def test_prevent_gs_invalid_xml(resources, outdir):
from ocrmypdf.__main__ import parser
from ocrmypdf._pipeline import convert_to_pdfa
from ocrmypdf.pdfa import generate_pdfa_ps
from ocrmypdf.pdfinfo import PdfInfo
generate_pdfa_ps(outdir / 'pdfa.ps')
copyfile(resources / 'enron1.pdf', outdir / 'layers.rendered.pdf')
options = parser.parse_args(
args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
)
pdfinfo = PdfInfo(resources / 'enron1.pdf')
context = PDFContext(options, outdir, resources / 'enron1.pdf', pdfinfo)
convert_to_pdfa(
str(outdir / 'layers.rendered.pdf'), str(outdir / 'pdfa.ps'), context
)
with open(outdir / 'pdfa.pdf', 'rb') as f:
with mmap.mmap(
f.fileno(), 0, flags=mmap.MAP_PRIVATE, prot=mmap.PROT_READ
) as mm:
# Since the XML may be invalid, we scan instead of actually feeding it
# to a parser.
XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
xmp_start = mm.find(XMP_MAGIC)
xmp_end = mm.rfind(b'<?xpacket end', xmp_start)
assert 0 < xmp_start < xmp_end
assert mm.find(b'�', xmp_start, xmp_end) == -1, "found escaped nul"
assert mm.find(b'\x00', xmp_start, xmp_end) == -1
def test_metadata_fixup_warning(resources, outdir, caplog):
from ocrmypdf.__main__ import parser
from ocrmypdf._pipeline import metadata_fixup
options = 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)
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)
metadata_fixup(working_file=outdir / 'graph.pdf', context=context)
assert any(record.levelname == 'WARNING' for record in caplog.records)
def test_prevent_gs_invalid_xml(resources, outdir):
from ocrmypdf.__main__ import parser
from ocrmypdf._pipeline import convert_to_pdfa
from ocrmypdf.pdfa import generate_pdfa_ps
from ocrmypdf.pdfinfo import PdfInfo
generate_pdfa_ps(outdir / 'pdfa.ps')
input_files = [str(outdir / 'layers.rendered.pdf'), str(outdir / 'pdfa.ps')]
copyfile(resources / 'enron1.pdf', outdir / 'layers.rendered.pdf')
log = logging.getLogger()
context = JobContext()
options = parser.parse_args(
args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
)
context.options = options
context.pdfinfo = PdfInfo(resources / 'enron1.pdf')
convert_to_pdfa(
input_files_groups=input_files,
output_file=outdir / 'pdfa.pdf',
log=log,
context=context,
)
with open(outdir / 'pdfa.pdf', 'rb') as f:
with mmap.mmap(
f.fileno(), 0, flags=mmap.MAP_PRIVATE, prot=mmap.PROT_READ
) as mm:
# Since the XML may be invalid, we scan instead of actually feeding it
# to a parser.
XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
xmp_start = mm.find(XMP_MAGIC)
xmp_end = mm.rfind(b'<?xpacket end', xmp_start)
assert 0 < xmp_start < xmp_end
assert mm.find(b'�', xmp_start, xmp_end) == -1, "found escaped nul"
assert mm.find(b'\x00', xmp_start, xmp_end) == -1
def test_prevent_gs_invalid_xml(resources, outdir):
from ocrmypdf.cli import parser
from ocrmypdf._pipeline import convert_to_pdfa
from ocrmypdf.pdfa import generate_pdfa_ps
from ocrmypdf.pdfinfo import PdfInfo
generate_pdfa_ps(outdir / 'pdfa.ps')
copyfile(resources / 'trivial.pdf', outdir / 'layers.rendered.pdf')
# Inject a string with a trailing nul character into the DocumentInfo
# dictionary of this PDF, as often occurs in practice.
with pikepdf.open(outdir / 'layers.rendered.pdf') as pike:
pike.Root.DocumentInfo = pikepdf.Dictionary(
Title=b'String with trailing nul\x00')
options = parser.parse_args(
args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf'])
pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf',
pdfinfo)
convert_to_pdfa(str(outdir / 'layers.rendered.pdf'),
str(outdir / 'pdfa.ps'), context)
with open(outdir / 'pdfa.pdf', 'r+b') as f:
with mmap.mmap(f.fileno(), 0) as mm:
# Since the XML may be invalid, we scan instead of actually feeding it
# to a parser.
XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
xmp_start = mm.find(XMP_MAGIC)
xmp_end = mm.rfind(b'<?xpacket end', xmp_start)
assert 0 < xmp_start < xmp_end
# Ensure we did not carry the nul forward.
assert mm.find(b'�', xmp_start,
xmp_end) == -1, "found escaped nul"
assert mm.find(b'\x00', xmp_start, xmp_end) == -1