Method _batch_encode_plus

bert/tokenization_utils.py:476–557

(
        self,
        batch_text_or_text_pairs: Union[
            List[TextInput],
            List[TextInputPair],
            List[PreTokenizedInput],
            List[PreTokenizedInputPair],
            List[EncodedInput],
            List[EncodedInputPair],
        ],
        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
    )

        )

    def _batch_encode_plus(
        self,
        batch_text_or_text_pairs: Union[
            List[TextInput],
            List[TextInputPair],
            List[PreTokenizedInput],
            List[PreTokenizedInputPair],
            List[EncodedInput],
            List[EncodedInputPair],
        ],
        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:
                raise ValueError(
                    "Input 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."
            )

        input_ids = []
        for ids_or_pair_ids in batch_text_or_text_pairs:
            if not isinstance(ids_or_pair_ids, (list, tuple)):
                ids, pair_ids = ids_or_pair_ids, None
            elif is_pretokenized and not isinstance(ids_or_pair_ids[0], (list, tuple)):
                ids, pair_ids = ids_or_pair_ids, None
            else: