초성 검색 : Unicode Study

chosung.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

chosungs = [u'ㄱ', u'ㄲ', u'ㄴ', u'ㄷ', u'ㄸ', u'ㄹ', u'ㅁ', u'ㅂ', u'ㅃ',
            u'ㅅ', u'ㅆ', u'ㅇ', u'ㅈ', u'ㅉ', u'ㅊ', u'ㅋ', u'ㅌ', u'ㅍ',
            u'ㅎ']
jungsungs = [u'ㅏ', u'ㅐ', u'ㅑ', u'ㅒ', u'ㅓ', u'ㅔ', u'ㅕ', u'ㅖ', u'ㅗ',
             u'ㅘ', u'ㅙ', u'ㅚ', u'ㅛ', u'ㅜ', u'ㅝ', u'ㅞ', u'ㅟ', u'ㅠ',
             u'ㅡ', u'ㅢ', u'ㅣ']
jongsungs = [u'', u'ㄱ', u'ㄲ', u'ㄳ', u'ㄴ', u'ㄵ', u'ㄶ', u'ㄷ', u'ㄹ',
             u'ㄺ', u'ㄻ', u'ㄼ', u'ㄽ', u'ㄾ', u'ㄿ', u'ㅀ', u'ㅁ', u'ㅂ',
             u'ㅄ', u'ㅅ', u'ㅆ', u'ㅇ', u'ㅈ', u'ㅊ', u'ㅋ', u'ㅌ', u'ㅍ',
             u'ㅎ']

CHO_LEN, JUNG_LEN, JONG_LEN = len(chosungs), len(jungsungs), len(jongsungs)
HAN_FST, HAN_LST = ord(u'가'), ord(u'힣')
JAUM_FST, JAUM_LST = ord(u'ㄱ'), ord(u'ㅎ')


def cho_jung_jong(han_char):
    code_point = ord(han_char)
    if HAN_FST <= code_point <= HAN_LST:
        code_diff = code_point - HAN_FST
        cho_idx = (code_diff / (JONG_LEN * JUNG_LEN)) % CHO_LEN
        jung_idx = (code_diff / JONG_LEN) % JUNG_LEN
        jong_idx = code_diff % JONG_LEN
        return (chosungs[cho_idx], jungsungs[jung_idx], jongsungs[jong_idx])
    elif JAUM_FST <= code_point <= JAUM_LST:
        cho_idx = code_point - JAUM_FST
        return (chosungs[cho_idx], '', '')
    else:
        return ('', '', '')


def parse_chosung(han_str):
    return ''.join([cho_jung_jong(i)[0] for i in han_str])


def compare_chosung(i, target):
    i, target = i.replace(' ', ''), target.replace(' ', '')
    return (i in target) or (i in parse_chosung(target))


def main():
    contacts = [i.decode('utf-8') for i in open('contacts.txt').readlines()]
    print ''.join([i for i in contacts])
    my_input = unicode(raw_input('search: '), 'utf-8')
    matches = [nm for nm in contacts if compare_chosung(my_input, nm)]
    print ', '.join(matches)

if __name__ == '__main__':
    main()

contacts.txt

김애란
김창완
김훈
밥 딜런
빈센트 반 고흐
장필순
클로드 모네