feat: leverage new list modeling, capture default markers (#1856)

* chore: update docling-core & regenerate test data

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* update backends to leverage new list modeling

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* repin docling-core

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* ensure availability of latest docling-core API

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

---------

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-06-27 16:37:15 +02:00
committed by GitHub
parent e79e4f0ab6
commit 0533da1923
90 changed files with 2252 additions and 2240 deletions

View File

@@ -121,7 +121,9 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
return prov
def handle_text_elements(self, shape, parent_slide, slide_ind, doc, slide_size):
def handle_text_elements(
self, shape, parent_slide, slide_ind, doc: DoclingDocument, slide_size
):
is_list_group_created = False
enum_list_item_value = 0
new_list = None
@@ -165,10 +167,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
enumerated = bullet_type == "Numbered"
if not is_list_group_created:
new_list = doc.add_group(
label=GroupLabel.ORDERED_LIST
if enumerated
else GroupLabel.LIST,
new_list = doc.add_list_group(
name="list",
parent=parent_slide,
)