Remove whitespaces in UTF-8 CJK string, by regex

remove_cjk_whitespace.py

import re

HANZI = r'([\u4E00-\u9FFF]|[\u3400-\u4DBF]|[\U00020000-\U0002A6DF]|[\U0002A700-\U0002B73F]|[\U0002B740-\U0002B81F]|[\U0002B820-\U0002CEAF]|[\uF900-\uFAFF]|[\U0002F800-\U0002FA1F])'

CJK_WHITESPACE_REGEX = re.compile(r'(?P<c>[\u2E80-\u9FFF])(\s+)')


def remove_cjk_whitespace(s):  # type: (str)->str
    """删除字符串中 CJK 文字之间的空格

    :param s: 要处理的字符串

        .. important:: **必须** 是 `UTF-8` 编码，否则工作会不正常

    :return: 删除空格后的字符串
    
    see: https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
    """
    return re.sub(CJK_WHITESPACE_REGEX, r'\g<c>', s.strip())