# coding=utf-8
# Copyright 2021 T5 Authors and 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 class for model ByT5."""

import warnings
from typing import List, Optional, Tuple

from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
from transformers.utils import logging

logger = logging.get_logger(__name__)

class UTF8LikeByteTokenizer(PreTrainedTokenizer):
    """
    Construct a ByT5 tokenizer. ByT5 simply uses raw bytes utf-8 encoding.

    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:
        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>

        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.
        extra_ids (`int`, *optional*, defaults to 125):
            Add a number of extra ids added to the end of the vocabulary for use as sentinels. These tokens are
            accessible as "<extra_id_{%d}>" where "{%d}" is a number between 0 and extra_ids-1. Extra tokens are
            indexed from the end of the vocabulary up to beginning ("<extra_id_0>" is the last token in the vocabulary
            like in ByT5 preprocessing see
            [here](https://github.com/google-research/text-to-text-transfer-transformer/blob/9fd7b14a769417be33bc6c850f9598764913c833/t5/data/preprocessors.py#L2117)).
        additional_special_tokens (`List[str]`, *optional*):
            Additional special tokens used by the tokenizer.
    """
    
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        bos_token="<s>",
        eos_token="</s>",
        pad_token="<pad>",
        cls_token="<cls>",
        sep_token="<sep>",
        mask_token="<mask>",
        extra_ids=26,
        additional_special_tokens=None,
        **kwargs,
    ) -> None:
        # Add extra_ids to the special token list
        if extra_ids > 0 and additional_special_tokens is None:
            additional_special_tokens = [f"<extra_id_{i}>" for i in range(extra_ids)]
        elif extra_ids > 0 and additional_special_tokens is not None and len(additional_special_tokens) > 0:
            # Check that we have the right number of extra_id special tokens
            extra_tokens = len(set(filter(lambda x: bool("extra_id" in str(x)), additional_special_tokens)))
            if extra_tokens != extra_ids:
                raise ValueError(
                    f"Both extra_ids ({extra_ids}) and additional_special_tokens ({additional_special_tokens}) are"
                    " provided to ByteTokenizer. In this case the additional_special_tokens must include the"
                    " extra_ids tokens"
                )

        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
        cls_token = AddedToken(cls_token, lstrip=False, rstrip=False) if isinstance(cls_token, str) else cls_token
        sep_token = AddedToken(sep_token, lstrip=False, rstrip=False) if isinstance(sep_token, str) else sep_token
        mask_token = AddedToken(mask_token, lstrip=False, rstrip=False) if isinstance(mask_token, str) else mask_token
        
        # unk token needs to be in the vocab with correct index
        self._added_tokens_decoder = {0: pad_token, 1: eos_token, 2: bos_token, 3: cls_token, 4: sep_token, 5: mask_token}
        self.offset = len(self._added_tokens_decoder)
        self._utf_vocab_size = 2**8  # utf is 8 bits
        super().__init__(
            bos_token=bos_token,
            eos_token=eos_token,
            pad_token=pad_token,
            cls_token=cls_token,
            sep_token=sep_token,
            mask_token=mask_token,
            extra_ids=0,
            additional_special_tokens=additional_special_tokens,  # TODO extra ids are not used :sweatywmile:
            **kwargs,
        )

    @property
    def vocab_size(self):
        return self._utf_vocab_size

    def get_vocab(self):
        vocab = {
            self.convert_ids_to_tokens(i): i for i in range(self.vocab_size + self.offset)
        }
        vocab.update(self.added_tokens_encoder)
        return vocab

    def _add_bos_if_not_present(self, token_ids: List[int]) -> List[int]:
        """Do not add bos again if user already added it."""
        if len(token_ids) > 0 and token_ids[0] == self.bos_token_id:
            warnings.warn(
                f"This sequence already has {self.bos_token}. In future versions this behavior may lead to duplicated"
                " bos tokens being added."
            )
            return token_ids
        else:
            return [self.bos_token_id] + token_ids


    
    def _add_eos_if_not_present(self, token_ids: List[int]) -> List[int]:
        """Do not add eos again if user already added it."""
        if len(token_ids) > 0 and token_ids[-1] == self.eos_token_id:
            warnings.warn(
                f"This sequence already has {self.eos_token}. In future versions this behavior may lead to duplicated"
                " eos tokens being added."
            )
            return token_ids
        else:
            return token_ids + [self.eos_token_id]


    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. A sequence has the following format:

        - single sequence: `X </s>`
        - pair of sequences: `A </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.
        """
        token_ids_0 = self._add_bos_if_not_present(token_ids_0)
        token_ids_0 = self._add_eos_if_not_present(token_ids_0)
        
        if token_ids_1 is None:
            return token_ids_0
        else:
            token_ids_1 = self._add_bos_if_not_present(token_ids_1)
            token_ids_1 = self._add_eos_if_not_present(token_ids_1)
            return token_ids_0 + token_ids_1

    def _tokenize(self, text: str) -> List[str]:
        """Take as input a string and return a list of strings (tokens) for words/sub-words"""
        token_ids = []
        for c in text:
            token_ids.extend(self.unicode_to_bytes(ord(c)))

        # Convert to string
        token_ids = [str(i) for i in token_ids]
        return token_ids

    def _convert_token_to_id(self, token):
        """Converts a token (str) in an id using the vocab."""
        token_id = int(token) + self.offset
        return token_id

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

    

    def convert_tokens_to_string(self, tokens):
        token_id_with_special_tokens = []
        for token in tokens:
            try:
                token_id = int(token)
                token_id_with_special_tokens.append(token_id)
            except ValueError:
                token_id_with_special_tokens.append(token)
        return self.decode_ids(token_id_with_special_tokens)
    
    def decode_ids(self, tokens: List[int]) -> str:
        decoded = ""
        i = 0
        try:
            while i < len(tokens):
                if type(tokens[i]) == str:
                    decoded += tokens[i]
                    i += 1
                    continue

                if tokens[i] < 0b10000000:
                    decoded += chr(tokens[i])
                    i += 1
                elif tokens[i] < 0b11000000:
                    decoded += chr(((tokens[i] & 0b00111111) << 7) + (tokens[i + 1] & 0b01111111))
                    i += 2
                elif tokens[i] < 0b11100000:
                    decoded += chr(((tokens[i] & 0b00011111) << 13) + ((tokens[i + 1] & 0b00111111) << 7) + (tokens[i + 2] & 0b01111111))
                    i += 3
                elif tokens[i] < 0b11110000:
                    decoded += chr(
                        ((tokens[i] & 0b00001111) << 18) + ((tokens[i + 1] & 0b00111111) << 13) + ((tokens[i + 2] & 0b00111111) << 7) + (tokens[i + 3] & 0b01111111)
                    )
                    i += 4
                else:
                    raise ValueError("invalid token")
        except IndexError:
            pass
        return decoded
    
    
    def unicode_to_bytes(self, codepoint: int) -> list[int]:
        codepoint_bin = f"{codepoint:b}"

        if len(codepoint_bin) <= 7:  # 1byte char
            codepoint_bin = f"{codepoint:07b}"
            bytes_bin = [
                "0" + codepoint_bin,
            ]
        elif len(codepoint_bin) <= 13:  # 2byte char
            codepoint_bin = f"{codepoint:013b}"
            bytes_bin = [
                "10" + codepoint_bin[:6],
                "0" + codepoint_bin[6:],
            ]
        elif len(codepoint_bin) <= 18:  # 3byte char
            codepoint_bin = f"{codepoint:018b}"
            bytes_bin = [
                "110" + codepoint_bin[:5],
                "10" + codepoint_bin[5:11],
                "0" + codepoint_bin[11:],
            ]
        elif len(codepoint_bin) <= 22:  # 4byte char
            codepoint_bin = f"{codepoint:022b}"
            bytes_bin = [
                "1110" + codepoint_bin[:4],
                "110" + codepoint_bin[4:9],
                "10" + codepoint_bin[9:15],
                "0" + codepoint_bin[15:],
            ]
        else:
            raise ValueError("codepoint is too large")

        return [int(byte, 2) for byte in bytes_bin]

    # ByteTokenizer has no vocab file
    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        return ()