mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 22:44:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Inferring image DPI from pptx file

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-11-18 14:06:43 +01:00
parent 22400089c0
commit b132c68a32
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/backend/mspowerpoint_backend.py
View File

@ -273,6 +273,8 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
# 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
# Open it with PIL # Open it with PIL
pil_image = Image.open(BytesIO(image_bytes)) pil_image = Image.open(BytesIO(image_bytes))
@ -280,7 +282,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
prov = self.generate_prov(shape, slide_ind, "") prov = self.generate_prov(shape, slide_ind, "")
doc.add_picture( doc.add_picture(
parent=parent_slide, parent=parent_slide,
image=ImageRef.from_pil(image=pil_image, dpi=72), image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
caption=None, caption=None,
prov=prov, prov=prov,
) )

2
tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json
View File

@ -127,7 +127,7 @@
"footnotes": [], "footnotes": [],
"image": { "image": {
"mimetype": "image/png", "mimetype": "image/png",
"dpi": 72, "dpi": 300,
"size": { "size": {
"width": 268.0, "width": 268.0,
"height": 268.0 "height": 268.0