한글의 자모 분리

입력된 문자가 음절인지 확인하고, check_ch_type()

음절인 경우 conv_jaso를 통해 자모 분해 & compatibility_jamo로 변환

import unicodedata

def check_ch_type(ch):

    valid_type = ['Lo']

    if unicodedata.category(ch) in valid_type:

        unicode_names = unicodedata.name(ch).split()

        if 'HANGUL' in unicode_names and 'SYLLABLE' in unicode_names:

            return True

        else:

            return False

    else:

        return False

def conv_jaso(ch=u'각'):

    def conv_compatibility_jamo(ch):

        unicode_names = unicodedata.name(ch)

        # print ch, unicode_names

        if unicode_names.find('CHOSEONG') >= 0:

            unicode_names = unicode_names.replace('CHOSEONG', 'LETTER')

        elif unicode_names.find('JUNGSEONG') >= 0:

            unicode_names = unicode_names.replace('JUNGSEONG', 'LETTER')

        elif unicode_names.find('JONGSEONG') >= 0:

            unicode_names = unicode_names.replace('JONGSEONG', 'LETTER')

        return unicodedata.lookup(unicode_names)

    jaso = []

    ch = ord(ch) - 0xAC00

    jong = ch % 28

    jung = ((ch - jong) / 28) % 21

    cho = (((ch - jong) / 28) - jung) / 21

    # print 'cho :', cho, (unichr(cho + 0x1100)).encode('utf-8')

    # print 'jung :', jung, (unichr(jung + 0x1161)).encode('utf-8')

    # print 'jong :', jong, (unichr(jong + 0x11A7)).encode('utf-8')

    if cho >= 0:

        jaso.append(conv_compatibility_jamo(unichr(cho + 0x1100)))

    if jung >= 0:

        jaso.append(conv_compatibility_jamo(unichr(jung + 0x1161)))

    if jong > 0:

        jaso.append(conv_compatibility_jamo(unichr(jong + 0x11A7)))

    return ''.join(jaso)