Monkeytype Ukrainian to Latin transliteration

uk2lat_json.py

#!/usr/bin/env python
import json
import logging
import re
import uklatn
from pathlib import Path


logger = logging.getLogger(Path(__file__).name)


def uk2latn(s, table=None):
    s = uklatn.encode(s, table=table)
    s = re.sub(r'^ĵ', 'j', s)
    return s


def process(obj, table=None):
    obj['name'] = obj['name'].replace('ukrainian', 'ukrainian_latynka')
    obj['words'] = list({uk2latn(w, table):0 for w in obj['words']})
    return obj


def main(args):
    table = getattr(uklatn, args.table.upper())
    for fn in args.file:
        logger.debug(f'read {fn}')
        with Path(fn).open() as fp:
            obj = json.load(fp)
        res = process(obj, table=table)
        fo = Path(fn).with_stem(Path(fn).stem.replace('ukrainian', 'ukrainian_latynka'))
        logger.debug(f'write {fo}')
        with fo.open('w') as fp:
            json.dump(res, fp, indent=2, ensure_ascii=False)
            fp.write('\n')


if __name__ == '__main__':
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('file', nargs='+', help='json file to transliterate')
    parser.add_argument('-t', '--table', choices=['DSTU_9112_A', 'DSTU_9112_B', 'KMU_55'],
        default='DSTU_9112_A', help='transliteration system (default: %(default)s)')
    parser.add_argument('-v', '--verbose', action='store_true',
        help='verbose output')

    args = parser.parse_args()

    level = logging.DEBUG if args.verbose else logging.WARNING
    logging.basicConfig(level=level)

    main(args)