zhuchaowe/maxkb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Part of the docx document is parsed incorrectly (#1981)

Browse Source
This commit is contained in:
shaohuzhang1 2025-01-06 14:37:51 +08:00 committed by GitHub
parent 00591a5b25
commit d9df013e33
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
apps/common/handle/impl/doc_split_handle.py
View File

@ -113,8 +113,10 @@ class DocSplitHandle(BaseSplitHandle):
def paragraph_to_md(paragraph: Paragraph, doc: Document, images_list, get_image_id): def paragraph_to_md(paragraph: Paragraph, doc: Document, images_list, get_image_id):
try: try:
psn = paragraph.style.name psn = paragraph.style.name
if psn.startswith('Heading'): if psn.startswith('Heading') or psn.startswith('TOC 标题') or psn.startswith('标题'):
title = "".join(["#" for i in range(int(psn.replace("Heading ", '')))]) + " " + paragraph.text title = "".join(["#" for i in range(
int(psn.replace("Heading ", '').replace('TOC 标题', '').replace('标题',
'')))]) + " " + paragraph.text
images = reduce(lambda x, y: [*x, *y], images = reduce(lambda x, y: [*x, *y],
[get_paragraph_element_images(e, doc, images_list, get_image_id) for e in [get_paragraph_element_images(e, doc, images_list, get_image_id) for e in
paragraph._element], paragraph._element],
@ -202,4 +204,4 @@ class DocSplitHandle(BaseSplitHandle):
return content return content
except BaseException as e: except BaseException as e:
traceback.print_exception(e) traceback.print_exception(e)
return f'{e}' return f'{e}'