mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix/poetry_check Signed-off-by: Benichou <fbenichou@deloitte.ca>

Browse Source
This commit is contained in:
Benichou 2025-06-20 16:24:48 -04:00
parent 4420c38936
commit ed56086a65
1 changed files with 5 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docling/backend/mspowerpoint_backend.py
View File

@ -2,8 +2,6 @@ import logging
from io import BytesIO from io import BytesIO
from pathlib import Path from pathlib import Path
from typing import Set, Union from typing import Set, Union
from lxml import etree
from lxml.etree import XPath
from docling_core.types.doc import ( from docling_core.types.doc import (
BoundingBox, BoundingBox,
@ -19,6 +17,8 @@ from docling_core.types.doc import (
TableData, TableData,
) )
from docling_core.types.doc.document import ContentLayer from docling_core.types.doc.document import ContentLayer
from lxml import etree
from lxml.etree import XPath
from PIL import Image, UnidentifiedImageError from PIL import Image, UnidentifiedImageError
from pptx import Presentation from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
@ -315,6 +315,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
doc.add_picture( doc.add_picture(
parent=parent_slide, parent=parent_slide,
image=ImageRef.from_pil(image=pil_image, dpi=int(im_dpi)), image=ImageRef.from_pil(image=pil_image, dpi=int(im_dpi)),
image=ImageRef.from_pil(image=pil_image, dpi=int(im_dpi)),
caption=None, caption=None,
prov=prov, prov=prov,
) )
@ -416,15 +417,9 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
if shape.shape_type == MSO_SHAPE_TYPE.PICTURE: if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
# Handle Pictures # Handle Pictures
drawing_blip = self.xpath_expr(shape.element) drawing_blip = self.xpath_expr(shape.element)
if drawing_blip: # ensure there is a drawing blip if drawing_blip:
self.handle_pictures( self.handle_pictures(
shape, shape, parent_slide, slide_ind, doc, drawing_blip, slide
parent_slide,
slide_ind,
doc,
slide_size,
drawing_blip,
slide,
) )
# If shape doesn't have any text, move on to the next shape # If shape doesn't have any text, move on to the next shape
if not hasattr(shape, "text"): if not hasattr(shape, "text"):