def get_orientation(input_file, options):
with patch_tesseract_run():
return TesseractOcrEngine.get_orientation(input_file, options)
def generate_pdf(input_file, output_pdf, output_text, options):
with patch_tesseract_run():
TesseractOcrEngine.generate_pdf(
input_file, output_pdf, output_text, options
)
def generate_pdf(input_file, output_pdf, output_text, options):
with patch('ocrmypdf._exec.tesseract.run',
new=partial(cached_run, options)):
TesseractOcrEngine.generate_pdf(input_file, output_pdf,
output_text, options)
def cached_run(options, run_args, **run_kwargs):
run_args = [str(arg) for arg in run_args] # flatten PosixPaths
args = parser.parse_args(run_args[1:])
if args.imagename in ('stdin', '-'):
return run(run_args, **run_kwargs)
source_file = options.input_file
cache_folder = get_cache_folder(source_file, run_args, args)
cache_folder.mkdir(parents=True, exist_ok=True)
log.debug(f"Using Tesseract cache {cache_folder}")
if (cache_folder / 'stderr.bin').exists():
log.debug("Cache HIT")
# Replicate stdout/err
if args.outputbase != 'stdout':
if not args.configfiles:
args.configfiles.append('txt')
for configfile in args.configfiles:
# cp cache -> output
tessfile = args.outputbase + '.' + configfile
shutil.copy(str(cache_folder / configfile) + '.bin', tessfile)
return CompletedProcess(
args=run_args,
returncode=0,
stdout=(cache_folder / 'stdout.bin').read_bytes(),
stderr=(cache_folder / 'stderr.bin').read_bytes(),
)
log.debug("Cache MISS")
cache_kwargs = {
k: v
for k, v in run_kwargs.items() if k not in ('stdout', 'stderr')
}
assert cache_kwargs['check']
try:
p = run(run_args, stdout=PIPE, stderr=PIPE, **cache_kwargs)
except CalledProcessError as e:
log.exception(e)
raise # Pass exception onward
# Update cache
(cache_folder / 'stdout.bin').write_bytes(p.stdout)
(cache_folder / 'stderr.bin').write_bytes(p.stderr)
if args.outputbase != 'stdout':
if not args.configfiles:
args.configfiles.append('txt')
for configfile in args.configfiles:
if configfile not in ('hocr', 'pdf', 'txt'):
continue
# cp pwd/{outputbase}.{configfile} -> {cache}/{configfile}
tessfile = args.outputbase + '.' + configfile
shutil.copy(tessfile, str(cache_folder / configfile) + '.bin')
manifest = {}
manifest['tesseract_version'] = TesseractOcrEngine.version().replace(
'\n', ' ')
manifest['platform'] = platform.platform()
manifest['python'] = platform.python_version()
manifest['argv_slug'] = cache_folder.name
manifest['sourcefile'] = str(Path(source_file).relative_to(TESTS_ROOT))
def clean_sys_argv():
for arg in run_args[1:]:
yield re.sub(r'.*/ocrmypdf[.]io[.][^/]+[/](.*)', r'$TMPDIR/\1',
arg)
manifest['args'] = list(clean_sys_argv())
with (Path(CACHE_ROOT) / 'manifest.jsonl').open('a') as f:
json.dump(manifest, f)
f.write('\n')
f.flush()
return p
def get_orientation(input_file, options):
with patch('ocrmypdf._exec.tesseract.run',
new=partial(cached_run, options)):
return TesseractOcrEngine.get_orientation(input_file, options)
def generate_pdf(input_file, output_pdf, output_text, options):
with patch('ocrmypdf._exec.tesseract.run', new=raise_size_exception):
TesseractOcrEngine.generate_pdf(
input_file, output_pdf, output_text, options
)
def get_orientation(input_file, options):
with patch('ocrmypdf._exec.tesseract.run', new=raise_size_exception):
return TesseractOcrEngine.get_orientation(input_file, options)
def generate_pdf(input_file, output_pdf, output_text, options):
with patch('ocrmypdf._exec.tesseract.run', new=bad_utf8):
TesseractOcrEngine.generate_pdf(input_file, output_pdf,
output_text, options)
def generate_hocr(input_file, output_hocr, output_text, options):
with patch('ocrmypdf._exec.tesseract.run', new=raise_crash):
TesseractOcrEngine.generate_hocr(input_file, output_hocr,
output_text, options)