NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(docx): declare image_data variable when handling pictures (#1359)

Browse Source 
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis 2025-04-11 13:04:00 +02:00 committed by GitHub
parent 250399948d
commit 415b877984
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
docling/backend/msword_backend.py
View File

@ -850,7 +850,8 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
def _handle_pictures( def _handle_pictures(
self, docx_obj: DocxDocument, drawing_blip: Any, doc: DoclingDocument self, docx_obj: DocxDocument, drawing_blip: Any, doc: DoclingDocument
) -> None: ) -> None:
def get_docx_image(drawing_blip): def get_docx_image(drawing_blip: Any) -> Optional[bytes]:
image_data: Optional[bytes] = None
rId = drawing_blip[0].get( rId = drawing_blip[0].get(
"{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed" "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed"
) )
@ -862,19 +863,26 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
level = self._get_level() level = self._get_level()
# Open the BytesIO object with PIL to create an Image # Open the BytesIO object with PIL to create an Image
try: image_data: Optional[bytes] = get_docx_image(drawing_blip)
image_data = get_docx_image(drawing_blip) if image_data is None:
image_bytes = BytesIO(image_data) _log.warning("Warning: image cannot be found")
pil_image = Image.open(image_bytes)
doc.add_picture(
parent=self.parents[level - 1],
image=ImageRef.from_pil(image=pil_image, dpi=72),
caption=None,
)
except (UnidentifiedImageError, OSError) as e:
_log.warning("Warning: image cannot be loaded by Pillow")
doc.add_picture( doc.add_picture(
parent=self.parents[level - 1], parent=self.parents[level - 1],
caption=None, caption=None,
) )
else:
try:
image_bytes = BytesIO(image_data)
pil_image = Image.open(image_bytes)
doc.add_picture(
parent=self.parents[level - 1],
image=ImageRef.from_pil(image=pil_image, dpi=72),
caption=None,
)
except (UnidentifiedImageError, OSError) as e:
_log.warning("Warning: image cannot be loaded by Pillow")
doc.add_picture(
parent=self.parents[level - 1],
caption=None,
)
return return