def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
if options.input_file == '-':
# stdin
log.info('reading file from standard input')
target = work_folder / 'stdin'
with open(target, 'wb') as stream_buffer:
copyfileobj(sys.stdin.buffer, stream_buffer)
return target, "stdin"
elif hasattr(options.input_file, 'readable'):
if not options.input_file.readable():
raise InputFileError("Input file stream is not readable")
log.info('reading file from input stream')
target = work_folder / 'stream'
with open(target, 'wb') as stream_buffer:
copyfileobj(options.input_file, stream_buffer)
return target, "stream"
else:
try:
target = work_folder / 'origin'
safe_symlink(options.input_file, target)
return target, os.fspath(options.input_file)
except FileNotFoundError:
msg = f"File not found - {options.input_file}"
if Path('/.dockerenv').exists(): # pragma: no cover
msg += (
"\nDocker cannot your working directory unless you "
"explicitly share it with the Docker container and set up"
"permissions correctly.\n"
"You may find it easier to use stdin/stdout:"
"\n"
"\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
)
raise InputFileError(msg)
def test_safe_symlink_relink(self, tmp_path):
(tmp_path / 'regular_file_a').touch()
(tmp_path / 'regular_file_b').write_bytes(b'ABC')
(tmp_path / 'link').symlink_to(tmp_path / 'regular_file_a')
helpers.safe_symlink(tmp_path / 'regular_file_b', tmp_path / 'link')
assert (tmp_path / 'link').samefile(
tmp_path / 'regular_file_b') or (tmp_path /
'link').read_bytes() == b'ABC'
def optimize(
input_file: Path,
output_file: Path,
context,
save_settings,
executor: Executor = SerialExecutor(),
) -> None:
options = context.options
if options.optimize == 0:
safe_symlink(input_file, output_file)
return
if options.jpeg_quality == 0:
options.jpeg_quality = DEFAULT_JPEG_QUALITY if options.optimize < 3 else 40
if options.png_quality == 0:
options.png_quality = DEFAULT_PNG_QUALITY if options.optimize < 3 else 30
if options.jbig2_page_group_size == 0:
options.jbig2_page_group_size = 10 if options.jbig2_lossy else 1
with pikepdf.Pdf.open(input_file) as pike:
root = output_file.parent / 'images'
root.mkdir(exist_ok=True)
jpegs, pngs = extract_images_generic(pike, root, options)
transcode_jpegs(pike, jpegs, root, options, executor)
# if options.optimize >= 2:
# Try pngifying the jpegs
# transcode_pngs(pike, jpegs, jpg_name, root, options)
transcode_pngs(pike, pngs, png_name, root, options, executor)
jbig2_groups = extract_images_jbig2(pike, root, options)
convert_to_jbig2(pike, jbig2_groups, root, options, executor)
target_file = output_file.with_suffix('.opt.pdf')
pike.remove_unreferenced_resources()
pike.save(target_file, **save_settings)
input_size = input_file.stat().st_size
output_size = target_file.stat().st_size
if output_size == 0:
raise OutputFileAccessError(
f"Output file not created after optimizing. We probably ran "
f"out of disk space in the temporary folder: {tempfile.gettempdir()}."
)
ratio = input_size / output_size
savings = 1 - output_size / input_size
log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
if savings < 0:
log.info("Image optimization did not improve the file - discarded")
# We still need to save the file
with pikepdf.open(input_file) as pike:
pike.remove_unreferenced_resources()
pike.save(output_file, **save_settings)
else:
safe_symlink(target_file, output_file)
def create_input_file(options, work_folder: Path) -> (Path, str):
if options.input_file == '-':
# stdin
log.info('reading file from standard input')
target = work_folder / 'stdin'
with open(target, 'wb') as stream_buffer:
copyfileobj(sys.stdin.buffer, stream_buffer)
return target, "<stdin>"
else:
try:
target = work_folder / 'origin'
safe_symlink(options.input_file, target)
return target, os.fspath(options.input_file)
except FileNotFoundError:
raise InputFileError(f"File not found - {options.input_file}")
def triage(original_filename, input_file, output_file, options):
try:
if _pdf_guess_version(input_file):
if options.image_dpi:
log.warning(
"Argument --image-dpi is being ignored because the "
"input file is a PDF, not an image.")
# Origin file is a pdf create a symlink with pdf extension
safe_symlink(input_file, output_file)
return output_file
except EnvironmentError as e:
log.debug(f"Temporary file was at: {input_file}")
msg = str(e).replace(str(input_file), original_filename)
raise InputFileError(msg) from e
triage_image_file(input_file, output_file, options)
return output_file
def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
options = context.options
input_pdfinfo = context.pdfinfo
fix_docinfo_file = context.get_path('fix_docinfo.pdf')
output_file = context.get_path('pdfa.pdf')
# If the DocumentInfo record contains NUL characters, Ghostscript will
# produce XMP metadata which contains invalid XML entities (�).
# NULs in DocumentInfo seem to be common since older Acrobats included them.
# pikepdf can deal with this, but we make the world a better place by
# stamping them out as soon as possible.
modified = False
with pikepdf.open(input_pdf) as pdf_file:
try:
len(pdf_file.docinfo)
except TypeError:
log.error(
"File contains a malformed DocumentInfo block - continuing anyway"
)
else:
if pdf_file.docinfo:
for k, v in pdf_file.docinfo.items():
if b'\x00' in bytes(v):
pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
modified = True
if modified:
pdf_file.save(fix_docinfo_file)
else:
safe_symlink(input_pdf, fix_docinfo_file)
context.plugin_manager.hook.generate_pdfa(
pdf_version=input_pdfinfo.min_version,
pdf_pages=[fix_docinfo_file],
pdfmark=input_ps_stub,
output_file=output_file,
compression=options.pdfa_image_compression,
pdfa_part=options.output_type[-1], # is pdfa-1, pdfa-2, or pdfa-3
progressbar_class=(context.plugin_manager.hook.get_progressbar_class()
if options.progress_bar else None),
)
return output_file
def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
if options.input_file == '-':
# stdin
log.info('reading file from standard input')
target = work_folder / 'stdin'
with open(target, 'wb') as stream_buffer:
copyfileobj(sys.stdin.buffer, stream_buffer)
return target, "stdin"
elif hasattr(options.input_file, 'readable'):
if not options.input_file.readable():
raise InputFileError("Input file stream is not readable")
log.info('reading file from input stream')
target = work_folder / 'stream'
with open(target, 'wb') as stream_buffer:
copyfileobj(options.input_file, stream_buffer)
return target, "stream"
else:
try:
target = work_folder / 'origin'
safe_symlink(options.input_file, target)
return target, os.fspath(options.input_file)
except FileNotFoundError:
raise InputFileError(f"File not found - {options.input_file}")
def test_safe_symlink_overwrite(self, tmp_path):
(tmp_path / 'regular_file').touch()
with pytest.raises(FileExistsError):
helpers.safe_symlink(tmp_path / 'input', tmp_path / 'regular_file')
def test_safe_symlink_link_self(self, tmp_path, caplog):
helpers.safe_symlink(tmp_path / 'self', tmp_path / 'self')
assert caplog.record_tuples[0][1] == logging.WARNING
