printing-friendly repr string for CJK characters.

readable_repr.py

# coding: utf8

import re

REPR_UNICODE_CHAR = re.compile(r'(?<!\\)(\\u[0-9a-f]{4,4})')


def readable_repr(obj):
    '''Return printing-friendly unicode string

    >>> u = u'cjk 中日韩 \\u535a'
    >>> u
    u'cjk \u4e2d\u65e5\u97e9 \\u535a'
    >>> repr(u)
    "u'cjk \\u4e2d\\u65e5\\u97e9 \\\\u535a'"
    >>> readable_repr(u)
    u"u'cjk \u4e2d\u65e5\u97e9 \\\\u535a'"
    >>> print repr(u)
    u'cjk \u4e2d\u65e5\u97e9 \\u535a'
    >>> print readable_repr(u)
    u'cjk 中日韩 \\u535a'
    '''
    
    def replace_unicode_char(repr_char):
        return unichr(int(str(repr_char.group())[2:], base=16))

    repr_string = repr(obj)
    return REPR_UNICODE_CHAR.sub(replace_unicode_char, repr_string)