gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Improve handling of position extraction in manual.py

Browse source 
Refactor position extraction logic to handle empty cases.
This commit is contained in:
Magicbook1108 2025-12-09 17:23:17 +08:00 • committed by GitHub
parent d992b46c3b
commit b970d4b425
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
rag/app/manual.py
View file

@ -229,13 +229,14 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
txt, layoutno, poss = section
if isinstance(poss, str):
poss = pdf_parser.extract_positions(poss)
first = poss[0] # tuple: ([pn], x1, x2, y1, y2)
pn = first[0]
if isinstance(pn, list):
pn = pn[0] # [pn] -> pn
poss[0] = (pn, *first[1:])
if poss:
poss = pdf_parser.extract_positions(poss)
first = poss[0] # tuple: ([pn], x1, x2, y1, y2)
pn = first[0]
if isinstance(pn, list) and pn:
pn = pn[0] # [pn] -> pn
poss[0] = (pn, *first[1:])
return (txt, layoutno, poss)
@ -345,4 +346,4 @@ if __name__ == "__main__":
pass
chunk(sys.argv[1], callback=dummy)
chunk(sys.argv[1], callback=dummy)