tokenization_sparse.py

from transformers.models.roformer.tokenization_roformer import (WordpieceTokenizer, whitespace_tokenize,
                                                                RoFormerTokenizer)


# Copied from transformers.models.roformer.tokenization_roformer.BasicTokenizer._is_chinese_char
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


# Modified from transformers.models.roformer.tokenization_roformer.WordpieceTokenizer
class ChineseWordpieceTokenizer(WordpieceTokenizer):
    def tokenize(self, text):
        """
        Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
        tokenization using the given vocabulary.

        For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.

        Args:
            text: A single token or whitespace separated tokens. This should have
                already been passed through *BasicTokenizer*.

        Returns:
            A list of wordpiece tokens.
        """

        output_tokens = []
        for token in whitespace_tokenize(text):
            chars = list(token)
            if len(chars) > self.max_input_chars_per_word:
                output_tokens.append(self.unk_token)
                continue

            is_bad = False
            start = 0
            sub_tokens = []
            while start < len(chars):
                end = len(chars)
                cur_substr = None
                while start < end:
                    substr = "".join(chars[start:end])
                    if start > 0 and not _is_chinese_char(ord(substr[0])):  # only add ## when not Chinese character
                        substr = "##" + substr
                    if substr in self.vocab:
                        cur_substr = substr
                        break
                    end -= 1
                if cur_substr is None:
                    is_bad = True
                    break
                sub_tokens.append(cur_substr)
                start = end

            if is_bad:
                output_tokens.append(self.unk_token)
            else:
                output_tokens.extend(sub_tokens)
        return output_tokens


class ChineseRoFormerTokenizer(RoFormerTokenizer):
    def __init__(
            self,
            vocab_file,
            do_lower_case=True,
            do_basic_tokenize=True,
            never_split=None,
            unk_token="[UNK]",
            sep_token="[SEP]",
            pad_token="[PAD]",
            cls_token="[CLS]",
            mask_token="[MASK]",
            tokenize_chinese_chars=False,
            strip_accents=None,
            **kwargs,
    ):
        super().__init__(
            vocab_file=vocab_file,
            do_lower_case=do_lower_case,
            do_basic_tokenize=do_basic_tokenize,
            never_split=never_split,
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            tokenize_chinese_chars=tokenize_chinese_chars,
            strip_accents=strip_accents,
            **kwargs,
        )
        self.wordpiece_tokenizer = ChineseWordpieceTokenizer(vocab=self.vocab, unk_token=str(unk_token))