error handling and removed if conditional

cdisc_rules_engine/utilities/data_processor.py

@@ -17,6 +17,7 @@
     DataServiceFactory,
     DummyDataService,
 )
+from cdisc_rules_engine.exceptions.custom_exceptions import PreprocessingError
 from cdisc_rules_engine.utilities.utils import (
     search_in_list_of_dicts,
 )
@@ -211,6 +212,9 @@ def merge_pivot_supp_dataset(
                 for key in static_keys
                 if key in left_dataset.columns and key in right_dataset.columns
             ]
+            DataProcessor._validate_merge_key_overlap(
+                left_dataset, right_dataset, common_keys
+            )
             if not is_blank:
                 common_keys.append(dynamic_key)
                 current_supp = right_dataset.rename(columns={"IDVARVAL": dynamic_key})
@@ -287,6 +291,9 @@ def _merge_supp_with_multiple_idvars(
                 for key in static_keys
                 if key in result_dataset.columns and key in group_data.columns
             ]
+            DataProcessor._validate_merge_key_overlap(
+                result_dataset, group_data, common_keys
+            )
             common_keys.append(idvar_value)
 
             agg_dict = {
@@ -480,3 +487,19 @@ def column_metadata_equal_to_define_and_library(
     @staticmethod
     def is_dummy_data(data_service: DataServiceInterface) -> bool:
         return isinstance(data_service, DummyDataService)
+
+    @staticmethod
+    def _validate_merge_key_overlap(
+        left_dataset: DatasetInterface,
+        right_dataset: DatasetInterface,
+        common_keys: List[str],
+    ):
+        for key in common_keys:
+            left_values = set(left_dataset[key].dropna().unique())
+            right_values = set(right_dataset[key].dropna().unique())
+            if left_values and right_values and left_values.isdisjoint(right_values):
+                raise PreprocessingError(
+                    f"SUPP merge key '{key}' has no overlapping values between "
+                    f"parent dataset and SUPP dataset. "
+                    f"Parent values: {left_values}, SUPP values: {right_values}."
+                )

tests/unit/test_dataset_preprocessor.py

@@ -17,7 +17,7 @@
 from cdisc_rules_engine.models.library_metadata_container import (
     LibraryMetadataContainer,
 )
-
+from cdisc_rules_engine.exceptions.custom_exceptions import PreprocessingError
 from cdisc_rules_engine.models.dataset import PandasDataset
 
 
@@ -1291,6 +1291,69 @@ def test_dm_merged_with_suppdm_without_dupes(
     assert result.data.loc[0, ["RACE1", "RACE2", "RACE3"]].notna().all()
 
 
+@patch("cdisc_rules_engine.services.data_services.LocalDataService.get_dataset")
+def test_preprocess_suppae_mismatched_studyid_raises_key_error(mock_get_dataset):
+    ae_dataset = PandasDataset(
+        pd.DataFrame(
+            {
+                "STUDYID": ["CDISC-PILOT-01"],
+                "DOMAIN": ["AE"],
+                "USUBJID": ["S001"],
+                "AESEQ": [1],
+                "AETERM": ["Headache"],
+            }
+        )
+    )
+    suppae_dataset = PandasDataset(
+        pd.DataFrame(
+            {
+                "STUDYID": ["COMPLETELY-DIFFERENT-STUDY"],
+                "RDOMAIN": ["AE"],
+                "USUBJID": ["S001"],
+                "IDVAR": ["AESEQ"],
+                "IDVARVAL": ["1"],
+                "QNAM": ["TEST"],
+                "QLABEL": ["Test"],
+                "QVAL": ["A"],
+            }
+        )
+    )
+
+    mock_get_dataset.return_value = suppae_dataset
+    rule = {
+        "core_id": "TestRule",
+        "datasets": [{"domain_name": "SUPPAE", "match_key": ["USUBJID"]}],
+        "conditions": ConditionCompositeFactory.get_condition_composite(
+            {
+                "all": [
+                    {
+                        "name": "get_dataset",
+                        "operator": "equal_to",
+                        "value": {"target": "TEST", "comparator": "A"},
+                    }
+                ]
+            }
+        ),
+    }
+    datasets = [
+        SDTMDatasetMetadata(
+            name="SUPPAE", first_record={"RDOMAIN": "AE"}, filename="suppae.xpt"
+        )
+    ]
+    data_service = LocalDataService(MagicMock(), MagicMock(), MagicMock())
+    preprocessor = DatasetPreprocessor(
+        ae_dataset,
+        SDTMDatasetMetadata(first_record={"DOMAIN": "AE"}, full_path="path"),
+        data_service,
+        InMemoryCacheService(),
+    )
+
+    with pytest.raises(
+        PreprocessingError, match="SUPP merge key 'STUDYID' has no overlapping values"
+    ):
+        preprocessor.preprocess(rule, datasets)
+
+
 def test_relrec_processed_correctly_with_others(rule_with_specific_supp):
     ec_meta = SDTMDatasetMetadata(
         name="EC",