mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/data/groundtruth/docling_v2/example_03.html.json vendored
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.4.0",
"version": "1.5.0",
"name": "example_03",
"origin": {
"mimetype": "text/html",
@@ -75,7 +75,7 @@
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
"label": "list"
},
{
"self_ref": "#/groups/3",
@@ -92,7 +92,7 @@
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
"label": "list"
}
],
"texts": [
@@ -198,7 +198,7 @@
"orig": "First item in unordered list",
"text": "First item in unordered list",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/6",
@@ -212,7 +212,7 @@
"orig": "Nested item 1",
"text": "Nested item 1",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/7",
@@ -226,7 +226,7 @@
"orig": "Nested item 2",
"text": "Nested item 2",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/8",
@@ -240,7 +240,7 @@
"orig": "Second item in unordered list",
"text": "Second item in unordered list",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/9",
@@ -258,7 +258,7 @@
"orig": "First item in ordered list",
"text": "First item in ordered list",
"enumerated": true,
"marker": "1"
"marker": ""
},
{
"self_ref": "#/texts/10",
@@ -272,7 +272,7 @@
"orig": "Nested ordered item 1",
"text": "Nested ordered item 1",
"enumerated": true,
"marker": "1."
"marker": ""
},
{
"self_ref": "#/texts/11",
@@ -286,7 +286,7 @@
"orig": "Nested ordered item 2",
"text": "Nested ordered item 2",
"enumerated": true,
"marker": "2."
"marker": ""
},
{
"self_ref": "#/texts/12",
@@ -300,7 +300,7 @@
"orig": "Second item in ordered list",
"text": "Second item in ordered list",
"enumerated": true,
"marker": "2."
"marker": ""
},
{
"self_ref": "#/texts/13",