tokenization_openai.py

# coding=utf-8
# Copyright 2018 The Open AI Team Authors 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 OpenAI GPT."""
from __future__ import (absolute_import, division, print_function,
                        unicode_literals)

import json
import logging
import os
import re
import sys
from io import open

from tqdm import tqdm

from .file_utils import cached_path
from .tokenization_utils import PreTrainedTokenizer, clean_up_tokenization
from .tokenization_bert import BasicTokenizer

logger = logging.getLogger(__name__)

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

PRETRAINED_VOCAB_FILES_MAP = {
    'vocab_file':
    {
        'openai-gpt': "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-vocab.json",
    },
    'merges_file':
    {
        'openai-gpt': "https://s3.amazonaws.com/models.huggingface.co/bert/openai-gpt-merges.txt",
    },
    'special_tokens_file':
    {
        'openai-gpt': None,
    }
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    'openai-gpt': 512,
}

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

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()

class OpenAIGPTTokenizer(PreTrainedTokenizer):
    """
    BPE tokenizer. Peculiarities:
        - lower case all inputs
        - uses SpaCy tokenizer and ftfy for pre-BPE tokenization if they are installed, fallback to BERT's BasicTokenizer if not.
        - argument special_tokens and function set_special_tokens:
            can be used to add additional symbols (ex: "__classify__") to a vocabulary.
    """
    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, special_tokens_file=None, special_tokens=None, max_len=None):
        try:
            import ftfy
            import spacy
            self.nlp = spacy.load('en', disable=['parser', 'tagger', 'ner', 'textcat'])
            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,
                                      never_split=special_tokens if special_tokens is not None else [])
            self.fix_text = None

        self.max_len = max_len if max_len is not None else int(1e12)
        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 = {}

        all_special_tokens = []
        if special_tokens_file is not None:
            special_tokens_to_add = open(special_tokens_file, encoding='utf-8').read().split('\n')[:-1]
            all_special_tokens.extend(special_tokens_to_add)
        if special_tokens is not None and special_tokens:
            all_special_tokens.extend(special_tokens)

        self.special_tokens = {}
        self.special_tokens_decoder = {}
        self.set_special_tokens(all_special_tokens)

    def __len__(self):
        return len(self.encoder) + len(self.special_tokens)

    def set_special_tokens(self, special_tokens):
        """ Add a list of additional tokens to the encoder.
            The additional tokens are indexed starting from the last index of the
            current vocabulary in the order of the `special_tokens` list.
        """
        if not special_tokens:
            self.special_tokens = {}
            self.special_tokens_decoder = {}
            return
        self.special_tokens = dict((tok, len(self.encoder) + i) for i, tok in enumerate(special_tokens))
        self.special_tokens_decoder = {v:k for k, v in self.special_tokens.items()}
        if self.fix_text is None:
            # Using BERT's BasicTokenizer: we can update the tokenizer
            self.nlp.never_split = special_tokens
        logger.info("Special tokens {}".format(self.special_tokens))

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

    def convert_tokens_to_ids(self, tokens):
        """ Converts a sequence of tokens into ids using the vocab. """
        ids = []
        if isinstance(tokens, str) or (sys.version_info[0] == 2 and isinstance(tokens, unicode)):
            if tokens in self.special_tokens:
                return self.special_tokens[tokens]
            else:
                return self.encoder.get(tokens, 0)
        for token in tokens:
            if token in self.special_tokens:
                ids.append(self.special_tokens[token])
            else:
                ids.append(self.encoder.get(token, 0))
        if len(ids) > self.max_len:
            logger.warning(
                "Token indices sequence length is longer than the specified maximum "
                " sequence length for this OpenAI GPT model ({} > {}). Running this"
                " sequence through the model will result in indexing errors".format(len(ids), self.max_len)
            )
        return ids

    def convert_ids_to_tokens(self, ids, skip_special_tokens=False):
        """Converts a sequence of ids in BPE tokens using the vocab."""
        tokens = []
        for i in ids:
            if i in self.special_tokens_decoder:
                if not skip_special_tokens:
                    tokens.append(self.special_tokens_decoder[i])
            else:
                tokens.append(self.decoder[i])
        return tokens

    def encode(self, text):
        return self.convert_tokens_to_ids(self.tokenize(text))

    def decode(self, ids, skip_special_tokens=False, clean_up_tokenization_spaces=True):
        """Converts a sequence of ids in a string."""
        tokens = self.convert_ids_to_tokens(ids, skip_special_tokens=skip_special_tokens)
        out_string = ''.join(tokens).replace('</w>', ' ').strip()
        if clean_up_tokenization_spaces:
            out_string = out_string.replace('<unk>', '')
            out_string = clean_up_tokenization(out_string)
        return out_string

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

        index = len(self.encoder)
        with open(special_tokens_file, 'w', encoding='utf-8') as writer:
            for token, token_index in sorted(self.special_tokens.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning("Saving special tokens vocabulary to {}: BPE indices are not consecutive."
                                   " Please check that the tokenizer is not corrupted!".format(special_tokens_file))
                    index = token_index
                writer.write(token + u'\n')
                index += 1

        return vocab_file, merge_file, special_tokens_file