mirror of
https://github.com/docling-project/docling-core.git
synced 2026-05-17 13:10:44 +00:00
Cesar Berrospi Ramis
8c55233d74
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
1482 lines
32 KiB
Plaintext
1482 lines
32 KiB
Plaintext
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.3.0",
|
|
"name": "Untitled 1",
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"content_layer": "furniture",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/groups/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/14"
|
|
},
|
|
{
|
|
"$ref": "#/tables/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/15"
|
|
},
|
|
{
|
|
"$ref": "#/pictures/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/16"
|
|
},
|
|
{
|
|
"$ref": "#/pictures/1"
|
|
},
|
|
{
|
|
"$ref": "#/groups/5"
|
|
},
|
|
{
|
|
"$ref": "#/groups/6"
|
|
},
|
|
{
|
|
"$ref": "#/groups/7"
|
|
},
|
|
{
|
|
"$ref": "#/groups/8"
|
|
},
|
|
{
|
|
"$ref": "#/texts/29"
|
|
},
|
|
{
|
|
"$ref": "#/texts/30"
|
|
},
|
|
{
|
|
"$ref": "#/texts/31"
|
|
},
|
|
{
|
|
"$ref": "#/texts/32"
|
|
},
|
|
{
|
|
"$ref": "#/key_value_items/0"
|
|
},
|
|
{
|
|
"$ref": "#/form_items/0"
|
|
},
|
|
{
|
|
"$ref": "#/groups/12"
|
|
},
|
|
{
|
|
"$ref": "#/groups/13"
|
|
},
|
|
{
|
|
"$ref": "#/texts/50"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [
|
|
{
|
|
"self_ref": "#/groups/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/4"
|
|
},
|
|
{
|
|
"$ref": "#/texts/5"
|
|
},
|
|
{
|
|
"$ref": "#/groups/2"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "Introduction",
|
|
"label": "chapter"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/2",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/6"
|
|
},
|
|
{
|
|
"$ref": "#/texts/7"
|
|
},
|
|
{
|
|
"$ref": "#/texts/8"
|
|
},
|
|
{
|
|
"$ref": "#/texts/13"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/3",
|
|
"parent": {
|
|
"$ref": "#/texts/8"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/9"
|
|
},
|
|
{
|
|
"$ref": "#/texts/10"
|
|
},
|
|
{
|
|
"$ref": "#/texts/11"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "ordered_list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/4",
|
|
"parent": {
|
|
"$ref": "#/texts/11"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/12"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "ordered_list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/5",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/17"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/6",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/7",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/18"
|
|
},
|
|
{
|
|
"$ref": "#/texts/19"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/8",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/20"
|
|
},
|
|
{
|
|
"$ref": "#/texts/21"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/9",
|
|
"parent": {
|
|
"$ref": "#/texts/21"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/22"
|
|
},
|
|
{
|
|
"$ref": "#/groups/10"
|
|
},
|
|
{
|
|
"$ref": "#/groups/11"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/10",
|
|
"parent": {
|
|
"$ref": "#/groups/9"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/23"
|
|
},
|
|
{
|
|
"$ref": "#/texts/24"
|
|
},
|
|
{
|
|
"$ref": "#/texts/25"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/11",
|
|
"parent": {
|
|
"$ref": "#/groups/9"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/26"
|
|
},
|
|
{
|
|
"$ref": "#/texts/27"
|
|
},
|
|
{
|
|
"$ref": "#/texts/28"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/12",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/33"
|
|
},
|
|
{
|
|
"$ref": "#/texts/34"
|
|
},
|
|
{
|
|
"$ref": "#/texts/35"
|
|
},
|
|
{
|
|
"$ref": "#/texts/36"
|
|
},
|
|
{
|
|
"$ref": "#/texts/37"
|
|
},
|
|
{
|
|
"$ref": "#/texts/38"
|
|
},
|
|
{
|
|
"$ref": "#/texts/39"
|
|
},
|
|
{
|
|
"$ref": "#/texts/40"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/13",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/41"
|
|
},
|
|
{
|
|
"$ref": "#/texts/42"
|
|
},
|
|
{
|
|
"$ref": "#/texts/43"
|
|
},
|
|
{
|
|
"$ref": "#/texts/49"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list A",
|
|
"label": "ordered_list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/14",
|
|
"parent": {
|
|
"$ref": "#/texts/43"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/44"
|
|
},
|
|
{
|
|
"$ref": "#/texts/45"
|
|
},
|
|
{
|
|
"$ref": "#/texts/48"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list B",
|
|
"label": "ordered_list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/15",
|
|
"parent": {
|
|
"$ref": "#/texts/45"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/46"
|
|
},
|
|
{
|
|
"$ref": "#/texts/47"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list C",
|
|
"label": "ordered_list"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item of leading list",
|
|
"text": "item of leading list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Title of the Document",
|
|
"text": "Title of the Document"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Author 1\nAffiliation 1",
|
|
"text": "Author 1\nAffiliation 1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Author 2\nAffiliation 2",
|
|
"text": "Author 2\nAffiliation 2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "1. Introduction",
|
|
"text": "1. Introduction",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This paper introduces the biggest invention ever made. ...",
|
|
"text": "This paper introduces the biggest invention ever made. ..."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 1",
|
|
"text": "list item 1",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/7",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 2",
|
|
"text": "list item 2",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/8",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 3",
|
|
"text": "list item 3",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/9",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 3.a",
|
|
"text": "list item 3.a",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/10",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 3.b",
|
|
"text": "list item 3.b",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/11",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/4"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 3.c",
|
|
"text": "list item 3.c",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/12",
|
|
"parent": {
|
|
"$ref": "#/groups/4"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 3.c.i",
|
|
"text": "list item 3.c.i",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/13",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "list item 4",
|
|
"text": "list item 4",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/14",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "This is the caption of table 1.",
|
|
"text": "This is the caption of table 1."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/15",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "This is the caption of figure 1.",
|
|
"text": "This is the caption of figure 1."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/16",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "caption",
|
|
"prov": [],
|
|
"orig": "This is the caption of figure 2.",
|
|
"text": "This is the caption of figure 2."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/17",
|
|
"parent": {
|
|
"$ref": "#/groups/5"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item 1 of list",
|
|
"text": "item 1 of list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/18",
|
|
"parent": {
|
|
"$ref": "#/groups/7"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item 1 of list after empty list",
|
|
"text": "item 1 of list after empty list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/19",
|
|
"parent": {
|
|
"$ref": "#/groups/7"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item 2 of list after empty list",
|
|
"text": "item 2 of list after empty list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/20",
|
|
"parent": {
|
|
"$ref": "#/groups/8"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item 1 of neighboring list",
|
|
"text": "item 1 of neighboring list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/21",
|
|
"parent": {
|
|
"$ref": "#/groups/8"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/9"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item 2 of neighboring list",
|
|
"text": "item 2 of neighboring list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/22",
|
|
"parent": {
|
|
"$ref": "#/groups/9"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "item 1 of sub list",
|
|
"text": "item 1 of sub list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/23",
|
|
"parent": {
|
|
"$ref": "#/groups/10"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Here a code snippet:",
|
|
"text": "Here a code snippet:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/24",
|
|
"parent": {
|
|
"$ref": "#/groups/10"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "code",
|
|
"prov": [],
|
|
"orig": "<p>Hello world</p>",
|
|
"text": "<p>Hello world</p>",
|
|
"captions": [],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"code_language": "unknown"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/25",
|
|
"parent": {
|
|
"$ref": "#/groups/10"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "(to be displayed inline)",
|
|
"text": "(to be displayed inline)"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/26",
|
|
"parent": {
|
|
"$ref": "#/groups/11"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Here a formula:",
|
|
"text": "Here a formula:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/27",
|
|
"parent": {
|
|
"$ref": "#/groups/11"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "formula",
|
|
"prov": [],
|
|
"orig": "E=mc^2",
|
|
"text": "E=mc^2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/28",
|
|
"parent": {
|
|
"$ref": "#/groups/11"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "(to be displayed inline)",
|
|
"text": "(to be displayed inline)"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/29",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Here a code block:",
|
|
"text": "Here a code block:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/30",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "code",
|
|
"prov": [],
|
|
"orig": "print(\"Hello world\")",
|
|
"text": "print(\"Hello world\")",
|
|
"captions": [],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"code_language": "unknown"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/31",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Here a formula block:",
|
|
"text": "Here a formula block:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/32",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "formula",
|
|
"prov": [],
|
|
"orig": "E=mc^2",
|
|
"text": "E=mc^2"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/33",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Some formatting chops:",
|
|
"text": "Some formatting chops:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/34",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "bold",
|
|
"text": "bold",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/35",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "italic",
|
|
"text": "italic",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/36",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "underline",
|
|
"text": "underline",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": true,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/37",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "strikethrough",
|
|
"text": "strikethrough",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": true
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/38",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "hyperlink",
|
|
"text": "hyperlink",
|
|
"hyperlink": "."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/39",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "&",
|
|
"text": "&"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/40",
|
|
"parent": {
|
|
"$ref": "#/groups/12"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "everything at the same time.",
|
|
"text": "everything at the same time.",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": true,
|
|
"underline": true,
|
|
"strikethrough": true
|
|
},
|
|
"hyperlink": "https://github.com/DS4SD/docling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/41",
|
|
"parent": {
|
|
"$ref": "#/groups/13"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 1 in A",
|
|
"text": "Item 1 in A",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/42",
|
|
"parent": {
|
|
"$ref": "#/groups/13"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 2 in A",
|
|
"text": "Item 2 in A",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/43",
|
|
"parent": {
|
|
"$ref": "#/groups/13"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/14"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 3 in A",
|
|
"text": "Item 3 in A",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/44",
|
|
"parent": {
|
|
"$ref": "#/groups/14"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 1 in B",
|
|
"text": "Item 1 in B",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/45",
|
|
"parent": {
|
|
"$ref": "#/groups/14"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/15"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 2 in B",
|
|
"text": "Item 2 in B",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/46",
|
|
"parent": {
|
|
"$ref": "#/groups/15"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 1 in C",
|
|
"text": "Item 1 in C",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/47",
|
|
"parent": {
|
|
"$ref": "#/groups/15"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 2 in C",
|
|
"text": "Item 2 in C",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/48",
|
|
"parent": {
|
|
"$ref": "#/groups/14"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 3 in B",
|
|
"text": "Item 3 in B",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/49",
|
|
"parent": {
|
|
"$ref": "#/groups/13"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Item 4 in A",
|
|
"text": "Item 4 in A",
|
|
"enumerated": true,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/50",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "The end.",
|
|
"text": "The end."
|
|
}
|
|
],
|
|
"pictures": [
|
|
{
|
|
"self_ref": "#/pictures/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "picture",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/15"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"annotations": []
|
|
},
|
|
{
|
|
"self_ref": "#/pictures/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "picture",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/16"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"image": {
|
|
"mimetype": "image/png",
|
|
"dpi": 72,
|
|
"size": {
|
|
"width": 64.0,
|
|
"height": 64.0
|
|
},
|
|
"uri": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAAIklEQVR4nO3BAQ0AAADCoPdPbQ8HFAAAAAAAAAAAAAAA8G4wQAABiwCo9wAAAABJRU5ErkJggg=="
|
|
},
|
|
"annotations": []
|
|
}
|
|
],
|
|
"tables": [
|
|
{
|
|
"self_ref": "#/tables/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "table",
|
|
"prov": [],
|
|
"captions": [
|
|
{
|
|
"$ref": "#/texts/14"
|
|
}
|
|
],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"data": {
|
|
"table_cells": [
|
|
{
|
|
"row_span": 2,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Product",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Years",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "2016",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "2017",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Apple",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "49823",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "695944",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
"num_rows": 3,
|
|
"num_cols": 3,
|
|
"grid": [
|
|
[
|
|
{
|
|
"row_span": 2,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Product",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Years",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Years",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 2,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Product",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "2016",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "2017",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Apple",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "49823",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "695944",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
]
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"key_value_items": [
|
|
{
|
|
"self_ref": "#/key_value_items/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "key_value_region",
|
|
"prov": [],
|
|
"captions": [],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"graph": {
|
|
"cells": [
|
|
{
|
|
"label": "key",
|
|
"cell_id": 0,
|
|
"text": "number",
|
|
"orig": "#"
|
|
},
|
|
{
|
|
"label": "value",
|
|
"cell_id": 1,
|
|
"text": "1",
|
|
"orig": "1"
|
|
}
|
|
],
|
|
"links": [
|
|
{
|
|
"label": "to_value",
|
|
"source_cell_id": 0,
|
|
"target_cell_id": 1
|
|
},
|
|
{
|
|
"label": "to_key",
|
|
"source_cell_id": 1,
|
|
"target_cell_id": 0
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"form_items": [
|
|
{
|
|
"self_ref": "#/form_items/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "form",
|
|
"prov": [],
|
|
"captions": [],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"graph": {
|
|
"cells": [
|
|
{
|
|
"label": "key",
|
|
"cell_id": 0,
|
|
"text": "number",
|
|
"orig": "#"
|
|
},
|
|
{
|
|
"label": "value",
|
|
"cell_id": 1,
|
|
"text": "1",
|
|
"orig": "1"
|
|
}
|
|
],
|
|
"links": [
|
|
{
|
|
"label": "to_value",
|
|
"source_cell_id": 0,
|
|
"target_cell_id": 1
|
|
},
|
|
{
|
|
"label": "to_key",
|
|
"source_cell_id": 1,
|
|
"target_cell_id": 0
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"annotations": [],
|
|
"pages": {}
|
|
} |