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

Populating extracted image data into docling picture for wordx backend

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-11-14 10:42:09 +01:00
parent c8aed776e2
commit c8888fe4c4
1 changed files with 22 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
docling/backend/msword_backend.py
View File

@ -10,10 +10,12 @@ from docling_core.types.doc import (
DoclingDocument, DoclingDocument,
DocumentOrigin, DocumentOrigin,
GroupLabel, GroupLabel,
ImageRef,
TableCell, TableCell,
TableData, TableData,
) )
from lxml import etree from lxml import etree
from PIL import Image
from docling.backend.abstract_backend import DeclarativeDocumentBackend from docling.backend.abstract_backend import DeclarativeDocumentBackend
from docling.datamodel.base_models import InputFormat from docling.datamodel.base_models import InputFormat
@ -488,17 +490,24 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
return return
def handle_pictures(self, element, docx_obj, drawing_blip, doc): def handle_pictures(self, element, docx_obj, drawing_blip, doc):
""" def get_docx_image(element, drawing_blip):
# WIP: base64_image_data = None
def get_base64_image(element, drawing_blip): rId = drawing_blip[0].get(
rId = drawing_blip[0].get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed') "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed"
# Access the image part using the relationship ID )
image_part = element.paragraph.runs[0].part.rels[rId].target_part if rId in docx_obj.part.rels:
image_data = image_part.blob # Get the binary image data # Access the image part using the relationship ID
# Encode the image data in base64 image_part = docx_obj.part.rels[rId].target_part
return base64.b64encode(image_data).decode('utf-8') image_data = image_part.blob # Get the binary image data
""" return image_data
# base64_image = get_base64_image(element, drawing_blip)
# print(base64_image) image_data = get_docx_image(element, drawing_blip)
doc.add_picture(parent=self.parents[self.level], caption=None) image_bytes = BytesIO(image_data)
# Open the BytesIO object with PIL to create an Image
pil_image = Image.open(image_bytes)
doc.add_picture(
parent=self.parents[self.level],
image=ImageRef.from_pil(image=pil_image, dpi=72),
caption=None,
)
return return