mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-29 13:34:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Handle header and footer

Browse Source 
Signed-off-by: SimJeg <sjegou@nvidia.com>
This commit is contained in:
SimJeg 2025-04-01 11:36:47 +02:00
parent 1033c25435
commit 61bd559f78
2 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

@ -116,7 +116,9 @@ 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.sections[0].header._element, self.docx_obj, doc)
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)
doc = self.walk_linear(self.docx_obj.sections[-1].footer._element, self.docx_obj, doc)
return doc return doc
else: else:
raise RuntimeError( raise RuntimeError(

BIN
tests/data/docx/unit_test_formatting.docx
View File

Binary file not shown.