tokenization_rnaernie2.py

import os
from transformers import PreTrainedTokenizer


_VOCAB = {
    "[PAD]": 0,
    "[UNK]": 1,
    "[CLS]": 2,
    "[EOS]": 3,
    "[SEP]": 4,
    "[MASK]": 5,
    "A": 6,
    "U": 7,
    "C": 8,
    "G": 9,
    "N": 10,
}


class RNAErnie2Tokenizer(PreTrainedTokenizer):
    """Character-level RNA tokenizer for RNAErnie2.

    Vocab (11 tokens): [PAD]=0, [UNK]=1, [CLS]=2, [EOS]=3, [SEP]=4, [MASK]=5,
    A=6, U=7, C=8, G=9, N=10.
    Sequences are wrapped [CLS] + tokens + [SEP].
    T is silently converted to U (RNA convention).
    """

    vocab_files_names = {"vocab_file": "vocab.txt"}
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file=None,
        pad_token="[PAD]",
        unk_token="[UNK]",
        cls_token="[CLS]",
        eos_token="[EOS]",
        sep_token="[SEP]",
        mask_token="[MASK]",
        **kwargs,
    ):
        self._vocab = {}
        if vocab_file and os.path.isfile(vocab_file):
            with open(vocab_file, encoding="utf-8") as f:
                for idx, line in enumerate(f):
                    token = line.rstrip("\n")
                    self._vocab[token] = idx
        else:
            self._vocab = dict(_VOCAB)
        self._ids_to_tokens = {v: k for k, v in self._vocab.items()}

        super().__init__(
            pad_token=pad_token,
            unk_token=unk_token,
            cls_token=cls_token,
            eos_token=eos_token,
            sep_token=sep_token,
            mask_token=mask_token,
            **kwargs,
        )

    @property
    def vocab_size(self):
        return len(self._vocab)

    def get_vocab(self):
        return dict(self._vocab)

    def _tokenize(self, text):
        return list(text.upper().replace("T", "U"))

    def _convert_token_to_id(self, token):
        return self._vocab.get(token, self._vocab.get("[UNK]", 1))

    def _convert_id_to_token(self, index):
        return self._ids_to_tokens.get(index, "[UNK]")

    def save_vocabulary(self, save_directory, filename_prefix=None):
        os.makedirs(save_directory, exist_ok=True)
        fname = (filename_prefix + "-" if filename_prefix else "") + "vocab.txt"
        path = os.path.join(save_directory, fname)
        with open(path, "w", encoding="utf-8") as f:
            for token, _ in sorted(self._vocab.items(), key=lambda x: x[1]):
                f.write(token + "\n")
        return (path,)

    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
        cls = [self.cls_token_id]
        sep = [self.sep_token_id]
        if token_ids_1 is None:
            return cls + token_ids_0 + sep
        return cls + token_ids_0 + sep + token_ids_1 + sep

    def get_special_tokens_mask(self, token_ids_0, token_ids_1=None, already_has_special_tokens=False):
        if already_has_special_tokens:
            return super().get_special_tokens_mask(token_ids_0, token_ids_1, True)
        mask = [1] + [0] * len(token_ids_0) + [1]
        if token_ids_1 is not None:
            mask += [0] * len(token_ids_1) + [1]
        return mask

    def create_token_type_ids_from_sequences(self, token_ids_0, token_ids_1=None):
        cls_sep = [0]
        if token_ids_1 is None:
            return cls_sep + [0] * len(token_ids_0) + cls_sep
        return cls_sep + [0] * len(token_ids_0) + cls_sep + [0] * len(token_ids_1) + cls_sep