# coding=utf-8 # Copyright 2018 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 RetriBERT.""" import json from typing import Optional from tokenizers import normalizers from ....tokenization_utils_fast import PreTrainedTokenizerFast from ....utils import logging from .tokenization_retribert import RetriBertTokenizer logger = logging.get_logger(__name__) VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.json"} class RetriBertTokenizerFast(PreTrainedTokenizerFast): r""" Construct a "fast" RetriBERT tokenizer (backed by HuggingFace's *tokenizers* library). [`RetriBertTokenizerFast`] is identical to [`BertTokenizerFast`] and runs end-to-end tokenization: punctuation splitting and wordpiece. This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Args: vocab_file (`str`): File containing the vocabulary. do_lower_case (`bool`, *optional*, defaults to `True`): Whether or not to lowercase the input when tokenizing. unk_token (`str`, *optional*, defaults to `"[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 (`str`, *optional*, defaults to `"[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 (`str`, *optional*, defaults to `"[PAD]"`): The token used for padding, for example when batching sequences of different lengths. cls_token (`str`, *optional*, defaults to `"[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 (`str`, *optional*, defaults to `"[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. clean_text (`bool`, *optional*, defaults to `True`): Whether or not to clean the text before tokenization by removing any control characters and replacing all whitespaces by the classic one. tokenize_chinese_chars (`bool`, *optional*, defaults to `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 (`bool`, *optional*): Whether or not to strip all accents. If this option is not specified, then it will be determined by the value for `lowercase` (as in the original BERT). wordpieces_prefix (`str`, *optional*, defaults to `"##"`): The prefix for subwords. """ vocab_files_names = VOCAB_FILES_NAMES slow_tokenizer_class = RetriBertTokenizer model_input_names = ["input_ids", "attention_mask"] def __init__( self, vocab_file=None, tokenizer_file=None, do_lower_case=True, 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__( vocab_file, tokenizer_file=tokenizer_file, do_lower_case=do_lower_case, 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, ) normalizer_state = json.loads(self.backend_tokenizer.normalizer.__getstate__()) if ( normalizer_state.get("lowercase", do_lower_case) != do_lower_case or normalizer_state.get("strip_accents", strip_accents) != strip_accents or normalizer_state.get("handle_chinese_chars", tokenize_chinese_chars) != tokenize_chinese_chars ): normalizer_class = getattr(normalizers, normalizer_state.pop("type")) normalizer_state["lowercase"] = do_lower_case normalizer_state["strip_accents"] = strip_accents normalizer_state["handle_chinese_chars"] = tokenize_chinese_chars self.backend_tokenizer.normalizer = normalizer_class(**normalizer_state) self.do_lower_case = do_lower_case def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None): """ 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 (`List[int]`): List of IDs to which the special tokens will be added. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. Returns: `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens. """ output = [self.cls_token_id] + token_ids_0 + [self.sep_token_id] if token_ids_1 is not None: output += token_ids_1 + [self.sep_token_id] return output def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> tuple[str]: files = self._tokenizer.model.save(save_directory, name=filename_prefix) return tuple(files) __all__ = ["RetriBertTokenizerFast"]