library_variable_has_codelist new metadata

cdisc_rules_engine/dataset_builders/base_dataset_builder.py

@@ -217,12 +217,14 @@ def get_library_variables_metadata(self) -> DatasetInterface:
         )
         for variable in variables:
             variable["ccode"] = ""
+            variable["has_codelist"] = False
             variable_metadata: Optional[dict] = variables_metadata.get(variable["name"])
             if variable_metadata:
                 if "_links" in variable and "codelist" in variable["_links"]:
                     first_codelist = variable["_links"]["codelist"][0]
                     codelist_code = first_codelist["href"].split("/")[-1]
                     variable["ccode"] = codelist_code
+                    variable["has_codelist"] = True
             if "role" not in variable:
                 variable["role"] = ""
             if "core" not in variable:

cdisc_rules_engine/dataset_builders/define_variables_with_library_metadata.py

@@ -29,6 +29,7 @@ def build(self):
         "library_variable_data_type",
         "library_variable_role",
         "library_variable_core",
+        "library_variable_has_codelist",
         "library_variable_ccode",
         "library_variable_order_number"
         """

cdisc_rules_engine/dataset_builders/variables_metadata_with_define_and_library_dataset_builder.py

@@ -36,6 +36,7 @@ def build(self):
         library_variable_data_type,
         library_variable_role,
         library_variable_core,
+        library_variable_has_codelist,
         library_variable_ccode,
         library_variable_order_number
         """
@@ -74,6 +75,7 @@ def build(self):
                     "library_variable_data_type",
                     "library_variable_role",
                     "library_variable_core",
+                    "library_variable_has_codelist",
                     "library_variable_ccode",
                     "library_variable_order_number",
                 ]

cdisc_rules_engine/dataset_builders/variables_metadata_with_library_metadata.py

@@ -20,6 +20,7 @@ def build(self):
         library_variable_role,
         library_variable_core,
         library_variable_ccode,
+        library_variable_has_codelist
         library_variable_order_number
         """
         # get dataset metadata and execute the rule
@@ -50,6 +51,7 @@ def build(self):
                     "library_variable_role",
                     "library_variable_core",
                     "library_variable_ccode",
+                    "library_variable_has_codelist",
                     "library_variable_order_number",
                 ]
             ],

resources/schema/rule/MetaVariables.json

@@ -139,6 +139,8 @@
     },
     { "const": "filename" },
     { "const": "library_variable_core" },
+    { "const": "library_variable_has_codelist" },
+    { "const": "library_variable_ccode" },
     { "const": "library_variable_data_type" },
     { "const": "library_variable_label" },
     { "const": "library_variable_name" },

resources/schema/rule/MetaVariables.md

@@ -222,6 +222,14 @@ ordinal attribute of a variable from the CDISC Library
 
 role attribute of a variable from the CDISC Library
 
+## library_variable_ccode
+
+ccode attribute of a variable from the CDISC Library
+
+## library_variable_has_codelist
+
+Indicates whether a variable has an associated codelist in the CDISC Library
+
 ## row_number
 
 1-based index of record number

resources/schema/rule/Rule_Type.md

@@ -315,6 +315,7 @@ all:
 - `library_variable_data_type`
 - `library_variable_role`
 - `library_variable_core`
+- `library_variable_has_codelist`
 - `library_variable_ccode`
 
 #### Rule Macro

tests/unit/test_dataset_builders/test_define_variables_with_library_metadata.py

@@ -55,6 +55,7 @@ def test_define_variables_metadata_with_library_metadata_dataset_builder(
             "library_variable_core": ["Req", "Req", "Req", "Req"],
             "library_variable_order_number": ["1", "2", "8", "9"],
             "library_variable_data_type": ["Char", "Char", "Num", "Char"],
+            "library_variable_has_codelist": [False, False, False, False],
         }
     )
     mock_get_library_variables_metadata.return_value = PandasDataset(library_vars_data)
@@ -232,6 +233,7 @@ def test_define_variables_metadata_with_library_metadata_dataset_builder(
         "library_variable_core",
         "library_variable_order_number",
         "library_variable_data_type",
+        "library_variable_has_codelist",
     ]
     intersection = {"STUDYID", "USUBJID", "AESEQ", "AETERM"}
 

tests/unit/test_dataset_builders/test_variables_metadata_with_define_and_library_dataset_builder.py

@@ -78,6 +78,7 @@ def test_build_combined_metadata(
             "library_variable_order_number": ["1", "2", "9", "8"],
             "library_variable_data_type": ["Char", "Char", "Char", "Num"],
             "library_variable_ccode": ["C49487", "C69256", "C41331", "C25364"],
+            "library_variable_has_codelist": [True, True, True, True],
         }
     )
     mock_get_library_variables_metadata.return_value = PandasDataset(library_vars_data)
@@ -181,6 +182,7 @@ def test_build_combined_metadata(
         "library_variable_role",
         "library_variable_core",
         "library_variable_ccode",
+        "library_variable_has_codelist",
         "library_variable_order_number",
         "variable_has_empty_values",
         "variable_is_empty",
@@ -228,3 +230,4 @@ def test_build_combined_metadata(
         assert row["library_variable_role"] in ["Identifier", "Topic"]
         assert row["library_variable_core"] == "Req"
         assert row["library_variable_ccode"] in ["C49487", "C69256", "C41331"]
+        assert row["library_variable_has_codelist"] in [True, True, True]

tests/unit/test_dataset_builders/test_variables_metadata_with_library_metadata_dataset_builder.py

@@ -55,6 +55,7 @@ def test_variable_metadata_with_library_metadata_dataset_builder(
             "library_variable_order_number": ["1", "2", "9", "8"],
             "library_variable_data_type": ["Char", "Char", "Char", "Num"],
             "library_variable_ccode": ["C49487", "C69256", "C41331", "C25364"],
+            "library_variable_has_codelist": [True, True, True, True],
         }
     )
     mock_get_library_variables_metadata.return_value = PandasDataset(library_vars_data)
@@ -164,6 +165,7 @@ def test_variable_metadata_with_library_metadata_dataset_builder(
         "library_variable_role",
         "library_variable_core",
         "library_variable_ccode",
+        "library_variable_has_codelist",
         "library_variable_order_number",
         "variable_has_empty_values",
         "variable_is_empty",
@@ -217,6 +219,7 @@ def test_variable_metadata_with_library_metadata_dataset_builder_variable_only_i
             "library_variable_order_number": ["1", "2", "9", "2000"],
             "library_variable_data_type": ["Char", "Char", "Char", "Num"],
             "library_variable_ccode": ["C49487", "C69256", "C41331", "C25364"],
+            "library_variable_has_codelist": [True, True, True, True],
         }
     )
     mock_get_library_variables_metadata.return_value = PandasDataset(library_vars_data)
@@ -388,6 +391,7 @@ def test_variable_metadata_with_library_metadata_dataset_builder_variable_only_i
             "library_variable_core",
             "library_variable_data_type",
             "library_variable_ccode",
+            "library_variable_has_codelist",
             "variable_has_empty_values",
             "variable_is_empty",
         ]