Skip to content

feat(doctags): add enclosing bbox to inline #302

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 53 additions & 6 deletions docling_core/transforms/serializer/doctags.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,12 +17,14 @@
BaseTableSerializer,
BaseTextSerializer,
SerializationResult,
Span,
)
from docling_core.transforms.serializer.common import (
CommonParams,
DocSerializer,
create_ser_result,
)
from docling_core.types.doc.base import BoundingBox
from docling_core.types.doc.document import (
CodeItem,
DocItem,
Expand All @@ -38,6 +40,7 @@
PictureItem,
PictureMoleculeData,
PictureTabularChartData,
ProvenanceItem,
TableItem,
TextItem,
UnorderedList,
Expand Down Expand Up @@ -414,6 +417,39 @@ def serialize(
class DocTagsInlineSerializer(BaseInlineSerializer):
"""DocTags-specific inline group serializer."""

def _get_inline_location_tags(
self, doc: DoclingDocument, item: InlineGroup, params: DocTagsParams
) -> SerializationResult:

prov: Optional[ProvenanceItem] = None
boxes: list[BoundingBox] = []
doc_items: list[DocItem] = []
for it, _ in doc.iterate_items(root=item):
if isinstance(it, DocItem):
for prov in it.prov:
boxes.append(prov.bbox)
doc_items.append(it)
if prov is None:
return create_ser_result()

bbox = BoundingBox.enclosing_bbox(boxes=boxes)

# using last seen prov as reference for page dims
page_w, page_h = doc.pages[prov.page_no].size.as_tuple()

loc_str = DocumentToken.get_location(
bbox=bbox.to_top_left_origin(page_h).as_tuple(),
page_w=page_w,
page_h=page_h,
xsize=params.xsize,
ysize=params.ysize,
)

return SerializationResult(
text=loc_str,
spans=[Span(item=it) for it in doc_items],
)

@override
def serialize(
self,
Expand All @@ -428,12 +464,23 @@ def serialize(
"""Serializes the passed item."""
my_visited = visited if visited is not None else set()
params = DocTagsParams(**kwargs)
parts = doc_serializer.get_parts(
item=item,
list_level=list_level,
is_inline_scope=True,
visited=my_visited,
**kwargs,
parts: List[SerializationResult] = []
if params.add_location:
inline_loc_tags_ser_res = self._get_inline_location_tags(
doc=doc,
item=item,
params=params,
)
parts.append(inline_loc_tags_ser_res)
params.add_location = False # suppress children location serialization
parts.extend(
doc_serializer.get_parts(
item=item,
list_level=list_level,
is_inline_scope=True,
visited=my_visited,
**{**kwargs, **params.model_dump()},
)
)
wrap_tag = DocumentToken.INLINE.value
delim = _get_delim(params=params)
Expand Down
Loading