Files
docling/tests/data/groundtruth/docling_v2/hyperlink_04.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

49 lines
979 B
JSON
Vendored

{
"schema_name": "DoclingDocument",
"version": "1.8.0",
"name": "hyperlink_04",
"origin": {
"mimetype": "text/html",
"binary_hash": 14205970924528394626,
"filename": "hyperlink_04.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is some text.",
"text": "This is some text.",
"hyperlink": "/start.html"
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}