def test_report_file_size(tmp_path, caplog):
in_ = tmp_path / 'a.pdf'
out = tmp_path / 'b.pdf'
in_.write_bytes(b'123')
out.write_bytes(b'')
opts = make_opts()
vd.report_output_file_size(opts, in_, out)
assert caplog.text == ''
os.truncate(in_, 25001)
os.truncate(out, 50000)
vd.report_output_file_size(opts, in_, out)
assert 'No reason' in caplog.text
def test_report_file_size(tmp_path, caplog):
in_ = tmp_path / 'a.pdf'
out = tmp_path / 'b.pdf'
pdf = pikepdf.new()
pdf.save(in_)
pdf.save(out)
opts = make_opts(output_type='pdf')
vd.report_output_file_size(opts, in_, out)
assert caplog.text == ''
caplog.clear()
waste_of_space = b'Dummy' * 5000
pdf.Root.Dummy = waste_of_space
pdf.save(in_)
pdf.Root.Dummy2 = waste_of_space + waste_of_space
pdf.save(out)
with patch('ocrmypdf._validation.jbig2enc.available', return_value=True), patch(
'ocrmypdf._validation.pngquant.available', return_value=True
):
vd.report_output_file_size(opts, in_, out)
assert 'No reason' in caplog.text
caplog.clear()
with patch('ocrmypdf._validation.jbig2enc.available', return_value=False), patch(
'ocrmypdf._validation.pngquant.available', return_value=True
):
vd.report_output_file_size(opts, in_, out)
assert 'optional dependency' in caplog.text
caplog.clear()
opts = make_opts(in_, out, optimize=0, output_type='pdf')
vd.report_output_file_size(opts, in_, out)
assert 'disabled' in caplog.text
caplog.clear()
def test_report_file_size(tmp_path, caplog):
in_ = tmp_path / 'a.pdf'
out = tmp_path / 'b.pdf'
in_.write_bytes(b'123')
out.write_bytes(b'')
opts = make_opts()
vd.report_output_file_size(opts, in_, out)
assert caplog.text == ''
caplog.clear()
os.truncate(in_, 25001)
os.truncate(out, 50000)
with patch('ocrmypdf._validation.jbig2enc.available',
return_value=True), patch(
'ocrmypdf._validation.pngquant.available',
return_value=True):
vd.report_output_file_size(opts, in_, out)
assert 'No reason' in caplog.text
caplog.clear()
with patch('ocrmypdf._validation.jbig2enc.available',
return_value=False), patch(
'ocrmypdf._validation.pngquant.available',
return_value=True):
vd.report_output_file_size(opts, in_, out)
assert 'optional dependency' in caplog.text
caplog.clear()
opts = make_opts(in_, out, optimize=0)
vd.report_output_file_size(opts, in_, out)
assert 'disabled' in caplog.text
caplog.clear()
def run_pipeline(options, *, plugin_manager, api=False):
# Any changes to options will not take effect for options that are already
# bound to function parameters in the pipeline. (For example
# options.input_file, options.pdf_renderer are already bound.)
if not options.jobs:
options.jobs = available_cpu_count()
if not plugin_manager:
plugin_manager = get_plugin_manager(options.plugins)
work_folder = Path(mkdtemp(prefix="ocrmypdf.io."))
debug_log_handler = None
if (
(options.keep_temporary_files or options.verbose >= 1)
and not os.environ.get('PYTEST_CURRENT_TEST', '')
and not api
):
# Debug log for command line interface only with verbose output
# See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
# when pytest is running
debug_log_handler = configure_debug_logging(
Path(work_folder) / "debug.log"
) # pragma: no cover
pikepdf_enable_mmap()
executor = setup_executor(plugin_manager)
try:
check_requested_output_file(options)
start_input_file, original_filename = create_input_file(options, work_folder)
# Triage image or pdf
origin_pdf = triage(
original_filename, start_input_file, work_folder / 'origin.pdf', options
)
# Gather pdfinfo and create context
pdfinfo = get_pdfinfo(
origin_pdf,
executor=executor,
detailed_analysis=options.redo_ocr,
progbar=options.progress_bar,
max_workers=options.jobs if not options.use_threads else 1, # To help debug
check_pages=options.pages,
)
context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
# Validate options are okay for this pdf
validate_pdfinfo_options(context)
# Execute the pipeline
exec_concurrent(context, executor)
if options.output_file == '-':
log.info("Output sent to stdout")
elif (
hasattr(options.output_file, 'writable') and options.output_file.writable()
):
log.info("Output written to stream")
elif samefile(options.output_file, os.devnull):
pass # Say nothing when sending to dev null
else:
if options.output_type.startswith('pdfa'):
pdfa_info = file_claims_pdfa(options.output_file)
if pdfa_info['pass']:
log.info(
"Output file is a %s (as expected)", pdfa_info['conformance']
)
else:
log.warning(
"Output file is okay but is not PDF/A (seems to be %s)",
pdfa_info['conformance'],
)
return ExitCode.pdfa_conversion_failed
if not check_pdf(options.output_file):
log.warning('Output file: The generated PDF is INVALID')
return ExitCode.invalid_output_pdf
report_output_file_size(options, start_input_file, options.output_file)
except (KeyboardInterrupt if not api else NeverRaise) as e:
if options.verbose >= 1:
log.exception("KeyboardInterrupt")
else:
log.error("KeyboardInterrupt")
return ExitCode.ctrl_c
except (ExitCodeException if not api else NeverRaise) as e:
if options.verbose >= 1:
log.exception("ExitCodeException")
elif str(e):
log.error("%s: %s", type(e).__name__, str(e))
else:
log.error(type(e).__name__)
return e.exit_code
except (Exception if not api else NeverRaise) as e: # pylint: disable=broad-except
log.exception("An exception occurred while executing the pipeline")
return ExitCode.other_error
finally:
if debug_log_handler:
try:
debug_log_handler.close()
log.removeHandler(debug_log_handler)
except EnvironmentError as e:
print(e, file=sys.stderr)
cleanup_working_files(work_folder, options)
return ExitCode.ok
