def validate_pdfinfo_options(context: PdfContext):
pdfinfo = context.pdfinfo
options = context.options
if pdfinfo.needs_rendering:
log.error(
"This PDF contains dynamic XFA forms created by Adobe LiveCycle "
"Designer and can only be read by Adobe Acrobat or Adobe Reader.")
raise InputFileError()
if pdfinfo.has_userunit and options.output_type.startswith('pdfa'):
log.error(
"This input file uses a PDF feature that is not supported "
"by Ghostscript, so you cannot use --output-type=pdfa for this "
"file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
"support very large or small page sizes, and Ghostscript cannot "
"output these files.) Use --output-type=pdf instead.")
raise InputFileError()
if pdfinfo.has_acroform:
if options.redo_ocr:
log.error("This PDF has a user fillable form. --redo-ocr is not "
"currently possible on such files.")
raise InputFileError()
else:
log.warning("This PDF has a fillable form. "
"Chances are it is a pure digital "
"document that does not need OCR.")
if not options.force_ocr:
log.info(
"Use the option --force-ocr to produce an image of the "
"form and all filled form fields. The output PDF will be "
"'flattened' and will no longer be fillable.")
context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
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 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 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 get_pdfinfo(
input_file,
detailed_analysis=False,
progbar=False,
max_workers=None,
check_pages=None,
):
try:
return PdfInfo(
input_file,
detailed_analysis=detailed_analysis,
progbar=progbar,
max_workers=max_workers,
check_pages=check_pages,
)
except pikepdf.PasswordError:
raise EncryptedPdfError()
except pikepdf.PdfError:
raise InputFileError()
def get_page_analysis(infile, pageno, pscript5_mode):
rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
if pdfminer.__version__ < '20200402':
# Workaround for https://github.com/pdfminer/pdfminer.six/issues/395
disable_boxes_flow = 2
else:
disable_boxes_flow = None
dev = TextPositionTracker(
rman,
laparams=LAParams(all_texts=True,
detect_vertical=True,
boxes_flow=disable_boxes_flow),
)
interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
patcher = None
if pscript5_mode:
patcher = patch.multiple(
'pdfminer.pdffont.PDFType3Font',
spec=True,
get_ascent=PDFType3Font__PScript5_get_ascent,
get_descent=PDFType3Font__PScript5_get_descent,
get_height=PDFType3Font__PScript5_get_height,
)
patcher.start()
try:
with Path(infile).open('rb') as f:
page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
page = next(page_iter, None)
if page is None:
raise InputFileError(
f"pdfminer could not process page {pageno} (counting from 0)."
)
interp.process_page(page)
except PDFTextExtractionNotAllowed as e:
raise EncryptedPdfError() from e
finally:
if patcher is not None:
patcher.stop()
return dev.get_result()
def get_pdfinfo(
input_file,
*,
executor: Executor,
detailed_analysis=False,
progbar=False,
max_workers=None,
check_pages=None,
) -> PdfInfo:
try:
return PdfInfo(
input_file,
detailed_analysis=detailed_analysis,
progbar=progbar,
max_workers=max_workers,
check_pages=check_pages,
executor=executor,
)
except pikepdf.PasswordError as e:
raise EncryptedPdfError() from e
except pikepdf.PdfError as e:
raise InputFileError() from e
def process_sigbus(*args):
raise InputFileError("A worker process lost access to an input file")
def sigbus(*args):
raise InputFileError("Lost access to the input file")
def update_pageinfo(result, pbar):
page = result
if not page:
raise InputFileError("Could read a page in the PDF")
pages[page.pageno] = page
pbar.update()
