目录

FullTokenizer代码

class FullTokenizer(object):
  """Runs end-to-end tokenziation."""

  def __init__(self, vocab_file, do_lower_case=True):
    self.vocab = load_vocab(vocab_file)
    self.inv_vocab = {v: k for k, v in self.vocab.items()}
    self.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case)
    self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab)

  def tokenize(self, text):
    split_tokens = []
    for token in self.basic_tokenizer.tokenize(text):
      for sub_token in self.wordpiece_tokenizer.tokenize(token):
        split_tokens.append(sub_token)

    return split_tokens

  def convert_tokens_to_ids(self, tokens):
    return convert_by_vocab(self.vocab, tokens)

  def convert_ids_to_tokens(self, ids):
    return convert_by_vocab(self.inv_vocab, ids)

字符判断的代码

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.startswith("C"):
    return True
  return False


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

load_vocab代码


def load_vocab(vocab_file):
  """Loads a vocabulary file into a dictionary."""
  vocab = collections.OrderedDict()
  index = 0
  with tf.gfile.GFile(vocab_file, "r") as reader:
    while True:
      token = convert_to_unicode(reader.readline())
      if not token:
        break
      token = token.strip()
      vocab[token] = index
      index += 1
  return vocab

BasicTokenizer代码

class BasicTokenizer(object):
  """Runs basic tokenization (punctuation splitting, lower casing, etc.)."""

  def __init__(self, do_lower_case=True):
    """Constructs a BasicTokenizer.

    Args:
      do_lower_case: Whether to lower case the input.
    """
    self.do_lower_case = do_lower_case

  def tokenize(self, text):
    """Tokenizes a piece of text."""
    text = convert_to_unicode(text)
    text = self._clean_text(text)

    # This was added on November 1st, 2018 for the multilingual and Chinese
    # models. This is also applied to the English models now, but it doesn't
    # matter since the English models were not trained on any Chinese data
    # and generally don't have any Chinese data in them (there are Chinese
    # characters in the vocabulary because Wikipedia does have some Chinese
    # words in the English Wikipedia.).
    text = self._tokenize_chinese_chars(text)

    orig_tokens = whitespace_tokenize(text)
    split_tokens = []
    for token in orig_tokens:
      if self.do_lower_case:
        token = token.lower()
        token = self._run_strip_accents(token)
      split_tokens.extend(self._run_split_on_punc(token))

    output_tokens = whitespace_tokenize(" ".join(split_tokens))
    return output_tokens

  def _run_strip_accents(self, text):
    """Strips accents from a piece of text."""
    text = unicodedata.normalize("NFD", text)
    output = []
    for char in text:
      cat = unicodedata.category(char)
      if cat == "Mn":
        continue
      output.append(char)
    return "".join(output)

  def _run_split_on_punc(self, text):
    """Splits punctuation on a piece of text."""
    chars = list(text)
    i = 0
    start_new_word = True
    output = []
    while i < len(chars):
      char = chars[i]
      if _is_punctuation(char):
        output.append([char])
        start_new_word = True
      else:
        if start_new_word:
          output.append([])
        start_new_word = False
        output[-1].append(char)
      i += 1

    return ["".join(x) for x in output]

  def _tokenize_chinese_chars(self, text):
    """Adds whitespace around any CJK character."""
    output = []
    for char in text:
      cp = ord(char)
      if self._is_chinese_char(cp):
        output.append(" ")
        output.append(char)
        output.append(" ")
      else:
        output.append(char)
    return "".join(output)

  def _is_chinese_char(self, 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

  def _clean_text(self, text):
    """Performs invalid character removal and whitespace cleanup on text."""
    output = []
    for char in text:
      cp = ord(char)
      if cp == 0 or cp == 0xfffd or _is_control(char):
        continue
      if _is_whitespace(char):
        output.append(" ")
      else:
        output.append(char)
    return "".join(output)

vocab_file内容截取

...
予
争
事
二
于
亏
云
互
五
井
亘
...