docling/tests/data/groundtruth/docling_v2/example_07.html.json
Alexander Vaagan 733360c7b2 A new HTML backend that handles styled html (ignors it) as well as images.
- Updated unit tests
- Added documentation (Example notebook)

Note: MyPy fails.
Seems to be a known issue with BeautifulSoup:
https://github.com/python/typeshed/pull/13604

Signed-off-by: Alexander Vaagan <alexander.vaagan@gmail.com>
Signed-off-by: vaaale <2428222+vaaale@users.noreply.github.com>
2025-05-24 22:29:22 +02:00

404 lines
8.0 KiB
JSON
Vendored

{
"schema_name": "DoclingDocument",
"version": "1.3.0",
"name": "example_07",
"origin": {
"mimetype": "text/html",
"binary_hash": 623628706615267627,
"filename": "example_07.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/groups/1"
},
{
"$ref": "#/texts/4"
},
{
"$ref": "#/groups/2"
},
{
"$ref": "#/texts/15"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/1",
"parent": {
"$ref": "#/groups/0"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
},
{
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/2",
"parent": {
"$ref": "#/groups/0"
},
"children": [
{
"$ref": "#/texts/5"
},
{
"$ref": "#/texts/6"
},
{
"$ref": "#/texts/7"
},
{
"$ref": "#/groups/3"
},
{
"$ref": "#/texts/11"
},
{
"$ref": "#/groups/5"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/3",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/8"
},
{
"$ref": "#/groups/4"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/4",
"parent": {
"$ref": "#/groups/3"
},
"children": [
{
"$ref": "#/texts/9"
},
{
"$ref": "#/texts/10"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/5",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/12"
},
{
"$ref": "#/groups/6"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/6",
"parent": {
"$ref": "#/groups/5"
},
"children": [
{
"$ref": "#/texts/13"
},
{
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Asia China Japan Thailand",
"text": "Asia China Japan Thailand",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "China",
"text": "China",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Japan",
"text": "Japan",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Thailand",
"text": "Thailand",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Europe UK Germany Switzerland Bern Aargau Italy Piedmont Liguria",
"text": "Europe UK Germany Switzerland Bern Aargau Italy Piedmont Liguria",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "UK",
"text": "UK",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Germany",
"text": "Germany",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Switzerland Bern Aargau",
"text": "Switzerland Bern Aargau",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Bern Aargau",
"text": "Bern Aargau",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Bern",
"text": "Bern",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/10",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Aargau",
"text": "Aargau",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/11",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Italy Piedmont Liguria",
"text": "Italy Piedmont Liguria",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/12",
"parent": {
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Piedmont Liguria",
"text": "Piedmont Liguria",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/13",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Piedmont",
"text": "Piedmont",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/14",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Liguria",
"text": "Liguria",
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/15",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Africa",
"text": "Africa",
"enumerated": false,
"marker": "-"
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}