tokenization_bart_japanese_news.py

# Copyright 2023 Stockmark Inc.
#
# 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.


import os
import unicodedata
from shutil import copyfile
from typing import Any, Dict, List, Optional, Tuple

import regex
import sentencepiece as spm
from transformers import AddedToken, BartTokenizer, logging

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

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "bart-base-japanese-news": "https://huggingface.co/stockmark/bart-base-japanese-news/resolve/main/spiece.model",
    }}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "bart-base-japanese-news": 512,
}

SPIECE_UNDERLINE = "▁"


class BartJapaneseNewsTokenizer(BartTokenizer):
    """
    Construct an Bart tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece).

    This tokenizer inherits from [`BartTokenizer`] which contains most of the main methods. Users should refer to
    this superclass for more information regarding those methods.

    Args:
        vocab_file (`str`):
            [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
            contains the vocabulary necessary to instantiate a tokenizer.
        do_lower_case (`bool`, *optional*, defaults to `False`):
            Whether or not to lowercase the input when tokenizing.
        remove_space (`bool`, *optional*, defaults to `False`):
            Whether or not to strip the text when tokenizing (removing excess spaces before and after the string).
        clean_text (`bool`, *optional*, defaults to `False`):
            Whether or not to clean input text

        bos_token (`str`, *optional*, defaults to `"<s>"`):
            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.

            <Tip>

            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 `cls_token`.

            </Tip>

        eos_token (`str`, *optional*, defaults to `"</s>"`):
            The end of sequence token.

            <Tip>

            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 `sep_token`.

            </Tip>

        sep_token (`str`, *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 (`str`, *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 (`str`, *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 (`str`, *optional*, defaults to `"<pad>"`):
            The token used for padding, for example when batching sequences of different lengths.
        mask_token (`str`, *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.

        sp_model_kwargs (`dict`, *optional*):
            Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
            SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
            to set:

            - `enable_sampling`: Enable subword regularization.
            - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.

              - `nbest_size = {0,1}`: No sampling is performed.
              - `nbest_size > 1`: samples from the nbest_size results.
              - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
                using forward-filtering-and-backward-sampling algorithm.

            - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
              BPE-dropout.

    Attributes:
        sp_model (`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=False,
        remove_space=False,
        clean_text=False,
        bos_token="<s>",
        eos_token="</s>",
        unk_token="<unk>",
        sep_token="</s>",
        pad_token="<pad>",
        cls_token="<s>",
        mask_token="<mask>",
        sp_model_kwargs: Optional[Dict[str, Any]] = None,
        **kwargs
    ) -> None:
        # Mask token behave like a normal word, i.e. include the space before it and
        # is included in the raw text, there should be a match in a non-normalized sentence.
        mask_token = (
            AddedToken(mask_token, lstrip=True, rstrip=True, normalized=False)
            if isinstance(mask_token, str)
            else mask_token
        )

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

        super(BartTokenizer, self).__init__(
            do_lower_case=do_lower_case,
            remove_space=remove_space,
            clean_text=clean_text,
            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,
            sp_model_kwargs=self.sp_model_kwargs,
            **kwargs,
        )

        self.do_lower_case = do_lower_case
        self.remove_space = remove_space
        self.clean_text = clean_text
        self.vocab_file = vocab_file

        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
        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

        # for backward compatibility
        if not hasattr(self, "sp_model_kwargs"):
            self.sp_model_kwargs = {}

        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
        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 = unicodedata.normalize("NFKD", outputs)
        outputs = ''.join([ s for s in outputs if not self._is_control(s) ])

        if self.clean_text:
            outputs = outputs.replace('‘','\'').replace('’','\'').replace('“','"').replace('”','"')
            outputs = outputs.replace('〈','<').replace('〉','>').replace('《','<').replace('》','>').replace('〔','【').replace('〕','】').replace('『','「').replace('』','」')
            outputs = regex.sub(r'[\p{GeometricShapes}\p{MiscellaneousSymbols}]','*', outputs)
            outputs = ''.join(regex.findall(r'[\p{InHiragana}\p{InKatakana}\p{BasicLatin}\p{Han}、。〃〆「」【】〒〜]',outputs))

        if self.do_lower_case:
            outputs = outputs.lower()

        outputs = unicodedata.normalize('NFKC',outputs)
        outputs = outputs.strip()
        return outputs

    def _tokenize(self, text: str) -> List[str]:
        """Tokenize a string."""
        text = self.preprocess_text(text)
        pieces = self.sp_model.encode(text, out_type=str)
        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):
        """Converts a sequence of tokens (string) in a single string."""
        current_sub_tokens = []
        out_string = ""
        prev_is_special = False
        for token in tokens:
            # make sure that special tokens are not decoded using sentencepiece model
            if token in self.all_special_tokens:
                if not prev_is_special:
                    out_string += " "
                out_string += self.sp_model.decode(current_sub_tokens) + token
                prev_is_special = True
                current_sub_tokens = []
            else:
                current_sub_tokens.append(token)
                prev_is_special = False
        out_string += self.sp_model.decode(current_sub_tokens)
        return out_string.strip()

    def _is_control(self, char):
        '''
        Check control char
        Args:
            char (str):
        Returns:
            bool:
        '''
        if char == "\t" or char == "\n" or char == "\r":
            return False
        cat = unicodedata.category(char)
        if cat.startswith("C") or ord(char)==0 or ord(char)==0xfffd:
            return True
        return False

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        if not os.path.isdir(save_directory):
            logger.error(f"Vocabulary path ({save_directory}) should be a 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) and os.path.isfile(self.vocab_file):
            copyfile(self.vocab_file, out_vocab_file)
        elif not os.path.isfile(self.vocab_file):
            with open(out_vocab_file, "wb") as fi:
                content_spiece_model = self.sp_model.serialized_model_proto()
                fi.write(content_spiece_model)

        return (out_vocab_file,)

    def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
        return super(BartTokenizer, self).prepare_for_tokenization(text, is_split_into_words=False, **kwargs)