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

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.4.0",
"version": "1.5.0",
"name": "example_02",
"origin": {
"mimetype": "text/html",
@@ -58,7 +58,7 @@
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
"label": "list"
}
],
"texts": [
@@ -140,7 +140,7 @@
"orig": "First item in unordered list",
"text": "First item in unordered list",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/5",
@@ -154,7 +154,7 @@
"orig": "Second item in unordered list",
"text": "Second item in unordered list",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/6",
@@ -168,7 +168,7 @@
"orig": "First item in ordered list",
"text": "First item in ordered list",
"enumerated": true,
"marker": "1."
"marker": ""
},
{
"self_ref": "#/texts/7",
@@ -182,7 +182,7 @@
"orig": "Second item in ordered list",
"text": "Second item in ordered list",
"enumerated": true,
"marker": "2."
"marker": ""
}
],
"pictures": [],