tokenization_kobert.py

# coding=utf-8
# Copyright 2021 SKT AI Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from typing import Any, Dict, List, Optional
from transformers.tokenization_utils import AddedToken
from transformers import XLNetTokenizer
from transformers import SPIECE_UNDERLINE


class KoBERTTokenizer(XLNetTokenizer):
    padding_side = "right"

    def __init__(
        self,
        vocab_file,
        do_lower_case=False,
        remove_space=True,
        keep_accents=False,
        bos_token="[CLS]",
        eos_token="[SEP]",
        unk_token="[UNK]",
        sep_token="[SEP]",
        pad_token="[PAD]",
        cls_token="[CLS]",
        mask_token="[MASK]",
        additional_special_tokens=None,
        sp_model_kwargs: Optional[Dict[str, Any]] = None,
        **kwargs
    ) -> None:
        # Mask token behave like a normal word, i.e. include the space before it
        mask_token = (
            AddedToken(mask_token, lstrip=True, rstrip=False)
            if isinstance(mask_token, str)
            else mask_token
        )

        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs

        super().__init__(
            vocab_file,
            do_lower_case=do_lower_case,
            remove_space=remove_space,
            keep_accents=keep_accents,
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            additional_special_tokens=additional_special_tokens,
            sp_model_kwargs=self.sp_model_kwargs,
            **kwargs,
        )
        self._pad_token_type_id = 0

    def build_inputs_with_special_tokens(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
        adding special tokens. An XLNet sequence has the following format:
        - single sequence: ``<cls> X <sep>``
        - pair of sequences: ``<cls> A <sep> B <sep>``
        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.
        Returns:
            :obj:`List[int]`: List of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
        """
        sep = [self.sep_token_id]
        cls = [self.cls_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 _tokenize(self, text: str) -> List[str]:
        """Tokenize a string."""
        text = self.preprocess_text(text)
        pieces = self.sp_model.encode(text, out_type=str, **self.sp_model_kwargs)
        new_pieces = []
        for piece in pieces:
            if len(piece) > 1 and piece[-1] == str(",") and piece[-2].isdigit():
                cur_pieces = self.sp_model.EncodeAsPieces(
                    piece[:-1].replace(SPIECE_UNDERLINE, "")
                )
                if (
                    piece[0] != SPIECE_UNDERLINE
                    and cur_pieces[0][0] == SPIECE_UNDERLINE
                ):
                    if len(cur_pieces[0]) == 1:
                        cur_pieces = cur_pieces[1:]
                    else:
                        cur_pieces[0] = cur_pieces[0][1:]
                cur_pieces.append(piece[-1])
                new_pieces.extend(cur_pieces)
            else:
                new_pieces.append(piece)

        return new_pieces

    def build_inputs_with_special_tokens(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
        adding special tokens. An XLNet sequence has the following format:

        - single sequence: ``<cls> X <sep> ``
        - pair of sequences: ``<cls> A <sep> B <sep>``

        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.

        Returns:
            :obj:`List[int]`: List of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
        """
        sep = [self.sep_token_id]
        cls = [self.cls_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 create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Create a mask from the two sequences passed to be used in a sequence-pair classification task. An XLNet
        sequence pair mask has the following format:

        ::

            0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
            | first sequence    | second sequence |

        If :obj:`token_ids_1` is :obj:`None`, this method only returns the first portion of the mask (0s).

        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.

        Returns:
            :obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
            sequence(s).
        """
        sep = [self.sep_token_id]
        cls = [self.cls_token_id]
        if token_ids_1 is None:
            return len(cls + token_ids_0 + sep) * [0]
        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]