mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 23:12:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

fixes for referencing drawing blip in wordx

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-11-25 16:42:48 +01:00
parent d7072b4b56
commit 508bbed8f8
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
docling/backend/msword_backend.py
View File

@ -14,6 +14,7 @@ from docling_core.types.doc import (
TableData, TableData,
) )
from lxml import etree from lxml import etree
from lxml.etree import XPath
from PIL import Image from PIL import Image
from docling.backend.abstract_backend import DeclarativeDocumentBackend from docling.backend.abstract_backend import DeclarativeDocumentBackend
@ -132,8 +133,14 @@ 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 (blip elements) # Check for Inline Images (blip elements)
drawing_blip = element.xpath(".//a:blip") namespaces = {
"a": "http://schemas.openxmlformats.org/drawingml/2006/main",
"r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
}
xpath_expr = XPath(".//a:blip", namespaces=namespaces)
drawing_blip = xpath_expr(element)
# Check for Tables # Check for Tables
if element.tag.endswith("tbl"): if element.tag.endswith("tbl"):