def check_options_optimizing(options):
if options.optimize >= 2:
check_external_program(
program='pngquant',
package='pngquant',
version_checker=pngquant.version,
need_version='2.0.1',
required_for='--optimize {2,3}',
)
if options.optimize >= 2:
# Although we use JBIG2 for optimize=1, don't nag about it unless the
# user is asking for more optimization
check_external_program(
program='jbig2',
package='jbig2enc',
version_checker=jbig2enc.version,
need_version='0.28',
required_for='--optimize {2,3} | --jbig2-lossy',
recommended=True if not options.jbig2_lossy else False,
)
if options.optimize == 0 and any(
[options.jbig2_lossy, options.png_quality, options.jpeg_quality]):
log.warning(
"The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
"will be ignored because --optimize=0.")
def check_options(options):
gs_version = ghostscript.version()
check_external_program(
program='gs',
package='ghostscript',
version_checker=gs_version,
need_version='9.15', # limited by Travis CI / Ubuntu 14.04 backports
)
if gs_version in ('9.24', '9.51'):
raise MissingDependencyError(
f"Ghostscript {gs_version} contains serious regressions and is not "
"supported. Please upgrade to a newer version, or downgrade to the "
"previous version.")
# We have these constraints to check for.
# 1. Ghostscript < 9.20 mangles multibyte Unicode
# 2. hocr doesn't work on non-Latin languages (so don't select it)
is_latin = options.languages.issubset(HOCR_OK_LANGS)
if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
# https://bugs.ghostscript.com/show_bug.cgi?id=696874
# Ghostscript < 9.20 fails to encode multibyte characters properly
log.warning(
f"The installed version of Ghostscript ({gs_version}) does not work "
"correctly with the OCR languages you specified. Use --output-type pdf or "
"upgrade to Ghostscript 9.20 or later to avoid this issue.")
if options.output_type == 'pdfa':
options.output_type = 'pdfa-2'
if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
raise MissingDependencyError(
"--output-type pdfa-3 requires Ghostscript 9.19 or later")
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_preprocessing(options):
if options.clean_final:
options.clean = True
if options.unpaper_args and not options.clean:
raise BadArgsError("--clean is required for --unpaper-args")
if options.clean:
check_external_program(
program='unpaper',
package='unpaper',
version_checker=unpaper.version,
need_version='6.1',
required_for=['--clean, --clean-final'],
)
try:
if options.unpaper_args:
options.unpaper_args = unpaper.validate_custom_args(
options.unpaper_args)
except Exception as e:
raise BadArgsError("--unpaper-args: " + str(e)) from e
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.")
