def check_options(options):
check_external_program(
program='tesseract',
package={'linux': 'tesseract-ocr'},
version_checker=tesseract.version,
need_version='4.0.0', # using backport for Travis CI
)
# Decide on what renderer to use
if options.pdf_renderer == 'auto':
options.pdf_renderer = 'sandwich'
if options.pdf_renderer == 'sandwich' and not tesseract.has_textonly_pdf(
set(options.languages)):
raise MissingDependencyError(
"You are using an alpha version of Tesseract 4.0 that does not support "
"the textonly_pdf parameter. We don't support versions this old.")
if not tesseract.has_user_words() and (options.user_words
or options.user_patterns):
log.warning(
"Tesseract 4.0 ignores --user-words and --user-patterns, so these "
"arguments have no effect.")
if options.tesseract_pagesegmode in (0, 2):
log.warning(
"The --tesseract-pagesegmode argument you select will disable OCR. "
"This may cause processing to fail.")
def check_options(options):
check_external_program(
program='tesseract',
package={'linux': 'tesseract-ocr'},
version_checker=tesseract.version,
need_version='4.0.0-beta.1', # using backport for Travis CI
version_parser=tesseract.TesseractVersion,
)
# Decide on what renderer to use
if options.pdf_renderer == 'auto':
options.pdf_renderer = 'sandwich'
if not tesseract.has_user_words() and (options.user_words
or options.user_patterns):
log.warning(
"Tesseract 4.0 ignores --user-words and --user-patterns, so these "
"arguments have no effect.")
if options.tesseract_pagesegmode in (0, 2):
log.warning(
"The --tesseract-pagesegmode argument you select will disable OCR. "
"This may cause processing to fail.")
p, _out, err = run_ocrmypdf(
resources / 'ccitt.pdf',
outdir / 'out.pdf',
'--pdf-renderer',
renderer,
'--tesseract-config',
cfg_file,
)
assert (
"parameter not found" in err.lower()
or "error occurred while parsing" in err.lower()
), "No error message"
assert p.returncode == ExitCode.invalid_config
@pytest.mark.skipif(not tesseract.has_user_words(), reason='not functional until 4.1.0')
def test_user_words_ocr(resources, outdir):
# Does not actually test if --user-words causes output to differ
word_list = outdir / 'wordlist.txt'
sidecar_after = outdir / 'sidecar.txt'
with word_list.open('w') as f:
f.write('cromulent\n') # a perfectly cromulent word
check_ocrmypdf(
resources / 'crom.png',
outdir / 'out.pdf',
'--image-dpi',
150,
'--sidecar',
sidecar_after,
''')
p, _out, err = run_ocrmypdf(
resources / 'ccitt.pdf',
outdir / 'out.pdf',
'--pdf-renderer',
renderer,
'--tesseract-config',
cfg_file,
)
assert ("parameter not found" in err.lower() or
"error occurred while parsing" in err.lower()), "No error message"
assert p.returncode == ExitCode.invalid_config
@pytest.mark.skipif(not tesseract.has_user_words(),
reason='not functional until 4.1.0')
def test_user_words_ocr(resources, outdir):
# Does not actually test if --user-words causes output to differ
word_list = outdir / 'wordlist.txt'
sidecar_after = outdir / 'sidecar.txt'
with word_list.open('w') as f:
f.write('cromulent\n') # a perfectly cromulent word
check_ocrmypdf(
resources / 'crom.png',
outdir / 'out.pdf',
'--image-dpi',
150,
'--sidecar',