pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: debug pipeline... (#10311)

Browse Source 
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-09-26 19:11:30 +08:00
committed by GitHub
parent 771a38434f
commit 76b1ee2a00
18 changed files with 116 additions and 474 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deepdoc/parser/pdf_parser.py
View File

@ -1127,7 +1127,7 @@ class RAGFlowPdfParser:
for tag in re.findall(r"@@[0-9-]+\t[0-9.\t]+##", txt):
pn, left, right, top, bottom = tag.strip("#").strip("@").split("\t")
left, right, top, bottom = float(left), float(right), float(top), float(bottom)
poss.append(([int(p) - 1 for p in pn.split("-")], left, right, top, bottom))
poss.append(([int(p) - 1 for p in pn.split("-")], int(left), int(right), int(top), int(bottom)))
return poss
def crop(self, text, ZM=3, need_position=False):