U ,-e5@sdZddlZddlZddlmZmZmZddlmZddl m Z e e Z ddd Zd d id d id Zd d iZddZGdddeZdS)z Tokenization classes for BioGPT.N)ListOptionalTuple)PreTrainedTokenizer)loggingz vocab.jsonz merges.txt) vocab_file merges_filezmicrosoft/biogptz?https://huggingface.co/microsoft/biogpt/resolve/main/vocab.jsonz?https://huggingface.co/microsoft/biogpt/resolve/main/merges.txticCs6t}|d}|ddD]}|||f|}q|S)z Return set of symbol pairs in a word. word is represented as tuple of symbols (symbols being variable-length strings) rN)setadd)wordpairsZ prev_charcharro/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/biogpt/tokenization_biogpt.py get_pairs+s rcs"eZdZdZeZeZeZ ddgZ d-fdd Z e d d Z d d ZddZddZddZd.ddZddZddZddZd/eeeeeeeddd Zd0eeeeeeeed!fd"d# Zd1eeeeeeedd$d%Zd2eeeeed&d'd(Zd)d*Z d+d,Z!Z"S)3BioGptTokenizera: Construct an FAIRSEQ Transformer tokenizer. Moses tokenization followed by Byte-Pair Encoding. This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Args: vocab_file (`str`): Path to the vocabulary file. merges_file (`str`): Merges file. unk_token (`str`, *optional*, defaults to `""`): 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. bos_token (`str`, *optional*, defaults to `""`): The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token. When building a sequence using special tokens, this is not the token that is used for the beginning of sequence. The token used is the `cls_token`. eos_token (`str`, *optional*, defaults to `""`): The end of sequence token. When building a sequence using special tokens, this is not the token that is used for the end of sequence. The token used is the `sep_token`. sep_token (`str`, *optional*, defaults to `""`): 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 `""`): The token used for padding, for example when batching sequences of different lengths. Z input_idsZattention_maskc sz ddl} Wntk r(tdYnXd|_| |_i|_i|_t|dd} t| |_ W5QRXdd|j D|_ t|dd} | ddd } W5QRXd d | D} tt| tt| |_i|_tjf|||||d |dS) NrzqYou need to install sacremoses to use BioGptTokenizer. See https://pypi.org/project/sacremoses/ for installation.enutf-8encodingcSsi|]\}}||qSrr).0kvrrr sz,BioGptTokenizer.__init__.. cSs g|]}t|ddqS)N)tuplesplit)rmergerrr sz,BioGptTokenizer.__init__..) bos_token eos_token sep_token unk_token pad_token) sacremoses ImportErrorlangsmcache_moses_tokenizercache_moses_detokenizeropenjsonloadencoderitemsdecoderreadr$dictziprangelen bpe_rankscachesuper__init__) selfrr r*r'r(r)r+kwargsr,Z vocab_handleZ merges_handleZmerges __class__rrr@hs6    zBioGptTokenizer.__init__cCs t|jS)zReturns vocab size)r<r5rArrr vocab_sizeszBioGptTokenizer.vocab_sizecCst|jf|jS)N)r9r5Zadded_tokens_encoderrErrr get_vocabszBioGptTokenizer.get_vocabcCs:||jkr"|jj|d}||j|<|j|j|ddddS)Nr.TF)Zaggressive_dash_splitsZ return_strescape)r0r/ZMosesTokenizertokenize)rAtextr.Zmoses_tokenizerrrrmoses_tokenizes   zBioGptTokenizer.moses_tokenizecCs2||jkr"|jj|d}||j|<|j||S)NrH)r1r/ZMosesDetokenizerZ detokenize)rAtokensr.Zmoses_detokenizerrrrmoses_detokenizes  z BioGptTokenizer.moses_detokenizec st|dd|ddf}|jkr2j|St|}|sF|dSt|fddd}|jkrhqf|\}}g}d}|t|krcsj|tdS)Ninf)r=getfloat)pairrErrz%BioGptTokenizer.bpe..keyrr r" z z ) r#r>rminr=r<index ValueErrorextendappendjoin) rAtokenr rZbigramfirstsecondZnew_wordijrrErbpesF    2      zBioGptTokenizer.bpeFcCsL|r|}n|||j}g}|D]"}|r$|t||dq$|S)zReturns a tokenized string.rX)r$rLr.r\listrd)rArKZbypass_tokenizerZ split_tokensr_rrr _tokenizes zBioGptTokenizer._tokenizecCs|j||j|jS)z0Converts a token (str) in an id using the vocab.)r5rQr*)rAr_rrr_convert_token_to_idsz$BioGptTokenizer._convert_token_to_idcCs|j||jS)z=Converts an index (integer) in a token (str) using the vocab.)r7rQr*)rArZrrr_convert_id_to_tokensz$BioGptTokenizer._convert_id_to_tokencCs.dd|D}d|}|||j}|S)z:Converts a sequence of tokens (string) in a single string.cSs g|]}|ddddqS)rXrO)replace)rtrrrr&sz.ri)r^r$rNr.)rArMrKrrrconvert_tokens_to_stringsz(BioGptTokenizer.convert_tokens_to_stringN) token_ids_0 token_ids_1returncCs,|dkr|jg|S|jg}||||S)a Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A BioGPT sequence has the following format: - single sequence: ` X ` - pair of sequences: ` A B ` 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. N) sep_token_idrArmrnseprrr build_inputs_with_special_tokenss z0BioGptTokenizer.build_inputs_with_special_tokens)rmrnalready_has_special_tokensrocsZ|rtj||ddS|dk rFdgdgt|dgdgt|Sdgdgt|S)a Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method. Args: token_ids_0 (`List[int]`): List of IDs. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. T)rmrnrtNr r)r?get_special_tokens_maskr<)rArmrnrtrCrrru s(z'BioGptTokenizer.get_special_tokens_maskcCsF|jg}|dkr"t||dgSt||dgt||dgS)a Create a mask from the two sequences passed to be used in a sequence-pair classification task. A FAIRSEQ Transformer sequence pair mask has the following format: ``` 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 | first sequence | second sequence | ``` If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s). Args: token_ids_0 (`List[int]`): List of IDs. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. Returns: `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s). Nrr )rpr<rqrrr$create_token_type_ids_from_sequences(sz4BioGptTokenizer.create_token_type_ids_from_sequences)save_directoryfilename_prefixroc Cstj|s"td|ddStj||r6|dndtd}tj||rX|dndtd}t|ddd $}|t j |j d d d d dW5QRXd}t|ddd `}t |j dddD]B\}} || krtd|d| }|d|d|d7}qW5QRX||fS)NzVocabulary path (z) should be a directory-rirr wrrr"TF)indent sort_keys ensure_asciir rcSs|dS)Nr r)kvrrrrTVrUz1BioGptTokenizer.save_vocabulary..rVzSaving vocabulary to zZ: BPE merge indices are not consecutive. Please check that the tokenizer is not corrupted!rXr )ospathisdirloggererrorr^VOCAB_FILES_NAMESr2writer3dumpsr5sortedr=r6warning) rArwrxrZ merge_filefrZwriterZ bpe_tokensZ token_indexrrrsave_vocabularyFs0 ( zBioGptTokenizer.save_vocabularycCs|j}d|d<|S)Nr/)__dict__copy)rAstaterrr __getstate__bs zBioGptTokenizer.__getstate__cCs:||_z ddl}Wntk r.tdYnX||_dS)NrznYou need to install sacremoses to use XLMTokenizer. See https://pypi.org/project/sacremoses/ for installation.)rr,r-r/)rAdr,rrr __setstate__gs  zBioGptTokenizer.__setstate__)rrrrr)F)N)NF)N)N)#__name__ __module__ __qualname____doc__rZvocab_files_namesPRETRAINED_VOCAB_FILES_MAPZpretrained_vocab_files_map&PRETRAINED_POSITIONAL_EMBEDDINGS_SIZESZmax_model_input_sizesZmodel_input_namesr@propertyrFrGrLrNrdrfrgrhrlrintrrsboolrurvstrrrrr __classcell__rrrCrr8sX*, ,       r)rr3rtypingrrrZtokenization_utilsrutilsrZ get_loggerrrrrrrrrrrrs&