def _is_chinese_char()

in mlm_wwm/run_chinese_ref.py [0:0]

• 13 lines of code
• 20 McCabe index (conditional complexity)

def _is_chinese_char(cp):
    """Checks whether CP is the codepoint of a CJK character."""
    # This defines a "chinese character" as anything in the CJK Unicode block:
    #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
    #
    # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
    # despite its name. The modern Korean Hangul alphabet is a different block,
    # as is Japanese Hiragana and Katakana. Those alphabets are used to write
    # space-separated words, so they are not treated specially and handled
    # like the all of the other languages.
    if (
        (cp >= 0x4E00 and cp <= 0x9FFF)
        or (cp >= 0x3400 and cp <= 0x4DBF)  #
        or (cp >= 0x20000 and cp <= 0x2A6DF)  #
        or (cp >= 0x2A700 and cp <= 0x2B73F)  #
        or (cp >= 0x2B740 and cp <= 0x2B81F)  #
        or (cp >= 0x2B820 and cp <= 0x2CEAF)  #
        or (cp >= 0xF900 and cp <= 0xFAFF)
        or (cp >= 0x2F800 and cp <= 0x2FA1F)  #
    ):  #
        return True

    return False