Docling/tests/test_backend_msexcel.py
Suehtam 1d17e7397a
test: avoid testing exact JSON in CSV backend (#1038)
* feat: updated verify_export
Moved verify_export to verify_utils
Reuse verify_export in tests

Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>

* feat: replace verify_export with verify_document in CSV conversion tests

Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>

---------

Signed-off-by: Matheus Abdias <matheusfabdias@gmail.com>
2025-02-24 08:10:40 +01:00

59 lines
1.5 KiB
Python

import os
from pathlib import Path
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult, DoclingDocument
from docling.document_converter import DocumentConverter
from .verify_utils import verify_document, verify_export
GENERATE = False
def get_xlsx_paths():
# Define the directory you want to search
directory = Path("./tests/data/xlsx/")
# List all PDF files in the directory and its subdirectories
pdf_files = sorted(directory.rglob("*.xlsx"))
return pdf_files
def get_converter():
converter = DocumentConverter(allowed_formats=[InputFormat.XLSX])
return converter
def test_e2e_xlsx_conversions():
xlsx_paths = get_xlsx_paths()
converter = get_converter()
for xlsx_path in xlsx_paths:
print(f"converting {xlsx_path}")
gt_path = (
xlsx_path.parent.parent / "groundtruth" / "docling_v2" / xlsx_path.name
)
conv_result: ConversionResult = converter.convert(xlsx_path)
doc: DoclingDocument = conv_result.document
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"