mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 05:08:14 +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

30
tests/data/groundtruth/docling_v2/example_07.html.json vendored
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.4.0",
"version": "1.5.0",
"name": "example_07",
"origin": {
"mimetype": "text/html",
@@ -169,7 +169,7 @@
"orig": "Asia",
"text": "Asia",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/1",
@@ -183,7 +183,7 @@
"orig": "China",
"text": "China",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/2",
@@ -197,7 +197,7 @@
"orig": "Japan",
"text": "Japan",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/3",
@@ -211,7 +211,7 @@
"orig": "Thailand",
"text": "Thailand",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/4",
@@ -229,7 +229,7 @@
"orig": "Europe",
"text": "Europe",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/5",
@@ -243,7 +243,7 @@
"orig": "UK",
"text": "UK",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/6",
@@ -257,7 +257,7 @@
"orig": "Germany",
"text": "Germany",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/7",
@@ -275,7 +275,7 @@
"orig": "Switzerland",
"text": "Switzerland",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/8",
@@ -289,7 +289,7 @@
"orig": "Bern",
"text": "Bern",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/9",
@@ -303,7 +303,7 @@
"orig": "Aargau",
"text": "Aargau",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/10",
@@ -321,7 +321,7 @@
"orig": "Italy",
"text": "Italy",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/11",
@@ -335,7 +335,7 @@
"orig": "Piedmont",
"text": "Piedmont",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/12",
@@ -349,7 +349,7 @@
"orig": "Liguria",
"text": "Liguria",
"enumerated": false,
"marker": "-"
"marker": ""
},
{
"self_ref": "#/texts/13",
@@ -363,7 +363,7 @@
"orig": "Africa",
"text": "Africa",
"enumerated": false,
"marker": "-"
"marker": ""
}
],
"pictures": [],