def main():
ocrmypdf.configure_logging(verbosity=ocrmypdf.Verbosity.default,
manage_root_logger=True)
log.info(f"Starting OCRmyPDF watcher with config:\n"
f"Input Directory: {INPUT_DIRECTORY}\n"
f"Output Directory: {OUTPUT_DIRECTORY}\n"
f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}")
log.debug(f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
f"DESKEW: {DESKEW}\n"
f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
f"LOGLEVEL: {LOGLEVEL}\n")
handler = HandleObserverEvent(patterns=PATTERNS)
observer = Observer()
observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
observer.start()
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
observer.stop()
observer.join()
def main():
ocrmypdf.configure_logging(
verbosity=ocrmypdf.Verbosity.default, manage_root_logger=True
)
log.setLevel(LOGLEVEL)
log.info(
f"Starting OCRmyPDF watcher with config:\n"
f"Input Directory: {INPUT_DIRECTORY}\n"
f"Output Directory: {OUTPUT_DIRECTORY}\n"
f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}"
)
log.debug(
f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
f"DESKEW: {DESKEW}\n"
f"ARGS: {OCR_JSON_SETTINGS}\n"
f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
f"USE_POLLING: {USE_POLLING}\n"
f"LOGLEVEL: {LOGLEVEL}\n"
)
if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
log.error('OCR_JSON_SETTINGS should not specify input file or output file')
sys.exit(1)
handler = HandleObserverEvent(patterns=PATTERNS)
if USE_POLLING:
observer = PollingObserver()
else:
observer = Observer()
observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
observer.start()
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
observer.stop()
observer.join()
def pdf2pdfa(args):
ok = False
if args['mime_type'] == 'application/pdf':
args['tmp_file_path'] = args['source_file_path']
# WAIT: Legg inn ekstra sjekk her om hva som skal gjøres hvis ocr = True
if args['version'] in ('1a', '1b', '2a', '2b'):
file_copy(args)
if os.path.exists(args['norm_file_path']):
ok = True
return ok
ocrmypdf.configure_logging(-1)
result = ocrmypdf.ocr(args['tmp_file_path'],
args['norm_file_path'],
tesseract_timeout=0,
progress_bar=False,
skip_text=True)
if str(result) == 'ExitCode.ok':
ok = True
return ok
else:
start_dir = '.'
if len(sys.argv) > 2:
log_file = sys.argv[2]
else:
log_file = script_dir + '/ocr-tree.log'
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s %(message)s',
filename=log_file,
filemode='w',
)
ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
for dir_name, _subdirs, file_list in os.walk(start_dir):
logging.info(dir_name + '\n')
os.chdir(dir_name)
for filename in file_list:
file_ext = os.path.splitext(filename)[1]
if file_ext == '.pdf':
full_path = dir_name + '/' + filename
print(full_path)
result = ocrmypdf.ocr(filename, filename, deskew=True)
if result == ocrmypdf.ExitCode.already_done_ocr:
print("Skipped document because it already contained text")
elif result == ocrmypdf.ExitCode.ok:
print("OCR complete")
logging.info(result)