transformers/src/transformers/tokenization_reformer.py

# coding=utf-8
# Copyright 2020 The Trax Authors and The HuggingFace Inc. team.
#
# 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.
""" Tokenization class for model Reformer."""


import os
from shutil import copyfile
from typing import Dict, Optional, Tuple

import sentencepiece as spm

from .tokenization_utils import PreTrainedTokenizer
from .utils import logging


logger = logging.get_logger(__name__)

SPIECE_UNDERLINE = "▁"


####################################################
# Mapping from the keyword arguments names of Tokenizer `__init__`
# to file names for serializing Tokenizer instances
####################################################
VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"}

####################################################
# Mapping from the keyword arguments names of Tokenizer `__init__`
# to pretrained vocabulary URL for all the model shortcut names.
####################################################
PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "google/reformer-crime-and-punishment": "https://cdn.huggingface.co/google/reformer-crime-and-punishment/spiece.model"
    }
}

####################################################
# Mapping from model shortcut names to max length of inputs
####################################################
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "google/reformer-crime-and-punishment": 524288,
}


class ReformerTokenizer(PreTrainedTokenizer):
    """
    Construct a Reformer tokenizer. Based on `SentencePiece <https://github.com/google/sentencepiece>`__ .

    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods.
    Users should refer to this superclass for more information regarding those methods.

    Args:
        vocab_file (:obj:`str`):
            `SentencePiece <https://github.com/google/sentencepiece>`__ file (generally has a `.spm` extension) that
            contains the vocabulary necessary to instantiate a tokenizer.
        eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
            The end of sequence token.

            .. note::

                When building a sequence using special tokens, this is not the token that is used for the end
                of sequence. The token used is the :obj:`sep_token`.
        unk_token (:obj:`str`, `optional`, defaults to :obj:`"<unk>"`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        pad_token (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
            The token used for padding, for example when batching sequences of different lengths.
        additional_special_tokens (:obj:`List[str]`, `optional`):
            Additional special tokens used by the tokenizer.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["attention_mask"]

    def __init__(
        self,
        vocab_file,
        eos_token="</s>",
        unk_token="<unk>",
        pad_token="<pad>",
        additional_special_tokens=[],
        **kwargs
    ):
        super().__init__(
            eos_token=eos_token,
            unk_token=unk_token,
            pad_token=pad_token,
            additional_special_tokens=additional_special_tokens,
            **kwargs,
        )

        self.vocab_file = vocab_file
        self.sp_model = spm.SentencePieceProcessor()
        self.sp_model.Load(vocab_file)

    @property
    def vocab_size(self):
        return self.sp_model.get_piece_size()

    def get_vocab(self) -> Dict[str, int]:
        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
        vocab.update(self.added_tokens_encoder)
        return vocab

    def __getstate__(self):
        state = self.__dict__.copy()
        state["sp_model"] = None
        return state

    def __setstate__(self, d):
        self.__dict__ = d
        self.sp_model = spm.SentencePieceProcessor()
        self.sp_model.Load(self.vocab_file)

    def _tokenize(self, text, sample=False):
        """Take as input a string and return a list of strings (tokens) for words/sub-words"""
        if not sample:
            pieces = self.sp_model.EncodeAsPieces(text)
        else:
            pieces = self.sp_model.SampleEncodeAsPieces(text, 64, 0.1)
        return pieces

    def _convert_token_to_id(self, token):
        """ Converts a token (str) in an id using the vocab. """
        return self.sp_model.piece_to_id(token)

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        if index < self.sp_model.get_piece_size():
            token = self.sp_model.IdToPiece(index)
        return token

    def convert_tokens_to_string(self, tokens):
        """ Converts a sequence of tokens (string) in a single string. """
        out_string = self.sp_model.decode_pieces(tokens)
        return out_string

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        if not os.path.isdir(save_directory):
            logger.error("Vocabulary path ({}) should be a directory".format(save_directory))
            return
        out_vocab_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
        )

        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
            copyfile(self.vocab_file, out_vocab_file)

        return (out_vocab_file,)