mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-10 13:48:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Extracting picture data for raster images found in PPTX (#349)

Browse Source 
* Added picture data for pptx pictures

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

* Added tests for pptx

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

* Inferring image DPI from pptx file

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
2024-11-18 15:22:28 +01:00
committed by GitHub
parent 7dbdbdeaf3
commit 7a97d7119f
9 changed files with 2467 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docling/backend/mspowerpoint_backend.py
View File

@@ -10,11 +10,13 @@ from docling_core.types.doc import (
DoclingDocument,
DocumentOrigin,
GroupLabel,
ImageRef,
ProvenanceItem,
Size,
TableCell,
TableData,
)
from PIL import Image
from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
@@ -268,9 +270,22 @@ 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
pil_image = Image.open(BytesIO(image_bytes))
# shape has picture
prov = self.generate_prov(shape, slide_ind, "")
doc.add_picture(parent=parent_slide, caption=None, prov=prov)
doc.add_picture(
parent=parent_slide,
image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
caption=None,
prov=prov,
)
return
def handle_tables(self, shape, parent_slide, slide_ind, doc):