mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Fix for the crash when encountering WMF images in pptx and docx (#837)

Browse Source 
* Fix for the crash when encountering WMF images in pptx and docx backends on non Windows platforms

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Updated faq

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maxim Lysak
2025-01-30 14:58:27 +01:00
committed by GitHub
parent d01a2e73ee
commit fea0a99a95
3 changed files with 14 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docling/backend/mspowerpoint_backend.py
View File

@@ -271,13 +271,12 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
return
def handle_pictures(self, shape, parent_slide, slide_ind, doc):
# Get the image bytes
image = shape.image
image_bytes = image.blob
im_dpi, _ = image.dpi
# Open it with PIL
try:
# Get the image bytes
image = shape.image
image_bytes = image.blob
im_dpi, _ = image.dpi
pil_image = Image.open(BytesIO(image_bytes))
# shape has picture

4
docling/backend/msword_backend.py
View File

@@ -520,11 +520,11 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
image_data = image_part.blob # Get the binary image data
return image_data
image_data = get_docx_image(element, drawing_blip)
image_bytes = BytesIO(image_data)
level = self.get_level()
# Open the BytesIO object with PIL to create an Image
try:
image_data = get_docx_image(element, drawing_blip)
image_bytes = BytesIO(image_data)
pil_image = Image.open(image_bytes)
doc.add_picture(
parent=self.parents[level - 1],