NumBertTokenizer.py

import collections
import os
import unicodedata
from typing import List, Optional, Tuple

from transformers.models.bert.tokenization_bert import VOCAB_FILES_NAMES, PRETRAINED_VOCAB_FILES_MAP, \
    PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES, PRETRAINED_INIT_CONFIGURATION, load_vocab, BasicTokenizer, \
    whitespace_tokenize,_is_whitespace,_is_control,_is_punctuation
from transformers.tokenization_utils import PreTrainedTokenizer
from transformers.utils import logging

logger = logging.get_logger(__name__)


class NumBertTokenizer(PreTrainedTokenizer):
    r"""
    Construct a BERT tokenizer. Based on WordPiece.

    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods.
    Users should refer to this superclass for more information regarding those methods.

    Args:
        vocab_file (:obj:`str`):
            File containing the vocabulary.
        do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not to lowercase the input when tokenizing.
        do_basic_tokenize (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not to do basic tokenization before WordPiece.
        never_split (:obj:`Iterable`, `optional`):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            :obj:`do_basic_tokenize=True`
        unk_token (:obj:`str`, `optional`, defaults to :obj:`"[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.
        sep_token (:obj:`str`, `optional`, defaults to :obj:`"[SEP]"`):
            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
            sequence classification or for a text and a question for question answering. It is also used as the last
            token of a sequence built with special tokens.
        pad_token (:obj:`str`, `optional`, defaults to :obj:`"[PAD]"`):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (:obj:`str`, `optional`, defaults to :obj:`"[CLS]"`):
            The classifier token which is used when doing sequence classification (classification of the whole sequence
            instead of per-token classification). It is the first token of the sequence when built with special tokens.
        mask_token (:obj:`str`, `optional`, defaults to :obj:`"[MASK]"`):
            The token used for masking values. This is the token used when training this model with masked language
            modeling. This is the token which the model will try to predict.
        tokenize_chinese_chars (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not to tokenize Chinese characters.

            This should likely be deactivated for Japanese (see this `issue
            <https://github.com/huggingface/transformers/issues/328>`__).
        strip_accents: (:obj:`bool`, `optional`):
            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
            value for :obj:`lowercase` (as in the original BERT).
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
    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,
            strip_accents=None,
            **kwargs
    ):
        super().__init__(
            do_lower_case=do_lower_case,
            do_basic_tokenize=do_basic_tokenize,
            never_split=never_split,
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            tokenize_chinese_chars=tokenize_chinese_chars,
            strip_accents=strip_accents,
            **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 = NumBERTBasicTokenizer(
                do_lower_case=do_lower_case,
                never_split=never_split,
                tokenize_chinese_chars=tokenize_chinese_chars,
                strip_accents=strip_accents,
            )
        self.wordpiece_tokenizer = NumberWordpieceTokenizer(vocab=self.vocab, unk_token=self.unk_token)

    @property
    def do_lower_case(self):
        return self.basic_tokenizer.do_lower_case

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

    def get_vocab(self):
        return dict(self.vocab, **self.added_tokens_encoder)

    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):

                # If the token is part of the never_split set
                if token in self.basic_tokenizer.never_split:
                    split_tokens.append(token)
                else:
                    split_tokens += self.wordpiece_tokenizer.tokenize(token)
        else:
            split_tokens = self.wordpiece_tokenizer.tokenize(text)
        return split_tokens

    def _convert_token_to_id(self, token):
        """ Converts a token (str) 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 (str) 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 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 BERT sequence has the following format:

        - single sequence: ``[CLS] X [SEP]``
        - pair of sequences: ``[CLS] A [SEP] B [SEP]``

        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.

        Returns:
            :obj:`List[int]`: List of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
        """
        if token_ids_1 is None:
            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
        cls = [self.cls_token_id]
        sep = [self.sep_token_id]
        return cls + token_ids_0 + sep + token_ids_1 + sep

    def get_special_tokens_mask(
            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None,
            already_has_special_tokens: bool = False
    ) -> List[int]:
        """
        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer ``prepare_for_model`` method.

        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """

        if already_has_special_tokens:
            if token_ids_1 is not None:
                raise ValueError(
                    "You should not supply a second sequence if the provided sequence of "
                    "ids is already formatted with special tokens for the model."
                )
            return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))

        if token_ids_1 is not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1]

    def create_token_type_ids_from_sequences(
            self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Create a mask from the two sequences passed to be used in a sequence-pair classification task. A BERT sequence
        pair mask has the following format:

        ::

            0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
            | first sequence    | second sequence |

        If :obj:`token_ids_1` is :obj:`None`, this method only returns the first portion of the mask (0s).

        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs.
            token_ids_1 (:obj:`List[int]`, `optional`):
                Optional second list of IDs for sequence pairs.

        Returns:
            :obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
            sequence(s).
        """
        sep = [self.sep_token_id]
        cls = [self.cls_token_id]
        if token_ids_1 is None:
            return len(cls + token_ids_0 + sep) * [0]
        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        index = 0
        if os.path.isdir(save_directory):
            vocab_file = os.path.join(
                save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
            )
        else:
            vocab_file = (filename_prefix + "-" if filename_prefix else "") + save_directory
        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 + "\n")
                index += 1
        return (vocab_file,)


class NumberWordpieceTokenizer(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, :obj:`input = "unaffable"` wil return as output :obj:`["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

            ########## Code changed for the number tokenization ##############
            chars_copy = chars.copy()
            if "." in chars_copy:
                chars_copy.remove(".")
            if "," in chars_copy:
                chars_copy.remove(",")
            if all([s.isdigit for s in chars_copy]):
                for index, char in enumerate(chars):
                    if index == 0:
                        output_tokens.append(char)
                    else:
                        output_tokens.append("##" + char)
            ########## end change ##############
            else:
                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


class NumBERTBasicTokenizer(object):
    """
    Constructs a BasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).

    Args:
        do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not to lowercase the input when tokenizing.
        never_split (:obj:`Iterable`, `optional`):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            :obj:`do_basic_tokenize=True`
        tokenize_chinese_chars (:obj:`bool`, `optional`, defaults to :obj:`True`):
            Whether or not to tokenize Chinese characters.

            This should likely be deactivated for Japanese (see this `issue
            <https://github.com/huggingface/transformers/issues/328>`__).
        strip_accents: (:obj:`bool`, `optional`):
            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
            value for :obj:`lowercase` (as in the original BERT).
    """

    def __init__(self, do_lower_case=True, never_split=None, tokenize_chinese_chars=True, strip_accents=None):
        if never_split is None:
            never_split = []
        self.do_lower_case = do_lower_case
        self.never_split = set(never_split)
        self.tokenize_chinese_chars = tokenize_chinese_chars
        self.strip_accents = strip_accents

    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.
        """
        # union() returns a new set by concatenating the two sets.
        never_split = self.never_split.union(set(never_split)) if never_split else self.never_split
        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 token not in never_split:
                if self.do_lower_case:
                    token = token.lower()
                    if self.strip_accents is not False:
                        token = self._run_strip_accents(token)
                elif self.strip_accents:
                    token = self._run_strip_accents(token)
            split_tokens.extend(self._run_split_on_punc(token, never_split))

        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 = []

        ########## Code changed for the number tokenization ##############
        chars_copy = chars.copy()
        if "." in chars_copy:
            chars_copy.remove(".")
        if "," in chars_copy:
            chars_copy.remove(",")
        if all([s.isdigit for s in chars_copy]):
            return [text]
        ########## end change ##############
        else:
            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):
                output.append(" ")
                output.append(char)
                output.append(" ")
            else:
                output.append(char)
        return "".join(output)

    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)