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

Upgrading docling core and adding groups

Browse Source
This commit is contained in:
Rafael Teixeira de Lima
2025-03-04 17:18:40 +01:00
parent 5630c6b8fd
commit 655e95dd72
19 changed files with 500 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
tests/data/groundtruth/docling_v2/equations.docx.itxt
View File

@@ -1,31 +1,40 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: paragraph: This is a word document and this ... nt an equation by line, I can do this:
item-2 at level 1: paragraph:
item-3 at level 1: formula: a^{2}+b^{2}=c^{2} \text{ \texttimes } 23
item-4 at level 1: paragraph: And that is an equation by itself. Cheers!
item-1 at level 1: inline: group group
item-2 at level 2: paragraph: This is a word document and this is an inline equation:
item-3 at level 2: formula: A= \pi r^{2}
item-4 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
item-5 at level 1: paragraph:
item-6 at level 1: paragraph: This is another equation:
item-7 at level 1: formula: f\left(x\right)=a_{0}+\sum_{n=1} ... })+b_{n}\sin(\frac{n \pi x}{L})\right)
item-6 at level 1: formula: a^{2}+b^{2}=c^{2} \text{ \texttimes } 23
item-7 at level 1: paragraph: And that is an equation by itself. Cheers!
item-8 at level 1: paragraph:
item-9 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
item-10 at level 1: paragraph:
item-9 at level 1: paragraph: This is another equation:
item-10 at level 1: formula: f\left(x\right)=a_{0}+\sum_{n=1} ... })+b_{n}\sin(\frac{n \pi x}{L})\right)
item-11 at level 1: paragraph:
item-12 at level 1: paragraph: This is a word document and this ... nt an equation by line, I can do this:
item-12 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
item-13 at level 1: paragraph:
item-14 at level 1: formula: \left(x+a\right)^{n}=\sum_{k=0}^ ... ac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}
item-15 at level 1: paragraph:
item-16 at level 1: paragraph: And that is an equation by itself. Cheers!
item-17 at level 1: paragraph:
item-18 at level 1: paragraph: This is another equation:
item-14 at level 1: paragraph:
item-15 at level 1: inline: group group
item-16 at level 2: paragraph: This is a word document and this is an inline equation:
item-17 at level 2: formula: A= \pi r^{2}
item-18 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
item-19 at level 1: paragraph:
item-20 at level 1: formula: \left(1+x\right)^{n}=1+\frac{nx} ... ht)x^{2}}{2!}+ \text{ \textellipsis }
item-20 at level 1: formula: \left(x+a\right)^{n}=\sum_{k=0}^ ... ac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}
item-21 at level 1: paragraph:
item-22 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
item-22 at level 1: paragraph: And that is an equation by itself. Cheers!
item-23 at level 1: paragraph:
item-24 at level 1: paragraph:
item-25 at level 1: paragraph: This is a word document and this ... nt an equation by line, I can do this:
item-26 at level 1: paragraph:
item-27 at level 1: formula: e^{x}=1+\frac{x}{1!}+\frac{x^{2} ... tellipsis } , - \infty < x < \infty
item-28 at level 1: paragraph:
item-29 at level 1: paragraph: And that is an equation by itself. Cheers!
item-30 at level 1: paragraph:
item-24 at level 1: paragraph: This is another equation:
item-25 at level 1: paragraph:
item-26 at level 1: formula: \left(1+x\right)^{n}=1+\frac{nx} ... ght)x^{2}}{2!}+ \text{ \textellipsis }
item-27 at level 1: paragraph:
item-28 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
item-29 at level 1: paragraph:
item-30 at level 1: paragraph:
item-31 at level 1: inline: group group
item-32 at level 2: paragraph: This is a word document and this is an inline equation:
item-33 at level 2: formula: A= \pi r^{2}
item-34 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
item-35 at level 1: paragraph:
item-36 at level 1: formula: e^{x}=1+\frac{x}{1!}+\frac{x^{2} ... xtellipsis } , - \infty < x < \infty
item-37 at level 1: paragraph:
item-38 at level 1: paragraph: And that is an equation by itself. Cheers!
item-39 at level 1: paragraph:

322
tests/data/groundtruth/docling_v2/equations.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.2.0",
"name": "equations",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@@ -17,13 +18,7 @@
"self_ref": "#/body",
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
"$ref": "#/groups/0"
},
{
"$ref": "#/texts/3"
@@ -56,13 +51,7 @@
"$ref": "#/texts/12"
},
{
"$ref": "#/texts/13"
},
{
"$ref": "#/texts/14"
},
{
"$ref": "#/texts/15"
"$ref": "#/groups/1"
},
{
"$ref": "#/texts/16"
@@ -101,49 +90,126 @@
"$ref": "#/texts/27"
},
{
"$ref": "#/texts/28"
"$ref": "#/groups/2"
},
{
"$ref": "#/texts/29"
"$ref": "#/texts/31"
},
{
"$ref": "#/texts/32"
},
{
"$ref": "#/texts/33"
},
{
"$ref": "#/texts/34"
},
{
"$ref": "#/texts/35"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [],
"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": {
"$ref": "#/body"
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"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} $. If instead, I want an equation by line, I can do this:"
"orig": "This is a word document and this is an inline equation: ",
"text": "This is a word document and this is an inline equation: "
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/body"
"$ref": "#/groups/0"
},
"children": [],
"label": "paragraph",
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "",
"text": ""
"orig": "A= \\pi r^{2} ",
"text": "A= \\pi r^{2} "
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/body"
"$ref": "#/groups/0"
},
"children": [],
"label": "formula",
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
"text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
"orig": ". If instead, I want an equation by line, I can do this:",
"text": ". If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/3",
@@ -151,10 +217,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/4",
@@ -162,10 +229,11 @@
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "",
"text": ""
"orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
"text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
},
{
"self_ref": "#/texts/5",
@@ -173,10 +241,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is another equation:",
"text": "This is another equation:"
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
},
{
"self_ref": "#/texts/6",
@@ -184,10 +253,11 @@
"$ref": "#/body"
},
"children": [],
"label": "formula",
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
"text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/7",
@@ -195,10 +265,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
"orig": "This is another equation:",
"text": "This is another equation:"
},
{
"self_ref": "#/texts/8",
@@ -206,10 +277,11 @@
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
"orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
"text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
},
{
"self_ref": "#/texts/9",
@@ -217,6 +289,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -228,10 +301,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
},
{
"self_ref": "#/texts/11",
@@ -239,10 +313,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"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} $. If instead, I want an equation by line, I can do this:"
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/12",
@@ -250,6 +325,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -258,35 +334,38 @@
{
"self_ref": "#/texts/13",
"parent": {
"$ref": "#/body"
"$ref": "#/groups/1"
},
"children": [],
"label": "formula",
"content_layer": "body",
"label": "paragraph",
"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}"
"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": {
"$ref": "#/body"
"$ref": "#/groups/1"
},
"children": [],
"label": "paragraph",
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "",
"text": ""
"orig": "A= \\pi r^{2} ",
"text": "A= \\pi r^{2} "
},
{
"self_ref": "#/texts/15",
"parent": {
"$ref": "#/body"
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
"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",
@@ -294,6 +373,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -305,10 +385,11 @@
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "This is another equation:",
"text": "This is another equation:"
"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",
@@ -316,6 +397,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -327,10 +409,11 @@
"$ref": "#/body"
},
"children": [],
"label": "formula",
"content_layer": "body",
"label": "paragraph",
"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 } "
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
},
{
"self_ref": "#/texts/20",
@@ -338,6 +421,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -349,10 +433,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"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."
"orig": "This is another equation:",
"text": "This is another equation:"
},
{
"self_ref": "#/texts/22",
@@ -360,6 +445,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -371,10 +457,11 @@
"$ref": "#/body"
},
"children": [],
"label": "paragraph",
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "",
"text": ""
"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",
@@ -382,10 +469,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"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} $. If instead, I want an equation by line, I can do this:"
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/25",
@@ -393,10 +481,11 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
"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/26",
@@ -404,10 +493,11 @@
"$ref": "#/body"
},
"children": [],
"label": "formula",
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty ",
"text": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty "
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/27",
@@ -415,6 +505,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -422,21 +513,95 @@
},
{
"self_ref": "#/texts/28",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is a word document and this is an inline equation: ",
"text": "This is a word document and this is an inline equation: "
},
{
"self_ref": "#/texts/29",
"parent": {
"$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": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": ". If instead, I want an equation by line, I can do this:",
"text": ". If instead, I want an equation by line, I can do this:"
},
{
"self_ref": "#/texts/31",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"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": "paragraph",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/34",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "And that is an equation by itself. Cheers!",
"text": "And that is an equation by itself. Cheers!"
},
{
"self_ref": "#/texts/29",
"self_ref": "#/texts/35",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@@ -446,5 +611,6 @@
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}

10
tests/data/groundtruth/docling_v2/equations.docx.md
View File

@@ -1,4 +1,4 @@
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:
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:
$$a^{2}+b^{2}=c^{2} \text{ \texttimes } 23$$
@@ -10,7 +10,7 @@ $$f\left(x\right)=a_{0}+\sum_{n=1}^{ \infty }\left(a_{n}\cos(\frac{n \pi x}{L})+
This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.
This is a word document and this is an inline equation: $A= \pi r^{2} $. If instead, I want an equation by line, I can do this:
This is a word document and this is an inline equation: $A= \pi r^{2} $ . If instead, I want an equation by line, I can do this:
$$\left(x+a\right)^{n}=\sum_{k=0}^{n}\left(\genfrac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}$$
@@ -18,12 +18,12 @@ And that is an equation by itself. Cheers!
This is another equation:
$$\left(1+x\right)^{n}=1+\frac{nx}{1!}+\frac{n\left(n-1\right)x^{2}}{2!}+ \text{ \textellipsis } $$
$$\left(1+x\right)^{n}=1+\frac{nx}{1!}+\frac{n\left(n-1\right)x^{2}}{2!}+ \text{ \textellipsis }$$
This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.
This is a word document and this is an inline equation: $A= \pi r^{2} $. If instead, I want an equation by line, I can do this:
This is a word document and this is an inline equation: $A= \pi r^{2} $ . If instead, I want an equation by line, I can do this:
$$e^{x}=1+\frac{x}{1!}+\frac{x^{2}}{2!}+\frac{x^{3}}{3!}+ \text{ \textellipsis } , - \infty < x < \infty $$
$$e^{x}=1+\frac{x}{1!}+\frac{x^{2}}{2!}+\frac{x^{3}}{3!}+ \text{ \textellipsis } , - \infty < x < \infty$$
And that is an equation by itself. Cheers!

3
tests/data/groundtruth/docling_v2/lorem_ipsum.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"version": "1.2.0",
"name": "lorem_ipsum",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -163,5 +163,6 @@
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}

3
tests/data/groundtruth/docling_v2/tablecell.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"version": "1.2.0",
"name": "tablecell",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -399,5 +399,6 @@
}
],
"key_value_items": [],
"form_items": [],
"pages": {}
}

5
tests/data/groundtruth/docling_v2/test_emf_docx.docx.json
View File

File diff suppressed because one or more lines are too long

3
tests/data/groundtruth/docling_v2/unit_test_headers.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"version": "1.2.0",
"name": "unit_test_headers",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -748,5 +748,6 @@
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}

3
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"version": "1.2.0",
"name": "unit_test_headers_numbered",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -802,5 +802,6 @@
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}

3
tests/data/groundtruth/docling_v2/unit_test_lists.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"version": "1.2.0",
"name": "unit_test_lists",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -979,5 +979,6 @@
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}

2
tests/data/groundtruth/docling_v2/word_sample.docx.itxt
View File

@@ -3,7 +3,7 @@ item-0 at level 0: unspecified: group _root_
item-2 at level 1: title: Swimming in the lake
item-3 at level 2: paragraph: Duck
item-4 at level 2: picture
item-5 at level 2: text: Figure 1: This is a cute duckling
item-5 at level 2: paragraph: Figure 1: This is a cute duckling
item-6 at level 2: section_header: Let’s swim!
item-7 at level 3: paragraph: To get started with swimming, fi ... down in a water and try not to drown:
item-8 at level 3: list: group list

5
tests/data/groundtruth/docling_v2/word_sample.docx.json
View File

File diff suppressed because one or more lines are too long

3
tests/data/groundtruth/docling_v2/word_tables.docx.json
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.1.0",
"version": "1.2.0",
"name": "word_tables",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -2372,5 +2372,6 @@
}
],
"key_value_items": [],
"form_items": [],
"pages": {}
}