A function to find non Turkish characters in text.

invalid_chars.py

alpha = 'ABC\xc3\x87DEFG\xc4\x9eHI\xc4\xb0JKLMNO\xc3\x96PRS\xc5\x9eTU' \
        '\xc3\x9cVYZabc\xc3\xa7defg\xc4\x9fh\xc4\xb1ijklmno\xc3' \
        '\xb6prs\xc5\x9ftu\xc3\xbcvyz'.decode('utf-8')


def invalid_chars(text, charset=alpha):
    return set(filter(lambda c: c not in charset, list(text)))


invalid_chars(u'üğüğüp0*2')
{u'*', u'0', u'2'}