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

feat: Rich tables support for HTML backend (#2324)

Browse Source 
* Rich tables support for HTML backend

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

* Decoupling JATS backend from HTML backend, ways of creating tables changed significantly

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

* updated and added tests

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

* Refactored parse_table_data in html_backend into few smaller functions

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

* Changing scope of few functions in html_backend.py, making them static, when possible

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

* Fix for HTML tables that have tbody and/or thead, now these tables are also properly supported

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
2025-09-29 18:12:16 +02:00
committed by GitHub
parent 325877aee9
commit c803abed9a
46 changed files with 9233 additions and 5815 deletions
Download Patch File Download Diff File Expand all files Collapse all files

417
tests/data/groundtruth/docling_v2/table_05.html.json vendored Normal file
View File

@@ -0,0 +1,417 @@
{
"schema_name": "DoclingDocument",
"version": "1.7.0",
"name": "table_05",
"origin": {
"mimetype": "text/html",
"binary_hash": 12827430000043968589,
"filename": "table_05.html"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/tables/0"
},
"children": [
{
"$ref": "#/tables/1"
}
],
"content_layer": "body",
"name": "rich_cell_group_2_0_1",
"label": "unspecified"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/tables/0"
},
{
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Header",
"text": "Header"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is the first paragraph.",
"text": "This is the first paragraph."
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "After table",
"text": "After table"
}
],
"pictures": [],
"tables": [
{
"self_ref": "#/tables/0",
"parent": {
"$ref": "#/texts/0"
},
"children": [
{
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
"references": [],
"footnotes": [],
"data": {
"table_cells": [
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 0,
"end_row_offset_idx": 1,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "A",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 0,
"end_row_offset_idx": 1,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "B",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 1,
"end_row_offset_idx": 2,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "A1B1C1\n\n\nD1E1F1",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false,
"ref": {
"$ref": "#/groups/0"
}
},
{
"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": "A1B1C1\n\n\nD1E1F1",
"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": []
},
{
"self_ref": "#/tables/1",
"parent": {
"$ref": "#/groups/0"
},
"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": "A1",
"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": "B1",
"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": 2,
"end_col_offset_idx": 3,
"text": "C1",
"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": "D1",
"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": "E1",
"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": 2,
"end_col_offset_idx": 3,
"text": "F1",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
"num_rows": 2,
"num_cols": 3,
"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": "A1",
"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": "B1",
"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": 2,
"end_col_offset_idx": 3,
"text": "C1",
"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": "D1",
"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": "E1",
"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": 2,
"end_col_offset_idx": 3,
"text": "F1",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
]
]
},
"annotations": []
}
],
"key_value_items": [],
"form_items": [],
"pages": {}
}