mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: find paragraphs in elements with images in docx

Browse Source 
Signed-off-by: Manuel030 <manuelenrique.plank@gmail.com>
This commit is contained in:
Manuel030 2025-04-28 13:46:08 +02:00
parent d8959c6b19
commit 387dd659c1
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docling/backend/msword_backend.py
View File

@ -123,6 +123,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
doc = DoclingDocument(name=self.file.stem or "file", origin=origin) doc = DoclingDocument(name=self.file.stem or "file", origin=origin)
if self.is_valid(): if self.is_valid():
assert self.docx_obj is not None assert self.docx_obj is not None
doc = self._walk_linear(self.docx_obj.element.body, self.docx_obj, doc) doc = self._walk_linear(self.docx_obj.element.body, self.docx_obj, doc)
return doc return doc
else: else:
@ -188,6 +189,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
elif drawing_blip: elif drawing_blip:
self._handle_pictures(docx_obj, drawing_blip, doc) self._handle_pictures(docx_obj, drawing_blip, doc)
self._handle_text_elements(element, docx_obj, doc)
# Check for the sdt containers, like table of contents # Check for the sdt containers, like table of contents
elif tag_name in ["sdt"]: elif tag_name in ["sdt"]:
sdt_content = element.find(".//w:sdtContent", namespaces=namespaces) sdt_content = element.find(".//w:sdtContent", namespaces=namespaces)