Search Unicode characters by name

unigrep.py

#!/usr/bin/env python3

import argparse
import re
import unicodedata


def gen_chars(rx, cp_max):
    for i in range(160, cp_max):
        try:
            c = chr(i)
            name = unicodedata.name(c)
            if rx.match(name):
                yield c, name
        except ValueError:
            pass

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('-n', '--names', action='store_true',
                        help='show Unicode names')
    parser.add_argument('-u', '--upper-limit', type=int, default=2**16,
                        help='maximum codepoint number')
    parser.add_argument('match', help='part of Unicode name to match')
    args = parser.parse_args()
    rx = re.compile(r'.*%s.*' % re.escape(args.match), re.IGNORECASE)
    gen = gen_chars(rx, args.upper_limit)
    if args.names:
        for char_name in gen:
            print('%s  %s' % char_name)
    else:
        print(''.join(c for c, n in gen))