mirror of
https://github.com/DS4SD/docling.git
synced 2025-08-01 15:02:21 +00:00
fix: add proper table provenance
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
parent
b88440a7c9
commit
483d1bfab0
@ -443,7 +443,17 @@ class VlmPipeline(PaginatedPipeline):
|
|||||||
|
|
||||||
if tag_name == DocumentToken.OTSL.value:
|
if tag_name == DocumentToken.OTSL.value:
|
||||||
table_data = parse_table_content(full_chunk)
|
table_data = parse_table_content(full_chunk)
|
||||||
doc.add_table(data=table_data)
|
bbox = extract_bounding_box(full_chunk)
|
||||||
|
|
||||||
|
if bbox:
|
||||||
|
prov = ProvenanceItem(
|
||||||
|
bbox=bbox.resize_by_scale(pg_width, pg_height),
|
||||||
|
charspan=(0, 0),
|
||||||
|
page_no=page_no,
|
||||||
|
)
|
||||||
|
doc.add_table(data=table_data, prov=prov)
|
||||||
|
else:
|
||||||
|
doc.add_table(data=table_data)
|
||||||
|
|
||||||
elif tag_name == DocItemLabel.PICTURE:
|
elif tag_name == DocItemLabel.PICTURE:
|
||||||
text_caption_content = extract_inner_text(full_chunk)
|
text_caption_content = extract_inner_text(full_chunk)
|
||||||
|
Loading…
Reference in New Issue
Block a user