HuggingFace_transformer/src/transformers/tokenization_xlm_roberta.py

# coding=utf-8
# Copyright 2018 Google AI, Google Brain and Carnegie Mellon University 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 classes for XLM-RoBERTa model."""


import os
from shutil import copyfile
from typing import List, Optional

from .tokenization_utils import PreTrainedTokenizer
from .tokenization_xlnet import SPIECE_UNDERLINE
from .utils import logging


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "xlm-roberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-base-sentencepiece.bpe.model",
        "xlm-roberta-large": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-sentencepiece.bpe.model",
        "xlm-roberta-large-finetuned-conll02-dutch": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-dutch-sentencepiece.bpe.model",
        "xlm-roberta-large-finetuned-conll02-spanish": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-spanish-sentencepiece.bpe.model",
        "xlm-roberta-large-finetuned-conll03-english": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-english-sentencepiece.bpe.model",
        "xlm-roberta-large-finetuned-conll03-german": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-german-sentencepiece.bpe.model",
    }
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "xlm-roberta-base": 512,
    "xlm-roberta-large": 512,
    "xlm-roberta-large-finetuned-conll02-dutch": 512,
    "xlm-roberta-large-finetuned-conll02-spanish": 512,
    "xlm-roberta-large-finetuned-conll03-english": 512,
    "xlm-roberta-large-finetuned-conll03-german": 512,
}


class XLMRobertaTokenizer(PreTrainedTokenizer):
    """
        Adapted from RobertaTokenizer and XLNetTokenizer
        SentencePiece based tokenizer. Peculiarities:

        - requires `SentencePiece <https://github.com/google/sentencepiece>`_

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

    Args:
        vocab_file (:obj:`str`):
            Path to the vocabulary file.
        bos_token (:obj:`string`, `optional`, defaults to "<s>"):
            The beginning of sequence token that was used during pre-training. Can be used a sequence classifier token.

            .. note::

                When building a sequence using special tokens, this is not the token that is used for the beginning
                of sequence. The token used is the :obj:`cls_token`.
        eos_token (:obj:`string`, `optional`, defaults to "</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`.
        sep_token (:obj:`string`, `optional`, defaults to "</s>"):
            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.
        cls_token (:obj:`string`, `optional`, defaults to "<s>"):
            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.
        unk_token (:obj:`string`, `optional`, defaults to "<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:`string`, `optional`, defaults to "<pad>"):
            The token used for padding, for example when batching sequences of different lengths.
        mask_token (:obj:`string`, `optional`, defaults to "<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.
        additional_special_tokens (:obj:`List[str]`, `optional`, defaults to :obj:`["<s>NOTUSED", "</s>NOTUSED"]`):
            Additional special tokens used by the tokenizer.

    Attributes:
        sp_model (:obj:`SentencePieceProcessor`):
            The `SentencePiece` processor that is used for every conversion (string, tokens and IDs).
    """

    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,
        bos_token="<s>",
        eos_token="</s>",
        sep_token="</s>",
        cls_token="<s>",
        unk_token="<unk>",
        pad_token="<pad>",
        mask_token="<mask>",
        **kwargs
    ):
        super().__init__(
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            sep_token=sep_token,
            cls_token=cls_token,
            pad_token=pad_token,
            mask_token=mask_token,
            **kwargs,
        )

        try:
            import sentencepiece as spm
        except ImportError:
            logger.warning(
                "You need to install SentencePiece to use XLMRobertaTokenizer: https://github.com/google/sentencepiece"
                "pip install sentencepiece"
            )
            raise

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

        # Original fairseq vocab and spm vocab must be "aligned":
        # Vocab    |    0    |    1    |   2    |    3    |  4  |  5  |  6  |   7   |   8   |  9
        # -------- | ------- | ------- | ------ | ------- | --- | --- | --- | ----- | ----- | ----
        # fairseq  | '<s>'   | '<pad>' | '</s>' | '<unk>' | ',' | '.' | '▁' | 's'   | '▁de' | '-'
        # spm      | '<unk>' | '<s>'   | '</s>' | ','     | '.' | '▁' | 's' | '▁de' | '-'   | '▁a'

        # Mimic fairseq token-to-id alignment for the first 4 token
        self.fairseq_tokens_to_ids = {"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3}

        # The first "real" token "," has position 4 in the original fairseq vocab and position 3 in the spm vocab
        self.fairseq_offset = 1

        self.fairseq_tokens_to_ids["<mask>"] = len(self.sp_model) + self.fairseq_offset
        self.fairseq_ids_to_tokens = {v: k for k, v in self.fairseq_tokens_to_ids.items()}

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

    def __setstate__(self, d):
        self.__dict__ = d
        try:
            import sentencepiece as spm
        except ImportError:
            logger.warning(
                "You need to install SentencePiece to use XLMRobertaTokenizer: https://github.com/google/sentencepiece"
                "pip install sentencepiece"
            )
            raise
        self.sp_model = spm.SentencePieceProcessor()
        self.sp_model.Load(self.vocab_file)

    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 XLM-R sequence has the following format:

        - single sequence: ``<s> X </s>``
        - pair of sequences: ``<s> A </s></s> B </s>``

        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 + 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]:
        """
        Retrieves 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`` methods.

        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`):
                Set to True if 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 None:
            return [1] + ([0] * len(token_ids_0)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]

    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
        XLM-R does not make use of token type ids, therefore a list of zeros is returned.

        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 zeros.

        """

        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 + sep + token_ids_1 + sep) * [0]

    @property
    def vocab_size(self):
        return len(self.sp_model) + self.fairseq_offset + 1  # Add the <mask> token

    def get_vocab(self):
        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
        vocab.update(self.added_tokens_encoder)
        return vocab

    def _tokenize(self, text):
        return self.sp_model.EncodeAsPieces(text)

    def _convert_token_to_id(self, token):
        """ Converts a token (str) in an id using the vocab. """
        if token in self.fairseq_tokens_to_ids:
            return self.fairseq_tokens_to_ids[token]
        spm_id = self.sp_model.PieceToId(token)

        # Need to return unknown token if the SP model returned 0
        return spm_id + self.fairseq_offset if spm_id else self.unk_token_id

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        if index in self.fairseq_ids_to_tokens:
            return self.fairseq_ids_to_tokens[index]
        return self.sp_model.IdToPiece(index - self.fairseq_offset)

    def convert_tokens_to_string(self, tokens):
        """Converts a sequence of tokens (strings for sub-words) in a single string."""
        out_string = "".join(tokens).replace(SPIECE_UNDERLINE, " ").strip()
        return out_string

    def save_vocabulary(self, save_directory):
        """
        Save the sentencepiece vocabulary (copy original file) and special tokens file to a directory.

        Args:
            save_directory (:obj:`str`):
                The directory in which to save the vocabulary.

        Returns:
            :obj:`Tuple(str)`: Paths to the files saved.
        """
        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, 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,)