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 plainPdf bugs (#152)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-26 15:11:07 +08:00
committed by GitHub
parent 75f7c6da2f
commit da21320b88
13 changed files with 36 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deepdoc/parser/pdf_parser.py
View File

@ -996,7 +996,7 @@ class HuParser:
if need_position: return None, None
return
max_width = np.max([right - left for (_, left, right, _, _) in poss])
max_width = max(np.max([right - left for (_, left, right, _, _) in poss]), 6)
GAP = 6
pos = poss[0]
poss.insert(0, ([pos[0][0]], pos[1], pos[2], max(0, pos[3] - 120), max(pos[3] - GAP, 0)))