whitespace column header removal

cdisc_rules_engine/services/data_readers/json_reader.py

@@ -10,7 +10,10 @@ def from_file(self, file_path):
         try:
             with open(file_path, "r", encoding=self.encoding) as fp:
                 json_data = load(fp)
+            self._detect_whitespace_in_dataset_keys(json_data, file_path)
             return json_data
+        except InvalidJSONFormat:
+            raise
         except (UnicodeDecodeError, UnicodeError) as e:
             raise InvalidJSONFormat(
                 f"\n  Error reading JSON from: {file_path}"
@@ -23,5 +26,21 @@ def from_file(self, file_path):
                 f"\n  {type(e).__name__}: {e}"
             )
 
+    def _detect_whitespace_in_dataset_keys(self, json_data: dict, file_path: str):
+        offending = []
+        for dataset in json_data.get("datasets", []):
+            dataset_name = dataset.get("filename")
+            records = dataset.get("records", {})
+            for key in records:
+                if key != key.strip():
+                    offending.append(f"    dataset '{dataset_name}': {repr(key)}")
+        if offending:
+            offending_list = "\n".join(offending)
+            raise InvalidJSONFormat(
+                f"\n  Error reading JSON from: {file_path}"
+                f"\n  The following column keys contain leading/trailing whitespace:"
+                f"\n{offending_list}"
+            )
+
     def read(self, data):
         pass

cdisc_rules_engine/services/data_services/excel_data_service.py

@@ -105,6 +105,12 @@ def get_dataset(self, dataset_name: str, **params) -> DatasetInterface:
             false_values=["False", "FALSE", "false", False, 0, "0"],
         )
         dataframe = dataframe.replace({nan: None})
+        offending = [col for col in dataframe.columns if col != col.strip()]
+        if offending:
+            raise ExcelTestDataError(
+                f"Sheet '{dataset_name}' has column headers with leading/trailing whitespace: "
+                f"{[repr(c) for c in offending]}."
+            )
         dataset = PandasDataset(dataframe)
         return dataset