def test_metadata_fixup_warning(resources, outdir, caplog):
options = get_parser().parse_args(
args=['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
)
copyfile(resources / 'graph.pdf', outdir / 'graph.pdf')
context = PdfContext(
options, outdir, outdir / 'graph.pdf', None, get_plugin_manager([])
)
metadata_fixup(working_file=outdir / 'graph.pdf', context=context)
for record in caplog.records:
assert record.levelname != 'WARNING'
# Now add some metadata that will not be copyable
graph = pikepdf.open(outdir / 'graph.pdf')
with graph.open_metadata() as meta:
meta['prism2:publicationName'] = 'OCRmyPDF Test'
graph.save(outdir / 'graph_mod.pdf')
context = PdfContext(
options, outdir, outdir / 'graph_mod.pdf', None, get_plugin_manager([])
)
metadata_fixup(working_file=outdir / 'graph.pdf', context=context)
assert any(record.levelname == 'WARNING' for record in caplog.records)
def post_process(pdf_file, context: PdfContext, executor: Executor):
pdf_out = pdf_file
if context.options.output_type.startswith('pdfa'):
ps_stub_out = generate_postscript_stub(context)
pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
pdf_out = metadata_fixup(pdf_out, context)
return optimize_pdf(pdf_out, context, executor)
def test_metadata_fixup_warning(resources, outdir, caplog):
from ocrmypdf._pipeline import metadata_fixup
input_files = [
str(outdir / 'graph.repaired.pdf'),
str(outdir / 'layers.rendered.pdf'),
str(outdir / 'pdfa.pdf'), # It is okay that this is not a PDF/A
]
for f in input_files:
copyfile(resources / 'graph.pdf', f)
log = logging.getLogger()
context = MagicMock()
metadata_fixup(
input_files_groups=input_files,
output_file=outdir / 'out.pdf',
log=log,
context=context,
)
for record in caplog.records:
assert record.levelname != 'WARNING'
# Now add some metadata that will not be copyable
with pikepdf.open(outdir / 'graph.repaired.pdf') as graph:
with graph.open_metadata() as meta:
meta['prism2:publicationName'] = 'OCRmyPDF Test'
graph.save(outdir / 'graph.repaired.modified.pdf')
move(outdir / 'graph.repaired.modified.pdf', outdir / 'graph.repaired.pdf')
log = logging.getLogger()
context = MagicMock()
metadata_fixup(
input_files_groups=input_files,
output_file=outdir / 'out.pdf',
log=log,
context=context,
)
assert any(record.levelname == 'WARNING' for record in caplog.records)
def test_metadata_fixup_warning(resources, outdir, caplog):
from ocrmypdf._pipeline import metadata_fixup
input_files = [
str(outdir / 'graph.repaired.pdf'),
str(outdir / 'layers.rendered.pdf'),
str(outdir / 'pdfa.pdf'), # It is okay that this is not a PDF/A
]
for f in input_files:
copyfile(resources / 'graph.pdf', f)
log = logging.getLogger()
context = MagicMock()
metadata_fixup(
input_files_groups=input_files,
output_file=outdir / 'out.pdf',
log=log,
context=context,
)
for record in caplog.records:
assert record.levelname != 'WARNING'
# Now add some metadata that will not be copyable
graph = pikepdf.open(outdir / 'graph.repaired.pdf')
with graph.open_metadata() as meta:
meta['prism2:publicationName'] = 'OCRmyPDF Test'
graph.save(outdir / 'graph.repaired.pdf')
log = logging.getLogger()
context = MagicMock()
metadata_fixup(
input_files_groups=input_files,
output_file=outdir / 'out.pdf',
log=log,
context=context,
)
assert any(record.levelname == 'WARNING' for record in caplog.records)
def test_metadata_fixup_warning(resources, outdir):
from ocrmypdf._pipeline import metadata_fixup
input_files = [
str(outdir / 'graph.repaired.pdf'),
str(outdir / 'layers.rendered.pdf'),
str(outdir / 'pdfa.pdf'), # It is okay that this is not a PDF/A
]
for f in input_files:
copyfile(resources / 'graph.pdf', f)
log = MagicMock()
context = MagicMock()
metadata_fixup(
input_files_groups=input_files,
output_file=outdir / 'out.pdf',
log=log,
context=context,
)
log.warning.assert_not_called()
# Now add some metadata that will not be copyable
graph = pikepdf.open(outdir / 'graph.repaired.pdf')
with graph.open_metadata() as meta:
meta['prism2:publicationName'] = 'OCRmyPDF Test'
graph.save(outdir / 'graph.repaired.pdf')
log = MagicMock()
context = MagicMock()
metadata_fixup(
input_files_groups=input_files,
output_file=outdir / 'out.pdf',
log=log,
context=context,
)
log.warning.assert_called_once()
