Files
docling/tests/data/groundtruth/docling_v2/hyperlink_02.html.json
Matvei Smirnov aebe25cf00 fix(html): prevent hierarchy reset in rich table cells (#2716)
* fix(html): restore parents after rich cell walking

Signed-off-by: Matvei Smirnov <vdalekesmirnov@gmail.com>

* fix(html): add table cell context manager, update tests

Signed-off-by: Matvei Smirnov <vdalekesmirnov@gmail.com>

* fix(html): table with heading test data

Signed-off-by: Matvei Smirnov <vdalekesmirnov@gmail.com>

---------

Signed-off-by: Matvei Smirnov <vdalekesmirnov@gmail.com>
2025-12-03 18:52:23 +01:00

102 lines
1.9 KiB
JSON
Vendored

{
"schema_name": "DoclingDocument",
"version": "1.8.0",
"name": "hyperlink_02",
"origin": {
"mimetype": "text/html",
"binary_hash": 15683290523889238210,
"filename": "hyperlink_02.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/pictures/0"
},
{
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/1"
}
],
"content_layer": "body",
"name": "header-1",
"label": "section"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "furniture",
"label": "caption",
"prov": [],
"orig": "Image alt text",
"text": "Image alt text"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Home",
"text": "Home",
"hyperlink": "/home.html",
"level": 1
}
],
"pictures": [
{
"self_ref": "#/pictures/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "furniture",
"label": "picture",
"prov": [],
"captions": [
{
"$ref": "#/texts/0"
}
],
"references": [],
"footnotes": [],
"annotations": []
}
],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}