docling/tests/data/groundtruth/docling_v2/example_06.html.json

{
  "schema_name": "DoclingDocument",
  "version": "1.7.0",
  "name": "example_06",
  "origin": {
    "mimetype": "text/html",
    "binary_hash": 10224930410364781672,
    "filename": "example_06.html"
  },
  "furniture": {
    "self_ref": "#/furniture",
    "children": [],
    "content_layer": "furniture",
    "name": "_root_",
    "label": "unspecified"
  },
  "body": {
    "self_ref": "#/body",
    "children": [
      {
        "$ref": "#/texts/0"
      },
      {
        "$ref": "#/texts/1"
      },
      {
        "$ref": "#/texts/2"
      },
      {
        "$ref": "#/texts/3"
      },
      {
        "$ref": "#/texts/4"
      },
      {
        "$ref": "#/texts/5"
      },
      {
        "$ref": "#/groups/0"
      },
      {
        "$ref": "#/groups/1"
      }
    ],
    "content_layer": "body",
    "name": "_root_",
    "label": "unspecified"
  },
  "groups": [
    {
      "self_ref": "#/groups/0",
      "parent": {
        "$ref": "#/body"
      },
      "children": [
        {
          "$ref": "#/texts/6"
        },
        {
          "$ref": "#/texts/7"
        }
      ],
      "content_layer": "body",
      "name": "details",
      "label": "section"
    },
    {
      "self_ref": "#/groups/1",
      "parent": {
        "$ref": "#/body"
      },
      "children": [
        {
          "$ref": "#/texts/8"
        },
        {
          "$ref": "#/texts/9"
        },
        {
          "$ref": "#/texts/10"
        }
      ],
      "content_layer": "body",
      "name": "group",
      "label": "inline"
    }
  ],
  "texts": [
    {
      "self_ref": "#/texts/0",
      "parent": {
        "$ref": "#/body"
      },
      "children": [],
      "content_layer": "furniture",
      "label": "title",
      "prov": [],
      "orig": "Sample HTML File",
      "text": "Sample HTML File"
    },
    {
      "self_ref": "#/texts/1",
      "parent": {
        "$ref": "#/body"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "This is a div with text.",
      "text": "This is a div with text."
    },
    {
      "self_ref": "#/texts/2",
      "parent": {
        "$ref": "#/body"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "This is another div with text.",
      "text": "This is another div with text."
    },
    {
      "self_ref": "#/texts/3",
      "parent": {
        "$ref": "#/body"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "This is a regular paragraph.",
      "text": "This is a regular paragraph."
    },
    {
      "self_ref": "#/texts/4",
      "parent": {
        "$ref": "#/body"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "This is a third div",
      "text": "This is a third div"
    },
    {
      "self_ref": "#/texts/5",
      "parent": {
        "$ref": "#/body"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "with a new line.",
      "text": "with a new line."
    },
    {
      "self_ref": "#/texts/6",
      "parent": {
        "$ref": "#/groups/0"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "Heading for the details element",
      "text": "Heading for the details element"
    },
    {
      "self_ref": "#/texts/7",
      "parent": {
        "$ref": "#/groups/0"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "Description of the details element.",
      "text": "Description of the details element."
    },
    {
      "self_ref": "#/texts/8",
      "parent": {
        "$ref": "#/groups/1"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "This is a fourth div with a",
      "text": "This is a fourth div with a"
    },
    {
      "self_ref": "#/texts/9",
      "parent": {
        "$ref": "#/groups/1"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "bold",
      "text": "bold",
      "formatting": {
        "bold": true,
        "italic": false,
        "underline": false,
        "strikethrough": false,
        "script": "baseline"
      }
    },
    {
      "self_ref": "#/texts/10",
      "parent": {
        "$ref": "#/groups/1"
      },
      "children": [],
      "content_layer": "body",
      "label": "text",
      "prov": [],
      "orig": "paragraph.",
      "text": "paragraph."
    }
  ],
  "pictures": [],
  "tables": [],
  "key_value_items": [],
  "form_items": [],
  "pages": {}
}