Fix docx parser line bug (#1715)

### What problem does this PR solve?
#1704 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
H
2024-07-29 10:06:02 +08:00
committed by GitHub
parent ebdd71ce68
commit 0cb588f7bf
2 changed files with 5 additions and 2 deletions

View File

@ -23,6 +23,8 @@ from rag.utils import num_tokens_from_string
from PIL import Image
from functools import reduce
from markdown import markdown
class Docx(DocxParser):
def __init__(self):
pass
@ -81,7 +83,8 @@ class Docx(DocxParser):
continue
if 'w:br' in run._element.xml and 'type="page"' in run._element.xml:
pn += 1
new_line = [(line[0], reduce(concat_img, line[1])) for line in lines]
new_line = [(line[0], reduce(concat_img, line[1]) if line[1] else None) for line in lines]
tbls = []
for tb in self.doc.tables:
html= "<table>"