yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-11-13 16:43:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove space between chinese chars and Egnlish symbols

Browse Source
This commit is contained in:
yangdx 2025-04-21 19:21:30 +08:00
parent ff65cba544
commit 17f5439952
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lightrag/utils.py
View File

@ -1448,9 +1448,9 @@ def normalize_extracted_info(name: str, is_entity=False) -> str:
# (?=[\u4e00-\u9fa5]): Positive lookahead for Chinese character # (?=[\u4e00-\u9fa5]): Positive lookahead for Chinese character
name = re.sub(r"(?<=[\u4e00-\u9fa5])\s+(?=[\u4e00-\u9fa5])", "", name) name = re.sub(r"(?<=[\u4e00-\u9fa5])\s+(?=[\u4e00-\u9fa5])", "", name)
# Remove spaces between Chinese and English/numbers # Remove spaces between Chinese and English/numbers/symbols
name = re.sub(r"(?<=[\u4e00-\u9fa5])\s+(?=[a-zA-Z0-9])", "", name) name = re.sub(r"(?<=[\u4e00-\u9fa5])\s+(?=[a-zA-Z0-9\(\)\[\]@#$%!&\*\-=+_])", "", name)
name = re.sub(r"(?<=[a-zA-Z0-9])\s+(?=[\u4e00-\u9fa5])", "", name) name = re.sub(r"(?<=[a-zA-Z0-9\(\)\[\]@#$%!&\*\-=+_])\s+(?=[\u4e00-\u9fa5])", "", name)
# Remove English quotation marks from the beginning and end # Remove English quotation marks from the beginning and end
if len(name) >= 2 and name.startswith('"') and name.endswith('"'): if len(name) >= 2 and name.startswith('"') and name.endswith('"'):