tokenizations/tokenization_bert_word_level.py

# coding=utf-8
# Copyright 2018 The Google AI Language 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."""

from __future__ import absolute_import, division, print_function, unicode_literals

import collections
import logging
import os
import unicodedata
import thulac
from io import open

from transformers.tokenization_utils import PreTrainedTokenizer

logger = logging.getLogger(__name__)

lac = thulac.thulac(user_dict='tokenizations/thulac_dict/seg', seg_only=True)

VOCAB_FILES_NAMES = {'vocab_file': 'vocab.txt'}

PRETRAINED_VOCAB_FILES_MAP = {
    'vocab_file':
    {
        'bert-base-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt",
        'bert-large-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt",
        'bert-base-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt",
        'bert-large-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt",
        'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt",
        'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt",
        'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt",
        'bert-base-german-cased': "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased-vocab.txt",
        'bert-large-uncased-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-vocab.txt",
        'bert-large-cased-whole-word-masking': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-vocab.txt",
        'bert-large-uncased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-vocab.txt",
        'bert-large-cased-whole-word-masking-finetuned-squad': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-vocab.txt",
        'bert-base-cased-finetuned-mrpc': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-vocab.txt",
    }
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    'bert-base-uncased': 512,
    'bert-large-uncased': 512,
    'bert-base-cased': 512,
    'bert-large-cased': 512,
    'bert-base-multilingual-uncased': 512,
    'bert-base-multilingual-cased': 512,
    'bert-base-chinese': 512,
    'bert-base-german-cased': 512,
    'bert-large-uncased-whole-word-masking': 512,
    'bert-large-cased-whole-word-masking': 512,
    'bert-large-uncased-whole-word-masking-finetuned-squad': 512,
    'bert-large-cased-whole-word-masking-finetuned-squad': 512,
    'bert-base-cased-finetuned-mrpc': 512,
}

def load_vocab(vocab_file):
    """Loads a vocabulary file into a dictionary."""
    vocab = collections.OrderedDict()
    with open(vocab_file, "r", encoding="utf-8") as reader:
        tokens = reader.readlines()
    for index, token in enumerate(tokens):
        token = token.rstrip('\n')
        vocab[token] = index
    return vocab


def whitespace_tokenize(text):
    """Runs basic whitespace cleaning and splitting on a piece of text."""
    text = text.strip()
    if not text:
        return []
    tokens = text.split()
    return tokens


class BertTokenizer(PreTrainedTokenizer):
    r"""
    Constructs a BertTokenizer.
    :class:`~pytorch_pretrained_bert.BertTokenizer` runs end-to-end tokenization: punctuation splitting + wordpiece

    Args:
        vocab_file: Path to a one-wordpiece-per-line vocabulary file
        do_lower_case: Whether to lower case the input. Only has an effect when do_wordpiece_only=False
        do_basic_tokenize: Whether to do basic tokenization before wordpiece.
        max_len: An artificial maximum length to truncate tokenized_doupo sequences to; Effective maximum length is always the
            minimum of this value (if specified) and the underlying BERT model's sequence length.
        never_split: List of tokens which will never be split during tokenization. Only has an effect when
            do_wordpiece_only=False
    """

    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, do_lower_case=True, do_basic_tokenize=True, never_split=None,
                 unk_token="[UNK]", sep_token="[SEP]", pad_token="[PAD]", cls_token="[CLS]",
                 mask_token="[MASK]", tokenize_chinese_chars=True, **kwargs):
        """Constructs a BertTokenizer.

        Args:
            **vocab_file**: Path to a one-wordpiece-per-line vocabulary file
            **do_lower_case**: (`optional`) boolean (default True)
                Whether to lower case the input
                Only has an effect when do_basic_tokenize=True
            **do_basic_tokenize**: (`optional`) boolean (default True)
                Whether to do basic tokenization before wordpiece.
            **never_split**: (`optional`) list of string
                List of tokens which will never be split during tokenization.
                Only has an effect when do_basic_tokenize=True
            **tokenize_chinese_chars**: (`optional`) boolean (default True)
                Whether to tokenize Chinese characters.
                This should likely be desactivated for Japanese:
                see: https://github.com/huggingface/pytorch-pretrained-BERT/issues/328
        """
        super(BertTokenizer, self).__init__(unk_token=unk_token, sep_token=sep_token,
                                            pad_token=pad_token, cls_token=cls_token,
                                            mask_token=mask_token, **kwargs)
        if not os.path.isfile(vocab_file):
            raise ValueError(
                "Can't find a vocabulary file at path '{}'. To load the vocabulary from a Google pretrained "
                "model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`".format(vocab_file))
        self.vocab = load_vocab(vocab_file)
        self.ids_to_tokens = collections.OrderedDict(
            [(ids, tok) for tok, ids in self.vocab.items()])
        self.do_basic_tokenize = do_basic_tokenize
        if do_basic_tokenize:
            self.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case,
                                                  never_split=never_split,
                                                  tokenize_chinese_chars=tokenize_chinese_chars)
        self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab, unk_token=self.unk_token)

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

    def _tokenize(self, text):
        split_tokens = []
        if self.do_basic_tokenize:
            for token in self.basic_tokenizer.tokenize(text, never_split=self.all_special_tokens):
                for sub_token in self.wordpiece_tokenizer.tokenize(token):
                    split_tokens.append(sub_token)
        else:
            split_tokens = self.wordpiece_tokenizer.tokenize(text)
        return split_tokens

    def _convert_token_to_id(self, token):
        """ Converts a token (str/unicode) 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 (string/unicode) using the vocab."""
        return self.ids_to_tokens.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, vocab_path):
        """Save the tokenizer vocabulary to a directory or file."""
        index = 0
        if os.path.isdir(vocab_path):
            vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES['vocab_file'])
        with open(vocab_file, "w", encoding="utf-8") as writer:
            for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning("Saving vocabulary to {}: vocabulary indices are not consecutive."
                                   " Please check that the vocabulary is not corrupted!".format(vocab_file))
                    index = token_index
                writer.write(token + u'\n')
                index += 1
        return (vocab_file,)

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs):
        """ Instantiate a BertTokenizer from pre-trained vocabulary files.
        """
        if pretrained_model_name_or_path in PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES:
            if '-cased' in pretrained_model_name_or_path and kwargs.get('do_lower_case', True):
                logger.warning("The pre-trained model you are loading is a cased model but you have not set "
                               "`do_lower_case` to False. We are setting `do_lower_case=False` for you but "
                               "you may want to check this behavior.")
                kwargs['do_lower_case'] = False
            elif '-cased' not in pretrained_model_name_or_path and not kwargs.get('do_lower_case', True):
                logger.warning("The pre-trained model you are loading is an uncased model but you have set "
                               "`do_lower_case` to False. We are setting `do_lower_case=True` for you "
                               "but you may want to check this behavior.")
                kwargs['do_lower_case'] = True

        return super(BertTokenizer, cls)._from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)


class BasicTokenizer(object):
    """Runs basic tokenization (punctuation splitting, lower casing, etc.)."""

    def __init__(self, do_lower_case=True, never_split=None, tokenize_chinese_chars=True):
        """ Constructs a BasicTokenizer.

        Args:
            **do_lower_case**: Whether to lower case the input.
            **never_split**: (`optional`) list of str
                Kept for backward compatibility purposes.
                Now implemented directly at the base class level (see :func:`PreTrainedTokenizer.tokenize`)
                List of token not to split.
            **tokenize_chinese_chars**: (`optional`) boolean (default True)
                Whether to tokenize Chinese characters.
                This should likely be desactivated for Japanese:
                see: https://github.com/huggingface/pytorch-pretrained-BERT/issues/328
        """
        if never_split is None:
            never_split = []
        self.do_lower_case = do_lower_case
        self.never_split = never_split
        self.tokenize_chinese_chars = tokenize_chinese_chars

    def tokenize(self, text, never_split=None):
        """ Basic Tokenization of a piece of text.
            Split on "white spaces" only, for sub-word tokenization, see WordPieceTokenizer.

        Args:
            **never_split**: (`optional`) list of str
                Kept for backward compatibility purposes.
                Now implemented directly at the base class level (see :func:`PreTrainedTokenizer.tokenize`)
                List of token not to split.
        """
        never_split = self.never_split + (never_split if never_split is not None else [])
        text = self._clean_text(text)
        # This was added on November 1st, 2018 for the multilingual and Chinese
        # models. This is also applied to the English models now, but it doesn't
        # matter since the English models were not trained on any Chinese data
        # and generally don't have any Chinese data in them (there are Chinese
        # characters in the vocabulary because Wikipedia does have some Chinese
        # words in the English Wikipedia.).
        if self.tokenize_chinese_chars:
            text = self._tokenize_chinese_chars(text)
        orig_tokens = whitespace_tokenize(text)
        split_tokens = []
        for token in orig_tokens:
            if self.do_lower_case and token not in never_split:
                token = token.lower()
                token = self._run_strip_accents(token)
            split_tokens.extend(self._run_split_on_punc(token))

        output_tokens = whitespace_tokenize(" ".join(split_tokens))
        return output_tokens

    def _run_strip_accents(self, text):
        """Strips accents from a piece of text."""
        text = unicodedata.normalize("NFD", text)
        output = []
        for char in text:
            cat = unicodedata.category(char)
            if cat == "Mn":
                continue
            output.append(char)
        return "".join(output)

    def _run_split_on_punc(self, text, never_split=None):
        """Splits punctuation on a piece of text."""
        if never_split is not None and text in never_split:
            return [text]
        chars = list(text)
        i = 0
        start_new_word = True
        output = []
        while i < len(chars):
            char = chars[i]
            if _is_punctuation(char):
                output.append([char])
                start_new_word = True
            else:
                if start_new_word:
                    output.append([])
                start_new_word = False
                output[-1].append(char)
            i += 1

        return ["".join(x) for x in output]

    # def _tokenize_chinese_chars(self, text):
    #     """Adds whitespace around any CJK character."""
    #     output = []
    #     for char in text:
    #         cp = ord(char)
    #         if self._is_chinese_char(cp) or char.isdigit():
    #             output.append(" ")
    #             output.append(char)
    #             output.append(" ")
    #         else:
    #             output.append(char)
    #     return "".join(output)
    def _tokenize_chinese_chars(self, text):
        """Adds whitespace around any CJK character."""
        output = []
        for char in text:
            if char.isdigit():
                output.append(" ")
                output.append(char)
                output.append(" ")
            else:
                output.append(char)
        text = "".join(output)
        text = [item[0].strip() for item in lac.cut(text)]
        text = [item for item in text if item]
        return " ".join(text)

    def _is_chinese_char(self, cp):
        """Checks whether CP is the codepoint of a CJK character."""
        # This defines a "chinese character" as anything in the CJK Unicode block:
        #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
        #
        # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
        # despite its name. The modern Korean Hangul alphabet is a different block,
        # as is Japanese Hiragana and Katakana. Those alphabets are used to write
        # space-separated words, so they are not treated specially and handled
        # like the all of the other languages.
        if ((cp >= 0x4E00 and cp <= 0x9FFF) or  #
                (cp >= 0x3400 and cp <= 0x4DBF) or  #
                (cp >= 0x20000 and cp <= 0x2A6DF) or  #
                (cp >= 0x2A700 and cp <= 0x2B73F) or  #
                (cp >= 0x2B740 and cp <= 0x2B81F) or  #
                (cp >= 0x2B820 and cp <= 0x2CEAF) or
                (cp >= 0xF900 and cp <= 0xFAFF) or  #
                (cp >= 0x2F800 and cp <= 0x2FA1F)):  #
            return True

        return False

    def _clean_text(self, text):
        """Performs invalid character removal and whitespace cleanup on text."""
        output = []
        for char in text:
            cp = ord(char)
            if cp == 0 or cp == 0xfffd or _is_control(char):
                continue
            if _is_whitespace(char):
                output.append(" ")
            else:
                output.append(char)
        return "".join(output)


class WordpieceTokenizer(object):
    """Runs WordPiece tokenization."""

    def __init__(self, vocab, unk_token, max_input_chars_per_word=100):
        self.vocab = vocab
        self.unk_token = unk_token
        self.max_input_chars_per_word = max_input_chars_per_word

    def tokenize(self, text):
        """Tokenizes a piece of text into its word pieces.

        This uses a greedy longest-match-first algorithm to perform tokenization
        using the given vocabulary.

        For example:
          input = "unaffable"
          output = ["un", "##aff", "##able"]

        Args:
          text: A single token or whitespace separated tokens. This should have
            already been passed through `BasicTokenizer`.

        Returns:
          A list of wordpiece tokens.
        """

        output_tokens = []
        for token in whitespace_tokenize(text):
            chars = list(token)
            if len(chars) > self.max_input_chars_per_word:
                output_tokens.append(self.unk_token)
                continue

            is_bad = False
            start = 0
            sub_tokens = []
            while start < len(chars):
                end = len(chars)
                cur_substr = None
                while start < end:
                    substr = "".join(chars[start:end])
                    if start > 0:
                        substr = "##" + substr
                    if substr in self.vocab:
                        cur_substr = substr
                        break
                    end -= 1
                if cur_substr is None:
                    is_bad = True
                    break
                sub_tokens.append(cur_substr)
                start = end

            if is_bad:
                output_tokens.append(self.unk_token)
            else:
                output_tokens.extend(sub_tokens)
        return output_tokens


def _is_whitespace(char):
    """Checks whether `chars` is a whitespace character."""
    # \t, \n, and \r are technically contorl characters but we treat them
    # as whitespace since they are generally considered as such.
    if char == " " or char == "\t" or char == "\n" or char == "\r":
        return True
    cat = unicodedata.category(char)
    if cat == "Zs":
        return True
    return False


def _is_control(char):
    """Checks whether `chars` is a control character."""
    # These are technically control characters but we count them as whitespace
    # characters.
    if char == "\t" or char == "\n" or char == "\r":
        return False
    cat = unicodedata.category(char)
    if cat.startswith("C"):
        return True
    return False


def _is_punctuation(char):
    """Checks whether `chars` is a punctuation character."""
    cp = ord(char)
    # We treat all non-letter/number ASCII as punctuation.
    # Characters such as "^", "$", and "`" are not in the Unicode
    # Punctuation class but we treat them as punctuation anyways, for
    # consistency.
    if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or
            (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)):
        return True
    cat = unicodedata.category(char)
    if cat.startswith("P"):
        return True
    return False