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": "powerpoint_sample",
"origin": {
"mimetype": "application/vnd.ms-powerpoint",
@@ -137,7 +137,7 @@
],
"content_layer": "body",
"name": "list",
"label": "ordered_list"
"label": "list"
},
{
"self_ref": "#/groups/4",
@@ -197,7 +197,7 @@
],
"content_layer": "body",
"name": "list",
"label": "ordered_list"
"label": "list"
},
{
"self_ref": "#/groups/7",
@@ -578,7 +578,7 @@
"orig": "I1",
"text": "I1",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/13",
@@ -607,7 +607,7 @@
"orig": "I2",
"text": "I2",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/14",
@@ -636,7 +636,7 @@
"orig": "I3",
"text": "I3",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/15",
@@ -665,7 +665,7 @@
"orig": "I4",
"text": "I4",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/16",
@@ -721,7 +721,7 @@
"orig": "Item A",
"text": "Item A",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/18",
@@ -750,7 +750,7 @@
"orig": "Item B",
"text": "Item B",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/19",
@@ -893,7 +893,7 @@
"orig": "l1 ",
"text": "l1 ",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/24",
@@ -922,7 +922,7 @@
"orig": "l2",
"text": "l2",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/25",
@@ -951,7 +951,7 @@
"orig": "l3",
"text": "l3",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/26",