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 github account login issue (#132)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-19 15:31:47 +08:00
committed by GitHub
parent 9da671b951
commit 9a843667b3
6 changed files with 15 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
rag/app/manual.py
View File

@ -62,9 +62,6 @@ class Pdf(PdfParser):
for b in self.boxes:
b["text"] = re.sub(r"([\t 　]|\u3000){2,}", " ", b["text"].strip())
# merge chunks with the same bullets
self._merge_with_same_bullet()
# set pivot using the most frequent type of title,
# then merge between 2 pivot
bull = bullets_category([b["text"] for b in self.boxes])
@ -79,7 +76,7 @@ class Pdf(PdfParser):
sections = [(b["text"], sec_ids[i], get_position(b)) for i, b in enumerate(self.boxes)]
for (img, rows), poss in tbls:
sections.append((rows[0], -1, [(p[0]+1, p[1], p[2], p[3], p[4]) for p in poss]))
sections.append((rows if isinstance(rows, str) else rows[0], -1, [(p[0]+1-from_page, p[1], p[2], p[3], p[4]) for p in poss]))
chunks = []
last_sid = -2