transformers/templates/adding_a_new_model/tokenization_xxx.py

# coding=utf-8
# Copyright 2018 XXX 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.
""" Tokenization class for model XXX."""


import collections
import logging
import os
from typing import List, Optional, Tuple

from .tokenization_utils import PreTrainedTokenizer


logger = logging.getLogger(__name__)

####################################################
# In this template, replace all the XXX (various casings) with your model name
####################################################

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

####################################################
# 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": {
        "xxx-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/xxx-base-uncased-vocab.txt",
        "xxx-large-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/xxx-large-uncased-vocab.txt",
    }
}

####################################################
# Mapping from model shortcut names to max length of inputs
####################################################
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "xxx-base-uncased": 512,
    "xxx-large-uncased": 512,
}

####################################################
# Mapping from model shortcut names to a dictionary of additional
# keyword arguments for Tokenizer `__init__`.
# To be used for checkpoint specific configurations.
####################################################
PRETRAINED_INIT_CONFIGURATION = {
    "xxx-base-uncased": {"do_lower_case": True},
    "xxx-large-uncased": {"do_lower_case": True},
}


def load_vocab(vocab_file):
    """Loads a vocabulary file into a dictionary."""
    vocab = collections.OrderedDict()
    with open(vocab_file, "r", encoding="utf-8") as reader:
        tokens = reader.readlines()
    for index, token in enumerate(tokens):
        token = token.rstrip("\n")
        vocab[token] = index
    return vocab


class XxxTokenizer(PreTrainedTokenizer):
    r"""
    Constructs a XXX tokenizer. Based on XXX.

    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`):
            File containing the vocabulary.
        do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not to lowercase the input when tokenizing.
        do_basic_tokenize (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether ot not to do basic tokenization before WordPiece.
        never_split (:obj:`Iterable`, `optional`):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            :obj:`do_basic_tokenize=True`
        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.
        sep_token (:obj:`str`, `optional`, defaults to :obj:`"[SEP]"`):
            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences
            for sequence classification or for a text and a question for question answering.
            It is also used as the last token of a sequence built with special tokens.
        pad_token (:obj:`str`, `optional`, defaults to :obj:`"[PAD]"`):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (:obj:`str`, `optional`, defaults to :obj:`"[CLS]"`):
            The classifier token which is used when doing sequence classification (classification of the whole
            sequence instead of per-token classification). It is the first token of the sequence when built with
            special tokens.
        mask_token (:obj:`str`, `optional`, defaults to :obj:`"[MASK]"`):
            The token used for masking values. This is the token used when training this model with masked language
            modeling. This is the token which the model will try to predict.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

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

        if not os.path.isfile(vocab_file):
            raise ValueError(
                "Can't find a vocabulary file at path '{}'. To load the vocabulary from a Google pretrained "
                "model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`".format(vocab_file)
            )
        self.vocab = load_vocab(vocab_file)
        self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
        self.do_basic_tokenize = do_basic_tokenize
        # Replace and adapt
        # if do_basic_tokenize:
        #    self.basic_tokenizer = BasicTokenizer(
        #        do_lower_case=do_lower_case, never_split=never_split, tokenize_chinese_chars=tokenize_chinese_chars
        #    )
        # self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab, unk_token=self.unk_token)

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

    def get_vocab(self):
        return dict(self.vocab, **self.added_tokens_encoder)

    def _tokenize(self, text):
        split_tokens = []
        if self.do_basic_tokenize:
            for token in self.basic_tokenizer.tokenize(text, never_split=self.all_special_tokens):

                # If the token is part of the never_split set
                if token in self.basic_tokenizer.never_split:
                    split_tokens.append(token)
                else:
                    split_tokens += self.wordpiece_tokenizer.tokenize(token)
        else:
            split_tokens = self.wordpiece_tokenizer.tokenize(text)
        return split_tokens

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

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        return self.ids_to_tokens.get(index, self.unk_token)

    def convert_tokens_to_string(self, tokens):
        """ Converts a sequence of tokens (string) in a single string. """
        out_string = " ".join(tokens).replace(" ##", "").strip()
        return out_string

    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.
        A XXX 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.
        """
        if token_ids_1 is None:
            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
        cls = [self.cls_token_id]
        sep = [self.sep_token_id]
        return cls + token_ids_0 + sep + token_ids_1 + sep

    def get_special_tokens_mask(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
    ) -> List[int]:
        """
        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer ``prepare_for_model`` method.

        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.
            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """

        if already_has_special_tokens:
            if token_ids_1 is not None:
                raise ValueError(
                    "You should not supply a second sequence if the provided sequence of "
                    "ids is already formated with special tokens for the model."
                )
            return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))

        if token_ids_1 is not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1]

    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.
        A BERT 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]

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        index = 0
        if os.path.isdir(save_directory):
            vocab_file = os.path.join(
                save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
            )
        else:
            vocab_file = (filename_prefix + "-" if filename_prefix else "") + save_directory
        with open(vocab_file, "w", encoding="utf-8") as writer:
            for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning(
                        "Saving vocabulary to {}: vocabulary indices are not consecutive."
                        " Please check that the vocabulary is not corrupted!".format(vocab_file)
                    )
                    index = token_index
                writer.write(token + "\n")
                index += 1
        return (vocab_file,)