fix: prov for merged-elems

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2025-06-07 07:31:54 +02:00
parent 9dbcb3d7d4
commit 6a02ec0f02
2 changed files with 5 additions and 4 deletions

View File

@ -334,12 +334,12 @@ class ReadingOrderModel:
"Labels of merged elements must match."
)
prov = ProvenanceItem(
page_no=element.page_no + 1,
page_no=merged_elem.page_no + 1,
charspan=(
len(new_item.text) + 1,
len(new_item.text) + 1 + len(merged_elem.text),
),
bbox=element.cluster.bbox.to_bottom_left_origin(page_height),
bbox=merged_elem.cluster.bbox.to_bottom_left_origin(page_height),
)
new_item.text += f" {merged_elem.text}"
new_item.orig += f" {merged_elem.text}" # TODO: This is incomplete, we don't have the `orig` field of the merged element.

View File

@ -143,7 +143,8 @@ constraints = [
[tool.uv]
package = true
default-groups = "all"
# default-groups = ["all"]
default-groups = ["dev", "docs", "examples"]
[tool.setuptools.packages.find]
include = ["docling*"]