mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

able to parse the captions and image uri's

Browse Source 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2024-10-22 09:13:08 +02:00
parent 1c0a766cc5
commit b04f14ec24
1 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docling/backend/asciidoc_backend.py
View File

@ -4,7 +4,12 @@ from io import BytesIO
from pathlib import Path
from typing import Set, Union
from pydantic import (
AnyUrl,
)
from docling_core.types.doc import (
Size,
DocItemLabel,
DoclingDocument,
DocumentOrigin,
@ -190,7 +195,19 @@ class AsciidocBackend(DeclarativeDocumentBackend):
item = self.parse_picture(line)
print(item)
image = ImageRef(mimetype="image/png", size=[100,100], dpi=70, uri=item["uri"])
size = None
if "width" in item and "height" in item:
size = Size(width=int(item["width"]), height=int(item["height"]))
uri = None
if "uri" in item and not item["uri"].startswith("http") and item["uri"].startswith("//"):
uri = "file:"+item["uri"]
elif "uri" in item and not item["uri"].startswith("http") and item["uri"].startswith("/"):
uri = "file:/"+item["uri"]
elif "uri" in item and not item["uri"].startswith("http"):
uri = "file://"+item["uri"]
image = ImageRef(mimetype="image/png", size=size, dpi=70, uri=uri)
doc.add_picture(image=image, caption=caption)
# Caption