Docling/tests/data/groundtruth/docling_v2/example_01.html.json
Panos Vagenas 0533da1923
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>
2025-06-27 16:37:15 +02:00

259 lines
5.4 KiB
JSON
Vendored

{
"schema_name": "DoclingDocument",
"version": "1.5.0",
"name": "example_01",
"origin": {
"mimetype": "text/html",
"binary_hash": 13726679883013609282,
"filename": "example_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/2"
},
"children": [
{
"$ref": "#/texts/4"
},
{
"$ref": "#/texts/5"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
{
"self_ref": "#/groups/1",
"parent": {
"$ref": "#/texts/2"
},
"children": [
{
"$ref": "#/texts/6"
},
{
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "list"
},
{
"self_ref": "#/groups/2",
"parent": {
"$ref": "#/texts/2"
},
"children": [
{
"$ref": "#/texts/8"
},
{
"$ref": "#/texts/9"
}
],
"content_layer": "body",
"name": "ordered list start 42",
"label": "list"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Introduction",
"text": "Introduction"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is the first paragraph of the introduction.",
"text": "This is the first paragraph of the introduction."
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/texts/3"
},
{
"$ref": "#/pictures/0"
},
{
"$ref": "#/groups/0"
},
{
"$ref": "#/groups/1"
},
{
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Background",
"text": "Background",
"level": 1
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Some background information here.",
"text": "Some background information here."
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in unordered list",
"text": "First item in unordered list",
"enumerated": false,
"marker": ""
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in unordered list",
"text": "Second item in unordered list",
"enumerated": false,
"marker": ""
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in ordered list",
"text": "First item in ordered list",
"enumerated": true,
"marker": ""
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in ordered list",
"text": "Second item in ordered list",
"enumerated": true,
"marker": ""
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in ordered list with start",
"text": "First item in ordered list with start",
"enumerated": true,
"marker": "42."
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in ordered list with start",
"text": "Second item in ordered list with start",
"enumerated": true,
"marker": "43."
}
],
"pictures": [
{
"self_ref": "#/pictures/0",
"parent": {
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
"references": [],
"footnotes": [],
"annotations": []
}
],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}