def test_no_languages(tmp_path):
env = os.environ.copy()
(tmp_path / 'tessdata').mkdir()
env['TESSDATA_PREFIX'] = fspath(tmp_path)
with pytest.raises(MissingDependencyError):
tesseract.languages(tesseract_env=env)
def test_no_languages(ensure_tess4, tmpdir):
env = ensure_tess4
(tmpdir / 'tessdata').mkdir()
env['TESSDATA_PREFIX'] = fspath(tmpdir)
with modified_os_environ(env):
with pytest.raises(MissingDependencyError):
tesseract.languages.cache_clear()
tesseract.languages()
def test_no_languages(ensure_tess4, tmpdir):
env = ensure_tess4
(tmpdir / 'tessdata').mkdir()
env['TESSDATA_PREFIX'] = fspath(tmpdir)
with modified_os_environ(env):
with pytest.raises(MissingDependencyError):
tesseract.languages.cache_clear()
tesseract.languages()
def test_german(spoof_tesseract_cache, resources, outdir):
# Produce a sidecar too - implicit test that system locale is set up
# properly. It is fine that we are testing -l deu on a French file because
# we are exercising the functionality not going for accuracy.
sidecar = outdir / 'francais.txt'
p, out, err = run_ocrmypdf(
resources / 'francais.pdf',
outdir / 'francais.pdf',
'-l',
'deu', # more commonly installed
'--sidecar',
sidecar,
env=spoof_tesseract_cache,
)
if 'deu' not in tesseract.languages():
pytest.xfail(reason="tesseract-deu language pack not installed")
assert p.returncode == ExitCode.ok, "Requires tesseract deu language pack"
def test_german(spoof_tesseract_cache, resources, outdir):
# Produce a sidecar too - implicit test that system locale is set up
# properly. It is fine that we are testing -l deu on a French file because
# we are exercising the functionality not going for accuracy.
sidecar = outdir / 'francais.txt'
try:
check_ocrmypdf(
resources / 'francais.pdf',
outdir / 'francais.pdf',
'-l',
'deu', # more commonly installed
'--sidecar',
sidecar,
env=spoof_tesseract_cache,
)
except MissingDependencyError:
if 'deu' not in tesseract.languages():
pytest.xfail(reason="tesseract-deu language pack not installed")
raise