mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 03:55:00 +00:00
f542460af3
* add real e2e tests for html and docx Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the output of itxt Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the text Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests (2) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the examples (1) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the output of the test Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the tests, moved the ground-truth Signed-off-by: Peter Staar <taa@zurich.ibm.com> * moved the ground-truth data Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the html tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * restructure title fix (#187) Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
329 lines
9.3 KiB
JSON
329 lines
9.3 KiB
JSON
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.0.0",
|
|
"name": "example_04",
|
|
"origin": {
|
|
"mimetype": "text/html",
|
|
"binary_hash": 2846345769602286603,
|
|
"filename": "example_04.html"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
}
|
|
],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/tables/0"
|
|
}
|
|
],
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Data Table with Rowspan and Colspan",
|
|
"text": "Data Table with Rowspan and Colspan"
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [
|
|
{
|
|
"self_ref": "#/tables/0",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [],
|
|
"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": "Header 1",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Header 2 & 3 (colspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 2,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Row 1 & 2, Col 1 (rowspan)",
|
|
"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": "Row 1, Col 2",
|
|
"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": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 1, Col 3",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 2, Col 2 & 3 (colspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Row 3, Col 1",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Row 3, Col 2",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 3, Col 3",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
"num_rows": 4,
|
|
"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": "Header 1",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Header 2 & 3 (colspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Header 2 & 3 (colspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 2,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Row 1 & 2, Col 1 (rowspan)",
|
|
"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": "Row 1, Col 2",
|
|
"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": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 1, Col 3",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 2,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Row 1 & 2, Col 1 (rowspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 2, Col 2 & 3 (colspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 2,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 2, Col 2 & 3 (colspan)",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Row 3, Col 1",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Row 3, Col 2",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Row 3, Col 3",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
]
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"key_value_items": [],
|
|
"pages": {}
|
|
} |