digisky
/
legal-doc-masker
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feature-ner-keyword-detect #1

Merged
tigeren merged 35 commits from feature-ner-keyword-detect into main 2025-07-20 13:44:00 +00:00
Conversation 0 Commits 35 Files Changed 78 +7
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 94e500c990 - Show all commits

7
backend/app/core/document_handlers/ner_processor.py
View File

@ -232,8 +232,15 @@ class NerProcessor:
logger.info(f"Final chunk mappings: {chunk_mappings}") logger.info(f"Final chunk mappings: {chunk_mappings}")
unique_entities = self._merge_entity_mappings(chunk_mappings) unique_entities = self._merge_entity_mappings(chunk_mappings)
logger.info(f"Unique entities: {unique_entities}")
entity_linkage = self._create_entity_linkage(unique_entities) entity_linkage = self._create_entity_linkage(unique_entities)
logger.info(f"Entity linkage: {entity_linkage}")
combined_mapping = self._generate_masked_mapping(unique_entities) combined_mapping = self._generate_masked_mapping(unique_entities)
logger.info(f"Combined mapping: {combined_mapping}")
final_mapping = self._apply_entity_linkage_to_mapping(combined_mapping, entity_linkage) final_mapping = self._apply_entity_linkage_to_mapping(combined_mapping, entity_linkage)
logger.info(f"Final mapping: {final_mapping}")
return final_mapping return final_mapping