mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-30 14:04:27 +00:00
fix: make sure page_items are sorted by page_no
Signed-off-by: Yusik Kim <kmyusk@gmail.com>
This commit is contained in:
parent
38a23eb50b
commit
3a09ca50bb
@ -38,6 +38,7 @@ def remove_doctags_content(doctags: str, images: list[PILImage.Image]) -> str:
|
||||
page_items[page_no].append(ser.serialize(item=item))
|
||||
else:
|
||||
page_items[page_no] = [ser.serialize(item=item)]
|
||||
pages = [ser.serialize_page(parts=parts) for parts in page_items.values()]
|
||||
sorted_items = [page_items[key] for key in sorted(page_items.keys())]
|
||||
pages = [ser.serialize_page(parts=parts) for parts in sorted_items]
|
||||
|
||||
return ser.serialize_doc(pages=pages).text
|
||||
|
Loading…
Reference in New Issue
Block a user