sgu!dZddlZddlmZmZmZddlmZddlm Z ddl m Z dd l m Z e jeZd d iZGd d e Zy)z'Fast Tokenization classes for Splinter.N)ListOptionalTuple) normalizers)PreTrainedTokenizerFast)logging)SplinterTokenizer vocab_filez vocab.txtceZdZdZeZeZ d fd Ze dZ d de e de e e de e fdZ d de e de e e de e fdZd d ed e edeefd ZxZS)SplinterTokenizerFasta Construct a "fast" Splinter tokenizer (backed by HuggingFace's *tokenizers* library). Based on 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. question_token (`str`, *optional*, defaults to `"[QUESTION]"`): The token used for constructing question representations. 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. c  t||f|||||||| | | fd | tj|jj j } | jd||k7s| jd| | k7r@tt| jd}|| d<| | d<|di| |j_||_ y)N) tokenizer_file do_lower_case unk_token sep_token pad_token cls_token mask_tokentokenize_chinese_chars strip_accentsadditional_special_tokens lowercasertype) super__init__jsonloadsbackend_tokenizer normalizer __getstate__getgetattrrpopr)selfr rrrrrrrquestion_tokenrrkwargs pre_tok_state pre_tok_class __class__s j/var/www/html/venv/lib/python3.12/site-packages/transformers/models/splinter/tokenization_splinter_fast.pyrzSplinterTokenizerFast.__init__Ms   )'!#9''5&7   4#9#9#D#D#Q#Q#ST   k= 9] J  -@MQ#K1B1B61JKM)6M+ &-:M/ *0=0N 0ND " " -*c8|j|jS)z `Optional[int]`: Id of the question token in the vocabulary, used to condition the answer on a question representation. )convert_tokens_to_idsr()r's r-question_token_idz'SplinterTokenizerFast.question_token_idws ))$*=*=>>r. token_ids_0 token_ids_1returnc||jg|z|jgzS|jg}|jg}|jg|jdgz}|jdk(r||z|z|z|z|zS||z|z|z|z|zS)a Build model inputs from a pair of sequence for question answering tasks by concatenating and adding special tokens. A Splinter sequence has the following format: - single sequence: `[CLS] X [SEP]` - pair of sequences for question answering: `[CLS] question_tokens [QUESTION] . [SEP] context_tokens [SEP]` Args: token_ids_0 (`List[int]`): The question token IDs if pad_on_right, else context tokens IDs token_ids_1 (`List[int]`, *optional*): The context token IDs if pad_on_right, else question token IDs Returns: `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens. .right) cls_token_id sep_token_idr1r0 padding_side)r'r2r3clssepquestion_suffixs r- build_inputs_with_special_tokensz6SplinterTokenizerFast.build_inputs_with_special_tokenss&  %%&48I8I7JJ J  !  !112d6P6PQT6U5VV    '$6<{JSP P$s*[8?JSP Pr.cn|jg}|jg}|jg|jdgz}|t ||z|zdgzS|j dk(r+t ||z|z|zdgzt ||zdgzzSt ||z|zdgzt ||z|zdgzzS)a Create the token type IDs corresponding to the sequences passed. [What are token type IDs?](../glossary#token-type-ids) Should be overridden in a subclass if the model has a special way of building those. Args: token_ids_0 (`List[int]`): The first tokenized sequence. token_ids_1 (`List[int]`, *optional*): The second tokenized sequence. Returns: `List[int]`: The token type ids. r6rr7r )r9r8r1r0lenr:)r'r2r3r<r;r=s r-$create_token_type_ids_from_sequencesz:SplinterTokenizerFast.create_token_type_ids_from_sequencess   !  !112d6P6PQT6U5VV  s[(3./1#5 5    's[(?:S@AQCG#k\_N_J`decfJff fs[(3./1#5K/*PU|r.) NNTz[UNK]z[SEP]z[PAD]z[CLS]z[MASK]z [QUESTION]TN)N)__name__ __module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesr slow_tokenizer_classrpropertyr1rintrr>rAstrrrK __classcell__)r,s@r-rr s'R*,##(+T??JNQ9Q3;DI3FQ cQBJNg9g3;DI3Fg cg:cHSM]bcf]gr.r)rOrtypingrrr tokenizersrtokenization_utils_fastrutilsr tokenization_splinterr get_loggerrLloggerrPrrr.r-r^sM. ((">4   H %!;/^3^r.