AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 16:38:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix pdfparser error (#1707)

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:
H 2024-07-25 18:54:36 +08:00 committed by GitHub
parent 935687998e
commit c943517932
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
deepdoc/vision/layout_recognizer.py
View File

@ -75,7 +75,7 @@ class LayoutRecognizer(Recognizer):
"x0": b["bbox"][0] / scale_factor, "x1": b["bbox"][2] / scale_factor, "x0": b["bbox"][0] / scale_factor, "x1": b["bbox"][2] / scale_factor,
"top": b["bbox"][1] / scale_factor, "bottom": b["bbox"][-1] / scale_factor, "top": b["bbox"][1] / scale_factor, "bottom": b["bbox"][-1] / scale_factor,
"page_number": pn, "page_number": pn,
} for b in lts] } for b in lts if float(b["score"]) >= 0.8 or b["type"] not in self.garbage_layouts]
lts = self.sort_Y_firstly(lts, np.mean( lts = self.sort_Y_firstly(lts, np.mean(
[l["bottom"] - l["top"] for l in lts]) / 2) [l["bottom"] - l["top"] for l in lts]) / 2)
lts = self.layouts_cleanup(bxs, lts) lts = self.layouts_cleanup(bxs, lts)