docling/tests/test_backend_msexcel.py
Ayraf df140227c3
feat: support xlsm files (#1520)
* code for xlsm support

* updated support for xlsm

* updated code for xlsm support

* Update docling_parse_v4_backend.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Update docling_parse_v4_backend.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Update test_backend_msexcel_xlsm.py

 updated the tests/test_backend_msexcel_xlsm.py:

 have a function starting with test
removed all print statements
** To add an explicit assert {test}=={pred}

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Update base_models.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Update test_backend_msexcel.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Update test_backend_msexcel_xlsm.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Update document_converter.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* Delete tests/test_backend_msexcel_xlsm.py

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* xlsm file

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>

* run tests

* ran tests

* Fix tests, upgrade XSLM example to a valid file

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: ShiroYasha18 <85089952+ShiroYasha18@users.noreply.github.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
2025-06-10 16:55:59 +02:00

100 lines
3.0 KiB
Python

import logging
from pathlib import Path
import pytest
from docling.backend.msexcel_backend import MsExcelDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult, DoclingDocument, InputDocument
from docling.document_converter import DocumentConverter
from .test_data_gen_flag import GEN_TEST_DATA
from .verify_utils import verify_document, verify_export
_log = logging.getLogger(__name__)
GENERATE = GEN_TEST_DATA
def get_excel_paths():
# Define the directory you want to search
directory = Path("./tests/data/xlsx/")
# List all Excel files in the directory and its subdirectories
excel_files = sorted(directory.rglob("*.xlsx")) + sorted(directory.rglob("*.xlsm"))
return excel_files
def get_converter():
converter = DocumentConverter(allowed_formats=[InputFormat.XLSX])
return converter
@pytest.fixture(scope="module")
def documents() -> list[tuple[Path, DoclingDocument]]:
documents: list[dict[Path, DoclingDocument]] = []
excel_paths = get_excel_paths()
converter = get_converter()
for excel_path in excel_paths:
_log.debug(f"converting {excel_path}")
gt_path = (
excel_path.parent.parent / "groundtruth" / "docling_v2" / excel_path.name
)
conv_result: ConversionResult = converter.convert(excel_path)
doc: DoclingDocument = conv_result.document
assert doc, f"Failed to convert document from file {gt_path}"
documents.append((gt_path, doc))
return documents
def test_e2e_excel_conversions(documents) -> None:
for gt_path, doc in documents:
pred_md: str = doc.export_to_markdown()
assert verify_export(pred_md, str(gt_path) + ".md"), "export to md"
pred_itxt: str = doc._export_to_indented_text(
max_text_len=70, explicit_tables=False
)
assert verify_export(pred_itxt, str(gt_path) + ".itxt"), (
"export to indented-text"
)
assert verify_document(doc, str(gt_path) + ".json", GENERATE), (
"document document"
)
def test_pages(documents) -> None:
"""Test the page count and page size of converted documents.
Args:
documents: The paths and converted documents.
"""
# number of pages from the backend method
path = next(item for item in get_excel_paths() if item.stem == "test-01")
in_doc = InputDocument(
path_or_stream=path,
format=InputFormat.XLSX,
filename=path.stem,
backend=MsExcelDocumentBackend,
)
backend = MsExcelDocumentBackend(in_doc=in_doc, path_or_stream=path)
assert backend.page_count() == 3
# number of pages from the converted document
doc = next(item for path, item in documents if path.stem == "test-01")
assert len(doc.pages) == 3
# page sizes as number of cells
assert doc.pages.get(1).size.as_tuple() == (3.0, 7.0)
assert doc.pages.get(2).size.as_tuple() == (9.0, 18.0)
assert doc.pages.get(3).size.as_tuple() == (13.0, 36.0)