mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: do not consider singleton cells in xlsx as TableItems but rather TextItems (#2589)

Browse Source 
fix: do not handle 1x1 cell as a tableitem but as a textitem

Signed-off-by: glypt <8trash-can8@protonmail.ch>
This commit is contained in:
glypt
2025-11-27 16:25:32 +01:00
committed by GitHub
parent c0b57ae389
commit 54cd6d7406
7 changed files with 729 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/data/groundtruth/docling_v2/xlsx_05_table_with_title.xlsx.itxt vendored Normal file
View File

@@ -0,0 +1,4 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: section: group sheet: Duck Observations
item-2 at level 2: table with [1x1]
item-3 at level 2: table with [7x2]

578
tests/data/groundtruth/docling_v2/xlsx_05_table_with_title.xlsx.json vendored Normal file
View File

@@ -0,0 +1,578 @@
{
"schema_name": "DoclingDocument",
"version": "1.7.0",
"name": "xlsx_05_table_with_title",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"binary_hash": 18126553641942797758,
"filename": "xlsx_05_table_with_title.xlsx",
"uri": null
},
"furniture": {
"self_ref": "#/furniture",
"parent": null,
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"parent": null,
"children": [
{
"cref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"cref": "#/body"
},
"children": [
{
"cref": "#/tables/0"
},
{
"cref": "#/tables/1"
}
],
"content_layer": "body",
"name": "sheet: Duck Observations",
"label": "section"
}
],
"texts": [],
"pictures": [],
"tables": [
{
"self_ref": "#/tables/0",
"parent": {
"cref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [
{
"page_no": 1,
"bbox": {
"l": 1.0,
"t": 1.0,
"r": 2.0,
"b": 2.0,
"coord_origin": "TOPLEFT"
},
"charspan": [
0,
0
]
}
],
"captions": [],
"references": [],
"footnotes": [],
"image": null,
"data": {
"table_cells": [
{
"bbox": null,
"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": "Number of freshwater ducks per year",
"column_header": true,
"row_header": false,
"row_section": false,
"fillable": false
}
],
"num_rows": 1,
"num_cols": 1,
"grid": [
[
{
"bbox": null,
"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": "Number of freshwater ducks per year",
"column_header": true,
"row_header": false,
"row_section": false,
"fillable": false
}
]
]
},
"annotations": []
},
{
"self_ref": "#/tables/1",
"parent": {
"cref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [
{
"page_no": 1,
"bbox": {
"l": 1.0,
"t": 3.0,
"r": 3.0,
"b": 10.0,
"coord_origin": "TOPLEFT"
},
"charspan": [
0,
0
]
}
],
"captions": [],
"references": [],
"footnotes": [],
"image": null,
"data": {
"table_cells": [
{
"bbox": null,
"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": "Year",
"column_header": true,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "Freshwater Ducks",
"column_header": true,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "2019",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "120",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 2,
"end_row_offset_idx": 3,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2020",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 2,
"end_row_offset_idx": 3,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "135",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "2021",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "150",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 4,
"end_row_offset_idx": 5,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2022",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 4,
"end_row_offset_idx": 5,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "170",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 5,
"end_row_offset_idx": 6,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2023",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 5,
"end_row_offset_idx": 6,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "160",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 6,
"end_row_offset_idx": 7,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2024",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 6,
"end_row_offset_idx": 7,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "180",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
"num_rows": 7,
"num_cols": 2,
"grid": [
[
{
"bbox": null,
"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": "Year",
"column_header": true,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "Freshwater Ducks",
"column_header": true,
"row_header": false,
"row_section": false,
"fillable": false
}
],
[
{
"bbox": null,
"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": "2019",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "120",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
[
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 2,
"end_row_offset_idx": 3,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2020",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 2,
"end_row_offset_idx": 3,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "135",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
[
{
"bbox": null,
"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": "2021",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"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": "150",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
[
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 4,
"end_row_offset_idx": 5,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2022",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 4,
"end_row_offset_idx": 5,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "170",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
[
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 5,
"end_row_offset_idx": 6,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2023",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 5,
"end_row_offset_idx": 6,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "160",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
],
[
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 6,
"end_row_offset_idx": 7,
"start_col_offset_idx": 0,
"end_col_offset_idx": 1,
"text": "2024",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
},
{
"bbox": null,
"row_span": 1,
"col_span": 1,
"start_row_offset_idx": 6,
"end_row_offset_idx": 7,
"start_col_offset_idx": 1,
"end_col_offset_idx": 2,
"text": "180",
"column_header": false,
"row_header": false,
"row_section": false,
"fillable": false
}
]
]
},
"annotations": []
}
],
"key_value_items": [],
"form_items": [],
"pages": {
"1": {
"size": {
"width": 2.0,
"height": 7.0
},
"image": null,
"page_no": 1
}
}
}

11
tests/data/groundtruth/docling_v2/xlsx_05_table_with_title.xlsx.md vendored Normal file
View File

@@ -0,0 +1,11 @@
| Number of freshwater ducks per year |
|---------------------------------------|
| Year | Freshwater Ducks |
|--------|--------------------|
| 2019 | 120 |
| 2020 | 135 |
| 2021 | 150 |
| 2022 | 170 |
| 2023 | 160 |
| 2024 | 180 |

BIN
tests/data/xlsx/xlsx_05_table_with_title.xlsx vendored Normal file
View File

Binary file not shown.

46
tests/test_backend_msexcel.py
View File

@@ -6,9 +6,10 @@ import pytest
from openpyxl import load_workbook
from docling.backend.msexcel_backend import MsExcelDocumentBackend
from docling.datamodel.backend_options import MsExcelBackendOptions
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult, DoclingDocument, InputDocument
from docling.document_converter import DocumentConverter
from docling.document_converter import DocumentConverter, ExcelFormatOption
from .test_data_gen_flag import GEN_TEST_DATA
from .verify_utils import verify_document, verify_export
@@ -227,6 +228,49 @@ def test_inflated_rows_handling(documents) -> None:
)
def test_table_with_title():
"""Test that singleton cells with non-numeric content are treated as TextItem.
When treat_singleton_as_text option is enabled, 1x1 tables containing non-numeric
text should be converted to TextItem instead of TableItem. This test verifies that
xlsx_05_table_with_title.xlsx is correctly parsed with this option.
"""
path = next(
item for item in get_excel_paths() if item.stem == "xlsx_05_table_with_title"
)
# Create converter with treat_singleton_as_text=True
options = MsExcelBackendOptions(treat_singleton_as_text=True)
format_options = {InputFormat.XLSX: ExcelFormatOption(backend_options=options)}
converter = DocumentConverter(
allowed_formats=[InputFormat.XLSX], format_options=format_options
)
conv_result: ConversionResult = converter.convert(path)
doc: DoclingDocument = conv_result.document
# With treat_singleton_as_text=True, the singleton title cell should be a TextItem
texts = list(doc.texts)
tables = list(doc.tables)
assert len(texts) == 1, f"Should have 1 text item (the title), got {len(texts)}"
assert len(tables) == 1, f"Should have 1 table, got {len(tables)}"
# Verify the text item contains the title
assert texts[0].text == "Number of freshwater ducks per year", (
f"Text should be 'Number of freshwater ducks per year', got '{texts[0].text}'"
)
# Verify table dimensions
table = tables[0]
assert table.data.num_rows == 7, (
f"Table should have 7 rows, got {table.data.num_rows}"
)
assert table.data.num_cols == 2, (
f"Table should have 2 columns, got {table.data.num_cols}"
)
def test_bytesio_stream():
"""Test that Excel files can be loaded from BytesIO streams.