mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
a30e6a76148079cc48fb179e4b9ca36371026b6f
docling/tests/data/groundtruth/docling_v2/equations.docx.json
Maxim Lysak e2482a2ada feat: Rich tables for MSWord backend (#2291) 
* Adding support of rich table cells to MSWord backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fixes for properly accounting lists, pictures and headers in rich table cells

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned up msword backend, re-generated docx tests

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added detection of simple table cells in word backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Cleaned up

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>
2025-09-22 16:41:59 +02:00

665 lines
16 KiB
JSON
Vendored
Raw Blame History

{
"schema_name": "DoclingDocument",
"version": "1.7.0",
"name": "equations",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"binary_hash": 11121138535595486899,
"filename": "equations.docx"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/groups/0"
},
{
"$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": "#/groups/1"
},
{
"$ref": "#/texts/16"
},
{
"$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"
},
{
"$ref": "#/groups/2"
},
{
"$ref": "#/texts/31"
},
{
"$ref": "#/texts/32"
},
{
"$ref": "#/texts/33"
},
{
"$ref": "#/texts/34"
},
{
"$ref": "#/texts/35"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"name": "group",
"label": "inline"
},
{
"self_ref": "#/groups/1",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/13"
},
{
"$ref": "#/texts/14"
},
{
"$ref": "#/texts/15"
}
],
"content_layer": "body",
"name": "group",
"label": "inline"
},
{
"self_ref": "#/groups/2",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/28"
},
{
"$ref": "#/texts/29"
},
{
"$ref": "#/texts/30"
}
],
"content_layer": "body",
"name": "group",
"label": "inline"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is a word document and this is an inline equation: ",
"text": "This is a word document and this is an inline equation: "
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "A= \\pi r^{2}",
"text": "A= \\pi r^{2}"
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": ". If instead, I want an equation by line, I can do this:",
"text": ". If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
"text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is another equation:",
"text": "This is another equation:",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
"text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/10",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/11",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/12",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/13",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is a word document and this is an inline equation: ",
"text": "This is a word document and this is an inline equation: "
},
{
"self_ref": "#/texts/14",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "A= \\pi r^{2}",
"text": "A= \\pi r^{2}"
},
{
"self_ref": "#/texts/15",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": ". If instead, I want an equation by line, I can do this:",
"text": ". If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/16",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/17",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"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/18",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/19",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/20",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/21",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is another equation:",
"text": "This is another equation:",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/22",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/23",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"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/24",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/25",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"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.",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/26",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/27",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/28",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is a word document and this is an inline equation: ",
"text": "This is a word document and this is an inline equation: "
},
{
"self_ref": "#/texts/29",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "A= \\pi r^{2}",
"text": "A= \\pi r^{2}"
},
{
"self_ref": "#/texts/30",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": ". If instead, I want an equation by line, I can do this:",
"text": ". If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/31",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/32",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty",
"text": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty"
},
{
"self_ref": "#/texts/33",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/34",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/35",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}
Reference in New Issue View Git Blame Copy Permalink