mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
fix: Proper heading support in rich tables for HTML backend (#2394)
* Fix for the proper headers support in rich tables in HTML Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * cleaning up Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Compatibility with older Python versions Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixing Furniture before the first heading rule Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Added minimalistic test case Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * added html for the test 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>
This commit is contained in:
Maxim Lysak
GitHub
4
tests/data/groundtruth/docling_v2/table_with_heading.html.itxt
vendored
Normal file
4
tests/data/groundtruth/docling_v2/table_with_heading.html.itxt
vendored
Normal file
@@ -0,0 +1,4 @@
|
||||
item-0 at level 0: unspecified: group _root_
|
||||
item-1 at level 1: text: Before tha table
|
||||
item-2 at level 1: table with [2x2]
|
||||
item-3 at level 1: text: After the table
|
||||
197
tests/data/groundtruth/docling_v2/table_with_heading.html.json
vendored
Normal file
197
tests/data/groundtruth/docling_v2/table_with_heading.html.json
vendored
Normal file
@@ -0,0 +1,197 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.7.0",
|
||||
"name": "table_with_heading",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
"binary_hash": 5578561753677933781,
|
||||
"filename": "table_with_heading.html"
|
||||
},
|
||||
"furniture": {
|
||||
"self_ref": "#/furniture",
|
||||
"children": [],
|
||||
"content_layer": "furniture",
|
||||
"name": "_root_",
|
||||
"label": "unspecified"
|
||||
},
|
||||
"body": {
|
||||
"self_ref": "#/body",
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/tables/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/1"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "_root_",
|
||||
"label": "unspecified"
|
||||
},
|
||||
"groups": [],
|
||||
"texts": [
|
||||
{
|
||||
"self_ref": "#/texts/0",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Before tha table",
|
||||
"text": "Before tha table"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/1",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "After the table",
|
||||
"text": "After the table"
|
||||
}
|
||||
],
|
||||
"pictures": [],
|
||||
"tables": [
|
||||
{
|
||||
"self_ref": "#/tables/0",
|
||||
"parent": {
|
||||
"$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": "A",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "B",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "1...",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "2...",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "A",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "B",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "1...",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": 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": "2...",
|
||||
"column_header": false,
|
||||
"row_header": false,
|
||||
"row_section": false,
|
||||
"fillable": false
|
||||
}
|
||||
]
|
||||
]
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
"form_items": [],
|
||||
"pages": {}
|
||||
}
|
||||
7
tests/data/groundtruth/docling_v2/table_with_heading.html.md
vendored
Normal file
7
tests/data/groundtruth/docling_v2/table_with_heading.html.md
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
Before tha table
|
||||
|
||||
| A | B |
|
||||
|------|------|
|
||||
| 1... | 2... |
|
||||
|
||||
After the table
|
||||
23
tests/data/html/table_with_heading.html
vendored
Normal file
23
tests/data/html/table_with_heading.html
vendored
Normal file
@@ -0,0 +1,23 @@
|
||||
<html>
|
||||
<head>
|
||||
<style>
|
||||
table, th, td {border: 1px solid black; border-collapse: collapse;}
|
||||
td {padding:30px;}
|
||||
table {margin: 30px;}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<p>Before tha table</p>
|
||||
<table>
|
||||
<tr>
|
||||
<td><h1>A</h1></td>
|
||||
<td>B</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>1...</td>
|
||||
<td>2...</td>
|
||||
</tr>
|
||||
</table>
|
||||
After the table
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user