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

fix(docx): parse integrals as n-ary objects without chr element (#2712)

Browse Source 
Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-12-03 11:25:52 +01:00
committed by GitHub
parent f80c903c24
commit c97715f5fd
6 changed files with 248 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

206
tests/data/groundtruth/docling_v2/equations.docx.json vendored
View File

@@ -1,10 +1,10 @@
{
"schema_name": "DoclingDocument",
"version": "1.7.0",
"version": "1.8.0",
"name": "equations",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"binary_hash": 11121138535595486899,
"binary_hash": 8638432756089077257,
"filename": "equations.docx"
},
"furniture": {
@@ -106,6 +106,45 @@
},
{
"$ref": "#/texts/35"
},
{
"$ref": "#/texts/36"
},
{
"$ref": "#/texts/37"
},
{
"$ref": "#/texts/38"
},
{
"$ref": "#/texts/39"
},
{
"$ref": "#/texts/40"
},
{
"$ref": "#/texts/41"
},
{
"$ref": "#/texts/42"
},
{
"$ref": "#/texts/43"
},
{
"$ref": "#/texts/44"
},
{
"$ref": "#/texts/45"
},
{
"$ref": "#/texts/46"
},
{
"$ref": "#/texts/47"
},
{
"$ref": "#/texts/48"
}
],
"content_layer": "body",
@@ -655,6 +694,169 @@
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/36",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Large operators and integrals are represented with n-ary objects in OMML XML:",
"text": "Large operators and integrals are represented with n-ary objects in OMML XML:",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/37",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
},
{
"self_ref": "#/texts/38",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\sum_{0}^{2}x",
"text": "\\sum_{0}^{2}x"
},
{
"self_ref": "#/texts/39",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\bigcup_{n=1}^{m}\\left(X_{n} \\cap Y_{n}\\right)",
"text": "\\bigcup_{n=1}^{m}\\left(X_{n} \\cap Y_{n}\\right)"
},
{
"self_ref": "#/texts/40",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\prod_{k=1}^{n}A_{k}",
"text": "\\prod_{k=1}^{n}A_{k}"
},
{
"self_ref": "#/texts/41",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\bigwedge_{}^{}x",
"text": "\\bigwedge_{}^{}x"
},
{
"self_ref": "#/texts/42",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\int_{}^{}(2x+1)dx",
"text": "\\int_{}^{}(2x+1)dx"
},
{
"self_ref": "#/texts/43",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\iint_{0}^{1}xdx",
"text": "\\iint_{0}^{1}xdx"
},
{
"self_ref": "#/texts/44",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\iiint_{}^{}ydy",
"text": "\\iiint_{}^{}ydy"
},
{
"self_ref": "#/texts/45",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\oint_{}^{}\\frac{dy}{dx}",
"text": "\\oint_{}^{}\\frac{dy}{dx}"
},
{
"self_ref": "#/texts/46",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\oiint_{0}^{2 \\pi }idt",
"text": "\\oiint_{0}^{2 \\pi }idt"
},
{
"self_ref": "#/texts/47",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "formula",
"prov": [],
"orig": "\\oiiint_{C}^{}\\frac{1}{z}dz",
"text": "\\oiiint_{C}^{}\\frac{1}{z}dz"
},
{
"self_ref": "#/texts/48",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "",
"text": ""
}
],
"pictures": [],