Class BasicTokenizer

bert/tokenization_bert.py:348–484

Runs basic tokenization (punctuation splitting, lower casing, etc.).

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

    def __init__(self, do_lower_case=True, never_split=None, tokenize_chinese_chars=True):
        """ Constructs a BasicTokenizer.

        Args:
            **do_lower_case**: Whether to lower case the input.
            **never_split**: (`optional`) list of str
                Kept for backward compatibility purposes.
                Now implemented directly at the base class level (see :func:`PreTrainedTokenizer.tokenize`)
                List of token not to split.
            **tokenize_chinese_chars**: (`optional`) boolean (default True)
                Whether to tokenize Chinese characters.
                This should likely be deactivated for Japanese:
                see: https://github.com/huggingface/pytorch-pretrained-BERT/issues/328
        """
        if never_split is None:
            never_split = []
        self.do_lower_case = do_lower_case
        self.never_split = set(never_split)
        self.tokenize_chinese_chars = tokenize_chinese_chars

    def tokenize(self, text, never_split=None):
        """ Basic Tokenization of a piece of text.
            Split on "white spaces" only, for sub-word tokenization, see WordPieceTokenizer.

        Args:
            **never_split**: (`optional`) list of str
                Kept for backward compatibility purposes.
                Now implemented directly at the base class level (see :func:`PreTrainedTokenizer.tokenize`)
                List of token not to split.
        """
        # union() returns a new set by concatenating the two sets.
        never_split = self.never_split.union(set(never_split)) if never_split else self.never_split

        # 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.).
        if self.tokenize_chinese_chars:
            text = self._tokenize_chinese_chars(text)
        orig_tokens = whitespace_tokenize(text)
        split_tokens = []
        for token in orig_tokens:
            if self.do_lower_case and token not in never_split:
                token = token.lower()
                token = self._run_strip_accents(token)
            split_tokens.extend(self._run_split_on_punc(token, never_split))

        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)