test/dify
1
0
Fork 0
mirror of https://gitee.com/dify_ai/dify.git synced 2024-12-03 19:57:37 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

extract docx filter comment element (#7092)

Browse Source
This commit is contained in:
Jyong 2024-08-08 16:53:29 +08:00 committed by GitHub
parent 925f0d2e09
commit 12095f8cd6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
api/core/rag/extractor/word_extractor.py
View File

@ -228,7 +228,7 @@ class WordExtractor(BaseExtractor):
def parse_paragraph(paragraph):
paragraph_content = []
for run in paragraph.runs:
if run.element.tag.endswith('r'):
if hasattr(run.element, 'tag') and isinstance(element.tag, str) and run.element.tag.endswith('r'):
drawing_elements = run.element.findall(
'.//{http://schemas.openxmlformats.org/wordprocessingml/2006/main}drawing')
for drawing in drawing_elements:
@ -248,13 +248,14 @@ class WordExtractor(BaseExtractor):
paragraphs = doc.paragraphs.copy()
tables = doc.tables.copy()
for element in doc.element.body:
if element.tag.endswith('p'): # paragraph
para = paragraphs.pop(0)
parsed_paragraph = parse_paragraph(para)
if parsed_paragraph:
content.append(parsed_paragraph)
elif element.tag.endswith('tbl'): # table
table = tables.pop(0)
content.append(self._table_to_markdown(table,image_map))
if hasattr(element, 'tag'):
if isinstance(element.tag, str) and element.tag.endswith('p'): # paragraph
para = paragraphs.pop(0)
parsed_paragraph = parse_paragraph(para)
if parsed_paragraph:
content.append(parsed_paragraph)
elif isinstance(element.tag, str) and element.tag.endswith('tbl'): # table
table = tables.pop(0)
content.append(self._table_to_markdown(table,image_map))
return '\n'.join(content)