docling/tests/test_invalid_input.py

45 lines
1.4 KiB
Python
Raw Permalink Normal View History

from io import BytesIO
from pathlib import Path
import pytest
from docling.datamodel.base_models import ConversionStatus, DocumentStream
from docling.document_converter import ConversionError, DocumentConverter
def get_pdf_path():
fix: Test cases for RTL programmatic PDFs and fixes for the formula model (#903) fix: Support for RTL programmatic documents fix(parser): detect and handle rotated pages fix(parser): fix bug causing duplicated text fix(formula): improve stopping criteria chore: update lock file fix: temporary constrain beautifulsoup * switch to code formula model v1.0.1 and new test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * switch to code formula model v1.0.1 and new test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * cleaned up the data folder in the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * switch to code formula model v1.0.1 and new test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * added three test-files for right-to-left Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fix black Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * added new gt for test_e2e_conversion Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * added new gt for test_e2e_conversion Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * Add code to expose text direction of cell Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * new test file Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * update lock Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix mypy reports Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix example filepaths Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add test data results Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * pin wheel of latest docling-parse release Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use latest docling-core Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * remove debugging code Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix path to files in example Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Revert unwanted RTL additions Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix test data paths in examples Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Co-authored-by: Peter Staar <taa@zurich.ibm.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
2025-02-07 08:43:31 +01:00
pdf_path = Path("./tests/data/pdf/2305.03393v1-pg9.pdf")
return pdf_path
@pytest.fixture
def converter():
converter = DocumentConverter()
return converter
def test_convert_unsupported_doc_format_wout_exception(converter: DocumentConverter):
result = converter.convert(
DocumentStream(name="input.xyz", stream=BytesIO(b"xyz")), raises_on_error=False
)
assert result.status == ConversionStatus.SKIPPED
def test_convert_unsupported_doc_format_with_exception(converter: DocumentConverter):
with pytest.raises(ConversionError):
converter.convert(
DocumentStream(name="input.xyz", stream=BytesIO(b"xyz")),
raises_on_error=True,
)
def test_convert_too_small_filesize_limit_wout_exception(converter: DocumentConverter):
result = converter.convert(get_pdf_path(), max_file_size=1, raises_on_error=False)
assert result.status == ConversionStatus.FAILURE
def test_convert_too_small_filesize_limit_with_exception(converter: DocumentConverter):
with pytest.raises(ConversionError):
converter.convert(get_pdf_path(), max_file_size=1, raises_on_error=True)