mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
97f444b11c
docling/tests/data/groundtruth/docling_v2/equations.docx.json
Rafael Teixeira de Lima 97f444b11c Update test files 
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
2025-01-29 16:06:33 +01:00

450 lines
12 KiB
JSON
Raw Blame History

{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"name": "equations",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"binary_hash": 11121138535595486899,
"filename": "equations.docx"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"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"
},
{
"$ref": "#/texts/6"
},
{
"$ref": "#/texts/7"
},
{
"$ref": "#/texts/8"
},
{
"$ref": "#/texts/9"
},
{
"$ref": "#/texts/10"
},
{
"$ref": "#/texts/11"
},
{
"$ref": "#/texts/12"
},
{
"$ref": "#/texts/13"
},
{
"$ref": "#/texts/14"
},
{
"$ref": "#/texts/15"
},
{
"$ref": "#/texts/16"
},
{
"$ref": "#/texts/17"
},
{
"$ref": "#/texts/18"
},
{
"$ref": "#/texts/19"
},
{
"$ref": "#/texts/20"
},
{
"$ref": "#/texts/21"
},
{
"$ref": "#/texts/22"
},
{
"$ref": "#/texts/23"
},
{
"$ref": "#/texts/24"
},
{
"$ref": "#/texts/25"
},
{
"$ref": "#/texts/26"
},
{
"$ref": "#/texts/27"
},
{
"$ref": "#/texts/28"
},
{
"$ref": "#/texts/29"
}
],
"name": "_root_",
"label": "unspecified"
},
"groups": [],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:",
"text": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "formula",
"prov": [],
"orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
"text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is another equation:",
"text": "This is another equation:"
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "formula",
"prov": [],
"orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
"text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/10",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/11",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:",
"text": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/12",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/13",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "formula",
"prov": [],
"orig": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}",
"text": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}"
},
{
"self_ref": "#/texts/14",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/15",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
},
{
"self_ref": "#/texts/16",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/17",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is another equation:",
"text": "This is another equation:"
},
{
"self_ref": "#/texts/18",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/19",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "formula",
"prov": [],
"orig": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis } ",
"text": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis } "
},
{
"self_ref": "#/texts/20",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/21",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
},
{
"self_ref": "#/texts/22",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/23",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/24",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:",
"text": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/25",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/26",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "formula",
"prov": [],
"orig": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty ",
"text": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty "
},
{
"self_ref": "#/texts/27",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/28",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
},
{
"self_ref": "#/texts/29",
"parent": {
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"pages": {}
}
Reference in New Issue View Git Blame Copy Permalink