# coding=utf-8
# Copyright 2023 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 MGT-STR CHAR."""

import json
import os
from typing import Optional

from ...tokenization_utils import PreTrainedTokenizer
from ...utils import logging


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "vocab.json"}


class MgpstrTokenizer(PreTrainedTokenizer):
    """
    Construct a MGP-STR char tokenizer.

    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.
        unk_token (`str`, *optional*, defaults to `"[GO]"`):
            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.
        bos_token (`str`, *optional*, defaults to `"[GO]"`):
            The beginning of sequence token.
        eos_token (`str`, *optional*, defaults to `"[s]"`):
            The end of sequence token.
        pad_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"[GO]"`):
            A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by
            attention mechanisms or loss computation.
    """

    vocab_files_names = VOCAB_FILES_NAMES

    def __init__(self, vocab_file, unk_token="[GO]", bos_token="[GO]", eos_token="[s]", pad_token="[GO]", **kwargs):
        with open(vocab_file, encoding="utf-8") as vocab_handle:
            self.vocab = json.load(vocab_handle)
        self.decoder = {v: k for k, v in self.vocab.items()}
        super().__init__(
            unk_token=unk_token,
            bos_token=bos_token,
            eos_token=eos_token,
            pad_token=pad_token,
            **kwargs,
        )

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

    def get_vocab(self):
        vocab = dict(self.vocab).copy()
        vocab.update(self.added_tokens_encoder)
        return vocab

    def _tokenize(self, text):
        """Tokenize a string."""
        char_tokens = []
        for s in text:
            char_tokens.extend(s)
        return char_tokens

    def _convert_token_to_id(self, token):
        """Converts a token (str) in an id using the vocab."""
        return self.vocab.get(token, self.vocab.get(self.unk_token))

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

    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
        vocab_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
        )

        with open(vocab_file, "w", encoding="utf-8") as f:
            f.write(json.dumps(self.vocab, indent=2, sort_keys=True, ensure_ascii=False) + "\n")

        return (vocab_file,)


__all__ = ["MgpstrTokenizer"]