AI 杂货铺

最近在看BERT源码，发现了几个很有意思的代码：
使用python 判断是否为中文、标点、空白字符等

• 判断是否为标点

def _is_punctuation(char):
  """Checks whether `chars` is a punctuation character."""
  cp = ord(char)
  # We treat all non-letter/number ASCII as punctuation.
  # Characters such as "^", "$", and "`" are not in the Unicode
  # Punctuation class but we treat them as punctuation anyways, for
  # consistency.
  if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or
      (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)):
    return True
  cat = unicodedata.category(char)
  if cat.startswith("P"):
    return True
  return False

• 判断是否为中文

  def _is_chinese_char(self, char):
    """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.
    cp = ord(char)
    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

• 判断空白字符

def _is_whitespace(char):
  """Checks whether `chars` is a whitespace character."""
  # \t, \n, and \r are technically contorl characters but we treat them
  # as whitespace since they are generally considered as such.
  if char == " " or char == "\t" or char == "\n" or char == "\r":
    return True
  cat = unicodedata.category(char)
  if cat == "Zs":
    return True
  return False


def _is_control(char):
  """Checks whether `chars` is a control character."""
  # These are technically control characters but we count them as whitespace
  # characters.
  if char == "\t" or char == "\n" or char == "\r":
    return False
  cat = unicodedata.category(char)
  if cat in ("Cc", "Cf"):
    return True
  return False