HuggingFace_transformer/src/transformers/tokenization_albert.py

# coding=utf-8
# Copyright 2018 Google AI, Google Brain 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 ALBERT model."""


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

from .tokenization_utils import PreTrainedTokenizer
from .utils import logging


logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "albert-base-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v1-spiece.model",
        "albert-large-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v1-spiece.model",
        "albert-xlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v1-spiece.model",
        "albert-xxlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v1-spiece.model",
        "albert-base-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v2-spiece.model",
        "albert-large-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v2-spiece.model",
        "albert-xlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v2-spiece.model",
        "albert-xxlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v2-spiece.model",
    }
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "albert-base-v1": 512,
    "albert-large-v1": 512,
    "albert-xlarge-v1": 512,
    "albert-xxlarge-v1": 512,
    "albert-base-v2": 512,
    "albert-large-v2": 512,
    "albert-xlarge-v2": 512,
    "albert-xxlarge-v2": 512,
}

SPIECE_UNDERLINE = "▁"


class AlbertTokenizer(PreTrainedTokenizer):
    """
    Constructs an ALBERT tokenizer. Based on `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:`string`):
            `SentencePiece <https://github.com/google/sentencepiece>`__ file (generally has a .spm extension) that
            contains the vocabulary necessary to instantiate a tokenizer.
        do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether to lowercase the input when tokenizing.
        remove_space (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether to strip the text when tokenizing (removing excess spaces before and after the string).
        keep_accents (:obj:`bool`, `optional`, defaults to :obj:`False`):
            Whether to keep accents when tokenizing.
        bos_token (:obj:`string`, `optional`, defaults to "[CLS]"):
            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 "[SEP]"):
            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:`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.
        sep_token (:obj:`string`, `optional`, defaults to "[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:`string`, `optional`, defaults to "<pad>"):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (:obj:`string`, `optional`, defaults to "[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:`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.

    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

    def __init__(
        self,
        vocab_file,
        do_lower_case=True,
        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]",
        **kwargs
    ):
        super().__init__(
            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,
            **kwargs,
        )

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

        self.do_lower_case = do_lower_case
        self.remove_space = remove_space
        self.keep_accents = keep_accents
        self.vocab_file = vocab_file

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

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

    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 __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 AlbertTokenizer: https://github.com/google/sentencepiece"
                "pip install sentencepiece"
            )
            raise
        self.sp_model = spm.SentencePieceProcessor()
        self.sp_model.Load(self.vocab_file)

    def preprocess_text(self, inputs):
        if self.remove_space:
            outputs = " ".join(inputs.strip().split())
        else:
            outputs = inputs
        outputs = outputs.replace("``", '"').replace("''", '"')

        if not self.keep_accents:
            outputs = unicodedata.normalize("NFKD", outputs)
            outputs = "".join([c for c in outputs if not unicodedata.combining(c)])
        if self.do_lower_case:
            outputs = outputs.lower()

        return outputs

    def _tokenize(self, text, sample=False):
        """ Tokenize a string. """
        text = self.preprocess_text(text)

        if not sample:
            pieces = self.sp_model.EncodeAsPieces(text)
        else:
            pieces = self.sp_model.SampleEncodeAsPieces(text, 64, 0.1)
        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 _convert_token_to_id(self, token):
        """ Converts a token (str) in an id using the vocab. """
        return self.sp_model.PieceToId(token)

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

    def convert_tokens_to_string(self, tokens):
        out_string = "".join(tokens).replace(SPIECE_UNDERLINE, " ").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.
        An ALBERT 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 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`` 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`):
                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 formatted 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]:
        """
        Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
        An ALBERT 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 token_ids_1 is None, 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):
        """
        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,)