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_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_creation_date_preserved(spoof_tesseract_noop, output_type, resources,
infile, outpdf):
input_file = resources / infile
before = pypdf.PdfFileReader(str(input_file)).getDocumentInfo()
check_ocrmypdf(
input_file, outpdf, '--output-type', output_type,
env=spoof_tesseract_noop)
after = pypdf.PdfFileReader(str(outpdf)).getDocumentInfo()
if not before:
# If there was input creation date, none should be output
# because of Ghostscript quirks we set it to null
# This test would be better if we had a test file with /DocumentInfo but
# no /CreationDate, which we don't
assert not after['/CreationDate'] or \
isinstance(after['/CreationDate'], pypdf.generic.NullObject)
else:
# We expect that the creation date stayed the same
date_before = decode_pdf_date(before['/CreationDate'])
date_after = decode_pdf_date(after['/CreationDate'])
assert seconds_between_dates(date_before, date_after) < 1000
# We expect that the modified date is quite recent
date_after = decode_pdf_date(after['/ModDate'])
assert seconds_between_dates(
date_after, datetime.datetime.now(timezone.utc)) < 1000
def test_creation_date_preserved(spoof_tesseract_noop, output_type, resources,
infile, outpdf):
input_file = resources / infile
check_ocrmypdf(input_file,
outpdf,
'--output-type',
output_type,
env=spoof_tesseract_noop)
pdf_before = pikepdf.open(input_file)
pdf_after = pikepdf.open(outpdf)
before = pdf_before.trailer.get('/Info', {})
after = pdf_after.trailer.get('/Info', {})
if not before:
# If there was input creation date, none should be output
# because of Ghostscript quirks we set it to null
# This test would be better if we had a test file with /DocumentInfo but
# no /CreationDate, which we don't
assert after.get('/CreationDate', '') == ''
else:
# We expect that the creation date stayed the same
date_before = decode_pdf_date(str(before['/CreationDate']))
date_after = decode_pdf_date(str(after['/CreationDate']))
assert seconds_between_dates(date_before, date_after) < 1000
# We expect that the modified date is quite recent
date_after = decode_pdf_date(str(after['/ModDate']))
assert seconds_between_dates(date_after, datetime.datetime.now(
timezone.utc)) < 1000