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 out of boundary. (#3786)

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

#3769
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2024-12-02 11:38:53 +08:00
committed by GitHub
parent a7efd3cac5
commit 7058ac0041
2 changed files with 25 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deepdoc/parser/pdf_parser.py
View File

@ -152,7 +152,7 @@ class RAGFlowPdfParser:
max(len(up["text"]), len(down["text"])),
len(tks_all) - len(tks_up) - len(tks_down),
len(tks_down) - len(tks_up),
tks_down[-1] == tks_up[-1],
tks_down[-1] == tks_up[-1] if tks_down and tks_up else False,
max(down["in_row"], up["in_row"]),
abs(down["in_row"] - up["in_row"]),
len(tks_down) == 1 and rag_tokenizer.tag(tks_down[0]).find("n") >= 0,