fix bug in pdf parser (#986)
### What problem does this PR solve? #963 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
parent
f077b57f8b
commit
843720f958
1 changed files with 1 additions and 1 deletions
|
|
@ -392,7 +392,7 @@ class RAGFlowPdfParser:
|
||||||
b["text"].strip()[-1] in ",;:'\",、‘“;:-",
|
b["text"].strip()[-1] in ",;:'\",、‘“;:-",
|
||||||
len(b["text"].strip()) > 1 and b["text"].strip(
|
len(b["text"].strip()) > 1 and b["text"].strip(
|
||||||
)[-2] in ",;:'\",‘“、;:",
|
)[-2] in ",;:'\",‘“、;:",
|
||||||
b_["text"].strip()[0] in "。;?!?”)),,、:",
|
b_["text"].strip() and b_["text"].strip()[0] in "。;?!?”)),,、:",
|
||||||
]
|
]
|
||||||
# features for not concating
|
# features for not concating
|
||||||
feats = [
|
feats = [
|
||||||
|
|
|
||||||
Loading…
Add table
Reference in a new issue