mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 12:48:28 +00:00
c803abed9a
* Rich tables support for HTML backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Decoupling JATS backend from HTML backend, ways of creating tables changed significantly Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * updated and added tests Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Refactored parse_table_data in html_backend into few smaller functions Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Changing scope of few functions in html_backend.py, making them static, when possible Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fix for HTML tables that have tbody and/or thead, now these tables are also properly supported Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> --------- Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
110 lines
2.1 KiB
JSON
Vendored
110 lines
2.1 KiB
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.7.0",
|
|
"name": "hyperlink_01",
|
|
"origin": {
|
|
"mimetype": "text/html",
|
|
"binary_hash": 17149231461445569313,
|
|
"filename": "hyperlink_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/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/0"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Something",
|
|
"text": "Something"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Please follow the link to:",
|
|
"text": "Please follow the link to:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This page",
|
|
"text": "This page",
|
|
"hyperlink": "#"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": ".",
|
|
"text": "."
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [],
|
|
"key_value_items": [],
|
|
"form_items": [],
|
|
"pages": {}
|
|
} |