new template, changed filename origin

README.md

@@ -100,7 +100,7 @@ Run `python core.py validate --help` to see the list of validation options.
   -me, --max-errors-per-rule INTEGER BOOLEAN
                                   Imposes a maximum number of errors per rule to enforce.
                                   Usage: -me <limit> <per_dataset_flag>
-                                  Example: -me 100 true
+                                  Example: -me 100 True (make sure to use capital for True/False)
 
                                   <limit>: Maximum number of errors (integer)
 
@@ -115,7 +115,7 @@ Run `python core.py validate --help` to see the list of validation options.
                                       the first <limit> issues per dataset are included in the report.
 
                                   Can be set via MAX_ERRORS_PER_RULE env variable;
-                                  if both .env and -me <limit> are specified, the larger value will be used.
+                                  if both .env and -me <limit> are specified, the larger value will be used.  If either sets the per_dataset_flag to true, it will be true
                                   If limit is set to 0, no maximum will be enforced.
                                   No maximum is the default behavior.
   -dv, --define-version TEXT      Define-XML version used for validation

cdisc_rules_engine/services/reporting/base_report_data.py

@@ -8,6 +8,7 @@
 from cdisc_rules_engine.services.reporting.report_metadata_item import (
     ReportMetadataItem,
 )
+from cdisc_rules_engine.utilities.utils import set_max_errors_per_rule
 
 
 class BaseReportData(ABC):
@@ -33,7 +34,9 @@ def __init__(
         self._template = template
         self._standard = args.standard.upper()
         self._version = args.version.replace("-", ".")
-        self._max_errors_limit, self._errors_per_dataset_flag = args.max_errors_per_rule
+        self._max_errors_limit, self._errors_per_dataset_flag = set_max_errors_per_rule(
+            args
+        )
 
     @staticmethod
     def process_values(values: list[str]) -> list[str]:

cdisc_rules_engine/services/reporting/sdtm_report_data.py

@@ -105,17 +105,17 @@ def get_conformance_details_data(
             ReportMetadataItem("CORE Engine Version", 4, __version__)
         )
         conformance_details.append(
-            ReportMetadataItem("Issue Limit Per Rule", 5, self._max_errors_limit)
+            ReportMetadataItem(
+                "Issue Limit Per Rule",
+                5,
+                "None" if self._max_errors_limit is None else self._max_errors_limit,
+            )
         )
         conformance_details.append(
             ReportMetadataItem(
                 "Issue Limit Per Dataset",
                 6,
-                (
-                    "None"
-                    if self._errors_per_dataset_flag == 0
-                    else str(self._errors_per_dataset_flag)
-                ),
+                "True" if self._errors_per_dataset_flag else "None",
             )
         )
         conformance_details.append(
@@ -186,7 +186,7 @@ def get_conformance_details_data(
     def get_dataset_details_data(self) -> list[dict]:
         return [
             {
-                "filename": dataset.filename,
+                "filename": dataset.name,
                 "label": dataset.label,
                 "path": str(Path(dataset.full_path or "").parent),
                 "modification_date": dataset.modification_date,

cdisc_rules_engine/utilities/utils.py

@@ -6,6 +6,7 @@
 import copy
 import os
 import re
+import ast
 import pandas as pd
 from datetime import datetime
 from typing import Callable, Iterable, List, Optional, Union
@@ -451,3 +452,32 @@ def validate_dataset_files_exist(dataset_path: tuple[str], logger, ctx):
     if non_existing_files:
         logger.error(f'Files {", ".join(non_existing_files)} are not found')
         ctx.exit(2)
+
+
+def set_max_errors_per_rule(args):
+    env_value = (
+        (os.getenv("MAX_ERRORS_PER_RULE")) if os.getenv("MAX_ERRORS_PER_RULE") else None
+    )
+
+    if env_value:
+        parsed_tuple = ast.literal_eval(env_value)
+        env_max_errors = parsed_tuple[0]
+        env_per_dataset = parsed_tuple[1]
+    else:
+        env_max_errors = None
+        env_per_dataset = None
+    cli_limit, cli_per_dataset = args.max_errors_per_rule
+    if env_max_errors is not None and cli_limit > 0:
+        max_errors_per_rule = max(env_max_errors, cli_limit)
+    elif env_max_errors is not None:
+        max_errors_per_rule = env_max_errors
+    elif cli_limit and cli_limit > 0:
+        max_errors_per_rule = cli_limit
+    else:
+        max_errors_per_rule = None
+
+    if max_errors_per_rule is not None and max_errors_per_rule <= 0:
+        max_errors_per_rule = None
+
+    per_dataset = bool(env_per_dataset or cli_per_dataset)
+    return max_errors_per_rule, per_dataset

env.example

@@ -1,4 +1,4 @@
-CDISC_LIBRARY_API_KEY = 012345
-DATASET_SIZE_THRESHOLD = size_in_bytes to force dask implementation
-MAX_REPORT_ROWS = maximum number of issues per excel sheet (plus headers) in result report
-MAX_ERRORS_PER_RULE = maximum number of errors to report per rule during a validation run.
+CDISC_LIBRARY_API_KEY=your_api_key_here
+DATASET_SIZE_THRESHOLD=10485760  # max dataset size in bytes to force dask implementation
+MAX_REPORT_ROWS = 10  # integer for maximum number of issues per excel sheet (plus headers) in result report
+MAX_ERRORS_PER_RULE = (10, True)  # Tuple for maximum number of errors to report per rule during a validation run. Also has a per dataset flag described as second bool value in readme. example value 

scripts/run_validation.py

@@ -37,14 +37,14 @@
     get_model_details_cache_key_from_ig,
     get_standard_details_cache_key,
     get_variable_codelist_map_cache_key,
+    set_max_errors_per_rule,
 )
 from scripts.script_utils import (
     fill_cache_with_dictionaries,
     get_cache_service,
     get_library_metadata_from_cache,
     get_rules,
     get_max_dataset_size,
-    set_max_errors_per_rule,
 )
 from cdisc_rules_engine.services.reporting import BaseReport, ReportFactory
 from cdisc_rules_engine.utilities.progress_displayers import get_progress_displayer

scripts/script_utils.py

@@ -530,25 +530,3 @@ def replace_yml_spaces(data):
         return [replace_yml_spaces(item) for item in data]
     else:
         return data
-
-
-def set_max_errors_per_rule(args):
-    env_value = (
-        int(os.getenv("MAX_ERRORS_PER_RULE"))
-        if os.getenv("MAX_ERRORS_PER_RULE")
-        else None
-    )
-    cli_limit, cli_per_dataset = args.max_errors_per_rule
-    if env_value is not None and cli_limit > 0:
-        max_errors_per_rule = max(env_value, cli_limit)
-    elif env_value is not None:
-        max_errors_per_rule = env_value
-    elif cli_limit > 0:
-        max_errors_per_rule = cli_limit
-    else:
-        max_errors_per_rule = None
-
-    if max_errors_per_rule is not None and max_errors_per_rule <= 0:
-        max_errors_per_rule = None
-
-    return max_errors_per_rule, cli_per_dataset

tests/unit/test_services/test_reporting/test_excel_export.py

@@ -25,7 +25,7 @@ def test_get_export(mock_validation_results):
         mock_args.meddra = "test"
         mock_args.whodrug = "test"
         mock_args.max_report_rows = None
-        mock_args.max_errors_per_rule = (None, False)
+        mock_args.max_errors_per_rule = (10, True)
         mock_args.controlled_terminology_package = ["sdtmct-03-2021"]
         mock_args.standard = "sdtmig"
         mock_args.substandard = None
@@ -34,6 +34,7 @@ def test_get_export(mock_validation_results):
         datasets = [
             SDTMDatasetMetadata(
                 **{
+                    "name": "test",
                     "filename": "test.xpt",
                     "label": "Test Data",
                     "full_path": str(Path("tests/unit/text.xpt")),
@@ -50,6 +51,9 @@ def test_get_export(mock_validation_results):
         wb = report.get_export()
         assert wb["Conformance Details"]["B3"].value == "10.1 seconds"
         assert wb["Conformance Details"]["B4"].value == __version__
+        assert wb["Conformance Details"]["B5"].value == 10
+        assert wb["Conformance Details"]["B6"].value == "True"
+        assert wb["Conformance Details"]["B7"].value == "10000"
         assert wb["Conformance Details"]["B9"].value == "SDTMIG"
         assert wb["Conformance Details"]["B10"].value == "NAP"
         assert wb["Conformance Details"]["B11"].value == "V3.4"
@@ -59,7 +63,7 @@ def test_get_export(mock_validation_results):
         assert wb["Conformance Details"]["B13"].value == "2.1"
 
         # Check dataset details tab
-        assert wb["Dataset Details"]["A2"].value == "test.xpt"  # filename
+        assert wb["Dataset Details"]["A2"].value == "test"  # filename
         assert wb["Dataset Details"]["B2"].value == "Test Data"  # label
         assert wb["Dataset Details"]["C2"].value == str(
             Path("tests/unit/text.xpt").parent

tests/unit/test_services/test_reporting/test_json_export.py

@@ -32,8 +32,9 @@ def test_get_export(_, mock_validation_results):
     assert export["Conformance_Details"]["Version"] == "V3.4"
     assert export["Conformance_Details"]["CT_Version"] == "sdtmct-03-2021"
     assert export["Conformance_Details"]["Define_XML_Version"] == "2.1"
-    assert export["Conformance_Details"]["Issue_Limit_Per_Rule"] is None
+    assert export["Conformance_Details"]["Issue_Limit_Per_Rule"] == "None"
     assert export["Conformance_Details"]["Issue_Limit_Per_Dataset"] == "None"
+    assert export["Conformance_Details"]["Issue_Limit_Per_Sheet"] is None
     assert "Dataset_Details" in export
     assert isinstance(export["Dataset_Details"], list)