# The implementation here is modified based on HuggingFace, originally Apache 2.0 License
# and publicly available at https://github.com/huggingface/transformers
# Copyright 2018 The HuggingFace Inc. team.
# Copyright 2021-2022 The Alibaba Fundamental Vision Team Authors. All rights reserved.

import gzip
import html
import os
from functools import lru_cache

import ftfy
import regex as re
import torch


@lru_cache()
def bytes_to_unicode():
    bs = list(range(ord('!'),
                    ord('~') + 1)) + list(range(
                        ord('¡'),
                        ord('¬') + 1)) + list(range(ord('®'),
                                                    ord('ÿ') + 1))
    cs = bs[:]
    n = 0
    for b in range(2**8):
        if b not in bs:
            bs.append(b)
            cs.append(2**8 + n)
            n += 1
    cs = [chr(n) for n in cs]
    return dict(zip(bs, cs))


def get_pairs(word):
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char
    return pairs


def basic_clean(text):
    text = ftfy.fix_text(text)
    text = html.unescape(html.unescape(text))
    return text.strip()


def whitespace_clean(text):
    text = re.sub(r'\s+', ' ', text)
    text = text.strip()
    return text


class LengthAdaptiveTokenizer(object):

    def __init__(self, config, bpe_path):
        self.byte_encoder = bytes_to_unicode()
        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
        merges = bpe_path
        merges = merges[1:49152 - 256 - 2 + 1]
        merges = [tuple(merge.split()) for merge in merges]
        vocab = list(bytes_to_unicode().values())
        vocab = vocab + [v + '</w>' for v in vocab]
        for merge in merges:
            vocab.append(''.join(merge))
        vocab.extend(['<|startoftext|>', '<|endoftext|>'])
        self.encoder = dict(zip(vocab, range(len(vocab))))
        self.decoder = {v: k for k, v in self.encoder.items()}
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {
            '<|startoftext|>': '<|startoftext|>',
            '<|endoftext|>': '<|endoftext|>'
        }
        self.pat = re.compile(
            r"""<\|startoftext\|>|<\|endoftext\|>|'s|'t|'re|'ve|'m|'ll|'d|[\p{L}]+|[\p{N}]|[^\s\p{L}\p{N}]+""",
            re.IGNORECASE)

        self.vocab = self.encoder

        self.tp_token_num = config.tp_prefix_token_num + config.tp_suffix_token_num

    def bpe(self, token):
        if token in self.cache:
            return self.cache[token]
        word = tuple(token[:-1]) + (token[-1] + '</w>', )
        pairs = get_pairs(word)

        if not pairs:
            return token + '</w>'

        while True:
            bigram = min(
                pairs, key=lambda pair: self.bpe_ranks.get(pair, float('inf')))
            if bigram not in self.bpe_ranks:
                break
            first, second = bigram
            new_word = []
            i = 0
            while i < len(word):
                try:
                    j = word.index(first, i)
                    new_word.extend(word[i:j])
                    i = j
                except ValueError:
                    new_word.extend(word[i:])
                    break

                if word[i] == first and i < len(word) - 1 and word[
                        i + 1] == second:
                    new_word.append(first + second)
                    i += 2
                else:
                    new_word.append(word[i])
                    i += 1
            new_word = tuple(new_word)
            word = new_word
            if len(word) == 1:
                break
            else:
                pairs = get_pairs(word)
        word = ' '.join(word)
        self.cache[token] = word
        return word

    def encode(self, text):
        bpe_tokens = []
        text = whitespace_clean(basic_clean(text)).lower()
        for token in re.findall(self.pat, text):
            token = ''.join(self.byte_encoder[b]
                            for b in token.encode('utf-8'))
            bpe_tokens.extend(self.encoder[bpe_token]
                              for bpe_token in self.bpe(token).split(' '))
        return bpe_tokens

    def __call__(self,
                 texts,
                 return_tensors='pt',
                 padding=True,
                 truncation=True):
        context_length = 77 - self.tp_token_num
        if isinstance(texts, str):
            texts = [texts]

        sot_token = self.encoder['<|startoftext|>']
        eot_token = self.encoder['<|endoftext|>']
        all_tokens = [[sot_token] + self.encode(text) + [eot_token]
                      for text in texts]
        result = torch.zeros(len(all_tokens), context_length, dtype=torch.long)

        for i, tokens in enumerate(all_tokens):
            if len(tokens) > context_length:
                new_tokens = [sot_token
                              ] + tokens[1:context_length - 1] + [eot_token]
                result[i, :len(tokens)] = torch.tensor(new_tokens)
            else:
                result[i, :len(tokens)] = torch.tensor(tokens)

        return result