# Copyright 2021 The Google AI Language Team Authors. # # 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 from __future__ import division from __future__ import print_function import collections import unicodedata import six import sentencepiece as sp from reader import gpt2_bpe_utils from reader.vocabulary import Vocabulary from nltk import tokenize 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() fin = open(vocab_file) for num, line in enumerate(fin): items = convert_to_unicode(line.strip()).split("\t") if len(items) > 2: break token = items[0] index = items[1] if len(items) == 2 else num token = token.strip() vocab[token] = int(index) return vocab def convert_by_vocab(vocab, items): """Converts a sequence of [tokens|ids] using the vocab.""" output = [] for item in items: output.append(vocab[item]) return output def convert_tokens_to_ids_include_unk(vocab, tokens, unk_token="[UNK]"): output = [] for token in tokens: if token in vocab: output.append(vocab[token]) else: output.append(vocab[unk_token]) return output def convert_tokens_to_ids(vocab, tokens): return convert_by_vocab(vocab, tokens) def convert_ids_to_tokens(inv_vocab, ids): return convert_by_vocab(inv_vocab, ids) def whitespace_tokenize(text): """Runs basic whitespace cleaning and splitting on a peice of text.""" text = text.strip() if not text: return [] tokens = text.split() return tokens class FullTokenizer(object): """Runs end-to-end tokenziation.""" def __init__(self, vocab_file, do_lower_case=True): self.vocab = load_vocab(vocab_file) self.inv_vocab = {v: k for k, v in self.vocab.items()} self.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case) self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab) 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): return convert_by_vocab(self.vocab, tokens) def convert_ids_to_tokens(self, ids): return convert_by_vocab(self.inv_vocab, ids) class CharTokenizer(object): """Runs end-to-end tokenziation.""" def __init__(self, vocab_file, do_lower_case=True): self.vocab = load_vocab(vocab_file) self.inv_vocab = {v: k for k, v in self.vocab.items()} self.tokenizer = WordpieceTokenizer(vocab=self.vocab) def tokenize(self, text): split_tokens = [] for token in text.lower().split(" "): for sub_token in self.tokenizer.tokenize(token): split_tokens.append(sub_token) return split_tokens def convert_tokens_to_ids(self, tokens): return convert_by_vocab(self.vocab, tokens) def convert_ids_to_tokens(self, ids): return convert_by_vocab(self.inv_vocab, ids) class BasicTokenizer(object): """Runs basic tokenization (punctuation splitting, lower casing, etc.).""" def __init__(self, do_lower_case=True): """Constructs a BasicTokenizer. Args: do_lower_case: Whether to lower case the input. """ self.do_lower_case = do_lower_case def tokenize(self, text): """Tokenizes a piece of text.""" text = convert_to_unicode(text) 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.). text = self._tokenize_chinese_chars(text) orig_tokens = whitespace_tokenize(text) split_tokens = [] for token in orig_tokens: if self.do_lower_case: 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.""" 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 SentencepieceTokenizer(object): """Runs SentencePiece tokenziation.""" def __init__(self, vocab_file, do_lower_case=True, unk_token="[UNK]"): self.vocab = load_vocab(vocab_file) self.inv_vocab = {v: k for k, v in self.vocab.items()} self.do_lower_case = do_lower_case self.tokenizer = sp.SentencePieceProcessor() self.tokenizer.Load(vocab_file + ".model") self.sp_unk_token = "" self.unk_token = unk_token def tokenize(self, text): """Tokenizes a piece of text into its word pieces. Returns: A list of wordpiece tokens. """ text = text.lower() if self.do_lower_case else text text = convert_to_unicode(text.replace("\1", " ")) tokens = self.tokenizer.EncodeAsPieces(text) output_tokens = [] for token in tokens: if token == self.sp_unk_token: token = self.unk_token if token in self.vocab: output_tokens.append(token) else: output_tokens.append(self.unk_token) return output_tokens def convert_tokens_to_ids(self, tokens): return convert_by_vocab(self.vocab, tokens) def convert_ids_to_tokens(self, ids): return convert_by_vocab(self.inv_vocab, ids) class WordsegTokenizer(object): """Runs Wordseg tokenziation.""" def __init__(self, vocab_file, do_lower_case=True, unk_token="[UNK]", split_token="\1"): self.vocab = load_vocab(vocab_file) self.inv_vocab = {v: k for k, v in self.vocab.items()} self.tokenizer = sp.SentencePieceProcessor() self.tokenizer.Load(vocab_file + ".model") self.do_lower_case = do_lower_case self.unk_token = unk_token self.split_token = split_token def tokenize(self, text): """Tokenizes a piece of text into its word pieces. Returns: A list of wordpiece tokens. """ text = text.lower() if self.do_lower_case else text text = convert_to_unicode(text) output_tokens = [] for token in text.split(self.split_token): if token in self.vocab: output_tokens.append(token) else: sp_tokens = self.tokenizer.EncodeAsPieces(token) for sp_token in sp_tokens: if sp_token in self.vocab: output_tokens.append(sp_token) return output_tokens def convert_tokens_to_ids(self, tokens): return convert_by_vocab(self.vocab, tokens) def convert_ids_to_tokens(self, ids): return convert_by_vocab(self.inv_vocab, ids) class WordpieceTokenizer(object): """Runs WordPiece tokenziation.""" 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. """ text = convert_to_unicode(text) 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 class BPETokenizer(object): """ Runs bpe tokenize """ def __init__(self, vocab_file, encoder_json_path="./configs/encoder.json", vocab_bpe_path="./configs/vocab.bpe", params=None): self.vocabulary = Vocabulary(vocab_file, unk_token="[UNK]") self.encoder = gpt2_bpe_utils.get_encoder(encoder_json_path, vocab_bpe_path) def tokenize(self, text, is_sentencepiece=True): text = convert_to_unicode(text) text = " ".join(text.split()) # remove duplicate whitespace if is_sentencepiece: sents = tokenize.sent_tokenize(text) bpe_ids = sum([self.encoder.encode(sent) for sent in sents], []) else: bpe_ids = self.encoder.encode(text) tokens = [str(bpe_id) for bpe_id in bpe_ids] return tokens def convert_tokens_to_ids(self, tokens): """ :param tokens: :return: """ return self.vocabulary.convert_tokens_to_ids(tokens) def convert_ids_to_tokens(self, ids): """ :param ids: :return: """ return self.vocabulary.convert_ids_to_tokens(ids) 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 def tokenize_chinese_chars(text): """Adds whitespace around any CJK character.""" def _is_chinese_char(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 output = [] buff = "" for char in text: cp = ord(char) if _is_chinese_char(cp): if buff != "": output.append(buff) buff = "" output.append(char) else: buff += char if buff != "": output.append(buff) return output