Hetu/python/hetu/tokenizers/bert_tokenizer.py

from __future__ import absolute_import, division, print_function, unicode_literals

import collections
import os
import unicodedata
import six
from io import open

from .utils import cached_path

PRETRAINED_VOCAB_ARCHIVE_MAP = {
    '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",
}
PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP = {
    '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,
}
VOCAB_NAME = 'vocab.txt'


def convert_to_unicode(text):
    """Converts `text` to Unicode (if it's not already), assuming utf-8 input."""
    if six.PY3:
        if isinstance(text, str):
            return text
        elif isinstance(text, bytes):
            return text.decode("utf-8", "ignore")
        else:
            raise ValueError("Unsupported string type: %s" % (type(text)))
    elif six.PY2:
        if isinstance(text, str):
            return text.decode("utf-8", "ignore")
        elif isinstance(text, unicode):
            return text
        else:
            raise ValueError("Unsupported string type: %s" % (type(text)))
    else:
        raise ValueError("Not running on Python2 or Python 3?")


def load_vocab(vocab_file):
    """Loads a vocabulary file into a dictionary."""
    vocab = collections.OrderedDict()
    index = 0
    with open(vocab_file, "r", encoding="utf-8") as reader:
        while True:
            token = reader.readline()
            if not token:
                break
            token = token.strip()
            vocab[token] = index
            index += 1
    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(object):
    """Runs end-to-end tokenization: punctuation splitting + wordpiece"""

    def __init__(self, vocab_file, do_lower_case=True, max_len=None,
                 never_split=("[UNK]", "[SEP]", "[PAD]", "[CLS]", "[MASK]")):
        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.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case,
                                              never_split=never_split)
        self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab)
        self.max_len = max_len if max_len is not None else int(1e12)

    def tokenize(self, text):
        split_tokens = []
        for token in self.basic_tokenizer.tokenize(text):
            for sub_token in self.wordpiece_tokenizer.tokenize(token):
                split_tokens.append(sub_token)
        return split_tokens

    def convert_tokens_to_ids(self, tokens):
        """Converts a sequence of tokens into ids using the vocab."""
        ids = []
        for token in tokens:
            ids.append(self.vocab[token])
        if len(ids) > self.max_len:
            raise ValueError(
                "Token indices sequence length is longer than the specified maximum "
                " sequence length for this BERT model ({} > {}). Running this"
                " sequence through BERT will result in indexing errors".format(
                    len(ids), self.max_len)
            )
        return ids

    def convert_ids_to_tokens(self, ids):
        """Converts a sequence of ids in wordpiece tokens using the vocab."""
        tokens = []
        for i in ids:
            tokens.append(self.ids_to_tokens[i])
        return tokens

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path, cache_dir=None, *inputs, **kwargs):
        """
        Instantiate a PreTrainedBertModel from a pre-trained model file.
        Download and cache the pre-trained model file if needed.
        """
        if pretrained_model_name_or_path in PRETRAINED_VOCAB_ARCHIVE_MAP:
            vocab_file = PRETRAINED_VOCAB_ARCHIVE_MAP[pretrained_model_name_or_path]
        else:
            vocab_file = pretrained_model_name_or_path
        if os.path.isdir(vocab_file):
            vocab_file = os.path.join(vocab_file, VOCAB_NAME)
        # redirect to the cache, if necessary
        try:
            resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir)
        except EnvironmentError:
            print(
                "Model name '{}' was not found in model name list ({}). "
                "We assumed '{}' was a path or url but couldn't find any file "
                "associated to this path or url.".format(
                    pretrained_model_name_or_path,
                    ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()),
                    vocab_file))
            return None
        if resolved_vocab_file == vocab_file:
            print("loading vocabulary file {}".format(vocab_file))
        else:
            print("loading vocabulary file {} from cache at {}".format(
                vocab_file, resolved_vocab_file))
        if pretrained_model_name_or_path in PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP:
            # if we're using a pretrained model, ensure the tokenizer wont index sequences longer
            # than the number of positional embeddings
            max_len = PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP[pretrained_model_name_or_path]
            kwargs['max_len'] = min(kwargs.get('max_len', int(1e12)), max_len)
        # Instantiate tokenizer.
        tokenizer = cls(resolved_vocab_file, *inputs, **kwargs)
        return tokenizer


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

    def __init__(self,
                 do_lower_case=True,
                 never_split=("[UNK]", "[SEP]", "[PAD]", "[CLS]", "[MASK]")):
        """Constructs a BasicTokenizer.
        Args:
          do_lower_case: Whether to lower case the input.
        """
        self.do_lower_case = do_lower_case
        self.never_split = never_split

    def tokenize(self, text):
        """Tokenizes a piece of text."""
        text = self._clean_text(text)
        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 self.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):
        """Splits punctuation on a piece of text."""
        if text in self.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):
                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)


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

    def __init__(self, vocab, unk_token="[UNK]", 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