def generate_pdf(input_file, output_pdf, output_text, options):
tesseract.generate_pdf(
input_file=input_file,
output_pdf=output_pdf,
output_text=output_text,
languages=options.languages,
engine_mode=options.tesseract_oem,
tessconfig=options.tesseract_config,
timeout=options.tesseract_timeout,
pagesegmode=options.tesseract_pagesegmode,
user_words=options.user_words,
user_patterns=options.user_patterns,
)
def test_image_too_large_pdf(monkeypatch, resources, outdir):
def dummy_run(args, *, env=None, **kwargs):
raise subprocess.CalledProcessError(1, 'tesseract', output=b'Image too large')
monkeypatch.setattr(tesseract, 'run', dummy_run)
tesseract.generate_pdf(
input_file=resources / 'crom.png',
output_pdf=outdir / 'pdf.pdf',
output_text=outdir / 'txt.txt',
languages=['eng'],
engine_mode=None,
tessconfig=[],
timeout=180.0,
pagesegmode=None,
user_words=None,
user_patterns=None,
)
assert Path(outdir / 'txt.txt').read_text() == '[skipped page]'
if os.name != 'nt': # different semantics
assert Path(outdir / 'pdf.pdf').stat().st_size == 0