zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-14 00:48:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(nlp): prevent dotted-number cross-references from being classified as headings in Laws chunker (#16626)

Browse Source
This commit is contained in:
OSHA-B
2026-07-06 07:02:58 +02:00
committed by GitHub
parent 48ef1f4965
commit d607b55c24
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/nlp/__init__.py
View File

@@ -296,7 +296,7 @@ def random_choices(arr, k):
def not_bullet(line):
patt = [r"0", r"[0-9]+ +[0-9~个只-]", r"[0-9]+\.{2,}"]
patt = [r"0", r"[0-9]+ +[0-9~个只-]", r"[0-9]+\.{2,}", r"[0-9]+(\.[0-9]+){2,}[的中]"]
return any([re.match(r, line) for r in patt])
@@ -1029,7 +1029,7 @@ def tree_merge(bull, sections, depth):
text = re.sub(r"\u3000", " ", text).strip()
for i, title in enumerate(BULLET_PATTERN[bull]):
if re.match(title, text.strip()):
if re.match(title, text.strip()) and not not_bullet(text):
return i + 1, text
else:
if re.search(r"(title|head)", layout) and not not_title(text):