Method _encode_plus

bert/tokenization_utils.py:402–474

(
        self,
        text: Union[TextInput, PreTokenizedInput, EncodedInput],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_pretokenized: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs
    )

        raise NotImplementedError

    def _encode_plus(
        self,
        text: Union[TextInput, PreTokenizedInput, EncodedInput],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_pretokenized: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs
    ) -> BatchEncoding:
        def get_input_ids(text):
            if isinstance(text, str):
                tokens = self.tokenize(text, **kwargs)
                return self.convert_tokens_to_ids(tokens)
            elif isinstance(text, (list, tuple)) and len(text) > 0 and isinstance(text[0], str):
                if is_pretokenized:
                    tokens = list(itertools.chain(*(self.tokenize(t, is_pretokenized=True, **kwargs) for t in text)))
                    return self.convert_tokens_to_ids(tokens)
                else:
                    return self.convert_tokens_to_ids(text)
            elif isinstance(text, (list, tuple)) and len(text) > 0 and isinstance(text[0], int):
                return text
            else:
                if is_pretokenized:
                    raise ValueError(
                        f"Input {text} is not valid. Should be a string or a list/tuple of strings when `is_pretokenized=True`."
                    )
                else:
                    raise ValueError(
                        f"Input {text} is not valid. Should be a string, a list/tuple of strings or a list/tuple of integers."
                    )

        if return_offsets_mapping:
            raise NotImplementedError(
                "return_offset_mapping is not available when using Python tokenizers."
                "To use this feature, change your tokenizer to one deriving from "
                "transformers.PreTrainedTokenizerFast."
                "More information on available tokenizers at "
                "https://github.com/huggingface/transformers/pull/2674"
            )

        first_ids = get_input_ids(text)
        second_ids = get_input_ids(text_pair) if text_pair is not None else None

        return self.prepare_for_model(
            first_ids,
            pair_ids=second_ids,