Docling/tests/data/groundtruth/docling_v2/unit_test_01.html.json
Panos Vagenas 7c5614a37a
fix(markdown): fix single-formatted headings & list items (#1820)
* fix(markdown): fix formatting & inline edge cases (show behavior before change)

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

* add change and updated test data

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

* update lock

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

* improve test case

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

---------

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
2025-06-25 13:05:06 +02:00

162 lines
3.1 KiB
JSON
Vendored

{
"schema_name": "DoclingDocument",
"version": "1.4.0",
"name": "unit_test_01",
"origin": {
"mimetype": "text/html",
"binary_hash": 11574357959810932112,
"filename": "unit_test_01.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/texts/3"
},
"children": [
{
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"name": "header-3",
"label": "section"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Title",
"text": "Title"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-1",
"text": "section-1",
"level": 1
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-1.1",
"text": "section-1.1",
"level": 2
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/groups/0"
},
{
"$ref": "#/texts/5"
},
{
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2",
"text": "section-2",
"level": 1
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.0.1",
"text": "section-2.0.1",
"level": 3
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.2",
"text": "section-2.2",
"level": 2
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.3",
"text": "section-2.3",
"level": 2
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}