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

Fixing images in the input Word files

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-11-13 17:16:49 +01:00
parent bf2a85f1d4
commit c8aed776e2
1 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
docling/backend/msword_backend.py
View File

@ -1,3 +1,4 @@
import base64
import logging import logging
from io import BytesIO from io import BytesIO
from pathlib import Path from pathlib import Path
@ -130,13 +131,8 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
def walk_linear(self, body, docx_obj, doc) -> DoclingDocument: def walk_linear(self, body, docx_obj, doc) -> DoclingDocument:
for element in body: for element in body:
tag_name = etree.QName(element).localname tag_name = etree.QName(element).localname
# Check for Inline Images (drawings or blip elements) # Check for Inline Images (blip elements)
found_drawing = etree.ElementBase.xpath( drawing_blip = element.xpath(".//a:blip")
element, ".//w:drawing", namespaces=self.xml_namespaces
)
found_pict = etree.ElementBase.xpath(
element, ".//w:pict", namespaces=self.xml_namespaces
)
# Check for Tables # Check for Tables
if element.tag.endswith("tbl"): if element.tag.endswith("tbl"):
@ -145,8 +141,8 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
except Exception: except Exception:
_log.debug("could not parse a table, broken docx table") _log.debug("could not parse a table, broken docx table")
elif found_drawing or found_pict: elif drawing_blip:
self.handle_pictures(element, docx_obj, doc) self.handle_pictures(element, docx_obj, drawing_blip, doc)
# Check for Text # Check for Text
elif tag_name in ["p"]: elif tag_name in ["p"]:
self.handle_text_elements(element, docx_obj, doc) self.handle_text_elements(element, docx_obj, doc)
@ -491,6 +487,18 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
doc.add_table(data=data, parent=self.parents[level - 1]) doc.add_table(data=data, parent=self.parents[level - 1])
return return
def handle_pictures(self, element, docx_obj, doc): def handle_pictures(self, element, docx_obj, drawing_blip, doc):
"""
# WIP:
def get_base64_image(element, drawing_blip):
rId = drawing_blip[0].get('{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
image_data = image_part.blob # Get the binary image data
# Encode the image data in base64
return base64.b64encode(image_data).decode('utf-8')
"""
# base64_image = get_base64_image(element, drawing_blip)
# print(base64_image)
doc.add_picture(parent=self.parents[self.level], caption=None) doc.add_picture(parent=self.parents[self.level], caption=None)
return return