mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-02 15:32:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-01-30 11:14:39 +01:00
parent d7c082894e
commit c93897b3df
2 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docling/backend/mspowerpoint_backend.py
View File

@ -271,13 +271,12 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
return return
def handle_pictures(self, shape, parent_slide, slide_ind, doc): def handle_pictures(self, shape, parent_slide, slide_ind, doc):
# Open it with PIL
try:
# Get the image bytes # Get the image bytes
image = shape.image image = shape.image
image_bytes = image.blob image_bytes = image.blob
im_dpi, _ = image.dpi im_dpi, _ = image.dpi
# Open it with PIL
try:
pil_image = Image.open(BytesIO(image_bytes)) pil_image = Image.open(BytesIO(image_bytes))
# shape has picture # 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 image_data = image_part.blob # Get the binary image data
return image_data return image_data
image_data = get_docx_image(element, drawing_blip)
image_bytes = BytesIO(image_data)
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: try:
image_data = get_docx_image(element, drawing_blip)
image_bytes = BytesIO(image_data)
pil_image = Image.open(image_bytes) pil_image = Image.open(image_bytes)
doc.add_picture( doc.add_picture(
parent=self.parents[level - 1], parent=self.parents[level - 1],