mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +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>
162 lines
3.1 KiB
JSON
Vendored
162 lines
3.1 KiB
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.7.0",
|
|
"name": "unit_test_01",
|
|
"origin": {
|
|
"mimetype": "text/html",
|
|
"binary_hash": 11574357959810932112,
|
|
"filename": "unit_test_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/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/4"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "header-3",
|
|
"label": "section"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Title",
|
|
"text": "Title"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/2"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "section-1",
|
|
"text": "section-1",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "section-1.1",
|
|
"text": "section-1.1",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/5"
|
|
},
|
|
{
|
|
"$ref": "#/texts/6"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "section-2",
|
|
"text": "section-2",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "section-2.0.1",
|
|
"text": "section-2.0.1",
|
|
"level": 3
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "section-2.2",
|
|
"text": "section-2.2",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "section-2.3",
|
|
"text": "section-2.3",
|
|
"level": 2
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [],
|
|
"key_value_items": [],
|
|
"form_items": [],
|
|
"pages": {}
|
|
} |