mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-09 13:18:24 +00:00
9687297262
* re-implement links for html backend. Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch> * fix inline groups in list items. write specific test for find_parent_annotation of _extract_text_and_hyperlink_recursively. Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch> * implement hack for images. Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch> --------- Signed-off-by: Roman Kayan BAZG <roman.kayan@bazg.admin.ch>
49 lines
979 B
JSON
Vendored
49 lines
979 B
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.5.0",
|
|
"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": {}
|
|
} |