def test_old_tesseract_error():
with patch('ocrmypdf._exec.tesseract.has_textonly_pdf',
return_value=False):
with pytest.raises(MissingDependencyError):
opts = make_opts(pdf_renderer='sandwich', language='eng')
plugin_manager = get_plugin_manager(opts.plugins)
vd.check_options(opts, plugin_manager)
def run(args=None):
_parser, options, plugin_manager = get_parser_options_plugins(args=args)
if not check_closed_streams(options):
return ExitCode.bad_args
if hasattr(os, 'nice'):
os.nice(5)
verbosity = options.verbose
if not os.isatty(sys.stderr.fileno()):
options.progress_bar = False
if options.quiet:
verbosity = Verbosity.quiet
options.progress_bar = False
configure_logging(verbosity,
progress_bar_friendly=options.progress_bar,
manage_root_logger=True)
log.debug('ocrmypdf %s', __version__)
try:
check_options(options, plugin_manager)
except ValueError as e:
log.error(e)
return ExitCode.bad_args
except BadArgsError as e:
log.error(e)
return e.exit_code
except MissingDependencyError as e:
log.error(e)
return ExitCode.missing_dependency
result = run_pipeline(options=options, plugin_manager=plugin_manager)
return result
def test_hocr_notlatin_warning(caplog):
# Bypass the test to see if the language is installed; we just want to pretend
# that a non-Latin language is installed
with patch('ocrmypdf._validation.check_options_languages',
return_value=None):
vd.check_options(*make_opts_pm(
language='chi_sim', pdf_renderer='hocr', output_type='pdfa'))
assert 'PDF renderer is known to cause' in caplog.text
def test_no_unpaper(resources, no_outpdf):
input_ = fspath(resources / "c02-22.pdf")
output = fspath(no_outpdf)
options = parser.parse_args(args=["--clean", input_, output])
with patch("ocrmypdf.exec.unpaper.version") as mock_unpaper_version:
mock_unpaper_version.side_effect = FileNotFoundError("unpaper")
with pytest.raises(MissingDependencyError):
check_options(options)
def test_no_progress_bar(progress_bar, resources):
opts = make_opts(progress_bar=progress_bar,
input_file=(resources / 'trivial.pdf'))
with patch('ocrmypdf.pdfinfo.info.tqdm', autospec=True) as tqdmpatch:
vd.check_options(opts)
pdfinfo = PdfInfo(opts.input_file, progbar=opts.progress_bar)
assert tqdmpatch.called
_args, kwargs = tqdmpatch.call_args
assert kwargs['disable'] != progress_bar
def test_old_unpaper(resources, no_outpdf):
input_ = fspath(resources / "c02-22.pdf")
output = fspath(no_outpdf)
_parser, options, pm = get_parser_options_plugins(
["--clean", input_, output])
with patch("ocrmypdf._exec.unpaper.version") as mock_unpaper_version:
mock_unpaper_version.return_value = '0.5'
with pytest.raises(MissingDependencyError):
check_options(options, pm)
def test_no_progress_bar(progress_bar, resources):
opts = make_opts(progress_bar=progress_bar,
input_file=(resources / 'trivial.pdf'))
plugin_manager = get_plugin_manager(opts.plugins)
with patch('ocrmypdf._concurrent.tqdm', autospec=True) as tqdmpatch:
vd.check_options(opts, plugin_manager)
pdfinfo = PdfInfo(opts.input_file, progbar=opts.progress_bar)
assert pdfinfo is not None
assert tqdmpatch.called
_args, kwargs = tqdmpatch.call_args
assert kwargs['disable'] != progress_bar
def test_no_unpaper(resources, no_outpdf):
input_ = fspath(resources / "c02-22.pdf")
output = fspath(no_outpdf)
_parser, options, pm = get_parser_options_plugins(
["--clean", input_, output])
with patch("ocrmypdf._exec.unpaper.version") as mock:
mock.side_effect = FileNotFoundError("unpaper")
with pytest.raises(MissingDependencyError):
check_options(options, pm)
mock.assert_called()
def test_user_words(caplog):
with patch('ocrmypdf._exec.tesseract.has_user_words', return_value=False):
opts = make_opts(user_words='foo')
plugin_manager = get_plugin_manager(opts.plugins)
vd.check_options(opts, plugin_manager)
assert '4.0 ignores --user-words' in caplog.text
caplog.clear()
with patch('ocrmypdf._exec.tesseract.has_user_words', return_value=True):
opts = make_opts(user_patterns='foo')
plugin_manager = get_plugin_manager(opts.plugins)
vd.check_options(opts, plugin_manager)
assert '4.0 ignores --user-words' not in caplog.text
def test_old_ghostscript(caplog):
with patch('ocrmypdf._exec.ghostscript.version',
return_value='9.19'), patch(
'ocrmypdf._exec.tesseract.has_textonly_pdf',
return_value=True), patch(
'ocrmypdf._validation.check_options_languages',
return_value=None):
vd.check_options(*make_opts_pm(language='chi_sim', output_type='pdfa'))
assert 'Ghostscript does not work correctly' in caplog.text
with patch('ocrmypdf._exec.ghostscript.version',
return_value='9.18'), patch(
'ocrmypdf._exec.tesseract.has_textonly_pdf',
return_value=True):
with pytest.raises(MissingDependencyError):
vd.check_options(*make_opts_pm(output_type='pdfa-3'))
with patch('ocrmypdf._exec.ghostscript.version',
return_value='9.24'), patch(
'ocrmypdf._exec.tesseract.has_textonly_pdf',
return_value=True):
with pytest.raises(MissingDependencyError):
vd.check_options(*make_opts_pm())
def ocr( # pylint: disable=unused-argument
input_file: PathOrIO,
output_file: PathOrIO,
*,
language: Iterable[str] = None,
image_dpi: int = None,
output_type=None,
sidecar: os.PathLike = None,
jobs: int = None,
use_threads: bool = None,
title: str = None,
author: str = None,
subject: str = None,
keywords: str = None,
rotate_pages: bool = None,
remove_background: bool = None,
deskew: bool = None,
clean: bool = None,
clean_final: bool = None,
unpaper_args: str = None,
oversample: int = None,
remove_vectors: bool = None,
threshold: bool = None,
force_ocr: bool = None,
skip_text: bool = None,
redo_ocr: bool = None,
skip_big: float = None,
optimize: int = None,
jpg_quality: int = None,
png_quality: int = None,
jbig2_lossy: bool = None,
jbig2_page_group_size: int = None,
pages: str = None,
max_image_mpixels: float = None,
tesseract_config: Iterable[str] = None,
tesseract_pagesegmode: int = None,
tesseract_oem: int = None,
pdf_renderer=None,
tesseract_timeout: float = None,
rotate_pages_threshold: float = None,
pdfa_image_compression=None,
user_words: os.PathLike = None,
user_patterns: os.PathLike = None,
fast_web_view: float = None,
plugins: Iterable[Union[str, Path]] = None,
keep_temporary_files: bool = None,
progress_bar: bool = None,
**kwargs,
):
"""Run OCRmyPDF on one PDF or image.
For most arguments, see documentation for the equivalent command line parameter.
A few specific arguments are discussed here:
Args:
use_threads: Use worker threads instead of processes. This reduces
performance but may make debugging easier since it is easier to set
breakpoints.
input_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
interpreted as file system path to the input file. If the object
appears to be a readable stream (with methods such as ``.read()``
and ``.seek()``), the object will be read in its entirety and saved to
a temporary file. If ``input_file`` is ``"-"``, standard input will be
read.
output_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
interpreted as file system path to the output file. If the object
appears to be a writable stream (with methods such as ``.read()`` and
``.seek()``), the output will be written to this stream. If
``output_file`` is ``"-"``, the output will be written to ``sys.stdout``
(provided that standard output does not seem to be a terminal device).
When a stream is used as output, whether via a writable object or
``"-"``, some final validation steps are not performed (we do not read
back the stream after it is written).
Raises:
ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
with the OCR layer.
ocrmypdf.MissingDependencyError: If a required dependency program is missing or
was not found on PATH.
ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
could not be read, or some other file type that is not a PDF.
ocrmypdf.DpiError: If the input file is an image, but the resolution of the
image is not credible (allowing it to proceed would cause poor OCR).
ocrmypdf.OutputFileAccessError: If an attempt to write to the intended output
file failed.
ocrmypdf.PriorOcrFoundError: If the input PDF seems to have OCR or digital
text already, and settings did not tell us to proceed.
ocrmypdf.InputFileError: Any other problem with the input file.
ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
ocrmypdf.EncryptedPdfERror: If the input PDF is encrypted (password protected).
OCRmyPDF does not remove passwords.
ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
valid.
Returns:
:class:`ocrmypdf.ExitCode`
"""
if not plugins:
plugins = []
elif isinstance(plugins, (str, Path)):
plugins = [plugins]
else:
plugins = list(plugins)
parser = get_parser()
_plugin_manager = get_plugin_manager(plugins)
_plugin_manager.hook.add_options(parser=parser) # pylint: disable=no-member
create_options_kwargs = {
k: v for k, v in locals().items() if not k.startswith('_') and k != 'kwargs'
}
create_options_kwargs.update(kwargs)
if 'verbose' in kwargs:
warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
options = create_options(**create_options_kwargs)
check_options(options, _plugin_manager)
return run_pipeline(options=options, plugin_manager=_plugin_manager, api=True)
def ocr( # pylint: disable=unused-argument
input_file: os.PathLike,
output_file: os.PathLike,
*,
language: Iterable[str] = None,
image_dpi: int = None,
output_type=None,
sidecar: os.PathLike = None,
jobs: int = None,
use_threads: bool = None,
title: str = None,
author: str = None,
subject: str = None,
keywords: str = None,
rotate_pages: bool = None,
remove_background: bool = None,
deskew: bool = None,
clean: bool = None,
clean_final: bool = None,
unpaper_args: str = None,
oversample: int = None,
remove_vectors: bool = None,
threshold: bool = None,
force_ocr: bool = None,
skip_text: bool = None,
redo_ocr: bool = None,
skip_big: float = None,
optimize: int = None,
jpg_quality: int = None,
png_quality: int = None,
jbig2_lossy: bool = None,
jbig2_page_group_size: int = None,
pages: str = None,
max_image_mpixels: float = None,
tesseract_config: Iterable[str] = None,
tesseract_pagesegmode: int = None,
tesseract_oem: int = None,
pdf_renderer=None,
tesseract_timeout: float = None,
rotate_pages_threshold: float = None,
pdfa_image_compression=None,
user_words: os.PathLike = None,
user_patterns: os.PathLike = None,
fast_web_view: float = None,
plugins: Iterable[str] = None,
keep_temporary_files: bool = None,
progress_bar: bool = None,
**kwargs,
):
"""Run OCRmyPDF on one PDF or image.
For most arguments, see documentation for the equivalent command line parameter.
A few specific arguments are discussed here:
Args:
use_threads (bool): Use worker threads instead of processes. This reduces
performance but may make debugging easier since it is easier to set
breakpoints.
Raises:
ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
with the OCR layer.
ocrmypdf.MissingDependencyError: If a required dependency program is missing or
was not found on PATH.
ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
could not be read, or some other file type that is not a PDF.
ocrmypdf.DpiError: If the input file is an image, but the resolution of the
image is not credible (allowing it to proceed would cause poor OCR).
ocrmypdf.OutputFileAccessError: If an attempt to write to the intended output
file failed.
ocrmypdf.PriorOcrFoundError: If the input PDF seems to have OCR or digital
text already, and settings did not tell us to proceed.
ocrmypdf.InputFileError: Any other problem with the input file.
ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
ocrmypdf.EncryptedPdfERror: If the input PDF is encrypted (password protected).
OCRmyPDF does not remove passwords.
ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
valid.
Returns:
:class:`ocrmypdf.ExitCode`
"""
if not plugins:
plugins = []
parser = get_parser()
_plugin_manager = get_plugin_manager(plugins)
_plugin_manager.hook.add_options(parser=parser) # pylint: disable=no-member
create_options_kwargs = {
k: v
for k, v in locals().items() if not k.startswith('_') and k != 'kwargs'
}
create_options_kwargs.update(kwargs)
options = create_options(**create_options_kwargs)
check_options(options, _plugin_manager)
return run_pipeline(options=options,
plugin_manager=_plugin_manager,
api=True)
def test_pagesegmode_warning(caplog):
opts = make_opts(tesseract_pagesegmode='0')
plugin_manager = get_plugin_manager(opts.plugins)
vd.check_options(opts, plugin_manager)
assert 'disable OCR' in caplog.text
