AutoAndroidController/py/venv/Lib/site-packages/transformers/models/xglm/tokenization_xglm.py

# coding=utf-8
# Copyright The HuggingFace Team and The HuggingFace Inc. team. All rights reserved.
#
# 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 ."""

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

import sentencepiece as spm

from ...tokenization_utils import PreTrainedTokenizer
from ...utils import logging
from ...utils.import_utils import requires


logger = logging.get_logger(__name__)

SPIECE_UNDERLINE = "▁"

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


@requires(backends=("sentencepiece",))
class XGLMTokenizer(PreTrainedTokenizer):
    """
    Adapted from [`RobertaTokenizer`] and [`XLNetTokenizer`]. Based on
    [SentencePiece](https://github.com/google/sentencepiece).

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

    Args:
        vocab_file (`str`):
            Path to the vocabulary file.
        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.
        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
    model_input_names = ["input_ids", "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>",
        sp_model_kwargs: Optional[dict[str, Any]] = None,
        **kwargs,
    ) -> None:
        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs

        # Compatibility with the original tokenizer
        self.num_madeup_words = 7
        madeup_words = [f"<madeupword{i}>" for i in range(self.num_madeup_words)]

        kwargs["additional_special_tokens"] = kwargs.get("additional_special_tokens", []) or []
        kwargs["additional_special_tokens"] += [
            word for word in madeup_words if word not in kwargs["additional_special_tokens"]
        ]

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

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

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

        sp_size = len(self.sp_model)
        madeup_words = {f"<madeupword{i}>": sp_size + i + self.fairseq_offset for i in range(self.num_madeup_words)}
        self.fairseq_tokens_to_ids.update(madeup_words)

        self.fairseq_ids_to_tokens = {v: k for k, v in self.fairseq_tokens_to_ids.items()}

        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,
            sp_model_kwargs=self.sp_model_kwargs,
            **kwargs,
        )

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

    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 XLM-RoBERTa sequence has the following format:

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

        Args:
            token_ids_0 (`list[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (`list[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `list[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
        """

        if token_ids_1 is None:
            return [self.sep_token_id] + token_ids_0
        sep = [self.sep_token_id]
        return sep + token_ids_0 + sep + sep + token_ids_1

    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 (`list[int]`):
                List of IDs.
            token_ids_1 (`list[int]`, *optional*):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            `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:
            return super().get_special_tokens_mask(
                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
            )

        if token_ids_1 is None:
            return [1] + ([0] * len(token_ids_0))
        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_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. XLM-RoBERTa does
        not make use of token type ids, therefore a list of zeros is returned.

        Args:
            token_ids_0 (`list[int]`):
                List of IDs.
            token_ids_1 (`list[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `list[int]`: List of zeros.

        """

        sep = [self.sep_token_id]

        if token_ids_1 is None:
            return len(sep + token_ids_0) * [0]
        return len(sep + token_ids_0 + sep + sep + token_ids_1) * [0]

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

    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: str) -> list[str]:
        return self.sp_model.encode(text, out_type=str)

    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: 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,)


__all__ = ["XGLMTokenizer"]