Get mapping of column names to their source data files
(self)
| 376 | self.logger.debug(f"Discovered schema for {source_name}: {len(result)} columns") |
| 377 | |
| 378 | def get_column_to_source_mapping(self) -> Dict[str, str]: |
| 379 | """Get mapping of column names to their source data files""" |
| 380 | mapping = {} |
| 381 | |
| 382 | for source_name, columns in self.schema_cache.items(): |
| 383 | alias = self.DATA_SOURCES[source_name]['alias'] |
| 384 | for col_name, _ in columns: |
| 385 | # Handle column name conflicts by prefixing with source alias |
| 386 | if col_name in mapping and mapping[col_name] != source_name: |
| 387 | # This column exists in multiple sources |
| 388 | prefixed_name = f"{alias}.{col_name}" |
| 389 | mapping[prefixed_name] = source_name |
| 390 | else: |
| 391 | mapping[col_name] = source_name |
| 392 | |
| 393 | return mapping |
| 394 | |
| 395 | def get_columns_by_source(self) -> Dict[str, List[str]]: |
| 396 | """Get columns grouped by their source""" |
no outgoing calls
no test coverage detected