mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(docx): Adding plain latex equations to table cells (#1986)

Browse Source 
* Adding plain latex equations to table cells

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>

* Adding test files

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>

---------

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
This commit is contained in:
Rafael Teixeira de Lima 2025-07-24 11:02:24 +02:00 committed by GitHub
parent 98e2fcff63
commit 0b83609531
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 190 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
docling/backend/msword_backend.py
View File

@ -1104,8 +1104,17 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
)
_log.debug(f" spanned before row {spanned_idx}")
# Detect equations in cell text
text, equations = self._handle_equations_in_text(
element=cell._element, text=cell.text
)
if len(equations) == 0:
text = cell.text
else:
text = text.replace("<eq>", "$").replace("</eq>", "$")
table_cell = TableCell(
text=cell.text,
text=text,
row_span=spanned_idx - row_idx,
col_span=cell.grid_span,
start_row_offset_idx=row.grid_cols_before + row_idx,

BIN
tests/data/docx/table_with_equations.docx vendored Normal file
View File

Binary file not shown.

3
tests/data/groundtruth/docling_v2/table_with_equations.docx.itxt vendored Normal file
View File

@ -0,0 +1,3 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: table with [2x2]
item-2 at level 1: paragraph:

174
tests/data/groundtruth/docling_v2/table_with_equations.docx.json vendored Normal file
View File

@ -0,0 +1,174 @@
{
"schema_name": "DoclingDocument",
"version": "1.5.0",
"name": "table_with_equations",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"binary_hash": 6528760837820727976,
"filename": "table_with_equations.docx"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/tables/0"
},
{
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
"text": ""
}
],
"pictures": [],
"tables": [
{
"self_ref": "#/tables/0",
"parent": {
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
"references": [],
"footnotes": [],
"data": {
"table_cells": [
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 0,
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "The next cell has an equation",
"column_header": true,
"row_header": false,
"row_section": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 0,
"end_row_offset_idx": 1,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "$A= \\pi r^{2}$",
"column_header": true,
"row_header": false,
"row_section": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 1,
"end_row_offset_idx": 2,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "The next cell has another equation",
"column_header": false,
"row_header": false,
"row_section": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 1,
"end_row_offset_idx": 2,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "$x=\\frac{-b \\pm \\sqrt{b^{2}-4ac}}{2a}$",
"column_header": false,
"row_header": false,
"row_section": false
}
],
"num_rows": 2,
"num_cols": 2,
"grid": [
[
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 0,
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "The next cell has an equation",
"column_header": true,
"row_header": false,
"row_section": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 0,
"end_row_offset_idx": 1,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "$A= \\pi r^{2}$",
"column_header": true,
"row_header": false,
"row_section": false
}
],
[
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 1,
"end_row_offset_idx": 2,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "The next cell has another equation",
"column_header": false,
"row_header": false,
"row_section": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 1,
"end_row_offset_idx": 2,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "$x=\\frac{-b \\pm \\sqrt{b^{2}-4ac}}{2a}$",
"column_header": false,
"row_header": false,
"row_section": false
}
]
]
},
"annotations": []
}
],
"key_value_items": [],
"form_items": [],
"pages": {}
}

3
tests/data/groundtruth/docling_v2/table_with_equations.docx.md vendored Normal file
View File

@ -0,0 +1,3 @@
| The next cell has an equation | $A= \pi r^{2}$ |
|------------------------------------|----------------------------------------|
| The next cell has another equation | $x=\frac{-b \pm \sqrt{b^{2}-4ac}}{2a}$ |