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>
560 lines
12 KiB
JSON
Vendored
560 lines
12 KiB
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.7.0",
|
|
"name": "example_09",
|
|
"origin": {
|
|
"mimetype": "text/html",
|
|
"binary_hash": 6785336133244366107,
|
|
"filename": "example_09.html"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"content_layer": "furniture",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/6"
|
|
},
|
|
{
|
|
"$ref": "#/texts/8"
|
|
},
|
|
{
|
|
"$ref": "#/texts/10"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [
|
|
{
|
|
"self_ref": "#/groups/0",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/5"
|
|
},
|
|
{
|
|
"$ref": "#/pictures/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/7"
|
|
},
|
|
{
|
|
"$ref": "#/pictures/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/9"
|
|
},
|
|
{
|
|
"$ref": "#/pictures/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/1",
|
|
"parent": {
|
|
"$ref": "#/texts/11"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/13"
|
|
},
|
|
{
|
|
"$ref": "#/texts/16"
|
|
},
|
|
{
|
|
"$ref": "#/texts/19"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "ordered list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/2",
|
|
"parent": {
|
|
"$ref": "#/texts/13"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/14"
|
|
},
|
|
{
|
|
"$ref": "#/texts/15"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/3",
|
|
"parent": {
|
|
"$ref": "#/texts/16"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/17"
|
|
},
|
|
{
|
|
"$ref": "#/texts/18"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/4",
|
|
"parent": {
|
|
"$ref": "#/texts/19"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/20"
|
|
},
|
|
{
|
|
"$ref": "#/texts/21"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/pictures/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Introduction to parsing HTML files with Docling",
|
|
"text": "Introduction to parsing HTML files with Docling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "Docling",
|
|
"text": "Docling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Docling simplifies document processing, parsing diverse formats - including HTML - and providing seamless integrations with the gen AI ecosystem.",
|
|
"text": "Docling simplifies document processing, parsing diverse formats - including HTML - and providing seamless integrations with the gen AI ecosystem."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/4"
|
|
},
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/11"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Supported file formats",
|
|
"text": "Supported file formats",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Docling supports multiple file formats..",
|
|
"text": "Docling supports multiple file formats.."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Advanced PDF understanding",
|
|
"text": "Advanced PDF understanding",
|
|
"enumerated": false,
|
|
"marker": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "PDF",
|
|
"text": "PDF"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/7",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Microsoft Office DOCX",
|
|
"text": "Microsoft Office DOCX",
|
|
"enumerated": false,
|
|
"marker": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/8",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "DOCX",
|
|
"text": "DOCX"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/9",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "HTML files (with optional support for images)",
|
|
"text": "HTML files (with optional support for images)",
|
|
"enumerated": false,
|
|
"marker": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/10",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "HTML",
|
|
"text": "HTML"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/11",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/12"
|
|
},
|
|
{
|
|
"$ref": "#/groups/1"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Three backends for handling HTML files",
|
|
"text": "Three backends for handling HTML files",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/12",
|
|
"parent": {
|
|
"$ref": "#/texts/11"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Docling has three backends for parsing HTML files:",
|
|
"text": "Docling has three backends for parsing HTML files:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/13",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/2"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": "",
|
|
"enumerated": true,
|
|
"marker": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/14",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "HTMLDocumentBackend",
|
|
"text": "HTMLDocumentBackend",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false,
|
|
"script": "baseline"
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/15",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Ignores images",
|
|
"text": "Ignores images"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/16",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": "",
|
|
"enumerated": true,
|
|
"marker": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/17",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "HTMLDocumentBackendImagesInline",
|
|
"text": "HTMLDocumentBackendImagesInline",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false,
|
|
"script": "baseline"
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/18",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Extracts images inline",
|
|
"text": "Extracts images inline"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/19",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/4"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": "",
|
|
"enumerated": true,
|
|
"marker": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/20",
|
|
"parent": {
|
|
"$ref": "#/groups/4"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "HTMLDocumentBackendImagesReferenced",
|
|
"text": "HTMLDocumentBackendImagesReferenced",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false,
|
|
"script": "baseline"
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/21",
|
|
"parent": {
|
|
"$ref": "#/groups/4"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Extracts images as references",
|
|
"text": "Extracts images as references"
|
|
}
|
|
],
|
|
"pictures": [
|
|
{
|
|
"self_ref": "#/pictures/0",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "picture",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/1"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"annotations": []
|
|
},
|
|
{
|
|
"self_ref": "#/pictures/1",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "picture",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/6"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"annotations": []
|
|
},
|
|
{
|
|
"self_ref": "#/pictures/2",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "picture",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/8"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"annotations": []
|
|
},
|
|
{
|
|
"self_ref": "#/pictures/3",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "picture",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/10"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"annotations": []
|
|
}
|
|
],
|
|
"tables": [],
|
|
"key_value_items": [],
|
|
"form_items": [],
|
|
"pages": {}
|
|
} |