docling/tests/data/groundtruth/docling_v2/example_02.html.json

{
  "schema_name": "DoclingDocument",
  "version": "1.7.0",
  "name": "example_02",
  "origin": {
    "mimetype": "text/html",
    "binary_hash": 17361433184833793580,
    "filename": "example_02.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/2"
      },
      "children": [
        {
          "$ref": "#/texts/4"
        },
        {
          "$ref": "#/texts/5"
        }
      ],
      "content_layer": "body",
      "name": "list",
      "label": "list"
    },
    {
      "self_ref": "#/groups/1",
      "parent": {
        "$ref": "#/texts/2"
      },
      "children": [
        {
          "$ref": "#/texts/6"
        },
        {
          "$ref": "#/texts/7"
        }
      ],
      "content_layer": "body",
      "name": "ordered list",
      "label": "list"
    }
  ],
  "texts": [
    {
      "self_ref": "#/texts/0",
      "parent": {
        "$ref": "#/body"
      },
      "children": [
        {
          "$ref": "#/texts/1"
        },
        {
          "$ref": "#/texts/2"
        }
      ],
      "content_layer": "body",
      "label": "title",
      "prov": [],
      "orig": "Introduction",
      "text": "Introduction"
    },
    {
      "self_ref": "#/texts/1",
      "parent": {
        "$ref": "#/texts/0"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "This is the first paragraph of the introduction.",
      "text": "This is the first paragraph of the introduction."
    },
    {
      "self_ref": "#/texts/2",
      "parent": {
        "$ref": "#/texts/0"
      },
      "children": [
        {
          "$ref": "#/texts/3"
        },
        {
          "$ref": "#/groups/0"
        },
        {
          "$ref": "#/groups/1"
        }
      ],
      "content_layer": "body",
      "label": "section_header",
      "prov": [],
      "orig": "Background",
      "text": "Background",
      "level": 1
    },
    {
      "self_ref": "#/texts/3",
      "parent": {
        "$ref": "#/texts/2"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "Some background information here.",
      "text": "Some background information here."
    },
    {
      "self_ref": "#/texts/4",
      "parent": {
        "$ref": "#/groups/0"
      },
      "children": [],
      "content_layer": "body",
      "label": "list_item",
      "prov": [],
      "orig": "First item in unordered list",
      "text": "First item in unordered list",
      "enumerated": false,
      "marker": ""
    },
    {
      "self_ref": "#/texts/5",
      "parent": {
        "$ref": "#/groups/0"
      },
      "children": [],
      "content_layer": "body",
      "label": "list_item",
      "prov": [],
      "orig": "Second item in unordered list",
      "text": "Second item in unordered list",
      "enumerated": false,
      "marker": ""
    },
    {
      "self_ref": "#/texts/6",
      "parent": {
        "$ref": "#/groups/1"
      },
      "children": [],
      "content_layer": "body",
      "label": "list_item",
      "prov": [],
      "orig": "First item in ordered list",
      "text": "First item in ordered list",
      "enumerated": true,
      "marker": ""
    },
    {
      "self_ref": "#/texts/7",
      "parent": {
        "$ref": "#/groups/1"
      },
      "children": [],
      "content_layer": "body",
      "label": "list_item",
      "prov": [],
      "orig": "Second item in ordered list",
      "text": "Second item in ordered list",
      "enumerated": true,
      "marker": ""
    }
  ],
  "pictures": [],
  "tables": [],
  "key_value_items": [],
  "form_items": [],
  "pages": {}
}