDecoder",
+ "StreamReader", "StreamWriter",
+ "StreamReaderWriter", "StreamRecoder",
+ "getencoder", "getdecoder", "getincrementalencoder",
+ "getincrementaldecoder", "getreader", "getwriter",
+ "encode", "decode", "iterencode", "iterdecode",
+ "strict_errors", "ignore_errors", "replace_errors",
+ "xmlcharrefreplace_errors",
+ "backslashreplace_errors", "namereplace_errors",
+ "register_error", "lookup_error"]
+
+### Constants
+
+#
+# Byte Order Mark (BOM = ZERO WIDTH NO-BREAK SPACE = U+FEFF)
+# and its possible byte string values
+# for UTF8/UTF16/UTF32 output and little/big endian machines
+#
+
+# UTF-8
+BOM_UTF8 = b'\xef\xbb\xbf'
+
+# UTF-16, little endian
+BOM_LE = BOM_UTF16_LE = b'\xff\xfe'
+
+# UTF-16, big endian
+BOM_BE = BOM_UTF16_BE = b'\xfe\xff'
+
+# UTF-32, little endian
+BOM_UTF32_LE = b'\xff\xfe\x00\x00'
+
+# UTF-32, big endian
+BOM_UTF32_BE = b'\x00\x00\xfe\xff'
+
+if sys.byteorder == 'little':
+
+ # UTF-16, native endianness
+ BOM = BOM_UTF16 = BOM_UTF16_LE
+
+ # UTF-32, native endianness
+ BOM_UTF32 = BOM_UTF32_LE
+
+else:
+
+ # UTF-16, native endianness
+ BOM = BOM_UTF16 = BOM_UTF16_BE
+
+ # UTF-32, native endianness
+ BOM_UTF32 = BOM_UTF32_BE
+
+# Old broken names (don't use in new code)
+BOM32_LE = BOM_UTF16_LE
+BOM32_BE = BOM_UTF16_BE
+BOM64_LE = BOM_UTF32_LE
+BOM64_BE = BOM_UTF32_BE
+
+
+### Codec base classes (defining the API)
+
+class CodecInfo(tuple):
+ """Codec details when looking up the codec registry"""
+
+ # Private API to allow Python 3.4 to blacklist the known non-Unicode
+ # codecs in the standard library. A more general mechanism to
+ # reliably distinguish test encodings from other codecs will hopefully
+ # be defined for Python 3.5
+ #
+ # See http://bugs.python.org/issue19619
+ _is_text_encoding = True # Assume codecs are text encodings by default
+
+ def __new__(cls, encode, decode, streamreader=None, streamwriter=None,
+ incrementalencoder=None, incrementaldecoder=None, name=None,
+ *, _is_text_encoding=None):
+ self = tuple.__new__(cls, (encode, decode, streamreader, streamwriter))
+ self.name = name
+ self.encode = encode
+ self.decode = decode
+ self.incrementalencoder = incrementalencoder
+ self.incrementaldecoder = incrementaldecoder
+ self.streamwriter = streamwriter
+ self.streamreader = streamreader
+ if _is_text_encoding is not None:
+ self._is_text_encoding = _is_text_encoding
+ return self
+
+ def __repr__(self):
+ return "<%s.%s object for encoding %s at %#x>" % \
+ (self.__class__.__module__, self.__class__.__qualname__,
+ self.name, id(self))
+
+class Codec:
+
+ """ Defines the interface for stateless encoders/decoders.
+
+ The .encode()/.decode() methods may use different error
+ handling schemes by providing the errors argument. These
+ string values are predefined:
+
+ 'strict' - raise a ValueError error (or a subclass)
+ 'ignore' - ignore the character and continue with the next
+ 'replace' - replace with a suitable replacement character;
+ Python will use the official U+FFFD REPLACEMENT
+ CHARACTER for the builtin Unicode codecs on
+ decoding and '?' on encoding.
+ 'surrogateescape' - replace with private code points U+DCnn.
+ 'xmlcharrefreplace' - Replace with the appropriate XML
+ character reference (only for encoding).
+ 'backslashreplace' - Replace with backslashed escape sequences.
+ 'namereplace' - Replace with \\N{...} escape sequences
+ (only for encoding).
+
+ The set of allowed values can be extended via register_error.
+
+ """
+ def encode(self, input, errors='strict'):
+
+ """ Encodes the object input and returns a tuple (output
+ object, length consumed).
+
+ errors defines the error handling to apply. It defaults to
+ 'strict' handling.
+
+ The method may not store state in the Codec instance. Use
+ StreamWriter for codecs which have to keep state in order to
+ make encoding efficient.
+
+ The encoder must be able to handle zero length input and
+ return an empty object of the output object type in this
+ situation.
+
+ """
+ raise NotImplementedError
+
+ def decode(self, input, errors='strict'):
+
+ """ Decodes the object input and returns a tuple (output
+ object, length consumed).
+
+ input must be an object which provides the bf_getreadbuf
+ buffer slot. Python strings, buffer objects and memory
+ mapped files are examples of objects providing this slot.
+
+ errors defines the error handling to apply. It defaults to
+ 'strict' handling.
+
+ The method may not store state in the Codec instance. Use
+ StreamReader for codecs which have to keep state in order to
+ make decoding efficient.
+
+ The decoder must be able to handle zero length input and
+ return an empty object of the output object type in this
+ situation.
+
+ """
+ raise NotImplementedError
+
+class IncrementalEncoder(object):
+ """
+ An IncrementalEncoder encodes an input in multiple steps. The input can
+ be passed piece by piece to the encode() method. The IncrementalEncoder
+ remembers the state of the encoding process between calls to encode().
+ """
+ def __init__(self, errors='strict'):
+ """
+ Creates an IncrementalEncoder instance.
+
+ The IncrementalEncoder may use different error handling schemes by
+ providing the errors keyword argument. See the module docstring
+ for a list of possible values.
+ """
+ self.errors = errors
+ self.buffer = ""
+
+ def encode(self, input, final=False):
+ """
+ Encodes input and returns the resulting object.
+ """
+ raise NotImplementedError
+
+ def reset(self):
+ """
+ Resets the encoder to the initial state.
+ """
+
+ def getstate(self):
+ """
+ Return the current state of the encoder.
+ """
+ return 0
+
+ def setstate(self, state):
+ """
+ Set the current state of the encoder. state must have been
+ returned by getstate().
+ """
+
+class BufferedIncrementalEncoder(IncrementalEncoder):
+ """
+ This subclass of IncrementalEncoder can be used as the baseclass for an
+ incremental encoder if the encoder must keep some of the output in a
+ buffer between calls to encode().
+ """
+ def __init__(self, errors='strict'):
+ IncrementalEncoder.__init__(self, errors)
+ # unencoded input that is kept between calls to encode()
+ self.buffer = ""
+
+ def _buffer_encode(self, input, errors, final):
+ # Overwrite this method in subclasses: It must encode input
+ # and return an (output, length consumed) tuple
+ raise NotImplementedError
+
+ def encode(self, input, final=False):
+ # encode input (taking the buffer into account)
+ data = self.buffer + input
+ (result, consumed) = self._buffer_encode(data, self.errors, final)
+ # keep unencoded input until the next call
+ self.buffer = data[consumed:]
+ return result
+
+ def reset(self):
+ IncrementalEncoder.reset(self)
+ self.buffer = ""
+
+ def getstate(self):
+ return self.buffer or 0
+
+ def setstate(self, state):
+ self.buffer = state or ""
+
+class IncrementalDecoder(object):
+ """
+ An IncrementalDecoder decodes an input in multiple steps. The input can
+ be passed piece by piece to the decode() method. The IncrementalDecoder
+ remembers the state of the decoding process between calls to decode().
+ """
+ def __init__(self, errors='strict'):
+ """
+ Create an IncrementalDecoder instance.
+
+ The IncrementalDecoder may use different error handling schemes by
+ providing the errors keyword argument. See the module docstring
+ for a list of possible values.
+ """
+ self.errors = errors
+
+ def decode(self, input, final=False):
+ """
+ Decode input and returns the resulting object.
+ """
+ raise NotImplementedError
+
+ def reset(self):
+ """
+ Reset the decoder to the initial state.
+ """
+
+ def getstate(self):
+ """
+ Return the current state of the decoder.
+
+ This must be a (buffered_input, additional_state_info) tuple.
+ buffered_input must be a bytes object containing bytes that
+ were passed to decode() that have not yet been converted.
+ additional_state_info must be a non-negative integer
+ representing the state of the decoder WITHOUT yet having
+ processed the contents of buffered_input. In the initial state
+ and after reset(), getstate() must return (b"", 0).
+ """
+ return (b"", 0)
+
+ def setstate(self, state):
+ """
+ Set the current state of the decoder.
+
+ state must have been returned by getstate(). The effect of
+ setstate((b"", 0)) must be equivalent to reset().
+ """
+
+class BufferedIncrementalDecoder(IncrementalDecoder):
+ """
+ This subclass of IncrementalDecoder can be used as the baseclass for an
+ incremental decoder if the decoder must be able to handle incomplete
+ byte sequences.
+ """
+ def __init__(self, errors='strict'):
+ IncrementalDecoder.__init__(self, errors)
+ # undecoded input that is kept between calls to decode()
+ self.buffer = b""
+
+ def _buffer_decode(self, input, errors, final):
+ # Overwrite this method in subclasses: It must decode input
+ # and return an (output, length consumed) tuple
+ raise NotImplementedError
+
+ def decode(self, input, final=False):
+ # decode input (taking the buffer into account)
+ data = self.buffer + input
+ (result, consumed) = self._buffer_decode(data, self.errors, final)
+ # keep undecoded input until the next call
+ self.buffer = data[consumed:]
+ return result
+
+ def reset(self):
+ IncrementalDecoder.reset(self)
+ self.buffer = b""
+
+ def getstate(self):
+ # additional state info is always 0
+ return (self.buffer, 0)
+
+ def setstate(self, state):
+ # ignore additional state info
+ self.buffer = state[0]
+
+#
+# The StreamWriter and StreamReader class provide generic working
+# interfaces which can be used to implement new encoding submodules
+# very easily. See encodings/utf_8.py for an example on how this is
+# done.
+#
+
+class StreamWriter(Codec):
+
+ def __init__(self, stream, errors='strict'):
+
+ """ Creates a StreamWriter instance.
+
+ stream must be a file-like object open for writing.
+
+ The StreamWriter may use different error handling
+ schemes by providing the errors keyword argument. These
+ parameters are predefined:
+
+ 'strict' - raise a ValueError (or a subclass)
+ 'ignore' - ignore the character and continue with the next
+ 'replace'- replace with a suitable replacement character
+ 'xmlcharrefreplace' - Replace with the appropriate XML
+ character reference.
+ 'backslashreplace' - Replace with backslashed escape
+ sequences.
+ 'namereplace' - Replace with \\N{...} escape sequences.
+
+ The set of allowed parameter values can be extended via
+ register_error.
+ """
+ self.stream = stream
+ self.errors = errors
+
+ def write(self, object):
+
+ """ Writes the object's contents encoded to self.stream.
+ """
+ data, consumed = self.encode(object, self.errors)
+ self.stream.write(data)
+
+ def writelines(self, list):
+
+ """ Writes the concatenated list of strings to the stream
+ using .write().
+ """
+ self.write(''.join(list))
+
+ def reset(self):
+
+ """ Flushes and resets the codec buffers used for keeping state.
+
+ Calling this method should ensure that the data on the
+ output is put into a clean state, that allows appending
+ of new fresh data without having to rescan the whole
+ stream to recover state.
+
+ """
+ pass
+
+ def seek(self, offset, whence=0):
+ self.stream.seek(offset, whence)
+ if whence == 0 and offset == 0:
+ self.reset()
+
+ def __getattr__(self, name,
+ getattr=getattr):
+
+ """ Inherit all other methods from the underlying stream.
+ """
+ return getattr(self.stream, name)
+
+ def __enter__(self):
+ return self
+
+ def __exit__(self, type, value, tb):
+ self.stream.close()
+
+###
+
+class StreamReader(Codec):
+
+ charbuffertype = str
+
+ def __init__(self, stream, errors='strict'):
+
+ """ Creates a StreamReader instance.
+
+ stream must be a file-like object open for reading.
+
+ The StreamReader may use different error handling
+ schemes by providing the errors keyword argument. These
+ parameters are predefined:
+
+ 'strict' - raise a ValueError (or a subclass)
+ 'ignore' - ignore the character and continue with the next
+ 'replace'- replace with a suitable replacement character
+ 'backslashreplace' - Replace with backslashed escape sequences;
+
+ The set of allowed parameter values can be extended via
+ register_error.
+ """
+ self.stream = stream
+ self.errors = errors
+ self.bytebuffer = b""
+ self._empty_charbuffer = self.charbuffertype()
+ self.charbuffer = self._empty_charbuffer
+ self.linebuffer = None
+
+ def decode(self, input, errors='strict'):
+ raise NotImplementedError
+
+ def read(self, size=-1, chars=-1, firstline=False):
+
+ """ Decodes data from the stream self.stream and returns the
+ resulting object.
+
+ chars indicates the number of decoded code points or bytes to
+ return. read() will never return more data than requested,
+ but it might return less, if there is not enough available.
+
+ size indicates the approximate maximum number of decoded
+ bytes or code points to read for decoding. The decoder
+ can modify this setting as appropriate. The default value
+ -1 indicates to read and decode as much as possible. size
+ is intended to prevent having to decode huge files in one
+ step.
+
+ If firstline is true, and a UnicodeDecodeError happens
+ after the first line terminator in the input only the first line
+ will be returned, the rest of the input will be kept until the
+ next call to read().
+
+ The method should use a greedy read strategy, meaning that
+ it should read as much data as is allowed within the
+ definition of the encoding and the given size, e.g. if
+ optional encoding endings or state markers are available
+ on the stream, these should be read too.
+ """
+ # If we have lines cached, first merge them back into characters
+ if self.linebuffer:
+ self.charbuffer = self._empty_charbuffer.join(self.linebuffer)
+ self.linebuffer = None
+
+ if chars < 0:
+ # For compatibility with other read() methods that take a
+ # single argument
+ chars = size
+
+ # read until we get the required number of characters (if available)
+ while True:
+ # can the request be satisfied from the character buffer?
+ if chars >= 0:
+ if len(self.charbuffer) >= chars:
+ break
+ # we need more data
+ if size < 0:
+ newdata = self.stream.read()
+ else:
+ newdata = self.stream.read(size)
+ # decode bytes (those remaining from the last call included)
+ data = self.bytebuffer + newdata
+ if not data:
+ break
+ try:
+ newchars, decodedbytes = self.decode(data, self.errors)
+ except UnicodeDecodeError as exc:
+ if firstline:
+ newchars, decodedbytes = \
+ self.decode(data[:exc.start], self.errors)
+ lines = newchars.splitlines(keepends=True)
+ if len(lines)<=1:
+ raise
+ else:
+ raise
+ # keep undecoded bytes until the next call
+ self.bytebuffer = data[decodedbytes:]
+ # put new characters in the character buffer
+ self.charbuffer += newchars
+ # there was no data available
+ if not newdata:
+ break
+ if chars < 0:
+ # Return everything we've got
+ result = self.charbuffer
+ self.charbuffer = self._empty_charbuffer
+ else:
+ # Return the first chars characters
+ result = self.charbuffer[:chars]
+ self.charbuffer = self.charbuffer[chars:]
+ return result
+
+ def readline(self, size=None, keepends=True):
+
+ """ Read one line from the input stream and return the
+ decoded data.
+
+ size, if given, is passed as size argument to the
+ read() method.
+
+ """
+ # If we have lines cached from an earlier read, return
+ # them unconditionally
+ if self.linebuffer:
+ line = self.linebuffer[0]
+ del self.linebuffer[0]
+ if len(self.linebuffer) == 1:
+ # revert to charbuffer mode; we might need more data
+ # next time
+ self.charbuffer = self.linebuffer[0]
+ self.linebuffer = None
+ if not keepends:
+ line = line.splitlines(keepends=False)[0]
+ return line
+
+ readsize = size or 72
+ line = self._empty_charbuffer
+ # If size is given, we call read() only once
+ while True:
+ data = self.read(readsize, firstline=True)
+ if data:
+ # If we're at a "\r" read one extra character (which might
+ # be a "\n") to get a proper line ending. If the stream is
+ # temporarily exhausted we return the wrong line ending.
+ if (isinstance(data, str) and data.endswith("\r")) or \
+ (isinstance(data, bytes) and data.endswith(b"\r")):
+ data += self.read(size=1, chars=1)
+
+ line += data
+ lines = line.splitlines(keepends=True)
+ if lines:
+ if len(lines) > 1:
+ # More than one line result; the first line is a full line
+ # to return
+ line = lines[0]
+ del lines[0]
+ if len(lines) > 1:
+ # cache the remaining lines
+ lines[-1] += self.charbuffer
+ self.linebuffer = lines
+ self.charbuffer = None
+ else:
+ # only one remaining line, put it back into charbuffer
+ self.charbuffer = lines[0] + self.charbuffer
+ if not keepends:
+ line = line.splitlines(keepends=False)[0]
+ break
+ line0withend = lines[0]
+ line0withoutend = lines[0].splitlines(keepends=False)[0]
+ if line0withend != line0withoutend: # We really have a line end
+ # Put the rest back together and keep it until the next call
+ self.charbuffer = self._empty_charbuffer.join(lines[1:]) + \
+ self.charbuffer
+ if keepends:
+ line = line0withend
+ else:
+ line = line0withoutend
+ break
+ # we didn't get anything or this was our only try
+ if not data or size is not None:
+ if line and not keepends:
+ line = line.splitlines(keepends=False)[0]
+ break
+ if readsize < 8000:
+ readsize *= 2
+ return line
+
+ def readlines(self, sizehint=None, keepends=True):
+
+ """ Read all lines available on the input stream
+ and return them as a list.
+
+ Line breaks are implemented using the codec's decoder
+ method and are included in the list entries.
+
+ sizehint, if given, is ignored since there is no efficient
+ way to finding the true end-of-line.
+
+ """
+ data = self.read()
+ return data.splitlines(keepends)
+
+ def reset(self):
+
+ """ Resets the codec buffers used for keeping state.
+
+ Note that no stream repositioning should take place.
+ This method is primarily intended to be able to recover
+ from decoding errors.
+
+ """
+ self.bytebuffer = b""
+ self.charbuffer = self._empty_charbuffer
+ self.linebuffer = None
+
+ def seek(self, offset, whence=0):
+ """ Set the input stream's current position.
+
+ Resets the codec buffers used for keeping state.
+ """
+ self.stream.seek(offset, whence)
+ self.reset()
+
+ def __next__(self):
+
+ """ Return the next decoded line from the input stream."""
+ line = self.readline()
+ if line:
+ return line
+ raise StopIteration
+
+ def __iter__(self):
+ return self
+
+ def __getattr__(self, name,
+ getattr=getattr):
+
+ """ Inherit all other methods from the underlying stream.
+ """
+ return getattr(self.stream, name)
+
+ def __enter__(self):
+ return self
+
+ def __exit__(self, type, value, tb):
+ self.stream.close()
+
+###
+
+class StreamReaderWriter:
+
+ """ StreamReaderWriter instances allow wrapping streams which
+ work in both read and write modes.
+
+ The design is such that one can use the factory functions
+ returned by the codec.lookup() function to construct the
+ instance.
+
+ """
+ # Optional attributes set by the file wrappers below
+ encoding = 'unknown'
+
+ def __init__(self, stream, Reader, Writer, errors='strict'):
+
+ """ Creates a StreamReaderWriter instance.
+
+ stream must be a Stream-like object.
+
+ Reader, Writer must be factory functions or classes
+ providing the StreamReader, StreamWriter interface resp.
+
+ Error handling is done in the same way as defined for the
+ StreamWriter/Readers.
+
+ """
+ self.stream = stream
+ self.reader = Reader(stream, errors)
+ self.writer = Writer(stream, errors)
+ self.errors = errors
+
+ def read(self, size=-1):
+
+ return self.reader.read(size)
+
+ def readline(self, size=None):
+
+ return self.reader.readline(size)
+
+ def readlines(self, sizehint=None):
+
+ return self.reader.readlines(sizehint)
+
+ def __next__(self):
+
+ """ Return the next decoded line from the input stream."""
+ return next(self.reader)
+
+ def __iter__(self):
+ return self
+
+ def write(self, data):
+
+ return self.writer.write(data)
+
+ def writelines(self, list):
+
+ return self.writer.writelines(list)
+
+ def reset(self):
+
+ self.reader.reset()
+ self.writer.reset()
+
+ def seek(self, offset, whence=0):
+ self.stream.seek(offset, whence)
+ self.reader.reset()
+ if whence == 0 and offset == 0:
+ self.writer.reset()
+
+ def __getattr__(self, name,
+ getattr=getattr):
+
+ """ Inherit all other methods from the underlying stream.
+ """
+ return getattr(self.stream, name)
+
+ # these are needed to make "with StreamReaderWriter(...)" work properly
+
+ def __enter__(self):
+ return self
+
+ def __exit__(self, type, value, tb):
+ self.stream.close()
+
+###
+
+class StreamRecoder:
+
+ """ StreamRecoder instances translate data from one encoding to another.
+
+ They use the complete set of APIs returned by the
+ codecs.lookup() function to implement their task.
+
+ Data written to the StreamRecoder is first decoded into an
+ intermediate format (depending on the "decode" codec) and then
+ written to the underlying stream using an instance of the provided
+ Writer class.
+
+ In the other direction, data is read from the underlying stream using
+ a Reader instance and then encoded and returned to the caller.
+
+ """
+ # Optional attributes set by the file wrappers below
+ data_encoding = 'unknown'
+ file_encoding = 'unknown'
+
+ def __init__(self, stream, encode, decode, Reader, Writer,
+ errors='strict'):
+
+ """ Creates a StreamRecoder instance which implements a two-way
+ conversion: encode and decode work on the frontend (the
+ data visible to .read() and .write()) while Reader and Writer
+ work on the backend (the data in stream).
+
+ You can use these objects to do transparent
+ transcodings from e.g. latin-1 to utf-8 and back.
+
+ stream must be a file-like object.
+
+ encode and decode must adhere to the Codec interface; Reader and
+ Writer must be factory functions or classes providing the
+ StreamReader and StreamWriter interfaces resp.
+
+ Error handling is done in the same way as defined for the
+ StreamWriter/Readers.
+
+ """
+ self.stream = stream
+ self.encode = encode
+ self.decode = decode
+ self.reader = Reader(stream, errors)
+ self.writer = Writer(stream, errors)
+ self.errors = errors
+
+ def read(self, size=-1):
+
+ data = self.reader.read(size)
+ data, bytesencoded = self.encode(data, self.errors)
+ return data
+
+ def readline(self, size=None):
+
+ if size is None:
+ data = self.reader.readline()
+ else:
+ data = self.reader.readline(size)
+ data, bytesencoded = self.encode(data, self.errors)
+ return data
+
+ def readlines(self, sizehint=None):
+
+ data = self.reader.read()
+ data, bytesencoded = self.encode(data, self.errors)
+ return data.splitlines(keepends=True)
+
+ def __next__(self):
+
+ """ Return the next decoded line from the input stream."""
+ data = next(self.reader)
+ data, bytesencoded = self.encode(data, self.errors)
+ return data
+
+ def __iter__(self):
+ return self
+
+ def write(self, data):
+
+ data, bytesdecoded = self.decode(data, self.errors)
+ return self.writer.write(data)
+
+ def writelines(self, list):
+
+ data = ''.join(list)
+ data, bytesdecoded = self.decode(data, self.errors)
+ return self.writer.write(data)
+
+ def reset(self):
+
+ self.reader.reset()
+ self.writer.reset()
+
+ def __getattr__(self, name,
+ getattr=getattr):
+
+ """ Inherit all other methods from the underlying stream.
+ """
+ return getattr(self.stream, name)
+
+ def __enter__(self):
+ return self
+
+ def __exit__(self, type, value, tb):
+ self.stream.close()
+
+### Shortcuts
+
+def open(filename, mode='r', encoding=None, errors='strict', buffering=1):
+
+ """ Open an encoded file using the given mode and return
+ a wrapped version providing transparent encoding/decoding.
+
+ Note: The wrapped version will only accept the object format
+ defined by the codecs, i.e. Unicode objects for most builtin
+ codecs. Output is also codec dependent and will usually be
+ Unicode as well.
+
+ Underlying encoded files are always opened in binary mode.
+ The default file mode is 'r', meaning to open the file in read mode.
+
+ encoding specifies the encoding which is to be used for the
+ file.
+
+ errors may be given to define the error handling. It defaults
+ to 'strict' which causes ValueErrors to be raised in case an
+ encoding error occurs.
+
+ buffering has the same meaning as for the builtin open() API.
+ It defaults to line buffered.
+
+ The returned wrapped file object provides an extra attribute
+ .encoding which allows querying the used encoding. This
+ attribute is only available if an encoding was specified as
+ parameter.
+
+ """
+ if encoding is not None and \
+ 'b' not in mode:
+ # Force opening of the file in binary mode
+ mode = mode + 'b'
+ file = builtins.open(filename, mode, buffering)
+ if encoding is None:
+ return file
+ info = lookup(encoding)
+ srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, errors)
+ # Add attributes to simplify introspection
+ srw.encoding = encoding
+ return srw
+
+def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'):
+
+ """ Return a wrapped version of file which provides transparent
+ encoding translation.
+
+ Data written to the wrapped file is decoded according
+ to the given data_encoding and then encoded to the underlying
+ file using file_encoding. The intermediate data type
+ will usually be Unicode but depends on the specified codecs.
+
+ Bytes read from the file are decoded using file_encoding and then
+ passed back to the caller encoded using data_encoding.
+
+ If file_encoding is not given, it defaults to data_encoding.
+
+ errors may be given to define the error handling. It defaults
+ to 'strict' which causes ValueErrors to be raised in case an
+ encoding error occurs.
+
+ The returned wrapped file object provides two extra attributes
+ .data_encoding and .file_encoding which reflect the given
+ parameters of the same name. The attributes can be used for
+ introspection by Python programs.
+
+ """
+ if file_encoding is None:
+ file_encoding = data_encoding
+ data_info = lookup(data_encoding)
+ file_info = lookup(file_encoding)
+ sr = StreamRecoder(file, data_info.encode, data_info.decode,
+ file_info.streamreader, file_info.streamwriter, errors)
+ # Add attributes to simplify introspection
+ sr.data_encoding = data_encoding
+ sr.file_encoding = file_encoding
+ return sr
+
+### Helpers for codec lookup
+
+def getencoder(encoding):
+
+ """ Lookup up the codec for the given encoding and return
+ its encoder function.
+
+ Raises a LookupError in case the encoding cannot be found.
+
+ """
+ return lookup(encoding).encode
+
+def getdecoder(encoding):
+
+ """ Lookup up the codec for the given encoding and return
+ its decoder function.
+
+ Raises a LookupError in case the encoding cannot be found.
+
+ """
+ return lookup(encoding).decode
+
+def getincrementalencoder(encoding):
+
+ """ Lookup up the codec for the given encoding and return
+ its IncrementalEncoder class or factory function.
+
+ Raises a LookupError in case the encoding cannot be found
+ or the codecs doesn't provide an incremental encoder.
+
+ """
+ encoder = lookup(encoding).incrementalencoder
+ if encoder is None:
+ raise LookupError(encoding)
+ return encoder
+
+def getincrementaldecoder(encoding):
+
+ """ Lookup up the codec for the given encoding and return
+ its IncrementalDecoder class or factory function.
+
+ Raises a LookupError in case the encoding cannot be found
+ or the codecs doesn't provide an incremental decoder.
+
+ """
+ decoder = lookup(encoding).incrementaldecoder
+ if decoder is None:
+ raise LookupError(encoding)
+ return decoder
+
+def getreader(encoding):
+
+ """ Lookup up the codec for the given encoding and return
+ its StreamReader class or factory function.
+
+ Raises a LookupError in case the encoding cannot be found.
+
+ """
+ return lookup(encoding).streamreader
+
+def getwriter(encoding):
+
+ """ Lookup up the codec for the given encoding and return
+ its StreamWriter class or factory function.
+
+ Raises a LookupError in case the encoding cannot be found.
+
+ """
+ return lookup(encoding).streamwriter
+
+def iterencode(iterator, encoding, errors='strict', **kwargs):
+ """
+ Encoding iterator.
+
+ Encodes the input strings from the iterator using an IncrementalEncoder.
+
+ errors and kwargs are passed through to the IncrementalEncoder
+ constructor.
+ """
+ encoder = getincrementalencoder(encoding)(errors, **kwargs)
+ for input in iterator:
+ output = encoder.encode(input)
+ if output:
+ yield output
+ output = encoder.encode("", True)
+ if output:
+ yield output
+
+def iterdecode(iterator, encoding, errors='strict', **kwargs):
+ """
+ Decoding iterator.
+
+ Decodes the input strings from the iterator using an IncrementalDecoder.
+
+ errors and kwargs are passed through to the IncrementalDecoder
+ constructor.
+ """
+ decoder = getincrementaldecoder(encoding)(errors, **kwargs)
+ for input in iterator:
+ output = decoder.decode(input)
+ if output:
+ yield output
+ output = decoder.decode(b"", True)
+ if output:
+ yield output
+
+### Helpers for charmap-based codecs
+
+def make_identity_dict(rng):
+
+ """ make_identity_dict(rng) -> dict
+
+ Return a dictionary where elements of the rng sequence are
+ mapped to themselves.
+
+ """
+ return {i:i for i in rng}
+
+def make_encoding_map(decoding_map):
+
+ """ Creates an encoding map from a decoding map.
+
+ If a target mapping in the decoding map occurs multiple
+ times, then that target is mapped to None (undefined mapping),
+ causing an exception when encountered by the charmap codec
+ during translation.
+
+ One example where this happens is cp875.py which decodes
+ multiple character to \\u001a.
+
+ """
+ m = {}
+ for k,v in decoding_map.items():
+ if not v in m:
+ m[v] = k
+ else:
+ m[v] = None
+ return m
+
+### error handlers
+
+try:
+ strict_errors = lookup_error("strict")
+ ignore_errors = lookup_error("ignore")
+ replace_errors = lookup_error("replace")
+ xmlcharrefreplace_errors = lookup_error("xmlcharrefreplace")
+ backslashreplace_errors = lookup_error("backslashreplace")
+ namereplace_errors = lookup_error("namereplace")
+except LookupError:
+ # In --disable-unicode builds, these error handler are missing
+ strict_errors = None
+ ignore_errors = None
+ replace_errors = None
+ xmlcharrefreplace_errors = None
+ backslashreplace_errors = None
+ namereplace_errors = None
+
+# Tell modulefinder that using codecs probably needs the encodings
+# package
+_false = 0
+if _false:
+ import encodings
+
+### Tests
+
+if __name__ == '__main__':
+
+ # Make stdout translate Latin-1 output into UTF-8 output
+ sys.stdout = EncodedFile(sys.stdout, 'latin-1', 'utf-8')
+
+ # Have stdin translate Latin-1 input into UTF-8 input
+ sys.stdin = EncodedFile(sys.stdin, 'utf-8', 'latin-1')
diff --git a/Lib/collections/__init__.py b/Lib/collections/__init__.py
new file mode 100644
index 0000000..9a753db
--- /dev/null
+++ b/Lib/collections/__init__.py
@@ -0,0 +1,1279 @@
+'''This module implements specialized container datatypes providing
+alternatives to Python's general purpose built-in containers, dict,
+list, set, and tuple.
+
+* namedtuple factory function for creating tuple subclasses with named fields
+* deque list-like container with fast appends and pops on either end
+* ChainMap dict-like class for creating a single view of multiple mappings
+* Counter dict subclass for counting hashable objects
+* OrderedDict dict subclass that remembers the order entries were added
+* defaultdict dict subclass that calls a factory function to supply missing values
+* UserDict wrapper around dictionary objects for easier dict subclassing
+* UserList wrapper around list objects for easier list subclassing
+* UserString wrapper around string objects for easier string subclassing
+
+'''
+
+__all__ = ['deque', 'defaultdict', 'namedtuple', 'UserDict', 'UserList',
+ 'UserString', 'Counter', 'OrderedDict', 'ChainMap']
+
+import _collections_abc
+from operator import itemgetter as _itemgetter, eq as _eq
+from keyword import iskeyword as _iskeyword
+import sys as _sys
+import heapq as _heapq
+from _weakref import proxy as _proxy
+from itertools import repeat as _repeat, chain as _chain, starmap as _starmap
+from reprlib import recursive_repr as _recursive_repr
+
+try:
+ from _collections import deque
+except ImportError:
+ pass
+else:
+ _collections_abc.MutableSequence.register(deque)
+
+try:
+ from _collections import defaultdict
+except ImportError:
+ pass
+
+
+def __getattr__(name):
+ # For backwards compatibility, continue to make the collections ABCs
+ # through Python 3.6 available through the collections module.
+ # Note, no new collections ABCs were added in Python 3.7
+ if name in _collections_abc.__all__:
+ obj = getattr(_collections_abc, name)
+ import warnings
+ warnings.warn("Using or importing the ABCs from 'collections' instead "
+ "of from 'collections.abc' is deprecated, "
+ "and in 3.8 it will stop working",
+ DeprecationWarning, stacklevel=2)
+ globals()[name] = obj
+ return obj
+ raise AttributeError(f'module {__name__!r} has no attribute {name!r}')
+
+################################################################################
+### OrderedDict
+################################################################################
+
+class _OrderedDictKeysView(_collections_abc.KeysView):
+
+ def __reversed__(self):
+ yield from reversed(self._mapping)
+
+class _OrderedDictItemsView(_collections_abc.ItemsView):
+
+ def __reversed__(self):
+ for key in reversed(self._mapping):
+ yield (key, self._mapping[key])
+
+class _OrderedDictValuesView(_collections_abc.ValuesView):
+
+ def __reversed__(self):
+ for key in reversed(self._mapping):
+ yield self._mapping[key]
+
+class _Link(object):
+ __slots__ = 'prev', 'next', 'key', '__weakref__'
+
+class OrderedDict(dict):
+ 'Dictionary that remembers insertion order'
+ # An inherited dict maps keys to values.
+ # The inherited dict provides __getitem__, __len__, __contains__, and get.
+ # The remaining methods are order-aware.
+ # Big-O running times for all methods are the same as regular dictionaries.
+
+ # The internal self.__map dict maps keys to links in a doubly linked list.
+ # The circular doubly linked list starts and ends with a sentinel element.
+ # The sentinel element never gets deleted (this simplifies the algorithm).
+ # The sentinel is in self.__hardroot with a weakref proxy in self.__root.
+ # The prev links are weakref proxies (to prevent circular references).
+ # Individual links are kept alive by the hard reference in self.__map.
+ # Those hard references disappear when a key is deleted from an OrderedDict.
+
+ def __init__(*args, **kwds):
+ '''Initialize an ordered dictionary. The signature is the same as
+ regular dictionaries. Keyword argument order is preserved.
+ '''
+ if not args:
+ raise TypeError("descriptor '__init__' of 'OrderedDict' object "
+ "needs an argument")
+ self, *args = args
+ if len(args) > 1:
+ raise TypeError('expected at most 1 arguments, got %d' % len(args))
+ try:
+ self.__root
+ except AttributeError:
+ self.__hardroot = _Link()
+ self.__root = root = _proxy(self.__hardroot)
+ root.prev = root.next = root
+ self.__map = {}
+ self.__update(*args, **kwds)
+
+ def __setitem__(self, key, value,
+ dict_setitem=dict.__setitem__, proxy=_proxy, Link=_Link):
+ 'od.__setitem__(i, y) <==> od[i]=y'
+ # Setting a new item creates a new link at the end of the linked list,
+ # and the inherited dictionary is updated with the new key/value pair.
+ if key not in self:
+ self.__map[key] = link = Link()
+ root = self.__root
+ last = root.prev
+ link.prev, link.next, link.key = last, root, key
+ last.next = link
+ root.prev = proxy(link)
+ dict_setitem(self, key, value)
+
+ def __delitem__(self, key, dict_delitem=dict.__delitem__):
+ 'od.__delitem__(y) <==> del od[y]'
+ # Deleting an existing item uses self.__map to find the link which gets
+ # removed by updating the links in the predecessor and successor nodes.
+ dict_delitem(self, key)
+ link = self.__map.pop(key)
+ link_prev = link.prev
+ link_next = link.next
+ link_prev.next = link_next
+ link_next.prev = link_prev
+ link.prev = None
+ link.next = None
+
+ def __iter__(self):
+ 'od.__iter__() <==> iter(od)'
+ # Traverse the linked list in order.
+ root = self.__root
+ curr = root.next
+ while curr is not root:
+ yield curr.key
+ curr = curr.next
+
+ def __reversed__(self):
+ 'od.__reversed__() <==> reversed(od)'
+ # Traverse the linked list in reverse order.
+ root = self.__root
+ curr = root.prev
+ while curr is not root:
+ yield curr.key
+ curr = curr.prev
+
+ def clear(self):
+ 'od.clear() -> None. Remove all items from od.'
+ root = self.__root
+ root.prev = root.next = root
+ self.__map.clear()
+ dict.clear(self)
+
+ def popitem(self, last=True):
+ '''Remove and return a (key, value) pair from the dictionary.
+
+ Pairs are returned in LIFO order if last is true or FIFO order if false.
+ '''
+ if not self:
+ raise KeyError('dictionary is empty')
+ root = self.__root
+ if last:
+ link = root.prev
+ link_prev = link.prev
+ link_prev.next = root
+ root.prev = link_prev
+ else:
+ link = root.next
+ link_next = link.next
+ root.next = link_next
+ link_next.prev = root
+ key = link.key
+ del self.__map[key]
+ value = dict.pop(self, key)
+ return key, value
+
+ def move_to_end(self, key, last=True):
+ '''Move an existing element to the end (or beginning if last is false).
+
+ Raise KeyError if the element does not exist.
+ '''
+ link = self.__map[key]
+ link_prev = link.prev
+ link_next = link.next
+ soft_link = link_next.prev
+ link_prev.next = link_next
+ link_next.prev = link_prev
+ root = self.__root
+ if last:
+ last = root.prev
+ link.prev = last
+ link.next = root
+ root.prev = soft_link
+ last.next = link
+ else:
+ first = root.next
+ link.prev = root
+ link.next = first
+ first.prev = soft_link
+ root.next = link
+
+ def __sizeof__(self):
+ sizeof = _sys.getsizeof
+ n = len(self) + 1 # number of links including root
+ size = sizeof(self.__dict__) # instance dictionary
+ size += sizeof(self.__map) * 2 # internal dict and inherited dict
+ size += sizeof(self.__hardroot) * n # link objects
+ size += sizeof(self.__root) * n # proxy objects
+ return size
+
+ update = __update = _collections_abc.MutableMapping.update
+
+ def keys(self):
+ "D.keys() -> a set-like object providing a view on D's keys"
+ return _OrderedDictKeysView(self)
+
+ def items(self):
+ "D.items() -> a set-like object providing a view on D's items"
+ return _OrderedDictItemsView(self)
+
+ def values(self):
+ "D.values() -> an object providing a view on D's values"
+ return _OrderedDictValuesView(self)
+
+ __ne__ = _collections_abc.MutableMapping.__ne__
+
+ __marker = object()
+
+ def pop(self, key, default=__marker):
+ '''od.pop(k[,d]) -> v, remove specified key and return the corresponding
+ value. If key is not found, d is returned if given, otherwise KeyError
+ is raised.
+
+ '''
+ if key in self:
+ result = self[key]
+ del self[key]
+ return result
+ if default is self.__marker:
+ raise KeyError(key)
+ return default
+
+ def setdefault(self, key, default=None):
+ '''Insert key with a value of default if key is not in the dictionary.
+
+ Return the value for key if key is in the dictionary, else default.
+ '''
+ if key in self:
+ return self[key]
+ self[key] = default
+ return default
+
+ @_recursive_repr()
+ def __repr__(self):
+ 'od.__repr__() <==> repr(od)'
+ if not self:
+ return '%s()' % (self.__class__.__name__,)
+ return '%s(%r)' % (self.__class__.__name__, list(self.items()))
+
+ def __reduce__(self):
+ 'Return state information for pickling'
+ inst_dict = vars(self).copy()
+ for k in vars(OrderedDict()):
+ inst_dict.pop(k, None)
+ return self.__class__, (), inst_dict or None, None, iter(self.items())
+
+ def copy(self):
+ 'od.copy() -> a shallow copy of od'
+ return self.__class__(self)
+
+ @classmethod
+ def fromkeys(cls, iterable, value=None):
+ '''Create a new ordered dictionary with keys from iterable and values set to value.
+ '''
+ self = cls()
+ for key in iterable:
+ self[key] = value
+ return self
+
+ def __eq__(self, other):
+ '''od.__eq__(y) <==> od==y. Comparison to another OD is order-sensitive
+ while comparison to a regular mapping is order-insensitive.
+
+ '''
+ if isinstance(other, OrderedDict):
+ return dict.__eq__(self, other) and all(map(_eq, self, other))
+ return dict.__eq__(self, other)
+
+
+try:
+ from _collections import OrderedDict
+except ImportError:
+ # Leave the pure Python version in place.
+ pass
+
+
+################################################################################
+### namedtuple
+################################################################################
+
+_nt_itemgetters = {}
+
+def namedtuple(typename, field_names, *, rename=False, defaults=None, module=None):
+ """Returns a new subclass of tuple with named fields.
+
+ >>> Point = namedtuple('Point', ['x', 'y'])
+ >>> Point.__doc__ # docstring for the new class
+ 'Point(x, y)'
+ >>> p = Point(11, y=22) # instantiate with positional args or keywords
+ >>> p[0] + p[1] # indexable like a plain tuple
+ 33
+ >>> x, y = p # unpack like a regular tuple
+ >>> x, y
+ (11, 22)
+ >>> p.x + p.y # fields also accessible by name
+ 33
+ >>> d = p._asdict() # convert to a dictionary
+ >>> d['x']
+ 11
+ >>> Point(**d) # convert from a dictionary
+ Point(x=11, y=22)
+ >>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
+ Point(x=100, y=22)
+
+ """
+
+ # Validate the field names. At the user's option, either generate an error
+ # message or automatically replace the field name with a valid name.
+ if isinstance(field_names, str):
+ field_names = field_names.replace(',', ' ').split()
+ field_names = list(map(str, field_names))
+ typename = _sys.intern(str(typename))
+
+ if rename:
+ seen = set()
+ for index, name in enumerate(field_names):
+ if (not name.isidentifier()
+ or _iskeyword(name)
+ or name.startswith('_')
+ or name in seen):
+ field_names[index] = f'_{index}'
+ seen.add(name)
+
+ for name in [typename] + field_names:
+ if type(name) is not str:
+ raise TypeError('Type names and field names must be strings')
+ if not name.isidentifier():
+ raise ValueError('Type names and field names must be valid '
+ f'identifiers: {name!r}')
+ if _iskeyword(name):
+ raise ValueError('Type names and field names cannot be a '
+ f'keyword: {name!r}')
+
+ seen = set()
+ for name in field_names:
+ if name.startswith('_') and not rename:
+ raise ValueError('Field names cannot start with an underscore: '
+ f'{name!r}')
+ if name in seen:
+ raise ValueError(f'Encountered duplicate field name: {name!r}')
+ seen.add(name)
+
+ field_defaults = {}
+ if defaults is not None:
+ defaults = tuple(defaults)
+ if len(defaults) > len(field_names):
+ raise TypeError('Got more default values than field names')
+ field_defaults = dict(reversed(list(zip(reversed(field_names),
+ reversed(defaults)))))
+
+ # Variables used in the methods and docstrings
+ field_names = tuple(map(_sys.intern, field_names))
+ num_fields = len(field_names)
+ arg_list = repr(field_names).replace("'", "")[1:-1]
+ repr_fmt = '(' + ', '.join(f'{name}=%r' for name in field_names) + ')'
+ tuple_new = tuple.__new__
+ _len = len
+
+ # Create all the named tuple methods to be added to the class namespace
+
+ s = f'def __new__(_cls, {arg_list}): return _tuple_new(_cls, ({arg_list}))'
+ namespace = {'_tuple_new': tuple_new, '__name__': f'namedtuple_{typename}'}
+ # Note: exec() has the side-effect of interning the field names
+ exec(s, namespace)
+ __new__ = namespace['__new__']
+ __new__.__doc__ = f'Create new instance of {typename}({arg_list})'
+ if defaults is not None:
+ __new__.__defaults__ = defaults
+
+ @classmethod
+ def _make(cls, iterable):
+ result = tuple_new(cls, iterable)
+ if _len(result) != num_fields:
+ raise TypeError(f'Expected {num_fields} arguments, got {len(result)}')
+ return result
+
+ _make.__func__.__doc__ = (f'Make a new {typename} object from a sequence '
+ 'or iterable')
+
+ def _replace(_self, **kwds):
+ result = _self._make(map(kwds.pop, field_names, _self))
+ if kwds:
+ raise ValueError(f'Got unexpected field names: {list(kwds)!r}')
+ return result
+
+ _replace.__doc__ = (f'Return a new {typename} object replacing specified '
+ 'fields with new values')
+
+ def __repr__(self):
+ 'Return a nicely formatted representation string'
+ return self.__class__.__name__ + repr_fmt % self
+
+ def _asdict(self):
+ 'Return a new OrderedDict which maps field names to their values.'
+ return OrderedDict(zip(self._fields, self))
+
+ def __getnewargs__(self):
+ 'Return self as a plain tuple. Used by copy and pickle.'
+ return tuple(self)
+
+ # Modify function metadata to help with introspection and debugging
+
+ for method in (__new__, _make.__func__, _replace,
+ __repr__, _asdict, __getnewargs__):
+ method.__qualname__ = f'{typename}.{method.__name__}'
+
+ # Build-up the class namespace dictionary
+ # and use type() to build the result class
+ class_namespace = {
+ '__doc__': f'{typename}({arg_list})',
+ '__slots__': (),
+ '_fields': field_names,
+ '_fields_defaults': field_defaults,
+ '__new__': __new__,
+ '_make': _make,
+ '_replace': _replace,
+ '__repr__': __repr__,
+ '_asdict': _asdict,
+ '__getnewargs__': __getnewargs__,
+ }
+ cache = _nt_itemgetters
+ for index, name in enumerate(field_names):
+ try:
+ itemgetter_object, doc = cache[index]
+ except KeyError:
+ itemgetter_object = _itemgetter(index)
+ doc = f'Alias for field number {index}'
+ cache[index] = itemgetter_object, doc
+ class_namespace[name] = property(itemgetter_object, doc=doc)
+
+ result = type(typename, (tuple,), class_namespace)
+
+ # For pickling to work, the __module__ variable needs to be set to the frame
+ # where the named tuple is created. Bypass this step in environments where
+ # sys._getframe is not defined (Jython for example) or sys._getframe is not
+ # defined for arguments greater than 0 (IronPython), or where the user has
+ # specified a particular module.
+ if module is None:
+ try:
+ module = _sys._getframe(1).f_globals.get('__name__', '__main__')
+ except (AttributeError, ValueError):
+ pass
+ if module is not None:
+ result.__module__ = module
+
+ return result
+
+
+########################################################################
+### Counter
+########################################################################
+
+def _count_elements(mapping, iterable):
+ 'Tally elements from the iterable.'
+ mapping_get = mapping.get
+ for elem in iterable:
+ mapping[elem] = mapping_get(elem, 0) + 1
+
+try: # Load C helper function if available
+ from _collections import _count_elements
+except ImportError:
+ pass
+
+class Counter(dict):
+ '''Dict subclass for counting hashable items. Sometimes called a bag
+ or multiset. Elements are stored as dictionary keys and their counts
+ are stored as dictionary values.
+
+ >>> c = Counter('abcdeabcdabcaba') # count elements from a string
+
+ >>> c.most_common(3) # three most common elements
+ [('a', 5), ('b', 4), ('c', 3)]
+ >>> sorted(c) # list all unique elements
+ ['a', 'b', 'c', 'd', 'e']
+ >>> ''.join(sorted(c.elements())) # list elements with repetitions
+ 'aaaaabbbbcccdde'
+ >>> sum(c.values()) # total of all counts
+ 15
+
+ >>> c['a'] # count of letter 'a'
+ 5
+ >>> for elem in 'shazam': # update counts from an iterable
+ ... c[elem] += 1 # by adding 1 to each element's count
+ >>> c['a'] # now there are seven 'a'
+ 7
+ >>> del c['b'] # remove all 'b'
+ >>> c['b'] # now there are zero 'b'
+ 0
+
+ >>> d = Counter('simsalabim') # make another counter
+ >>> c.update(d) # add in the second counter
+ >>> c['a'] # now there are nine 'a'
+ 9
+
+ >>> c.clear() # empty the counter
+ >>> c
+ Counter()
+
+ Note: If a count is set to zero or reduced to zero, it will remain
+ in the counter until the entry is deleted or the counter is cleared:
+
+ >>> c = Counter('aaabbc')
+ >>> c['b'] -= 2 # reduce the count of 'b' by two
+ >>> c.most_common() # 'b' is still in, but its count is zero
+ [('a', 3), ('c', 1), ('b', 0)]
+
+ '''
+ # References:
+ # http://en.wikipedia.org/wiki/Multiset
+ # http://www.gnu.org/software/smalltalk/manual-base/html_node/Bag.html
+ # http://www.demo2s.com/Tutorial/Cpp/0380__set-multiset/Catalog0380__set-multiset.htm
+ # http://code.activestate.com/recipes/259174/
+ # Knuth, TAOCP Vol. II section 4.6.3
+
+ def __init__(*args, **kwds):
+ '''Create a new, empty Counter object. And if given, count elements
+ from an input iterable. Or, initialize the count from another mapping
+ of elements to their counts.
+
+ >>> c = Counter() # a new, empty counter
+ >>> c = Counter('gallahad') # a new counter from an iterable
+ >>> c = Counter({'a': 4, 'b': 2}) # a new counter from a mapping
+ >>> c = Counter(a=4, b=2) # a new counter from keyword args
+
+ '''
+ if not args:
+ raise TypeError("descriptor '__init__' of 'Counter' object "
+ "needs an argument")
+ self, *args = args
+ if len(args) > 1:
+ raise TypeError('expected at most 1 arguments, got %d' % len(args))
+ super(Counter, self).__init__()
+ self.update(*args, **kwds)
+
+ def __missing__(self, key):
+ 'The count of elements not in the Counter is zero.'
+ # Needed so that self[missing_item] does not raise KeyError
+ return 0
+
+ def most_common(self, n=None):
+ '''List the n most common elements and their counts from the most
+ common to the least. If n is None, then list all element counts.
+
+ >>> Counter('abcdeabcdabcaba').most_common(3)
+ [('a', 5), ('b', 4), ('c', 3)]
+
+ '''
+ # Emulate Bag.sortedByCount from Smalltalk
+ if n is None:
+ return sorted(self.items(), key=_itemgetter(1), reverse=True)
+ return _heapq.nlargest(n, self.items(), key=_itemgetter(1))
+
+ def elements(self):
+ '''Iterator over elements repeating each as many times as its count.
+
+ >>> c = Counter('ABCABC')
+ >>> sorted(c.elements())
+ ['A', 'A', 'B', 'B', 'C', 'C']
+
+ # Knuth's example for prime factors of 1836: 2**2 * 3**3 * 17**1
+ >>> prime_factors = Counter({2: 2, 3: 3, 17: 1})
+ >>> product = 1
+ >>> for factor in prime_factors.elements(): # loop over factors
+ ... product *= factor # and multiply them
+ >>> product
+ 1836
+
+ Note, if an element's count has been set to zero or is a negative
+ number, elements() will ignore it.
+
+ '''
+ # Emulate Bag.do from Smalltalk and Multiset.begin from C++.
+ return _chain.from_iterable(_starmap(_repeat, self.items()))
+
+ # Override dict methods where necessary
+
+ @classmethod
+ def fromkeys(cls, iterable, v=None):
+ # There is no equivalent method for counters because setting v=1
+ # means that no element can have a count greater than one.
+ raise NotImplementedError(
+ 'Counter.fromkeys() is undefined. Use Counter(iterable) instead.')
+
+ def update(*args, **kwds):
+ '''Like dict.update() but add counts instead of replacing them.
+
+ Source can be an iterable, a dictionary, or another Counter instance.
+
+ >>> c = Counter('which')
+ >>> c.update('witch') # add elements from another iterable
+ >>> d = Counter('watch')
+ >>> c.update(d) # add elements from another counter
+ >>> c['h'] # four 'h' in which, witch, and watch
+ 4
+
+ '''
+ # The regular dict.update() operation makes no sense here because the
+ # replace behavior results in the some of original untouched counts
+ # being mixed-in with all of the other counts for a mismash that
+ # doesn't have a straight-forward interpretation in most counting
+ # contexts. Instead, we implement straight-addition. Both the inputs
+ # and outputs are allowed to contain zero and negative counts.
+
+ if not args:
+ raise TypeError("descriptor 'update' of 'Counter' object "
+ "needs an argument")
+ self, *args = args
+ if len(args) > 1:
+ raise TypeError('expected at most 1 arguments, got %d' % len(args))
+ iterable = args[0] if args else None
+ if iterable is not None:
+ if isinstance(iterable, _collections_abc.Mapping):
+ if self:
+ self_get = self.get
+ for elem, count in iterable.items():
+ self[elem] = count + self_get(elem, 0)
+ else:
+ super(Counter, self).update(iterable) # fast path when counter is empty
+ else:
+ _count_elements(self, iterable)
+ if kwds:
+ self.update(kwds)
+
+ def subtract(*args, **kwds):
+ '''Like dict.update() but subtracts counts instead of replacing them.
+ Counts can be reduced below zero. Both the inputs and outputs are
+ allowed to contain zero and negative counts.
+
+ Source can be an iterable, a dictionary, or another Counter instance.
+
+ >>> c = Counter('which')
+ >>> c.subtract('witch') # subtract elements from another iterable
+ >>> c.subtract(Counter('watch')) # subtract elements from another counter
+ >>> c['h'] # 2 in which, minus 1 in witch, minus 1 in watch
+ 0
+ >>> c['w'] # 1 in which, minus 1 in witch, minus 1 in watch
+ -1
+
+ '''
+ if not args:
+ raise TypeError("descriptor 'subtract' of 'Counter' object "
+ "needs an argument")
+ self, *args = args
+ if len(args) > 1:
+ raise TypeError('expected at most 1 arguments, got %d' % len(args))
+ iterable = args[0] if args else None
+ if iterable is not None:
+ self_get = self.get
+ if isinstance(iterable, _collections_abc.Mapping):
+ for elem, count in iterable.items():
+ self[elem] = self_get(elem, 0) - count
+ else:
+ for elem in iterable:
+ self[elem] = self_get(elem, 0) - 1
+ if kwds:
+ self.subtract(kwds)
+
+ def copy(self):
+ 'Return a shallow copy.'
+ return self.__class__(self)
+
+ def __reduce__(self):
+ return self.__class__, (dict(self),)
+
+ def __delitem__(self, elem):
+ 'Like dict.__delitem__() but does not raise KeyError for missing values.'
+ if elem in self:
+ super().__delitem__(elem)
+
+ def __repr__(self):
+ if not self:
+ return '%s()' % self.__class__.__name__
+ try:
+ items = ', '.join(map('%r: %r'.__mod__, self.most_common()))
+ return '%s({%s})' % (self.__class__.__name__, items)
+ except TypeError:
+ # handle case where values are not orderable
+ return '{0}({1!r})'.format(self.__class__.__name__, dict(self))
+
+ # Multiset-style mathematical operations discussed in:
+ # Knuth TAOCP Volume II section 4.6.3 exercise 19
+ # and at http://en.wikipedia.org/wiki/Multiset
+ #
+ # Outputs guaranteed to only include positive counts.
+ #
+ # To strip negative and zero counts, add-in an empty counter:
+ # c += Counter()
+
+ def __add__(self, other):
+ '''Add counts from two counters.
+
+ >>> Counter('abbb') + Counter('bcc')
+ Counter({'b': 4, 'c': 2, 'a': 1})
+
+ '''
+ if not isinstance(other, Counter):
+ return NotImplemented
+ result = Counter()
+ for elem, count in self.items():
+ newcount = count + other[elem]
+ if newcount > 0:
+ result[elem] = newcount
+ for elem, count in other.items():
+ if elem not in self and count > 0:
+ result[elem] = count
+ return result
+
+ def __sub__(self, other):
+ ''' Subtract count, but keep only results with positive counts.
+
+ >>> Counter('abbbc') - Counter('bccd')
+ Counter({'b': 2, 'a': 1})
+
+ '''
+ if not isinstance(other, Counter):
+ return NotImplemented
+ result = Counter()
+ for elem, count in self.items():
+ newcount = count - other[elem]
+ if newcount > 0:
+ result[elem] = newcount
+ for elem, count in other.items():
+ if elem not in self and count < 0:
+ result[elem] = 0 - count
+ return result
+
+ def __or__(self, other):
+ '''Union is the maximum of value in either of the input counters.
+
+ >>> Counter('abbb') | Counter('bcc')
+ Counter({'b': 3, 'c': 2, 'a': 1})
+
+ '''
+ if not isinstance(other, Counter):
+ return NotImplemented
+ result = Counter()
+ for elem, count in self.items():
+ other_count = other[elem]
+ newcount = other_count if count < other_count else count
+ if newcount > 0:
+ result[elem] = newcount
+ for elem, count in other.items():
+ if elem not in self and count > 0:
+ result[elem] = count
+ return result
+
+ def __and__(self, other):
+ ''' Intersection is the minimum of corresponding counts.
+
+ >>> Counter('abbb') & Counter('bcc')
+ Counter({'b': 1})
+
+ '''
+ if not isinstance(other, Counter):
+ return NotImplemented
+ result = Counter()
+ for elem, count in self.items():
+ other_count = other[elem]
+ newcount = count if count < other_count else other_count
+ if newcount > 0:
+ result[elem] = newcount
+ return result
+
+ def __pos__(self):
+ 'Adds an empty counter, effectively stripping negative and zero counts'
+ result = Counter()
+ for elem, count in self.items():
+ if count > 0:
+ result[elem] = count
+ return result
+
+ def __neg__(self):
+ '''Subtracts from an empty counter. Strips positive and zero counts,
+ and flips the sign on negative counts.
+
+ '''
+ result = Counter()
+ for elem, count in self.items():
+ if count < 0:
+ result[elem] = 0 - count
+ return result
+
+ def _keep_positive(self):
+ '''Internal method to strip elements with a negative or zero count'''
+ nonpositive = [elem for elem, count in self.items() if not count > 0]
+ for elem in nonpositive:
+ del self[elem]
+ return self
+
+ def __iadd__(self, other):
+ '''Inplace add from another counter, keeping only positive counts.
+
+ >>> c = Counter('abbb')
+ >>> c += Counter('bcc')
+ >>> c
+ Counter({'b': 4, 'c': 2, 'a': 1})
+
+ '''
+ for elem, count in other.items():
+ self[elem] += count
+ return self._keep_positive()
+
+ def __isub__(self, other):
+ '''Inplace subtract counter, but keep only results with positive counts.
+
+ >>> c = Counter('abbbc')
+ >>> c -= Counter('bccd')
+ >>> c
+ Counter({'b': 2, 'a': 1})
+
+ '''
+ for elem, count in other.items():
+ self[elem] -= count
+ return self._keep_positive()
+
+ def __ior__(self, other):
+ '''Inplace union is the maximum of value from either counter.
+
+ >>> c = Counter('abbb')
+ >>> c |= Counter('bcc')
+ >>> c
+ Counter({'b': 3, 'c': 2, 'a': 1})
+
+ '''
+ for elem, other_count in other.items():
+ count = self[elem]
+ if other_count > count:
+ self[elem] = other_count
+ return self._keep_positive()
+
+ def __iand__(self, other):
+ '''Inplace intersection is the minimum of corresponding counts.
+
+ >>> c = Counter('abbb')
+ >>> c &= Counter('bcc')
+ >>> c
+ Counter({'b': 1})
+
+ '''
+ for elem, count in self.items():
+ other_count = other[elem]
+ if other_count < count:
+ self[elem] = other_count
+ return self._keep_positive()
+
+
+########################################################################
+### ChainMap
+########################################################################
+
+class ChainMap(_collections_abc.MutableMapping):
+ ''' A ChainMap groups multiple dicts (or other mappings) together
+ to create a single, updateable view.
+
+ The underlying mappings are stored in a list. That list is public and can
+ be accessed or updated using the *maps* attribute. There is no other
+ state.
+
+ Lookups search the underlying mappings successively until a key is found.
+ In contrast, writes, updates, and deletions only operate on the first
+ mapping.
+
+ '''
+
+ def __init__(self, *maps):
+ '''Initialize a ChainMap by setting *maps* to the given mappings.
+ If no mappings are provided, a single empty dictionary is used.
+
+ '''
+ self.maps = list(maps) or [{}] # always at least one map
+
+ def __missing__(self, key):
+ raise KeyError(key)
+
+ def __getitem__(self, key):
+ for mapping in self.maps:
+ try:
+ return mapping[key] # can't use 'key in mapping' with defaultdict
+ except KeyError:
+ pass
+ return self.__missing__(key) # support subclasses that define __missing__
+
+ def get(self, key, default=None):
+ return self[key] if key in self else default
+
+ def __len__(self):
+ return len(set().union(*self.maps)) # reuses stored hash values if possible
+
+ def __iter__(self):
+ d = {}
+ for mapping in reversed(self.maps):
+ d.update(mapping) # reuses stored hash values if possible
+ return iter(d)
+
+ def __contains__(self, key):
+ return any(key in m for m in self.maps)
+
+ def __bool__(self):
+ return any(self.maps)
+
+ @_recursive_repr()
+ def __repr__(self):
+ return '{0.__class__.__name__}({1})'.format(
+ self, ', '.join(map(repr, self.maps)))
+
+ @classmethod
+ def fromkeys(cls, iterable, *args):
+ 'Create a ChainMap with a single dict created from the iterable.'
+ return cls(dict.fromkeys(iterable, *args))
+
+ def copy(self):
+ 'New ChainMap or subclass with a new copy of maps[0] and refs to maps[1:]'
+ return self.__class__(self.maps[0].copy(), *self.maps[1:])
+
+ __copy__ = copy
+
+ def new_child(self, m=None): # like Django's Context.push()
+ '''New ChainMap with a new map followed by all previous maps.
+ If no map is provided, an empty dict is used.
+ '''
+ if m is None:
+ m = {}
+ return self.__class__(m, *self.maps)
+
+ @property
+ def parents(self): # like Django's Context.pop()
+ 'New ChainMap from maps[1:].'
+ return self.__class__(*self.maps[1:])
+
+ def __setitem__(self, key, value):
+ self.maps[0][key] = value
+
+ def __delitem__(self, key):
+ try:
+ del self.maps[0][key]
+ except KeyError:
+ raise KeyError('Key not found in the first mapping: {!r}'.format(key))
+
+ def popitem(self):
+ 'Remove and return an item pair from maps[0]. Raise KeyError is maps[0] is empty.'
+ try:
+ return self.maps[0].popitem()
+ except KeyError:
+ raise KeyError('No keys found in the first mapping.')
+
+ def pop(self, key, *args):
+ 'Remove *key* from maps[0] and return its value. Raise KeyError if *key* not in maps[0].'
+ try:
+ return self.maps[0].pop(key, *args)
+ except KeyError:
+ raise KeyError('Key not found in the first mapping: {!r}'.format(key))
+
+ def clear(self):
+ 'Clear maps[0], leaving maps[1:] intact.'
+ self.maps[0].clear()
+
+
+################################################################################
+### UserDict
+################################################################################
+
+class UserDict(_collections_abc.MutableMapping):
+
+ # Start by filling-out the abstract methods
+ def __init__(*args, **kwargs):
+ if not args:
+ raise TypeError("descriptor '__init__' of 'UserDict' object "
+ "needs an argument")
+ self, *args = args
+ if len(args) > 1:
+ raise TypeError('expected at most 1 arguments, got %d' % len(args))
+ if args:
+ dict = args[0]
+ elif 'dict' in kwargs:
+ dict = kwargs.pop('dict')
+ import warnings
+ warnings.warn("Passing 'dict' as keyword argument is deprecated",
+ DeprecationWarning, stacklevel=2)
+ else:
+ dict = None
+ self.data = {}
+ if dict is not None:
+ self.update(dict)
+ if len(kwargs):
+ self.update(kwargs)
+ def __len__(self): return len(self.data)
+ def __getitem__(self, key):
+ if key in self.data:
+ return self.data[key]
+ if hasattr(self.__class__, "__missing__"):
+ return self.__class__.__missing__(self, key)
+ raise KeyError(key)
+ def __setitem__(self, key, item): self.data[key] = item
+ def __delitem__(self, key): del self.data[key]
+ def __iter__(self):
+ return iter(self.data)
+
+ # Modify __contains__ to work correctly when __missing__ is present
+ def __contains__(self, key):
+ return key in self.data
+
+ # Now, add the methods in dicts but not in MutableMapping
+ def __repr__(self): return repr(self.data)
+ def copy(self):
+ if self.__class__ is UserDict:
+ return UserDict(self.data.copy())
+ import copy
+ data = self.data
+ try:
+ self.data = {}
+ c = copy.copy(self)
+ finally:
+ self.data = data
+ c.update(self)
+ return c
+ @classmethod
+ def fromkeys(cls, iterable, value=None):
+ d = cls()
+ for key in iterable:
+ d[key] = value
+ return d
+
+
+
+################################################################################
+### UserList
+################################################################################
+
+class UserList(_collections_abc.MutableSequence):
+ """A more or less complete user-defined wrapper around list objects."""
+ def __init__(self, initlist=None):
+ self.data = []
+ if initlist is not None:
+ # XXX should this accept an arbitrary sequence?
+ if type(initlist) == type(self.data):
+ self.data[:] = initlist
+ elif isinstance(initlist, UserList):
+ self.data[:] = initlist.data[:]
+ else:
+ self.data = list(initlist)
+ def __repr__(self): return repr(self.data)
+ def __lt__(self, other): return self.data < self.__cast(other)
+ def __le__(self, other): return self.data <= self.__cast(other)
+ def __eq__(self, other): return self.data == self.__cast(other)
+ def __gt__(self, other): return self.data > self.__cast(other)
+ def __ge__(self, other): return self.data >= self.__cast(other)
+ def __cast(self, other):
+ return other.data if isinstance(other, UserList) else other
+ def __contains__(self, item): return item in self.data
+ def __len__(self): return len(self.data)
+ def __getitem__(self, i): return self.data[i]
+ def __setitem__(self, i, item): self.data[i] = item
+ def __delitem__(self, i): del self.data[i]
+ def __add__(self, other):
+ if isinstance(other, UserList):
+ return self.__class__(self.data + other.data)
+ elif isinstance(other, type(self.data)):
+ return self.__class__(self.data + other)
+ return self.__class__(self.data + list(other))
+ def __radd__(self, other):
+ if isinstance(other, UserList):
+ return self.__class__(other.data + self.data)
+ elif isinstance(other, type(self.data)):
+ return self.__class__(other + self.data)
+ return self.__class__(list(other) + self.data)
+ def __iadd__(self, other):
+ if isinstance(other, UserList):
+ self.data += other.data
+ elif isinstance(other, type(self.data)):
+ self.data += other
+ else:
+ self.data += list(other)
+ return self
+ def __mul__(self, n):
+ return self.__class__(self.data*n)
+ __rmul__ = __mul__
+ def __imul__(self, n):
+ self.data *= n
+ return self
+ def append(self, item): self.data.append(item)
+ def insert(self, i, item): self.data.insert(i, item)
+ def pop(self, i=-1): return self.data.pop(i)
+ def remove(self, item): self.data.remove(item)
+ def clear(self): self.data.clear()
+ def copy(self): return self.__class__(self)
+ def count(self, item): return self.data.count(item)
+ def index(self, item, *args): return self.data.index(item, *args)
+ def reverse(self): self.data.reverse()
+ def sort(self, *args, **kwds): self.data.sort(*args, **kwds)
+ def extend(self, other):
+ if isinstance(other, UserList):
+ self.data.extend(other.data)
+ else:
+ self.data.extend(other)
+
+
+
+################################################################################
+### UserString
+################################################################################
+
+class UserString(_collections_abc.Sequence):
+ def __init__(self, seq):
+ if isinstance(seq, str):
+ self.data = seq
+ elif isinstance(seq, UserString):
+ self.data = seq.data[:]
+ else:
+ self.data = str(seq)
+ def __str__(self): return str(self.data)
+ def __repr__(self): return repr(self.data)
+ def __int__(self): return int(self.data)
+ def __float__(self): return float(self.data)
+ def __complex__(self): return complex(self.data)
+ def __hash__(self): return hash(self.data)
+ def __getnewargs__(self):
+ return (self.data[:],)
+
+ def __eq__(self, string):
+ if isinstance(string, UserString):
+ return self.data == string.data
+ return self.data == string
+ def __lt__(self, string):
+ if isinstance(string, UserString):
+ return self.data < string.data
+ return self.data < string
+ def __le__(self, string):
+ if isinstance(string, UserString):
+ return self.data <= string.data
+ return self.data <= string
+ def __gt__(self, string):
+ if isinstance(string, UserString):
+ return self.data > string.data
+ return self.data > string
+ def __ge__(self, string):
+ if isinstance(string, UserString):
+ return self.data >= string.data
+ return self.data >= string
+
+ def __contains__(self, char):
+ if isinstance(char, UserString):
+ char = char.data
+ return char in self.data
+
+ def __len__(self): return len(self.data)
+ def __getitem__(self, index): return self.__class__(self.data[index])
+ def __add__(self, other):
+ if isinstance(other, UserString):
+ return self.__class__(self.data + other.data)
+ elif isinstance(other, str):
+ return self.__class__(self.data + other)
+ return self.__class__(self.data + str(other))
+ def __radd__(self, other):
+ if isinstance(other, str):
+ return self.__class__(other + self.data)
+ return self.__class__(str(other) + self.data)
+ def __mul__(self, n):
+ return self.__class__(self.data*n)
+ __rmul__ = __mul__
+ def __mod__(self, args):
+ return self.__class__(self.data % args)
+ def __rmod__(self, format):
+ return self.__class__(format % args)
+
+ # the following methods are defined in alphabetical order:
+ def capitalize(self): return self.__class__(self.data.capitalize())
+ def casefold(self):
+ return self.__class__(self.data.casefold())
+ def center(self, width, *args):
+ return self.__class__(self.data.center(width, *args))
+ def count(self, sub, start=0, end=_sys.maxsize):
+ if isinstance(sub, UserString):
+ sub = sub.data
+ return self.data.count(sub, start, end)
+ def encode(self, encoding=None, errors=None): # XXX improve this?
+ if encoding:
+ if errors:
+ return self.__class__(self.data.encode(encoding, errors))
+ return self.__class__(self.data.encode(encoding))
+ return self.__class__(self.data.encode())
+ def endswith(self, suffix, start=0, end=_sys.maxsize):
+ return self.data.endswith(suffix, start, end)
+ def expandtabs(self, tabsize=8):
+ return self.__class__(self.data.expandtabs(tabsize))
+ def find(self, sub, start=0, end=_sys.maxsize):
+ if isinstance(sub, UserString):
+ sub = sub.data
+ return self.data.find(sub, start, end)
+ def format(self, *args, **kwds):
+ return self.data.format(*args, **kwds)
+ def format_map(self, mapping):
+ return self.data.format_map(mapping)
+ def index(self, sub, start=0, end=_sys.maxsize):
+ return self.data.index(sub, start, end)
+ def isalpha(self): return self.data.isalpha()
+ def isalnum(self): return self.data.isalnum()
+ def isascii(self): return self.data.isascii()
+ def isdecimal(self): return self.data.isdecimal()
+ def isdigit(self): return self.data.isdigit()
+ def isidentifier(self): return self.data.isidentifier()
+ def islower(self): return self.data.islower()
+ def isnumeric(self): return self.data.isnumeric()
+ def isprintable(self): return self.data.isprintable()
+ def isspace(self): return self.data.isspace()
+ def istitle(self): return self.data.istitle()
+ def isupper(self): return self.data.isupper()
+ def join(self, seq): return self.data.join(seq)
+ def ljust(self, width, *args):
+ return self.__class__(self.data.ljust(width, *args))
+ def lower(self): return self.__class__(self.data.lower())
+ def lstrip(self, chars=None): return self.__class__(self.data.lstrip(chars))
+ maketrans = str.maketrans
+ def partition(self, sep):
+ return self.data.partition(sep)
+ def replace(self, old, new, maxsplit=-1):
+ if isinstance(old, UserString):
+ old = old.data
+ if isinstance(new, UserString):
+ new = new.data
+ return self.__class__(self.data.replace(old, new, maxsplit))
+ def rfind(self, sub, start=0, end=_sys.maxsize):
+ if isinstance(sub, UserString):
+ sub = sub.data
+ return self.data.rfind(sub, start, end)
+ def rindex(self, sub, start=0, end=_sys.maxsize):
+ return self.data.rindex(sub, start, end)
+ def rjust(self, width, *args):
+ return self.__class__(self.data.rjust(width, *args))
+ def rpartition(self, sep):
+ return self.data.rpartition(sep)
+ def rstrip(self, chars=None):
+ return self.__class__(self.data.rstrip(chars))
+ def split(self, sep=None, maxsplit=-1):
+ return self.data.split(sep, maxsplit)
+ def rsplit(self, sep=None, maxsplit=-1):
+ return self.data.rsplit(sep, maxsplit)
+ def splitlines(self, keepends=False): return self.data.splitlines(keepends)
+ def startswith(self, prefix, start=0, end=_sys.maxsize):
+ return self.data.startswith(prefix, start, end)
+ def strip(self, chars=None): return self.__class__(self.data.strip(chars))
+ def swapcase(self): return self.__class__(self.data.swapcase())
+ def title(self): return self.__class__(self.data.title())
+ def translate(self, *args):
+ return self.__class__(self.data.translate(*args))
+ def upper(self): return self.__class__(self.data.upper())
+ def zfill(self, width): return self.__class__(self.data.zfill(width))
diff --git a/Lib/collections/__pycache__/__init__.cpython-37.pyc b/Lib/collections/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000..f907d76
Binary files /dev/null and b/Lib/collections/__pycache__/__init__.cpython-37.pyc differ
diff --git a/Lib/collections/__pycache__/abc.cpython-37.pyc b/Lib/collections/__pycache__/abc.cpython-37.pyc
new file mode 100644
index 0000000..828f915
Binary files /dev/null and b/Lib/collections/__pycache__/abc.cpython-37.pyc differ
diff --git a/Lib/collections/abc.py b/Lib/collections/abc.py
new file mode 100644
index 0000000..891600d
--- /dev/null
+++ b/Lib/collections/abc.py
@@ -0,0 +1,2 @@
+from _collections_abc import *
+from _collections_abc import __all__
diff --git a/Lib/copy.py b/Lib/copy.py
new file mode 100644
index 0000000..f86040a
--- /dev/null
+++ b/Lib/copy.py
@@ -0,0 +1,313 @@
+"""Generic (shallow and deep) copying operations.
+
+Interface summary:
+
+ import copy
+
+ x = copy.copy(y) # make a shallow copy of y
+ x = copy.deepcopy(y) # make a deep copy of y
+
+For module specific errors, copy.Error is raised.
+
+The difference between shallow and deep copying is only relevant for
+compound objects (objects that contain other objects, like lists or
+class instances).
+
+- A shallow copy constructs a new compound object and then (to the
+ extent possible) inserts *the same objects* into it that the
+ original contains.
+
+- A deep copy constructs a new compound object and then, recursively,
+ inserts *copies* into it of the objects found in the original.
+
+Two problems often exist with deep copy operations that don't exist
+with shallow copy operations:
+
+ a) recursive objects (compound objects that, directly or indirectly,
+ contain a reference to themselves) may cause a recursive loop
+
+ b) because deep copy copies *everything* it may copy too much, e.g.
+ administrative data structures that should be shared even between
+ copies
+
+Python's deep copy operation avoids these problems by:
+
+ a) keeping a table of objects already copied during the current
+ copying pass
+
+ b) letting user-defined classes override the copying operation or the
+ set of components copied
+
+This version does not copy types like module, class, function, method,
+nor stack trace, stack frame, nor file, socket, window, nor array, nor
+any similar types.
+
+Classes can use the same interfaces to control copying that they use
+to control pickling: they can define methods called __getinitargs__(),
+__getstate__() and __setstate__(). See the documentation for module
+"pickle" for information on these methods.
+"""
+
+import types
+import weakref
+from copyreg import dispatch_table
+
+class Error(Exception):
+ pass
+error = Error # backward compatibility
+
+try:
+ from org.python.core import PyStringMap
+except ImportError:
+ PyStringMap = None
+
+__all__ = ["Error", "copy", "deepcopy"]
+
+def copy(x):
+ """Shallow copy operation on arbitrary Python objects.
+
+ See the module's __doc__ string for more info.
+ """
+
+ cls = type(x)
+
+ copier = _copy_dispatch.get(cls)
+ if copier:
+ return copier(x)
+
+ try:
+ issc = issubclass(cls, type)
+ except TypeError: # cls is not a class
+ issc = False
+ if issc:
+ # treat it as a regular class:
+ return _copy_immutable(x)
+
+ copier = getattr(cls, "__copy__", None)
+ if copier:
+ return copier(x)
+
+ reductor = dispatch_table.get(cls)
+ if reductor:
+ rv = reductor(x)
+ else:
+ reductor = getattr(x, "__reduce_ex__", None)
+ if reductor:
+ rv = reductor(4)
+ else:
+ reductor = getattr(x, "__reduce__", None)
+ if reductor:
+ rv = reductor()
+ else:
+ raise Error("un(shallow)copyable object of type %s" % cls)
+
+ if isinstance(rv, str):
+ return x
+ return _reconstruct(x, None, *rv)
+
+
+_copy_dispatch = d = {}
+
+def _copy_immutable(x):
+ return x
+for t in (type(None), int, float, bool, complex, str, tuple,
+ bytes, frozenset, type, range, slice,
+ types.BuiltinFunctionType, type(Ellipsis), type(NotImplemented),
+ types.FunctionType, weakref.ref):
+ d[t] = _copy_immutable
+t = getattr(types, "CodeType", None)
+if t is not None:
+ d[t] = _copy_immutable
+
+d[list] = list.copy
+d[dict] = dict.copy
+d[set] = set.copy
+d[bytearray] = bytearray.copy
+
+if PyStringMap is not None:
+ d[PyStringMap] = PyStringMap.copy
+
+del d, t
+
+def deepcopy(x, memo=None, _nil=[]):
+ """Deep copy operation on arbitrary Python objects.
+
+ See the module's __doc__ string for more info.
+ """
+
+ if memo is None:
+ memo = {}
+
+ d = id(x)
+ y = memo.get(d, _nil)
+ if y is not _nil:
+ return y
+
+ cls = type(x)
+
+ copier = _deepcopy_dispatch.get(cls)
+ if copier:
+ y = copier(x, memo)
+ else:
+ try:
+ issc = issubclass(cls, type)
+ except TypeError: # cls is not a class (old Boost; see SF #502085)
+ issc = 0
+ if issc:
+ y = _deepcopy_atomic(x, memo)
+ else:
+ copier = getattr(x, "__deepcopy__", None)
+ if copier:
+ y = copier(memo)
+ else:
+ reductor = dispatch_table.get(cls)
+ if reductor:
+ rv = reductor(x)
+ else:
+ reductor = getattr(x, "__reduce_ex__", None)
+ if reductor:
+ rv = reductor(4)
+ else:
+ reductor = getattr(x, "__reduce__", None)
+ if reductor:
+ rv = reductor()
+ else:
+ raise Error(
+ "un(deep)copyable object of type %s" % cls)
+ if isinstance(rv, str):
+ y = x
+ else:
+ y = _reconstruct(x, memo, *rv)
+
+ # If is its own copy, don't memoize.
+ if y is not x:
+ memo[d] = y
+ _keep_alive(x, memo) # Make sure x lives at least as long as d
+ return y
+
+_deepcopy_dispatch = d = {}
+
+def _deepcopy_atomic(x, memo):
+ return x
+d[type(None)] = _deepcopy_atomic
+d[type(Ellipsis)] = _deepcopy_atomic
+d[type(NotImplemented)] = _deepcopy_atomic
+d[int] = _deepcopy_atomic
+d[float] = _deepcopy_atomic
+d[bool] = _deepcopy_atomic
+d[complex] = _deepcopy_atomic
+d[bytes] = _deepcopy_atomic
+d[str] = _deepcopy_atomic
+try:
+ d[types.CodeType] = _deepcopy_atomic
+except AttributeError:
+ pass
+d[type] = _deepcopy_atomic
+d[types.BuiltinFunctionType] = _deepcopy_atomic
+d[types.FunctionType] = _deepcopy_atomic
+d[weakref.ref] = _deepcopy_atomic
+
+def _deepcopy_list(x, memo, deepcopy=deepcopy):
+ y = []
+ memo[id(x)] = y
+ append = y.append
+ for a in x:
+ append(deepcopy(a, memo))
+ return y
+d[list] = _deepcopy_list
+
+def _deepcopy_tuple(x, memo, deepcopy=deepcopy):
+ y = [deepcopy(a, memo) for a in x]
+ # We're not going to put the tuple in the memo, but it's still important we
+ # check for it, in case the tuple contains recursive mutable structures.
+ try:
+ return memo[id(x)]
+ except KeyError:
+ pass
+ for k, j in zip(x, y):
+ if k is not j:
+ y = tuple(y)
+ break
+ else:
+ y = x
+ return y
+d[tuple] = _deepcopy_tuple
+
+def _deepcopy_dict(x, memo, deepcopy=deepcopy):
+ y = {}
+ memo[id(x)] = y
+ for key, value in x.items():
+ y[deepcopy(key, memo)] = deepcopy(value, memo)
+ return y
+d[dict] = _deepcopy_dict
+if PyStringMap is not None:
+ d[PyStringMap] = _deepcopy_dict
+
+def _deepcopy_method(x, memo): # Copy instance methods
+ return type(x)(x.__func__, deepcopy(x.__self__, memo))
+d[types.MethodType] = _deepcopy_method
+
+del d
+
+def _keep_alive(x, memo):
+ """Keeps a reference to the object x in the memo.
+
+ Because we remember objects by their id, we have
+ to assure that possibly temporary objects are kept
+ alive by referencing them.
+ We store a reference at the id of the memo, which should
+ normally not be used unless someone tries to deepcopy
+ the memo itself...
+ """
+ try:
+ memo[id(memo)].append(x)
+ except KeyError:
+ # aha, this is the first one :-)
+ memo[id(memo)]=[x]
+
+def _reconstruct(x, memo, func, args,
+ state=None, listiter=None, dictiter=None,
+ deepcopy=deepcopy):
+ deep = memo is not None
+ if deep and args:
+ args = (deepcopy(arg, memo) for arg in args)
+ y = func(*args)
+ if deep:
+ memo[id(x)] = y
+
+ if state is not None:
+ if deep:
+ state = deepcopy(state, memo)
+ if hasattr(y, '__setstate__'):
+ y.__setstate__(state)
+ else:
+ if isinstance(state, tuple) and len(state) == 2:
+ state, slotstate = state
+ else:
+ slotstate = None
+ if state is not None:
+ y.__dict__.update(state)
+ if slotstate is not None:
+ for key, value in slotstate.items():
+ setattr(y, key, value)
+
+ if listiter is not None:
+ if deep:
+ for item in listiter:
+ item = deepcopy(item, memo)
+ y.append(item)
+ else:
+ for item in listiter:
+ y.append(item)
+ if dictiter is not None:
+ if deep:
+ for key, value in dictiter:
+ key = deepcopy(key, memo)
+ value = deepcopy(value, memo)
+ y[key] = value
+ else:
+ for key, value in dictiter:
+ y[key] = value
+ return y
+
+del types, weakref, PyStringMap
diff --git a/Lib/copyreg.py b/Lib/copyreg.py
new file mode 100644
index 0000000..bbe1af4
--- /dev/null
+++ b/Lib/copyreg.py
@@ -0,0 +1,206 @@
+"""Helper to provide extensibility for pickle.
+
+This is only useful to add pickle support for extension types defined in
+C, not for instances of user-defined classes.
+"""
+
+__all__ = ["pickle", "constructor",
+ "add_extension", "remove_extension", "clear_extension_cache"]
+
+dispatch_table = {}
+
+def pickle(ob_type, pickle_function, constructor_ob=None):
+ if not callable(pickle_function):
+ raise TypeError("reduction functions must be callable")
+ dispatch_table[ob_type] = pickle_function
+
+ # The constructor_ob function is a vestige of safe for unpickling.
+ # There is no reason for the caller to pass it anymore.
+ if constructor_ob is not None:
+ constructor(constructor_ob)
+
+def constructor(object):
+ if not callable(object):
+ raise TypeError("constructors must be callable")
+
+# Example: provide pickling support for complex numbers.
+
+try:
+ complex
+except NameError:
+ pass
+else:
+
+ def pickle_complex(c):
+ return complex, (c.real, c.imag)
+
+ pickle(complex, pickle_complex, complex)
+
+# Support for pickling new-style objects
+
+def _reconstructor(cls, base, state):
+ if base is object:
+ obj = object.__new__(cls)
+ else:
+ obj = base.__new__(cls, state)
+ if base.__init__ != object.__init__:
+ base.__init__(obj, state)
+ return obj
+
+_HEAPTYPE = 1<<9
+
+# Python code for object.__reduce_ex__ for protocols 0 and 1
+
+def _reduce_ex(self, proto):
+ assert proto < 2
+ for base in self.__class__.__mro__:
+ if hasattr(base, '__flags__') and not base.__flags__ & _HEAPTYPE:
+ break
+ else:
+ base = object # not really reachable
+ if base is object:
+ state = None
+ else:
+ if base is self.__class__:
+ raise TypeError("can't pickle %s objects" % base.__name__)
+ state = base(self)
+ args = (self.__class__, base, state)
+ try:
+ getstate = self.__getstate__
+ except AttributeError:
+ if getattr(self, "__slots__", None):
+ raise TypeError("a class that defines __slots__ without "
+ "defining __getstate__ cannot be pickled") from None
+ try:
+ dict = self.__dict__
+ except AttributeError:
+ dict = None
+ else:
+ dict = getstate()
+ if dict:
+ return _reconstructor, args, dict
+ else:
+ return _reconstructor, args
+
+# Helper for __reduce_ex__ protocol 2
+
+def __newobj__(cls, *args):
+ return cls.__new__(cls, *args)
+
+def __newobj_ex__(cls, args, kwargs):
+ """Used by pickle protocol 4, instead of __newobj__ to allow classes with
+ keyword-only arguments to be pickled correctly.
+ """
+ return cls.__new__(cls, *args, **kwargs)
+
+def _slotnames(cls):
+ """Return a list of slot names for a given class.
+
+ This needs to find slots defined by the class and its bases, so we
+ can't simply return the __slots__ attribute. We must walk down
+ the Method Resolution Order and concatenate the __slots__ of each
+ class found there. (This assumes classes don't modify their
+ __slots__ attribute to misrepresent their slots after the class is
+ defined.)
+ """
+
+ # Get the value from a cache in the class if possible
+ names = cls.__dict__.get("__slotnames__")
+ if names is not None:
+ return names
+
+ # Not cached -- calculate the value
+ names = []
+ if not hasattr(cls, "__slots__"):
+ # This class has no slots
+ pass
+ else:
+ # Slots found -- gather slot names from all base classes
+ for c in cls.__mro__:
+ if "__slots__" in c.__dict__:
+ slots = c.__dict__['__slots__']
+ # if class has a single slot, it can be given as a string
+ if isinstance(slots, str):
+ slots = (slots,)
+ for name in slots:
+ # special descriptors
+ if name in ("__dict__", "__weakref__"):
+ continue
+ # mangled names
+ elif name.startswith('__') and not name.endswith('__'):
+ stripped = c.__name__.lstrip('_')
+ if stripped:
+ names.append('_%s%s' % (stripped, name))
+ else:
+ names.append(name)
+ else:
+ names.append(name)
+
+ # Cache the outcome in the class if at all possible
+ try:
+ cls.__slotnames__ = names
+ except:
+ pass # But don't die if we can't
+
+ return names
+
+# A registry of extension codes. This is an ad-hoc compression
+# mechanism. Whenever a global reference to , is about
+# to be pickled, the (, ) tuple is looked up here to see
+# if it is a registered extension code for it. Extension codes are
+# universal, so that the meaning of a pickle does not depend on
+# context. (There are also some codes reserved for local use that
+# don't have this restriction.) Codes are positive ints; 0 is
+# reserved.
+
+_extension_registry = {} # key -> code
+_inverted_registry = {} # code -> key
+_extension_cache = {} # code -> object
+# Don't ever rebind those names: pickling grabs a reference to them when
+# it's initialized, and won't see a rebinding.
+
+def add_extension(module, name, code):
+ """Register an extension code."""
+ code = int(code)
+ if not 1 <= code <= 0x7fffffff:
+ raise ValueError("code out of range")
+ key = (module, name)
+ if (_extension_registry.get(key) == code and
+ _inverted_registry.get(code) == key):
+ return # Redundant registrations are benign
+ if key in _extension_registry:
+ raise ValueError("key %s is already registered with code %s" %
+ (key, _extension_registry[key]))
+ if code in _inverted_registry:
+ raise ValueError("code %s is already in use for key %s" %
+ (code, _inverted_registry[code]))
+ _extension_registry[key] = code
+ _inverted_registry[code] = key
+
+def remove_extension(module, name, code):
+ """Unregister an extension code. For testing only."""
+ key = (module, name)
+ if (_extension_registry.get(key) != code or
+ _inverted_registry.get(code) != key):
+ raise ValueError("key %s is not registered with code %s" %
+ (key, code))
+ del _extension_registry[key]
+ del _inverted_registry[code]
+ if code in _extension_cache:
+ del _extension_cache[code]
+
+def clear_extension_cache():
+ _extension_cache.clear()
+
+# Standard extension code assignments
+
+# Reserved ranges
+
+# First Last Count Purpose
+# 1 127 127 Reserved for Python standard library
+# 128 191 64 Reserved for Zope
+# 192 239 48 Reserved for 3rd parties
+# 240 255 16 Reserved for private use (will never be assigned)
+# 256 Inf Inf Reserved for future assignment
+
+# Extension codes are assigned by the Python Software Foundation.
diff --git a/Lib/distutils/__init__.py b/Lib/distutils/__init__.py
new file mode 100644
index 0000000..29fc1da
--- /dev/null
+++ b/Lib/distutils/__init__.py
@@ -0,0 +1,101 @@
+import os
+import sys
+import warnings
+import imp
+import opcode # opcode is not a virtualenv module, so we can use it to find the stdlib
+ # Important! To work on pypy, this must be a module that resides in the
+ # lib-python/modified-x.y.z directory
+
+dirname = os.path.dirname
+
+distutils_path = os.path.join(os.path.dirname(opcode.__file__), 'distutils')
+if os.path.normpath(distutils_path) == os.path.dirname(os.path.normpath(__file__)):
+ warnings.warn(
+ "The virtualenv distutils package at %s appears to be in the same location as the system distutils?")
+else:
+ __path__.insert(0, distutils_path)
+ real_distutils = imp.load_module("_virtualenv_distutils", None, distutils_path, ('', '', imp.PKG_DIRECTORY))
+ # Copy the relevant attributes
+ try:
+ __revision__ = real_distutils.__revision__
+ except AttributeError:
+ pass
+ __version__ = real_distutils.__version__
+
+from distutils import dist, sysconfig
+
+try:
+ basestring
+except NameError:
+ basestring = str
+
+## patch build_ext (distutils doesn't know how to get the libs directory
+## path on windows - it hardcodes the paths around the patched sys.prefix)
+
+if sys.platform == 'win32':
+ from distutils.command.build_ext import build_ext as old_build_ext
+ class build_ext(old_build_ext):
+ def finalize_options (self):
+ if self.library_dirs is None:
+ self.library_dirs = []
+ elif isinstance(self.library_dirs, basestring):
+ self.library_dirs = self.library_dirs.split(os.pathsep)
+
+ self.library_dirs.insert(0, os.path.join(sys.real_prefix, "Libs"))
+ old_build_ext.finalize_options(self)
+
+ from distutils.command import build_ext as build_ext_module
+ build_ext_module.build_ext = build_ext
+
+## distutils.dist patches:
+
+old_find_config_files = dist.Distribution.find_config_files
+def find_config_files(self):
+ found = old_find_config_files(self)
+ system_distutils = os.path.join(distutils_path, 'distutils.cfg')
+ #if os.path.exists(system_distutils):
+ # found.insert(0, system_distutils)
+ # What to call the per-user config file
+ if os.name == 'posix':
+ user_filename = ".pydistutils.cfg"
+ else:
+ user_filename = "pydistutils.cfg"
+ user_filename = os.path.join(sys.prefix, user_filename)
+ if os.path.isfile(user_filename):
+ for item in list(found):
+ if item.endswith('pydistutils.cfg'):
+ found.remove(item)
+ found.append(user_filename)
+ return found
+dist.Distribution.find_config_files = find_config_files
+
+## distutils.sysconfig patches:
+
+old_get_python_inc = sysconfig.get_python_inc
+def sysconfig_get_python_inc(plat_specific=0, prefix=None):
+ if prefix is None:
+ prefix = sys.real_prefix
+ return old_get_python_inc(plat_specific, prefix)
+sysconfig_get_python_inc.__doc__ = old_get_python_inc.__doc__
+sysconfig.get_python_inc = sysconfig_get_python_inc
+
+old_get_python_lib = sysconfig.get_python_lib
+def sysconfig_get_python_lib(plat_specific=0, standard_lib=0, prefix=None):
+ if standard_lib and prefix is None:
+ prefix = sys.real_prefix
+ return old_get_python_lib(plat_specific, standard_lib, prefix)
+sysconfig_get_python_lib.__doc__ = old_get_python_lib.__doc__
+sysconfig.get_python_lib = sysconfig_get_python_lib
+
+old_get_config_vars = sysconfig.get_config_vars
+def sysconfig_get_config_vars(*args):
+ real_vars = old_get_config_vars(*args)
+ if sys.platform == 'win32':
+ lib_dir = os.path.join(sys.real_prefix, "libs")
+ if isinstance(real_vars, dict) and 'LIBDIR' not in real_vars:
+ real_vars['LIBDIR'] = lib_dir # asked for all
+ elif isinstance(real_vars, list) and 'LIBDIR' in args:
+ real_vars = real_vars + [lib_dir] # asked for list
+ return real_vars
+sysconfig_get_config_vars.__doc__ = old_get_config_vars.__doc__
+sysconfig.get_config_vars = sysconfig_get_config_vars
diff --git a/Lib/distutils/__pycache__/__init__.cpython-37.pyc b/Lib/distutils/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000..a7b446a
Binary files /dev/null and b/Lib/distutils/__pycache__/__init__.cpython-37.pyc differ
diff --git a/Lib/distutils/distutils.cfg b/Lib/distutils/distutils.cfg
new file mode 100644
index 0000000..1af230e
--- /dev/null
+++ b/Lib/distutils/distutils.cfg
@@ -0,0 +1,6 @@
+# This is a config file local to this virtualenv installation
+# You may include options that will be used by all distutils commands,
+# and by easy_install. For instance:
+#
+# [easy_install]
+# find_links = http://mylocalsite
diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py
new file mode 100644
index 0000000..025b7a8
--- /dev/null
+++ b/Lib/encodings/__init__.py
@@ -0,0 +1,170 @@
+""" Standard "encodings" Package
+
+ Standard Python encoding modules are stored in this package
+ directory.
+
+ Codec modules must have names corresponding to normalized encoding
+ names as defined in the normalize_encoding() function below, e.g.
+ 'utf-8' must be implemented by the module 'utf_8.py'.
+
+ Each codec module must export the following interface:
+
+ * getregentry() -> codecs.CodecInfo object
+ The getregentry() API must return a CodecInfo object with encoder, decoder,
+ incrementalencoder, incrementaldecoder, streamwriter and streamreader
+ atttributes which adhere to the Python Codec Interface Standard.
+
+ In addition, a module may optionally also define the following
+ APIs which are then used by the package's codec search function:
+
+ * getaliases() -> sequence of encoding name strings to use as aliases
+
+ Alias names returned by getaliases() must be normalized encoding
+ names as defined by normalize_encoding().
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
+
+"""#"
+
+import codecs
+import sys
+from . import aliases
+
+_cache = {}
+_unknown = '--unknown--'
+_import_tail = ['*']
+_aliases = aliases.aliases
+
+class CodecRegistryError(LookupError, SystemError):
+ pass
+
+def normalize_encoding(encoding):
+
+ """ Normalize an encoding name.
+
+ Normalization works as follows: all non-alphanumeric
+ characters except the dot used for Python package names are
+ collapsed and replaced with a single underscore, e.g. ' -;#'
+ becomes '_'. Leading and trailing underscores are removed.
+
+ Note that encoding names should be ASCII only; if they do use
+ non-ASCII characters, these must be Latin-1 compatible.
+
+ """
+ if isinstance(encoding, bytes):
+ encoding = str(encoding, "ascii")
+
+ chars = []
+ punct = False
+ for c in encoding:
+ if c.isalnum() or c == '.':
+ if punct and chars:
+ chars.append('_')
+ chars.append(c)
+ punct = False
+ else:
+ punct = True
+ return ''.join(chars)
+
+def search_function(encoding):
+
+ # Cache lookup
+ entry = _cache.get(encoding, _unknown)
+ if entry is not _unknown:
+ return entry
+
+ # Import the module:
+ #
+ # First try to find an alias for the normalized encoding
+ # name and lookup the module using the aliased name, then try to
+ # lookup the module using the standard import scheme, i.e. first
+ # try in the encodings package, then at top-level.
+ #
+ norm_encoding = normalize_encoding(encoding)
+ aliased_encoding = _aliases.get(norm_encoding) or \
+ _aliases.get(norm_encoding.replace('.', '_'))
+ if aliased_encoding is not None:
+ modnames = [aliased_encoding,
+ norm_encoding]
+ else:
+ modnames = [norm_encoding]
+ for modname in modnames:
+ if not modname or '.' in modname:
+ continue
+ try:
+ # Import is absolute to prevent the possibly malicious import of a
+ # module with side-effects that is not in the 'encodings' package.
+ mod = __import__('encodings.' + modname, fromlist=_import_tail,
+ level=0)
+ except ImportError:
+ # ImportError may occur because 'encodings.(modname)' does not exist,
+ # or because it imports a name that does not exist (see mbcs and oem)
+ pass
+ else:
+ break
+ else:
+ mod = None
+
+ try:
+ getregentry = mod.getregentry
+ except AttributeError:
+ # Not a codec module
+ mod = None
+
+ if mod is None:
+ # Cache misses
+ _cache[encoding] = None
+ return None
+
+ # Now ask the module for the registry entry
+ entry = getregentry()
+ if not isinstance(entry, codecs.CodecInfo):
+ if not 4 <= len(entry) <= 7:
+ raise CodecRegistryError('module "%s" (%s) failed to register'
+ % (mod.__name__, mod.__file__))
+ if not callable(entry[0]) or not callable(entry[1]) or \
+ (entry[2] is not None and not callable(entry[2])) or \
+ (entry[3] is not None and not callable(entry[3])) or \
+ (len(entry) > 4 and entry[4] is not None and not callable(entry[4])) or \
+ (len(entry) > 5 and entry[5] is not None and not callable(entry[5])):
+ raise CodecRegistryError('incompatible codecs in module "%s" (%s)'
+ % (mod.__name__, mod.__file__))
+ if len(entry)<7 or entry[6] is None:
+ entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],)
+ entry = codecs.CodecInfo(*entry)
+
+ # Cache the codec registry entry
+ _cache[encoding] = entry
+
+ # Register its aliases (without overwriting previously registered
+ # aliases)
+ try:
+ codecaliases = mod.getaliases()
+ except AttributeError:
+ pass
+ else:
+ for alias in codecaliases:
+ if alias not in _aliases:
+ _aliases[alias] = modname
+
+ # Return the registry entry
+ return entry
+
+# Register the search_function in the Python codec registry
+codecs.register(search_function)
+
+if sys.platform == 'win32':
+ def _alias_mbcs(encoding):
+ try:
+ import _winapi
+ ansi_code_page = "cp%s" % _winapi.GetACP()
+ if encoding == ansi_code_page:
+ import encodings.mbcs
+ return encodings.mbcs.getregentry()
+ except ImportError:
+ # Imports may fail while we are shutting down
+ pass
+
+ codecs.register(_alias_mbcs)
diff --git a/Lib/encodings/__pycache__/__init__.cpython-37.pyc b/Lib/encodings/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000..2204762
Binary files /dev/null and b/Lib/encodings/__pycache__/__init__.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/aliases.cpython-37.pyc b/Lib/encodings/__pycache__/aliases.cpython-37.pyc
new file mode 100644
index 0000000..32442d3
Binary files /dev/null and b/Lib/encodings/__pycache__/aliases.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/cp1252.cpython-37.pyc b/Lib/encodings/__pycache__/cp1252.cpython-37.pyc
new file mode 100644
index 0000000..df1584a
Binary files /dev/null and b/Lib/encodings/__pycache__/cp1252.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/cp437.cpython-37.pyc b/Lib/encodings/__pycache__/cp437.cpython-37.pyc
new file mode 100644
index 0000000..a335b28
Binary files /dev/null and b/Lib/encodings/__pycache__/cp437.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/idna.cpython-37.pyc b/Lib/encodings/__pycache__/idna.cpython-37.pyc
new file mode 100644
index 0000000..fb696c9
Binary files /dev/null and b/Lib/encodings/__pycache__/idna.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/latin_1.cpython-37.pyc b/Lib/encodings/__pycache__/latin_1.cpython-37.pyc
new file mode 100644
index 0000000..b868d88
Binary files /dev/null and b/Lib/encodings/__pycache__/latin_1.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/utf_16_be.cpython-37.pyc b/Lib/encodings/__pycache__/utf_16_be.cpython-37.pyc
new file mode 100644
index 0000000..1a50bda
Binary files /dev/null and b/Lib/encodings/__pycache__/utf_16_be.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/utf_16_le.cpython-37.pyc b/Lib/encodings/__pycache__/utf_16_le.cpython-37.pyc
new file mode 100644
index 0000000..13f0270
Binary files /dev/null and b/Lib/encodings/__pycache__/utf_16_le.cpython-37.pyc differ
diff --git a/Lib/encodings/__pycache__/utf_8.cpython-37.pyc b/Lib/encodings/__pycache__/utf_8.cpython-37.pyc
new file mode 100644
index 0000000..d9d142e
Binary files /dev/null and b/Lib/encodings/__pycache__/utf_8.cpython-37.pyc differ
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
new file mode 100644
index 0000000..2e63c2f
--- /dev/null
+++ b/Lib/encodings/aliases.py
@@ -0,0 +1,550 @@
+""" Encoding Aliases Support
+
+ This module is used by the encodings package search function to
+ map encodings names to module names.
+
+ Note that the search function normalizes the encoding names before
+ doing the lookup, so the mapping will have to map normalized
+ encoding names to module names.
+
+ Contents:
+
+ The following aliases dictionary contains mappings of all IANA
+ character set names for which the Python core library provides
+ codecs. In addition to these, a few Python specific codec
+ aliases have also been added.
+
+"""
+aliases = {
+
+ # Please keep this list sorted alphabetically by value !
+
+ # ascii codec
+ '646' : 'ascii',
+ 'ansi_x3.4_1968' : 'ascii',
+ 'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name
+ 'ansi_x3.4_1986' : 'ascii',
+ 'cp367' : 'ascii',
+ 'csascii' : 'ascii',
+ 'ibm367' : 'ascii',
+ 'iso646_us' : 'ascii',
+ 'iso_646.irv_1991' : 'ascii',
+ 'iso_ir_6' : 'ascii',
+ 'us' : 'ascii',
+ 'us_ascii' : 'ascii',
+
+ # base64_codec codec
+ 'base64' : 'base64_codec',
+ 'base_64' : 'base64_codec',
+
+ # big5 codec
+ 'big5_tw' : 'big5',
+ 'csbig5' : 'big5',
+
+ # big5hkscs codec
+ 'big5_hkscs' : 'big5hkscs',
+ 'hkscs' : 'big5hkscs',
+
+ # bz2_codec codec
+ 'bz2' : 'bz2_codec',
+
+ # cp037 codec
+ '037' : 'cp037',
+ 'csibm037' : 'cp037',
+ 'ebcdic_cp_ca' : 'cp037',
+ 'ebcdic_cp_nl' : 'cp037',
+ 'ebcdic_cp_us' : 'cp037',
+ 'ebcdic_cp_wt' : 'cp037',
+ 'ibm037' : 'cp037',
+ 'ibm039' : 'cp037',
+
+ # cp1026 codec
+ '1026' : 'cp1026',
+ 'csibm1026' : 'cp1026',
+ 'ibm1026' : 'cp1026',
+
+ # cp1125 codec
+ '1125' : 'cp1125',
+ 'ibm1125' : 'cp1125',
+ 'cp866u' : 'cp1125',
+ 'ruscii' : 'cp1125',
+
+ # cp1140 codec
+ '1140' : 'cp1140',
+ 'ibm1140' : 'cp1140',
+
+ # cp1250 codec
+ '1250' : 'cp1250',
+ 'windows_1250' : 'cp1250',
+
+ # cp1251 codec
+ '1251' : 'cp1251',
+ 'windows_1251' : 'cp1251',
+
+ # cp1252 codec
+ '1252' : 'cp1252',
+ 'windows_1252' : 'cp1252',
+
+ # cp1253 codec
+ '1253' : 'cp1253',
+ 'windows_1253' : 'cp1253',
+
+ # cp1254 codec
+ '1254' : 'cp1254',
+ 'windows_1254' : 'cp1254',
+
+ # cp1255 codec
+ '1255' : 'cp1255',
+ 'windows_1255' : 'cp1255',
+
+ # cp1256 codec
+ '1256' : 'cp1256',
+ 'windows_1256' : 'cp1256',
+
+ # cp1257 codec
+ '1257' : 'cp1257',
+ 'windows_1257' : 'cp1257',
+
+ # cp1258 codec
+ '1258' : 'cp1258',
+ 'windows_1258' : 'cp1258',
+
+ # cp273 codec
+ '273' : 'cp273',
+ 'ibm273' : 'cp273',
+ 'csibm273' : 'cp273',
+
+ # cp424 codec
+ '424' : 'cp424',
+ 'csibm424' : 'cp424',
+ 'ebcdic_cp_he' : 'cp424',
+ 'ibm424' : 'cp424',
+
+ # cp437 codec
+ '437' : 'cp437',
+ 'cspc8codepage437' : 'cp437',
+ 'ibm437' : 'cp437',
+
+ # cp500 codec
+ '500' : 'cp500',
+ 'csibm500' : 'cp500',
+ 'ebcdic_cp_be' : 'cp500',
+ 'ebcdic_cp_ch' : 'cp500',
+ 'ibm500' : 'cp500',
+
+ # cp775 codec
+ '775' : 'cp775',
+ 'cspc775baltic' : 'cp775',
+ 'ibm775' : 'cp775',
+
+ # cp850 codec
+ '850' : 'cp850',
+ 'cspc850multilingual' : 'cp850',
+ 'ibm850' : 'cp850',
+
+ # cp852 codec
+ '852' : 'cp852',
+ 'cspcp852' : 'cp852',
+ 'ibm852' : 'cp852',
+
+ # cp855 codec
+ '855' : 'cp855',
+ 'csibm855' : 'cp855',
+ 'ibm855' : 'cp855',
+
+ # cp857 codec
+ '857' : 'cp857',
+ 'csibm857' : 'cp857',
+ 'ibm857' : 'cp857',
+
+ # cp858 codec
+ '858' : 'cp858',
+ 'csibm858' : 'cp858',
+ 'ibm858' : 'cp858',
+
+ # cp860 codec
+ '860' : 'cp860',
+ 'csibm860' : 'cp860',
+ 'ibm860' : 'cp860',
+
+ # cp861 codec
+ '861' : 'cp861',
+ 'cp_is' : 'cp861',
+ 'csibm861' : 'cp861',
+ 'ibm861' : 'cp861',
+
+ # cp862 codec
+ '862' : 'cp862',
+ 'cspc862latinhebrew' : 'cp862',
+ 'ibm862' : 'cp862',
+
+ # cp863 codec
+ '863' : 'cp863',
+ 'csibm863' : 'cp863',
+ 'ibm863' : 'cp863',
+
+ # cp864 codec
+ '864' : 'cp864',
+ 'csibm864' : 'cp864',
+ 'ibm864' : 'cp864',
+
+ # cp865 codec
+ '865' : 'cp865',
+ 'csibm865' : 'cp865',
+ 'ibm865' : 'cp865',
+
+ # cp866 codec
+ '866' : 'cp866',
+ 'csibm866' : 'cp866',
+ 'ibm866' : 'cp866',
+
+ # cp869 codec
+ '869' : 'cp869',
+ 'cp_gr' : 'cp869',
+ 'csibm869' : 'cp869',
+ 'ibm869' : 'cp869',
+
+ # cp932 codec
+ '932' : 'cp932',
+ 'ms932' : 'cp932',
+ 'mskanji' : 'cp932',
+ 'ms_kanji' : 'cp932',
+
+ # cp949 codec
+ '949' : 'cp949',
+ 'ms949' : 'cp949',
+ 'uhc' : 'cp949',
+
+ # cp950 codec
+ '950' : 'cp950',
+ 'ms950' : 'cp950',
+
+ # euc_jis_2004 codec
+ 'jisx0213' : 'euc_jis_2004',
+ 'eucjis2004' : 'euc_jis_2004',
+ 'euc_jis2004' : 'euc_jis_2004',
+
+ # euc_jisx0213 codec
+ 'eucjisx0213' : 'euc_jisx0213',
+
+ # euc_jp codec
+ 'eucjp' : 'euc_jp',
+ 'ujis' : 'euc_jp',
+ 'u_jis' : 'euc_jp',
+
+ # euc_kr codec
+ 'euckr' : 'euc_kr',
+ 'korean' : 'euc_kr',
+ 'ksc5601' : 'euc_kr',
+ 'ks_c_5601' : 'euc_kr',
+ 'ks_c_5601_1987' : 'euc_kr',
+ 'ksx1001' : 'euc_kr',
+ 'ks_x_1001' : 'euc_kr',
+
+ # gb18030 codec
+ 'gb18030_2000' : 'gb18030',
+
+ # gb2312 codec
+ 'chinese' : 'gb2312',
+ 'csiso58gb231280' : 'gb2312',
+ 'euc_cn' : 'gb2312',
+ 'euccn' : 'gb2312',
+ 'eucgb2312_cn' : 'gb2312',
+ 'gb2312_1980' : 'gb2312',
+ 'gb2312_80' : 'gb2312',
+ 'iso_ir_58' : 'gb2312',
+
+ # gbk codec
+ '936' : 'gbk',
+ 'cp936' : 'gbk',
+ 'ms936' : 'gbk',
+
+ # hex_codec codec
+ 'hex' : 'hex_codec',
+
+ # hp_roman8 codec
+ 'roman8' : 'hp_roman8',
+ 'r8' : 'hp_roman8',
+ 'csHPRoman8' : 'hp_roman8',
+
+ # hz codec
+ 'hzgb' : 'hz',
+ 'hz_gb' : 'hz',
+ 'hz_gb_2312' : 'hz',
+
+ # iso2022_jp codec
+ 'csiso2022jp' : 'iso2022_jp',
+ 'iso2022jp' : 'iso2022_jp',
+ 'iso_2022_jp' : 'iso2022_jp',
+
+ # iso2022_jp_1 codec
+ 'iso2022jp_1' : 'iso2022_jp_1',
+ 'iso_2022_jp_1' : 'iso2022_jp_1',
+
+ # iso2022_jp_2 codec
+ 'iso2022jp_2' : 'iso2022_jp_2',
+ 'iso_2022_jp_2' : 'iso2022_jp_2',
+
+ # iso2022_jp_2004 codec
+ 'iso_2022_jp_2004' : 'iso2022_jp_2004',
+ 'iso2022jp_2004' : 'iso2022_jp_2004',
+
+ # iso2022_jp_3 codec
+ 'iso2022jp_3' : 'iso2022_jp_3',
+ 'iso_2022_jp_3' : 'iso2022_jp_3',
+
+ # iso2022_jp_ext codec
+ 'iso2022jp_ext' : 'iso2022_jp_ext',
+ 'iso_2022_jp_ext' : 'iso2022_jp_ext',
+
+ # iso2022_kr codec
+ 'csiso2022kr' : 'iso2022_kr',
+ 'iso2022kr' : 'iso2022_kr',
+ 'iso_2022_kr' : 'iso2022_kr',
+
+ # iso8859_10 codec
+ 'csisolatin6' : 'iso8859_10',
+ 'iso_8859_10' : 'iso8859_10',
+ 'iso_8859_10_1992' : 'iso8859_10',
+ 'iso_ir_157' : 'iso8859_10',
+ 'l6' : 'iso8859_10',
+ 'latin6' : 'iso8859_10',
+
+ # iso8859_11 codec
+ 'thai' : 'iso8859_11',
+ 'iso_8859_11' : 'iso8859_11',
+ 'iso_8859_11_2001' : 'iso8859_11',
+
+ # iso8859_13 codec
+ 'iso_8859_13' : 'iso8859_13',
+ 'l7' : 'iso8859_13',
+ 'latin7' : 'iso8859_13',
+
+ # iso8859_14 codec
+ 'iso_8859_14' : 'iso8859_14',
+ 'iso_8859_14_1998' : 'iso8859_14',
+ 'iso_celtic' : 'iso8859_14',
+ 'iso_ir_199' : 'iso8859_14',
+ 'l8' : 'iso8859_14',
+ 'latin8' : 'iso8859_14',
+
+ # iso8859_15 codec
+ 'iso_8859_15' : 'iso8859_15',
+ 'l9' : 'iso8859_15',
+ 'latin9' : 'iso8859_15',
+
+ # iso8859_16 codec
+ 'iso_8859_16' : 'iso8859_16',
+ 'iso_8859_16_2001' : 'iso8859_16',
+ 'iso_ir_226' : 'iso8859_16',
+ 'l10' : 'iso8859_16',
+ 'latin10' : 'iso8859_16',
+
+ # iso8859_2 codec
+ 'csisolatin2' : 'iso8859_2',
+ 'iso_8859_2' : 'iso8859_2',
+ 'iso_8859_2_1987' : 'iso8859_2',
+ 'iso_ir_101' : 'iso8859_2',
+ 'l2' : 'iso8859_2',
+ 'latin2' : 'iso8859_2',
+
+ # iso8859_3 codec
+ 'csisolatin3' : 'iso8859_3',
+ 'iso_8859_3' : 'iso8859_3',
+ 'iso_8859_3_1988' : 'iso8859_3',
+ 'iso_ir_109' : 'iso8859_3',
+ 'l3' : 'iso8859_3',
+ 'latin3' : 'iso8859_3',
+
+ # iso8859_4 codec
+ 'csisolatin4' : 'iso8859_4',
+ 'iso_8859_4' : 'iso8859_4',
+ 'iso_8859_4_1988' : 'iso8859_4',
+ 'iso_ir_110' : 'iso8859_4',
+ 'l4' : 'iso8859_4',
+ 'latin4' : 'iso8859_4',
+
+ # iso8859_5 codec
+ 'csisolatincyrillic' : 'iso8859_5',
+ 'cyrillic' : 'iso8859_5',
+ 'iso_8859_5' : 'iso8859_5',
+ 'iso_8859_5_1988' : 'iso8859_5',
+ 'iso_ir_144' : 'iso8859_5',
+
+ # iso8859_6 codec
+ 'arabic' : 'iso8859_6',
+ 'asmo_708' : 'iso8859_6',
+ 'csisolatinarabic' : 'iso8859_6',
+ 'ecma_114' : 'iso8859_6',
+ 'iso_8859_6' : 'iso8859_6',
+ 'iso_8859_6_1987' : 'iso8859_6',
+ 'iso_ir_127' : 'iso8859_6',
+
+ # iso8859_7 codec
+ 'csisolatingreek' : 'iso8859_7',
+ 'ecma_118' : 'iso8859_7',
+ 'elot_928' : 'iso8859_7',
+ 'greek' : 'iso8859_7',
+ 'greek8' : 'iso8859_7',
+ 'iso_8859_7' : 'iso8859_7',
+ 'iso_8859_7_1987' : 'iso8859_7',
+ 'iso_ir_126' : 'iso8859_7',
+
+ # iso8859_8 codec
+ 'csisolatinhebrew' : 'iso8859_8',
+ 'hebrew' : 'iso8859_8',
+ 'iso_8859_8' : 'iso8859_8',
+ 'iso_8859_8_1988' : 'iso8859_8',
+ 'iso_ir_138' : 'iso8859_8',
+
+ # iso8859_9 codec
+ 'csisolatin5' : 'iso8859_9',
+ 'iso_8859_9' : 'iso8859_9',
+ 'iso_8859_9_1989' : 'iso8859_9',
+ 'iso_ir_148' : 'iso8859_9',
+ 'l5' : 'iso8859_9',
+ 'latin5' : 'iso8859_9',
+
+ # johab codec
+ 'cp1361' : 'johab',
+ 'ms1361' : 'johab',
+
+ # koi8_r codec
+ 'cskoi8r' : 'koi8_r',
+
+ # kz1048 codec
+ 'kz_1048' : 'kz1048',
+ 'rk1048' : 'kz1048',
+ 'strk1048_2002' : 'kz1048',
+
+ # latin_1 codec
+ #
+ # Note that the latin_1 codec is implemented internally in C and a
+ # lot faster than the charmap codec iso8859_1 which uses the same
+ # encoding. This is why we discourage the use of the iso8859_1
+ # codec and alias it to latin_1 instead.
+ #
+ '8859' : 'latin_1',
+ 'cp819' : 'latin_1',
+ 'csisolatin1' : 'latin_1',
+ 'ibm819' : 'latin_1',
+ 'iso8859' : 'latin_1',
+ 'iso8859_1' : 'latin_1',
+ 'iso_8859_1' : 'latin_1',
+ 'iso_8859_1_1987' : 'latin_1',
+ 'iso_ir_100' : 'latin_1',
+ 'l1' : 'latin_1',
+ 'latin' : 'latin_1',
+ 'latin1' : 'latin_1',
+
+ # mac_cyrillic codec
+ 'maccyrillic' : 'mac_cyrillic',
+
+ # mac_greek codec
+ 'macgreek' : 'mac_greek',
+
+ # mac_iceland codec
+ 'maciceland' : 'mac_iceland',
+
+ # mac_latin2 codec
+ 'maccentraleurope' : 'mac_latin2',
+ 'maclatin2' : 'mac_latin2',
+
+ # mac_roman codec
+ 'macintosh' : 'mac_roman',
+ 'macroman' : 'mac_roman',
+
+ # mac_turkish codec
+ 'macturkish' : 'mac_turkish',
+
+ # mbcs codec
+ 'ansi' : 'mbcs',
+ 'dbcs' : 'mbcs',
+
+ # ptcp154 codec
+ 'csptcp154' : 'ptcp154',
+ 'pt154' : 'ptcp154',
+ 'cp154' : 'ptcp154',
+ 'cyrillic_asian' : 'ptcp154',
+
+ # quopri_codec codec
+ 'quopri' : 'quopri_codec',
+ 'quoted_printable' : 'quopri_codec',
+ 'quotedprintable' : 'quopri_codec',
+
+ # rot_13 codec
+ 'rot13' : 'rot_13',
+
+ # shift_jis codec
+ 'csshiftjis' : 'shift_jis',
+ 'shiftjis' : 'shift_jis',
+ 'sjis' : 'shift_jis',
+ 's_jis' : 'shift_jis',
+
+ # shift_jis_2004 codec
+ 'shiftjis2004' : 'shift_jis_2004',
+ 'sjis_2004' : 'shift_jis_2004',
+ 's_jis_2004' : 'shift_jis_2004',
+
+ # shift_jisx0213 codec
+ 'shiftjisx0213' : 'shift_jisx0213',
+ 'sjisx0213' : 'shift_jisx0213',
+ 's_jisx0213' : 'shift_jisx0213',
+
+ # tactis codec
+ 'tis260' : 'tactis',
+
+ # tis_620 codec
+ 'tis620' : 'tis_620',
+ 'tis_620_0' : 'tis_620',
+ 'tis_620_2529_0' : 'tis_620',
+ 'tis_620_2529_1' : 'tis_620',
+ 'iso_ir_166' : 'tis_620',
+
+ # utf_16 codec
+ 'u16' : 'utf_16',
+ 'utf16' : 'utf_16',
+
+ # utf_16_be codec
+ 'unicodebigunmarked' : 'utf_16_be',
+ 'utf_16be' : 'utf_16_be',
+
+ # utf_16_le codec
+ 'unicodelittleunmarked' : 'utf_16_le',
+ 'utf_16le' : 'utf_16_le',
+
+ # utf_32 codec
+ 'u32' : 'utf_32',
+ 'utf32' : 'utf_32',
+
+ # utf_32_be codec
+ 'utf_32be' : 'utf_32_be',
+
+ # utf_32_le codec
+ 'utf_32le' : 'utf_32_le',
+
+ # utf_7 codec
+ 'u7' : 'utf_7',
+ 'utf7' : 'utf_7',
+ 'unicode_1_1_utf_7' : 'utf_7',
+
+ # utf_8 codec
+ 'u8' : 'utf_8',
+ 'utf' : 'utf_8',
+ 'utf8' : 'utf_8',
+ 'utf8_ucs2' : 'utf_8',
+ 'utf8_ucs4' : 'utf_8',
+
+ # uu_codec codec
+ 'uu' : 'uu_codec',
+
+ # zlib_codec codec
+ 'zip' : 'zlib_codec',
+ 'zlib' : 'zlib_codec',
+
+ # temporary mac CJK aliases, will be replaced by proper codecs in 3.1
+ 'x_mac_japanese' : 'shift_jis',
+ 'x_mac_korean' : 'euc_kr',
+ 'x_mac_simp_chinese' : 'gb2312',
+ 'x_mac_trad_chinese' : 'big5',
+}
diff --git a/Lib/encodings/ascii.py b/Lib/encodings/ascii.py
new file mode 100644
index 0000000..2033cde
--- /dev/null
+++ b/Lib/encodings/ascii.py
@@ -0,0 +1,50 @@
+""" Python 'ascii' Codec
+
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
+
+"""
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ # Note: Binding these as C functions will result in the class not
+ # converting them to methods. This is intended.
+ encode = codecs.ascii_encode
+ decode = codecs.ascii_decode
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.ascii_encode(input, self.errors)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.ascii_decode(input, self.errors)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+class StreamConverter(StreamWriter,StreamReader):
+
+ encode = codecs.ascii_decode
+ decode = codecs.ascii_encode
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='ascii',
+ encode=Codec.encode,
+ decode=Codec.decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/base64_codec.py b/Lib/encodings/base64_codec.py
new file mode 100644
index 0000000..8e7703b
--- /dev/null
+++ b/Lib/encodings/base64_codec.py
@@ -0,0 +1,55 @@
+"""Python 'base64_codec' Codec - base64 content transfer encoding.
+
+This codec de/encodes from bytes to bytes.
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import base64
+
+### Codec APIs
+
+def base64_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (base64.encodebytes(input), len(input))
+
+def base64_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (base64.decodebytes(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return base64_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return base64_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ assert self.errors == 'strict'
+ return base64.encodebytes(input)
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ assert self.errors == 'strict'
+ return base64.decodebytes(input)
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='base64',
+ encode=base64_encode,
+ decode=base64_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ _is_text_encoding=False,
+ )
diff --git a/Lib/encodings/big5.py b/Lib/encodings/big5.py
new file mode 100644
index 0000000..7adeb0e
--- /dev/null
+++ b/Lib/encodings/big5.py
@@ -0,0 +1,39 @@
+#
+# big5.py: Python Unicode Codec for BIG5
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_tw, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_tw.getcodec('big5')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='big5',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/big5hkscs.py b/Lib/encodings/big5hkscs.py
new file mode 100644
index 0000000..350df37
--- /dev/null
+++ b/Lib/encodings/big5hkscs.py
@@ -0,0 +1,39 @@
+#
+# big5hkscs.py: Python Unicode Codec for BIG5HKSCS
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_hk, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_hk.getcodec('big5hkscs')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='big5hkscs',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/bz2_codec.py b/Lib/encodings/bz2_codec.py
new file mode 100644
index 0000000..fd9495e
--- /dev/null
+++ b/Lib/encodings/bz2_codec.py
@@ -0,0 +1,78 @@
+"""Python 'bz2_codec' Codec - bz2 compression encoding.
+
+This codec de/encodes from bytes to bytes and is therefore usable with
+bytes.transform() and bytes.untransform().
+
+Adapted by Raymond Hettinger from zlib_codec.py which was written
+by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import bz2 # this codec needs the optional bz2 module !
+
+### Codec APIs
+
+def bz2_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (bz2.compress(input), len(input))
+
+def bz2_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (bz2.decompress(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return bz2_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return bz2_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def __init__(self, errors='strict'):
+ assert errors == 'strict'
+ self.errors = errors
+ self.compressobj = bz2.BZ2Compressor()
+
+ def encode(self, input, final=False):
+ if final:
+ c = self.compressobj.compress(input)
+ return c + self.compressobj.flush()
+ else:
+ return self.compressobj.compress(input)
+
+ def reset(self):
+ self.compressobj = bz2.BZ2Compressor()
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def __init__(self, errors='strict'):
+ assert errors == 'strict'
+ self.errors = errors
+ self.decompressobj = bz2.BZ2Decompressor()
+
+ def decode(self, input, final=False):
+ try:
+ return self.decompressobj.decompress(input)
+ except EOFError:
+ return ''
+
+ def reset(self):
+ self.decompressobj = bz2.BZ2Decompressor()
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name="bz2",
+ encode=bz2_encode,
+ decode=bz2_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ _is_text_encoding=False,
+ )
diff --git a/Lib/encodings/charmap.py b/Lib/encodings/charmap.py
new file mode 100644
index 0000000..81189b1
--- /dev/null
+++ b/Lib/encodings/charmap.py
@@ -0,0 +1,69 @@
+""" Generic Python Character Mapping Codec.
+
+ Use this codec directly rather than through the automatic
+ conversion mechanisms supplied by unicode() and .encode().
+
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+
+(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ # Note: Binding these as C functions will result in the class not
+ # converting them to methods. This is intended.
+ encode = codecs.charmap_encode
+ decode = codecs.charmap_decode
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def __init__(self, errors='strict', mapping=None):
+ codecs.IncrementalEncoder.__init__(self, errors)
+ self.mapping = mapping
+
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input, self.errors, self.mapping)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def __init__(self, errors='strict', mapping=None):
+ codecs.IncrementalDecoder.__init__(self, errors)
+ self.mapping = mapping
+
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input, self.errors, self.mapping)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+
+ def __init__(self,stream,errors='strict',mapping=None):
+ codecs.StreamWriter.__init__(self,stream,errors)
+ self.mapping = mapping
+
+ def encode(self,input,errors='strict'):
+ return Codec.encode(input,errors,self.mapping)
+
+class StreamReader(Codec,codecs.StreamReader):
+
+ def __init__(self,stream,errors='strict',mapping=None):
+ codecs.StreamReader.__init__(self,stream,errors)
+ self.mapping = mapping
+
+ def decode(self,input,errors='strict'):
+ return Codec.decode(input,errors,self.mapping)
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='charmap',
+ encode=Codec.encode,
+ decode=Codec.decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/cp037.py b/Lib/encodings/cp037.py
new file mode 100644
index 0000000..4edd708
--- /dev/null
+++ b/Lib/encodings/cp037.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp037',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x9c' # 0x04 -> CONTROL
+ '\t' # 0x05 -> HORIZONTAL TABULATION
+ '\x86' # 0x06 -> CONTROL
+ '\x7f' # 0x07 -> DELETE
+ '\x97' # 0x08 -> CONTROL
+ '\x8d' # 0x09 -> CONTROL
+ '\x8e' # 0x0A -> CONTROL
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x9d' # 0x14 -> CONTROL
+ '\x85' # 0x15 -> CONTROL
+ '\x08' # 0x16 -> BACKSPACE
+ '\x87' # 0x17 -> CONTROL
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x92' # 0x1A -> CONTROL
+ '\x8f' # 0x1B -> CONTROL
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ '\x80' # 0x20 -> CONTROL
+ '\x81' # 0x21 -> CONTROL
+ '\x82' # 0x22 -> CONTROL
+ '\x83' # 0x23 -> CONTROL
+ '\x84' # 0x24 -> CONTROL
+ '\n' # 0x25 -> LINE FEED
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK
+ '\x1b' # 0x27 -> ESCAPE
+ '\x88' # 0x28 -> CONTROL
+ '\x89' # 0x29 -> CONTROL
+ '\x8a' # 0x2A -> CONTROL
+ '\x8b' # 0x2B -> CONTROL
+ '\x8c' # 0x2C -> CONTROL
+ '\x05' # 0x2D -> ENQUIRY
+ '\x06' # 0x2E -> ACKNOWLEDGE
+ '\x07' # 0x2F -> BELL
+ '\x90' # 0x30 -> CONTROL
+ '\x91' # 0x31 -> CONTROL
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE
+ '\x93' # 0x33 -> CONTROL
+ '\x94' # 0x34 -> CONTROL
+ '\x95' # 0x35 -> CONTROL
+ '\x96' # 0x36 -> CONTROL
+ '\x04' # 0x37 -> END OF TRANSMISSION
+ '\x98' # 0x38 -> CONTROL
+ '\x99' # 0x39 -> CONTROL
+ '\x9a' # 0x3A -> CONTROL
+ '\x9b' # 0x3B -> CONTROL
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
+ '\x9e' # 0x3E -> CONTROL
+ '\x1a' # 0x3F -> SUBSTITUTE
+ ' ' # 0x40 -> SPACE
+ '\xa0' # 0x41 -> NO-BREAK SPACE
+ '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
+ '\xa2' # 0x4A -> CENT SIGN
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '|' # 0x4F -> VERTICAL LINE
+ '&' # 0x50 -> AMPERSAND
+ '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
+ '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
+ '!' # 0x5A -> EXCLAMATION MARK
+ '$' # 0x5B -> DOLLAR SIGN
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '\xac' # 0x5F -> NOT SIGN
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xa6' # 0x6A -> BROKEN BAR
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
+ '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '`' # 0x79 -> GRAVE ACCENT
+ ':' # 0x7A -> COLON
+ '#' # 0x7B -> NUMBER SIGN
+ '@' # 0x7C -> COMMERCIAL AT
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '"' # 0x7F -> QUOTATION MARK
+ '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
+ '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
+ '\xb1' # 0x8F -> PLUS-MINUS SIGN
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
+ '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
+ '\xb8' # 0x9D -> CEDILLA
+ '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
+ '\xa4' # 0x9F -> CURRENCY SIGN
+ '\xb5' # 0xA0 -> MICRO SIGN
+ '~' # 0xA1 -> TILDE
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
+ '\xbf' # 0xAB -> INVERTED QUESTION MARK
+ '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
+ '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
+ '\xae' # 0xAF -> REGISTERED SIGN
+ '^' # 0xB0 -> CIRCUMFLEX ACCENT
+ '\xa3' # 0xB1 -> POUND SIGN
+ '\xa5' # 0xB2 -> YEN SIGN
+ '\xb7' # 0xB3 -> MIDDLE DOT
+ '\xa9' # 0xB4 -> COPYRIGHT SIGN
+ '\xa7' # 0xB5 -> SECTION SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+ '[' # 0xBA -> LEFT SQUARE BRACKET
+ ']' # 0xBB -> RIGHT SQUARE BRACKET
+ '\xaf' # 0xBC -> MACRON
+ '\xa8' # 0xBD -> DIAERESIS
+ '\xb4' # 0xBE -> ACUTE ACCENT
+ '\xd7' # 0xBF -> MULTIPLICATION SIGN
+ '{' # 0xC0 -> LEFT CURLY BRACKET
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
+ '}' # 0xD0 -> RIGHT CURLY BRACKET
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb9' # 0xDA -> SUPERSCRIPT ONE
+ '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
+ '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\\' # 0xE0 -> REVERSE SOLIDUS
+ '\xf7' # 0xE1 -> DIVISION SIGN
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\x9f' # 0xFF -> CONTROL
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1006.py b/Lib/encodings/cp1006.py
new file mode 100644
index 0000000..a1221c3
--- /dev/null
+++ b/Lib/encodings/cp1006.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1006',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\x80' # 0x80 ->
+ '\x81' # 0x81 ->
+ '\x82' # 0x82 ->
+ '\x83' # 0x83 ->
+ '\x84' # 0x84 ->
+ '\x85' # 0x85 ->
+ '\x86' # 0x86 ->
+ '\x87' # 0x87 ->
+ '\x88' # 0x88 ->
+ '\x89' # 0x89 ->
+ '\x8a' # 0x8A ->
+ '\x8b' # 0x8B ->
+ '\x8c' # 0x8C ->
+ '\x8d' # 0x8D ->
+ '\x8e' # 0x8E ->
+ '\x8f' # 0x8F ->
+ '\x90' # 0x90 ->
+ '\x91' # 0x91 ->
+ '\x92' # 0x92 ->
+ '\x93' # 0x93 ->
+ '\x94' # 0x94 ->
+ '\x95' # 0x95 ->
+ '\x96' # 0x96 ->
+ '\x97' # 0x97 ->
+ '\x98' # 0x98 ->
+ '\x99' # 0x99 ->
+ '\x9a' # 0x9A ->
+ '\x9b' # 0x9B ->
+ '\x9c' # 0x9C ->
+ '\x9d' # 0x9D ->
+ '\x9e' # 0x9E ->
+ '\x9f' # 0x9F ->
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO
+ '\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE
+ '\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO
+ '\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE
+ '\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR
+ '\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE
+ '\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX
+ '\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN
+ '\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT
+ '\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE
+ '\u060c' # 0xAB -> ARABIC COMMA
+ '\u061b' # 0xAC -> ARABIC SEMICOLON
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\u061f' # 0xAE -> ARABIC QUESTION MARK
+ '\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
+ '\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM
+ '\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM
+ '\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM
+ '\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM
+ '\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM
+ '\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM
+ '\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM
+ '\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM
+ '\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM
+ '\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM
+ '\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM
+ '\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM
+ '\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM
+ '\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM
+ '\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM
+ '\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM
+ '\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM
+ '\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM
+ '\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM
+ '\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM
+ '\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM
+ '\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM
+ '\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM
+ '\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN
+ '\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM
+ '\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM
+ '\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM
+ '\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM
+ '\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM
+ '\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM
+ '\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM
+ '\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM
+ '\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM
+ '\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM
+ '\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM
+ '\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM
+ '\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM
+ '\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM
+ '\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM
+ '\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM
+ '\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM
+ '\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM
+ '\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM
+ '\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM
+ '\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM
+ '\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM
+ '\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM
+ '\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM
+ '\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM
+ '\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM
+ '\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM
+ '\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM
+ '\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM
+ '\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM
+ '\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM
+ '\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM
+ '\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM
+ '\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM
+ '\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM
+ '\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM
+ '\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM
+ '\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM
+ '\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM
+ '\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
+ '\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM
+ '\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM
+ '\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM
+ '\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM
+ '\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM
+ '\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM
+ '\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM
+ '\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM
+ '\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
+ '\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM
+ '\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM
+ '\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM
+ '\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM
+ '\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM
+ '\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM
+ '\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1026.py b/Lib/encodings/cp1026.py
new file mode 100644
index 0000000..46f71f7
--- /dev/null
+++ b/Lib/encodings/cp1026.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1026',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x9c' # 0x04 -> CONTROL
+ '\t' # 0x05 -> HORIZONTAL TABULATION
+ '\x86' # 0x06 -> CONTROL
+ '\x7f' # 0x07 -> DELETE
+ '\x97' # 0x08 -> CONTROL
+ '\x8d' # 0x09 -> CONTROL
+ '\x8e' # 0x0A -> CONTROL
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x9d' # 0x14 -> CONTROL
+ '\x85' # 0x15 -> CONTROL
+ '\x08' # 0x16 -> BACKSPACE
+ '\x87' # 0x17 -> CONTROL
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x92' # 0x1A -> CONTROL
+ '\x8f' # 0x1B -> CONTROL
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ '\x80' # 0x20 -> CONTROL
+ '\x81' # 0x21 -> CONTROL
+ '\x82' # 0x22 -> CONTROL
+ '\x83' # 0x23 -> CONTROL
+ '\x84' # 0x24 -> CONTROL
+ '\n' # 0x25 -> LINE FEED
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK
+ '\x1b' # 0x27 -> ESCAPE
+ '\x88' # 0x28 -> CONTROL
+ '\x89' # 0x29 -> CONTROL
+ '\x8a' # 0x2A -> CONTROL
+ '\x8b' # 0x2B -> CONTROL
+ '\x8c' # 0x2C -> CONTROL
+ '\x05' # 0x2D -> ENQUIRY
+ '\x06' # 0x2E -> ACKNOWLEDGE
+ '\x07' # 0x2F -> BELL
+ '\x90' # 0x30 -> CONTROL
+ '\x91' # 0x31 -> CONTROL
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE
+ '\x93' # 0x33 -> CONTROL
+ '\x94' # 0x34 -> CONTROL
+ '\x95' # 0x35 -> CONTROL
+ '\x96' # 0x36 -> CONTROL
+ '\x04' # 0x37 -> END OF TRANSMISSION
+ '\x98' # 0x38 -> CONTROL
+ '\x99' # 0x39 -> CONTROL
+ '\x9a' # 0x3A -> CONTROL
+ '\x9b' # 0x3B -> CONTROL
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
+ '\x9e' # 0x3E -> CONTROL
+ '\x1a' # 0x3F -> SUBSTITUTE
+ ' ' # 0x40 -> SPACE
+ '\xa0' # 0x41 -> NO-BREAK SPACE
+ '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '{' # 0x48 -> LEFT CURLY BRACKET
+ '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
+ '\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '!' # 0x4F -> EXCLAMATION MARK
+ '&' # 0x50 -> AMPERSAND
+ '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
+ '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
+ '\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE
+ '\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '^' # 0x5F -> CIRCUMFLEX ACCENT
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '[' # 0x68 -> LEFT SQUARE BRACKET
+ '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
+ '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I
+ ':' # 0x7A -> COLON
+ '\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '}' # 0x8C -> RIGHT CURLY BRACKET
+ '`' # 0x8D -> GRAVE ACCENT
+ '\xa6' # 0x8E -> BROKEN BAR
+ '\xb1' # 0x8F -> PLUS-MINUS SIGN
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
+ '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
+ '\xb8' # 0x9D -> CEDILLA
+ '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
+ '\xa4' # 0x9F -> CURRENCY SIGN
+ '\xb5' # 0xA0 -> MICRO SIGN
+ '\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
+ '\xbf' # 0xAB -> INVERTED QUESTION MARK
+ ']' # 0xAC -> RIGHT SQUARE BRACKET
+ '$' # 0xAD -> DOLLAR SIGN
+ '@' # 0xAE -> COMMERCIAL AT
+ '\xae' # 0xAF -> REGISTERED SIGN
+ '\xa2' # 0xB0 -> CENT SIGN
+ '\xa3' # 0xB1 -> POUND SIGN
+ '\xa5' # 0xB2 -> YEN SIGN
+ '\xb7' # 0xB3 -> MIDDLE DOT
+ '\xa9' # 0xB4 -> COPYRIGHT SIGN
+ '\xa7' # 0xB5 -> SECTION SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+ '\xac' # 0xBA -> NOT SIGN
+ '|' # 0xBB -> VERTICAL LINE
+ '\xaf' # 0xBC -> MACRON
+ '\xa8' # 0xBD -> DIAERESIS
+ '\xb4' # 0xBE -> ACUTE ACCENT
+ '\xd7' # 0xBF -> MULTIPLICATION SIGN
+ '\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '~' # 0xCC -> TILDE
+ '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
+ '\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb9' # 0xDA -> SUPERSCRIPT ONE
+ '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\\' # 0xDC -> REVERSE SOLIDUS
+ '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
+ '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xf7' # 0xE1 -> DIVISION SIGN
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '#' # 0xEC -> NUMBER SIGN
+ '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '"' # 0xFC -> QUOTATION MARK
+ '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\x9f' # 0xFF -> CONTROL
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1125.py b/Lib/encodings/cp1125.py
new file mode 100644
index 0000000..b1fd69d
--- /dev/null
+++ b/Lib/encodings/cp1125.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec for CP1125
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1125',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x0410, # CYRILLIC CAPITAL LETTER A
+ 0x0081: 0x0411, # CYRILLIC CAPITAL LETTER BE
+ 0x0082: 0x0412, # CYRILLIC CAPITAL LETTER VE
+ 0x0083: 0x0413, # CYRILLIC CAPITAL LETTER GHE
+ 0x0084: 0x0414, # CYRILLIC CAPITAL LETTER DE
+ 0x0085: 0x0415, # CYRILLIC CAPITAL LETTER IE
+ 0x0086: 0x0416, # CYRILLIC CAPITAL LETTER ZHE
+ 0x0087: 0x0417, # CYRILLIC CAPITAL LETTER ZE
+ 0x0088: 0x0418, # CYRILLIC CAPITAL LETTER I
+ 0x0089: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I
+ 0x008a: 0x041a, # CYRILLIC CAPITAL LETTER KA
+ 0x008b: 0x041b, # CYRILLIC CAPITAL LETTER EL
+ 0x008c: 0x041c, # CYRILLIC CAPITAL LETTER EM
+ 0x008d: 0x041d, # CYRILLIC CAPITAL LETTER EN
+ 0x008e: 0x041e, # CYRILLIC CAPITAL LETTER O
+ 0x008f: 0x041f, # CYRILLIC CAPITAL LETTER PE
+ 0x0090: 0x0420, # CYRILLIC CAPITAL LETTER ER
+ 0x0091: 0x0421, # CYRILLIC CAPITAL LETTER ES
+ 0x0092: 0x0422, # CYRILLIC CAPITAL LETTER TE
+ 0x0093: 0x0423, # CYRILLIC CAPITAL LETTER U
+ 0x0094: 0x0424, # CYRILLIC CAPITAL LETTER EF
+ 0x0095: 0x0425, # CYRILLIC CAPITAL LETTER HA
+ 0x0096: 0x0426, # CYRILLIC CAPITAL LETTER TSE
+ 0x0097: 0x0427, # CYRILLIC CAPITAL LETTER CHE
+ 0x0098: 0x0428, # CYRILLIC CAPITAL LETTER SHA
+ 0x0099: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA
+ 0x009a: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN
+ 0x009b: 0x042b, # CYRILLIC CAPITAL LETTER YERU
+ 0x009c: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN
+ 0x009d: 0x042d, # CYRILLIC CAPITAL LETTER E
+ 0x009e: 0x042e, # CYRILLIC CAPITAL LETTER YU
+ 0x009f: 0x042f, # CYRILLIC CAPITAL LETTER YA
+ 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A
+ 0x00a1: 0x0431, # CYRILLIC SMALL LETTER BE
+ 0x00a2: 0x0432, # CYRILLIC SMALL LETTER VE
+ 0x00a3: 0x0433, # CYRILLIC SMALL LETTER GHE
+ 0x00a4: 0x0434, # CYRILLIC SMALL LETTER DE
+ 0x00a5: 0x0435, # CYRILLIC SMALL LETTER IE
+ 0x00a6: 0x0436, # CYRILLIC SMALL LETTER ZHE
+ 0x00a7: 0x0437, # CYRILLIC SMALL LETTER ZE
+ 0x00a8: 0x0438, # CYRILLIC SMALL LETTER I
+ 0x00a9: 0x0439, # CYRILLIC SMALL LETTER SHORT I
+ 0x00aa: 0x043a, # CYRILLIC SMALL LETTER KA
+ 0x00ab: 0x043b, # CYRILLIC SMALL LETTER EL
+ 0x00ac: 0x043c, # CYRILLIC SMALL LETTER EM
+ 0x00ad: 0x043d, # CYRILLIC SMALL LETTER EN
+ 0x00ae: 0x043e, # CYRILLIC SMALL LETTER O
+ 0x00af: 0x043f, # CYRILLIC SMALL LETTER PE
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x0440, # CYRILLIC SMALL LETTER ER
+ 0x00e1: 0x0441, # CYRILLIC SMALL LETTER ES
+ 0x00e2: 0x0442, # CYRILLIC SMALL LETTER TE
+ 0x00e3: 0x0443, # CYRILLIC SMALL LETTER U
+ 0x00e4: 0x0444, # CYRILLIC SMALL LETTER EF
+ 0x00e5: 0x0445, # CYRILLIC SMALL LETTER HA
+ 0x00e6: 0x0446, # CYRILLIC SMALL LETTER TSE
+ 0x00e7: 0x0447, # CYRILLIC SMALL LETTER CHE
+ 0x00e8: 0x0448, # CYRILLIC SMALL LETTER SHA
+ 0x00e9: 0x0449, # CYRILLIC SMALL LETTER SHCHA
+ 0x00ea: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN
+ 0x00eb: 0x044b, # CYRILLIC SMALL LETTER YERU
+ 0x00ec: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN
+ 0x00ed: 0x044d, # CYRILLIC SMALL LETTER E
+ 0x00ee: 0x044e, # CYRILLIC SMALL LETTER YU
+ 0x00ef: 0x044f, # CYRILLIC SMALL LETTER YA
+ 0x00f0: 0x0401, # CYRILLIC CAPITAL LETTER IO
+ 0x00f1: 0x0451, # CYRILLIC SMALL LETTER IO
+ 0x00f2: 0x0490, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+ 0x00f3: 0x0491, # CYRILLIC SMALL LETTER GHE WITH UPTURN
+ 0x00f4: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ 0x00f5: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE
+ 0x00f6: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x00f7: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x00f8: 0x0407, # CYRILLIC CAPITAL LETTER YI
+ 0x00f9: 0x0457, # CYRILLIC SMALL LETTER YI
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x2116, # NUMERO SIGN
+ 0x00fd: 0x00a4, # CURRENCY SIGN
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\u0410' # 0x0080 -> CYRILLIC CAPITAL LETTER A
+ '\u0411' # 0x0081 -> CYRILLIC CAPITAL LETTER BE
+ '\u0412' # 0x0082 -> CYRILLIC CAPITAL LETTER VE
+ '\u0413' # 0x0083 -> CYRILLIC CAPITAL LETTER GHE
+ '\u0414' # 0x0084 -> CYRILLIC CAPITAL LETTER DE
+ '\u0415' # 0x0085 -> CYRILLIC CAPITAL LETTER IE
+ '\u0416' # 0x0086 -> CYRILLIC CAPITAL LETTER ZHE
+ '\u0417' # 0x0087 -> CYRILLIC CAPITAL LETTER ZE
+ '\u0418' # 0x0088 -> CYRILLIC CAPITAL LETTER I
+ '\u0419' # 0x0089 -> CYRILLIC CAPITAL LETTER SHORT I
+ '\u041a' # 0x008a -> CYRILLIC CAPITAL LETTER KA
+ '\u041b' # 0x008b -> CYRILLIC CAPITAL LETTER EL
+ '\u041c' # 0x008c -> CYRILLIC CAPITAL LETTER EM
+ '\u041d' # 0x008d -> CYRILLIC CAPITAL LETTER EN
+ '\u041e' # 0x008e -> CYRILLIC CAPITAL LETTER O
+ '\u041f' # 0x008f -> CYRILLIC CAPITAL LETTER PE
+ '\u0420' # 0x0090 -> CYRILLIC CAPITAL LETTER ER
+ '\u0421' # 0x0091 -> CYRILLIC CAPITAL LETTER ES
+ '\u0422' # 0x0092 -> CYRILLIC CAPITAL LETTER TE
+ '\u0423' # 0x0093 -> CYRILLIC CAPITAL LETTER U
+ '\u0424' # 0x0094 -> CYRILLIC CAPITAL LETTER EF
+ '\u0425' # 0x0095 -> CYRILLIC CAPITAL LETTER HA
+ '\u0426' # 0x0096 -> CYRILLIC CAPITAL LETTER TSE
+ '\u0427' # 0x0097 -> CYRILLIC CAPITAL LETTER CHE
+ '\u0428' # 0x0098 -> CYRILLIC CAPITAL LETTER SHA
+ '\u0429' # 0x0099 -> CYRILLIC CAPITAL LETTER SHCHA
+ '\u042a' # 0x009a -> CYRILLIC CAPITAL LETTER HARD SIGN
+ '\u042b' # 0x009b -> CYRILLIC CAPITAL LETTER YERU
+ '\u042c' # 0x009c -> CYRILLIC CAPITAL LETTER SOFT SIGN
+ '\u042d' # 0x009d -> CYRILLIC CAPITAL LETTER E
+ '\u042e' # 0x009e -> CYRILLIC CAPITAL LETTER YU
+ '\u042f' # 0x009f -> CYRILLIC CAPITAL LETTER YA
+ '\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A
+ '\u0431' # 0x00a1 -> CYRILLIC SMALL LETTER BE
+ '\u0432' # 0x00a2 -> CYRILLIC SMALL LETTER VE
+ '\u0433' # 0x00a3 -> CYRILLIC SMALL LETTER GHE
+ '\u0434' # 0x00a4 -> CYRILLIC SMALL LETTER DE
+ '\u0435' # 0x00a5 -> CYRILLIC SMALL LETTER IE
+ '\u0436' # 0x00a6 -> CYRILLIC SMALL LETTER ZHE
+ '\u0437' # 0x00a7 -> CYRILLIC SMALL LETTER ZE
+ '\u0438' # 0x00a8 -> CYRILLIC SMALL LETTER I
+ '\u0439' # 0x00a9 -> CYRILLIC SMALL LETTER SHORT I
+ '\u043a' # 0x00aa -> CYRILLIC SMALL LETTER KA
+ '\u043b' # 0x00ab -> CYRILLIC SMALL LETTER EL
+ '\u043c' # 0x00ac -> CYRILLIC SMALL LETTER EM
+ '\u043d' # 0x00ad -> CYRILLIC SMALL LETTER EN
+ '\u043e' # 0x00ae -> CYRILLIC SMALL LETTER O
+ '\u043f' # 0x00af -> CYRILLIC SMALL LETTER PE
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u0440' # 0x00e0 -> CYRILLIC SMALL LETTER ER
+ '\u0441' # 0x00e1 -> CYRILLIC SMALL LETTER ES
+ '\u0442' # 0x00e2 -> CYRILLIC SMALL LETTER TE
+ '\u0443' # 0x00e3 -> CYRILLIC SMALL LETTER U
+ '\u0444' # 0x00e4 -> CYRILLIC SMALL LETTER EF
+ '\u0445' # 0x00e5 -> CYRILLIC SMALL LETTER HA
+ '\u0446' # 0x00e6 -> CYRILLIC SMALL LETTER TSE
+ '\u0447' # 0x00e7 -> CYRILLIC SMALL LETTER CHE
+ '\u0448' # 0x00e8 -> CYRILLIC SMALL LETTER SHA
+ '\u0449' # 0x00e9 -> CYRILLIC SMALL LETTER SHCHA
+ '\u044a' # 0x00ea -> CYRILLIC SMALL LETTER HARD SIGN
+ '\u044b' # 0x00eb -> CYRILLIC SMALL LETTER YERU
+ '\u044c' # 0x00ec -> CYRILLIC SMALL LETTER SOFT SIGN
+ '\u044d' # 0x00ed -> CYRILLIC SMALL LETTER E
+ '\u044e' # 0x00ee -> CYRILLIC SMALL LETTER YU
+ '\u044f' # 0x00ef -> CYRILLIC SMALL LETTER YA
+ '\u0401' # 0x00f0 -> CYRILLIC CAPITAL LETTER IO
+ '\u0451' # 0x00f1 -> CYRILLIC SMALL LETTER IO
+ '\u0490' # 0x00f2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+ '\u0491' # 0x00f3 -> CYRILLIC SMALL LETTER GHE WITH UPTURN
+ '\u0404' # 0x00f4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ '\u0454' # 0x00f5 -> CYRILLIC SMALL LETTER UKRAINIAN IE
+ '\u0406' # 0x00f6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ '\u0456' # 0x00f7 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ '\u0407' # 0x00f8 -> CYRILLIC CAPITAL LETTER YI
+ '\u0457' # 0x00f9 -> CYRILLIC SMALL LETTER YI
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u2116' # 0x00fc -> NUMERO SIGN
+ '\xa4' # 0x00fd -> CURRENCY SIGN
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a4: 0x00fd, # CURRENCY SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x0401: 0x00f0, # CYRILLIC CAPITAL LETTER IO
+ 0x0404: 0x00f4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ 0x0406: 0x00f6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x0407: 0x00f8, # CYRILLIC CAPITAL LETTER YI
+ 0x0410: 0x0080, # CYRILLIC CAPITAL LETTER A
+ 0x0411: 0x0081, # CYRILLIC CAPITAL LETTER BE
+ 0x0412: 0x0082, # CYRILLIC CAPITAL LETTER VE
+ 0x0413: 0x0083, # CYRILLIC CAPITAL LETTER GHE
+ 0x0414: 0x0084, # CYRILLIC CAPITAL LETTER DE
+ 0x0415: 0x0085, # CYRILLIC CAPITAL LETTER IE
+ 0x0416: 0x0086, # CYRILLIC CAPITAL LETTER ZHE
+ 0x0417: 0x0087, # CYRILLIC CAPITAL LETTER ZE
+ 0x0418: 0x0088, # CYRILLIC CAPITAL LETTER I
+ 0x0419: 0x0089, # CYRILLIC CAPITAL LETTER SHORT I
+ 0x041a: 0x008a, # CYRILLIC CAPITAL LETTER KA
+ 0x041b: 0x008b, # CYRILLIC CAPITAL LETTER EL
+ 0x041c: 0x008c, # CYRILLIC CAPITAL LETTER EM
+ 0x041d: 0x008d, # CYRILLIC CAPITAL LETTER EN
+ 0x041e: 0x008e, # CYRILLIC CAPITAL LETTER O
+ 0x041f: 0x008f, # CYRILLIC CAPITAL LETTER PE
+ 0x0420: 0x0090, # CYRILLIC CAPITAL LETTER ER
+ 0x0421: 0x0091, # CYRILLIC CAPITAL LETTER ES
+ 0x0422: 0x0092, # CYRILLIC CAPITAL LETTER TE
+ 0x0423: 0x0093, # CYRILLIC CAPITAL LETTER U
+ 0x0424: 0x0094, # CYRILLIC CAPITAL LETTER EF
+ 0x0425: 0x0095, # CYRILLIC CAPITAL LETTER HA
+ 0x0426: 0x0096, # CYRILLIC CAPITAL LETTER TSE
+ 0x0427: 0x0097, # CYRILLIC CAPITAL LETTER CHE
+ 0x0428: 0x0098, # CYRILLIC CAPITAL LETTER SHA
+ 0x0429: 0x0099, # CYRILLIC CAPITAL LETTER SHCHA
+ 0x042a: 0x009a, # CYRILLIC CAPITAL LETTER HARD SIGN
+ 0x042b: 0x009b, # CYRILLIC CAPITAL LETTER YERU
+ 0x042c: 0x009c, # CYRILLIC CAPITAL LETTER SOFT SIGN
+ 0x042d: 0x009d, # CYRILLIC CAPITAL LETTER E
+ 0x042e: 0x009e, # CYRILLIC CAPITAL LETTER YU
+ 0x042f: 0x009f, # CYRILLIC CAPITAL LETTER YA
+ 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A
+ 0x0431: 0x00a1, # CYRILLIC SMALL LETTER BE
+ 0x0432: 0x00a2, # CYRILLIC SMALL LETTER VE
+ 0x0433: 0x00a3, # CYRILLIC SMALL LETTER GHE
+ 0x0434: 0x00a4, # CYRILLIC SMALL LETTER DE
+ 0x0435: 0x00a5, # CYRILLIC SMALL LETTER IE
+ 0x0436: 0x00a6, # CYRILLIC SMALL LETTER ZHE
+ 0x0437: 0x00a7, # CYRILLIC SMALL LETTER ZE
+ 0x0438: 0x00a8, # CYRILLIC SMALL LETTER I
+ 0x0439: 0x00a9, # CYRILLIC SMALL LETTER SHORT I
+ 0x043a: 0x00aa, # CYRILLIC SMALL LETTER KA
+ 0x043b: 0x00ab, # CYRILLIC SMALL LETTER EL
+ 0x043c: 0x00ac, # CYRILLIC SMALL LETTER EM
+ 0x043d: 0x00ad, # CYRILLIC SMALL LETTER EN
+ 0x043e: 0x00ae, # CYRILLIC SMALL LETTER O
+ 0x043f: 0x00af, # CYRILLIC SMALL LETTER PE
+ 0x0440: 0x00e0, # CYRILLIC SMALL LETTER ER
+ 0x0441: 0x00e1, # CYRILLIC SMALL LETTER ES
+ 0x0442: 0x00e2, # CYRILLIC SMALL LETTER TE
+ 0x0443: 0x00e3, # CYRILLIC SMALL LETTER U
+ 0x0444: 0x00e4, # CYRILLIC SMALL LETTER EF
+ 0x0445: 0x00e5, # CYRILLIC SMALL LETTER HA
+ 0x0446: 0x00e6, # CYRILLIC SMALL LETTER TSE
+ 0x0447: 0x00e7, # CYRILLIC SMALL LETTER CHE
+ 0x0448: 0x00e8, # CYRILLIC SMALL LETTER SHA
+ 0x0449: 0x00e9, # CYRILLIC SMALL LETTER SHCHA
+ 0x044a: 0x00ea, # CYRILLIC SMALL LETTER HARD SIGN
+ 0x044b: 0x00eb, # CYRILLIC SMALL LETTER YERU
+ 0x044c: 0x00ec, # CYRILLIC SMALL LETTER SOFT SIGN
+ 0x044d: 0x00ed, # CYRILLIC SMALL LETTER E
+ 0x044e: 0x00ee, # CYRILLIC SMALL LETTER YU
+ 0x044f: 0x00ef, # CYRILLIC SMALL LETTER YA
+ 0x0451: 0x00f1, # CYRILLIC SMALL LETTER IO
+ 0x0454: 0x00f5, # CYRILLIC SMALL LETTER UKRAINIAN IE
+ 0x0456: 0x00f7, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x0457: 0x00f9, # CYRILLIC SMALL LETTER YI
+ 0x0490: 0x00f2, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+ 0x0491: 0x00f3, # CYRILLIC SMALL LETTER GHE WITH UPTURN
+ 0x2116: 0x00fc, # NUMERO SIGN
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp1140.py b/Lib/encodings/cp1140.py
new file mode 100644
index 0000000..0a919d8
--- /dev/null
+++ b/Lib/encodings/cp1140.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1140',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x9c' # 0x04 -> CONTROL
+ '\t' # 0x05 -> HORIZONTAL TABULATION
+ '\x86' # 0x06 -> CONTROL
+ '\x7f' # 0x07 -> DELETE
+ '\x97' # 0x08 -> CONTROL
+ '\x8d' # 0x09 -> CONTROL
+ '\x8e' # 0x0A -> CONTROL
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x9d' # 0x14 -> CONTROL
+ '\x85' # 0x15 -> CONTROL
+ '\x08' # 0x16 -> BACKSPACE
+ '\x87' # 0x17 -> CONTROL
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x92' # 0x1A -> CONTROL
+ '\x8f' # 0x1B -> CONTROL
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ '\x80' # 0x20 -> CONTROL
+ '\x81' # 0x21 -> CONTROL
+ '\x82' # 0x22 -> CONTROL
+ '\x83' # 0x23 -> CONTROL
+ '\x84' # 0x24 -> CONTROL
+ '\n' # 0x25 -> LINE FEED
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK
+ '\x1b' # 0x27 -> ESCAPE
+ '\x88' # 0x28 -> CONTROL
+ '\x89' # 0x29 -> CONTROL
+ '\x8a' # 0x2A -> CONTROL
+ '\x8b' # 0x2B -> CONTROL
+ '\x8c' # 0x2C -> CONTROL
+ '\x05' # 0x2D -> ENQUIRY
+ '\x06' # 0x2E -> ACKNOWLEDGE
+ '\x07' # 0x2F -> BELL
+ '\x90' # 0x30 -> CONTROL
+ '\x91' # 0x31 -> CONTROL
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE
+ '\x93' # 0x33 -> CONTROL
+ '\x94' # 0x34 -> CONTROL
+ '\x95' # 0x35 -> CONTROL
+ '\x96' # 0x36 -> CONTROL
+ '\x04' # 0x37 -> END OF TRANSMISSION
+ '\x98' # 0x38 -> CONTROL
+ '\x99' # 0x39 -> CONTROL
+ '\x9a' # 0x3A -> CONTROL
+ '\x9b' # 0x3B -> CONTROL
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
+ '\x9e' # 0x3E -> CONTROL
+ '\x1a' # 0x3F -> SUBSTITUTE
+ ' ' # 0x40 -> SPACE
+ '\xa0' # 0x41 -> NO-BREAK SPACE
+ '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
+ '\xa2' # 0x4A -> CENT SIGN
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '|' # 0x4F -> VERTICAL LINE
+ '&' # 0x50 -> AMPERSAND
+ '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
+ '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
+ '!' # 0x5A -> EXCLAMATION MARK
+ '$' # 0x5B -> DOLLAR SIGN
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '\xac' # 0x5F -> NOT SIGN
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xa6' # 0x6A -> BROKEN BAR
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
+ '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '`' # 0x79 -> GRAVE ACCENT
+ ':' # 0x7A -> COLON
+ '#' # 0x7B -> NUMBER SIGN
+ '@' # 0x7C -> COMMERCIAL AT
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '"' # 0x7F -> QUOTATION MARK
+ '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
+ '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
+ '\xb1' # 0x8F -> PLUS-MINUS SIGN
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
+ '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
+ '\xb8' # 0x9D -> CEDILLA
+ '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
+ '\u20ac' # 0x9F -> EURO SIGN
+ '\xb5' # 0xA0 -> MICRO SIGN
+ '~' # 0xA1 -> TILDE
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
+ '\xbf' # 0xAB -> INVERTED QUESTION MARK
+ '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
+ '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
+ '\xae' # 0xAF -> REGISTERED SIGN
+ '^' # 0xB0 -> CIRCUMFLEX ACCENT
+ '\xa3' # 0xB1 -> POUND SIGN
+ '\xa5' # 0xB2 -> YEN SIGN
+ '\xb7' # 0xB3 -> MIDDLE DOT
+ '\xa9' # 0xB4 -> COPYRIGHT SIGN
+ '\xa7' # 0xB5 -> SECTION SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+ '[' # 0xBA -> LEFT SQUARE BRACKET
+ ']' # 0xBB -> RIGHT SQUARE BRACKET
+ '\xaf' # 0xBC -> MACRON
+ '\xa8' # 0xBD -> DIAERESIS
+ '\xb4' # 0xBE -> ACUTE ACCENT
+ '\xd7' # 0xBF -> MULTIPLICATION SIGN
+ '{' # 0xC0 -> LEFT CURLY BRACKET
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
+ '}' # 0xD0 -> RIGHT CURLY BRACKET
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb9' # 0xDA -> SUPERSCRIPT ONE
+ '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
+ '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\\' # 0xE0 -> REVERSE SOLIDUS
+ '\xf7' # 0xE1 -> DIVISION SIGN
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\x9f' # 0xFF -> CONTROL
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1250.py b/Lib/encodings/cp1250.py
new file mode 100644
index 0000000..c2c83aa
--- /dev/null
+++ b/Lib/encodings/cp1250.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1250',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\ufffe' # 0x83 -> UNDEFINED
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\ufffe' # 0x88 -> UNDEFINED
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE
+ '\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON
+ '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
+ '\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\ufffe' # 0x98 -> UNDEFINED
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE
+ '\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON
+ '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
+ '\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u02c7' # 0xA1 -> CARON
+ '\u02d8' # 0xA2 -> BREVE
+ '\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\u02db' # 0xB2 -> OGONEK
+ '\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK
+ '\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON
+ '\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT
+ '\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON
+ '\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE
+ '\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE
+ '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE
+ '\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE
+ '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
+ '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON
+ '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON
+ '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
+ '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
+ '\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON
+ '\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE
+ '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
+ '\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE
+ '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE
+ '\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE
+ '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON
+ '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON
+ '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
+ '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
+ '\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON
+ '\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE
+ '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
+ '\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
+ '\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA
+ '\u02d9' # 0xFF -> DOT ABOVE
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1251.py b/Lib/encodings/cp1251.py
new file mode 100644
index 0000000..22bc660
--- /dev/null
+++ b/Lib/encodings/cp1251.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1251',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE
+ '\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\u20ac' # 0x88 -> EURO SIGN
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE
+ '\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE
+ '\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE
+ '\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE
+ '\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\ufffe' # 0x98 -> UNDEFINED
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE
+ '\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE
+ '\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE
+ '\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U
+ '\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U
+ '\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ '\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ '\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO
+ '\u2116' # 0xB9 -> NUMERO SIGN
+ '\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE
+ '\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE
+ '\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE
+ '\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI
+ '\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A
+ '\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE
+ '\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE
+ '\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE
+ '\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE
+ '\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE
+ '\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE
+ '\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE
+ '\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I
+ '\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I
+ '\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA
+ '\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL
+ '\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM
+ '\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN
+ '\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O
+ '\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE
+ '\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER
+ '\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES
+ '\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE
+ '\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U
+ '\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF
+ '\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA
+ '\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE
+ '\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE
+ '\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA
+ '\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA
+ '\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN
+ '\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU
+ '\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN
+ '\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E
+ '\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU
+ '\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA
+ '\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A
+ '\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE
+ '\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE
+ '\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE
+ '\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE
+ '\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE
+ '\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE
+ '\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE
+ '\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I
+ '\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I
+ '\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA
+ '\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL
+ '\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM
+ '\u043d' # 0xED -> CYRILLIC SMALL LETTER EN
+ '\u043e' # 0xEE -> CYRILLIC SMALL LETTER O
+ '\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE
+ '\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER
+ '\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES
+ '\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE
+ '\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U
+ '\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF
+ '\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA
+ '\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE
+ '\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE
+ '\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA
+ '\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA
+ '\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN
+ '\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU
+ '\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN
+ '\u044d' # 0xFD -> CYRILLIC SMALL LETTER E
+ '\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU
+ '\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1252.py b/Lib/encodings/cp1252.py
new file mode 100644
index 0000000..c0e8088
--- /dev/null
+++ b/Lib/encodings/cp1252.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1252',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
+ '\ufffe' # 0x8F -> UNDEFINED
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\u02dc' # 0x98 -> SMALL TILDE
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
+ '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xaf' # 0xAF -> MACRON
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\xbf' # 0xBF -> INVERTED QUESTION MARK
+ '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
+ '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH
+ '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
+ '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe6' # 0xE6 -> LATIN SMALL LETTER AE
+ '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
+ '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH
+ '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
+ '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
+ '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
+ '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0xFE -> LATIN SMALL LETTER THORN
+ '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1253.py b/Lib/encodings/cp1253.py
new file mode 100644
index 0000000..ec9c097
--- /dev/null
+++ b/Lib/encodings/cp1253.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1253',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\ufffe' # 0x88 -> UNDEFINED
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\ufffe' # 0x8A -> UNDEFINED
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\ufffe' # 0x8C -> UNDEFINED
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\ufffe' # 0x8E -> UNDEFINED
+ '\ufffe' # 0x8F -> UNDEFINED
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\ufffe' # 0x98 -> UNDEFINED
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\ufffe' # 0x9A -> UNDEFINED
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\ufffe' # 0x9C -> UNDEFINED
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\ufffe' # 0x9E -> UNDEFINED
+ '\ufffe' # 0x9F -> UNDEFINED
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS
+ '\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\ufffe' # 0xAA -> UNDEFINED
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\u2015' # 0xAF -> HORIZONTAL BAR
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\u0384' # 0xB4 -> GREEK TONOS
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
+ '\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS
+ '\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS
+ '\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS
+ '\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ '\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA
+ '\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA
+ '\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA
+ '\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA
+ '\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON
+ '\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA
+ '\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA
+ '\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA
+ '\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA
+ '\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA
+ '\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA
+ '\u039c' # 0xCC -> GREEK CAPITAL LETTER MU
+ '\u039d' # 0xCD -> GREEK CAPITAL LETTER NU
+ '\u039e' # 0xCE -> GREEK CAPITAL LETTER XI
+ '\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON
+ '\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI
+ '\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO
+ '\ufffe' # 0xD2 -> UNDEFINED
+ '\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA
+ '\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU
+ '\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON
+ '\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI
+ '\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI
+ '\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI
+ '\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA
+ '\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ '\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ '\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS
+ '\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS
+ '\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS
+ '\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS
+ '\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ '\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA
+ '\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA
+ '\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA
+ '\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA
+ '\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON
+ '\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA
+ '\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA
+ '\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA
+ '\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA
+ '\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA
+ '\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA
+ '\u03bc' # 0xEC -> GREEK SMALL LETTER MU
+ '\u03bd' # 0xED -> GREEK SMALL LETTER NU
+ '\u03be' # 0xEE -> GREEK SMALL LETTER XI
+ '\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON
+ '\u03c0' # 0xF0 -> GREEK SMALL LETTER PI
+ '\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO
+ '\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA
+ '\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA
+ '\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU
+ '\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON
+ '\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI
+ '\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI
+ '\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI
+ '\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA
+ '\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ '\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ '\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS
+ '\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS
+ '\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS
+ '\ufffe' # 0xFF -> UNDEFINED
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1254.py b/Lib/encodings/cp1254.py
new file mode 100644
index 0000000..4912327
--- /dev/null
+++ b/Lib/encodings/cp1254.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1254 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1254',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\ufffe' # 0x8E -> UNDEFINED
+ '\ufffe' # 0x8F -> UNDEFINED
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\u02dc' # 0x98 -> SMALL TILDE
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\ufffe' # 0x9E -> UNDEFINED
+ '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xaf' # 0xAF -> MACRON
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\xbf' # 0xBF -> INVERTED QUESTION MARK
+ '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
+ '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE
+ '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE
+ '\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
+ '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe6' # 0xE6 -> LATIN SMALL LETTER AE
+ '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
+ '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE
+ '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
+ '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
+ '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
+ '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I
+ '\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA
+ '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1255.py b/Lib/encodings/cp1255.py
new file mode 100644
index 0000000..91ce26b
--- /dev/null
+++ b/Lib/encodings/cp1255.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1255 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1255',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\ufffe' # 0x8A -> UNDEFINED
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\ufffe' # 0x8C -> UNDEFINED
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\ufffe' # 0x8E -> UNDEFINED
+ '\ufffe' # 0x8F -> UNDEFINED
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\u02dc' # 0x98 -> SMALL TILDE
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\ufffe' # 0x9A -> UNDEFINED
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\ufffe' # 0x9C -> UNDEFINED
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\ufffe' # 0x9E -> UNDEFINED
+ '\ufffe' # 0x9F -> UNDEFINED
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\u20aa' # 0xA4 -> NEW SHEQEL SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\xd7' # 0xAA -> MULTIPLICATION SIGN
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xaf' # 0xAF -> MACRON
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\xf7' # 0xBA -> DIVISION SIGN
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\xbf' # 0xBF -> INVERTED QUESTION MARK
+ '\u05b0' # 0xC0 -> HEBREW POINT SHEVA
+ '\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL
+ '\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH
+ '\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS
+ '\u05b4' # 0xC4 -> HEBREW POINT HIRIQ
+ '\u05b5' # 0xC5 -> HEBREW POINT TSERE
+ '\u05b6' # 0xC6 -> HEBREW POINT SEGOL
+ '\u05b7' # 0xC7 -> HEBREW POINT PATAH
+ '\u05b8' # 0xC8 -> HEBREW POINT QAMATS
+ '\u05b9' # 0xC9 -> HEBREW POINT HOLAM
+ '\ufffe' # 0xCA -> UNDEFINED
+ '\u05bb' # 0xCB -> HEBREW POINT QUBUTS
+ '\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ
+ '\u05bd' # 0xCD -> HEBREW POINT METEG
+ '\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF
+ '\u05bf' # 0xCF -> HEBREW POINT RAFE
+ '\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ
+ '\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT
+ '\u05c2' # 0xD2 -> HEBREW POINT SIN DOT
+ '\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ
+ '\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV
+ '\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD
+ '\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD
+ '\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH
+ '\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM
+ '\ufffe' # 0xD9 -> UNDEFINED
+ '\ufffe' # 0xDA -> UNDEFINED
+ '\ufffe' # 0xDB -> UNDEFINED
+ '\ufffe' # 0xDC -> UNDEFINED
+ '\ufffe' # 0xDD -> UNDEFINED
+ '\ufffe' # 0xDE -> UNDEFINED
+ '\ufffe' # 0xDF -> UNDEFINED
+ '\u05d0' # 0xE0 -> HEBREW LETTER ALEF
+ '\u05d1' # 0xE1 -> HEBREW LETTER BET
+ '\u05d2' # 0xE2 -> HEBREW LETTER GIMEL
+ '\u05d3' # 0xE3 -> HEBREW LETTER DALET
+ '\u05d4' # 0xE4 -> HEBREW LETTER HE
+ '\u05d5' # 0xE5 -> HEBREW LETTER VAV
+ '\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN
+ '\u05d7' # 0xE7 -> HEBREW LETTER HET
+ '\u05d8' # 0xE8 -> HEBREW LETTER TET
+ '\u05d9' # 0xE9 -> HEBREW LETTER YOD
+ '\u05da' # 0xEA -> HEBREW LETTER FINAL KAF
+ '\u05db' # 0xEB -> HEBREW LETTER KAF
+ '\u05dc' # 0xEC -> HEBREW LETTER LAMED
+ '\u05dd' # 0xED -> HEBREW LETTER FINAL MEM
+ '\u05de' # 0xEE -> HEBREW LETTER MEM
+ '\u05df' # 0xEF -> HEBREW LETTER FINAL NUN
+ '\u05e0' # 0xF0 -> HEBREW LETTER NUN
+ '\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH
+ '\u05e2' # 0xF2 -> HEBREW LETTER AYIN
+ '\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE
+ '\u05e4' # 0xF4 -> HEBREW LETTER PE
+ '\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI
+ '\u05e6' # 0xF6 -> HEBREW LETTER TSADI
+ '\u05e7' # 0xF7 -> HEBREW LETTER QOF
+ '\u05e8' # 0xF8 -> HEBREW LETTER RESH
+ '\u05e9' # 0xF9 -> HEBREW LETTER SHIN
+ '\u05ea' # 0xFA -> HEBREW LETTER TAV
+ '\ufffe' # 0xFB -> UNDEFINED
+ '\ufffe' # 0xFC -> UNDEFINED
+ '\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
+ '\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
+ '\ufffe' # 0xFF -> UNDEFINED
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1256.py b/Lib/encodings/cp1256.py
new file mode 100644
index 0000000..fd6afab
--- /dev/null
+++ b/Lib/encodings/cp1256.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1256 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1256',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\u067e' # 0x81 -> ARABIC LETTER PEH
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\u0679' # 0x8A -> ARABIC LETTER TTEH
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
+ '\u0686' # 0x8D -> ARABIC LETTER TCHEH
+ '\u0698' # 0x8E -> ARABIC LETTER JEH
+ '\u0688' # 0x8F -> ARABIC LETTER DDAL
+ '\u06af' # 0x90 -> ARABIC LETTER GAF
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\u06a9' # 0x98 -> ARABIC LETTER KEHEH
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\u0691' # 0x9A -> ARABIC LETTER RREH
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
+ '\u200c' # 0x9D -> ZERO WIDTH NON-JOINER
+ '\u200d' # 0x9E -> ZERO WIDTH JOINER
+ '\u06ba' # 0x9F -> ARABIC LETTER NOON GHUNNA
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u060c' # 0xA1 -> ARABIC COMMA
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\u06be' # 0xAA -> ARABIC LETTER HEH DOACHASHMEE
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xaf' # 0xAF -> MACRON
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\u061b' # 0xBA -> ARABIC SEMICOLON
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\u061f' # 0xBF -> ARABIC QUESTION MARK
+ '\u06c1' # 0xC0 -> ARABIC LETTER HEH GOAL
+ '\u0621' # 0xC1 -> ARABIC LETTER HAMZA
+ '\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE
+ '\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE
+ '\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE
+ '\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW
+ '\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE
+ '\u0627' # 0xC7 -> ARABIC LETTER ALEF
+ '\u0628' # 0xC8 -> ARABIC LETTER BEH
+ '\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA
+ '\u062a' # 0xCA -> ARABIC LETTER TEH
+ '\u062b' # 0xCB -> ARABIC LETTER THEH
+ '\u062c' # 0xCC -> ARABIC LETTER JEEM
+ '\u062d' # 0xCD -> ARABIC LETTER HAH
+ '\u062e' # 0xCE -> ARABIC LETTER KHAH
+ '\u062f' # 0xCF -> ARABIC LETTER DAL
+ '\u0630' # 0xD0 -> ARABIC LETTER THAL
+ '\u0631' # 0xD1 -> ARABIC LETTER REH
+ '\u0632' # 0xD2 -> ARABIC LETTER ZAIN
+ '\u0633' # 0xD3 -> ARABIC LETTER SEEN
+ '\u0634' # 0xD4 -> ARABIC LETTER SHEEN
+ '\u0635' # 0xD5 -> ARABIC LETTER SAD
+ '\u0636' # 0xD6 -> ARABIC LETTER DAD
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\u0637' # 0xD8 -> ARABIC LETTER TAH
+ '\u0638' # 0xD9 -> ARABIC LETTER ZAH
+ '\u0639' # 0xDA -> ARABIC LETTER AIN
+ '\u063a' # 0xDB -> ARABIC LETTER GHAIN
+ '\u0640' # 0xDC -> ARABIC TATWEEL
+ '\u0641' # 0xDD -> ARABIC LETTER FEH
+ '\u0642' # 0xDE -> ARABIC LETTER QAF
+ '\u0643' # 0xDF -> ARABIC LETTER KAF
+ '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
+ '\u0644' # 0xE1 -> ARABIC LETTER LAM
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\u0645' # 0xE3 -> ARABIC LETTER MEEM
+ '\u0646' # 0xE4 -> ARABIC LETTER NOON
+ '\u0647' # 0xE5 -> ARABIC LETTER HEH
+ '\u0648' # 0xE6 -> ARABIC LETTER WAW
+ '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\u0649' # 0xEC -> ARABIC LETTER ALEF MAKSURA
+ '\u064a' # 0xED -> ARABIC LETTER YEH
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\u064b' # 0xF0 -> ARABIC FATHATAN
+ '\u064c' # 0xF1 -> ARABIC DAMMATAN
+ '\u064d' # 0xF2 -> ARABIC KASRATAN
+ '\u064e' # 0xF3 -> ARABIC FATHA
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\u064f' # 0xF5 -> ARABIC DAMMA
+ '\u0650' # 0xF6 -> ARABIC KASRA
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\u0651' # 0xF8 -> ARABIC SHADDA
+ '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
+ '\u0652' # 0xFA -> ARABIC SUKUN
+ '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
+ '\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
+ '\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1257.py b/Lib/encodings/cp1257.py
new file mode 100644
index 0000000..9ebc90d
--- /dev/null
+++ b/Lib/encodings/cp1257.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1257 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1257',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\ufffe' # 0x83 -> UNDEFINED
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\ufffe' # 0x88 -> UNDEFINED
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\ufffe' # 0x8A -> UNDEFINED
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\ufffe' # 0x8C -> UNDEFINED
+ '\xa8' # 0x8D -> DIAERESIS
+ '\u02c7' # 0x8E -> CARON
+ '\xb8' # 0x8F -> CEDILLA
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\ufffe' # 0x98 -> UNDEFINED
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\ufffe' # 0x9A -> UNDEFINED
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\ufffe' # 0x9C -> UNDEFINED
+ '\xaf' # 0x9D -> MACRON
+ '\u02db' # 0x9E -> OGONEK
+ '\ufffe' # 0x9F -> UNDEFINED
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\ufffe' # 0xA1 -> UNDEFINED
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\ufffe' # 0xA5 -> UNDEFINED
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xc6' # 0xAF -> LATIN CAPITAL LETTER AE
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\xe6' # 0xBF -> LATIN SMALL LETTER AE
+ '\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK
+ '\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK
+ '\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON
+ '\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK
+ '\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON
+ '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE
+ '\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE
+ '\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA
+ '\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA
+ '\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON
+ '\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA
+ '\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON
+ '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
+ '\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON
+ '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK
+ '\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE
+ '\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE
+ '\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ '\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
+ '\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK
+ '\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK
+ '\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON
+ '\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK
+ '\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON
+ '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE
+ '\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE
+ '\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA
+ '\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA
+ '\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON
+ '\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA
+ '\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON
+ '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
+ '\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON
+ '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK
+ '\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE
+ '\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE
+ '\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE
+ '\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON
+ '\u02d9' # 0xFF -> DOT ABOVE
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp1258.py b/Lib/encodings/cp1258.py
new file mode 100644
index 0000000..784378a
--- /dev/null
+++ b/Lib/encodings/cp1258.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp1258',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
+ '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
+ '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\u2020' # 0x86 -> DAGGER
+ '\u2021' # 0x87 -> DOUBLE DAGGER
+ '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
+ '\u2030' # 0x89 -> PER MILLE SIGN
+ '\ufffe' # 0x8A -> UNDEFINED
+ '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\ufffe' # 0x8E -> UNDEFINED
+ '\ufffe' # 0x8F -> UNDEFINED
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\u02dc' # 0x98 -> SMALL TILDE
+ '\u2122' # 0x99 -> TRADE MARK SIGN
+ '\ufffe' # 0x9A -> UNDEFINED
+ '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\ufffe' # 0x9E -> UNDEFINED
+ '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xaf' # 0xAF -> MACRON
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\xbf' # 0xBF -> INVERTED QUESTION MARK
+ '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
+ '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\u0300' # 0xCC -> COMBINING GRAVE ACCENT
+ '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
+ '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\u0309' # 0xD2 -> COMBINING HOOK ABOVE
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN
+ '\u0303' # 0xDE -> COMBINING TILDE
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
+ '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe6' # 0xE6 -> LATIN SMALL LETTER AE
+ '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\u0301' # 0xEC -> COMBINING ACUTE ACCENT
+ '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
+ '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
+ '\u0323' # 0xF2 -> COMBINING DOT BELOW
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
+ '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
+ '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN
+ '\u20ab' # 0xFE -> DONG SIGN
+ '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp273.py b/Lib/encodings/cp273.py
new file mode 100644
index 0000000..69c6d77
--- /dev/null
+++ b/Lib/encodings/cp273.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp273 generated from 'python-mappings/CP273.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp273',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL (NUL)
+ '\x01' # 0x01 -> START OF HEADING (SOH)
+ '\x02' # 0x02 -> START OF TEXT (STX)
+ '\x03' # 0x03 -> END OF TEXT (ETX)
+ '\x9c' # 0x04 -> STRING TERMINATOR (ST)
+ '\t' # 0x05 -> CHARACTER TABULATION (HT)
+ '\x86' # 0x06 -> START OF SELECTED AREA (SSA)
+ '\x7f' # 0x07 -> DELETE (DEL)
+ '\x97' # 0x08 -> END OF GUARDED AREA (EPA)
+ '\x8d' # 0x09 -> REVERSE LINE FEED (RI)
+ '\x8e' # 0x0A -> SINGLE-SHIFT TWO (SS2)
+ '\x0b' # 0x0B -> LINE TABULATION (VT)
+ '\x0c' # 0x0C -> FORM FEED (FF)
+ '\r' # 0x0D -> CARRIAGE RETURN (CR)
+ '\x0e' # 0x0E -> SHIFT OUT (SO)
+ '\x0f' # 0x0F -> SHIFT IN (SI)
+ '\x10' # 0x10 -> DATALINK ESCAPE (DLE)
+ '\x11' # 0x11 -> DEVICE CONTROL ONE (DC1)
+ '\x12' # 0x12 -> DEVICE CONTROL TWO (DC2)
+ '\x13' # 0x13 -> DEVICE CONTROL THREE (DC3)
+ '\x9d' # 0x14 -> OPERATING SYSTEM COMMAND (OSC)
+ '\x85' # 0x15 -> NEXT LINE (NEL)
+ '\x08' # 0x16 -> BACKSPACE (BS)
+ '\x87' # 0x17 -> END OF SELECTED AREA (ESA)
+ '\x18' # 0x18 -> CANCEL (CAN)
+ '\x19' # 0x19 -> END OF MEDIUM (EM)
+ '\x92' # 0x1A -> PRIVATE USE TWO (PU2)
+ '\x8f' # 0x1B -> SINGLE-SHIFT THREE (SS3)
+ '\x1c' # 0x1C -> FILE SEPARATOR (IS4)
+ '\x1d' # 0x1D -> GROUP SEPARATOR (IS3)
+ '\x1e' # 0x1E -> RECORD SEPARATOR (IS2)
+ '\x1f' # 0x1F -> UNIT SEPARATOR (IS1)
+ '\x80' # 0x20 -> PADDING CHARACTER (PAD)
+ '\x81' # 0x21 -> HIGH OCTET PRESET (HOP)
+ '\x82' # 0x22 -> BREAK PERMITTED HERE (BPH)
+ '\x83' # 0x23 -> NO BREAK HERE (NBH)
+ '\x84' # 0x24 -> INDEX (IND)
+ '\n' # 0x25 -> LINE FEED (LF)
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK (ETB)
+ '\x1b' # 0x27 -> ESCAPE (ESC)
+ '\x88' # 0x28 -> CHARACTER TABULATION SET (HTS)
+ '\x89' # 0x29 -> CHARACTER TABULATION WITH JUSTIFICATION (HTJ)
+ '\x8a' # 0x2A -> LINE TABULATION SET (VTS)
+ '\x8b' # 0x2B -> PARTIAL LINE FORWARD (PLD)
+ '\x8c' # 0x2C -> PARTIAL LINE BACKWARD (PLU)
+ '\x05' # 0x2D -> ENQUIRY (ENQ)
+ '\x06' # 0x2E -> ACKNOWLEDGE (ACK)
+ '\x07' # 0x2F -> BELL (BEL)
+ '\x90' # 0x30 -> DEVICE CONTROL STRING (DCS)
+ '\x91' # 0x31 -> PRIVATE USE ONE (PU1)
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE (SYN)
+ '\x93' # 0x33 -> SET TRANSMIT STATE (STS)
+ '\x94' # 0x34 -> CANCEL CHARACTER (CCH)
+ '\x95' # 0x35 -> MESSAGE WAITING (MW)
+ '\x96' # 0x36 -> START OF GUARDED AREA (SPA)
+ '\x04' # 0x37 -> END OF TRANSMISSION (EOT)
+ '\x98' # 0x38 -> START OF STRING (SOS)
+ '\x99' # 0x39 -> SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI)
+ '\x9a' # 0x3A -> SINGLE CHARACTER INTRODUCER (SCI)
+ '\x9b' # 0x3B -> CONTROL SEQUENCE INTRODUCER (CSI)
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR (DC4)
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE (NAK)
+ '\x9e' # 0x3E -> PRIVACY MESSAGE (PM)
+ '\x1a' # 0x3F -> SUBSTITUTE (SUB)
+ ' ' # 0x40 -> SPACE
+ '\xa0' # 0x41 -> NO-BREAK SPACE
+ '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '{' # 0x43 -> LEFT CURLY BRACKET
+ '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
+ '\xc4' # 0x4A -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '!' # 0x4F -> EXCLAMATION MARK
+ '&' # 0x50 -> AMPERSAND
+ '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
+ '~' # 0x59 -> TILDE
+ '\xdc' # 0x5A -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '$' # 0x5B -> DOLLAR SIGN
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '^' # 0x5F -> CIRCUMFLEX ACCENT
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '[' # 0x63 -> LEFT SQUARE BRACKET
+ '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xf6' # 0x6A -> LATIN SMALL LETTER O WITH DIAERESIS
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
+ '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '`' # 0x79 -> GRAVE ACCENT
+ ':' # 0x7A -> COLON
+ '#' # 0x7B -> NUMBER SIGN
+ '\xa7' # 0x7C -> SECTION SIGN
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '"' # 0x7F -> QUOTATION MARK
+ '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (Icelandic)
+ '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (Icelandic)
+ '\xb1' # 0x8F -> PLUS-MINUS SIGN
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
+ '\xe6' # 0x9C -> LATIN SMALL LETTER AE
+ '\xb8' # 0x9D -> CEDILLA
+ '\xc6' # 0x9E -> LATIN CAPITAL LETTER AE
+ '\xa4' # 0x9F -> CURRENCY SIGN
+ '\xb5' # 0xA0 -> MICRO SIGN
+ '\xdf' # 0xA1 -> LATIN SMALL LETTER SHARP S (German)
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
+ '\xbf' # 0xAB -> INVERTED QUESTION MARK
+ '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (Icelandic)
+ '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (Icelandic)
+ '\xae' # 0xAF -> REGISTERED SIGN
+ '\xa2' # 0xB0 -> CENT SIGN
+ '\xa3' # 0xB1 -> POUND SIGN
+ '\xa5' # 0xB2 -> YEN SIGN
+ '\xb7' # 0xB3 -> MIDDLE DOT
+ '\xa9' # 0xB4 -> COPYRIGHT SIGN
+ '@' # 0xB5 -> COMMERCIAL AT
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+ '\xac' # 0xBA -> NOT SIGN
+ '|' # 0xBB -> VERTICAL LINE
+ '\u203e' # 0xBC -> OVERLINE
+ '\xa8' # 0xBD -> DIAERESIS
+ '\xb4' # 0xBE -> ACUTE ACCENT
+ '\xd7' # 0xBF -> MULTIPLICATION SIGN
+ '\xe4' # 0xC0 -> LATIN SMALL LETTER A WITH DIAERESIS
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xa6' # 0xCC -> BROKEN BAR
+ '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
+ '\xfc' # 0xD0 -> LATIN SMALL LETTER U WITH DIAERESIS
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb9' # 0xDA -> SUPERSCRIPT ONE
+ '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '}' # 0xDC -> RIGHT CURLY BRACKET
+ '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
+ '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xd6' # 0xE0 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xf7' # 0xE1 -> DIVISION SIGN
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\\' # 0xEC -> REVERSE SOLIDUS
+ '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ ']' # 0xFC -> RIGHT SQUARE BRACKET
+ '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\x9f' # 0xFF -> APPLICATION PROGRAM COMMAND (APC)
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp424.py b/Lib/encodings/cp424.py
new file mode 100644
index 0000000..6753daf
--- /dev/null
+++ b/Lib/encodings/cp424.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp424',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x9c' # 0x04 -> SELECT
+ '\t' # 0x05 -> HORIZONTAL TABULATION
+ '\x86' # 0x06 -> REQUIRED NEW LINE
+ '\x7f' # 0x07 -> DELETE
+ '\x97' # 0x08 -> GRAPHIC ESCAPE
+ '\x8d' # 0x09 -> SUPERSCRIPT
+ '\x8e' # 0x0A -> REPEAT
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION
+ '\x85' # 0x15 -> NEW LINE
+ '\x08' # 0x16 -> BACKSPACE
+ '\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x92' # 0x1A -> UNIT BACK SPACE
+ '\x8f' # 0x1B -> CUSTOMER USE ONE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ '\x80' # 0x20 -> DIGIT SELECT
+ '\x81' # 0x21 -> START OF SIGNIFICANCE
+ '\x82' # 0x22 -> FIELD SEPARATOR
+ '\x83' # 0x23 -> WORD UNDERSCORE
+ '\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION
+ '\n' # 0x25 -> LINE FEED
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK
+ '\x1b' # 0x27 -> ESCAPE
+ '\x88' # 0x28 -> SET ATTRIBUTE
+ '\x89' # 0x29 -> START FIELD EXTENDED
+ '\x8a' # 0x2A -> SET MODE OR SWITCH
+ '\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX
+ '\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE
+ '\x05' # 0x2D -> ENQUIRY
+ '\x06' # 0x2E -> ACKNOWLEDGE
+ '\x07' # 0x2F -> BELL
+ '\x90' # 0x30 ->
+ '\x91' # 0x31 ->
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE
+ '\x93' # 0x33 -> INDEX RETURN
+ '\x94' # 0x34 -> PRESENTATION POSITION
+ '\x95' # 0x35 -> TRANSPARENT
+ '\x96' # 0x36 -> NUMERIC BACKSPACE
+ '\x04' # 0x37 -> END OF TRANSMISSION
+ '\x98' # 0x38 -> SUBSCRIPT
+ '\x99' # 0x39 -> INDENT TABULATION
+ '\x9a' # 0x3A -> REVERSE FORM FEED
+ '\x9b' # 0x3B -> CUSTOMER USE THREE
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
+ '\x9e' # 0x3E ->
+ '\x1a' # 0x3F -> SUBSTITUTE
+ ' ' # 0x40 -> SPACE
+ '\u05d0' # 0x41 -> HEBREW LETTER ALEF
+ '\u05d1' # 0x42 -> HEBREW LETTER BET
+ '\u05d2' # 0x43 -> HEBREW LETTER GIMEL
+ '\u05d3' # 0x44 -> HEBREW LETTER DALET
+ '\u05d4' # 0x45 -> HEBREW LETTER HE
+ '\u05d5' # 0x46 -> HEBREW LETTER VAV
+ '\u05d6' # 0x47 -> HEBREW LETTER ZAYIN
+ '\u05d7' # 0x48 -> HEBREW LETTER HET
+ '\u05d8' # 0x49 -> HEBREW LETTER TET
+ '\xa2' # 0x4A -> CENT SIGN
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '|' # 0x4F -> VERTICAL LINE
+ '&' # 0x50 -> AMPERSAND
+ '\u05d9' # 0x51 -> HEBREW LETTER YOD
+ '\u05da' # 0x52 -> HEBREW LETTER FINAL KAF
+ '\u05db' # 0x53 -> HEBREW LETTER KAF
+ '\u05dc' # 0x54 -> HEBREW LETTER LAMED
+ '\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM
+ '\u05de' # 0x56 -> HEBREW LETTER MEM
+ '\u05df' # 0x57 -> HEBREW LETTER FINAL NUN
+ '\u05e0' # 0x58 -> HEBREW LETTER NUN
+ '\u05e1' # 0x59 -> HEBREW LETTER SAMEKH
+ '!' # 0x5A -> EXCLAMATION MARK
+ '$' # 0x5B -> DOLLAR SIGN
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '\xac' # 0x5F -> NOT SIGN
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\u05e2' # 0x62 -> HEBREW LETTER AYIN
+ '\u05e3' # 0x63 -> HEBREW LETTER FINAL PE
+ '\u05e4' # 0x64 -> HEBREW LETTER PE
+ '\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI
+ '\u05e6' # 0x66 -> HEBREW LETTER TSADI
+ '\u05e7' # 0x67 -> HEBREW LETTER QOF
+ '\u05e8' # 0x68 -> HEBREW LETTER RESH
+ '\u05e9' # 0x69 -> HEBREW LETTER SHIN
+ '\xa6' # 0x6A -> BROKEN BAR
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\ufffe' # 0x70 -> UNDEFINED
+ '\u05ea' # 0x71 -> HEBREW LETTER TAV
+ '\ufffe' # 0x72 -> UNDEFINED
+ '\ufffe' # 0x73 -> UNDEFINED
+ '\xa0' # 0x74 -> NO-BREAK SPACE
+ '\ufffe' # 0x75 -> UNDEFINED
+ '\ufffe' # 0x76 -> UNDEFINED
+ '\ufffe' # 0x77 -> UNDEFINED
+ '\u2017' # 0x78 -> DOUBLE LOW LINE
+ '`' # 0x79 -> GRAVE ACCENT
+ ':' # 0x7A -> COLON
+ '#' # 0x7B -> NUMBER SIGN
+ '@' # 0x7C -> COMMERCIAL AT
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '"' # 0x7F -> QUOTATION MARK
+ '\ufffe' # 0x80 -> UNDEFINED
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\ufffe' # 0x8C -> UNDEFINED
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\ufffe' # 0x8E -> UNDEFINED
+ '\xb1' # 0x8F -> PLUS-MINUS SIGN
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\ufffe' # 0x9A -> UNDEFINED
+ '\ufffe' # 0x9B -> UNDEFINED
+ '\ufffe' # 0x9C -> UNDEFINED
+ '\xb8' # 0x9D -> CEDILLA
+ '\ufffe' # 0x9E -> UNDEFINED
+ '\xa4' # 0x9F -> CURRENCY SIGN
+ '\xb5' # 0xA0 -> MICRO SIGN
+ '~' # 0xA1 -> TILDE
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\ufffe' # 0xAA -> UNDEFINED
+ '\ufffe' # 0xAB -> UNDEFINED
+ '\ufffe' # 0xAC -> UNDEFINED
+ '\ufffe' # 0xAD -> UNDEFINED
+ '\ufffe' # 0xAE -> UNDEFINED
+ '\xae' # 0xAF -> REGISTERED SIGN
+ '^' # 0xB0 -> CIRCUMFLEX ACCENT
+ '\xa3' # 0xB1 -> POUND SIGN
+ '\xa5' # 0xB2 -> YEN SIGN
+ '\xb7' # 0xB3 -> MIDDLE DOT
+ '\xa9' # 0xB4 -> COPYRIGHT SIGN
+ '\xa7' # 0xB5 -> SECTION SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+ '[' # 0xBA -> LEFT SQUARE BRACKET
+ ']' # 0xBB -> RIGHT SQUARE BRACKET
+ '\xaf' # 0xBC -> MACRON
+ '\xa8' # 0xBD -> DIAERESIS
+ '\xb4' # 0xBE -> ACUTE ACCENT
+ '\xd7' # 0xBF -> MULTIPLICATION SIGN
+ '{' # 0xC0 -> LEFT CURLY BRACKET
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\ufffe' # 0xCB -> UNDEFINED
+ '\ufffe' # 0xCC -> UNDEFINED
+ '\ufffe' # 0xCD -> UNDEFINED
+ '\ufffe' # 0xCE -> UNDEFINED
+ '\ufffe' # 0xCF -> UNDEFINED
+ '}' # 0xD0 -> RIGHT CURLY BRACKET
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb9' # 0xDA -> SUPERSCRIPT ONE
+ '\ufffe' # 0xDB -> UNDEFINED
+ '\ufffe' # 0xDC -> UNDEFINED
+ '\ufffe' # 0xDD -> UNDEFINED
+ '\ufffe' # 0xDE -> UNDEFINED
+ '\ufffe' # 0xDF -> UNDEFINED
+ '\\' # 0xE0 -> REVERSE SOLIDUS
+ '\xf7' # 0xE1 -> DIVISION SIGN
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\ufffe' # 0xEB -> UNDEFINED
+ '\ufffe' # 0xEC -> UNDEFINED
+ '\ufffe' # 0xED -> UNDEFINED
+ '\ufffe' # 0xEE -> UNDEFINED
+ '\ufffe' # 0xEF -> UNDEFINED
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\ufffe' # 0xFB -> UNDEFINED
+ '\ufffe' # 0xFC -> UNDEFINED
+ '\ufffe' # 0xFD -> UNDEFINED
+ '\ufffe' # 0xFE -> UNDEFINED
+ '\x9f' # 0xFF -> EIGHT ONES
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp437.py b/Lib/encodings/cp437.py
new file mode 100644
index 0000000..b6c75e2
--- /dev/null
+++ b/Lib/encodings/cp437.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec cp437 generated from 'VENDORS/MICSFT/PC/CP437.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp437',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00a2, # CENT SIGN
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00a5, # YEN SIGN
+ 0x009e: 0x20a7, # PESETA SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x2310, # REVERSED NOT SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00e3: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00ec: 0x221e, # INFINITY
+ 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00ef: 0x2229, # INTERSECTION
+ 0x00f0: 0x2261, # IDENTICAL TO
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x2320, # TOP HALF INTEGRAL
+ 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xa2' # 0x009b -> CENT SIGN
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xa5' # 0x009d -> YEN SIGN
+ '\u20a7' # 0x009e -> PESETA SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\u2310' # 0x00a9 -> REVERSED NOT SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
+ '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
+ '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
+ '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
+ '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
+ '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
+ '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
+ '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
+ '\u221e' # 0x00ec -> INFINITY
+ '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
+ '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
+ '\u2229' # 0x00ef -> INTERSECTION
+ '\u2261' # 0x00f0 -> IDENTICAL TO
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u2320' # 0x00f4 -> TOP HALF INTEGRAL
+ '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x009b, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a5: 0x009d, # YEN SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
+ 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
+ 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
+ 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
+ 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
+ 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
+ 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
+ 0x03c0: 0x00e3, # GREEK SMALL LETTER PI
+ 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
+ 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x20a7: 0x009e, # PESETA SIGN
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x221e: 0x00ec, # INFINITY
+ 0x2229: 0x00ef, # INTERSECTION
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2261: 0x00f0, # IDENTICAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2310: 0x00a9, # REVERSED NOT SIGN
+ 0x2320: 0x00f4, # TOP HALF INTEGRAL
+ 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp500.py b/Lib/encodings/cp500.py
new file mode 100644
index 0000000..5f61535
--- /dev/null
+++ b/Lib/encodings/cp500.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp500 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp500',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x9c' # 0x04 -> CONTROL
+ '\t' # 0x05 -> HORIZONTAL TABULATION
+ '\x86' # 0x06 -> CONTROL
+ '\x7f' # 0x07 -> DELETE
+ '\x97' # 0x08 -> CONTROL
+ '\x8d' # 0x09 -> CONTROL
+ '\x8e' # 0x0A -> CONTROL
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x9d' # 0x14 -> CONTROL
+ '\x85' # 0x15 -> CONTROL
+ '\x08' # 0x16 -> BACKSPACE
+ '\x87' # 0x17 -> CONTROL
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x92' # 0x1A -> CONTROL
+ '\x8f' # 0x1B -> CONTROL
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ '\x80' # 0x20 -> CONTROL
+ '\x81' # 0x21 -> CONTROL
+ '\x82' # 0x22 -> CONTROL
+ '\x83' # 0x23 -> CONTROL
+ '\x84' # 0x24 -> CONTROL
+ '\n' # 0x25 -> LINE FEED
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK
+ '\x1b' # 0x27 -> ESCAPE
+ '\x88' # 0x28 -> CONTROL
+ '\x89' # 0x29 -> CONTROL
+ '\x8a' # 0x2A -> CONTROL
+ '\x8b' # 0x2B -> CONTROL
+ '\x8c' # 0x2C -> CONTROL
+ '\x05' # 0x2D -> ENQUIRY
+ '\x06' # 0x2E -> ACKNOWLEDGE
+ '\x07' # 0x2F -> BELL
+ '\x90' # 0x30 -> CONTROL
+ '\x91' # 0x31 -> CONTROL
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE
+ '\x93' # 0x33 -> CONTROL
+ '\x94' # 0x34 -> CONTROL
+ '\x95' # 0x35 -> CONTROL
+ '\x96' # 0x36 -> CONTROL
+ '\x04' # 0x37 -> END OF TRANSMISSION
+ '\x98' # 0x38 -> CONTROL
+ '\x99' # 0x39 -> CONTROL
+ '\x9a' # 0x3A -> CONTROL
+ '\x9b' # 0x3B -> CONTROL
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
+ '\x9e' # 0x3E -> CONTROL
+ '\x1a' # 0x3F -> SUBSTITUTE
+ ' ' # 0x40 -> SPACE
+ '\xa0' # 0x41 -> NO-BREAK SPACE
+ '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
+ '[' # 0x4A -> LEFT SQUARE BRACKET
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '!' # 0x4F -> EXCLAMATION MARK
+ '&' # 0x50 -> AMPERSAND
+ '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
+ '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
+ ']' # 0x5A -> RIGHT SQUARE BRACKET
+ '$' # 0x5B -> DOLLAR SIGN
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '^' # 0x5F -> CIRCUMFLEX ACCENT
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xa6' # 0x6A -> BROKEN BAR
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
+ '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '`' # 0x79 -> GRAVE ACCENT
+ ':' # 0x7A -> COLON
+ '#' # 0x7B -> NUMBER SIGN
+ '@' # 0x7C -> COMMERCIAL AT
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '"' # 0x7F -> QUOTATION MARK
+ '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
+ '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
+ '\xb1' # 0x8F -> PLUS-MINUS SIGN
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
+ '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
+ '\xb8' # 0x9D -> CEDILLA
+ '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
+ '\xa4' # 0x9F -> CURRENCY SIGN
+ '\xb5' # 0xA0 -> MICRO SIGN
+ '~' # 0xA1 -> TILDE
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
+ '\xbf' # 0xAB -> INVERTED QUESTION MARK
+ '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
+ '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
+ '\xae' # 0xAF -> REGISTERED SIGN
+ '\xa2' # 0xB0 -> CENT SIGN
+ '\xa3' # 0xB1 -> POUND SIGN
+ '\xa5' # 0xB2 -> YEN SIGN
+ '\xb7' # 0xB3 -> MIDDLE DOT
+ '\xa9' # 0xB4 -> COPYRIGHT SIGN
+ '\xa7' # 0xB5 -> SECTION SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
+ '\xac' # 0xBA -> NOT SIGN
+ '|' # 0xBB -> VERTICAL LINE
+ '\xaf' # 0xBC -> MACRON
+ '\xa8' # 0xBD -> DIAERESIS
+ '\xb4' # 0xBE -> ACUTE ACCENT
+ '\xd7' # 0xBF -> MULTIPLICATION SIGN
+ '{' # 0xC0 -> LEFT CURLY BRACKET
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
+ '}' # 0xD0 -> RIGHT CURLY BRACKET
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb9' # 0xDA -> SUPERSCRIPT ONE
+ '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
+ '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\\' # 0xE0 -> REVERSE SOLIDUS
+ '\xf7' # 0xE1 -> DIVISION SIGN
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\x9f' # 0xFF -> CONTROL
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp65001.py b/Lib/encodings/cp65001.py
new file mode 100644
index 0000000..95cb2ae
--- /dev/null
+++ b/Lib/encodings/cp65001.py
@@ -0,0 +1,43 @@
+"""
+Code page 65001: Windows UTF-8 (CP_UTF8).
+"""
+
+import codecs
+import functools
+
+if not hasattr(codecs, 'code_page_encode'):
+ raise LookupError("cp65001 encoding is only available on Windows")
+
+### Codec APIs
+
+encode = functools.partial(codecs.code_page_encode, 65001)
+_decode = functools.partial(codecs.code_page_decode, 65001)
+
+def decode(input, errors='strict'):
+ return codecs.code_page_decode(65001, input, errors, True)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return encode(input, self.errors)[0]
+
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
+ _buffer_decode = _decode
+
+class StreamWriter(codecs.StreamWriter):
+ encode = encode
+
+class StreamReader(codecs.StreamReader):
+ decode = _decode
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp65001',
+ encode=encode,
+ decode=decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/cp720.py b/Lib/encodings/cp720.py
new file mode 100644
index 0000000..96d6096
--- /dev/null
+++ b/Lib/encodings/cp720.py
@@ -0,0 +1,309 @@
+"""Python Character Mapping Codec cp720 generated on Windows:
+Vista 6.0.6002 SP2 Multiprocessor Free with the command:
+ python Tools/unicode/genwincodec.py 720
+"""#"
+
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp720',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> CONTROL CHARACTER
+ '\x01' # 0x01 -> CONTROL CHARACTER
+ '\x02' # 0x02 -> CONTROL CHARACTER
+ '\x03' # 0x03 -> CONTROL CHARACTER
+ '\x04' # 0x04 -> CONTROL CHARACTER
+ '\x05' # 0x05 -> CONTROL CHARACTER
+ '\x06' # 0x06 -> CONTROL CHARACTER
+ '\x07' # 0x07 -> CONTROL CHARACTER
+ '\x08' # 0x08 -> CONTROL CHARACTER
+ '\t' # 0x09 -> CONTROL CHARACTER
+ '\n' # 0x0A -> CONTROL CHARACTER
+ '\x0b' # 0x0B -> CONTROL CHARACTER
+ '\x0c' # 0x0C -> CONTROL CHARACTER
+ '\r' # 0x0D -> CONTROL CHARACTER
+ '\x0e' # 0x0E -> CONTROL CHARACTER
+ '\x0f' # 0x0F -> CONTROL CHARACTER
+ '\x10' # 0x10 -> CONTROL CHARACTER
+ '\x11' # 0x11 -> CONTROL CHARACTER
+ '\x12' # 0x12 -> CONTROL CHARACTER
+ '\x13' # 0x13 -> CONTROL CHARACTER
+ '\x14' # 0x14 -> CONTROL CHARACTER
+ '\x15' # 0x15 -> CONTROL CHARACTER
+ '\x16' # 0x16 -> CONTROL CHARACTER
+ '\x17' # 0x17 -> CONTROL CHARACTER
+ '\x18' # 0x18 -> CONTROL CHARACTER
+ '\x19' # 0x19 -> CONTROL CHARACTER
+ '\x1a' # 0x1A -> CONTROL CHARACTER
+ '\x1b' # 0x1B -> CONTROL CHARACTER
+ '\x1c' # 0x1C -> CONTROL CHARACTER
+ '\x1d' # 0x1D -> CONTROL CHARACTER
+ '\x1e' # 0x1E -> CONTROL CHARACTER
+ '\x1f' # 0x1F -> CONTROL CHARACTER
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> CONTROL CHARACTER
+ '\x80'
+ '\x81'
+ '\xe9' # 0x82 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x83 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\x84'
+ '\xe0' # 0x85 -> LATIN SMALL LETTER A WITH GRAVE
+ '\x86'
+ '\xe7' # 0x87 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x88 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x89 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x8A -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x8B -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x8C -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\x8d'
+ '\x8e'
+ '\x8f'
+ '\x90'
+ '\u0651' # 0x91 -> ARABIC SHADDA
+ '\u0652' # 0x92 -> ARABIC SUKUN
+ '\xf4' # 0x93 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xa4' # 0x94 -> CURRENCY SIGN
+ '\u0640' # 0x95 -> ARABIC TATWEEL
+ '\xfb' # 0x96 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x97 -> LATIN SMALL LETTER U WITH GRAVE
+ '\u0621' # 0x98 -> ARABIC LETTER HAMZA
+ '\u0622' # 0x99 -> ARABIC LETTER ALEF WITH MADDA ABOVE
+ '\u0623' # 0x9A -> ARABIC LETTER ALEF WITH HAMZA ABOVE
+ '\u0624' # 0x9B -> ARABIC LETTER WAW WITH HAMZA ABOVE
+ '\xa3' # 0x9C -> POUND SIGN
+ '\u0625' # 0x9D -> ARABIC LETTER ALEF WITH HAMZA BELOW
+ '\u0626' # 0x9E -> ARABIC LETTER YEH WITH HAMZA ABOVE
+ '\u0627' # 0x9F -> ARABIC LETTER ALEF
+ '\u0628' # 0xA0 -> ARABIC LETTER BEH
+ '\u0629' # 0xA1 -> ARABIC LETTER TEH MARBUTA
+ '\u062a' # 0xA2 -> ARABIC LETTER TEH
+ '\u062b' # 0xA3 -> ARABIC LETTER THEH
+ '\u062c' # 0xA4 -> ARABIC LETTER JEEM
+ '\u062d' # 0xA5 -> ARABIC LETTER HAH
+ '\u062e' # 0xA6 -> ARABIC LETTER KHAH
+ '\u062f' # 0xA7 -> ARABIC LETTER DAL
+ '\u0630' # 0xA8 -> ARABIC LETTER THAL
+ '\u0631' # 0xA9 -> ARABIC LETTER REH
+ '\u0632' # 0xAA -> ARABIC LETTER ZAIN
+ '\u0633' # 0xAB -> ARABIC LETTER SEEN
+ '\u0634' # 0xAC -> ARABIC LETTER SHEEN
+ '\u0635' # 0xAD -> ARABIC LETTER SAD
+ '\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0xB0 -> LIGHT SHADE
+ '\u2592' # 0xB1 -> MEDIUM SHADE
+ '\u2593' # 0xB2 -> DARK SHADE
+ '\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0xB5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0xB6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0xB8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0xBD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0xBE -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0xC6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0xC7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0xCF -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0xD0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0xD1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0xD2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0xD3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0xD4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0xD5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0xD6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0xD7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0xD8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0xDB -> FULL BLOCK
+ '\u2584' # 0xDC -> LOWER HALF BLOCK
+ '\u258c' # 0xDD -> LEFT HALF BLOCK
+ '\u2590' # 0xDE -> RIGHT HALF BLOCK
+ '\u2580' # 0xDF -> UPPER HALF BLOCK
+ '\u0636' # 0xE0 -> ARABIC LETTER DAD
+ '\u0637' # 0xE1 -> ARABIC LETTER TAH
+ '\u0638' # 0xE2 -> ARABIC LETTER ZAH
+ '\u0639' # 0xE3 -> ARABIC LETTER AIN
+ '\u063a' # 0xE4 -> ARABIC LETTER GHAIN
+ '\u0641' # 0xE5 -> ARABIC LETTER FEH
+ '\xb5' # 0xE6 -> MICRO SIGN
+ '\u0642' # 0xE7 -> ARABIC LETTER QAF
+ '\u0643' # 0xE8 -> ARABIC LETTER KAF
+ '\u0644' # 0xE9 -> ARABIC LETTER LAM
+ '\u0645' # 0xEA -> ARABIC LETTER MEEM
+ '\u0646' # 0xEB -> ARABIC LETTER NOON
+ '\u0647' # 0xEC -> ARABIC LETTER HEH
+ '\u0648' # 0xED -> ARABIC LETTER WAW
+ '\u0649' # 0xEE -> ARABIC LETTER ALEF MAKSURA
+ '\u064a' # 0xEF -> ARABIC LETTER YEH
+ '\u2261' # 0xF0 -> IDENTICAL TO
+ '\u064b' # 0xF1 -> ARABIC FATHATAN
+ '\u064c' # 0xF2 -> ARABIC DAMMATAN
+ '\u064d' # 0xF3 -> ARABIC KASRATAN
+ '\u064e' # 0xF4 -> ARABIC FATHA
+ '\u064f' # 0xF5 -> ARABIC DAMMA
+ '\u0650' # 0xF6 -> ARABIC KASRA
+ '\u2248' # 0xF7 -> ALMOST EQUAL TO
+ '\xb0' # 0xF8 -> DEGREE SIGN
+ '\u2219' # 0xF9 -> BULLET OPERATOR
+ '\xb7' # 0xFA -> MIDDLE DOT
+ '\u221a' # 0xFB -> SQUARE ROOT
+ '\u207f' # 0xFC -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0xFD -> SUPERSCRIPT TWO
+ '\u25a0' # 0xFE -> BLACK SQUARE
+ '\xa0' # 0xFF -> NO-BREAK SPACE
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp737.py b/Lib/encodings/cp737.py
new file mode 100644
index 0000000..9685bae
--- /dev/null
+++ b/Lib/encodings/cp737.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec cp737 generated from 'VENDORS/MICSFT/PC/CP737.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp737',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x0391, # GREEK CAPITAL LETTER ALPHA
+ 0x0081: 0x0392, # GREEK CAPITAL LETTER BETA
+ 0x0082: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x0083: 0x0394, # GREEK CAPITAL LETTER DELTA
+ 0x0084: 0x0395, # GREEK CAPITAL LETTER EPSILON
+ 0x0085: 0x0396, # GREEK CAPITAL LETTER ZETA
+ 0x0086: 0x0397, # GREEK CAPITAL LETTER ETA
+ 0x0087: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x0088: 0x0399, # GREEK CAPITAL LETTER IOTA
+ 0x0089: 0x039a, # GREEK CAPITAL LETTER KAPPA
+ 0x008a: 0x039b, # GREEK CAPITAL LETTER LAMDA
+ 0x008b: 0x039c, # GREEK CAPITAL LETTER MU
+ 0x008c: 0x039d, # GREEK CAPITAL LETTER NU
+ 0x008d: 0x039e, # GREEK CAPITAL LETTER XI
+ 0x008e: 0x039f, # GREEK CAPITAL LETTER OMICRON
+ 0x008f: 0x03a0, # GREEK CAPITAL LETTER PI
+ 0x0090: 0x03a1, # GREEK CAPITAL LETTER RHO
+ 0x0091: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x0092: 0x03a4, # GREEK CAPITAL LETTER TAU
+ 0x0093: 0x03a5, # GREEK CAPITAL LETTER UPSILON
+ 0x0094: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x0095: 0x03a7, # GREEK CAPITAL LETTER CHI
+ 0x0096: 0x03a8, # GREEK CAPITAL LETTER PSI
+ 0x0097: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x0098: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x0099: 0x03b2, # GREEK SMALL LETTER BETA
+ 0x009a: 0x03b3, # GREEK SMALL LETTER GAMMA
+ 0x009b: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x009c: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x009d: 0x03b6, # GREEK SMALL LETTER ZETA
+ 0x009e: 0x03b7, # GREEK SMALL LETTER ETA
+ 0x009f: 0x03b8, # GREEK SMALL LETTER THETA
+ 0x00a0: 0x03b9, # GREEK SMALL LETTER IOTA
+ 0x00a1: 0x03ba, # GREEK SMALL LETTER KAPPA
+ 0x00a2: 0x03bb, # GREEK SMALL LETTER LAMDA
+ 0x00a3: 0x03bc, # GREEK SMALL LETTER MU
+ 0x00a4: 0x03bd, # GREEK SMALL LETTER NU
+ 0x00a5: 0x03be, # GREEK SMALL LETTER XI
+ 0x00a6: 0x03bf, # GREEK SMALL LETTER OMICRON
+ 0x00a7: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00a8: 0x03c1, # GREEK SMALL LETTER RHO
+ 0x00a9: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00aa: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
+ 0x00ab: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00ac: 0x03c5, # GREEK SMALL LETTER UPSILON
+ 0x00ad: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ae: 0x03c7, # GREEK SMALL LETTER CHI
+ 0x00af: 0x03c8, # GREEK SMALL LETTER PSI
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03c9, # GREEK SMALL LETTER OMEGA
+ 0x00e1: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
+ 0x00e2: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
+ 0x00e3: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
+ 0x00e4: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ 0x00e5: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
+ 0x00e6: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
+ 0x00e7: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
+ 0x00e8: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ 0x00e9: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
+ 0x00ea: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
+ 0x00eb: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
+ 0x00ec: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
+ 0x00ed: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
+ 0x00ee: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
+ 0x00ef: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
+ 0x00f0: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ 0x00f5: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\u0391' # 0x0080 -> GREEK CAPITAL LETTER ALPHA
+ '\u0392' # 0x0081 -> GREEK CAPITAL LETTER BETA
+ '\u0393' # 0x0082 -> GREEK CAPITAL LETTER GAMMA
+ '\u0394' # 0x0083 -> GREEK CAPITAL LETTER DELTA
+ '\u0395' # 0x0084 -> GREEK CAPITAL LETTER EPSILON
+ '\u0396' # 0x0085 -> GREEK CAPITAL LETTER ZETA
+ '\u0397' # 0x0086 -> GREEK CAPITAL LETTER ETA
+ '\u0398' # 0x0087 -> GREEK CAPITAL LETTER THETA
+ '\u0399' # 0x0088 -> GREEK CAPITAL LETTER IOTA
+ '\u039a' # 0x0089 -> GREEK CAPITAL LETTER KAPPA
+ '\u039b' # 0x008a -> GREEK CAPITAL LETTER LAMDA
+ '\u039c' # 0x008b -> GREEK CAPITAL LETTER MU
+ '\u039d' # 0x008c -> GREEK CAPITAL LETTER NU
+ '\u039e' # 0x008d -> GREEK CAPITAL LETTER XI
+ '\u039f' # 0x008e -> GREEK CAPITAL LETTER OMICRON
+ '\u03a0' # 0x008f -> GREEK CAPITAL LETTER PI
+ '\u03a1' # 0x0090 -> GREEK CAPITAL LETTER RHO
+ '\u03a3' # 0x0091 -> GREEK CAPITAL LETTER SIGMA
+ '\u03a4' # 0x0092 -> GREEK CAPITAL LETTER TAU
+ '\u03a5' # 0x0093 -> GREEK CAPITAL LETTER UPSILON
+ '\u03a6' # 0x0094 -> GREEK CAPITAL LETTER PHI
+ '\u03a7' # 0x0095 -> GREEK CAPITAL LETTER CHI
+ '\u03a8' # 0x0096 -> GREEK CAPITAL LETTER PSI
+ '\u03a9' # 0x0097 -> GREEK CAPITAL LETTER OMEGA
+ '\u03b1' # 0x0098 -> GREEK SMALL LETTER ALPHA
+ '\u03b2' # 0x0099 -> GREEK SMALL LETTER BETA
+ '\u03b3' # 0x009a -> GREEK SMALL LETTER GAMMA
+ '\u03b4' # 0x009b -> GREEK SMALL LETTER DELTA
+ '\u03b5' # 0x009c -> GREEK SMALL LETTER EPSILON
+ '\u03b6' # 0x009d -> GREEK SMALL LETTER ZETA
+ '\u03b7' # 0x009e -> GREEK SMALL LETTER ETA
+ '\u03b8' # 0x009f -> GREEK SMALL LETTER THETA
+ '\u03b9' # 0x00a0 -> GREEK SMALL LETTER IOTA
+ '\u03ba' # 0x00a1 -> GREEK SMALL LETTER KAPPA
+ '\u03bb' # 0x00a2 -> GREEK SMALL LETTER LAMDA
+ '\u03bc' # 0x00a3 -> GREEK SMALL LETTER MU
+ '\u03bd' # 0x00a4 -> GREEK SMALL LETTER NU
+ '\u03be' # 0x00a5 -> GREEK SMALL LETTER XI
+ '\u03bf' # 0x00a6 -> GREEK SMALL LETTER OMICRON
+ '\u03c0' # 0x00a7 -> GREEK SMALL LETTER PI
+ '\u03c1' # 0x00a8 -> GREEK SMALL LETTER RHO
+ '\u03c3' # 0x00a9 -> GREEK SMALL LETTER SIGMA
+ '\u03c2' # 0x00aa -> GREEK SMALL LETTER FINAL SIGMA
+ '\u03c4' # 0x00ab -> GREEK SMALL LETTER TAU
+ '\u03c5' # 0x00ac -> GREEK SMALL LETTER UPSILON
+ '\u03c6' # 0x00ad -> GREEK SMALL LETTER PHI
+ '\u03c7' # 0x00ae -> GREEK SMALL LETTER CHI
+ '\u03c8' # 0x00af -> GREEK SMALL LETTER PSI
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03c9' # 0x00e0 -> GREEK SMALL LETTER OMEGA
+ '\u03ac' # 0x00e1 -> GREEK SMALL LETTER ALPHA WITH TONOS
+ '\u03ad' # 0x00e2 -> GREEK SMALL LETTER EPSILON WITH TONOS
+ '\u03ae' # 0x00e3 -> GREEK SMALL LETTER ETA WITH TONOS
+ '\u03ca' # 0x00e4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ '\u03af' # 0x00e5 -> GREEK SMALL LETTER IOTA WITH TONOS
+ '\u03cc' # 0x00e6 -> GREEK SMALL LETTER OMICRON WITH TONOS
+ '\u03cd' # 0x00e7 -> GREEK SMALL LETTER UPSILON WITH TONOS
+ '\u03cb' # 0x00e8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ '\u03ce' # 0x00e9 -> GREEK SMALL LETTER OMEGA WITH TONOS
+ '\u0386' # 0x00ea -> GREEK CAPITAL LETTER ALPHA WITH TONOS
+ '\u0388' # 0x00eb -> GREEK CAPITAL LETTER EPSILON WITH TONOS
+ '\u0389' # 0x00ec -> GREEK CAPITAL LETTER ETA WITH TONOS
+ '\u038a' # 0x00ed -> GREEK CAPITAL LETTER IOTA WITH TONOS
+ '\u038c' # 0x00ee -> GREEK CAPITAL LETTER OMICRON WITH TONOS
+ '\u038e' # 0x00ef -> GREEK CAPITAL LETTER UPSILON WITH TONOS
+ '\u038f' # 0x00f0 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u03aa' # 0x00f4 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ '\u03ab' # 0x00f5 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x0386: 0x00ea, # GREEK CAPITAL LETTER ALPHA WITH TONOS
+ 0x0388: 0x00eb, # GREEK CAPITAL LETTER EPSILON WITH TONOS
+ 0x0389: 0x00ec, # GREEK CAPITAL LETTER ETA WITH TONOS
+ 0x038a: 0x00ed, # GREEK CAPITAL LETTER IOTA WITH TONOS
+ 0x038c: 0x00ee, # GREEK CAPITAL LETTER OMICRON WITH TONOS
+ 0x038e: 0x00ef, # GREEK CAPITAL LETTER UPSILON WITH TONOS
+ 0x038f: 0x00f0, # GREEK CAPITAL LETTER OMEGA WITH TONOS
+ 0x0391: 0x0080, # GREEK CAPITAL LETTER ALPHA
+ 0x0392: 0x0081, # GREEK CAPITAL LETTER BETA
+ 0x0393: 0x0082, # GREEK CAPITAL LETTER GAMMA
+ 0x0394: 0x0083, # GREEK CAPITAL LETTER DELTA
+ 0x0395: 0x0084, # GREEK CAPITAL LETTER EPSILON
+ 0x0396: 0x0085, # GREEK CAPITAL LETTER ZETA
+ 0x0397: 0x0086, # GREEK CAPITAL LETTER ETA
+ 0x0398: 0x0087, # GREEK CAPITAL LETTER THETA
+ 0x0399: 0x0088, # GREEK CAPITAL LETTER IOTA
+ 0x039a: 0x0089, # GREEK CAPITAL LETTER KAPPA
+ 0x039b: 0x008a, # GREEK CAPITAL LETTER LAMDA
+ 0x039c: 0x008b, # GREEK CAPITAL LETTER MU
+ 0x039d: 0x008c, # GREEK CAPITAL LETTER NU
+ 0x039e: 0x008d, # GREEK CAPITAL LETTER XI
+ 0x039f: 0x008e, # GREEK CAPITAL LETTER OMICRON
+ 0x03a0: 0x008f, # GREEK CAPITAL LETTER PI
+ 0x03a1: 0x0090, # GREEK CAPITAL LETTER RHO
+ 0x03a3: 0x0091, # GREEK CAPITAL LETTER SIGMA
+ 0x03a4: 0x0092, # GREEK CAPITAL LETTER TAU
+ 0x03a5: 0x0093, # GREEK CAPITAL LETTER UPSILON
+ 0x03a6: 0x0094, # GREEK CAPITAL LETTER PHI
+ 0x03a7: 0x0095, # GREEK CAPITAL LETTER CHI
+ 0x03a8: 0x0096, # GREEK CAPITAL LETTER PSI
+ 0x03a9: 0x0097, # GREEK CAPITAL LETTER OMEGA
+ 0x03aa: 0x00f4, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ 0x03ab: 0x00f5, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ 0x03ac: 0x00e1, # GREEK SMALL LETTER ALPHA WITH TONOS
+ 0x03ad: 0x00e2, # GREEK SMALL LETTER EPSILON WITH TONOS
+ 0x03ae: 0x00e3, # GREEK SMALL LETTER ETA WITH TONOS
+ 0x03af: 0x00e5, # GREEK SMALL LETTER IOTA WITH TONOS
+ 0x03b1: 0x0098, # GREEK SMALL LETTER ALPHA
+ 0x03b2: 0x0099, # GREEK SMALL LETTER BETA
+ 0x03b3: 0x009a, # GREEK SMALL LETTER GAMMA
+ 0x03b4: 0x009b, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x009c, # GREEK SMALL LETTER EPSILON
+ 0x03b6: 0x009d, # GREEK SMALL LETTER ZETA
+ 0x03b7: 0x009e, # GREEK SMALL LETTER ETA
+ 0x03b8: 0x009f, # GREEK SMALL LETTER THETA
+ 0x03b9: 0x00a0, # GREEK SMALL LETTER IOTA
+ 0x03ba: 0x00a1, # GREEK SMALL LETTER KAPPA
+ 0x03bb: 0x00a2, # GREEK SMALL LETTER LAMDA
+ 0x03bc: 0x00a3, # GREEK SMALL LETTER MU
+ 0x03bd: 0x00a4, # GREEK SMALL LETTER NU
+ 0x03be: 0x00a5, # GREEK SMALL LETTER XI
+ 0x03bf: 0x00a6, # GREEK SMALL LETTER OMICRON
+ 0x03c0: 0x00a7, # GREEK SMALL LETTER PI
+ 0x03c1: 0x00a8, # GREEK SMALL LETTER RHO
+ 0x03c2: 0x00aa, # GREEK SMALL LETTER FINAL SIGMA
+ 0x03c3: 0x00a9, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00ab, # GREEK SMALL LETTER TAU
+ 0x03c5: 0x00ac, # GREEK SMALL LETTER UPSILON
+ 0x03c6: 0x00ad, # GREEK SMALL LETTER PHI
+ 0x03c7: 0x00ae, # GREEK SMALL LETTER CHI
+ 0x03c8: 0x00af, # GREEK SMALL LETTER PSI
+ 0x03c9: 0x00e0, # GREEK SMALL LETTER OMEGA
+ 0x03ca: 0x00e4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ 0x03cb: 0x00e8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ 0x03cc: 0x00e6, # GREEK SMALL LETTER OMICRON WITH TONOS
+ 0x03cd: 0x00e7, # GREEK SMALL LETTER UPSILON WITH TONOS
+ 0x03ce: 0x00e9, # GREEK SMALL LETTER OMEGA WITH TONOS
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp775.py b/Lib/encodings/cp775.py
new file mode 100644
index 0000000..fe06e7b
--- /dev/null
+++ b/Lib/encodings/cp775.py
@@ -0,0 +1,697 @@
+""" Python Character Mapping Codec cp775 generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp775',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x0101, # LATIN SMALL LETTER A WITH MACRON
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x0123, # LATIN SMALL LETTER G WITH CEDILLA
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x0107, # LATIN SMALL LETTER C WITH ACUTE
+ 0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE
+ 0x0089: 0x0113, # LATIN SMALL LETTER E WITH MACRON
+ 0x008a: 0x0156, # LATIN CAPITAL LETTER R WITH CEDILLA
+ 0x008b: 0x0157, # LATIN SMALL LETTER R WITH CEDILLA
+ 0x008c: 0x012b, # LATIN SMALL LETTER I WITH MACRON
+ 0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x014d, # LATIN SMALL LETTER O WITH MACRON
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x0122, # LATIN CAPITAL LETTER G WITH CEDILLA
+ 0x0096: 0x00a2, # CENT SIGN
+ 0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE
+ 0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x00d7, # MULTIPLICATION SIGN
+ 0x009f: 0x00a4, # CURRENCY SIGN
+ 0x00a0: 0x0100, # LATIN CAPITAL LETTER A WITH MACRON
+ 0x00a1: 0x012a, # LATIN CAPITAL LETTER I WITH MACRON
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ 0x00a4: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE
+ 0x00a5: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE
+ 0x00a6: 0x201d, # RIGHT DOUBLE QUOTATION MARK
+ 0x00a7: 0x00a6, # BROKEN BAR
+ 0x00a8: 0x00a9, # COPYRIGHT SIGN
+ 0x00a9: 0x00ae, # REGISTERED SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK
+ 0x00b6: 0x010c, # LATIN CAPITAL LETTER C WITH CARON
+ 0x00b7: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK
+ 0x00b8: 0x0116, # LATIN CAPITAL LETTER E WITH DOT ABOVE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x012e, # LATIN CAPITAL LETTER I WITH OGONEK
+ 0x00be: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x0172, # LATIN CAPITAL LETTER U WITH OGONEK
+ 0x00c7: 0x016a, # LATIN CAPITAL LETTER U WITH MACRON
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON
+ 0x00d0: 0x0105, # LATIN SMALL LETTER A WITH OGONEK
+ 0x00d1: 0x010d, # LATIN SMALL LETTER C WITH CARON
+ 0x00d2: 0x0119, # LATIN SMALL LETTER E WITH OGONEK
+ 0x00d3: 0x0117, # LATIN SMALL LETTER E WITH DOT ABOVE
+ 0x00d4: 0x012f, # LATIN SMALL LETTER I WITH OGONEK
+ 0x00d5: 0x0161, # LATIN SMALL LETTER S WITH CARON
+ 0x00d6: 0x0173, # LATIN SMALL LETTER U WITH OGONEK
+ 0x00d7: 0x016b, # LATIN SMALL LETTER U WITH MACRON
+ 0x00d8: 0x017e, # LATIN SMALL LETTER Z WITH CARON
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN)
+ 0x00e2: 0x014c, # LATIN CAPITAL LETTER O WITH MACRON
+ 0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE
+ 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
+ 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x0144, # LATIN SMALL LETTER N WITH ACUTE
+ 0x00e8: 0x0136, # LATIN CAPITAL LETTER K WITH CEDILLA
+ 0x00e9: 0x0137, # LATIN SMALL LETTER K WITH CEDILLA
+ 0x00ea: 0x013b, # LATIN CAPITAL LETTER L WITH CEDILLA
+ 0x00eb: 0x013c, # LATIN SMALL LETTER L WITH CEDILLA
+ 0x00ec: 0x0146, # LATIN SMALL LETTER N WITH CEDILLA
+ 0x00ed: 0x0112, # LATIN CAPITAL LETTER E WITH MACRON
+ 0x00ee: 0x0145, # LATIN CAPITAL LETTER N WITH CEDILLA
+ 0x00ef: 0x2019, # RIGHT SINGLE QUOTATION MARK
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x201c, # LEFT DOUBLE QUOTATION MARK
+ 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00f4: 0x00b6, # PILCROW SIGN
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x201e, # DOUBLE LOW-9 QUOTATION MARK
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x00b9, # SUPERSCRIPT ONE
+ 0x00fc: 0x00b3, # SUPERSCRIPT THREE
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\u0106' # 0x0080 -> LATIN CAPITAL LETTER C WITH ACUTE
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\u0101' # 0x0083 -> LATIN SMALL LETTER A WITH MACRON
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\u0123' # 0x0085 -> LATIN SMALL LETTER G WITH CEDILLA
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\u0107' # 0x0087 -> LATIN SMALL LETTER C WITH ACUTE
+ '\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE
+ '\u0113' # 0x0089 -> LATIN SMALL LETTER E WITH MACRON
+ '\u0156' # 0x008a -> LATIN CAPITAL LETTER R WITH CEDILLA
+ '\u0157' # 0x008b -> LATIN SMALL LETTER R WITH CEDILLA
+ '\u012b' # 0x008c -> LATIN SMALL LETTER I WITH MACRON
+ '\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\u014d' # 0x0093 -> LATIN SMALL LETTER O WITH MACRON
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\u0122' # 0x0095 -> LATIN CAPITAL LETTER G WITH CEDILLA
+ '\xa2' # 0x0096 -> CENT SIGN
+ '\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE
+ '\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd7' # 0x009e -> MULTIPLICATION SIGN
+ '\xa4' # 0x009f -> CURRENCY SIGN
+ '\u0100' # 0x00a0 -> LATIN CAPITAL LETTER A WITH MACRON
+ '\u012a' # 0x00a1 -> LATIN CAPITAL LETTER I WITH MACRON
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\u017b' # 0x00a3 -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ '\u017c' # 0x00a4 -> LATIN SMALL LETTER Z WITH DOT ABOVE
+ '\u017a' # 0x00a5 -> LATIN SMALL LETTER Z WITH ACUTE
+ '\u201d' # 0x00a6 -> RIGHT DOUBLE QUOTATION MARK
+ '\xa6' # 0x00a7 -> BROKEN BAR
+ '\xa9' # 0x00a8 -> COPYRIGHT SIGN
+ '\xae' # 0x00a9 -> REGISTERED SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\u0141' # 0x00ad -> LATIN CAPITAL LETTER L WITH STROKE
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u0104' # 0x00b5 -> LATIN CAPITAL LETTER A WITH OGONEK
+ '\u010c' # 0x00b6 -> LATIN CAPITAL LETTER C WITH CARON
+ '\u0118' # 0x00b7 -> LATIN CAPITAL LETTER E WITH OGONEK
+ '\u0116' # 0x00b8 -> LATIN CAPITAL LETTER E WITH DOT ABOVE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u012e' # 0x00bd -> LATIN CAPITAL LETTER I WITH OGONEK
+ '\u0160' # 0x00be -> LATIN CAPITAL LETTER S WITH CARON
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u0172' # 0x00c6 -> LATIN CAPITAL LETTER U WITH OGONEK
+ '\u016a' # 0x00c7 -> LATIN CAPITAL LETTER U WITH MACRON
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u017d' # 0x00cf -> LATIN CAPITAL LETTER Z WITH CARON
+ '\u0105' # 0x00d0 -> LATIN SMALL LETTER A WITH OGONEK
+ '\u010d' # 0x00d1 -> LATIN SMALL LETTER C WITH CARON
+ '\u0119' # 0x00d2 -> LATIN SMALL LETTER E WITH OGONEK
+ '\u0117' # 0x00d3 -> LATIN SMALL LETTER E WITH DOT ABOVE
+ '\u012f' # 0x00d4 -> LATIN SMALL LETTER I WITH OGONEK
+ '\u0161' # 0x00d5 -> LATIN SMALL LETTER S WITH CARON
+ '\u0173' # 0x00d6 -> LATIN SMALL LETTER U WITH OGONEK
+ '\u016b' # 0x00d7 -> LATIN SMALL LETTER U WITH MACRON
+ '\u017e' # 0x00d8 -> LATIN SMALL LETTER Z WITH CARON
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN)
+ '\u014c' # 0x00e2 -> LATIN CAPITAL LETTER O WITH MACRON
+ '\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE
+ '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
+ '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u0144' # 0x00e7 -> LATIN SMALL LETTER N WITH ACUTE
+ '\u0136' # 0x00e8 -> LATIN CAPITAL LETTER K WITH CEDILLA
+ '\u0137' # 0x00e9 -> LATIN SMALL LETTER K WITH CEDILLA
+ '\u013b' # 0x00ea -> LATIN CAPITAL LETTER L WITH CEDILLA
+ '\u013c' # 0x00eb -> LATIN SMALL LETTER L WITH CEDILLA
+ '\u0146' # 0x00ec -> LATIN SMALL LETTER N WITH CEDILLA
+ '\u0112' # 0x00ed -> LATIN CAPITAL LETTER E WITH MACRON
+ '\u0145' # 0x00ee -> LATIN CAPITAL LETTER N WITH CEDILLA
+ '\u2019' # 0x00ef -> RIGHT SINGLE QUOTATION MARK
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u201c' # 0x00f2 -> LEFT DOUBLE QUOTATION MARK
+ '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
+ '\xb6' # 0x00f4 -> PILCROW SIGN
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u201e' # 0x00f7 -> DOUBLE LOW-9 QUOTATION MARK
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\xb9' # 0x00fb -> SUPERSCRIPT ONE
+ '\xb3' # 0x00fc -> SUPERSCRIPT THREE
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a2: 0x0096, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x009f, # CURRENCY SIGN
+ 0x00a6: 0x00a7, # BROKEN BAR
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a9: 0x00a8, # COPYRIGHT SIGN
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00ae: 0x00a9, # REGISTERED SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b3: 0x00fc, # SUPERSCRIPT THREE
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b6: 0x00f4, # PILCROW SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00b9: 0x00fb, # SUPERSCRIPT ONE
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d7: 0x009e, # MULTIPLICATION SIGN
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN)
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0100: 0x00a0, # LATIN CAPITAL LETTER A WITH MACRON
+ 0x0101: 0x0083, # LATIN SMALL LETTER A WITH MACRON
+ 0x0104: 0x00b5, # LATIN CAPITAL LETTER A WITH OGONEK
+ 0x0105: 0x00d0, # LATIN SMALL LETTER A WITH OGONEK
+ 0x0106: 0x0080, # LATIN CAPITAL LETTER C WITH ACUTE
+ 0x0107: 0x0087, # LATIN SMALL LETTER C WITH ACUTE
+ 0x010c: 0x00b6, # LATIN CAPITAL LETTER C WITH CARON
+ 0x010d: 0x00d1, # LATIN SMALL LETTER C WITH CARON
+ 0x0112: 0x00ed, # LATIN CAPITAL LETTER E WITH MACRON
+ 0x0113: 0x0089, # LATIN SMALL LETTER E WITH MACRON
+ 0x0116: 0x00b8, # LATIN CAPITAL LETTER E WITH DOT ABOVE
+ 0x0117: 0x00d3, # LATIN SMALL LETTER E WITH DOT ABOVE
+ 0x0118: 0x00b7, # LATIN CAPITAL LETTER E WITH OGONEK
+ 0x0119: 0x00d2, # LATIN SMALL LETTER E WITH OGONEK
+ 0x0122: 0x0095, # LATIN CAPITAL LETTER G WITH CEDILLA
+ 0x0123: 0x0085, # LATIN SMALL LETTER G WITH CEDILLA
+ 0x012a: 0x00a1, # LATIN CAPITAL LETTER I WITH MACRON
+ 0x012b: 0x008c, # LATIN SMALL LETTER I WITH MACRON
+ 0x012e: 0x00bd, # LATIN CAPITAL LETTER I WITH OGONEK
+ 0x012f: 0x00d4, # LATIN SMALL LETTER I WITH OGONEK
+ 0x0136: 0x00e8, # LATIN CAPITAL LETTER K WITH CEDILLA
+ 0x0137: 0x00e9, # LATIN SMALL LETTER K WITH CEDILLA
+ 0x013b: 0x00ea, # LATIN CAPITAL LETTER L WITH CEDILLA
+ 0x013c: 0x00eb, # LATIN SMALL LETTER L WITH CEDILLA
+ 0x0141: 0x00ad, # LATIN CAPITAL LETTER L WITH STROKE
+ 0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE
+ 0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE
+ 0x0144: 0x00e7, # LATIN SMALL LETTER N WITH ACUTE
+ 0x0145: 0x00ee, # LATIN CAPITAL LETTER N WITH CEDILLA
+ 0x0146: 0x00ec, # LATIN SMALL LETTER N WITH CEDILLA
+ 0x014c: 0x00e2, # LATIN CAPITAL LETTER O WITH MACRON
+ 0x014d: 0x0093, # LATIN SMALL LETTER O WITH MACRON
+ 0x0156: 0x008a, # LATIN CAPITAL LETTER R WITH CEDILLA
+ 0x0157: 0x008b, # LATIN SMALL LETTER R WITH CEDILLA
+ 0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE
+ 0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE
+ 0x0160: 0x00be, # LATIN CAPITAL LETTER S WITH CARON
+ 0x0161: 0x00d5, # LATIN SMALL LETTER S WITH CARON
+ 0x016a: 0x00c7, # LATIN CAPITAL LETTER U WITH MACRON
+ 0x016b: 0x00d7, # LATIN SMALL LETTER U WITH MACRON
+ 0x0172: 0x00c6, # LATIN CAPITAL LETTER U WITH OGONEK
+ 0x0173: 0x00d6, # LATIN SMALL LETTER U WITH OGONEK
+ 0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE
+ 0x017a: 0x00a5, # LATIN SMALL LETTER Z WITH ACUTE
+ 0x017b: 0x00a3, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ 0x017c: 0x00a4, # LATIN SMALL LETTER Z WITH DOT ABOVE
+ 0x017d: 0x00cf, # LATIN CAPITAL LETTER Z WITH CARON
+ 0x017e: 0x00d8, # LATIN SMALL LETTER Z WITH CARON
+ 0x2019: 0x00ef, # RIGHT SINGLE QUOTATION MARK
+ 0x201c: 0x00f2, # LEFT DOUBLE QUOTATION MARK
+ 0x201d: 0x00a6, # RIGHT DOUBLE QUOTATION MARK
+ 0x201e: 0x00f7, # DOUBLE LOW-9 QUOTATION MARK
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp850.py b/Lib/encodings/cp850.py
new file mode 100644
index 0000000..f98aef9
--- /dev/null
+++ b/Lib/encodings/cp850.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP850.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp850',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x00d7, # MULTIPLICATION SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x00ae, # REGISTERED SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00b8: 0x00a9, # COPYRIGHT SIGN
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x00a2, # CENT SIGN
+ 0x00be: 0x00a5, # YEN SIGN
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
+ 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x00a4, # CURRENCY SIGN
+ 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH
+ 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH
+ 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00d5: 0x0131, # LATIN SMALL LETTER DOTLESS I
+ 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x00a6, # BROKEN BAR
+ 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
+ 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN
+ 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN
+ 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00ee: 0x00af, # MACRON
+ 0x00ef: 0x00b4, # ACUTE ACCENT
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2017, # DOUBLE LOW LINE
+ 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00f4: 0x00b6, # PILCROW SIGN
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x00b8, # CEDILLA
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x00a8, # DIAERESIS
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x00b9, # SUPERSCRIPT ONE
+ 0x00fc: 0x00b3, # SUPERSCRIPT THREE
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd7' # 0x009e -> MULTIPLICATION SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\xae' # 0x00a9 -> REGISTERED SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xa9' # 0x00b8 -> COPYRIGHT SIGN
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\xa2' # 0x00bd -> CENT SIGN
+ '\xa5' # 0x00be -> YEN SIGN
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
+ '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0x00cf -> CURRENCY SIGN
+ '\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH
+ '\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH
+ '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\u0131' # 0x00d5 -> LATIN SMALL LETTER DOTLESS I
+ '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\xa6' # 0x00dd -> BROKEN BAR
+ '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
+ '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN
+ '\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN
+ '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xaf' # 0x00ee -> MACRON
+ '\xb4' # 0x00ef -> ACUTE ACCENT
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2017' # 0x00f2 -> DOUBLE LOW LINE
+ '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
+ '\xb6' # 0x00f4 -> PILCROW SIGN
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\xb8' # 0x00f7 -> CEDILLA
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\xa8' # 0x00f9 -> DIAERESIS
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\xb9' # 0x00fb -> SUPERSCRIPT ONE
+ '\xb3' # 0x00fc -> SUPERSCRIPT THREE
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x00bd, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x00cf, # CURRENCY SIGN
+ 0x00a5: 0x00be, # YEN SIGN
+ 0x00a6: 0x00dd, # BROKEN BAR
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a8: 0x00f9, # DIAERESIS
+ 0x00a9: 0x00b8, # COPYRIGHT SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00ae: 0x00a9, # REGISTERED SIGN
+ 0x00af: 0x00ee, # MACRON
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b3: 0x00fc, # SUPERSCRIPT THREE
+ 0x00b4: 0x00ef, # ACUTE ACCENT
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b6: 0x00f4, # PILCROW SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00b8: 0x00f7, # CEDILLA
+ 0x00b9: 0x00fb, # SUPERSCRIPT ONE
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d7: 0x009e, # MULTIPLICATION SIGN
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN
+ 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0131: 0x00d5, # LATIN SMALL LETTER DOTLESS I
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x2017: 0x00f2, # DOUBLE LOW LINE
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp852.py b/Lib/encodings/cp852.py
new file mode 100644
index 0000000..34d8a0e
--- /dev/null
+++ b/Lib/encodings/cp852.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP852.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp852',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x016f, # LATIN SMALL LETTER U WITH RING ABOVE
+ 0x0086: 0x0107, # LATIN SMALL LETTER C WITH ACUTE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x0150, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+ 0x008b: 0x0151, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x0139, # LATIN CAPITAL LETTER L WITH ACUTE
+ 0x0092: 0x013a, # LATIN SMALL LETTER L WITH ACUTE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x013d, # LATIN CAPITAL LETTER L WITH CARON
+ 0x0096: 0x013e, # LATIN SMALL LETTER L WITH CARON
+ 0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE
+ 0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x0164, # LATIN CAPITAL LETTER T WITH CARON
+ 0x009c: 0x0165, # LATIN SMALL LETTER T WITH CARON
+ 0x009d: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE
+ 0x009e: 0x00d7, # MULTIPLICATION SIGN
+ 0x009f: 0x010d, # LATIN SMALL LETTER C WITH CARON
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK
+ 0x00a5: 0x0105, # LATIN SMALL LETTER A WITH OGONEK
+ 0x00a6: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON
+ 0x00a7: 0x017e, # LATIN SMALL LETTER Z WITH CARON
+ 0x00a8: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK
+ 0x00a9: 0x0119, # LATIN SMALL LETTER E WITH OGONEK
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE
+ 0x00ac: 0x010c, # LATIN CAPITAL LETTER C WITH CARON
+ 0x00ad: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00b7: 0x011a, # LATIN CAPITAL LETTER E WITH CARON
+ 0x00b8: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ 0x00be: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x0102, # LATIN CAPITAL LETTER A WITH BREVE
+ 0x00c7: 0x0103, # LATIN SMALL LETTER A WITH BREVE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x00a4, # CURRENCY SIGN
+ 0x00d0: 0x0111, # LATIN SMALL LETTER D WITH STROKE
+ 0x00d1: 0x0110, # LATIN CAPITAL LETTER D WITH STROKE
+ 0x00d2: 0x010e, # LATIN CAPITAL LETTER D WITH CARON
+ 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00d4: 0x010f, # LATIN SMALL LETTER D WITH CARON
+ 0x00d5: 0x0147, # LATIN CAPITAL LETTER N WITH CARON
+ 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00d8: 0x011b, # LATIN SMALL LETTER E WITH CARON
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x0162, # LATIN CAPITAL LETTER T WITH CEDILLA
+ 0x00de: 0x016e, # LATIN CAPITAL LETTER U WITH RING ABOVE
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE
+ 0x00e4: 0x0144, # LATIN SMALL LETTER N WITH ACUTE
+ 0x00e5: 0x0148, # LATIN SMALL LETTER N WITH CARON
+ 0x00e6: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
+ 0x00e7: 0x0161, # LATIN SMALL LETTER S WITH CARON
+ 0x00e8: 0x0154, # LATIN CAPITAL LETTER R WITH ACUTE
+ 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00ea: 0x0155, # LATIN SMALL LETTER R WITH ACUTE
+ 0x00eb: 0x0170, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+ 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00ee: 0x0163, # LATIN SMALL LETTER T WITH CEDILLA
+ 0x00ef: 0x00b4, # ACUTE ACCENT
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x02dd, # DOUBLE ACUTE ACCENT
+ 0x00f2: 0x02db, # OGONEK
+ 0x00f3: 0x02c7, # CARON
+ 0x00f4: 0x02d8, # BREVE
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x00b8, # CEDILLA
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x00a8, # DIAERESIS
+ 0x00fa: 0x02d9, # DOT ABOVE
+ 0x00fb: 0x0171, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
+ 0x00fc: 0x0158, # LATIN CAPITAL LETTER R WITH CARON
+ 0x00fd: 0x0159, # LATIN SMALL LETTER R WITH CARON
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\u016f' # 0x0085 -> LATIN SMALL LETTER U WITH RING ABOVE
+ '\u0107' # 0x0086 -> LATIN SMALL LETTER C WITH ACUTE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\u0150' # 0x008a -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+ '\u0151' # 0x008b -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\u0106' # 0x008f -> LATIN CAPITAL LETTER C WITH ACUTE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\u0139' # 0x0091 -> LATIN CAPITAL LETTER L WITH ACUTE
+ '\u013a' # 0x0092 -> LATIN SMALL LETTER L WITH ACUTE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\u013d' # 0x0095 -> LATIN CAPITAL LETTER L WITH CARON
+ '\u013e' # 0x0096 -> LATIN SMALL LETTER L WITH CARON
+ '\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE
+ '\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\u0164' # 0x009b -> LATIN CAPITAL LETTER T WITH CARON
+ '\u0165' # 0x009c -> LATIN SMALL LETTER T WITH CARON
+ '\u0141' # 0x009d -> LATIN CAPITAL LETTER L WITH STROKE
+ '\xd7' # 0x009e -> MULTIPLICATION SIGN
+ '\u010d' # 0x009f -> LATIN SMALL LETTER C WITH CARON
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\u0104' # 0x00a4 -> LATIN CAPITAL LETTER A WITH OGONEK
+ '\u0105' # 0x00a5 -> LATIN SMALL LETTER A WITH OGONEK
+ '\u017d' # 0x00a6 -> LATIN CAPITAL LETTER Z WITH CARON
+ '\u017e' # 0x00a7 -> LATIN SMALL LETTER Z WITH CARON
+ '\u0118' # 0x00a8 -> LATIN CAPITAL LETTER E WITH OGONEK
+ '\u0119' # 0x00a9 -> LATIN SMALL LETTER E WITH OGONEK
+ '\xac' # 0x00aa -> NOT SIGN
+ '\u017a' # 0x00ab -> LATIN SMALL LETTER Z WITH ACUTE
+ '\u010c' # 0x00ac -> LATIN CAPITAL LETTER C WITH CARON
+ '\u015f' # 0x00ad -> LATIN SMALL LETTER S WITH CEDILLA
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\u011a' # 0x00b7 -> LATIN CAPITAL LETTER E WITH CARON
+ '\u015e' # 0x00b8 -> LATIN CAPITAL LETTER S WITH CEDILLA
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u017b' # 0x00bd -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ '\u017c' # 0x00be -> LATIN SMALL LETTER Z WITH DOT ABOVE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u0102' # 0x00c6 -> LATIN CAPITAL LETTER A WITH BREVE
+ '\u0103' # 0x00c7 -> LATIN SMALL LETTER A WITH BREVE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0x00cf -> CURRENCY SIGN
+ '\u0111' # 0x00d0 -> LATIN SMALL LETTER D WITH STROKE
+ '\u0110' # 0x00d1 -> LATIN CAPITAL LETTER D WITH STROKE
+ '\u010e' # 0x00d2 -> LATIN CAPITAL LETTER D WITH CARON
+ '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\u010f' # 0x00d4 -> LATIN SMALL LETTER D WITH CARON
+ '\u0147' # 0x00d5 -> LATIN CAPITAL LETTER N WITH CARON
+ '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\u011b' # 0x00d8 -> LATIN SMALL LETTER E WITH CARON
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u0162' # 0x00dd -> LATIN CAPITAL LETTER T WITH CEDILLA
+ '\u016e' # 0x00de -> LATIN CAPITAL LETTER U WITH RING ABOVE
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE
+ '\u0144' # 0x00e4 -> LATIN SMALL LETTER N WITH ACUTE
+ '\u0148' # 0x00e5 -> LATIN SMALL LETTER N WITH CARON
+ '\u0160' # 0x00e6 -> LATIN CAPITAL LETTER S WITH CARON
+ '\u0161' # 0x00e7 -> LATIN SMALL LETTER S WITH CARON
+ '\u0154' # 0x00e8 -> LATIN CAPITAL LETTER R WITH ACUTE
+ '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\u0155' # 0x00ea -> LATIN SMALL LETTER R WITH ACUTE
+ '\u0170' # 0x00eb -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+ '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\u0163' # 0x00ee -> LATIN SMALL LETTER T WITH CEDILLA
+ '\xb4' # 0x00ef -> ACUTE ACCENT
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\u02dd' # 0x00f1 -> DOUBLE ACUTE ACCENT
+ '\u02db' # 0x00f2 -> OGONEK
+ '\u02c7' # 0x00f3 -> CARON
+ '\u02d8' # 0x00f4 -> BREVE
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\xb8' # 0x00f7 -> CEDILLA
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\xa8' # 0x00f9 -> DIAERESIS
+ '\u02d9' # 0x00fa -> DOT ABOVE
+ '\u0171' # 0x00fb -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
+ '\u0158' # 0x00fc -> LATIN CAPITAL LETTER R WITH CARON
+ '\u0159' # 0x00fd -> LATIN SMALL LETTER R WITH CARON
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a4: 0x00cf, # CURRENCY SIGN
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a8: 0x00f9, # DIAERESIS
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b4: 0x00ef, # ACUTE ACCENT
+ 0x00b8: 0x00f7, # CEDILLA
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d7: 0x009e, # MULTIPLICATION SIGN
+ 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x0102: 0x00c6, # LATIN CAPITAL LETTER A WITH BREVE
+ 0x0103: 0x00c7, # LATIN SMALL LETTER A WITH BREVE
+ 0x0104: 0x00a4, # LATIN CAPITAL LETTER A WITH OGONEK
+ 0x0105: 0x00a5, # LATIN SMALL LETTER A WITH OGONEK
+ 0x0106: 0x008f, # LATIN CAPITAL LETTER C WITH ACUTE
+ 0x0107: 0x0086, # LATIN SMALL LETTER C WITH ACUTE
+ 0x010c: 0x00ac, # LATIN CAPITAL LETTER C WITH CARON
+ 0x010d: 0x009f, # LATIN SMALL LETTER C WITH CARON
+ 0x010e: 0x00d2, # LATIN CAPITAL LETTER D WITH CARON
+ 0x010f: 0x00d4, # LATIN SMALL LETTER D WITH CARON
+ 0x0110: 0x00d1, # LATIN CAPITAL LETTER D WITH STROKE
+ 0x0111: 0x00d0, # LATIN SMALL LETTER D WITH STROKE
+ 0x0118: 0x00a8, # LATIN CAPITAL LETTER E WITH OGONEK
+ 0x0119: 0x00a9, # LATIN SMALL LETTER E WITH OGONEK
+ 0x011a: 0x00b7, # LATIN CAPITAL LETTER E WITH CARON
+ 0x011b: 0x00d8, # LATIN SMALL LETTER E WITH CARON
+ 0x0139: 0x0091, # LATIN CAPITAL LETTER L WITH ACUTE
+ 0x013a: 0x0092, # LATIN SMALL LETTER L WITH ACUTE
+ 0x013d: 0x0095, # LATIN CAPITAL LETTER L WITH CARON
+ 0x013e: 0x0096, # LATIN SMALL LETTER L WITH CARON
+ 0x0141: 0x009d, # LATIN CAPITAL LETTER L WITH STROKE
+ 0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE
+ 0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE
+ 0x0144: 0x00e4, # LATIN SMALL LETTER N WITH ACUTE
+ 0x0147: 0x00d5, # LATIN CAPITAL LETTER N WITH CARON
+ 0x0148: 0x00e5, # LATIN SMALL LETTER N WITH CARON
+ 0x0150: 0x008a, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+ 0x0151: 0x008b, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
+ 0x0154: 0x00e8, # LATIN CAPITAL LETTER R WITH ACUTE
+ 0x0155: 0x00ea, # LATIN SMALL LETTER R WITH ACUTE
+ 0x0158: 0x00fc, # LATIN CAPITAL LETTER R WITH CARON
+ 0x0159: 0x00fd, # LATIN SMALL LETTER R WITH CARON
+ 0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE
+ 0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE
+ 0x015e: 0x00b8, # LATIN CAPITAL LETTER S WITH CEDILLA
+ 0x015f: 0x00ad, # LATIN SMALL LETTER S WITH CEDILLA
+ 0x0160: 0x00e6, # LATIN CAPITAL LETTER S WITH CARON
+ 0x0161: 0x00e7, # LATIN SMALL LETTER S WITH CARON
+ 0x0162: 0x00dd, # LATIN CAPITAL LETTER T WITH CEDILLA
+ 0x0163: 0x00ee, # LATIN SMALL LETTER T WITH CEDILLA
+ 0x0164: 0x009b, # LATIN CAPITAL LETTER T WITH CARON
+ 0x0165: 0x009c, # LATIN SMALL LETTER T WITH CARON
+ 0x016e: 0x00de, # LATIN CAPITAL LETTER U WITH RING ABOVE
+ 0x016f: 0x0085, # LATIN SMALL LETTER U WITH RING ABOVE
+ 0x0170: 0x00eb, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+ 0x0171: 0x00fb, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
+ 0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE
+ 0x017a: 0x00ab, # LATIN SMALL LETTER Z WITH ACUTE
+ 0x017b: 0x00bd, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
+ 0x017c: 0x00be, # LATIN SMALL LETTER Z WITH DOT ABOVE
+ 0x017d: 0x00a6, # LATIN CAPITAL LETTER Z WITH CARON
+ 0x017e: 0x00a7, # LATIN SMALL LETTER Z WITH CARON
+ 0x02c7: 0x00f3, # CARON
+ 0x02d8: 0x00f4, # BREVE
+ 0x02d9: 0x00fa, # DOT ABOVE
+ 0x02db: 0x00f2, # OGONEK
+ 0x02dd: 0x00f1, # DOUBLE ACUTE ACCENT
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp855.py b/Lib/encodings/cp855.py
new file mode 100644
index 0000000..4fe9210
--- /dev/null
+++ b/Lib/encodings/cp855.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP855.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp855',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x0452, # CYRILLIC SMALL LETTER DJE
+ 0x0081: 0x0402, # CYRILLIC CAPITAL LETTER DJE
+ 0x0082: 0x0453, # CYRILLIC SMALL LETTER GJE
+ 0x0083: 0x0403, # CYRILLIC CAPITAL LETTER GJE
+ 0x0084: 0x0451, # CYRILLIC SMALL LETTER IO
+ 0x0085: 0x0401, # CYRILLIC CAPITAL LETTER IO
+ 0x0086: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE
+ 0x0087: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ 0x0088: 0x0455, # CYRILLIC SMALL LETTER DZE
+ 0x0089: 0x0405, # CYRILLIC CAPITAL LETTER DZE
+ 0x008a: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x008b: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x008c: 0x0457, # CYRILLIC SMALL LETTER YI
+ 0x008d: 0x0407, # CYRILLIC CAPITAL LETTER YI
+ 0x008e: 0x0458, # CYRILLIC SMALL LETTER JE
+ 0x008f: 0x0408, # CYRILLIC CAPITAL LETTER JE
+ 0x0090: 0x0459, # CYRILLIC SMALL LETTER LJE
+ 0x0091: 0x0409, # CYRILLIC CAPITAL LETTER LJE
+ 0x0092: 0x045a, # CYRILLIC SMALL LETTER NJE
+ 0x0093: 0x040a, # CYRILLIC CAPITAL LETTER NJE
+ 0x0094: 0x045b, # CYRILLIC SMALL LETTER TSHE
+ 0x0095: 0x040b, # CYRILLIC CAPITAL LETTER TSHE
+ 0x0096: 0x045c, # CYRILLIC SMALL LETTER KJE
+ 0x0097: 0x040c, # CYRILLIC CAPITAL LETTER KJE
+ 0x0098: 0x045e, # CYRILLIC SMALL LETTER SHORT U
+ 0x0099: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U
+ 0x009a: 0x045f, # CYRILLIC SMALL LETTER DZHE
+ 0x009b: 0x040f, # CYRILLIC CAPITAL LETTER DZHE
+ 0x009c: 0x044e, # CYRILLIC SMALL LETTER YU
+ 0x009d: 0x042e, # CYRILLIC CAPITAL LETTER YU
+ 0x009e: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN
+ 0x009f: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN
+ 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A
+ 0x00a1: 0x0410, # CYRILLIC CAPITAL LETTER A
+ 0x00a2: 0x0431, # CYRILLIC SMALL LETTER BE
+ 0x00a3: 0x0411, # CYRILLIC CAPITAL LETTER BE
+ 0x00a4: 0x0446, # CYRILLIC SMALL LETTER TSE
+ 0x00a5: 0x0426, # CYRILLIC CAPITAL LETTER TSE
+ 0x00a6: 0x0434, # CYRILLIC SMALL LETTER DE
+ 0x00a7: 0x0414, # CYRILLIC CAPITAL LETTER DE
+ 0x00a8: 0x0435, # CYRILLIC SMALL LETTER IE
+ 0x00a9: 0x0415, # CYRILLIC CAPITAL LETTER IE
+ 0x00aa: 0x0444, # CYRILLIC SMALL LETTER EF
+ 0x00ab: 0x0424, # CYRILLIC CAPITAL LETTER EF
+ 0x00ac: 0x0433, # CYRILLIC SMALL LETTER GHE
+ 0x00ad: 0x0413, # CYRILLIC CAPITAL LETTER GHE
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x0445, # CYRILLIC SMALL LETTER HA
+ 0x00b6: 0x0425, # CYRILLIC CAPITAL LETTER HA
+ 0x00b7: 0x0438, # CYRILLIC SMALL LETTER I
+ 0x00b8: 0x0418, # CYRILLIC CAPITAL LETTER I
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x0439, # CYRILLIC SMALL LETTER SHORT I
+ 0x00be: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x043a, # CYRILLIC SMALL LETTER KA
+ 0x00c7: 0x041a, # CYRILLIC CAPITAL LETTER KA
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x00a4, # CURRENCY SIGN
+ 0x00d0: 0x043b, # CYRILLIC SMALL LETTER EL
+ 0x00d1: 0x041b, # CYRILLIC CAPITAL LETTER EL
+ 0x00d2: 0x043c, # CYRILLIC SMALL LETTER EM
+ 0x00d3: 0x041c, # CYRILLIC CAPITAL LETTER EM
+ 0x00d4: 0x043d, # CYRILLIC SMALL LETTER EN
+ 0x00d5: 0x041d, # CYRILLIC CAPITAL LETTER EN
+ 0x00d6: 0x043e, # CYRILLIC SMALL LETTER O
+ 0x00d7: 0x041e, # CYRILLIC CAPITAL LETTER O
+ 0x00d8: 0x043f, # CYRILLIC SMALL LETTER PE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x041f, # CYRILLIC CAPITAL LETTER PE
+ 0x00de: 0x044f, # CYRILLIC SMALL LETTER YA
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x042f, # CYRILLIC CAPITAL LETTER YA
+ 0x00e1: 0x0440, # CYRILLIC SMALL LETTER ER
+ 0x00e2: 0x0420, # CYRILLIC CAPITAL LETTER ER
+ 0x00e3: 0x0441, # CYRILLIC SMALL LETTER ES
+ 0x00e4: 0x0421, # CYRILLIC CAPITAL LETTER ES
+ 0x00e5: 0x0442, # CYRILLIC SMALL LETTER TE
+ 0x00e6: 0x0422, # CYRILLIC CAPITAL LETTER TE
+ 0x00e7: 0x0443, # CYRILLIC SMALL LETTER U
+ 0x00e8: 0x0423, # CYRILLIC CAPITAL LETTER U
+ 0x00e9: 0x0436, # CYRILLIC SMALL LETTER ZHE
+ 0x00ea: 0x0416, # CYRILLIC CAPITAL LETTER ZHE
+ 0x00eb: 0x0432, # CYRILLIC SMALL LETTER VE
+ 0x00ec: 0x0412, # CYRILLIC CAPITAL LETTER VE
+ 0x00ed: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN
+ 0x00ee: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN
+ 0x00ef: 0x2116, # NUMERO SIGN
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x044b, # CYRILLIC SMALL LETTER YERU
+ 0x00f2: 0x042b, # CYRILLIC CAPITAL LETTER YERU
+ 0x00f3: 0x0437, # CYRILLIC SMALL LETTER ZE
+ 0x00f4: 0x0417, # CYRILLIC CAPITAL LETTER ZE
+ 0x00f5: 0x0448, # CYRILLIC SMALL LETTER SHA
+ 0x00f6: 0x0428, # CYRILLIC CAPITAL LETTER SHA
+ 0x00f7: 0x044d, # CYRILLIC SMALL LETTER E
+ 0x00f8: 0x042d, # CYRILLIC CAPITAL LETTER E
+ 0x00f9: 0x0449, # CYRILLIC SMALL LETTER SHCHA
+ 0x00fa: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA
+ 0x00fb: 0x0447, # CYRILLIC SMALL LETTER CHE
+ 0x00fc: 0x0427, # CYRILLIC CAPITAL LETTER CHE
+ 0x00fd: 0x00a7, # SECTION SIGN
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\u0452' # 0x0080 -> CYRILLIC SMALL LETTER DJE
+ '\u0402' # 0x0081 -> CYRILLIC CAPITAL LETTER DJE
+ '\u0453' # 0x0082 -> CYRILLIC SMALL LETTER GJE
+ '\u0403' # 0x0083 -> CYRILLIC CAPITAL LETTER GJE
+ '\u0451' # 0x0084 -> CYRILLIC SMALL LETTER IO
+ '\u0401' # 0x0085 -> CYRILLIC CAPITAL LETTER IO
+ '\u0454' # 0x0086 -> CYRILLIC SMALL LETTER UKRAINIAN IE
+ '\u0404' # 0x0087 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ '\u0455' # 0x0088 -> CYRILLIC SMALL LETTER DZE
+ '\u0405' # 0x0089 -> CYRILLIC CAPITAL LETTER DZE
+ '\u0456' # 0x008a -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ '\u0406' # 0x008b -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ '\u0457' # 0x008c -> CYRILLIC SMALL LETTER YI
+ '\u0407' # 0x008d -> CYRILLIC CAPITAL LETTER YI
+ '\u0458' # 0x008e -> CYRILLIC SMALL LETTER JE
+ '\u0408' # 0x008f -> CYRILLIC CAPITAL LETTER JE
+ '\u0459' # 0x0090 -> CYRILLIC SMALL LETTER LJE
+ '\u0409' # 0x0091 -> CYRILLIC CAPITAL LETTER LJE
+ '\u045a' # 0x0092 -> CYRILLIC SMALL LETTER NJE
+ '\u040a' # 0x0093 -> CYRILLIC CAPITAL LETTER NJE
+ '\u045b' # 0x0094 -> CYRILLIC SMALL LETTER TSHE
+ '\u040b' # 0x0095 -> CYRILLIC CAPITAL LETTER TSHE
+ '\u045c' # 0x0096 -> CYRILLIC SMALL LETTER KJE
+ '\u040c' # 0x0097 -> CYRILLIC CAPITAL LETTER KJE
+ '\u045e' # 0x0098 -> CYRILLIC SMALL LETTER SHORT U
+ '\u040e' # 0x0099 -> CYRILLIC CAPITAL LETTER SHORT U
+ '\u045f' # 0x009a -> CYRILLIC SMALL LETTER DZHE
+ '\u040f' # 0x009b -> CYRILLIC CAPITAL LETTER DZHE
+ '\u044e' # 0x009c -> CYRILLIC SMALL LETTER YU
+ '\u042e' # 0x009d -> CYRILLIC CAPITAL LETTER YU
+ '\u044a' # 0x009e -> CYRILLIC SMALL LETTER HARD SIGN
+ '\u042a' # 0x009f -> CYRILLIC CAPITAL LETTER HARD SIGN
+ '\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A
+ '\u0410' # 0x00a1 -> CYRILLIC CAPITAL LETTER A
+ '\u0431' # 0x00a2 -> CYRILLIC SMALL LETTER BE
+ '\u0411' # 0x00a3 -> CYRILLIC CAPITAL LETTER BE
+ '\u0446' # 0x00a4 -> CYRILLIC SMALL LETTER TSE
+ '\u0426' # 0x00a5 -> CYRILLIC CAPITAL LETTER TSE
+ '\u0434' # 0x00a6 -> CYRILLIC SMALL LETTER DE
+ '\u0414' # 0x00a7 -> CYRILLIC CAPITAL LETTER DE
+ '\u0435' # 0x00a8 -> CYRILLIC SMALL LETTER IE
+ '\u0415' # 0x00a9 -> CYRILLIC CAPITAL LETTER IE
+ '\u0444' # 0x00aa -> CYRILLIC SMALL LETTER EF
+ '\u0424' # 0x00ab -> CYRILLIC CAPITAL LETTER EF
+ '\u0433' # 0x00ac -> CYRILLIC SMALL LETTER GHE
+ '\u0413' # 0x00ad -> CYRILLIC CAPITAL LETTER GHE
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u0445' # 0x00b5 -> CYRILLIC SMALL LETTER HA
+ '\u0425' # 0x00b6 -> CYRILLIC CAPITAL LETTER HA
+ '\u0438' # 0x00b7 -> CYRILLIC SMALL LETTER I
+ '\u0418' # 0x00b8 -> CYRILLIC CAPITAL LETTER I
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u0439' # 0x00bd -> CYRILLIC SMALL LETTER SHORT I
+ '\u0419' # 0x00be -> CYRILLIC CAPITAL LETTER SHORT I
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u043a' # 0x00c6 -> CYRILLIC SMALL LETTER KA
+ '\u041a' # 0x00c7 -> CYRILLIC CAPITAL LETTER KA
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0x00cf -> CURRENCY SIGN
+ '\u043b' # 0x00d0 -> CYRILLIC SMALL LETTER EL
+ '\u041b' # 0x00d1 -> CYRILLIC CAPITAL LETTER EL
+ '\u043c' # 0x00d2 -> CYRILLIC SMALL LETTER EM
+ '\u041c' # 0x00d3 -> CYRILLIC CAPITAL LETTER EM
+ '\u043d' # 0x00d4 -> CYRILLIC SMALL LETTER EN
+ '\u041d' # 0x00d5 -> CYRILLIC CAPITAL LETTER EN
+ '\u043e' # 0x00d6 -> CYRILLIC SMALL LETTER O
+ '\u041e' # 0x00d7 -> CYRILLIC CAPITAL LETTER O
+ '\u043f' # 0x00d8 -> CYRILLIC SMALL LETTER PE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u041f' # 0x00dd -> CYRILLIC CAPITAL LETTER PE
+ '\u044f' # 0x00de -> CYRILLIC SMALL LETTER YA
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u042f' # 0x00e0 -> CYRILLIC CAPITAL LETTER YA
+ '\u0440' # 0x00e1 -> CYRILLIC SMALL LETTER ER
+ '\u0420' # 0x00e2 -> CYRILLIC CAPITAL LETTER ER
+ '\u0441' # 0x00e3 -> CYRILLIC SMALL LETTER ES
+ '\u0421' # 0x00e4 -> CYRILLIC CAPITAL LETTER ES
+ '\u0442' # 0x00e5 -> CYRILLIC SMALL LETTER TE
+ '\u0422' # 0x00e6 -> CYRILLIC CAPITAL LETTER TE
+ '\u0443' # 0x00e7 -> CYRILLIC SMALL LETTER U
+ '\u0423' # 0x00e8 -> CYRILLIC CAPITAL LETTER U
+ '\u0436' # 0x00e9 -> CYRILLIC SMALL LETTER ZHE
+ '\u0416' # 0x00ea -> CYRILLIC CAPITAL LETTER ZHE
+ '\u0432' # 0x00eb -> CYRILLIC SMALL LETTER VE
+ '\u0412' # 0x00ec -> CYRILLIC CAPITAL LETTER VE
+ '\u044c' # 0x00ed -> CYRILLIC SMALL LETTER SOFT SIGN
+ '\u042c' # 0x00ee -> CYRILLIC CAPITAL LETTER SOFT SIGN
+ '\u2116' # 0x00ef -> NUMERO SIGN
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\u044b' # 0x00f1 -> CYRILLIC SMALL LETTER YERU
+ '\u042b' # 0x00f2 -> CYRILLIC CAPITAL LETTER YERU
+ '\u0437' # 0x00f3 -> CYRILLIC SMALL LETTER ZE
+ '\u0417' # 0x00f4 -> CYRILLIC CAPITAL LETTER ZE
+ '\u0448' # 0x00f5 -> CYRILLIC SMALL LETTER SHA
+ '\u0428' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHA
+ '\u044d' # 0x00f7 -> CYRILLIC SMALL LETTER E
+ '\u042d' # 0x00f8 -> CYRILLIC CAPITAL LETTER E
+ '\u0449' # 0x00f9 -> CYRILLIC SMALL LETTER SHCHA
+ '\u0429' # 0x00fa -> CYRILLIC CAPITAL LETTER SHCHA
+ '\u0447' # 0x00fb -> CYRILLIC SMALL LETTER CHE
+ '\u0427' # 0x00fc -> CYRILLIC CAPITAL LETTER CHE
+ '\xa7' # 0x00fd -> SECTION SIGN
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a4: 0x00cf, # CURRENCY SIGN
+ 0x00a7: 0x00fd, # SECTION SIGN
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x0401: 0x0085, # CYRILLIC CAPITAL LETTER IO
+ 0x0402: 0x0081, # CYRILLIC CAPITAL LETTER DJE
+ 0x0403: 0x0083, # CYRILLIC CAPITAL LETTER GJE
+ 0x0404: 0x0087, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ 0x0405: 0x0089, # CYRILLIC CAPITAL LETTER DZE
+ 0x0406: 0x008b, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x0407: 0x008d, # CYRILLIC CAPITAL LETTER YI
+ 0x0408: 0x008f, # CYRILLIC CAPITAL LETTER JE
+ 0x0409: 0x0091, # CYRILLIC CAPITAL LETTER LJE
+ 0x040a: 0x0093, # CYRILLIC CAPITAL LETTER NJE
+ 0x040b: 0x0095, # CYRILLIC CAPITAL LETTER TSHE
+ 0x040c: 0x0097, # CYRILLIC CAPITAL LETTER KJE
+ 0x040e: 0x0099, # CYRILLIC CAPITAL LETTER SHORT U
+ 0x040f: 0x009b, # CYRILLIC CAPITAL LETTER DZHE
+ 0x0410: 0x00a1, # CYRILLIC CAPITAL LETTER A
+ 0x0411: 0x00a3, # CYRILLIC CAPITAL LETTER BE
+ 0x0412: 0x00ec, # CYRILLIC CAPITAL LETTER VE
+ 0x0413: 0x00ad, # CYRILLIC CAPITAL LETTER GHE
+ 0x0414: 0x00a7, # CYRILLIC CAPITAL LETTER DE
+ 0x0415: 0x00a9, # CYRILLIC CAPITAL LETTER IE
+ 0x0416: 0x00ea, # CYRILLIC CAPITAL LETTER ZHE
+ 0x0417: 0x00f4, # CYRILLIC CAPITAL LETTER ZE
+ 0x0418: 0x00b8, # CYRILLIC CAPITAL LETTER I
+ 0x0419: 0x00be, # CYRILLIC CAPITAL LETTER SHORT I
+ 0x041a: 0x00c7, # CYRILLIC CAPITAL LETTER KA
+ 0x041b: 0x00d1, # CYRILLIC CAPITAL LETTER EL
+ 0x041c: 0x00d3, # CYRILLIC CAPITAL LETTER EM
+ 0x041d: 0x00d5, # CYRILLIC CAPITAL LETTER EN
+ 0x041e: 0x00d7, # CYRILLIC CAPITAL LETTER O
+ 0x041f: 0x00dd, # CYRILLIC CAPITAL LETTER PE
+ 0x0420: 0x00e2, # CYRILLIC CAPITAL LETTER ER
+ 0x0421: 0x00e4, # CYRILLIC CAPITAL LETTER ES
+ 0x0422: 0x00e6, # CYRILLIC CAPITAL LETTER TE
+ 0x0423: 0x00e8, # CYRILLIC CAPITAL LETTER U
+ 0x0424: 0x00ab, # CYRILLIC CAPITAL LETTER EF
+ 0x0425: 0x00b6, # CYRILLIC CAPITAL LETTER HA
+ 0x0426: 0x00a5, # CYRILLIC CAPITAL LETTER TSE
+ 0x0427: 0x00fc, # CYRILLIC CAPITAL LETTER CHE
+ 0x0428: 0x00f6, # CYRILLIC CAPITAL LETTER SHA
+ 0x0429: 0x00fa, # CYRILLIC CAPITAL LETTER SHCHA
+ 0x042a: 0x009f, # CYRILLIC CAPITAL LETTER HARD SIGN
+ 0x042b: 0x00f2, # CYRILLIC CAPITAL LETTER YERU
+ 0x042c: 0x00ee, # CYRILLIC CAPITAL LETTER SOFT SIGN
+ 0x042d: 0x00f8, # CYRILLIC CAPITAL LETTER E
+ 0x042e: 0x009d, # CYRILLIC CAPITAL LETTER YU
+ 0x042f: 0x00e0, # CYRILLIC CAPITAL LETTER YA
+ 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A
+ 0x0431: 0x00a2, # CYRILLIC SMALL LETTER BE
+ 0x0432: 0x00eb, # CYRILLIC SMALL LETTER VE
+ 0x0433: 0x00ac, # CYRILLIC SMALL LETTER GHE
+ 0x0434: 0x00a6, # CYRILLIC SMALL LETTER DE
+ 0x0435: 0x00a8, # CYRILLIC SMALL LETTER IE
+ 0x0436: 0x00e9, # CYRILLIC SMALL LETTER ZHE
+ 0x0437: 0x00f3, # CYRILLIC SMALL LETTER ZE
+ 0x0438: 0x00b7, # CYRILLIC SMALL LETTER I
+ 0x0439: 0x00bd, # CYRILLIC SMALL LETTER SHORT I
+ 0x043a: 0x00c6, # CYRILLIC SMALL LETTER KA
+ 0x043b: 0x00d0, # CYRILLIC SMALL LETTER EL
+ 0x043c: 0x00d2, # CYRILLIC SMALL LETTER EM
+ 0x043d: 0x00d4, # CYRILLIC SMALL LETTER EN
+ 0x043e: 0x00d6, # CYRILLIC SMALL LETTER O
+ 0x043f: 0x00d8, # CYRILLIC SMALL LETTER PE
+ 0x0440: 0x00e1, # CYRILLIC SMALL LETTER ER
+ 0x0441: 0x00e3, # CYRILLIC SMALL LETTER ES
+ 0x0442: 0x00e5, # CYRILLIC SMALL LETTER TE
+ 0x0443: 0x00e7, # CYRILLIC SMALL LETTER U
+ 0x0444: 0x00aa, # CYRILLIC SMALL LETTER EF
+ 0x0445: 0x00b5, # CYRILLIC SMALL LETTER HA
+ 0x0446: 0x00a4, # CYRILLIC SMALL LETTER TSE
+ 0x0447: 0x00fb, # CYRILLIC SMALL LETTER CHE
+ 0x0448: 0x00f5, # CYRILLIC SMALL LETTER SHA
+ 0x0449: 0x00f9, # CYRILLIC SMALL LETTER SHCHA
+ 0x044a: 0x009e, # CYRILLIC SMALL LETTER HARD SIGN
+ 0x044b: 0x00f1, # CYRILLIC SMALL LETTER YERU
+ 0x044c: 0x00ed, # CYRILLIC SMALL LETTER SOFT SIGN
+ 0x044d: 0x00f7, # CYRILLIC SMALL LETTER E
+ 0x044e: 0x009c, # CYRILLIC SMALL LETTER YU
+ 0x044f: 0x00de, # CYRILLIC SMALL LETTER YA
+ 0x0451: 0x0084, # CYRILLIC SMALL LETTER IO
+ 0x0452: 0x0080, # CYRILLIC SMALL LETTER DJE
+ 0x0453: 0x0082, # CYRILLIC SMALL LETTER GJE
+ 0x0454: 0x0086, # CYRILLIC SMALL LETTER UKRAINIAN IE
+ 0x0455: 0x0088, # CYRILLIC SMALL LETTER DZE
+ 0x0456: 0x008a, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+ 0x0457: 0x008c, # CYRILLIC SMALL LETTER YI
+ 0x0458: 0x008e, # CYRILLIC SMALL LETTER JE
+ 0x0459: 0x0090, # CYRILLIC SMALL LETTER LJE
+ 0x045a: 0x0092, # CYRILLIC SMALL LETTER NJE
+ 0x045b: 0x0094, # CYRILLIC SMALL LETTER TSHE
+ 0x045c: 0x0096, # CYRILLIC SMALL LETTER KJE
+ 0x045e: 0x0098, # CYRILLIC SMALL LETTER SHORT U
+ 0x045f: 0x009a, # CYRILLIC SMALL LETTER DZHE
+ 0x2116: 0x00ef, # NUMERO SIGN
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp856.py b/Lib/encodings/cp856.py
new file mode 100644
index 0000000..cacbfb2
--- /dev/null
+++ b/Lib/encodings/cp856.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp856 generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp856',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u05d0' # 0x80 -> HEBREW LETTER ALEF
+ '\u05d1' # 0x81 -> HEBREW LETTER BET
+ '\u05d2' # 0x82 -> HEBREW LETTER GIMEL
+ '\u05d3' # 0x83 -> HEBREW LETTER DALET
+ '\u05d4' # 0x84 -> HEBREW LETTER HE
+ '\u05d5' # 0x85 -> HEBREW LETTER VAV
+ '\u05d6' # 0x86 -> HEBREW LETTER ZAYIN
+ '\u05d7' # 0x87 -> HEBREW LETTER HET
+ '\u05d8' # 0x88 -> HEBREW LETTER TET
+ '\u05d9' # 0x89 -> HEBREW LETTER YOD
+ '\u05da' # 0x8A -> HEBREW LETTER FINAL KAF
+ '\u05db' # 0x8B -> HEBREW LETTER KAF
+ '\u05dc' # 0x8C -> HEBREW LETTER LAMED
+ '\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM
+ '\u05de' # 0x8E -> HEBREW LETTER MEM
+ '\u05df' # 0x8F -> HEBREW LETTER FINAL NUN
+ '\u05e0' # 0x90 -> HEBREW LETTER NUN
+ '\u05e1' # 0x91 -> HEBREW LETTER SAMEKH
+ '\u05e2' # 0x92 -> HEBREW LETTER AYIN
+ '\u05e3' # 0x93 -> HEBREW LETTER FINAL PE
+ '\u05e4' # 0x94 -> HEBREW LETTER PE
+ '\u05e5' # 0x95 -> HEBREW LETTER FINAL TSADI
+ '\u05e6' # 0x96 -> HEBREW LETTER TSADI
+ '\u05e7' # 0x97 -> HEBREW LETTER QOF
+ '\u05e8' # 0x98 -> HEBREW LETTER RESH
+ '\u05e9' # 0x99 -> HEBREW LETTER SHIN
+ '\u05ea' # 0x9A -> HEBREW LETTER TAV
+ '\ufffe' # 0x9B -> UNDEFINED
+ '\xa3' # 0x9C -> POUND SIGN
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\xd7' # 0x9E -> MULTIPLICATION SIGN
+ '\ufffe' # 0x9F -> UNDEFINED
+ '\ufffe' # 0xA0 -> UNDEFINED
+ '\ufffe' # 0xA1 -> UNDEFINED
+ '\ufffe' # 0xA2 -> UNDEFINED
+ '\ufffe' # 0xA3 -> UNDEFINED
+ '\ufffe' # 0xA4 -> UNDEFINED
+ '\ufffe' # 0xA5 -> UNDEFINED
+ '\ufffe' # 0xA6 -> UNDEFINED
+ '\ufffe' # 0xA7 -> UNDEFINED
+ '\ufffe' # 0xA8 -> UNDEFINED
+ '\xae' # 0xA9 -> REGISTERED SIGN
+ '\xac' # 0xAA -> NOT SIGN
+ '\xbd' # 0xAB -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER
+ '\ufffe' # 0xAD -> UNDEFINED
+ '\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0xB0 -> LIGHT SHADE
+ '\u2592' # 0xB1 -> MEDIUM SHADE
+ '\u2593' # 0xB2 -> DARK SHADE
+ '\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\ufffe' # 0xB5 -> UNDEFINED
+ '\ufffe' # 0xB6 -> UNDEFINED
+ '\ufffe' # 0xB7 -> UNDEFINED
+ '\xa9' # 0xB8 -> COPYRIGHT SIGN
+ '\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\xa2' # 0xBD -> CENT SIGN
+ '\xa5' # 0xBE -> YEN SIGN
+ '\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\ufffe' # 0xC6 -> UNDEFINED
+ '\ufffe' # 0xC7 -> UNDEFINED
+ '\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0xCF -> CURRENCY SIGN
+ '\ufffe' # 0xD0 -> UNDEFINED
+ '\ufffe' # 0xD1 -> UNDEFINED
+ '\ufffe' # 0xD2 -> UNDEFINED
+ '\ufffe' # 0xD3 -> UNDEFINEDS
+ '\ufffe' # 0xD4 -> UNDEFINED
+ '\ufffe' # 0xD5 -> UNDEFINED
+ '\ufffe' # 0xD6 -> UNDEFINEDE
+ '\ufffe' # 0xD7 -> UNDEFINED
+ '\ufffe' # 0xD8 -> UNDEFINED
+ '\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0xDB -> FULL BLOCK
+ '\u2584' # 0xDC -> LOWER HALF BLOCK
+ '\xa6' # 0xDD -> BROKEN BAR
+ '\ufffe' # 0xDE -> UNDEFINED
+ '\u2580' # 0xDF -> UPPER HALF BLOCK
+ '\ufffe' # 0xE0 -> UNDEFINED
+ '\ufffe' # 0xE1 -> UNDEFINED
+ '\ufffe' # 0xE2 -> UNDEFINED
+ '\ufffe' # 0xE3 -> UNDEFINED
+ '\ufffe' # 0xE4 -> UNDEFINED
+ '\ufffe' # 0xE5 -> UNDEFINED
+ '\xb5' # 0xE6 -> MICRO SIGN
+ '\ufffe' # 0xE7 -> UNDEFINED
+ '\ufffe' # 0xE8 -> UNDEFINED
+ '\ufffe' # 0xE9 -> UNDEFINED
+ '\ufffe' # 0xEA -> UNDEFINED
+ '\ufffe' # 0xEB -> UNDEFINED
+ '\ufffe' # 0xEC -> UNDEFINED
+ '\ufffe' # 0xED -> UNDEFINED
+ '\xaf' # 0xEE -> MACRON
+ '\xb4' # 0xEF -> ACUTE ACCENT
+ '\xad' # 0xF0 -> SOFT HYPHEN
+ '\xb1' # 0xF1 -> PLUS-MINUS SIGN
+ '\u2017' # 0xF2 -> DOUBLE LOW LINE
+ '\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS
+ '\xb6' # 0xF4 -> PILCROW SIGN
+ '\xa7' # 0xF5 -> SECTION SIGN
+ '\xf7' # 0xF6 -> DIVISION SIGN
+ '\xb8' # 0xF7 -> CEDILLA
+ '\xb0' # 0xF8 -> DEGREE SIGN
+ '\xa8' # 0xF9 -> DIAERESIS
+ '\xb7' # 0xFA -> MIDDLE DOT
+ '\xb9' # 0xFB -> SUPERSCRIPT ONE
+ '\xb3' # 0xFC -> SUPERSCRIPT THREE
+ '\xb2' # 0xFD -> SUPERSCRIPT TWO
+ '\u25a0' # 0xFE -> BLACK SQUARE
+ '\xa0' # 0xFF -> NO-BREAK SPACE
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp857.py b/Lib/encodings/cp857.py
new file mode 100644
index 0000000..741b059
--- /dev/null
+++ b/Lib/encodings/cp857.py
@@ -0,0 +1,694 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP857.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp857',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x0131, # LATIN SMALL LETTER DOTLESS I
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x0130, # LATIN CAPITAL LETTER I WITH DOT ABOVE
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA
+ 0x009f: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x011e, # LATIN CAPITAL LETTER G WITH BREVE
+ 0x00a7: 0x011f, # LATIN SMALL LETTER G WITH BREVE
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x00ae, # REGISTERED SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00b8: 0x00a9, # COPYRIGHT SIGN
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x00a2, # CENT SIGN
+ 0x00be: 0x00a5, # YEN SIGN
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
+ 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x00a4, # CURRENCY SIGN
+ 0x00d0: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00d1: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00d5: None, # UNDEFINED
+ 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x00a6, # BROKEN BAR
+ 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
+ 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: None, # UNDEFINED
+ 0x00e8: 0x00d7, # MULTIPLICATION SIGN
+ 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00ed: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x00ee: 0x00af, # MACRON
+ 0x00ef: 0x00b4, # ACUTE ACCENT
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: None, # UNDEFINED
+ 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00f4: 0x00b6, # PILCROW SIGN
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x00b8, # CEDILLA
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x00a8, # DIAERESIS
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x00b9, # SUPERSCRIPT ONE
+ 0x00fc: 0x00b3, # SUPERSCRIPT THREE
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\u0131' # 0x008d -> LATIN SMALL LETTER DOTLESS I
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\u0130' # 0x0098 -> LATIN CAPITAL LETTER I WITH DOT ABOVE
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\u015e' # 0x009e -> LATIN CAPITAL LETTER S WITH CEDILLA
+ '\u015f' # 0x009f -> LATIN SMALL LETTER S WITH CEDILLA
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\u011e' # 0x00a6 -> LATIN CAPITAL LETTER G WITH BREVE
+ '\u011f' # 0x00a7 -> LATIN SMALL LETTER G WITH BREVE
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\xae' # 0x00a9 -> REGISTERED SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xa9' # 0x00b8 -> COPYRIGHT SIGN
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\xa2' # 0x00bd -> CENT SIGN
+ '\xa5' # 0x00be -> YEN SIGN
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
+ '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0x00cf -> CURRENCY SIGN
+ '\xba' # 0x00d0 -> MASCULINE ORDINAL INDICATOR
+ '\xaa' # 0x00d1 -> FEMININE ORDINAL INDICATOR
+ '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\ufffe' # 0x00d5 -> UNDEFINED
+ '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\xa6' # 0x00dd -> BROKEN BAR
+ '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
+ '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\ufffe' # 0x00e7 -> UNDEFINED
+ '\xd7' # 0x00e8 -> MULTIPLICATION SIGN
+ '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xec' # 0x00ec -> LATIN SMALL LETTER I WITH GRAVE
+ '\xff' # 0x00ed -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xaf' # 0x00ee -> MACRON
+ '\xb4' # 0x00ef -> ACUTE ACCENT
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\ufffe' # 0x00f2 -> UNDEFINED
+ '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
+ '\xb6' # 0x00f4 -> PILCROW SIGN
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\xb8' # 0x00f7 -> CEDILLA
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\xa8' # 0x00f9 -> DIAERESIS
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\xb9' # 0x00fb -> SUPERSCRIPT ONE
+ '\xb3' # 0x00fc -> SUPERSCRIPT THREE
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x00bd, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x00cf, # CURRENCY SIGN
+ 0x00a5: 0x00be, # YEN SIGN
+ 0x00a6: 0x00dd, # BROKEN BAR
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a8: 0x00f9, # DIAERESIS
+ 0x00a9: 0x00b8, # COPYRIGHT SIGN
+ 0x00aa: 0x00d1, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00ae: 0x00a9, # REGISTERED SIGN
+ 0x00af: 0x00ee, # MACRON
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b3: 0x00fc, # SUPERSCRIPT THREE
+ 0x00b4: 0x00ef, # ACUTE ACCENT
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b6: 0x00f4, # PILCROW SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00b8: 0x00f7, # CEDILLA
+ 0x00b9: 0x00fb, # SUPERSCRIPT ONE
+ 0x00ba: 0x00d0, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d7: 0x00e8, # MULTIPLICATION SIGN
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ec: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00ff: 0x00ed, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x011e: 0x00a6, # LATIN CAPITAL LETTER G WITH BREVE
+ 0x011f: 0x00a7, # LATIN SMALL LETTER G WITH BREVE
+ 0x0130: 0x0098, # LATIN CAPITAL LETTER I WITH DOT ABOVE
+ 0x0131: 0x008d, # LATIN SMALL LETTER DOTLESS I
+ 0x015e: 0x009e, # LATIN CAPITAL LETTER S WITH CEDILLA
+ 0x015f: 0x009f, # LATIN SMALL LETTER S WITH CEDILLA
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp858.py b/Lib/encodings/cp858.py
new file mode 100644
index 0000000..7579f52
--- /dev/null
+++ b/Lib/encodings/cp858.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec for CP858, modified from cp850.
+
+"""
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp858',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x00d7, # MULTIPLICATION SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x00ae, # REGISTERED SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00b8: 0x00a9, # COPYRIGHT SIGN
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x00a2, # CENT SIGN
+ 0x00be: 0x00a5, # YEN SIGN
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
+ 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x00a4, # CURRENCY SIGN
+ 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH
+ 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH
+ 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00d5: 0x20ac, # EURO SIGN
+ 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x00a6, # BROKEN BAR
+ 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
+ 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN
+ 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN
+ 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00ee: 0x00af, # MACRON
+ 0x00ef: 0x00b4, # ACUTE ACCENT
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2017, # DOUBLE LOW LINE
+ 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00f4: 0x00b6, # PILCROW SIGN
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x00b8, # CEDILLA
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x00a8, # DIAERESIS
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x00b9, # SUPERSCRIPT ONE
+ 0x00fc: 0x00b3, # SUPERSCRIPT THREE
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd7' # 0x009e -> MULTIPLICATION SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\xae' # 0x00a9 -> REGISTERED SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xa9' # 0x00b8 -> COPYRIGHT SIGN
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\xa2' # 0x00bd -> CENT SIGN
+ '\xa5' # 0x00be -> YEN SIGN
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
+ '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\xa4' # 0x00cf -> CURRENCY SIGN
+ '\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH
+ '\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH
+ '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\u20ac' # 0x00d5 -> EURO SIGN
+ '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\xa6' # 0x00dd -> BROKEN BAR
+ '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
+ '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN
+ '\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN
+ '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xaf' # 0x00ee -> MACRON
+ '\xb4' # 0x00ef -> ACUTE ACCENT
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2017' # 0x00f2 -> DOUBLE LOW LINE
+ '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
+ '\xb6' # 0x00f4 -> PILCROW SIGN
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\xb8' # 0x00f7 -> CEDILLA
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\xa8' # 0x00f9 -> DIAERESIS
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\xb9' # 0x00fb -> SUPERSCRIPT ONE
+ '\xb3' # 0x00fc -> SUPERSCRIPT THREE
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x00bd, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x00cf, # CURRENCY SIGN
+ 0x00a5: 0x00be, # YEN SIGN
+ 0x00a6: 0x00dd, # BROKEN BAR
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a8: 0x00f9, # DIAERESIS
+ 0x00a9: 0x00b8, # COPYRIGHT SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00ae: 0x00a9, # REGISTERED SIGN
+ 0x00af: 0x00ee, # MACRON
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b3: 0x00fc, # SUPERSCRIPT THREE
+ 0x00b4: 0x00ef, # ACUTE ACCENT
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b6: 0x00f4, # PILCROW SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00b8: 0x00f7, # CEDILLA
+ 0x00b9: 0x00fb, # SUPERSCRIPT ONE
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d7: 0x009e, # MULTIPLICATION SIGN
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN
+ 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x20ac: 0x00d5, # EURO SIGN
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x2017: 0x00f2, # DOUBLE LOW LINE
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp860.py b/Lib/encodings/cp860.py
new file mode 100644
index 0000000..65903e7
--- /dev/null
+++ b/Lib/encodings/cp860.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP860.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp860',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x008c: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x008e: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x008f: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x0092: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x0099: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00a2, # CENT SIGN
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x009e: 0x20a7, # PESETA SIGN
+ 0x009f: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00e3: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00ec: 0x221e, # INFINITY
+ 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00ef: 0x2229, # INTERSECTION
+ 0x00f0: 0x2261, # IDENTICAL TO
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x2320, # TOP HALF INTEGRAL
+ 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe3' # 0x0084 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xc1' # 0x0086 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xca' # 0x0089 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xcd' # 0x008b -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xd4' # 0x008c -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
+ '\xc3' # 0x008e -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc2' # 0x008f -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xc0' # 0x0091 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc8' # 0x0092 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf5' # 0x0094 -> LATIN SMALL LETTER O WITH TILDE
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xda' # 0x0096 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xcc' # 0x0098 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\xd5' # 0x0099 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xa2' # 0x009b -> CENT SIGN
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\u20a7' # 0x009e -> PESETA SIGN
+ '\xd3' # 0x009f -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\xd2' # 0x00a9 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
+ '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
+ '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
+ '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
+ '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
+ '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
+ '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
+ '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
+ '\u221e' # 0x00ec -> INFINITY
+ '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
+ '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
+ '\u2229' # 0x00ef -> INTERSECTION
+ '\u2261' # 0x00f0 -> IDENTICAL TO
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u2320' # 0x00f4 -> TOP HALF INTEGRAL
+ '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x009b, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c0: 0x0091, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00c1: 0x0086, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c2: 0x008f, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c3: 0x008e, # LATIN CAPITAL LETTER A WITH TILDE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c8: 0x0092, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00ca: 0x0089, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00cc: 0x0098, # LATIN CAPITAL LETTER I WITH GRAVE
+ 0x00cd: 0x008b, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d2: 0x00a9, # LATIN CAPITAL LETTER O WITH GRAVE
+ 0x00d3: 0x009f, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d4: 0x008c, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d5: 0x0099, # LATIN CAPITAL LETTER O WITH TILDE
+ 0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00da: 0x0096, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e3: 0x0084, # LATIN SMALL LETTER A WITH TILDE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f5: 0x0094, # LATIN SMALL LETTER O WITH TILDE
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
+ 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
+ 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
+ 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
+ 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
+ 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
+ 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
+ 0x03c0: 0x00e3, # GREEK SMALL LETTER PI
+ 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
+ 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x20a7: 0x009e, # PESETA SIGN
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x221e: 0x00ec, # INFINITY
+ 0x2229: 0x00ef, # INTERSECTION
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2261: 0x00f0, # IDENTICAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2320: 0x00f4, # TOP HALF INTEGRAL
+ 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp861.py b/Lib/encodings/cp861.py
new file mode 100644
index 0000000..860a05f
--- /dev/null
+++ b/Lib/encodings/cp861.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP861.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp861',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00d0, # LATIN CAPITAL LETTER ETH
+ 0x008c: 0x00f0, # LATIN SMALL LETTER ETH
+ 0x008d: 0x00de, # LATIN CAPITAL LETTER THORN
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00fe, # LATIN SMALL LETTER THORN
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x0098: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x20a7, # PESETA SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00a5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00a6: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00a7: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x2310, # REVERSED NOT SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00e3: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00ec: 0x221e, # INFINITY
+ 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00ef: 0x2229, # INTERSECTION
+ 0x00f0: 0x2261, # IDENTICAL TO
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x2320, # TOP HALF INTEGRAL
+ 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xd0' # 0x008b -> LATIN CAPITAL LETTER ETH
+ '\xf0' # 0x008c -> LATIN SMALL LETTER ETH
+ '\xde' # 0x008d -> LATIN CAPITAL LETTER THORN
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xfe' # 0x0095 -> LATIN SMALL LETTER THORN
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xdd' # 0x0097 -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xfd' # 0x0098 -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\u20a7' # 0x009e -> PESETA SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xc1' # 0x00a4 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xcd' # 0x00a5 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xd3' # 0x00a6 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xda' # 0x00a7 -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\u2310' # 0x00a9 -> REVERSED NOT SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
+ '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
+ '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
+ '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
+ '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
+ '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
+ '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
+ '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
+ '\u221e' # 0x00ec -> INFINITY
+ '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
+ '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
+ '\u2229' # 0x00ef -> INTERSECTION
+ '\u2261' # 0x00f0 -> IDENTICAL TO
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u2320' # 0x00f4 -> TOP HALF INTEGRAL
+ '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c1: 0x00a4, # LATIN CAPITAL LETTER A WITH ACUTE
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00cd: 0x00a5, # LATIN CAPITAL LETTER I WITH ACUTE
+ 0x00d0: 0x008b, # LATIN CAPITAL LETTER ETH
+ 0x00d3: 0x00a6, # LATIN CAPITAL LETTER O WITH ACUTE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00da: 0x00a7, # LATIN CAPITAL LETTER U WITH ACUTE
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00dd: 0x0097, # LATIN CAPITAL LETTER Y WITH ACUTE
+ 0x00de: 0x008d, # LATIN CAPITAL LETTER THORN
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00f0: 0x008c, # LATIN SMALL LETTER ETH
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00fd: 0x0098, # LATIN SMALL LETTER Y WITH ACUTE
+ 0x00fe: 0x0095, # LATIN SMALL LETTER THORN
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
+ 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
+ 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
+ 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
+ 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
+ 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
+ 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
+ 0x03c0: 0x00e3, # GREEK SMALL LETTER PI
+ 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
+ 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x20a7: 0x009e, # PESETA SIGN
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x221e: 0x00ec, # INFINITY
+ 0x2229: 0x00ef, # INTERSECTION
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2261: 0x00f0, # IDENTICAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2310: 0x00a9, # REVERSED NOT SIGN
+ 0x2320: 0x00f4, # TOP HALF INTEGRAL
+ 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp862.py b/Lib/encodings/cp862.py
new file mode 100644
index 0000000..3df22f9
--- /dev/null
+++ b/Lib/encodings/cp862.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP862.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp862',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x05d0, # HEBREW LETTER ALEF
+ 0x0081: 0x05d1, # HEBREW LETTER BET
+ 0x0082: 0x05d2, # HEBREW LETTER GIMEL
+ 0x0083: 0x05d3, # HEBREW LETTER DALET
+ 0x0084: 0x05d4, # HEBREW LETTER HE
+ 0x0085: 0x05d5, # HEBREW LETTER VAV
+ 0x0086: 0x05d6, # HEBREW LETTER ZAYIN
+ 0x0087: 0x05d7, # HEBREW LETTER HET
+ 0x0088: 0x05d8, # HEBREW LETTER TET
+ 0x0089: 0x05d9, # HEBREW LETTER YOD
+ 0x008a: 0x05da, # HEBREW LETTER FINAL KAF
+ 0x008b: 0x05db, # HEBREW LETTER KAF
+ 0x008c: 0x05dc, # HEBREW LETTER LAMED
+ 0x008d: 0x05dd, # HEBREW LETTER FINAL MEM
+ 0x008e: 0x05de, # HEBREW LETTER MEM
+ 0x008f: 0x05df, # HEBREW LETTER FINAL NUN
+ 0x0090: 0x05e0, # HEBREW LETTER NUN
+ 0x0091: 0x05e1, # HEBREW LETTER SAMEKH
+ 0x0092: 0x05e2, # HEBREW LETTER AYIN
+ 0x0093: 0x05e3, # HEBREW LETTER FINAL PE
+ 0x0094: 0x05e4, # HEBREW LETTER PE
+ 0x0095: 0x05e5, # HEBREW LETTER FINAL TSADI
+ 0x0096: 0x05e6, # HEBREW LETTER TSADI
+ 0x0097: 0x05e7, # HEBREW LETTER QOF
+ 0x0098: 0x05e8, # HEBREW LETTER RESH
+ 0x0099: 0x05e9, # HEBREW LETTER SHIN
+ 0x009a: 0x05ea, # HEBREW LETTER TAV
+ 0x009b: 0x00a2, # CENT SIGN
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00a5, # YEN SIGN
+ 0x009e: 0x20a7, # PESETA SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x2310, # REVERSED NOT SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN)
+ 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00e3: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00ec: 0x221e, # INFINITY
+ 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00ef: 0x2229, # INTERSECTION
+ 0x00f0: 0x2261, # IDENTICAL TO
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x2320, # TOP HALF INTEGRAL
+ 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\u05d0' # 0x0080 -> HEBREW LETTER ALEF
+ '\u05d1' # 0x0081 -> HEBREW LETTER BET
+ '\u05d2' # 0x0082 -> HEBREW LETTER GIMEL
+ '\u05d3' # 0x0083 -> HEBREW LETTER DALET
+ '\u05d4' # 0x0084 -> HEBREW LETTER HE
+ '\u05d5' # 0x0085 -> HEBREW LETTER VAV
+ '\u05d6' # 0x0086 -> HEBREW LETTER ZAYIN
+ '\u05d7' # 0x0087 -> HEBREW LETTER HET
+ '\u05d8' # 0x0088 -> HEBREW LETTER TET
+ '\u05d9' # 0x0089 -> HEBREW LETTER YOD
+ '\u05da' # 0x008a -> HEBREW LETTER FINAL KAF
+ '\u05db' # 0x008b -> HEBREW LETTER KAF
+ '\u05dc' # 0x008c -> HEBREW LETTER LAMED
+ '\u05dd' # 0x008d -> HEBREW LETTER FINAL MEM
+ '\u05de' # 0x008e -> HEBREW LETTER MEM
+ '\u05df' # 0x008f -> HEBREW LETTER FINAL NUN
+ '\u05e0' # 0x0090 -> HEBREW LETTER NUN
+ '\u05e1' # 0x0091 -> HEBREW LETTER SAMEKH
+ '\u05e2' # 0x0092 -> HEBREW LETTER AYIN
+ '\u05e3' # 0x0093 -> HEBREW LETTER FINAL PE
+ '\u05e4' # 0x0094 -> HEBREW LETTER PE
+ '\u05e5' # 0x0095 -> HEBREW LETTER FINAL TSADI
+ '\u05e6' # 0x0096 -> HEBREW LETTER TSADI
+ '\u05e7' # 0x0097 -> HEBREW LETTER QOF
+ '\u05e8' # 0x0098 -> HEBREW LETTER RESH
+ '\u05e9' # 0x0099 -> HEBREW LETTER SHIN
+ '\u05ea' # 0x009a -> HEBREW LETTER TAV
+ '\xa2' # 0x009b -> CENT SIGN
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xa5' # 0x009d -> YEN SIGN
+ '\u20a7' # 0x009e -> PESETA SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\u2310' # 0x00a9 -> REVERSED NOT SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN)
+ '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
+ '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
+ '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
+ '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
+ '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
+ '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
+ '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
+ '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
+ '\u221e' # 0x00ec -> INFINITY
+ '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
+ '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
+ '\u2229' # 0x00ef -> INTERSECTION
+ '\u2261' # 0x00f0 -> IDENTICAL TO
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u2320' # 0x00f4 -> TOP HALF INTEGRAL
+ '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a2: 0x009b, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a5: 0x009d, # YEN SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN)
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
+ 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
+ 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
+ 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
+ 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
+ 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
+ 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
+ 0x03c0: 0x00e3, # GREEK SMALL LETTER PI
+ 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
+ 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
+ 0x05d0: 0x0080, # HEBREW LETTER ALEF
+ 0x05d1: 0x0081, # HEBREW LETTER BET
+ 0x05d2: 0x0082, # HEBREW LETTER GIMEL
+ 0x05d3: 0x0083, # HEBREW LETTER DALET
+ 0x05d4: 0x0084, # HEBREW LETTER HE
+ 0x05d5: 0x0085, # HEBREW LETTER VAV
+ 0x05d6: 0x0086, # HEBREW LETTER ZAYIN
+ 0x05d7: 0x0087, # HEBREW LETTER HET
+ 0x05d8: 0x0088, # HEBREW LETTER TET
+ 0x05d9: 0x0089, # HEBREW LETTER YOD
+ 0x05da: 0x008a, # HEBREW LETTER FINAL KAF
+ 0x05db: 0x008b, # HEBREW LETTER KAF
+ 0x05dc: 0x008c, # HEBREW LETTER LAMED
+ 0x05dd: 0x008d, # HEBREW LETTER FINAL MEM
+ 0x05de: 0x008e, # HEBREW LETTER MEM
+ 0x05df: 0x008f, # HEBREW LETTER FINAL NUN
+ 0x05e0: 0x0090, # HEBREW LETTER NUN
+ 0x05e1: 0x0091, # HEBREW LETTER SAMEKH
+ 0x05e2: 0x0092, # HEBREW LETTER AYIN
+ 0x05e3: 0x0093, # HEBREW LETTER FINAL PE
+ 0x05e4: 0x0094, # HEBREW LETTER PE
+ 0x05e5: 0x0095, # HEBREW LETTER FINAL TSADI
+ 0x05e6: 0x0096, # HEBREW LETTER TSADI
+ 0x05e7: 0x0097, # HEBREW LETTER QOF
+ 0x05e8: 0x0098, # HEBREW LETTER RESH
+ 0x05e9: 0x0099, # HEBREW LETTER SHIN
+ 0x05ea: 0x009a, # HEBREW LETTER TAV
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x20a7: 0x009e, # PESETA SIGN
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x221e: 0x00ec, # INFINITY
+ 0x2229: 0x00ef, # INTERSECTION
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2261: 0x00f0, # IDENTICAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2310: 0x00a9, # REVERSED NOT SIGN
+ 0x2320: 0x00f4, # TOP HALF INTEGRAL
+ 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp863.py b/Lib/encodings/cp863.py
new file mode 100644
index 0000000..764180b
--- /dev/null
+++ b/Lib/encodings/cp863.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP863.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp863',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00b6, # PILCROW SIGN
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x2017, # DOUBLE LOW LINE
+ 0x008e: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x008f: 0x00a7, # SECTION SIGN
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x0092: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x0095: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00a4, # CURRENCY SIGN
+ 0x0099: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00a2, # CENT SIGN
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x009e: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00a6, # BROKEN BAR
+ 0x00a1: 0x00b4, # ACUTE ACCENT
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00a8, # DIAERESIS
+ 0x00a5: 0x00b8, # CEDILLA
+ 0x00a6: 0x00b3, # SUPERSCRIPT THREE
+ 0x00a7: 0x00af, # MACRON
+ 0x00a8: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00a9: 0x2310, # REVERSED NOT SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00be, # VULGAR FRACTION THREE QUARTERS
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00e3: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00ec: 0x221e, # INFINITY
+ 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00ef: 0x2229, # INTERSECTION
+ 0x00f0: 0x2261, # IDENTICAL TO
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x2320, # TOP HALF INTEGRAL
+ 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xc2' # 0x0084 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xb6' # 0x0086 -> PILCROW SIGN
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\u2017' # 0x008d -> DOUBLE LOW LINE
+ '\xc0' # 0x008e -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xa7' # 0x008f -> SECTION SIGN
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xc8' # 0x0091 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xca' # 0x0092 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xcb' # 0x0094 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xcf' # 0x0095 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xa4' # 0x0098 -> CURRENCY SIGN
+ '\xd4' # 0x0099 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xa2' # 0x009b -> CENT SIGN
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xdb' # 0x009e -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xa6' # 0x00a0 -> BROKEN BAR
+ '\xb4' # 0x00a1 -> ACUTE ACCENT
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xa8' # 0x00a4 -> DIAERESIS
+ '\xb8' # 0x00a5 -> CEDILLA
+ '\xb3' # 0x00a6 -> SUPERSCRIPT THREE
+ '\xaf' # 0x00a7 -> MACRON
+ '\xce' # 0x00a8 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\u2310' # 0x00a9 -> REVERSED NOT SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xbe' # 0x00ad -> VULGAR FRACTION THREE QUARTERS
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
+ '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
+ '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
+ '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
+ '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
+ '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
+ '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
+ '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
+ '\u221e' # 0x00ec -> INFINITY
+ '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
+ '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
+ '\u2229' # 0x00ef -> INTERSECTION
+ '\u2261' # 0x00f0 -> IDENTICAL TO
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u2320' # 0x00f4 -> TOP HALF INTEGRAL
+ '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a2: 0x009b, # CENT SIGN
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x0098, # CURRENCY SIGN
+ 0x00a6: 0x00a0, # BROKEN BAR
+ 0x00a7: 0x008f, # SECTION SIGN
+ 0x00a8: 0x00a4, # DIAERESIS
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00af: 0x00a7, # MACRON
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b3: 0x00a6, # SUPERSCRIPT THREE
+ 0x00b4: 0x00a1, # ACUTE ACCENT
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b6: 0x0086, # PILCROW SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00b8: 0x00a5, # CEDILLA
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00be: 0x00ad, # VULGAR FRACTION THREE QUARTERS
+ 0x00c0: 0x008e, # LATIN CAPITAL LETTER A WITH GRAVE
+ 0x00c2: 0x0084, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c8: 0x0091, # LATIN CAPITAL LETTER E WITH GRAVE
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00ca: 0x0092, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ 0x00cb: 0x0094, # LATIN CAPITAL LETTER E WITH DIAERESIS
+ 0x00ce: 0x00a8, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ 0x00cf: 0x0095, # LATIN CAPITAL LETTER I WITH DIAERESIS
+ 0x00d4: 0x0099, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ 0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE
+ 0x00db: 0x009e, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
+ 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
+ 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
+ 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
+ 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
+ 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
+ 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
+ 0x03c0: 0x00e3, # GREEK SMALL LETTER PI
+ 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
+ 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
+ 0x2017: 0x008d, # DOUBLE LOW LINE
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x221e: 0x00ec, # INFINITY
+ 0x2229: 0x00ef, # INTERSECTION
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2261: 0x00f0, # IDENTICAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2310: 0x00a9, # REVERSED NOT SIGN
+ 0x2320: 0x00f4, # TOP HALF INTEGRAL
+ 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp864.py b/Lib/encodings/cp864.py
new file mode 100644
index 0000000..53df482
--- /dev/null
+++ b/Lib/encodings/cp864.py
@@ -0,0 +1,690 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP864.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp864',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0025: 0x066a, # ARABIC PERCENT SIGN
+ 0x0080: 0x00b0, # DEGREE SIGN
+ 0x0081: 0x00b7, # MIDDLE DOT
+ 0x0082: 0x2219, # BULLET OPERATOR
+ 0x0083: 0x221a, # SQUARE ROOT
+ 0x0084: 0x2592, # MEDIUM SHADE
+ 0x0085: 0x2500, # FORMS LIGHT HORIZONTAL
+ 0x0086: 0x2502, # FORMS LIGHT VERTICAL
+ 0x0087: 0x253c, # FORMS LIGHT VERTICAL AND HORIZONTAL
+ 0x0088: 0x2524, # FORMS LIGHT VERTICAL AND LEFT
+ 0x0089: 0x252c, # FORMS LIGHT DOWN AND HORIZONTAL
+ 0x008a: 0x251c, # FORMS LIGHT VERTICAL AND RIGHT
+ 0x008b: 0x2534, # FORMS LIGHT UP AND HORIZONTAL
+ 0x008c: 0x2510, # FORMS LIGHT DOWN AND LEFT
+ 0x008d: 0x250c, # FORMS LIGHT DOWN AND RIGHT
+ 0x008e: 0x2514, # FORMS LIGHT UP AND RIGHT
+ 0x008f: 0x2518, # FORMS LIGHT UP AND LEFT
+ 0x0090: 0x03b2, # GREEK SMALL BETA
+ 0x0091: 0x221e, # INFINITY
+ 0x0092: 0x03c6, # GREEK SMALL PHI
+ 0x0093: 0x00b1, # PLUS-OR-MINUS SIGN
+ 0x0094: 0x00bd, # FRACTION 1/2
+ 0x0095: 0x00bc, # FRACTION 1/4
+ 0x0096: 0x2248, # ALMOST EQUAL TO
+ 0x0097: 0x00ab, # LEFT POINTING GUILLEMET
+ 0x0098: 0x00bb, # RIGHT POINTING GUILLEMET
+ 0x0099: 0xfef7, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
+ 0x009a: 0xfef8, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
+ 0x009b: None, # UNDEFINED
+ 0x009c: None, # UNDEFINED
+ 0x009d: 0xfefb, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
+ 0x009e: 0xfefc, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM
+ 0x009f: None, # UNDEFINED
+ 0x00a1: 0x00ad, # SOFT HYPHEN
+ 0x00a2: 0xfe82, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
+ 0x00a5: 0xfe84, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
+ 0x00a6: None, # UNDEFINED
+ 0x00a7: None, # UNDEFINED
+ 0x00a8: 0xfe8e, # ARABIC LETTER ALEF FINAL FORM
+ 0x00a9: 0xfe8f, # ARABIC LETTER BEH ISOLATED FORM
+ 0x00aa: 0xfe95, # ARABIC LETTER TEH ISOLATED FORM
+ 0x00ab: 0xfe99, # ARABIC LETTER THEH ISOLATED FORM
+ 0x00ac: 0x060c, # ARABIC COMMA
+ 0x00ad: 0xfe9d, # ARABIC LETTER JEEM ISOLATED FORM
+ 0x00ae: 0xfea1, # ARABIC LETTER HAH ISOLATED FORM
+ 0x00af: 0xfea5, # ARABIC LETTER KHAH ISOLATED FORM
+ 0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO
+ 0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE
+ 0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO
+ 0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE
+ 0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR
+ 0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE
+ 0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX
+ 0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN
+ 0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT
+ 0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE
+ 0x00ba: 0xfed1, # ARABIC LETTER FEH ISOLATED FORM
+ 0x00bb: 0x061b, # ARABIC SEMICOLON
+ 0x00bc: 0xfeb1, # ARABIC LETTER SEEN ISOLATED FORM
+ 0x00bd: 0xfeb5, # ARABIC LETTER SHEEN ISOLATED FORM
+ 0x00be: 0xfeb9, # ARABIC LETTER SAD ISOLATED FORM
+ 0x00bf: 0x061f, # ARABIC QUESTION MARK
+ 0x00c0: 0x00a2, # CENT SIGN
+ 0x00c1: 0xfe80, # ARABIC LETTER HAMZA ISOLATED FORM
+ 0x00c2: 0xfe81, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
+ 0x00c3: 0xfe83, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
+ 0x00c4: 0xfe85, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
+ 0x00c5: 0xfeca, # ARABIC LETTER AIN FINAL FORM
+ 0x00c6: 0xfe8b, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
+ 0x00c7: 0xfe8d, # ARABIC LETTER ALEF ISOLATED FORM
+ 0x00c8: 0xfe91, # ARABIC LETTER BEH INITIAL FORM
+ 0x00c9: 0xfe93, # ARABIC LETTER TEH MARBUTA ISOLATED FORM
+ 0x00ca: 0xfe97, # ARABIC LETTER TEH INITIAL FORM
+ 0x00cb: 0xfe9b, # ARABIC LETTER THEH INITIAL FORM
+ 0x00cc: 0xfe9f, # ARABIC LETTER JEEM INITIAL FORM
+ 0x00cd: 0xfea3, # ARABIC LETTER HAH INITIAL FORM
+ 0x00ce: 0xfea7, # ARABIC LETTER KHAH INITIAL FORM
+ 0x00cf: 0xfea9, # ARABIC LETTER DAL ISOLATED FORM
+ 0x00d0: 0xfeab, # ARABIC LETTER THAL ISOLATED FORM
+ 0x00d1: 0xfead, # ARABIC LETTER REH ISOLATED FORM
+ 0x00d2: 0xfeaf, # ARABIC LETTER ZAIN ISOLATED FORM
+ 0x00d3: 0xfeb3, # ARABIC LETTER SEEN INITIAL FORM
+ 0x00d4: 0xfeb7, # ARABIC LETTER SHEEN INITIAL FORM
+ 0x00d5: 0xfebb, # ARABIC LETTER SAD INITIAL FORM
+ 0x00d6: 0xfebf, # ARABIC LETTER DAD INITIAL FORM
+ 0x00d7: 0xfec1, # ARABIC LETTER TAH ISOLATED FORM
+ 0x00d8: 0xfec5, # ARABIC LETTER ZAH ISOLATED FORM
+ 0x00d9: 0xfecb, # ARABIC LETTER AIN INITIAL FORM
+ 0x00da: 0xfecf, # ARABIC LETTER GHAIN INITIAL FORM
+ 0x00db: 0x00a6, # BROKEN VERTICAL BAR
+ 0x00dc: 0x00ac, # NOT SIGN
+ 0x00dd: 0x00f7, # DIVISION SIGN
+ 0x00de: 0x00d7, # MULTIPLICATION SIGN
+ 0x00df: 0xfec9, # ARABIC LETTER AIN ISOLATED FORM
+ 0x00e0: 0x0640, # ARABIC TATWEEL
+ 0x00e1: 0xfed3, # ARABIC LETTER FEH INITIAL FORM
+ 0x00e2: 0xfed7, # ARABIC LETTER QAF INITIAL FORM
+ 0x00e3: 0xfedb, # ARABIC LETTER KAF INITIAL FORM
+ 0x00e4: 0xfedf, # ARABIC LETTER LAM INITIAL FORM
+ 0x00e5: 0xfee3, # ARABIC LETTER MEEM INITIAL FORM
+ 0x00e6: 0xfee7, # ARABIC LETTER NOON INITIAL FORM
+ 0x00e7: 0xfeeb, # ARABIC LETTER HEH INITIAL FORM
+ 0x00e8: 0xfeed, # ARABIC LETTER WAW ISOLATED FORM
+ 0x00e9: 0xfeef, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM
+ 0x00ea: 0xfef3, # ARABIC LETTER YEH INITIAL FORM
+ 0x00eb: 0xfebd, # ARABIC LETTER DAD ISOLATED FORM
+ 0x00ec: 0xfecc, # ARABIC LETTER AIN MEDIAL FORM
+ 0x00ed: 0xfece, # ARABIC LETTER GHAIN FINAL FORM
+ 0x00ee: 0xfecd, # ARABIC LETTER GHAIN ISOLATED FORM
+ 0x00ef: 0xfee1, # ARABIC LETTER MEEM ISOLATED FORM
+ 0x00f0: 0xfe7d, # ARABIC SHADDA MEDIAL FORM
+ 0x00f1: 0x0651, # ARABIC SHADDAH
+ 0x00f2: 0xfee5, # ARABIC LETTER NOON ISOLATED FORM
+ 0x00f3: 0xfee9, # ARABIC LETTER HEH ISOLATED FORM
+ 0x00f4: 0xfeec, # ARABIC LETTER HEH MEDIAL FORM
+ 0x00f5: 0xfef0, # ARABIC LETTER ALEF MAKSURA FINAL FORM
+ 0x00f6: 0xfef2, # ARABIC LETTER YEH FINAL FORM
+ 0x00f7: 0xfed0, # ARABIC LETTER GHAIN MEDIAL FORM
+ 0x00f8: 0xfed5, # ARABIC LETTER QAF ISOLATED FORM
+ 0x00f9: 0xfef5, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
+ 0x00fa: 0xfef6, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
+ 0x00fb: 0xfedd, # ARABIC LETTER LAM ISOLATED FORM
+ 0x00fc: 0xfed9, # ARABIC LETTER KAF ISOLATED FORM
+ 0x00fd: 0xfef1, # ARABIC LETTER YEH ISOLATED FORM
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: None, # UNDEFINED
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '\u066a' # 0x0025 -> ARABIC PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xb0' # 0x0080 -> DEGREE SIGN
+ '\xb7' # 0x0081 -> MIDDLE DOT
+ '\u2219' # 0x0082 -> BULLET OPERATOR
+ '\u221a' # 0x0083 -> SQUARE ROOT
+ '\u2592' # 0x0084 -> MEDIUM SHADE
+ '\u2500' # 0x0085 -> FORMS LIGHT HORIZONTAL
+ '\u2502' # 0x0086 -> FORMS LIGHT VERTICAL
+ '\u253c' # 0x0087 -> FORMS LIGHT VERTICAL AND HORIZONTAL
+ '\u2524' # 0x0088 -> FORMS LIGHT VERTICAL AND LEFT
+ '\u252c' # 0x0089 -> FORMS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x008a -> FORMS LIGHT VERTICAL AND RIGHT
+ '\u2534' # 0x008b -> FORMS LIGHT UP AND HORIZONTAL
+ '\u2510' # 0x008c -> FORMS LIGHT DOWN AND LEFT
+ '\u250c' # 0x008d -> FORMS LIGHT DOWN AND RIGHT
+ '\u2514' # 0x008e -> FORMS LIGHT UP AND RIGHT
+ '\u2518' # 0x008f -> FORMS LIGHT UP AND LEFT
+ '\u03b2' # 0x0090 -> GREEK SMALL BETA
+ '\u221e' # 0x0091 -> INFINITY
+ '\u03c6' # 0x0092 -> GREEK SMALL PHI
+ '\xb1' # 0x0093 -> PLUS-OR-MINUS SIGN
+ '\xbd' # 0x0094 -> FRACTION 1/2
+ '\xbc' # 0x0095 -> FRACTION 1/4
+ '\u2248' # 0x0096 -> ALMOST EQUAL TO
+ '\xab' # 0x0097 -> LEFT POINTING GUILLEMET
+ '\xbb' # 0x0098 -> RIGHT POINTING GUILLEMET
+ '\ufef7' # 0x0099 -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
+ '\ufef8' # 0x009a -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
+ '\ufffe' # 0x009b -> UNDEFINED
+ '\ufffe' # 0x009c -> UNDEFINED
+ '\ufefb' # 0x009d -> ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
+ '\ufefc' # 0x009e -> ARABIC LIGATURE LAM WITH ALEF FINAL FORM
+ '\ufffe' # 0x009f -> UNDEFINED
+ '\xa0' # 0x00a0 -> NON-BREAKING SPACE
+ '\xad' # 0x00a1 -> SOFT HYPHEN
+ '\ufe82' # 0x00a2 -> ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
+ '\xa3' # 0x00a3 -> POUND SIGN
+ '\xa4' # 0x00a4 -> CURRENCY SIGN
+ '\ufe84' # 0x00a5 -> ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
+ '\ufffe' # 0x00a6 -> UNDEFINED
+ '\ufffe' # 0x00a7 -> UNDEFINED
+ '\ufe8e' # 0x00a8 -> ARABIC LETTER ALEF FINAL FORM
+ '\ufe8f' # 0x00a9 -> ARABIC LETTER BEH ISOLATED FORM
+ '\ufe95' # 0x00aa -> ARABIC LETTER TEH ISOLATED FORM
+ '\ufe99' # 0x00ab -> ARABIC LETTER THEH ISOLATED FORM
+ '\u060c' # 0x00ac -> ARABIC COMMA
+ '\ufe9d' # 0x00ad -> ARABIC LETTER JEEM ISOLATED FORM
+ '\ufea1' # 0x00ae -> ARABIC LETTER HAH ISOLATED FORM
+ '\ufea5' # 0x00af -> ARABIC LETTER KHAH ISOLATED FORM
+ '\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO
+ '\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE
+ '\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO
+ '\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE
+ '\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR
+ '\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE
+ '\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX
+ '\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN
+ '\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT
+ '\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE
+ '\ufed1' # 0x00ba -> ARABIC LETTER FEH ISOLATED FORM
+ '\u061b' # 0x00bb -> ARABIC SEMICOLON
+ '\ufeb1' # 0x00bc -> ARABIC LETTER SEEN ISOLATED FORM
+ '\ufeb5' # 0x00bd -> ARABIC LETTER SHEEN ISOLATED FORM
+ '\ufeb9' # 0x00be -> ARABIC LETTER SAD ISOLATED FORM
+ '\u061f' # 0x00bf -> ARABIC QUESTION MARK
+ '\xa2' # 0x00c0 -> CENT SIGN
+ '\ufe80' # 0x00c1 -> ARABIC LETTER HAMZA ISOLATED FORM
+ '\ufe81' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
+ '\ufe83' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
+ '\ufe85' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
+ '\ufeca' # 0x00c5 -> ARABIC LETTER AIN FINAL FORM
+ '\ufe8b' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
+ '\ufe8d' # 0x00c7 -> ARABIC LETTER ALEF ISOLATED FORM
+ '\ufe91' # 0x00c8 -> ARABIC LETTER BEH INITIAL FORM
+ '\ufe93' # 0x00c9 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM
+ '\ufe97' # 0x00ca -> ARABIC LETTER TEH INITIAL FORM
+ '\ufe9b' # 0x00cb -> ARABIC LETTER THEH INITIAL FORM
+ '\ufe9f' # 0x00cc -> ARABIC LETTER JEEM INITIAL FORM
+ '\ufea3' # 0x00cd -> ARABIC LETTER HAH INITIAL FORM
+ '\ufea7' # 0x00ce -> ARABIC LETTER KHAH INITIAL FORM
+ '\ufea9' # 0x00cf -> ARABIC LETTER DAL ISOLATED FORM
+ '\ufeab' # 0x00d0 -> ARABIC LETTER THAL ISOLATED FORM
+ '\ufead' # 0x00d1 -> ARABIC LETTER REH ISOLATED FORM
+ '\ufeaf' # 0x00d2 -> ARABIC LETTER ZAIN ISOLATED FORM
+ '\ufeb3' # 0x00d3 -> ARABIC LETTER SEEN INITIAL FORM
+ '\ufeb7' # 0x00d4 -> ARABIC LETTER SHEEN INITIAL FORM
+ '\ufebb' # 0x00d5 -> ARABIC LETTER SAD INITIAL FORM
+ '\ufebf' # 0x00d6 -> ARABIC LETTER DAD INITIAL FORM
+ '\ufec1' # 0x00d7 -> ARABIC LETTER TAH ISOLATED FORM
+ '\ufec5' # 0x00d8 -> ARABIC LETTER ZAH ISOLATED FORM
+ '\ufecb' # 0x00d9 -> ARABIC LETTER AIN INITIAL FORM
+ '\ufecf' # 0x00da -> ARABIC LETTER GHAIN INITIAL FORM
+ '\xa6' # 0x00db -> BROKEN VERTICAL BAR
+ '\xac' # 0x00dc -> NOT SIGN
+ '\xf7' # 0x00dd -> DIVISION SIGN
+ '\xd7' # 0x00de -> MULTIPLICATION SIGN
+ '\ufec9' # 0x00df -> ARABIC LETTER AIN ISOLATED FORM
+ '\u0640' # 0x00e0 -> ARABIC TATWEEL
+ '\ufed3' # 0x00e1 -> ARABIC LETTER FEH INITIAL FORM
+ '\ufed7' # 0x00e2 -> ARABIC LETTER QAF INITIAL FORM
+ '\ufedb' # 0x00e3 -> ARABIC LETTER KAF INITIAL FORM
+ '\ufedf' # 0x00e4 -> ARABIC LETTER LAM INITIAL FORM
+ '\ufee3' # 0x00e5 -> ARABIC LETTER MEEM INITIAL FORM
+ '\ufee7' # 0x00e6 -> ARABIC LETTER NOON INITIAL FORM
+ '\ufeeb' # 0x00e7 -> ARABIC LETTER HEH INITIAL FORM
+ '\ufeed' # 0x00e8 -> ARABIC LETTER WAW ISOLATED FORM
+ '\ufeef' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA ISOLATED FORM
+ '\ufef3' # 0x00ea -> ARABIC LETTER YEH INITIAL FORM
+ '\ufebd' # 0x00eb -> ARABIC LETTER DAD ISOLATED FORM
+ '\ufecc' # 0x00ec -> ARABIC LETTER AIN MEDIAL FORM
+ '\ufece' # 0x00ed -> ARABIC LETTER GHAIN FINAL FORM
+ '\ufecd' # 0x00ee -> ARABIC LETTER GHAIN ISOLATED FORM
+ '\ufee1' # 0x00ef -> ARABIC LETTER MEEM ISOLATED FORM
+ '\ufe7d' # 0x00f0 -> ARABIC SHADDA MEDIAL FORM
+ '\u0651' # 0x00f1 -> ARABIC SHADDAH
+ '\ufee5' # 0x00f2 -> ARABIC LETTER NOON ISOLATED FORM
+ '\ufee9' # 0x00f3 -> ARABIC LETTER HEH ISOLATED FORM
+ '\ufeec' # 0x00f4 -> ARABIC LETTER HEH MEDIAL FORM
+ '\ufef0' # 0x00f5 -> ARABIC LETTER ALEF MAKSURA FINAL FORM
+ '\ufef2' # 0x00f6 -> ARABIC LETTER YEH FINAL FORM
+ '\ufed0' # 0x00f7 -> ARABIC LETTER GHAIN MEDIAL FORM
+ '\ufed5' # 0x00f8 -> ARABIC LETTER QAF ISOLATED FORM
+ '\ufef5' # 0x00f9 -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
+ '\ufef6' # 0x00fa -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
+ '\ufedd' # 0x00fb -> ARABIC LETTER LAM ISOLATED FORM
+ '\ufed9' # 0x00fc -> ARABIC LETTER KAF ISOLATED FORM
+ '\ufef1' # 0x00fd -> ARABIC LETTER YEH ISOLATED FORM
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\ufffe' # 0x00ff -> UNDEFINED
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00a0, # NON-BREAKING SPACE
+ 0x00a2: 0x00c0, # CENT SIGN
+ 0x00a3: 0x00a3, # POUND SIGN
+ 0x00a4: 0x00a4, # CURRENCY SIGN
+ 0x00a6: 0x00db, # BROKEN VERTICAL BAR
+ 0x00ab: 0x0097, # LEFT POINTING GUILLEMET
+ 0x00ac: 0x00dc, # NOT SIGN
+ 0x00ad: 0x00a1, # SOFT HYPHEN
+ 0x00b0: 0x0080, # DEGREE SIGN
+ 0x00b1: 0x0093, # PLUS-OR-MINUS SIGN
+ 0x00b7: 0x0081, # MIDDLE DOT
+ 0x00bb: 0x0098, # RIGHT POINTING GUILLEMET
+ 0x00bc: 0x0095, # FRACTION 1/4
+ 0x00bd: 0x0094, # FRACTION 1/2
+ 0x00d7: 0x00de, # MULTIPLICATION SIGN
+ 0x00f7: 0x00dd, # DIVISION SIGN
+ 0x03b2: 0x0090, # GREEK SMALL BETA
+ 0x03c6: 0x0092, # GREEK SMALL PHI
+ 0x060c: 0x00ac, # ARABIC COMMA
+ 0x061b: 0x00bb, # ARABIC SEMICOLON
+ 0x061f: 0x00bf, # ARABIC QUESTION MARK
+ 0x0640: 0x00e0, # ARABIC TATWEEL
+ 0x0651: 0x00f1, # ARABIC SHADDAH
+ 0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO
+ 0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE
+ 0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO
+ 0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE
+ 0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR
+ 0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE
+ 0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX
+ 0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN
+ 0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT
+ 0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE
+ 0x066a: 0x0025, # ARABIC PERCENT SIGN
+ 0x2219: 0x0082, # BULLET OPERATOR
+ 0x221a: 0x0083, # SQUARE ROOT
+ 0x221e: 0x0091, # INFINITY
+ 0x2248: 0x0096, # ALMOST EQUAL TO
+ 0x2500: 0x0085, # FORMS LIGHT HORIZONTAL
+ 0x2502: 0x0086, # FORMS LIGHT VERTICAL
+ 0x250c: 0x008d, # FORMS LIGHT DOWN AND RIGHT
+ 0x2510: 0x008c, # FORMS LIGHT DOWN AND LEFT
+ 0x2514: 0x008e, # FORMS LIGHT UP AND RIGHT
+ 0x2518: 0x008f, # FORMS LIGHT UP AND LEFT
+ 0x251c: 0x008a, # FORMS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x0088, # FORMS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x0089, # FORMS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x008b, # FORMS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x0087, # FORMS LIGHT VERTICAL AND HORIZONTAL
+ 0x2592: 0x0084, # MEDIUM SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+ 0xfe7d: 0x00f0, # ARABIC SHADDA MEDIAL FORM
+ 0xfe80: 0x00c1, # ARABIC LETTER HAMZA ISOLATED FORM
+ 0xfe81: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
+ 0xfe82: 0x00a2, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
+ 0xfe83: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
+ 0xfe84: 0x00a5, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
+ 0xfe85: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
+ 0xfe8b: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
+ 0xfe8d: 0x00c7, # ARABIC LETTER ALEF ISOLATED FORM
+ 0xfe8e: 0x00a8, # ARABIC LETTER ALEF FINAL FORM
+ 0xfe8f: 0x00a9, # ARABIC LETTER BEH ISOLATED FORM
+ 0xfe91: 0x00c8, # ARABIC LETTER BEH INITIAL FORM
+ 0xfe93: 0x00c9, # ARABIC LETTER TEH MARBUTA ISOLATED FORM
+ 0xfe95: 0x00aa, # ARABIC LETTER TEH ISOLATED FORM
+ 0xfe97: 0x00ca, # ARABIC LETTER TEH INITIAL FORM
+ 0xfe99: 0x00ab, # ARABIC LETTER THEH ISOLATED FORM
+ 0xfe9b: 0x00cb, # ARABIC LETTER THEH INITIAL FORM
+ 0xfe9d: 0x00ad, # ARABIC LETTER JEEM ISOLATED FORM
+ 0xfe9f: 0x00cc, # ARABIC LETTER JEEM INITIAL FORM
+ 0xfea1: 0x00ae, # ARABIC LETTER HAH ISOLATED FORM
+ 0xfea3: 0x00cd, # ARABIC LETTER HAH INITIAL FORM
+ 0xfea5: 0x00af, # ARABIC LETTER KHAH ISOLATED FORM
+ 0xfea7: 0x00ce, # ARABIC LETTER KHAH INITIAL FORM
+ 0xfea9: 0x00cf, # ARABIC LETTER DAL ISOLATED FORM
+ 0xfeab: 0x00d0, # ARABIC LETTER THAL ISOLATED FORM
+ 0xfead: 0x00d1, # ARABIC LETTER REH ISOLATED FORM
+ 0xfeaf: 0x00d2, # ARABIC LETTER ZAIN ISOLATED FORM
+ 0xfeb1: 0x00bc, # ARABIC LETTER SEEN ISOLATED FORM
+ 0xfeb3: 0x00d3, # ARABIC LETTER SEEN INITIAL FORM
+ 0xfeb5: 0x00bd, # ARABIC LETTER SHEEN ISOLATED FORM
+ 0xfeb7: 0x00d4, # ARABIC LETTER SHEEN INITIAL FORM
+ 0xfeb9: 0x00be, # ARABIC LETTER SAD ISOLATED FORM
+ 0xfebb: 0x00d5, # ARABIC LETTER SAD INITIAL FORM
+ 0xfebd: 0x00eb, # ARABIC LETTER DAD ISOLATED FORM
+ 0xfebf: 0x00d6, # ARABIC LETTER DAD INITIAL FORM
+ 0xfec1: 0x00d7, # ARABIC LETTER TAH ISOLATED FORM
+ 0xfec5: 0x00d8, # ARABIC LETTER ZAH ISOLATED FORM
+ 0xfec9: 0x00df, # ARABIC LETTER AIN ISOLATED FORM
+ 0xfeca: 0x00c5, # ARABIC LETTER AIN FINAL FORM
+ 0xfecb: 0x00d9, # ARABIC LETTER AIN INITIAL FORM
+ 0xfecc: 0x00ec, # ARABIC LETTER AIN MEDIAL FORM
+ 0xfecd: 0x00ee, # ARABIC LETTER GHAIN ISOLATED FORM
+ 0xfece: 0x00ed, # ARABIC LETTER GHAIN FINAL FORM
+ 0xfecf: 0x00da, # ARABIC LETTER GHAIN INITIAL FORM
+ 0xfed0: 0x00f7, # ARABIC LETTER GHAIN MEDIAL FORM
+ 0xfed1: 0x00ba, # ARABIC LETTER FEH ISOLATED FORM
+ 0xfed3: 0x00e1, # ARABIC LETTER FEH INITIAL FORM
+ 0xfed5: 0x00f8, # ARABIC LETTER QAF ISOLATED FORM
+ 0xfed7: 0x00e2, # ARABIC LETTER QAF INITIAL FORM
+ 0xfed9: 0x00fc, # ARABIC LETTER KAF ISOLATED FORM
+ 0xfedb: 0x00e3, # ARABIC LETTER KAF INITIAL FORM
+ 0xfedd: 0x00fb, # ARABIC LETTER LAM ISOLATED FORM
+ 0xfedf: 0x00e4, # ARABIC LETTER LAM INITIAL FORM
+ 0xfee1: 0x00ef, # ARABIC LETTER MEEM ISOLATED FORM
+ 0xfee3: 0x00e5, # ARABIC LETTER MEEM INITIAL FORM
+ 0xfee5: 0x00f2, # ARABIC LETTER NOON ISOLATED FORM
+ 0xfee7: 0x00e6, # ARABIC LETTER NOON INITIAL FORM
+ 0xfee9: 0x00f3, # ARABIC LETTER HEH ISOLATED FORM
+ 0xfeeb: 0x00e7, # ARABIC LETTER HEH INITIAL FORM
+ 0xfeec: 0x00f4, # ARABIC LETTER HEH MEDIAL FORM
+ 0xfeed: 0x00e8, # ARABIC LETTER WAW ISOLATED FORM
+ 0xfeef: 0x00e9, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM
+ 0xfef0: 0x00f5, # ARABIC LETTER ALEF MAKSURA FINAL FORM
+ 0xfef1: 0x00fd, # ARABIC LETTER YEH ISOLATED FORM
+ 0xfef2: 0x00f6, # ARABIC LETTER YEH FINAL FORM
+ 0xfef3: 0x00ea, # ARABIC LETTER YEH INITIAL FORM
+ 0xfef5: 0x00f9, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
+ 0xfef6: 0x00fa, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
+ 0xfef7: 0x0099, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
+ 0xfef8: 0x009a, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
+ 0xfefb: 0x009d, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
+ 0xfefc: 0x009e, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM
+}
diff --git a/Lib/encodings/cp865.py b/Lib/encodings/cp865.py
new file mode 100644
index 0000000..6726cf3
--- /dev/null
+++ b/Lib/encodings/cp865.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP865.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp865',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
+ 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
+ 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
+ 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
+ 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
+ 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
+ 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
+ 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
+ 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x009e: 0x20a7, # PESETA SIGN
+ 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
+ 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
+ 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
+ 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
+ 0x00a8: 0x00bf, # INVERTED QUESTION MARK
+ 0x00a9: 0x2310, # REVERSED NOT SIGN
+ 0x00aa: 0x00ac, # NOT SIGN
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
+ 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00a4, # CURRENCY SIGN
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
+ 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00e3: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00e6: 0x00b5, # MICRO SIGN
+ 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00ec: 0x221e, # INFINITY
+ 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00ef: 0x2229, # INTERSECTION
+ 0x00f0: 0x2261, # IDENTICAL TO
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
+ 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
+ 0x00f4: 0x2320, # TOP HALF INTEGRAL
+ 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
+ 0x00f6: 0x00f7, # DIVISION SIGN
+ 0x00f7: 0x2248, # ALMOST EQUAL TO
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x00fd: 0x00b2, # SUPERSCRIPT TWO
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
+ '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
+ '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
+ '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
+ '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
+ '\xa3' # 0x009c -> POUND SIGN
+ '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
+ '\u20a7' # 0x009e -> PESETA SIGN
+ '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
+ '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
+ '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
+ '\xbf' # 0x00a8 -> INVERTED QUESTION MARK
+ '\u2310' # 0x00a9 -> REVERSED NOT SIGN
+ '\xac' # 0x00aa -> NOT SIGN
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
+ '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xa4' # 0x00af -> CURRENCY SIGN
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
+ '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
+ '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
+ '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
+ '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
+ '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
+ '\xb5' # 0x00e6 -> MICRO SIGN
+ '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
+ '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
+ '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
+ '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
+ '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
+ '\u221e' # 0x00ec -> INFINITY
+ '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
+ '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
+ '\u2229' # 0x00ef -> INTERSECTION
+ '\u2261' # 0x00f0 -> IDENTICAL TO
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
+ '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
+ '\u2320' # 0x00f4 -> TOP HALF INTEGRAL
+ '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
+ '\xf7' # 0x00f6 -> DIVISION SIGN
+ '\u2248' # 0x00f7 -> ALMOST EQUAL TO
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
+ '\xb2' # 0x00fd -> SUPERSCRIPT TWO
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a4: 0x00af, # CURRENCY SIGN
+ 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x00aa, # NOT SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x00fd, # SUPERSCRIPT TWO
+ 0x00b5: 0x00e6, # MICRO SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
+ 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x00bf: 0x00a8, # INVERTED QUESTION MARK
+ 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
+ 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
+ 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
+ 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
+ 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
+ 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
+ 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
+ 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
+ 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
+ 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
+ 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
+ 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
+ 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
+ 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
+ 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
+ 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
+ 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
+ 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
+ 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
+ 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
+ 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
+ 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
+ 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
+ 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
+ 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
+ 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
+ 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
+ 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
+ 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
+ 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
+ 0x00f7: 0x00f6, # DIVISION SIGN
+ 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
+ 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
+ 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
+ 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
+ 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
+ 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
+ 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
+ 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
+ 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
+ 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
+ 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
+ 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
+ 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
+ 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
+ 0x03c0: 0x00e3, # GREEK SMALL LETTER PI
+ 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
+ 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
+ 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
+ 0x20a7: 0x009e, # PESETA SIGN
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x221e: 0x00ec, # INFINITY
+ 0x2229: 0x00ef, # INTERSECTION
+ 0x2248: 0x00f7, # ALMOST EQUAL TO
+ 0x2261: 0x00f0, # IDENTICAL TO
+ 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
+ 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
+ 0x2310: 0x00a9, # REVERSED NOT SIGN
+ 0x2320: 0x00f4, # TOP HALF INTEGRAL
+ 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp866.py b/Lib/encodings/cp866.py
new file mode 100644
index 0000000..bec7ae3
--- /dev/null
+++ b/Lib/encodings/cp866.py
@@ -0,0 +1,698 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP866.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp866',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: 0x0410, # CYRILLIC CAPITAL LETTER A
+ 0x0081: 0x0411, # CYRILLIC CAPITAL LETTER BE
+ 0x0082: 0x0412, # CYRILLIC CAPITAL LETTER VE
+ 0x0083: 0x0413, # CYRILLIC CAPITAL LETTER GHE
+ 0x0084: 0x0414, # CYRILLIC CAPITAL LETTER DE
+ 0x0085: 0x0415, # CYRILLIC CAPITAL LETTER IE
+ 0x0086: 0x0416, # CYRILLIC CAPITAL LETTER ZHE
+ 0x0087: 0x0417, # CYRILLIC CAPITAL LETTER ZE
+ 0x0088: 0x0418, # CYRILLIC CAPITAL LETTER I
+ 0x0089: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I
+ 0x008a: 0x041a, # CYRILLIC CAPITAL LETTER KA
+ 0x008b: 0x041b, # CYRILLIC CAPITAL LETTER EL
+ 0x008c: 0x041c, # CYRILLIC CAPITAL LETTER EM
+ 0x008d: 0x041d, # CYRILLIC CAPITAL LETTER EN
+ 0x008e: 0x041e, # CYRILLIC CAPITAL LETTER O
+ 0x008f: 0x041f, # CYRILLIC CAPITAL LETTER PE
+ 0x0090: 0x0420, # CYRILLIC CAPITAL LETTER ER
+ 0x0091: 0x0421, # CYRILLIC CAPITAL LETTER ES
+ 0x0092: 0x0422, # CYRILLIC CAPITAL LETTER TE
+ 0x0093: 0x0423, # CYRILLIC CAPITAL LETTER U
+ 0x0094: 0x0424, # CYRILLIC CAPITAL LETTER EF
+ 0x0095: 0x0425, # CYRILLIC CAPITAL LETTER HA
+ 0x0096: 0x0426, # CYRILLIC CAPITAL LETTER TSE
+ 0x0097: 0x0427, # CYRILLIC CAPITAL LETTER CHE
+ 0x0098: 0x0428, # CYRILLIC CAPITAL LETTER SHA
+ 0x0099: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA
+ 0x009a: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN
+ 0x009b: 0x042b, # CYRILLIC CAPITAL LETTER YERU
+ 0x009c: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN
+ 0x009d: 0x042d, # CYRILLIC CAPITAL LETTER E
+ 0x009e: 0x042e, # CYRILLIC CAPITAL LETTER YU
+ 0x009f: 0x042f, # CYRILLIC CAPITAL LETTER YA
+ 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A
+ 0x00a1: 0x0431, # CYRILLIC SMALL LETTER BE
+ 0x00a2: 0x0432, # CYRILLIC SMALL LETTER VE
+ 0x00a3: 0x0433, # CYRILLIC SMALL LETTER GHE
+ 0x00a4: 0x0434, # CYRILLIC SMALL LETTER DE
+ 0x00a5: 0x0435, # CYRILLIC SMALL LETTER IE
+ 0x00a6: 0x0436, # CYRILLIC SMALL LETTER ZHE
+ 0x00a7: 0x0437, # CYRILLIC SMALL LETTER ZE
+ 0x00a8: 0x0438, # CYRILLIC SMALL LETTER I
+ 0x00a9: 0x0439, # CYRILLIC SMALL LETTER SHORT I
+ 0x00aa: 0x043a, # CYRILLIC SMALL LETTER KA
+ 0x00ab: 0x043b, # CYRILLIC SMALL LETTER EL
+ 0x00ac: 0x043c, # CYRILLIC SMALL LETTER EM
+ 0x00ad: 0x043d, # CYRILLIC SMALL LETTER EN
+ 0x00ae: 0x043e, # CYRILLIC SMALL LETTER O
+ 0x00af: 0x043f, # CYRILLIC SMALL LETTER PE
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x258c, # LEFT HALF BLOCK
+ 0x00de: 0x2590, # RIGHT HALF BLOCK
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x0440, # CYRILLIC SMALL LETTER ER
+ 0x00e1: 0x0441, # CYRILLIC SMALL LETTER ES
+ 0x00e2: 0x0442, # CYRILLIC SMALL LETTER TE
+ 0x00e3: 0x0443, # CYRILLIC SMALL LETTER U
+ 0x00e4: 0x0444, # CYRILLIC SMALL LETTER EF
+ 0x00e5: 0x0445, # CYRILLIC SMALL LETTER HA
+ 0x00e6: 0x0446, # CYRILLIC SMALL LETTER TSE
+ 0x00e7: 0x0447, # CYRILLIC SMALL LETTER CHE
+ 0x00e8: 0x0448, # CYRILLIC SMALL LETTER SHA
+ 0x00e9: 0x0449, # CYRILLIC SMALL LETTER SHCHA
+ 0x00ea: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN
+ 0x00eb: 0x044b, # CYRILLIC SMALL LETTER YERU
+ 0x00ec: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN
+ 0x00ed: 0x044d, # CYRILLIC SMALL LETTER E
+ 0x00ee: 0x044e, # CYRILLIC SMALL LETTER YU
+ 0x00ef: 0x044f, # CYRILLIC SMALL LETTER YA
+ 0x00f0: 0x0401, # CYRILLIC CAPITAL LETTER IO
+ 0x00f1: 0x0451, # CYRILLIC SMALL LETTER IO
+ 0x00f2: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ 0x00f3: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE
+ 0x00f4: 0x0407, # CYRILLIC CAPITAL LETTER YI
+ 0x00f5: 0x0457, # CYRILLIC SMALL LETTER YI
+ 0x00f6: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U
+ 0x00f7: 0x045e, # CYRILLIC SMALL LETTER SHORT U
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x2219, # BULLET OPERATOR
+ 0x00fa: 0x00b7, # MIDDLE DOT
+ 0x00fb: 0x221a, # SQUARE ROOT
+ 0x00fc: 0x2116, # NUMERO SIGN
+ 0x00fd: 0x00a4, # CURRENCY SIGN
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\u0410' # 0x0080 -> CYRILLIC CAPITAL LETTER A
+ '\u0411' # 0x0081 -> CYRILLIC CAPITAL LETTER BE
+ '\u0412' # 0x0082 -> CYRILLIC CAPITAL LETTER VE
+ '\u0413' # 0x0083 -> CYRILLIC CAPITAL LETTER GHE
+ '\u0414' # 0x0084 -> CYRILLIC CAPITAL LETTER DE
+ '\u0415' # 0x0085 -> CYRILLIC CAPITAL LETTER IE
+ '\u0416' # 0x0086 -> CYRILLIC CAPITAL LETTER ZHE
+ '\u0417' # 0x0087 -> CYRILLIC CAPITAL LETTER ZE
+ '\u0418' # 0x0088 -> CYRILLIC CAPITAL LETTER I
+ '\u0419' # 0x0089 -> CYRILLIC CAPITAL LETTER SHORT I
+ '\u041a' # 0x008a -> CYRILLIC CAPITAL LETTER KA
+ '\u041b' # 0x008b -> CYRILLIC CAPITAL LETTER EL
+ '\u041c' # 0x008c -> CYRILLIC CAPITAL LETTER EM
+ '\u041d' # 0x008d -> CYRILLIC CAPITAL LETTER EN
+ '\u041e' # 0x008e -> CYRILLIC CAPITAL LETTER O
+ '\u041f' # 0x008f -> CYRILLIC CAPITAL LETTER PE
+ '\u0420' # 0x0090 -> CYRILLIC CAPITAL LETTER ER
+ '\u0421' # 0x0091 -> CYRILLIC CAPITAL LETTER ES
+ '\u0422' # 0x0092 -> CYRILLIC CAPITAL LETTER TE
+ '\u0423' # 0x0093 -> CYRILLIC CAPITAL LETTER U
+ '\u0424' # 0x0094 -> CYRILLIC CAPITAL LETTER EF
+ '\u0425' # 0x0095 -> CYRILLIC CAPITAL LETTER HA
+ '\u0426' # 0x0096 -> CYRILLIC CAPITAL LETTER TSE
+ '\u0427' # 0x0097 -> CYRILLIC CAPITAL LETTER CHE
+ '\u0428' # 0x0098 -> CYRILLIC CAPITAL LETTER SHA
+ '\u0429' # 0x0099 -> CYRILLIC CAPITAL LETTER SHCHA
+ '\u042a' # 0x009a -> CYRILLIC CAPITAL LETTER HARD SIGN
+ '\u042b' # 0x009b -> CYRILLIC CAPITAL LETTER YERU
+ '\u042c' # 0x009c -> CYRILLIC CAPITAL LETTER SOFT SIGN
+ '\u042d' # 0x009d -> CYRILLIC CAPITAL LETTER E
+ '\u042e' # 0x009e -> CYRILLIC CAPITAL LETTER YU
+ '\u042f' # 0x009f -> CYRILLIC CAPITAL LETTER YA
+ '\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A
+ '\u0431' # 0x00a1 -> CYRILLIC SMALL LETTER BE
+ '\u0432' # 0x00a2 -> CYRILLIC SMALL LETTER VE
+ '\u0433' # 0x00a3 -> CYRILLIC SMALL LETTER GHE
+ '\u0434' # 0x00a4 -> CYRILLIC SMALL LETTER DE
+ '\u0435' # 0x00a5 -> CYRILLIC SMALL LETTER IE
+ '\u0436' # 0x00a6 -> CYRILLIC SMALL LETTER ZHE
+ '\u0437' # 0x00a7 -> CYRILLIC SMALL LETTER ZE
+ '\u0438' # 0x00a8 -> CYRILLIC SMALL LETTER I
+ '\u0439' # 0x00a9 -> CYRILLIC SMALL LETTER SHORT I
+ '\u043a' # 0x00aa -> CYRILLIC SMALL LETTER KA
+ '\u043b' # 0x00ab -> CYRILLIC SMALL LETTER EL
+ '\u043c' # 0x00ac -> CYRILLIC SMALL LETTER EM
+ '\u043d' # 0x00ad -> CYRILLIC SMALL LETTER EN
+ '\u043e' # 0x00ae -> CYRILLIC SMALL LETTER O
+ '\u043f' # 0x00af -> CYRILLIC SMALL LETTER PE
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u258c' # 0x00dd -> LEFT HALF BLOCK
+ '\u2590' # 0x00de -> RIGHT HALF BLOCK
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u0440' # 0x00e0 -> CYRILLIC SMALL LETTER ER
+ '\u0441' # 0x00e1 -> CYRILLIC SMALL LETTER ES
+ '\u0442' # 0x00e2 -> CYRILLIC SMALL LETTER TE
+ '\u0443' # 0x00e3 -> CYRILLIC SMALL LETTER U
+ '\u0444' # 0x00e4 -> CYRILLIC SMALL LETTER EF
+ '\u0445' # 0x00e5 -> CYRILLIC SMALL LETTER HA
+ '\u0446' # 0x00e6 -> CYRILLIC SMALL LETTER TSE
+ '\u0447' # 0x00e7 -> CYRILLIC SMALL LETTER CHE
+ '\u0448' # 0x00e8 -> CYRILLIC SMALL LETTER SHA
+ '\u0449' # 0x00e9 -> CYRILLIC SMALL LETTER SHCHA
+ '\u044a' # 0x00ea -> CYRILLIC SMALL LETTER HARD SIGN
+ '\u044b' # 0x00eb -> CYRILLIC SMALL LETTER YERU
+ '\u044c' # 0x00ec -> CYRILLIC SMALL LETTER SOFT SIGN
+ '\u044d' # 0x00ed -> CYRILLIC SMALL LETTER E
+ '\u044e' # 0x00ee -> CYRILLIC SMALL LETTER YU
+ '\u044f' # 0x00ef -> CYRILLIC SMALL LETTER YA
+ '\u0401' # 0x00f0 -> CYRILLIC CAPITAL LETTER IO
+ '\u0451' # 0x00f1 -> CYRILLIC SMALL LETTER IO
+ '\u0404' # 0x00f2 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ '\u0454' # 0x00f3 -> CYRILLIC SMALL LETTER UKRAINIAN IE
+ '\u0407' # 0x00f4 -> CYRILLIC CAPITAL LETTER YI
+ '\u0457' # 0x00f5 -> CYRILLIC SMALL LETTER YI
+ '\u040e' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHORT U
+ '\u045e' # 0x00f7 -> CYRILLIC SMALL LETTER SHORT U
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\u2219' # 0x00f9 -> BULLET OPERATOR
+ '\xb7' # 0x00fa -> MIDDLE DOT
+ '\u221a' # 0x00fb -> SQUARE ROOT
+ '\u2116' # 0x00fc -> NUMERO SIGN
+ '\xa4' # 0x00fd -> CURRENCY SIGN
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a4: 0x00fd, # CURRENCY SIGN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b7: 0x00fa, # MIDDLE DOT
+ 0x0401: 0x00f0, # CYRILLIC CAPITAL LETTER IO
+ 0x0404: 0x00f2, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
+ 0x0407: 0x00f4, # CYRILLIC CAPITAL LETTER YI
+ 0x040e: 0x00f6, # CYRILLIC CAPITAL LETTER SHORT U
+ 0x0410: 0x0080, # CYRILLIC CAPITAL LETTER A
+ 0x0411: 0x0081, # CYRILLIC CAPITAL LETTER BE
+ 0x0412: 0x0082, # CYRILLIC CAPITAL LETTER VE
+ 0x0413: 0x0083, # CYRILLIC CAPITAL LETTER GHE
+ 0x0414: 0x0084, # CYRILLIC CAPITAL LETTER DE
+ 0x0415: 0x0085, # CYRILLIC CAPITAL LETTER IE
+ 0x0416: 0x0086, # CYRILLIC CAPITAL LETTER ZHE
+ 0x0417: 0x0087, # CYRILLIC CAPITAL LETTER ZE
+ 0x0418: 0x0088, # CYRILLIC CAPITAL LETTER I
+ 0x0419: 0x0089, # CYRILLIC CAPITAL LETTER SHORT I
+ 0x041a: 0x008a, # CYRILLIC CAPITAL LETTER KA
+ 0x041b: 0x008b, # CYRILLIC CAPITAL LETTER EL
+ 0x041c: 0x008c, # CYRILLIC CAPITAL LETTER EM
+ 0x041d: 0x008d, # CYRILLIC CAPITAL LETTER EN
+ 0x041e: 0x008e, # CYRILLIC CAPITAL LETTER O
+ 0x041f: 0x008f, # CYRILLIC CAPITAL LETTER PE
+ 0x0420: 0x0090, # CYRILLIC CAPITAL LETTER ER
+ 0x0421: 0x0091, # CYRILLIC CAPITAL LETTER ES
+ 0x0422: 0x0092, # CYRILLIC CAPITAL LETTER TE
+ 0x0423: 0x0093, # CYRILLIC CAPITAL LETTER U
+ 0x0424: 0x0094, # CYRILLIC CAPITAL LETTER EF
+ 0x0425: 0x0095, # CYRILLIC CAPITAL LETTER HA
+ 0x0426: 0x0096, # CYRILLIC CAPITAL LETTER TSE
+ 0x0427: 0x0097, # CYRILLIC CAPITAL LETTER CHE
+ 0x0428: 0x0098, # CYRILLIC CAPITAL LETTER SHA
+ 0x0429: 0x0099, # CYRILLIC CAPITAL LETTER SHCHA
+ 0x042a: 0x009a, # CYRILLIC CAPITAL LETTER HARD SIGN
+ 0x042b: 0x009b, # CYRILLIC CAPITAL LETTER YERU
+ 0x042c: 0x009c, # CYRILLIC CAPITAL LETTER SOFT SIGN
+ 0x042d: 0x009d, # CYRILLIC CAPITAL LETTER E
+ 0x042e: 0x009e, # CYRILLIC CAPITAL LETTER YU
+ 0x042f: 0x009f, # CYRILLIC CAPITAL LETTER YA
+ 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A
+ 0x0431: 0x00a1, # CYRILLIC SMALL LETTER BE
+ 0x0432: 0x00a2, # CYRILLIC SMALL LETTER VE
+ 0x0433: 0x00a3, # CYRILLIC SMALL LETTER GHE
+ 0x0434: 0x00a4, # CYRILLIC SMALL LETTER DE
+ 0x0435: 0x00a5, # CYRILLIC SMALL LETTER IE
+ 0x0436: 0x00a6, # CYRILLIC SMALL LETTER ZHE
+ 0x0437: 0x00a7, # CYRILLIC SMALL LETTER ZE
+ 0x0438: 0x00a8, # CYRILLIC SMALL LETTER I
+ 0x0439: 0x00a9, # CYRILLIC SMALL LETTER SHORT I
+ 0x043a: 0x00aa, # CYRILLIC SMALL LETTER KA
+ 0x043b: 0x00ab, # CYRILLIC SMALL LETTER EL
+ 0x043c: 0x00ac, # CYRILLIC SMALL LETTER EM
+ 0x043d: 0x00ad, # CYRILLIC SMALL LETTER EN
+ 0x043e: 0x00ae, # CYRILLIC SMALL LETTER O
+ 0x043f: 0x00af, # CYRILLIC SMALL LETTER PE
+ 0x0440: 0x00e0, # CYRILLIC SMALL LETTER ER
+ 0x0441: 0x00e1, # CYRILLIC SMALL LETTER ES
+ 0x0442: 0x00e2, # CYRILLIC SMALL LETTER TE
+ 0x0443: 0x00e3, # CYRILLIC SMALL LETTER U
+ 0x0444: 0x00e4, # CYRILLIC SMALL LETTER EF
+ 0x0445: 0x00e5, # CYRILLIC SMALL LETTER HA
+ 0x0446: 0x00e6, # CYRILLIC SMALL LETTER TSE
+ 0x0447: 0x00e7, # CYRILLIC SMALL LETTER CHE
+ 0x0448: 0x00e8, # CYRILLIC SMALL LETTER SHA
+ 0x0449: 0x00e9, # CYRILLIC SMALL LETTER SHCHA
+ 0x044a: 0x00ea, # CYRILLIC SMALL LETTER HARD SIGN
+ 0x044b: 0x00eb, # CYRILLIC SMALL LETTER YERU
+ 0x044c: 0x00ec, # CYRILLIC SMALL LETTER SOFT SIGN
+ 0x044d: 0x00ed, # CYRILLIC SMALL LETTER E
+ 0x044e: 0x00ee, # CYRILLIC SMALL LETTER YU
+ 0x044f: 0x00ef, # CYRILLIC SMALL LETTER YA
+ 0x0451: 0x00f1, # CYRILLIC SMALL LETTER IO
+ 0x0454: 0x00f3, # CYRILLIC SMALL LETTER UKRAINIAN IE
+ 0x0457: 0x00f5, # CYRILLIC SMALL LETTER YI
+ 0x045e: 0x00f7, # CYRILLIC SMALL LETTER SHORT U
+ 0x2116: 0x00fc, # NUMERO SIGN
+ 0x2219: 0x00f9, # BULLET OPERATOR
+ 0x221a: 0x00fb, # SQUARE ROOT
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
+ 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
+ 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
+ 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
+ 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
+ 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
+ 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
+ 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
+ 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
+ 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x258c: 0x00dd, # LEFT HALF BLOCK
+ 0x2590: 0x00de, # RIGHT HALF BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp869.py b/Lib/encodings/cp869.py
new file mode 100644
index 0000000..8d8a29b
--- /dev/null
+++ b/Lib/encodings/cp869.py
@@ -0,0 +1,689 @@
+""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP869.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_map)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_map)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp869',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+### Decoding Map
+
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
+ 0x0080: None, # UNDEFINED
+ 0x0081: None, # UNDEFINED
+ 0x0082: None, # UNDEFINED
+ 0x0083: None, # UNDEFINED
+ 0x0084: None, # UNDEFINED
+ 0x0085: None, # UNDEFINED
+ 0x0086: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
+ 0x0087: None, # UNDEFINED
+ 0x0088: 0x00b7, # MIDDLE DOT
+ 0x0089: 0x00ac, # NOT SIGN
+ 0x008a: 0x00a6, # BROKEN BAR
+ 0x008b: 0x2018, # LEFT SINGLE QUOTATION MARK
+ 0x008c: 0x2019, # RIGHT SINGLE QUOTATION MARK
+ 0x008d: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
+ 0x008e: 0x2015, # HORIZONTAL BAR
+ 0x008f: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
+ 0x0090: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
+ 0x0091: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ 0x0092: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
+ 0x0093: None, # UNDEFINED
+ 0x0094: None, # UNDEFINED
+ 0x0095: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
+ 0x0096: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ 0x0097: 0x00a9, # COPYRIGHT SIGN
+ 0x0098: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
+ 0x0099: 0x00b2, # SUPERSCRIPT TWO
+ 0x009a: 0x00b3, # SUPERSCRIPT THREE
+ 0x009b: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
+ 0x009c: 0x00a3, # POUND SIGN
+ 0x009d: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
+ 0x009e: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
+ 0x009f: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
+ 0x00a0: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ 0x00a1: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ 0x00a2: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
+ 0x00a3: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
+ 0x00a4: 0x0391, # GREEK CAPITAL LETTER ALPHA
+ 0x00a5: 0x0392, # GREEK CAPITAL LETTER BETA
+ 0x00a6: 0x0393, # GREEK CAPITAL LETTER GAMMA
+ 0x00a7: 0x0394, # GREEK CAPITAL LETTER DELTA
+ 0x00a8: 0x0395, # GREEK CAPITAL LETTER EPSILON
+ 0x00a9: 0x0396, # GREEK CAPITAL LETTER ZETA
+ 0x00aa: 0x0397, # GREEK CAPITAL LETTER ETA
+ 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
+ 0x00ac: 0x0398, # GREEK CAPITAL LETTER THETA
+ 0x00ad: 0x0399, # GREEK CAPITAL LETTER IOTA
+ 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00b0: 0x2591, # LIGHT SHADE
+ 0x00b1: 0x2592, # MEDIUM SHADE
+ 0x00b2: 0x2593, # DARK SHADE
+ 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
+ 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x00b5: 0x039a, # GREEK CAPITAL LETTER KAPPA
+ 0x00b6: 0x039b, # GREEK CAPITAL LETTER LAMDA
+ 0x00b7: 0x039c, # GREEK CAPITAL LETTER MU
+ 0x00b8: 0x039d, # GREEK CAPITAL LETTER NU
+ 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x00bd: 0x039e, # GREEK CAPITAL LETTER XI
+ 0x00be: 0x039f, # GREEK CAPITAL LETTER OMICRON
+ 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x00c6: 0x03a0, # GREEK CAPITAL LETTER PI
+ 0x00c7: 0x03a1, # GREEK CAPITAL LETTER RHO
+ 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x00cf: 0x03a3, # GREEK CAPITAL LETTER SIGMA
+ 0x00d0: 0x03a4, # GREEK CAPITAL LETTER TAU
+ 0x00d1: 0x03a5, # GREEK CAPITAL LETTER UPSILON
+ 0x00d2: 0x03a6, # GREEK CAPITAL LETTER PHI
+ 0x00d3: 0x03a7, # GREEK CAPITAL LETTER CHI
+ 0x00d4: 0x03a8, # GREEK CAPITAL LETTER PSI
+ 0x00d5: 0x03a9, # GREEK CAPITAL LETTER OMEGA
+ 0x00d6: 0x03b1, # GREEK SMALL LETTER ALPHA
+ 0x00d7: 0x03b2, # GREEK SMALL LETTER BETA
+ 0x00d8: 0x03b3, # GREEK SMALL LETTER GAMMA
+ 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x00db: 0x2588, # FULL BLOCK
+ 0x00dc: 0x2584, # LOWER HALF BLOCK
+ 0x00dd: 0x03b4, # GREEK SMALL LETTER DELTA
+ 0x00de: 0x03b5, # GREEK SMALL LETTER EPSILON
+ 0x00df: 0x2580, # UPPER HALF BLOCK
+ 0x00e0: 0x03b6, # GREEK SMALL LETTER ZETA
+ 0x00e1: 0x03b7, # GREEK SMALL LETTER ETA
+ 0x00e2: 0x03b8, # GREEK SMALL LETTER THETA
+ 0x00e3: 0x03b9, # GREEK SMALL LETTER IOTA
+ 0x00e4: 0x03ba, # GREEK SMALL LETTER KAPPA
+ 0x00e5: 0x03bb, # GREEK SMALL LETTER LAMDA
+ 0x00e6: 0x03bc, # GREEK SMALL LETTER MU
+ 0x00e7: 0x03bd, # GREEK SMALL LETTER NU
+ 0x00e8: 0x03be, # GREEK SMALL LETTER XI
+ 0x00e9: 0x03bf, # GREEK SMALL LETTER OMICRON
+ 0x00ea: 0x03c0, # GREEK SMALL LETTER PI
+ 0x00eb: 0x03c1, # GREEK SMALL LETTER RHO
+ 0x00ec: 0x03c3, # GREEK SMALL LETTER SIGMA
+ 0x00ed: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
+ 0x00ee: 0x03c4, # GREEK SMALL LETTER TAU
+ 0x00ef: 0x0384, # GREEK TONOS
+ 0x00f0: 0x00ad, # SOFT HYPHEN
+ 0x00f1: 0x00b1, # PLUS-MINUS SIGN
+ 0x00f2: 0x03c5, # GREEK SMALL LETTER UPSILON
+ 0x00f3: 0x03c6, # GREEK SMALL LETTER PHI
+ 0x00f4: 0x03c7, # GREEK SMALL LETTER CHI
+ 0x00f5: 0x00a7, # SECTION SIGN
+ 0x00f6: 0x03c8, # GREEK SMALL LETTER PSI
+ 0x00f7: 0x0385, # GREEK DIALYTIKA TONOS
+ 0x00f8: 0x00b0, # DEGREE SIGN
+ 0x00f9: 0x00a8, # DIAERESIS
+ 0x00fa: 0x03c9, # GREEK SMALL LETTER OMEGA
+ 0x00fb: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ 0x00fc: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ 0x00fd: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
+ 0x00fe: 0x25a0, # BLACK SQUARE
+ 0x00ff: 0x00a0, # NO-BREAK SPACE
+})
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x0000 -> NULL
+ '\x01' # 0x0001 -> START OF HEADING
+ '\x02' # 0x0002 -> START OF TEXT
+ '\x03' # 0x0003 -> END OF TEXT
+ '\x04' # 0x0004 -> END OF TRANSMISSION
+ '\x05' # 0x0005 -> ENQUIRY
+ '\x06' # 0x0006 -> ACKNOWLEDGE
+ '\x07' # 0x0007 -> BELL
+ '\x08' # 0x0008 -> BACKSPACE
+ '\t' # 0x0009 -> HORIZONTAL TABULATION
+ '\n' # 0x000a -> LINE FEED
+ '\x0b' # 0x000b -> VERTICAL TABULATION
+ '\x0c' # 0x000c -> FORM FEED
+ '\r' # 0x000d -> CARRIAGE RETURN
+ '\x0e' # 0x000e -> SHIFT OUT
+ '\x0f' # 0x000f -> SHIFT IN
+ '\x10' # 0x0010 -> DATA LINK ESCAPE
+ '\x11' # 0x0011 -> DEVICE CONTROL ONE
+ '\x12' # 0x0012 -> DEVICE CONTROL TWO
+ '\x13' # 0x0013 -> DEVICE CONTROL THREE
+ '\x14' # 0x0014 -> DEVICE CONTROL FOUR
+ '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x0016 -> SYNCHRONOUS IDLE
+ '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x0018 -> CANCEL
+ '\x19' # 0x0019 -> END OF MEDIUM
+ '\x1a' # 0x001a -> SUBSTITUTE
+ '\x1b' # 0x001b -> ESCAPE
+ '\x1c' # 0x001c -> FILE SEPARATOR
+ '\x1d' # 0x001d -> GROUP SEPARATOR
+ '\x1e' # 0x001e -> RECORD SEPARATOR
+ '\x1f' # 0x001f -> UNIT SEPARATOR
+ ' ' # 0x0020 -> SPACE
+ '!' # 0x0021 -> EXCLAMATION MARK
+ '"' # 0x0022 -> QUOTATION MARK
+ '#' # 0x0023 -> NUMBER SIGN
+ '$' # 0x0024 -> DOLLAR SIGN
+ '%' # 0x0025 -> PERCENT SIGN
+ '&' # 0x0026 -> AMPERSAND
+ "'" # 0x0027 -> APOSTROPHE
+ '(' # 0x0028 -> LEFT PARENTHESIS
+ ')' # 0x0029 -> RIGHT PARENTHESIS
+ '*' # 0x002a -> ASTERISK
+ '+' # 0x002b -> PLUS SIGN
+ ',' # 0x002c -> COMMA
+ '-' # 0x002d -> HYPHEN-MINUS
+ '.' # 0x002e -> FULL STOP
+ '/' # 0x002f -> SOLIDUS
+ '0' # 0x0030 -> DIGIT ZERO
+ '1' # 0x0031 -> DIGIT ONE
+ '2' # 0x0032 -> DIGIT TWO
+ '3' # 0x0033 -> DIGIT THREE
+ '4' # 0x0034 -> DIGIT FOUR
+ '5' # 0x0035 -> DIGIT FIVE
+ '6' # 0x0036 -> DIGIT SIX
+ '7' # 0x0037 -> DIGIT SEVEN
+ '8' # 0x0038 -> DIGIT EIGHT
+ '9' # 0x0039 -> DIGIT NINE
+ ':' # 0x003a -> COLON
+ ';' # 0x003b -> SEMICOLON
+ '<' # 0x003c -> LESS-THAN SIGN
+ '=' # 0x003d -> EQUALS SIGN
+ '>' # 0x003e -> GREATER-THAN SIGN
+ '?' # 0x003f -> QUESTION MARK
+ '@' # 0x0040 -> COMMERCIAL AT
+ 'A' # 0x0041 -> LATIN CAPITAL LETTER A
+ 'B' # 0x0042 -> LATIN CAPITAL LETTER B
+ 'C' # 0x0043 -> LATIN CAPITAL LETTER C
+ 'D' # 0x0044 -> LATIN CAPITAL LETTER D
+ 'E' # 0x0045 -> LATIN CAPITAL LETTER E
+ 'F' # 0x0046 -> LATIN CAPITAL LETTER F
+ 'G' # 0x0047 -> LATIN CAPITAL LETTER G
+ 'H' # 0x0048 -> LATIN CAPITAL LETTER H
+ 'I' # 0x0049 -> LATIN CAPITAL LETTER I
+ 'J' # 0x004a -> LATIN CAPITAL LETTER J
+ 'K' # 0x004b -> LATIN CAPITAL LETTER K
+ 'L' # 0x004c -> LATIN CAPITAL LETTER L
+ 'M' # 0x004d -> LATIN CAPITAL LETTER M
+ 'N' # 0x004e -> LATIN CAPITAL LETTER N
+ 'O' # 0x004f -> LATIN CAPITAL LETTER O
+ 'P' # 0x0050 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x0052 -> LATIN CAPITAL LETTER R
+ 'S' # 0x0053 -> LATIN CAPITAL LETTER S
+ 'T' # 0x0054 -> LATIN CAPITAL LETTER T
+ 'U' # 0x0055 -> LATIN CAPITAL LETTER U
+ 'V' # 0x0056 -> LATIN CAPITAL LETTER V
+ 'W' # 0x0057 -> LATIN CAPITAL LETTER W
+ 'X' # 0x0058 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x005a -> LATIN CAPITAL LETTER Z
+ '[' # 0x005b -> LEFT SQUARE BRACKET
+ '\\' # 0x005c -> REVERSE SOLIDUS
+ ']' # 0x005d -> RIGHT SQUARE BRACKET
+ '^' # 0x005e -> CIRCUMFLEX ACCENT
+ '_' # 0x005f -> LOW LINE
+ '`' # 0x0060 -> GRAVE ACCENT
+ 'a' # 0x0061 -> LATIN SMALL LETTER A
+ 'b' # 0x0062 -> LATIN SMALL LETTER B
+ 'c' # 0x0063 -> LATIN SMALL LETTER C
+ 'd' # 0x0064 -> LATIN SMALL LETTER D
+ 'e' # 0x0065 -> LATIN SMALL LETTER E
+ 'f' # 0x0066 -> LATIN SMALL LETTER F
+ 'g' # 0x0067 -> LATIN SMALL LETTER G
+ 'h' # 0x0068 -> LATIN SMALL LETTER H
+ 'i' # 0x0069 -> LATIN SMALL LETTER I
+ 'j' # 0x006a -> LATIN SMALL LETTER J
+ 'k' # 0x006b -> LATIN SMALL LETTER K
+ 'l' # 0x006c -> LATIN SMALL LETTER L
+ 'm' # 0x006d -> LATIN SMALL LETTER M
+ 'n' # 0x006e -> LATIN SMALL LETTER N
+ 'o' # 0x006f -> LATIN SMALL LETTER O
+ 'p' # 0x0070 -> LATIN SMALL LETTER P
+ 'q' # 0x0071 -> LATIN SMALL LETTER Q
+ 'r' # 0x0072 -> LATIN SMALL LETTER R
+ 's' # 0x0073 -> LATIN SMALL LETTER S
+ 't' # 0x0074 -> LATIN SMALL LETTER T
+ 'u' # 0x0075 -> LATIN SMALL LETTER U
+ 'v' # 0x0076 -> LATIN SMALL LETTER V
+ 'w' # 0x0077 -> LATIN SMALL LETTER W
+ 'x' # 0x0078 -> LATIN SMALL LETTER X
+ 'y' # 0x0079 -> LATIN SMALL LETTER Y
+ 'z' # 0x007a -> LATIN SMALL LETTER Z
+ '{' # 0x007b -> LEFT CURLY BRACKET
+ '|' # 0x007c -> VERTICAL LINE
+ '}' # 0x007d -> RIGHT CURLY BRACKET
+ '~' # 0x007e -> TILDE
+ '\x7f' # 0x007f -> DELETE
+ '\ufffe' # 0x0080 -> UNDEFINED
+ '\ufffe' # 0x0081 -> UNDEFINED
+ '\ufffe' # 0x0082 -> UNDEFINED
+ '\ufffe' # 0x0083 -> UNDEFINED
+ '\ufffe' # 0x0084 -> UNDEFINED
+ '\ufffe' # 0x0085 -> UNDEFINED
+ '\u0386' # 0x0086 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
+ '\ufffe' # 0x0087 -> UNDEFINED
+ '\xb7' # 0x0088 -> MIDDLE DOT
+ '\xac' # 0x0089 -> NOT SIGN
+ '\xa6' # 0x008a -> BROKEN BAR
+ '\u2018' # 0x008b -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x008c -> RIGHT SINGLE QUOTATION MARK
+ '\u0388' # 0x008d -> GREEK CAPITAL LETTER EPSILON WITH TONOS
+ '\u2015' # 0x008e -> HORIZONTAL BAR
+ '\u0389' # 0x008f -> GREEK CAPITAL LETTER ETA WITH TONOS
+ '\u038a' # 0x0090 -> GREEK CAPITAL LETTER IOTA WITH TONOS
+ '\u03aa' # 0x0091 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ '\u038c' # 0x0092 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
+ '\ufffe' # 0x0093 -> UNDEFINED
+ '\ufffe' # 0x0094 -> UNDEFINED
+ '\u038e' # 0x0095 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
+ '\u03ab' # 0x0096 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ '\xa9' # 0x0097 -> COPYRIGHT SIGN
+ '\u038f' # 0x0098 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
+ '\xb2' # 0x0099 -> SUPERSCRIPT TWO
+ '\xb3' # 0x009a -> SUPERSCRIPT THREE
+ '\u03ac' # 0x009b -> GREEK SMALL LETTER ALPHA WITH TONOS
+ '\xa3' # 0x009c -> POUND SIGN
+ '\u03ad' # 0x009d -> GREEK SMALL LETTER EPSILON WITH TONOS
+ '\u03ae' # 0x009e -> GREEK SMALL LETTER ETA WITH TONOS
+ '\u03af' # 0x009f -> GREEK SMALL LETTER IOTA WITH TONOS
+ '\u03ca' # 0x00a0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ '\u0390' # 0x00a1 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ '\u03cc' # 0x00a2 -> GREEK SMALL LETTER OMICRON WITH TONOS
+ '\u03cd' # 0x00a3 -> GREEK SMALL LETTER UPSILON WITH TONOS
+ '\u0391' # 0x00a4 -> GREEK CAPITAL LETTER ALPHA
+ '\u0392' # 0x00a5 -> GREEK CAPITAL LETTER BETA
+ '\u0393' # 0x00a6 -> GREEK CAPITAL LETTER GAMMA
+ '\u0394' # 0x00a7 -> GREEK CAPITAL LETTER DELTA
+ '\u0395' # 0x00a8 -> GREEK CAPITAL LETTER EPSILON
+ '\u0396' # 0x00a9 -> GREEK CAPITAL LETTER ZETA
+ '\u0397' # 0x00aa -> GREEK CAPITAL LETTER ETA
+ '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
+ '\u0398' # 0x00ac -> GREEK CAPITAL LETTER THETA
+ '\u0399' # 0x00ad -> GREEK CAPITAL LETTER IOTA
+ '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u2591' # 0x00b0 -> LIGHT SHADE
+ '\u2592' # 0x00b1 -> MEDIUM SHADE
+ '\u2593' # 0x00b2 -> DARK SHADE
+ '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
+ '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ '\u039a' # 0x00b5 -> GREEK CAPITAL LETTER KAPPA
+ '\u039b' # 0x00b6 -> GREEK CAPITAL LETTER LAMDA
+ '\u039c' # 0x00b7 -> GREEK CAPITAL LETTER MU
+ '\u039d' # 0x00b8 -> GREEK CAPITAL LETTER NU
+ '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
+ '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
+ '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
+ '\u039e' # 0x00bd -> GREEK CAPITAL LETTER XI
+ '\u039f' # 0x00be -> GREEK CAPITAL LETTER OMICRON
+ '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
+ '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
+ '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
+ '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ '\u03a0' # 0x00c6 -> GREEK CAPITAL LETTER PI
+ '\u03a1' # 0x00c7 -> GREEK CAPITAL LETTER RHO
+ '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
+ '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
+ '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ '\u03a3' # 0x00cf -> GREEK CAPITAL LETTER SIGMA
+ '\u03a4' # 0x00d0 -> GREEK CAPITAL LETTER TAU
+ '\u03a5' # 0x00d1 -> GREEK CAPITAL LETTER UPSILON
+ '\u03a6' # 0x00d2 -> GREEK CAPITAL LETTER PHI
+ '\u03a7' # 0x00d3 -> GREEK CAPITAL LETTER CHI
+ '\u03a8' # 0x00d4 -> GREEK CAPITAL LETTER PSI
+ '\u03a9' # 0x00d5 -> GREEK CAPITAL LETTER OMEGA
+ '\u03b1' # 0x00d6 -> GREEK SMALL LETTER ALPHA
+ '\u03b2' # 0x00d7 -> GREEK SMALL LETTER BETA
+ '\u03b3' # 0x00d8 -> GREEK SMALL LETTER GAMMA
+ '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
+ '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
+ '\u2588' # 0x00db -> FULL BLOCK
+ '\u2584' # 0x00dc -> LOWER HALF BLOCK
+ '\u03b4' # 0x00dd -> GREEK SMALL LETTER DELTA
+ '\u03b5' # 0x00de -> GREEK SMALL LETTER EPSILON
+ '\u2580' # 0x00df -> UPPER HALF BLOCK
+ '\u03b6' # 0x00e0 -> GREEK SMALL LETTER ZETA
+ '\u03b7' # 0x00e1 -> GREEK SMALL LETTER ETA
+ '\u03b8' # 0x00e2 -> GREEK SMALL LETTER THETA
+ '\u03b9' # 0x00e3 -> GREEK SMALL LETTER IOTA
+ '\u03ba' # 0x00e4 -> GREEK SMALL LETTER KAPPA
+ '\u03bb' # 0x00e5 -> GREEK SMALL LETTER LAMDA
+ '\u03bc' # 0x00e6 -> GREEK SMALL LETTER MU
+ '\u03bd' # 0x00e7 -> GREEK SMALL LETTER NU
+ '\u03be' # 0x00e8 -> GREEK SMALL LETTER XI
+ '\u03bf' # 0x00e9 -> GREEK SMALL LETTER OMICRON
+ '\u03c0' # 0x00ea -> GREEK SMALL LETTER PI
+ '\u03c1' # 0x00eb -> GREEK SMALL LETTER RHO
+ '\u03c3' # 0x00ec -> GREEK SMALL LETTER SIGMA
+ '\u03c2' # 0x00ed -> GREEK SMALL LETTER FINAL SIGMA
+ '\u03c4' # 0x00ee -> GREEK SMALL LETTER TAU
+ '\u0384' # 0x00ef -> GREEK TONOS
+ '\xad' # 0x00f0 -> SOFT HYPHEN
+ '\xb1' # 0x00f1 -> PLUS-MINUS SIGN
+ '\u03c5' # 0x00f2 -> GREEK SMALL LETTER UPSILON
+ '\u03c6' # 0x00f3 -> GREEK SMALL LETTER PHI
+ '\u03c7' # 0x00f4 -> GREEK SMALL LETTER CHI
+ '\xa7' # 0x00f5 -> SECTION SIGN
+ '\u03c8' # 0x00f6 -> GREEK SMALL LETTER PSI
+ '\u0385' # 0x00f7 -> GREEK DIALYTIKA TONOS
+ '\xb0' # 0x00f8 -> DEGREE SIGN
+ '\xa8' # 0x00f9 -> DIAERESIS
+ '\u03c9' # 0x00fa -> GREEK SMALL LETTER OMEGA
+ '\u03cb' # 0x00fb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ '\u03b0' # 0x00fc -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ '\u03ce' # 0x00fd -> GREEK SMALL LETTER OMEGA WITH TONOS
+ '\u25a0' # 0x00fe -> BLACK SQUARE
+ '\xa0' # 0x00ff -> NO-BREAK SPACE
+)
+
+### Encoding Map
+
+encoding_map = {
+ 0x0000: 0x0000, # NULL
+ 0x0001: 0x0001, # START OF HEADING
+ 0x0002: 0x0002, # START OF TEXT
+ 0x0003: 0x0003, # END OF TEXT
+ 0x0004: 0x0004, # END OF TRANSMISSION
+ 0x0005: 0x0005, # ENQUIRY
+ 0x0006: 0x0006, # ACKNOWLEDGE
+ 0x0007: 0x0007, # BELL
+ 0x0008: 0x0008, # BACKSPACE
+ 0x0009: 0x0009, # HORIZONTAL TABULATION
+ 0x000a: 0x000a, # LINE FEED
+ 0x000b: 0x000b, # VERTICAL TABULATION
+ 0x000c: 0x000c, # FORM FEED
+ 0x000d: 0x000d, # CARRIAGE RETURN
+ 0x000e: 0x000e, # SHIFT OUT
+ 0x000f: 0x000f, # SHIFT IN
+ 0x0010: 0x0010, # DATA LINK ESCAPE
+ 0x0011: 0x0011, # DEVICE CONTROL ONE
+ 0x0012: 0x0012, # DEVICE CONTROL TWO
+ 0x0013: 0x0013, # DEVICE CONTROL THREE
+ 0x0014: 0x0014, # DEVICE CONTROL FOUR
+ 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
+ 0x0016: 0x0016, # SYNCHRONOUS IDLE
+ 0x0017: 0x0017, # END OF TRANSMISSION BLOCK
+ 0x0018: 0x0018, # CANCEL
+ 0x0019: 0x0019, # END OF MEDIUM
+ 0x001a: 0x001a, # SUBSTITUTE
+ 0x001b: 0x001b, # ESCAPE
+ 0x001c: 0x001c, # FILE SEPARATOR
+ 0x001d: 0x001d, # GROUP SEPARATOR
+ 0x001e: 0x001e, # RECORD SEPARATOR
+ 0x001f: 0x001f, # UNIT SEPARATOR
+ 0x0020: 0x0020, # SPACE
+ 0x0021: 0x0021, # EXCLAMATION MARK
+ 0x0022: 0x0022, # QUOTATION MARK
+ 0x0023: 0x0023, # NUMBER SIGN
+ 0x0024: 0x0024, # DOLLAR SIGN
+ 0x0025: 0x0025, # PERCENT SIGN
+ 0x0026: 0x0026, # AMPERSAND
+ 0x0027: 0x0027, # APOSTROPHE
+ 0x0028: 0x0028, # LEFT PARENTHESIS
+ 0x0029: 0x0029, # RIGHT PARENTHESIS
+ 0x002a: 0x002a, # ASTERISK
+ 0x002b: 0x002b, # PLUS SIGN
+ 0x002c: 0x002c, # COMMA
+ 0x002d: 0x002d, # HYPHEN-MINUS
+ 0x002e: 0x002e, # FULL STOP
+ 0x002f: 0x002f, # SOLIDUS
+ 0x0030: 0x0030, # DIGIT ZERO
+ 0x0031: 0x0031, # DIGIT ONE
+ 0x0032: 0x0032, # DIGIT TWO
+ 0x0033: 0x0033, # DIGIT THREE
+ 0x0034: 0x0034, # DIGIT FOUR
+ 0x0035: 0x0035, # DIGIT FIVE
+ 0x0036: 0x0036, # DIGIT SIX
+ 0x0037: 0x0037, # DIGIT SEVEN
+ 0x0038: 0x0038, # DIGIT EIGHT
+ 0x0039: 0x0039, # DIGIT NINE
+ 0x003a: 0x003a, # COLON
+ 0x003b: 0x003b, # SEMICOLON
+ 0x003c: 0x003c, # LESS-THAN SIGN
+ 0x003d: 0x003d, # EQUALS SIGN
+ 0x003e: 0x003e, # GREATER-THAN SIGN
+ 0x003f: 0x003f, # QUESTION MARK
+ 0x0040: 0x0040, # COMMERCIAL AT
+ 0x0041: 0x0041, # LATIN CAPITAL LETTER A
+ 0x0042: 0x0042, # LATIN CAPITAL LETTER B
+ 0x0043: 0x0043, # LATIN CAPITAL LETTER C
+ 0x0044: 0x0044, # LATIN CAPITAL LETTER D
+ 0x0045: 0x0045, # LATIN CAPITAL LETTER E
+ 0x0046: 0x0046, # LATIN CAPITAL LETTER F
+ 0x0047: 0x0047, # LATIN CAPITAL LETTER G
+ 0x0048: 0x0048, # LATIN CAPITAL LETTER H
+ 0x0049: 0x0049, # LATIN CAPITAL LETTER I
+ 0x004a: 0x004a, # LATIN CAPITAL LETTER J
+ 0x004b: 0x004b, # LATIN CAPITAL LETTER K
+ 0x004c: 0x004c, # LATIN CAPITAL LETTER L
+ 0x004d: 0x004d, # LATIN CAPITAL LETTER M
+ 0x004e: 0x004e, # LATIN CAPITAL LETTER N
+ 0x004f: 0x004f, # LATIN CAPITAL LETTER O
+ 0x0050: 0x0050, # LATIN CAPITAL LETTER P
+ 0x0051: 0x0051, # LATIN CAPITAL LETTER Q
+ 0x0052: 0x0052, # LATIN CAPITAL LETTER R
+ 0x0053: 0x0053, # LATIN CAPITAL LETTER S
+ 0x0054: 0x0054, # LATIN CAPITAL LETTER T
+ 0x0055: 0x0055, # LATIN CAPITAL LETTER U
+ 0x0056: 0x0056, # LATIN CAPITAL LETTER V
+ 0x0057: 0x0057, # LATIN CAPITAL LETTER W
+ 0x0058: 0x0058, # LATIN CAPITAL LETTER X
+ 0x0059: 0x0059, # LATIN CAPITAL LETTER Y
+ 0x005a: 0x005a, # LATIN CAPITAL LETTER Z
+ 0x005b: 0x005b, # LEFT SQUARE BRACKET
+ 0x005c: 0x005c, # REVERSE SOLIDUS
+ 0x005d: 0x005d, # RIGHT SQUARE BRACKET
+ 0x005e: 0x005e, # CIRCUMFLEX ACCENT
+ 0x005f: 0x005f, # LOW LINE
+ 0x0060: 0x0060, # GRAVE ACCENT
+ 0x0061: 0x0061, # LATIN SMALL LETTER A
+ 0x0062: 0x0062, # LATIN SMALL LETTER B
+ 0x0063: 0x0063, # LATIN SMALL LETTER C
+ 0x0064: 0x0064, # LATIN SMALL LETTER D
+ 0x0065: 0x0065, # LATIN SMALL LETTER E
+ 0x0066: 0x0066, # LATIN SMALL LETTER F
+ 0x0067: 0x0067, # LATIN SMALL LETTER G
+ 0x0068: 0x0068, # LATIN SMALL LETTER H
+ 0x0069: 0x0069, # LATIN SMALL LETTER I
+ 0x006a: 0x006a, # LATIN SMALL LETTER J
+ 0x006b: 0x006b, # LATIN SMALL LETTER K
+ 0x006c: 0x006c, # LATIN SMALL LETTER L
+ 0x006d: 0x006d, # LATIN SMALL LETTER M
+ 0x006e: 0x006e, # LATIN SMALL LETTER N
+ 0x006f: 0x006f, # LATIN SMALL LETTER O
+ 0x0070: 0x0070, # LATIN SMALL LETTER P
+ 0x0071: 0x0071, # LATIN SMALL LETTER Q
+ 0x0072: 0x0072, # LATIN SMALL LETTER R
+ 0x0073: 0x0073, # LATIN SMALL LETTER S
+ 0x0074: 0x0074, # LATIN SMALL LETTER T
+ 0x0075: 0x0075, # LATIN SMALL LETTER U
+ 0x0076: 0x0076, # LATIN SMALL LETTER V
+ 0x0077: 0x0077, # LATIN SMALL LETTER W
+ 0x0078: 0x0078, # LATIN SMALL LETTER X
+ 0x0079: 0x0079, # LATIN SMALL LETTER Y
+ 0x007a: 0x007a, # LATIN SMALL LETTER Z
+ 0x007b: 0x007b, # LEFT CURLY BRACKET
+ 0x007c: 0x007c, # VERTICAL LINE
+ 0x007d: 0x007d, # RIGHT CURLY BRACKET
+ 0x007e: 0x007e, # TILDE
+ 0x007f: 0x007f, # DELETE
+ 0x00a0: 0x00ff, # NO-BREAK SPACE
+ 0x00a3: 0x009c, # POUND SIGN
+ 0x00a6: 0x008a, # BROKEN BAR
+ 0x00a7: 0x00f5, # SECTION SIGN
+ 0x00a8: 0x00f9, # DIAERESIS
+ 0x00a9: 0x0097, # COPYRIGHT SIGN
+ 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00ac: 0x0089, # NOT SIGN
+ 0x00ad: 0x00f0, # SOFT HYPHEN
+ 0x00b0: 0x00f8, # DEGREE SIGN
+ 0x00b1: 0x00f1, # PLUS-MINUS SIGN
+ 0x00b2: 0x0099, # SUPERSCRIPT TWO
+ 0x00b3: 0x009a, # SUPERSCRIPT THREE
+ 0x00b7: 0x0088, # MIDDLE DOT
+ 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
+ 0x0384: 0x00ef, # GREEK TONOS
+ 0x0385: 0x00f7, # GREEK DIALYTIKA TONOS
+ 0x0386: 0x0086, # GREEK CAPITAL LETTER ALPHA WITH TONOS
+ 0x0388: 0x008d, # GREEK CAPITAL LETTER EPSILON WITH TONOS
+ 0x0389: 0x008f, # GREEK CAPITAL LETTER ETA WITH TONOS
+ 0x038a: 0x0090, # GREEK CAPITAL LETTER IOTA WITH TONOS
+ 0x038c: 0x0092, # GREEK CAPITAL LETTER OMICRON WITH TONOS
+ 0x038e: 0x0095, # GREEK CAPITAL LETTER UPSILON WITH TONOS
+ 0x038f: 0x0098, # GREEK CAPITAL LETTER OMEGA WITH TONOS
+ 0x0390: 0x00a1, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ 0x0391: 0x00a4, # GREEK CAPITAL LETTER ALPHA
+ 0x0392: 0x00a5, # GREEK CAPITAL LETTER BETA
+ 0x0393: 0x00a6, # GREEK CAPITAL LETTER GAMMA
+ 0x0394: 0x00a7, # GREEK CAPITAL LETTER DELTA
+ 0x0395: 0x00a8, # GREEK CAPITAL LETTER EPSILON
+ 0x0396: 0x00a9, # GREEK CAPITAL LETTER ZETA
+ 0x0397: 0x00aa, # GREEK CAPITAL LETTER ETA
+ 0x0398: 0x00ac, # GREEK CAPITAL LETTER THETA
+ 0x0399: 0x00ad, # GREEK CAPITAL LETTER IOTA
+ 0x039a: 0x00b5, # GREEK CAPITAL LETTER KAPPA
+ 0x039b: 0x00b6, # GREEK CAPITAL LETTER LAMDA
+ 0x039c: 0x00b7, # GREEK CAPITAL LETTER MU
+ 0x039d: 0x00b8, # GREEK CAPITAL LETTER NU
+ 0x039e: 0x00bd, # GREEK CAPITAL LETTER XI
+ 0x039f: 0x00be, # GREEK CAPITAL LETTER OMICRON
+ 0x03a0: 0x00c6, # GREEK CAPITAL LETTER PI
+ 0x03a1: 0x00c7, # GREEK CAPITAL LETTER RHO
+ 0x03a3: 0x00cf, # GREEK CAPITAL LETTER SIGMA
+ 0x03a4: 0x00d0, # GREEK CAPITAL LETTER TAU
+ 0x03a5: 0x00d1, # GREEK CAPITAL LETTER UPSILON
+ 0x03a6: 0x00d2, # GREEK CAPITAL LETTER PHI
+ 0x03a7: 0x00d3, # GREEK CAPITAL LETTER CHI
+ 0x03a8: 0x00d4, # GREEK CAPITAL LETTER PSI
+ 0x03a9: 0x00d5, # GREEK CAPITAL LETTER OMEGA
+ 0x03aa: 0x0091, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ 0x03ab: 0x0096, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ 0x03ac: 0x009b, # GREEK SMALL LETTER ALPHA WITH TONOS
+ 0x03ad: 0x009d, # GREEK SMALL LETTER EPSILON WITH TONOS
+ 0x03ae: 0x009e, # GREEK SMALL LETTER ETA WITH TONOS
+ 0x03af: 0x009f, # GREEK SMALL LETTER IOTA WITH TONOS
+ 0x03b0: 0x00fc, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ 0x03b1: 0x00d6, # GREEK SMALL LETTER ALPHA
+ 0x03b2: 0x00d7, # GREEK SMALL LETTER BETA
+ 0x03b3: 0x00d8, # GREEK SMALL LETTER GAMMA
+ 0x03b4: 0x00dd, # GREEK SMALL LETTER DELTA
+ 0x03b5: 0x00de, # GREEK SMALL LETTER EPSILON
+ 0x03b6: 0x00e0, # GREEK SMALL LETTER ZETA
+ 0x03b7: 0x00e1, # GREEK SMALL LETTER ETA
+ 0x03b8: 0x00e2, # GREEK SMALL LETTER THETA
+ 0x03b9: 0x00e3, # GREEK SMALL LETTER IOTA
+ 0x03ba: 0x00e4, # GREEK SMALL LETTER KAPPA
+ 0x03bb: 0x00e5, # GREEK SMALL LETTER LAMDA
+ 0x03bc: 0x00e6, # GREEK SMALL LETTER MU
+ 0x03bd: 0x00e7, # GREEK SMALL LETTER NU
+ 0x03be: 0x00e8, # GREEK SMALL LETTER XI
+ 0x03bf: 0x00e9, # GREEK SMALL LETTER OMICRON
+ 0x03c0: 0x00ea, # GREEK SMALL LETTER PI
+ 0x03c1: 0x00eb, # GREEK SMALL LETTER RHO
+ 0x03c2: 0x00ed, # GREEK SMALL LETTER FINAL SIGMA
+ 0x03c3: 0x00ec, # GREEK SMALL LETTER SIGMA
+ 0x03c4: 0x00ee, # GREEK SMALL LETTER TAU
+ 0x03c5: 0x00f2, # GREEK SMALL LETTER UPSILON
+ 0x03c6: 0x00f3, # GREEK SMALL LETTER PHI
+ 0x03c7: 0x00f4, # GREEK SMALL LETTER CHI
+ 0x03c8: 0x00f6, # GREEK SMALL LETTER PSI
+ 0x03c9: 0x00fa, # GREEK SMALL LETTER OMEGA
+ 0x03ca: 0x00a0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ 0x03cb: 0x00fb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ 0x03cc: 0x00a2, # GREEK SMALL LETTER OMICRON WITH TONOS
+ 0x03cd: 0x00a3, # GREEK SMALL LETTER UPSILON WITH TONOS
+ 0x03ce: 0x00fd, # GREEK SMALL LETTER OMEGA WITH TONOS
+ 0x2015: 0x008e, # HORIZONTAL BAR
+ 0x2018: 0x008b, # LEFT SINGLE QUOTATION MARK
+ 0x2019: 0x008c, # RIGHT SINGLE QUOTATION MARK
+ 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
+ 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
+ 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
+ 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
+ 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
+ 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
+ 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
+ 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
+ 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
+ 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
+ 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
+ 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
+ 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
+ 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
+ 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
+ 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
+ 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
+ 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
+ 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
+ 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
+ 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
+ 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
+ 0x2580: 0x00df, # UPPER HALF BLOCK
+ 0x2584: 0x00dc, # LOWER HALF BLOCK
+ 0x2588: 0x00db, # FULL BLOCK
+ 0x2591: 0x00b0, # LIGHT SHADE
+ 0x2592: 0x00b1, # MEDIUM SHADE
+ 0x2593: 0x00b2, # DARK SHADE
+ 0x25a0: 0x00fe, # BLACK SQUARE
+}
diff --git a/Lib/encodings/cp874.py b/Lib/encodings/cp874.py
new file mode 100644
index 0000000..59bfcbc
--- /dev/null
+++ b/Lib/encodings/cp874.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp874 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp874',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\u20ac' # 0x80 -> EURO SIGN
+ '\ufffe' # 0x81 -> UNDEFINED
+ '\ufffe' # 0x82 -> UNDEFINED
+ '\ufffe' # 0x83 -> UNDEFINED
+ '\ufffe' # 0x84 -> UNDEFINED
+ '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
+ '\ufffe' # 0x86 -> UNDEFINED
+ '\ufffe' # 0x87 -> UNDEFINED
+ '\ufffe' # 0x88 -> UNDEFINED
+ '\ufffe' # 0x89 -> UNDEFINED
+ '\ufffe' # 0x8A -> UNDEFINED
+ '\ufffe' # 0x8B -> UNDEFINED
+ '\ufffe' # 0x8C -> UNDEFINED
+ '\ufffe' # 0x8D -> UNDEFINED
+ '\ufffe' # 0x8E -> UNDEFINED
+ '\ufffe' # 0x8F -> UNDEFINED
+ '\ufffe' # 0x90 -> UNDEFINED
+ '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
+ '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
+ '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
+ '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
+ '\u2022' # 0x95 -> BULLET
+ '\u2013' # 0x96 -> EN DASH
+ '\u2014' # 0x97 -> EM DASH
+ '\ufffe' # 0x98 -> UNDEFINED
+ '\ufffe' # 0x99 -> UNDEFINED
+ '\ufffe' # 0x9A -> UNDEFINED
+ '\ufffe' # 0x9B -> UNDEFINED
+ '\ufffe' # 0x9C -> UNDEFINED
+ '\ufffe' # 0x9D -> UNDEFINED
+ '\ufffe' # 0x9E -> UNDEFINED
+ '\ufffe' # 0x9F -> UNDEFINED
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u0e01' # 0xA1 -> THAI CHARACTER KO KAI
+ '\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI
+ '\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT
+ '\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI
+ '\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON
+ '\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG
+ '\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU
+ '\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN
+ '\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING
+ '\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG
+ '\u0e0b' # 0xAB -> THAI CHARACTER SO SO
+ '\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE
+ '\u0e0d' # 0xAD -> THAI CHARACTER YO YING
+ '\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA
+ '\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK
+ '\u0e10' # 0xB0 -> THAI CHARACTER THO THAN
+ '\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO
+ '\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO
+ '\u0e13' # 0xB3 -> THAI CHARACTER NO NEN
+ '\u0e14' # 0xB4 -> THAI CHARACTER DO DEK
+ '\u0e15' # 0xB5 -> THAI CHARACTER TO TAO
+ '\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG
+ '\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN
+ '\u0e18' # 0xB8 -> THAI CHARACTER THO THONG
+ '\u0e19' # 0xB9 -> THAI CHARACTER NO NU
+ '\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI
+ '\u0e1b' # 0xBB -> THAI CHARACTER PO PLA
+ '\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG
+ '\u0e1d' # 0xBD -> THAI CHARACTER FO FA
+ '\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN
+ '\u0e1f' # 0xBF -> THAI CHARACTER FO FAN
+ '\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO
+ '\u0e21' # 0xC1 -> THAI CHARACTER MO MA
+ '\u0e22' # 0xC2 -> THAI CHARACTER YO YAK
+ '\u0e23' # 0xC3 -> THAI CHARACTER RO RUA
+ '\u0e24' # 0xC4 -> THAI CHARACTER RU
+ '\u0e25' # 0xC5 -> THAI CHARACTER LO LING
+ '\u0e26' # 0xC6 -> THAI CHARACTER LU
+ '\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN
+ '\u0e28' # 0xC8 -> THAI CHARACTER SO SALA
+ '\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI
+ '\u0e2a' # 0xCA -> THAI CHARACTER SO SUA
+ '\u0e2b' # 0xCB -> THAI CHARACTER HO HIP
+ '\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA
+ '\u0e2d' # 0xCD -> THAI CHARACTER O ANG
+ '\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK
+ '\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI
+ '\u0e30' # 0xD0 -> THAI CHARACTER SARA A
+ '\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT
+ '\u0e32' # 0xD2 -> THAI CHARACTER SARA AA
+ '\u0e33' # 0xD3 -> THAI CHARACTER SARA AM
+ '\u0e34' # 0xD4 -> THAI CHARACTER SARA I
+ '\u0e35' # 0xD5 -> THAI CHARACTER SARA II
+ '\u0e36' # 0xD6 -> THAI CHARACTER SARA UE
+ '\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE
+ '\u0e38' # 0xD8 -> THAI CHARACTER SARA U
+ '\u0e39' # 0xD9 -> THAI CHARACTER SARA UU
+ '\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU
+ '\ufffe' # 0xDB -> UNDEFINED
+ '\ufffe' # 0xDC -> UNDEFINED
+ '\ufffe' # 0xDD -> UNDEFINED
+ '\ufffe' # 0xDE -> UNDEFINED
+ '\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT
+ '\u0e40' # 0xE0 -> THAI CHARACTER SARA E
+ '\u0e41' # 0xE1 -> THAI CHARACTER SARA AE
+ '\u0e42' # 0xE2 -> THAI CHARACTER SARA O
+ '\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN
+ '\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI
+ '\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO
+ '\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK
+ '\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU
+ '\u0e48' # 0xE8 -> THAI CHARACTER MAI EK
+ '\u0e49' # 0xE9 -> THAI CHARACTER MAI THO
+ '\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI
+ '\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA
+ '\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT
+ '\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT
+ '\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN
+ '\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN
+ '\u0e50' # 0xF0 -> THAI DIGIT ZERO
+ '\u0e51' # 0xF1 -> THAI DIGIT ONE
+ '\u0e52' # 0xF2 -> THAI DIGIT TWO
+ '\u0e53' # 0xF3 -> THAI DIGIT THREE
+ '\u0e54' # 0xF4 -> THAI DIGIT FOUR
+ '\u0e55' # 0xF5 -> THAI DIGIT FIVE
+ '\u0e56' # 0xF6 -> THAI DIGIT SIX
+ '\u0e57' # 0xF7 -> THAI DIGIT SEVEN
+ '\u0e58' # 0xF8 -> THAI DIGIT EIGHT
+ '\u0e59' # 0xF9 -> THAI DIGIT NINE
+ '\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU
+ '\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT
+ '\ufffe' # 0xFC -> UNDEFINED
+ '\ufffe' # 0xFD -> UNDEFINED
+ '\ufffe' # 0xFE -> UNDEFINED
+ '\ufffe' # 0xFF -> UNDEFINED
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp875.py b/Lib/encodings/cp875.py
new file mode 100644
index 0000000..c25a5a4
--- /dev/null
+++ b/Lib/encodings/cp875.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec cp875 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp875',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x9c' # 0x04 -> CONTROL
+ '\t' # 0x05 -> HORIZONTAL TABULATION
+ '\x86' # 0x06 -> CONTROL
+ '\x7f' # 0x07 -> DELETE
+ '\x97' # 0x08 -> CONTROL
+ '\x8d' # 0x09 -> CONTROL
+ '\x8e' # 0x0A -> CONTROL
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x9d' # 0x14 -> CONTROL
+ '\x85' # 0x15 -> CONTROL
+ '\x08' # 0x16 -> BACKSPACE
+ '\x87' # 0x17 -> CONTROL
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x92' # 0x1A -> CONTROL
+ '\x8f' # 0x1B -> CONTROL
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ '\x80' # 0x20 -> CONTROL
+ '\x81' # 0x21 -> CONTROL
+ '\x82' # 0x22 -> CONTROL
+ '\x83' # 0x23 -> CONTROL
+ '\x84' # 0x24 -> CONTROL
+ '\n' # 0x25 -> LINE FEED
+ '\x17' # 0x26 -> END OF TRANSMISSION BLOCK
+ '\x1b' # 0x27 -> ESCAPE
+ '\x88' # 0x28 -> CONTROL
+ '\x89' # 0x29 -> CONTROL
+ '\x8a' # 0x2A -> CONTROL
+ '\x8b' # 0x2B -> CONTROL
+ '\x8c' # 0x2C -> CONTROL
+ '\x05' # 0x2D -> ENQUIRY
+ '\x06' # 0x2E -> ACKNOWLEDGE
+ '\x07' # 0x2F -> BELL
+ '\x90' # 0x30 -> CONTROL
+ '\x91' # 0x31 -> CONTROL
+ '\x16' # 0x32 -> SYNCHRONOUS IDLE
+ '\x93' # 0x33 -> CONTROL
+ '\x94' # 0x34 -> CONTROL
+ '\x95' # 0x35 -> CONTROL
+ '\x96' # 0x36 -> CONTROL
+ '\x04' # 0x37 -> END OF TRANSMISSION
+ '\x98' # 0x38 -> CONTROL
+ '\x99' # 0x39 -> CONTROL
+ '\x9a' # 0x3A -> CONTROL
+ '\x9b' # 0x3B -> CONTROL
+ '\x14' # 0x3C -> DEVICE CONTROL FOUR
+ '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
+ '\x9e' # 0x3E -> CONTROL
+ '\x1a' # 0x3F -> SUBSTITUTE
+ ' ' # 0x40 -> SPACE
+ '\u0391' # 0x41 -> GREEK CAPITAL LETTER ALPHA
+ '\u0392' # 0x42 -> GREEK CAPITAL LETTER BETA
+ '\u0393' # 0x43 -> GREEK CAPITAL LETTER GAMMA
+ '\u0394' # 0x44 -> GREEK CAPITAL LETTER DELTA
+ '\u0395' # 0x45 -> GREEK CAPITAL LETTER EPSILON
+ '\u0396' # 0x46 -> GREEK CAPITAL LETTER ZETA
+ '\u0397' # 0x47 -> GREEK CAPITAL LETTER ETA
+ '\u0398' # 0x48 -> GREEK CAPITAL LETTER THETA
+ '\u0399' # 0x49 -> GREEK CAPITAL LETTER IOTA
+ '[' # 0x4A -> LEFT SQUARE BRACKET
+ '.' # 0x4B -> FULL STOP
+ '<' # 0x4C -> LESS-THAN SIGN
+ '(' # 0x4D -> LEFT PARENTHESIS
+ '+' # 0x4E -> PLUS SIGN
+ '!' # 0x4F -> EXCLAMATION MARK
+ '&' # 0x50 -> AMPERSAND
+ '\u039a' # 0x51 -> GREEK CAPITAL LETTER KAPPA
+ '\u039b' # 0x52 -> GREEK CAPITAL LETTER LAMDA
+ '\u039c' # 0x53 -> GREEK CAPITAL LETTER MU
+ '\u039d' # 0x54 -> GREEK CAPITAL LETTER NU
+ '\u039e' # 0x55 -> GREEK CAPITAL LETTER XI
+ '\u039f' # 0x56 -> GREEK CAPITAL LETTER OMICRON
+ '\u03a0' # 0x57 -> GREEK CAPITAL LETTER PI
+ '\u03a1' # 0x58 -> GREEK CAPITAL LETTER RHO
+ '\u03a3' # 0x59 -> GREEK CAPITAL LETTER SIGMA
+ ']' # 0x5A -> RIGHT SQUARE BRACKET
+ '$' # 0x5B -> DOLLAR SIGN
+ '*' # 0x5C -> ASTERISK
+ ')' # 0x5D -> RIGHT PARENTHESIS
+ ';' # 0x5E -> SEMICOLON
+ '^' # 0x5F -> CIRCUMFLEX ACCENT
+ '-' # 0x60 -> HYPHEN-MINUS
+ '/' # 0x61 -> SOLIDUS
+ '\u03a4' # 0x62 -> GREEK CAPITAL LETTER TAU
+ '\u03a5' # 0x63 -> GREEK CAPITAL LETTER UPSILON
+ '\u03a6' # 0x64 -> GREEK CAPITAL LETTER PHI
+ '\u03a7' # 0x65 -> GREEK CAPITAL LETTER CHI
+ '\u03a8' # 0x66 -> GREEK CAPITAL LETTER PSI
+ '\u03a9' # 0x67 -> GREEK CAPITAL LETTER OMEGA
+ '\u03aa' # 0x68 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
+ '\u03ab' # 0x69 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
+ '|' # 0x6A -> VERTICAL LINE
+ ',' # 0x6B -> COMMA
+ '%' # 0x6C -> PERCENT SIGN
+ '_' # 0x6D -> LOW LINE
+ '>' # 0x6E -> GREATER-THAN SIGN
+ '?' # 0x6F -> QUESTION MARK
+ '\xa8' # 0x70 -> DIAERESIS
+ '\u0386' # 0x71 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
+ '\u0388' # 0x72 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
+ '\u0389' # 0x73 -> GREEK CAPITAL LETTER ETA WITH TONOS
+ '\xa0' # 0x74 -> NO-BREAK SPACE
+ '\u038a' # 0x75 -> GREEK CAPITAL LETTER IOTA WITH TONOS
+ '\u038c' # 0x76 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
+ '\u038e' # 0x77 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
+ '\u038f' # 0x78 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
+ '`' # 0x79 -> GRAVE ACCENT
+ ':' # 0x7A -> COLON
+ '#' # 0x7B -> NUMBER SIGN
+ '@' # 0x7C -> COMMERCIAL AT
+ "'" # 0x7D -> APOSTROPHE
+ '=' # 0x7E -> EQUALS SIGN
+ '"' # 0x7F -> QUOTATION MARK
+ '\u0385' # 0x80 -> GREEK DIALYTIKA TONOS
+ 'a' # 0x81 -> LATIN SMALL LETTER A
+ 'b' # 0x82 -> LATIN SMALL LETTER B
+ 'c' # 0x83 -> LATIN SMALL LETTER C
+ 'd' # 0x84 -> LATIN SMALL LETTER D
+ 'e' # 0x85 -> LATIN SMALL LETTER E
+ 'f' # 0x86 -> LATIN SMALL LETTER F
+ 'g' # 0x87 -> LATIN SMALL LETTER G
+ 'h' # 0x88 -> LATIN SMALL LETTER H
+ 'i' # 0x89 -> LATIN SMALL LETTER I
+ '\u03b1' # 0x8A -> GREEK SMALL LETTER ALPHA
+ '\u03b2' # 0x8B -> GREEK SMALL LETTER BETA
+ '\u03b3' # 0x8C -> GREEK SMALL LETTER GAMMA
+ '\u03b4' # 0x8D -> GREEK SMALL LETTER DELTA
+ '\u03b5' # 0x8E -> GREEK SMALL LETTER EPSILON
+ '\u03b6' # 0x8F -> GREEK SMALL LETTER ZETA
+ '\xb0' # 0x90 -> DEGREE SIGN
+ 'j' # 0x91 -> LATIN SMALL LETTER J
+ 'k' # 0x92 -> LATIN SMALL LETTER K
+ 'l' # 0x93 -> LATIN SMALL LETTER L
+ 'm' # 0x94 -> LATIN SMALL LETTER M
+ 'n' # 0x95 -> LATIN SMALL LETTER N
+ 'o' # 0x96 -> LATIN SMALL LETTER O
+ 'p' # 0x97 -> LATIN SMALL LETTER P
+ 'q' # 0x98 -> LATIN SMALL LETTER Q
+ 'r' # 0x99 -> LATIN SMALL LETTER R
+ '\u03b7' # 0x9A -> GREEK SMALL LETTER ETA
+ '\u03b8' # 0x9B -> GREEK SMALL LETTER THETA
+ '\u03b9' # 0x9C -> GREEK SMALL LETTER IOTA
+ '\u03ba' # 0x9D -> GREEK SMALL LETTER KAPPA
+ '\u03bb' # 0x9E -> GREEK SMALL LETTER LAMDA
+ '\u03bc' # 0x9F -> GREEK SMALL LETTER MU
+ '\xb4' # 0xA0 -> ACUTE ACCENT
+ '~' # 0xA1 -> TILDE
+ 's' # 0xA2 -> LATIN SMALL LETTER S
+ 't' # 0xA3 -> LATIN SMALL LETTER T
+ 'u' # 0xA4 -> LATIN SMALL LETTER U
+ 'v' # 0xA5 -> LATIN SMALL LETTER V
+ 'w' # 0xA6 -> LATIN SMALL LETTER W
+ 'x' # 0xA7 -> LATIN SMALL LETTER X
+ 'y' # 0xA8 -> LATIN SMALL LETTER Y
+ 'z' # 0xA9 -> LATIN SMALL LETTER Z
+ '\u03bd' # 0xAA -> GREEK SMALL LETTER NU
+ '\u03be' # 0xAB -> GREEK SMALL LETTER XI
+ '\u03bf' # 0xAC -> GREEK SMALL LETTER OMICRON
+ '\u03c0' # 0xAD -> GREEK SMALL LETTER PI
+ '\u03c1' # 0xAE -> GREEK SMALL LETTER RHO
+ '\u03c3' # 0xAF -> GREEK SMALL LETTER SIGMA
+ '\xa3' # 0xB0 -> POUND SIGN
+ '\u03ac' # 0xB1 -> GREEK SMALL LETTER ALPHA WITH TONOS
+ '\u03ad' # 0xB2 -> GREEK SMALL LETTER EPSILON WITH TONOS
+ '\u03ae' # 0xB3 -> GREEK SMALL LETTER ETA WITH TONOS
+ '\u03ca' # 0xB4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
+ '\u03af' # 0xB5 -> GREEK SMALL LETTER IOTA WITH TONOS
+ '\u03cc' # 0xB6 -> GREEK SMALL LETTER OMICRON WITH TONOS
+ '\u03cd' # 0xB7 -> GREEK SMALL LETTER UPSILON WITH TONOS
+ '\u03cb' # 0xB8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
+ '\u03ce' # 0xB9 -> GREEK SMALL LETTER OMEGA WITH TONOS
+ '\u03c2' # 0xBA -> GREEK SMALL LETTER FINAL SIGMA
+ '\u03c4' # 0xBB -> GREEK SMALL LETTER TAU
+ '\u03c5' # 0xBC -> GREEK SMALL LETTER UPSILON
+ '\u03c6' # 0xBD -> GREEK SMALL LETTER PHI
+ '\u03c7' # 0xBE -> GREEK SMALL LETTER CHI
+ '\u03c8' # 0xBF -> GREEK SMALL LETTER PSI
+ '{' # 0xC0 -> LEFT CURLY BRACKET
+ 'A' # 0xC1 -> LATIN CAPITAL LETTER A
+ 'B' # 0xC2 -> LATIN CAPITAL LETTER B
+ 'C' # 0xC3 -> LATIN CAPITAL LETTER C
+ 'D' # 0xC4 -> LATIN CAPITAL LETTER D
+ 'E' # 0xC5 -> LATIN CAPITAL LETTER E
+ 'F' # 0xC6 -> LATIN CAPITAL LETTER F
+ 'G' # 0xC7 -> LATIN CAPITAL LETTER G
+ 'H' # 0xC8 -> LATIN CAPITAL LETTER H
+ 'I' # 0xC9 -> LATIN CAPITAL LETTER I
+ '\xad' # 0xCA -> SOFT HYPHEN
+ '\u03c9' # 0xCB -> GREEK SMALL LETTER OMEGA
+ '\u0390' # 0xCC -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+ '\u03b0' # 0xCD -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+ '\u2018' # 0xCE -> LEFT SINGLE QUOTATION MARK
+ '\u2015' # 0xCF -> HORIZONTAL BAR
+ '}' # 0xD0 -> RIGHT CURLY BRACKET
+ 'J' # 0xD1 -> LATIN CAPITAL LETTER J
+ 'K' # 0xD2 -> LATIN CAPITAL LETTER K
+ 'L' # 0xD3 -> LATIN CAPITAL LETTER L
+ 'M' # 0xD4 -> LATIN CAPITAL LETTER M
+ 'N' # 0xD5 -> LATIN CAPITAL LETTER N
+ 'O' # 0xD6 -> LATIN CAPITAL LETTER O
+ 'P' # 0xD7 -> LATIN CAPITAL LETTER P
+ 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
+ 'R' # 0xD9 -> LATIN CAPITAL LETTER R
+ '\xb1' # 0xDA -> PLUS-MINUS SIGN
+ '\xbd' # 0xDB -> VULGAR FRACTION ONE HALF
+ '\x1a' # 0xDC -> SUBSTITUTE
+ '\u0387' # 0xDD -> GREEK ANO TELEIA
+ '\u2019' # 0xDE -> RIGHT SINGLE QUOTATION MARK
+ '\xa6' # 0xDF -> BROKEN BAR
+ '\\' # 0xE0 -> REVERSE SOLIDUS
+ '\x1a' # 0xE1 -> SUBSTITUTE
+ 'S' # 0xE2 -> LATIN CAPITAL LETTER S
+ 'T' # 0xE3 -> LATIN CAPITAL LETTER T
+ 'U' # 0xE4 -> LATIN CAPITAL LETTER U
+ 'V' # 0xE5 -> LATIN CAPITAL LETTER V
+ 'W' # 0xE6 -> LATIN CAPITAL LETTER W
+ 'X' # 0xE7 -> LATIN CAPITAL LETTER X
+ 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
+ '\xb2' # 0xEA -> SUPERSCRIPT TWO
+ '\xa7' # 0xEB -> SECTION SIGN
+ '\x1a' # 0xEC -> SUBSTITUTE
+ '\x1a' # 0xED -> SUBSTITUTE
+ '\xab' # 0xEE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xEF -> NOT SIGN
+ '0' # 0xF0 -> DIGIT ZERO
+ '1' # 0xF1 -> DIGIT ONE
+ '2' # 0xF2 -> DIGIT TWO
+ '3' # 0xF3 -> DIGIT THREE
+ '4' # 0xF4 -> DIGIT FOUR
+ '5' # 0xF5 -> DIGIT FIVE
+ '6' # 0xF6 -> DIGIT SIX
+ '7' # 0xF7 -> DIGIT SEVEN
+ '8' # 0xF8 -> DIGIT EIGHT
+ '9' # 0xF9 -> DIGIT NINE
+ '\xb3' # 0xFA -> SUPERSCRIPT THREE
+ '\xa9' # 0xFB -> COPYRIGHT SIGN
+ '\x1a' # 0xFC -> SUBSTITUTE
+ '\x1a' # 0xFD -> SUBSTITUTE
+ '\xbb' # 0xFE -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\x9f' # 0xFF -> CONTROL
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/cp932.py b/Lib/encodings/cp932.py
new file mode 100644
index 0000000..e01f59b
--- /dev/null
+++ b/Lib/encodings/cp932.py
@@ -0,0 +1,39 @@
+#
+# cp932.py: Python Unicode Codec for CP932
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_jp, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_jp.getcodec('cp932')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp932',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/cp949.py b/Lib/encodings/cp949.py
new file mode 100644
index 0000000..627c871
--- /dev/null
+++ b/Lib/encodings/cp949.py
@@ -0,0 +1,39 @@
+#
+# cp949.py: Python Unicode Codec for CP949
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_kr, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_kr.getcodec('cp949')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp949',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/cp950.py b/Lib/encodings/cp950.py
new file mode 100644
index 0000000..39eec5e
--- /dev/null
+++ b/Lib/encodings/cp950.py
@@ -0,0 +1,39 @@
+#
+# cp950.py: Python Unicode Codec for CP950
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_tw, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_tw.getcodec('cp950')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='cp950',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/euc_jis_2004.py b/Lib/encodings/euc_jis_2004.py
new file mode 100644
index 0000000..72b87ae
--- /dev/null
+++ b/Lib/encodings/euc_jis_2004.py
@@ -0,0 +1,39 @@
+#
+# euc_jis_2004.py: Python Unicode Codec for EUC_JIS_2004
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_jp, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_jp.getcodec('euc_jis_2004')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='euc_jis_2004',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/euc_jisx0213.py b/Lib/encodings/euc_jisx0213.py
new file mode 100644
index 0000000..cc47d04
--- /dev/null
+++ b/Lib/encodings/euc_jisx0213.py
@@ -0,0 +1,39 @@
+#
+# euc_jisx0213.py: Python Unicode Codec for EUC_JISX0213
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_jp, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_jp.getcodec('euc_jisx0213')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='euc_jisx0213',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/euc_jp.py b/Lib/encodings/euc_jp.py
new file mode 100644
index 0000000..7bcbe41
--- /dev/null
+++ b/Lib/encodings/euc_jp.py
@@ -0,0 +1,39 @@
+#
+# euc_jp.py: Python Unicode Codec for EUC_JP
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_jp, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_jp.getcodec('euc_jp')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='euc_jp',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/euc_kr.py b/Lib/encodings/euc_kr.py
new file mode 100644
index 0000000..c1fb126
--- /dev/null
+++ b/Lib/encodings/euc_kr.py
@@ -0,0 +1,39 @@
+#
+# euc_kr.py: Python Unicode Codec for EUC_KR
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_kr, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_kr.getcodec('euc_kr')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='euc_kr',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/gb18030.py b/Lib/encodings/gb18030.py
new file mode 100644
index 0000000..34fb6c3
--- /dev/null
+++ b/Lib/encodings/gb18030.py
@@ -0,0 +1,39 @@
+#
+# gb18030.py: Python Unicode Codec for GB18030
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_cn, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_cn.getcodec('gb18030')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='gb18030',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/gb2312.py b/Lib/encodings/gb2312.py
new file mode 100644
index 0000000..3c3b837
--- /dev/null
+++ b/Lib/encodings/gb2312.py
@@ -0,0 +1,39 @@
+#
+# gb2312.py: Python Unicode Codec for GB2312
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_cn, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_cn.getcodec('gb2312')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='gb2312',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/gbk.py b/Lib/encodings/gbk.py
new file mode 100644
index 0000000..1b45db8
--- /dev/null
+++ b/Lib/encodings/gbk.py
@@ -0,0 +1,39 @@
+#
+# gbk.py: Python Unicode Codec for GBK
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_cn, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_cn.getcodec('gbk')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='gbk',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/hex_codec.py b/Lib/encodings/hex_codec.py
new file mode 100644
index 0000000..9fb1072
--- /dev/null
+++ b/Lib/encodings/hex_codec.py
@@ -0,0 +1,55 @@
+"""Python 'hex_codec' Codec - 2-digit hex content transfer encoding.
+
+This codec de/encodes from bytes to bytes.
+
+Written by Marc-Andre Lemburg (mal@lemburg.com).
+"""
+
+import codecs
+import binascii
+
+### Codec APIs
+
+def hex_encode(input, errors='strict'):
+ assert errors == 'strict'
+ return (binascii.b2a_hex(input), len(input))
+
+def hex_decode(input, errors='strict'):
+ assert errors == 'strict'
+ return (binascii.a2b_hex(input), len(input))
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+ return hex_encode(input, errors)
+ def decode(self, input, errors='strict'):
+ return hex_decode(input, errors)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ assert self.errors == 'strict'
+ return binascii.b2a_hex(input)
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ assert self.errors == 'strict'
+ return binascii.a2b_hex(input)
+
+class StreamWriter(Codec, codecs.StreamWriter):
+ charbuffertype = bytes
+
+class StreamReader(Codec, codecs.StreamReader):
+ charbuffertype = bytes
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='hex',
+ encode=hex_encode,
+ decode=hex_decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ _is_text_encoding=False,
+ )
diff --git a/Lib/encodings/hp_roman8.py b/Lib/encodings/hp_roman8.py
new file mode 100644
index 0000000..58de103
--- /dev/null
+++ b/Lib/encodings/hp_roman8.py
@@ -0,0 +1,314 @@
+""" Python Character Mapping Codec generated from 'hp_roman8.txt' with gencodec.py.
+
+ Based on data from ftp://dkuug.dk/i18n/charmaps/HP-ROMAN8 (Keld Simonsen)
+
+ Original source: LaserJet IIP Printer User's Manual HP part no
+ 33471-90901, Hewlet-Packard, June 1989.
+
+ (Used with permission)
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='hp-roman8',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\x80' # 0x80 ->
+ '\x81' # 0x81 ->
+ '\x82' # 0x82 ->
+ '\x83' # 0x83 ->
+ '\x84' # 0x84 ->
+ '\x85' # 0x85 ->
+ '\x86' # 0x86 ->
+ '\x87' # 0x87 ->
+ '\x88' # 0x88 ->
+ '\x89' # 0x89 ->
+ '\x8a' # 0x8A ->
+ '\x8b' # 0x8B ->
+ '\x8c' # 0x8C ->
+ '\x8d' # 0x8D ->
+ '\x8e' # 0x8E ->
+ '\x8f' # 0x8F ->
+ '\x90' # 0x90 ->
+ '\x91' # 0x91 ->
+ '\x92' # 0x92 ->
+ '\x93' # 0x93 ->
+ '\x94' # 0x94 ->
+ '\x95' # 0x95 ->
+ '\x96' # 0x96 ->
+ '\x97' # 0x97 ->
+ '\x98' # 0x98 ->
+ '\x99' # 0x99 ->
+ '\x9a' # 0x9A ->
+ '\x9b' # 0x9B ->
+ '\x9c' # 0x9C ->
+ '\x9d' # 0x9D ->
+ '\x9e' # 0x9E ->
+ '\x9f' # 0x9F ->
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\xc0' # 0xA1 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc2' # 0xA2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc8' # 0xA3 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xca' # 0xA4 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0xA5 -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xce' # 0xA6 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0xA7 -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xb4' # 0xA8 -> ACUTE ACCENT
+ '\u02cb' # 0xA9 -> MODIFIER LETTER GRAVE ACCENT (MANDARIN CHINESE FOURTH TONE)
+ '\u02c6' # 0xAA -> MODIFIER LETTER CIRCUMFLEX ACCENT
+ '\xa8' # 0xAB -> DIAERESIS
+ '\u02dc' # 0xAC -> SMALL TILDE
+ '\xd9' # 0xAD -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xdb' # 0xAE -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\u20a4' # 0xAF -> LIRA SIGN
+ '\xaf' # 0xB0 -> MACRON
+ '\xdd' # 0xB1 -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xfd' # 0xB2 -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xb0' # 0xB3 -> DEGREE SIGN
+ '\xc7' # 0xB4 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xe7' # 0xB5 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xd1' # 0xB6 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xf1' # 0xB7 -> LATIN SMALL LETTER N WITH TILDE
+ '\xa1' # 0xB8 -> INVERTED EXCLAMATION MARK
+ '\xbf' # 0xB9 -> INVERTED QUESTION MARK
+ '\xa4' # 0xBA -> CURRENCY SIGN
+ '\xa3' # 0xBB -> POUND SIGN
+ '\xa5' # 0xBC -> YEN SIGN
+ '\xa7' # 0xBD -> SECTION SIGN
+ '\u0192' # 0xBE -> LATIN SMALL LETTER F WITH HOOK
+ '\xa2' # 0xBF -> CENT SIGN
+ '\xe2' # 0xC0 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xea' # 0xC1 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xf4' # 0xC2 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xfb' # 0xC3 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xe1' # 0xC4 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe9' # 0xC5 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xf3' # 0xC6 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xfa' # 0xC7 -> LATIN SMALL LETTER U WITH ACUTE
+ '\xe0' # 0xC8 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe8' # 0xC9 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xf2' # 0xCA -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf9' # 0xCB -> LATIN SMALL LETTER U WITH GRAVE
+ '\xe4' # 0xCC -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xeb' # 0xCD -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xf6' # 0xCE -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xfc' # 0xCF -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xc5' # 0xD0 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xee' # 0xD1 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xd8' # 0xD2 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xc6' # 0xD3 -> LATIN CAPITAL LETTER AE
+ '\xe5' # 0xD4 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xed' # 0xD5 -> LATIN SMALL LETTER I WITH ACUTE
+ '\xf8' # 0xD6 -> LATIN SMALL LETTER O WITH STROKE
+ '\xe6' # 0xD7 -> LATIN SMALL LETTER AE
+ '\xc4' # 0xD8 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xec' # 0xD9 -> LATIN SMALL LETTER I WITH GRAVE
+ '\xd6' # 0xDA -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xdc' # 0xDB -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xc9' # 0xDC -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xef' # 0xDD -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xdf' # 0xDE -> LATIN SMALL LETTER SHARP S (GERMAN)
+ '\xd4' # 0xDF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xc1' # 0xE0 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc3' # 0xE1 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xe3' # 0xE2 -> LATIN SMALL LETTER A WITH TILDE
+ '\xd0' # 0xE3 -> LATIN CAPITAL LETTER ETH (ICELANDIC)
+ '\xf0' # 0xE4 -> LATIN SMALL LETTER ETH (ICELANDIC)
+ '\xcd' # 0xE5 -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xcc' # 0xE6 -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\xd3' # 0xE7 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd2' # 0xE8 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd5' # 0xE9 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xf5' # 0xEA -> LATIN SMALL LETTER O WITH TILDE
+ '\u0160' # 0xEB -> LATIN CAPITAL LETTER S WITH CARON
+ '\u0161' # 0xEC -> LATIN SMALL LETTER S WITH CARON
+ '\xda' # 0xED -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\u0178' # 0xEE -> LATIN CAPITAL LETTER Y WITH DIAERESIS
+ '\xff' # 0xEF -> LATIN SMALL LETTER Y WITH DIAERESIS
+ '\xde' # 0xF0 -> LATIN CAPITAL LETTER THORN (ICELANDIC)
+ '\xfe' # 0xF1 -> LATIN SMALL LETTER THORN (ICELANDIC)
+ '\xb7' # 0xF2 -> MIDDLE DOT
+ '\xb5' # 0xF3 -> MICRO SIGN
+ '\xb6' # 0xF4 -> PILCROW SIGN
+ '\xbe' # 0xF5 -> VULGAR FRACTION THREE QUARTERS
+ '\u2014' # 0xF6 -> EM DASH
+ '\xbc' # 0xF7 -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xF8 -> VULGAR FRACTION ONE HALF
+ '\xaa' # 0xF9 -> FEMININE ORDINAL INDICATOR
+ '\xba' # 0xFA -> MASCULINE ORDINAL INDICATOR
+ '\xab' # 0xFB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\u25a0' # 0xFC -> BLACK SQUARE
+ '\xbb' # 0xFD -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xb1' # 0xFE -> PLUS-MINUS SIGN
+ '\ufffe'
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/hz.py b/Lib/encodings/hz.py
new file mode 100644
index 0000000..383442a
--- /dev/null
+++ b/Lib/encodings/hz.py
@@ -0,0 +1,39 @@
+#
+# hz.py: Python Unicode Codec for HZ
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_cn, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_cn.getcodec('hz')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='hz',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py
new file mode 100644
index 0000000..ea40585
--- /dev/null
+++ b/Lib/encodings/idna.py
@@ -0,0 +1,309 @@
+# This module implements the RFCs 3490 (IDNA) and 3491 (Nameprep)
+
+import stringprep, re, codecs
+from unicodedata import ucd_3_2_0 as unicodedata
+
+# IDNA section 3.1
+dots = re.compile("[\u002E\u3002\uFF0E\uFF61]")
+
+# IDNA section 5
+ace_prefix = b"xn--"
+sace_prefix = "xn--"
+
+# This assumes query strings, so AllowUnassigned is true
+def nameprep(label):
+ # Map
+ newlabel = []
+ for c in label:
+ if stringprep.in_table_b1(c):
+ # Map to nothing
+ continue
+ newlabel.append(stringprep.map_table_b2(c))
+ label = "".join(newlabel)
+
+ # Normalize
+ label = unicodedata.normalize("NFKC", label)
+
+ # Prohibit
+ for c in label:
+ if stringprep.in_table_c12(c) or \
+ stringprep.in_table_c22(c) or \
+ stringprep.in_table_c3(c) or \
+ stringprep.in_table_c4(c) or \
+ stringprep.in_table_c5(c) or \
+ stringprep.in_table_c6(c) or \
+ stringprep.in_table_c7(c) or \
+ stringprep.in_table_c8(c) or \
+ stringprep.in_table_c9(c):
+ raise UnicodeError("Invalid character %r" % c)
+
+ # Check bidi
+ RandAL = [stringprep.in_table_d1(x) for x in label]
+ for c in RandAL:
+ if c:
+ # There is a RandAL char in the string. Must perform further
+ # tests:
+ # 1) The characters in section 5.8 MUST be prohibited.
+ # This is table C.8, which was already checked
+ # 2) If a string contains any RandALCat character, the string
+ # MUST NOT contain any LCat character.
+ if any(stringprep.in_table_d2(x) for x in label):
+ raise UnicodeError("Violation of BIDI requirement 2")
+
+ # 3) If a string contains any RandALCat character, a
+ # RandALCat character MUST be the first character of the
+ # string, and a RandALCat character MUST be the last
+ # character of the string.
+ if not RandAL[0] or not RandAL[-1]:
+ raise UnicodeError("Violation of BIDI requirement 3")
+
+ return label
+
+def ToASCII(label):
+ try:
+ # Step 1: try ASCII
+ label = label.encode("ascii")
+ except UnicodeError:
+ pass
+ else:
+ # Skip to step 3: UseSTD3ASCIIRules is false, so
+ # Skip to step 8.
+ if 0 < len(label) < 64:
+ return label
+ raise UnicodeError("label empty or too long")
+
+ # Step 2: nameprep
+ label = nameprep(label)
+
+ # Step 3: UseSTD3ASCIIRules is false
+ # Step 4: try ASCII
+ try:
+ label = label.encode("ascii")
+ except UnicodeError:
+ pass
+ else:
+ # Skip to step 8.
+ if 0 < len(label) < 64:
+ return label
+ raise UnicodeError("label empty or too long")
+
+ # Step 5: Check ACE prefix
+ if label.startswith(sace_prefix):
+ raise UnicodeError("Label starts with ACE prefix")
+
+ # Step 6: Encode with PUNYCODE
+ label = label.encode("punycode")
+
+ # Step 7: Prepend ACE prefix
+ label = ace_prefix + label
+
+ # Step 8: Check size
+ if 0 < len(label) < 64:
+ return label
+ raise UnicodeError("label empty or too long")
+
+def ToUnicode(label):
+ # Step 1: Check for ASCII
+ if isinstance(label, bytes):
+ pure_ascii = True
+ else:
+ try:
+ label = label.encode("ascii")
+ pure_ascii = True
+ except UnicodeError:
+ pure_ascii = False
+ if not pure_ascii:
+ # Step 2: Perform nameprep
+ label = nameprep(label)
+ # It doesn't say this, but apparently, it should be ASCII now
+ try:
+ label = label.encode("ascii")
+ except UnicodeError:
+ raise UnicodeError("Invalid character in IDN label")
+ # Step 3: Check for ACE prefix
+ if not label.startswith(ace_prefix):
+ return str(label, "ascii")
+
+ # Step 4: Remove ACE prefix
+ label1 = label[len(ace_prefix):]
+
+ # Step 5: Decode using PUNYCODE
+ result = label1.decode("punycode")
+
+ # Step 6: Apply ToASCII
+ label2 = ToASCII(result)
+
+ # Step 7: Compare the result of step 6 with the one of step 3
+ # label2 will already be in lower case.
+ if str(label, "ascii").lower() != str(label2, "ascii"):
+ raise UnicodeError("IDNA does not round-trip", label, label2)
+
+ # Step 8: return the result of step 5
+ return result
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+ def encode(self, input, errors='strict'):
+
+ if errors != 'strict':
+ # IDNA is quite clear that implementations must be strict
+ raise UnicodeError("unsupported error handling "+errors)
+
+ if not input:
+ return b'', 0
+
+ try:
+ result = input.encode('ascii')
+ except UnicodeEncodeError:
+ pass
+ else:
+ # ASCII name: fast path
+ labels = result.split(b'.')
+ for label in labels[:-1]:
+ if not (0 < len(label) < 64):
+ raise UnicodeError("label empty or too long")
+ if len(labels[-1]) >= 64:
+ raise UnicodeError("label too long")
+ return result, len(input)
+
+ result = bytearray()
+ labels = dots.split(input)
+ if labels and not labels[-1]:
+ trailing_dot = b'.'
+ del labels[-1]
+ else:
+ trailing_dot = b''
+ for label in labels:
+ if result:
+ # Join with U+002E
+ result.extend(b'.')
+ result.extend(ToASCII(label))
+ return bytes(result+trailing_dot), len(input)
+
+ def decode(self, input, errors='strict'):
+
+ if errors != 'strict':
+ raise UnicodeError("Unsupported error handling "+errors)
+
+ if not input:
+ return "", 0
+
+ # IDNA allows decoding to operate on Unicode strings, too.
+ if not isinstance(input, bytes):
+ # XXX obviously wrong, see #3232
+ input = bytes(input)
+
+ if ace_prefix not in input:
+ # Fast path
+ try:
+ return input.decode('ascii'), len(input)
+ except UnicodeDecodeError:
+ pass
+
+ labels = input.split(b".")
+
+ if labels and len(labels[-1]) == 0:
+ trailing_dot = '.'
+ del labels[-1]
+ else:
+ trailing_dot = ''
+
+ result = []
+ for label in labels:
+ result.append(ToUnicode(label))
+
+ return ".".join(result)+trailing_dot, len(input)
+
+class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
+ def _buffer_encode(self, input, errors, final):
+ if errors != 'strict':
+ # IDNA is quite clear that implementations must be strict
+ raise UnicodeError("unsupported error handling "+errors)
+
+ if not input:
+ return (b'', 0)
+
+ labels = dots.split(input)
+ trailing_dot = b''
+ if labels:
+ if not labels[-1]:
+ trailing_dot = b'.'
+ del labels[-1]
+ elif not final:
+ # Keep potentially unfinished label until the next call
+ del labels[-1]
+ if labels:
+ trailing_dot = b'.'
+
+ result = bytearray()
+ size = 0
+ for label in labels:
+ if size:
+ # Join with U+002E
+ result.extend(b'.')
+ size += 1
+ result.extend(ToASCII(label))
+ size += len(label)
+
+ result += trailing_dot
+ size += len(trailing_dot)
+ return (bytes(result), size)
+
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
+ def _buffer_decode(self, input, errors, final):
+ if errors != 'strict':
+ raise UnicodeError("Unsupported error handling "+errors)
+
+ if not input:
+ return ("", 0)
+
+ # IDNA allows decoding to operate on Unicode strings, too.
+ if isinstance(input, str):
+ labels = dots.split(input)
+ else:
+ # Must be ASCII string
+ input = str(input, "ascii")
+ labels = input.split(".")
+
+ trailing_dot = ''
+ if labels:
+ if not labels[-1]:
+ trailing_dot = '.'
+ del labels[-1]
+ elif not final:
+ # Keep potentially unfinished label until the next call
+ del labels[-1]
+ if labels:
+ trailing_dot = '.'
+
+ result = []
+ size = 0
+ for label in labels:
+ result.append(ToUnicode(label))
+ if size:
+ size += 1
+ size += len(label)
+
+ result = ".".join(result) + trailing_dot
+ size += len(trailing_dot)
+ return (result, size)
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='idna',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamwriter=StreamWriter,
+ streamreader=StreamReader,
+ )
diff --git a/Lib/encodings/iso2022_jp.py b/Lib/encodings/iso2022_jp.py
new file mode 100644
index 0000000..ab04060
--- /dev/null
+++ b/Lib/encodings/iso2022_jp.py
@@ -0,0 +1,39 @@
+#
+# iso2022_jp.py: Python Unicode Codec for ISO2022_JP
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_jp')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_jp',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso2022_jp_1.py b/Lib/encodings/iso2022_jp_1.py
new file mode 100644
index 0000000..997044d
--- /dev/null
+++ b/Lib/encodings/iso2022_jp_1.py
@@ -0,0 +1,39 @@
+#
+# iso2022_jp_1.py: Python Unicode Codec for ISO2022_JP_1
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_jp_1')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_jp_1',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso2022_jp_2.py b/Lib/encodings/iso2022_jp_2.py
new file mode 100644
index 0000000..9106bf7
--- /dev/null
+++ b/Lib/encodings/iso2022_jp_2.py
@@ -0,0 +1,39 @@
+#
+# iso2022_jp_2.py: Python Unicode Codec for ISO2022_JP_2
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_jp_2')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_jp_2',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso2022_jp_2004.py b/Lib/encodings/iso2022_jp_2004.py
new file mode 100644
index 0000000..40198bf
--- /dev/null
+++ b/Lib/encodings/iso2022_jp_2004.py
@@ -0,0 +1,39 @@
+#
+# iso2022_jp_2004.py: Python Unicode Codec for ISO2022_JP_2004
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_jp_2004')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_jp_2004',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso2022_jp_3.py b/Lib/encodings/iso2022_jp_3.py
new file mode 100644
index 0000000..346e08b
--- /dev/null
+++ b/Lib/encodings/iso2022_jp_3.py
@@ -0,0 +1,39 @@
+#
+# iso2022_jp_3.py: Python Unicode Codec for ISO2022_JP_3
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_jp_3')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_jp_3',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso2022_jp_ext.py b/Lib/encodings/iso2022_jp_ext.py
new file mode 100644
index 0000000..752bab9
--- /dev/null
+++ b/Lib/encodings/iso2022_jp_ext.py
@@ -0,0 +1,39 @@
+#
+# iso2022_jp_ext.py: Python Unicode Codec for ISO2022_JP_EXT
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_jp_ext')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_jp_ext',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso2022_kr.py b/Lib/encodings/iso2022_kr.py
new file mode 100644
index 0000000..bf70187
--- /dev/null
+++ b/Lib/encodings/iso2022_kr.py
@@ -0,0 +1,39 @@
+#
+# iso2022_kr.py: Python Unicode Codec for ISO2022_KR
+#
+# Written by Hye-Shik Chang
+#
+
+import _codecs_iso2022, codecs
+import _multibytecodec as mbc
+
+codec = _codecs_iso2022.getcodec('iso2022_kr')
+
+class Codec(codecs.Codec):
+ encode = codec.encode
+ decode = codec.decode
+
+class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
+ codecs.IncrementalEncoder):
+ codec = codec
+
+class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
+ codecs.IncrementalDecoder):
+ codec = codec
+
+class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
+ codec = codec
+
+class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
+ codec = codec
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso2022_kr',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
diff --git a/Lib/encodings/iso8859_1.py b/Lib/encodings/iso8859_1.py
new file mode 100644
index 0000000..8cfc01f
--- /dev/null
+++ b/Lib/encodings/iso8859_1.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec iso8859_1 generated from 'MAPPINGS/ISO8859/8859-1.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso8859-1',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\x80' # 0x80 ->
+ '\x81' # 0x81 ->
+ '\x82' # 0x82 ->
+ '\x83' # 0x83 ->
+ '\x84' # 0x84 ->
+ '\x85' # 0x85 ->
+ '\x86' # 0x86 ->
+ '\x87' # 0x87 ->
+ '\x88' # 0x88 ->
+ '\x89' # 0x89 ->
+ '\x8a' # 0x8A ->
+ '\x8b' # 0x8B ->
+ '\x8c' # 0x8C ->
+ '\x8d' # 0x8D ->
+ '\x8e' # 0x8E ->
+ '\x8f' # 0x8F ->
+ '\x90' # 0x90 ->
+ '\x91' # 0x91 ->
+ '\x92' # 0x92 ->
+ '\x93' # 0x93 ->
+ '\x94' # 0x94 ->
+ '\x95' # 0x95 ->
+ '\x96' # 0x96 ->
+ '\x97' # 0x97 ->
+ '\x98' # 0x98 ->
+ '\x99' # 0x99 ->
+ '\x9a' # 0x9A ->
+ '\x9b' # 0x9B ->
+ '\x9c' # 0x9C ->
+ '\x9d' # 0x9D ->
+ '\x9e' # 0x9E ->
+ '\x9f' # 0x9F ->
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
+ '\xa2' # 0xA2 -> CENT SIGN
+ '\xa3' # 0xA3 -> POUND SIGN
+ '\xa4' # 0xA4 -> CURRENCY SIGN
+ '\xa5' # 0xA5 -> YEN SIGN
+ '\xa6' # 0xA6 -> BROKEN BAR
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\xa8' # 0xA8 -> DIAERESIS
+ '\xa9' # 0xA9 -> COPYRIGHT SIGN
+ '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
+ '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xac' # 0xAC -> NOT SIGN
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\xae' # 0xAE -> REGISTERED SIGN
+ '\xaf' # 0xAF -> MACRON
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\xb1' # 0xB1 -> PLUS-MINUS SIGN
+ '\xb2' # 0xB2 -> SUPERSCRIPT TWO
+ '\xb3' # 0xB3 -> SUPERSCRIPT THREE
+ '\xb4' # 0xB4 -> ACUTE ACCENT
+ '\xb5' # 0xB5 -> MICRO SIGN
+ '\xb6' # 0xB6 -> PILCROW SIGN
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\xb8' # 0xB8 -> CEDILLA
+ '\xb9' # 0xB9 -> SUPERSCRIPT ONE
+ '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
+ '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
+ '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
+ '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
+ '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
+ '\xbf' # 0xBF -> INVERTED QUESTION MARK
+ '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
+ '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
+ '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
+ '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
+ '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic)
+ '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
+ '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\xd7' # 0xD7 -> MULTIPLICATION SIGN
+ '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
+ '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic)
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German)
+ '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
+ '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe6' # 0xE6 -> LATIN SMALL LETTER AE
+ '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
+ '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
+ '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic)
+ '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
+ '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\xf7' # 0xF7 -> DIVISION SIGN
+ '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
+ '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
+ '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
+ '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic)
+ '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/iso8859_10.py b/Lib/encodings/iso8859_10.py
new file mode 100644
index 0000000..b4fb041
--- /dev/null
+++ b/Lib/encodings/iso8859_10.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec iso8859_10 generated from 'MAPPINGS/ISO8859/8859-10.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso8859-10',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\x80' # 0x80 ->
+ '\x81' # 0x81 ->
+ '\x82' # 0x82 ->
+ '\x83' # 0x83 ->
+ '\x84' # 0x84 ->
+ '\x85' # 0x85 ->
+ '\x86' # 0x86 ->
+ '\x87' # 0x87 ->
+ '\x88' # 0x88 ->
+ '\x89' # 0x89 ->
+ '\x8a' # 0x8A ->
+ '\x8b' # 0x8B ->
+ '\x8c' # 0x8C ->
+ '\x8d' # 0x8D ->
+ '\x8e' # 0x8E ->
+ '\x8f' # 0x8F ->
+ '\x90' # 0x90 ->
+ '\x91' # 0x91 ->
+ '\x92' # 0x92 ->
+ '\x93' # 0x93 ->
+ '\x94' # 0x94 ->
+ '\x95' # 0x95 ->
+ '\x96' # 0x96 ->
+ '\x97' # 0x97 ->
+ '\x98' # 0x98 ->
+ '\x99' # 0x99 ->
+ '\x9a' # 0x9A ->
+ '\x9b' # 0x9B ->
+ '\x9c' # 0x9C ->
+ '\x9d' # 0x9D ->
+ '\x9e' # 0x9E ->
+ '\x9f' # 0x9F ->
+ '\xa0' # 0xA0 -> NO-BREAK SPACE
+ '\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK
+ '\u0112' # 0xA2 -> LATIN CAPITAL LETTER E WITH MACRON
+ '\u0122' # 0xA3 -> LATIN CAPITAL LETTER G WITH CEDILLA
+ '\u012a' # 0xA4 -> LATIN CAPITAL LETTER I WITH MACRON
+ '\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE
+ '\u0136' # 0xA6 -> LATIN CAPITAL LETTER K WITH CEDILLA
+ '\xa7' # 0xA7 -> SECTION SIGN
+ '\u013b' # 0xA8 -> LATIN CAPITAL LETTER L WITH CEDILLA
+ '\u0110' # 0xA9 -> LATIN CAPITAL LETTER D WITH STROKE
+ '\u0160' # 0xAA -> LATIN CAPITAL LETTER S WITH CARON
+ '\u0166' # 0xAB -> LATIN CAPITAL LETTER T WITH STROKE
+ '\u017d' # 0xAC -> LATIN CAPITAL LETTER Z WITH CARON
+ '\xad' # 0xAD -> SOFT HYPHEN
+ '\u016a' # 0xAE -> LATIN CAPITAL LETTER U WITH MACRON
+ '\u014a' # 0xAF -> LATIN CAPITAL LETTER ENG
+ '\xb0' # 0xB0 -> DEGREE SIGN
+ '\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK
+ '\u0113' # 0xB2 -> LATIN SMALL LETTER E WITH MACRON
+ '\u0123' # 0xB3 -> LATIN SMALL LETTER G WITH CEDILLA
+ '\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON
+ '\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE
+ '\u0137' # 0xB6 -> LATIN SMALL LETTER K WITH CEDILLA
+ '\xb7' # 0xB7 -> MIDDLE DOT
+ '\u013c' # 0xB8 -> LATIN SMALL LETTER L WITH CEDILLA
+ '\u0111' # 0xB9 -> LATIN SMALL LETTER D WITH STROKE
+ '\u0161' # 0xBA -> LATIN SMALL LETTER S WITH CARON
+ '\u0167' # 0xBB -> LATIN SMALL LETTER T WITH STROKE
+ '\u017e' # 0xBC -> LATIN SMALL LETTER Z WITH CARON
+ '\u2015' # 0xBD -> HORIZONTAL BAR
+ '\u016b' # 0xBE -> LATIN SMALL LETTER U WITH MACRON
+ '\u014b' # 0xBF -> LATIN SMALL LETTER ENG
+ '\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON
+ '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
+ '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
+ '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
+ '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
+ '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
+ '\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK
+ '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
+ '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
+ '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
+ '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
+ '\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE
+ '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
+ '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
+ '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic)
+ '\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA
+ '\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON
+ '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
+ '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
+ '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
+ '\u0168' # 0xD7 -> LATIN CAPITAL LETTER U WITH TILDE
+ '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
+ '\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK
+ '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
+ '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
+ '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
+ '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic)
+ '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German)
+ '\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON
+ '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
+ '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
+ '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
+ '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
+ '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
+ '\xe6' # 0xE6 -> LATIN SMALL LETTER AE
+ '\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK
+ '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
+ '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
+ '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
+ '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
+ '\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE
+ '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
+ '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
+ '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
+ '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic)
+ '\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA
+ '\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON
+ '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
+ '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
+ '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
+ '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
+ '\u0169' # 0xF7 -> LATIN SMALL LETTER U WITH TILDE
+ '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
+ '\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK
+ '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
+ '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
+ '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
+ '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
+ '\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic)
+ '\u0138' # 0xFF -> LATIN SMALL LETTER KRA
+)
+
+### Encoding table
+encoding_table=codecs.charmap_build(decoding_table)
diff --git a/Lib/encodings/iso8859_11.py b/Lib/encodings/iso8859_11.py
new file mode 100644
index 0000000..c7258ec
--- /dev/null
+++ b/Lib/encodings/iso8859_11.py
@@ -0,0 +1,307 @@
+""" Python Character Mapping Codec iso8859_11 generated from 'MAPPINGS/ISO8859/8859-11.TXT' with gencodec.py.
+
+"""#"
+
+import codecs
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+ def encode(self,input,errors='strict'):
+ return codecs.charmap_encode(input,errors,encoding_table)
+
+ def decode(self,input,errors='strict'):
+ return codecs.charmap_decode(input,errors,decoding_table)
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+ def encode(self, input, final=False):
+ return codecs.charmap_encode(input,self.errors,encoding_table)[0]
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+ def decode(self, input, final=False):
+ return codecs.charmap_decode(input,self.errors,decoding_table)[0]
+
+class StreamWriter(Codec,codecs.StreamWriter):
+ pass
+
+class StreamReader(Codec,codecs.StreamReader):
+ pass
+
+### encodings module API
+
+def getregentry():
+ return codecs.CodecInfo(
+ name='iso8859-11',
+ encode=Codec().encode,
+ decode=Codec().decode,
+ incrementalencoder=IncrementalEncoder,
+ incrementaldecoder=IncrementalDecoder,
+ streamreader=StreamReader,
+ streamwriter=StreamWriter,
+ )
+
+
+### Decoding Table
+
+decoding_table = (
+ '\x00' # 0x00 -> NULL
+ '\x01' # 0x01 -> START OF HEADING
+ '\x02' # 0x02 -> START OF TEXT
+ '\x03' # 0x03 -> END OF TEXT
+ '\x04' # 0x04 -> END OF TRANSMISSION
+ '\x05' # 0x05 -> ENQUIRY
+ '\x06' # 0x06 -> ACKNOWLEDGE
+ '\x07' # 0x07 -> BELL
+ '\x08' # 0x08 -> BACKSPACE
+ '\t' # 0x09 -> HORIZONTAL TABULATION
+ '\n' # 0x0A -> LINE FEED
+ '\x0b' # 0x0B -> VERTICAL TABULATION
+ '\x0c' # 0x0C -> FORM FEED
+ '\r' # 0x0D -> CARRIAGE RETURN
+ '\x0e' # 0x0E -> SHIFT OUT
+ '\x0f' # 0x0F -> SHIFT IN
+ '\x10' # 0x10 -> DATA LINK ESCAPE
+ '\x11' # 0x11 -> DEVICE CONTROL ONE
+ '\x12' # 0x12 -> DEVICE CONTROL TWO
+ '\x13' # 0x13 -> DEVICE CONTROL THREE
+ '\x14' # 0x14 -> DEVICE CONTROL FOUR
+ '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
+ '\x16' # 0x16 -> SYNCHRONOUS IDLE
+ '\x17' # 0x17 -> END OF TRANSMISSION BLOCK
+ '\x18' # 0x18 -> CANCEL
+ '\x19' # 0x19 -> END OF MEDIUM
+ '\x1a' # 0x1A -> SUBSTITUTE
+ '\x1b' # 0x1B -> ESCAPE
+ '\x1c' # 0x1C -> FILE SEPARATOR
+ '\x1d' # 0x1D -> GROUP SEPARATOR
+ '\x1e' # 0x1E -> RECORD SEPARATOR
+ '\x1f' # 0x1F -> UNIT SEPARATOR
+ ' ' # 0x20 -> SPACE
+ '!' # 0x21 -> EXCLAMATION MARK
+ '"' # 0x22 -> QUOTATION MARK
+ '#' # 0x23 -> NUMBER SIGN
+ '$' # 0x24 -> DOLLAR SIGN
+ '%' # 0x25 -> PERCENT SIGN
+ '&' # 0x26 -> AMPERSAND
+ "'" # 0x27 -> APOSTROPHE
+ '(' # 0x28 -> LEFT PARENTHESIS
+ ')' # 0x29 -> RIGHT PARENTHESIS
+ '*' # 0x2A -> ASTERISK
+ '+' # 0x2B -> PLUS SIGN
+ ',' # 0x2C -> COMMA
+ '-' # 0x2D -> HYPHEN-MINUS
+ '.' # 0x2E -> FULL STOP
+ '/' # 0x2F -> SOLIDUS
+ '0' # 0x30 -> DIGIT ZERO
+ '1' # 0x31 -> DIGIT ONE
+ '2' # 0x32 -> DIGIT TWO
+ '3' # 0x33 -> DIGIT THREE
+ '4' # 0x34 -> DIGIT FOUR
+ '5' # 0x35 -> DIGIT FIVE
+ '6' # 0x36 -> DIGIT SIX
+ '7' # 0x37 -> DIGIT SEVEN
+ '8' # 0x38 -> DIGIT EIGHT
+ '9' # 0x39 -> DIGIT NINE
+ ':' # 0x3A -> COLON
+ ';' # 0x3B -> SEMICOLON
+ '<' # 0x3C -> LESS-THAN SIGN
+ '=' # 0x3D -> EQUALS SIGN
+ '>' # 0x3E -> GREATER-THAN SIGN
+ '?' # 0x3F -> QUESTION MARK
+ '@' # 0x40 -> COMMERCIAL AT
+ 'A' # 0x41 -> LATIN CAPITAL LETTER A
+ 'B' # 0x42 -> LATIN CAPITAL LETTER B
+ 'C' # 0x43 -> LATIN CAPITAL LETTER C
+ 'D' # 0x44 -> LATIN CAPITAL LETTER D
+ 'E' # 0x45 -> LATIN CAPITAL LETTER E
+ 'F' # 0x46 -> LATIN CAPITAL LETTER F
+ 'G' # 0x47 -> LATIN CAPITAL LETTER G
+ 'H' # 0x48 -> LATIN CAPITAL LETTER H
+ 'I' # 0x49 -> LATIN CAPITAL LETTER I
+ 'J' # 0x4A -> LATIN CAPITAL LETTER J
+ 'K' # 0x4B -> LATIN CAPITAL LETTER K
+ 'L' # 0x4C -> LATIN CAPITAL LETTER L
+ 'M' # 0x4D -> LATIN CAPITAL LETTER M
+ 'N' # 0x4E -> LATIN CAPITAL LETTER N
+ 'O' # 0x4F -> LATIN CAPITAL LETTER O
+ 'P' # 0x50 -> LATIN CAPITAL LETTER P
+ 'Q' # 0x51 -> LATIN CAPITAL LETTER Q
+ 'R' # 0x52 -> LATIN CAPITAL LETTER R
+ 'S' # 0x53 -> LATIN CAPITAL LETTER S
+ 'T' # 0x54 -> LATIN CAPITAL LETTER T
+ 'U' # 0x55 -> LATIN CAPITAL LETTER U
+ 'V' # 0x56 -> LATIN CAPITAL LETTER V
+ 'W' # 0x57 -> LATIN CAPITAL LETTER W
+ 'X' # 0x58 -> LATIN CAPITAL LETTER X
+ 'Y' # 0x59 -> LATIN CAPITAL LETTER Y
+ 'Z' # 0x5A -> LATIN CAPITAL LETTER Z
+ '[' # 0x5B -> LEFT SQUARE BRACKET
+ '\\' # 0x5C -> REVERSE SOLIDUS
+ ']' # 0x5D -> RIGHT SQUARE BRACKET
+ '^' # 0x5E -> CIRCUMFLEX ACCENT
+ '_' # 0x5F -> LOW LINE
+ '`' # 0x60 -> GRAVE ACCENT
+ 'a' # 0x61 -> LATIN SMALL LETTER A
+ 'b' # 0x62 -> LATIN SMALL LETTER B
+ 'c' # 0x63 -> LATIN SMALL LETTER C
+ 'd' # 0x64 -> LATIN SMALL LETTER D
+ 'e' # 0x65 -> LATIN SMALL LETTER E
+ 'f' # 0x66 -> LATIN SMALL LETTER F
+ 'g' # 0x67 -> LATIN SMALL LETTER G
+ 'h' # 0x68 -> LATIN SMALL LETTER H
+ 'i' # 0x69 -> LATIN SMALL LETTER I
+ 'j' # 0x6A -> LATIN SMALL LETTER J
+ 'k' # 0x6B -> LATIN SMALL LETTER K
+ 'l' # 0x6C -> LATIN SMALL LETTER L
+ 'm' # 0x6D -> LATIN SMALL LETTER M
+ 'n' # 0x6E -> LATIN SMALL LETTER N
+ 'o' # 0x6F -> LATIN SMALL LETTER O
+ 'p' # 0x70 -> LATIN SMALL LETTER P
+ 'q' # 0x71 -> LATIN SMALL LETTER Q
+ 'r' # 0x72 -> LATIN SMALL LETTER R
+ 's' # 0x73 -> LATIN SMALL LETTER S
+ 't' # 0x74 -> LATIN SMALL LETTER T
+ 'u' # 0x75 -> LATIN SMALL LETTER U
+ 'v' # 0x76 -> LATIN SMALL LETTER V
+ 'w' # 0x77 -> LATIN SMALL LETTER W
+ 'x' # 0x78 -> LATIN SMALL LETTER X
+ 'y' # 0x79 -> LATIN SMALL LETTER Y
+ 'z' # 0x7A -> LATIN SMALL LETTER Z
+ '{' # 0x7B -> LEFT CURLY BRACKET
+ '|' # 0x7C -> VERTICAL LINE
+ '}' # 0x7D -> RIGHT CURLY BRACKET
+ '~' # 0x7E -> TILDE
+ '\x7f' # 0x7F -> DELETE
+ '\x80' # 0x80 ->
+ '\x81' # 0x81 ->
+ '\x82' # 0x82 ->
+ '\x83' # 0x83 ->
+ '\x84' # 0x84 ->
+ '\x85' # 0x85 ->
+ '\x86' # 0x86 ->
+ '\x87' # 0x87 ->
+ '\x88' # 0x88 ->