HuggingFace_transformer/transformers/tokenization_ctrl.py

# coding=utf-8
# Copyright 2018 Salesforce and 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 Salesforce CTRL."""
from __future__ import (absolute_import, division, print_function,
                        unicode_literals)

import json
import logging
import os
import regex as re
from io import open

from .tokenization_bert import BasicTokenizer

from .tokenization_utils import PreTrainedTokenizer

logger = logging.getLogger(__name__)

VOCAB_FILES_NAMES = {
    'vocab_file': 'vocab.json',
    'merges_file': 'merges.txt',
}

PRETRAINED_VOCAB_FILES_MAP = {
    'vocab_file':
    {
        'ctrl': "https://raw.githubusercontent.com/salesforce/ctrl/master/ctrl-vocab.json",
    },
    'merges_file':
    {
        'ctrl': "https://raw.githubusercontent.com/salesforce/ctrl/master/ctrl-merges.txt",
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    'ctrl': 256,
}

def text_standardize(text):
    """
    fixes some issues the spacy tokenizer had on books corpus
    also does some whitespace standardization
    """
    text = text.replace('—', '-')
    text = text.replace('–', '-')
    text = text.replace('―', '-')
    text = text.replace('…', '...')
    text = text.replace('´', "'")
    text = re.sub(r'''(-+|~+|!+|"+|;+|\?+|\++|,+|\)+|\(+|\\+|\/+|\*+|\[+|\]+|}+|{+|\|+|_+)''', r' \1 ', text)
    text = re.sub(r'\s*\n\s*', ' \n ', text)
    text = re.sub(r'[^\S\n]+', ' ', text)
    return text.strip()


def get_pairs(word):
    """Return set of symbol pairs in a word.

    Word is represented as tuple of symbols (symbols being variable-length strings).
    """
    # pairs = []
    # prev_char = word[0]
    # for i, char in enumerate(word[1:]):
    #     #_i = i + 1
    #     #if word[_i+1:] == tuple('</w>'):
    #     #    pairs.append((prev_char, char+'</w>'))
    #     #    break
    #     #else:
    #     if True:
    #         pairs.append((prev_char, char))
    #         prev_char = char

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

    pairs = set(pairs)
    return pairs

class CTRLTokenizer(PreTrainedTokenizer):
    """
    CTRL BPE tokenizer. Peculiarities:
        - Byte-level Byte-Pair-Encoding
        - Requires a space to start the input string => the encoding methods should be called with the
          ``add_prefix_space`` flag set to ``True``.
          Otherwise, this tokenizer ``encode`` and ``decode`` method will not conserve
          the absence of a space at the beginning of a string: `tokenizer.decode(tokenizer.encode("Hello")) = " Hello"`
    """
    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

    def __init__(self, vocab_file, merges_file, unk_token="<unk>", **kwargs):
        super(CTRLTokenizer, self).__init__(unk_token=unk_token, **kwargs)
        self.max_len_single_sentence = self.max_len # no default special tokens - you can update this value if you add special tokens
        self.max_len_sentences_pair = self.max_len # no default special tokens - you can update this value if you add special tokens

        try:
            import ftfy
            from spacy.lang.en import English
            _nlp = English()
            self.nlp = _nlp.Defaults.create_tokenizer(_nlp)
            self.fix_text = ftfy.fix_text
        except ImportError:
            logger.warning("ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.")
            self.nlp = BasicTokenizer(do_lower_case=True)
            self.fix_text = None

        self.encoder = json.load(open(vocab_file, encoding="utf-8"))
        self.decoder = {v:k for k,v in self.encoder.items()}
        merges = open(merges_file, encoding='utf-8').read().split('\n')[1:-1]
        merges = [tuple(merge.split()) for merge in merges]
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {}

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

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

        if not pairs:
            return token

        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:
                    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)
        word = word[:-4]
        self.cache[token] = word
        return word

    def _tokenize(self, text):
        """ Tokenize a string.
        """
        split_tokens = []
        if self.fix_text is None:
            # Using BERT's BasicTokenizer
            text = self.nlp.tokenize(text)
            for token in text:
                split_tokens.extend([t for t in self.bpe(token).split(' ')])
        else:
            # Using SpaCy & ftfy (original tokenization process of OpenAI GPT)
            text = self.nlp(text_standardize(self.fix_text(text)))
            for token in text:
                split_tokens.extend([t for t in self.bpe(token.text.lower()).split(' ')])
        # for token in text.split():
        #     if sys.version_info[0] == 2:
        #         token = ''.join(self.byte_encoder[ord(b)] for b in token) # Maps all our bytes to unicode strings, avoiding controle tokens of the BPE (spaces in our case)
        #     else:
        #         token = ''.join(self.byte_encoder[b] for b in token.encode('utf-8')) # Maps all our bytes to unicode strings, avoiding controle tokens of the BPE (spaces in our case)
        #     bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(' '))
        return split_tokens

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

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

    def convert_tokens_to_string(self, tokens):
        """ Converts a sequence of tokens (string) in a single string. """
        out_string = ''.join(tokens).replace('@@', ' ').strip()
        return out_string

    def save_vocabulary(self, save_directory):
        """Save the tokenizer vocabulary and merge files to a directory."""
        if not os.path.isdir(save_directory):
            logger.error("Vocabulary path ({}) should be a directory".format(save_directory))
            return
        vocab_file = os.path.join(save_directory, VOCAB_FILES_NAMES['vocab_file'])
        merge_file = os.path.join(save_directory, VOCAB_FILES_NAMES['merges_file'])

        with open(vocab_file, 'w', encoding='utf-8') as f:
            f.write(json.dumps(self.encoder, ensure_ascii=False))

        index = 0
        with open(merge_file, "w", encoding="utf-8") as writer:
            writer.write(u'#version: 0.2\n')
            for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning("Saving vocabulary to {}: BPE merge indices are not consecutive."
                                   " Please check that the tokenizer is not corrupted!".format(merge_file))
                    index = token_index
                writer.write(' '.join(bpe_tokens) + u'\n')
                index += 1

        return vocab_file, merge_file

    # def decode(self, token_ids, skip_special_tokens=False, clean_up_tokenization_spaces=True):
    #     filtered_tokens = ' '.join(self.convert_ids_to_tokens(token_ids, skip_special_tokens=skip_special_tokens))
    #     tokens_generated_so_far = re.sub('(@@ )', '', string=filtered_tokens)
    #     tokens_generated_so_far = re.sub('(@@ ?$)', '', string=tokens_generated_so_far)
    #     return ''.join(tokens_generated_so_far)