# Copyright (c) 2020, NVIDIA CORPORATION.  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 class for model BertGeneration."""

from typing import Any

from ...tokenization_utils_sentencepiece import SentencePieceBackend
from ...utils import logging
from ...utils.import_utils import requires


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"}


@requires(backends=("sentencepiece",))
class BertGenerationTokenizer(SentencePieceBackend):
    """
    Construct a BertGeneration tokenizer. 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`):
            [SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
            contains the vocabulary necessary to instantiate a tokenizer.
        bos_token (`str`, *optional*, defaults to `"<s>"`):
            The begin of sequence token.
        eos_token (`str`, *optional*, defaults to `"</s>"`):
            The end of sequence token.
        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.
        sep_token (`str`, *optional*, defaults to `"<::::>"`):
            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.
        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.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    prefix_tokens: list[int] = []
    model_input_names = ["input_ids", "attention_mask"]
    is_fast = False

    def __init__(
        self,
        vocab_file,
        bos_token="<s>",
        eos_token="</s>",
        unk_token="<unk>",
        pad_token="<pad>",
        sep_token="<::::>",
        sp_model_kwargs: dict[str, Any] | None = None,
        **kwargs,
    ) -> None:
        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs

        # Call parent init (which will load sp_model)
        super().__init__(
            vocab_file=vocab_file,
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            pad_token=pad_token,
            sep_token=sep_token,
            sp_model_kwargs=self.sp_model_kwargs,
            special_tokens_pattern="none",
            **kwargs,
        )


__all__ = ["BertGenerationTokenizer"]