def test_override_metadata(spoof_tesseract_noop, output_type):
input_file = _infile('c02-22.pdf')
output_file = _outfile('test_override_metadata.pdf')
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
high_unicode = 'U+1030C is: 𐌌'
p, out, err = run_ocrmypdf(
input_file, output_file,
'--title', german,
'--author', chinese,
'--subject', high_unicode,
'--output-type', output_type,
env=spoof_tesseract_noop)
assert p.returncode == ExitCode.ok
pdf = output_file
out_pdfinfo = check_output(['pdfinfo', pdf], universal_newlines=True)
lines_pdfinfo = out_pdfinfo.splitlines()
pdfinfo = {}
for line in lines_pdfinfo:
k, v = line.strip().split(':', maxsplit=1)
pdfinfo[k.strip()] = v.strip()
assert pdfinfo['Title'] == german
assert pdfinfo['Author'] == chinese
assert pdfinfo['Subject'] == high_unicode
assert pdfinfo.get('Keywords', '') == ''
pdfa_info = file_claims_pdfa(output_file)
assert pdfa_info['output'] == output_type
def test_override_metadata(spoof_tesseract_noop, output_type, resources,
outpdf):
input_file = resources / 'c02-22.pdf'
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
p, out, err = run_ocrmypdf(input_file,
outpdf,
'--title',
german,
'--author',
chinese,
'--output-type',
output_type,
env=spoof_tesseract_noop)
assert p.returncode == ExitCode.ok, err
before = pikepdf.open(input_file)
after = pikepdf.open(outpdf)
if ghostscript.version() >= '9.24':
pytest.xfail('Ghostscript 9.24+ does not support Unicode DOCINFO')
assert after.metadata.Title == german, after.metadata
assert after.metadata.Author == chinese, after.metadata
assert after.metadata.get('/Keywords', '') == ''
before_date = decode_pdf_date(str(before.metadata.CreationDate))
after_date = decode_pdf_date(str(after.metadata.CreationDate))
assert before_date == after_date
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['output'] == output_type
def test_override_metadata(spoof_tesseract_noop, output_type):
input_file = _infile('c02-22.pdf')
output_file = _outfile('test_override_metadata.pdf')
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
high_unicode = 'U+1030C is: 𐌌'
p, out, err = run_ocrmypdf(
input_file, output_file,
'--title', german,
'--author', chinese,
'--subject', high_unicode,
'--output-type', output_type,
env=spoof_tesseract_noop)
assert p.returncode == ExitCode.ok
pdf = output_file
out_pdfinfo = check_output(['pdfinfo', pdf], universal_newlines=True)
lines_pdfinfo = out_pdfinfo.splitlines()
pdfinfo = {}
for line in lines_pdfinfo:
k, v = line.strip().split(':', maxsplit=1)
pdfinfo[k.strip()] = v.strip()
assert pdfinfo['Title'] == german
assert pdfinfo['Author'] == chinese
assert pdfinfo['Subject'] == high_unicode
assert pdfinfo.get('Keywords', '') == ''
pdfa_info = file_claims_pdfa(output_file)
assert pdfa_info['output'] == output_type
def test_override_metadata(output_type, resources, outpdf):
input_file = resources / 'c02-22.pdf'
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
p, _out, err = run_ocrmypdf(
input_file,
outpdf,
'--title',
german,
'--author',
chinese,
'--output-type',
output_type,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
assert p.returncode == ExitCode.ok, err
before = pikepdf.open(input_file)
after = pikepdf.open(outpdf)
assert after.docinfo.Title == german, after.docinfo
assert after.docinfo.Author == chinese, after.docinfo
assert after.docinfo.get('/Keywords', '') == ''
before_date = decode_pdf_date(str(before.docinfo.CreationDate))
after_date = decode_pdf_date(str(after.docinfo.CreationDate))
assert before_date == after_date
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['output'] == output_type
def test_override_metadata(spoof_tesseract_noop, output_type, resources, outpdf):
input_file = resources / 'c02-22.pdf'
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
p, out, err = run_ocrmypdf(
input_file,
outpdf,
'--title',
german,
'--author',
chinese,
'--output-type',
output_type,
env=spoof_tesseract_noop,
)
assert p.returncode == ExitCode.ok, err
before = pikepdf.open(input_file)
after = pikepdf.open(outpdf)
assert after.docinfo.Title == german, after.docinfo
assert after.docinfo.Author == chinese, after.docinfo
assert after.docinfo.get('/Keywords', '') == ''
before_date = decode_pdf_date(str(before.docinfo.CreationDate))
after_date = decode_pdf_date(str(after.docinfo.CreationDate))
assert before_date == after_date
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['output'] == output_type
def test_override_metadata(spoof_tesseract_noop, output_type, resources,
outpdf):
input_file = resources / 'c02-22.pdf'
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
p, out, err = run_ocrmypdf(
input_file, outpdf,
'--title', german,
'--author', chinese,
'--output-type', output_type,
env=spoof_tesseract_noop)
assert p.returncode == ExitCode.ok, err
before = pypdf.PdfFileReader(str(input_file))
after = pypdf.PdfFileReader(outpdf)
assert after.documentInfo['/Title'] == german
assert after.documentInfo['/Author'] == chinese
assert after.documentInfo.get('/Keywords', '') == ''
before_date = decode_pdf_date(before.documentInfo['/CreationDate'])
after_date = decode_pdf_date(after.documentInfo['/CreationDate'])
assert before_date == after_date
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['output'] == output_type
def test_pdfa_1(spoof_tesseract_cache, resources, outpdf):
check_ocrmypdf(resources / 'ccitt.pdf',
outpdf,
'--output-type',
'pdfa-1',
env=spoof_tesseract_cache)
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['conformance'] == 'PDF/A-1B'
def test_pdfa_1(spoof_tesseract_cache, resources, outpdf):
check_ocrmypdf(
resources / 'ccitt.pdf', outpdf,
'--output-type', 'pdfa-1',
env=spoof_tesseract_cache
)
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['conformance'] == 'PDF/A-1B'
def test_pdfa_n(spoof_tesseract_cache, pdfa_level, resources, outpdf):
if pdfa_level == '3' and ghostscript.version() < '9.19':
pytest.xfail(reason='Ghostscript >= 9.19 required')
check_ocrmypdf(
resources / 'ccitt.pdf', outpdf,
'--output-type', 'pdfa-' + pdfa_level,
env=spoof_tesseract_cache
)
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['conformance'] == 'PDF/A-{}B'.format(pdfa_level)
def test_preserve_metadata(spoof_tesseract_noop, output_type):
pdf_before = pypdf.PdfFileReader(_infile('graph.pdf'))
output = check_ocrmypdf('graph.pdf', 'test_metadata_preserve.pdf',
'--output-type', output_type,
env=spoof_tesseract_noop)
pdf_after = pypdf.PdfFileReader(output)
for key in ('/Title', '/Author'):
assert pdf_before.documentInfo[key] == pdf_after.documentInfo[key]
pdfa_info = file_claims_pdfa(output)
assert pdfa_info['output'] == output_type
def test_preserve_metadata(spoof_tesseract_noop, output_type):
pdf_before = pypdf.PdfFileReader(_infile('graph.pdf'))
output = check_ocrmypdf('graph.pdf', 'test_metadata_preserve.pdf',
'--output-type', output_type,
env=spoof_tesseract_noop)
pdf_after = pypdf.PdfFileReader(output)
for key in ('/Title', '/Author'):
assert pdf_before.documentInfo[key] == pdf_after.documentInfo[key]
pdfa_info = file_claims_pdfa(output)
assert pdfa_info['output'] == output_type
def test_pdfa_n(pdfa_level, resources, outpdf):
if pdfa_level == '3' and ghostscript.version() < '9.19':
pytest.xfail(reason='Ghostscript >= 9.19 required')
check_ocrmypdf(
resources / 'ccitt.pdf',
outpdf,
'--output-type',
'pdfa-' + pdfa_level,
'--plugin',
'tests/plugins/tesseract_cache.py',
)
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['conformance'] == f'PDF/A-{pdfa_level}B'
def test_preserve_metadata(spoof_tesseract_noop, output_type,
resources, outpdf):
pdf_before = pikepdf.open(resources / 'graph.pdf')
output = check_ocrmypdf(
resources / 'graph.pdf', outpdf,
'--output-type', output_type,
env=spoof_tesseract_noop)
pdf_after = pikepdf.open(output)
for key in ('/Title', '/Author'):
assert pdf_before.docinfo[key] == pdf_after.docinfo[key]
pdfa_info = file_claims_pdfa(str(output))
assert pdfa_info['output'] == output_type
def test_preserve_metadata(spoof_tesseract_noop, output_type, resources, outpdf):
pdf_before = pikepdf.open(resources / 'graph.pdf')
output = check_ocrmypdf(
resources / 'graph.pdf',
outpdf,
'--output-type',
output_type,
env=spoof_tesseract_noop,
)
pdf_after = pikepdf.open(output)
for key in ('/Title', '/Author'):
assert pdf_before.docinfo[key] == pdf_after.docinfo[key]
pdfa_info = file_claims_pdfa(str(output))
assert pdfa_info['output'] == output_type
def test_preserve_docinfo(output_type, resources, outpdf):
pdf_before = pikepdf.open(resources / 'graph.pdf')
output = check_ocrmypdf(
resources / 'graph.pdf',
outpdf,
'--output-type',
output_type,
'--plugin',
'tests/plugins/tesseract_noop.py',
)
pdf_after = pikepdf.open(output)
for key in ('/Title', '/Author'):
assert pdf_before.docinfo[key] == pdf_after.docinfo[key]
pdfa_info = file_claims_pdfa(str(output))
assert pdfa_info['output'] == output_type
def test_override_metadata(spoof_tesseract_noop, output_type, resources,
outpdf):
input_file = resources / 'c02-22.pdf'
german = 'Du siehst den Wald vor lauter Bäumen nicht.'
chinese = '孔子'
p, out, err = run_ocrmypdf(
input_file, outpdf,
'--title', german,
'--author', chinese,
'--output-type', output_type,
env=spoof_tesseract_noop)
assert p.returncode == ExitCode.ok, err
reader = pypdf.PdfFileReader(outpdf)
assert reader.documentInfo['/Title'] == german
assert reader.documentInfo['/Author'] == chinese
assert reader.documentInfo.get('/Keywords', '') == ''
pdfa_info = file_claims_pdfa(outpdf)
assert pdfa_info['output'] == output_type
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