o hT@sddlZddlmZddlmZmZmZmZmZddl Z ddl m Z m Z mZddlmZeeZdZdd d Zd d d dddddddddddddiZdddddddddddddddZgdgddZdd d!d"d#d$d%d&ZGd'd(d(eZdS))N)copyfile)AnyDictListOptionalTuple) AddedToken BatchEncodingPreTrainedTokenizer)loggingu▁zsentencepiece.bpe.modelztokenizer.json) vocab_filetokenizer_filer zOhttps://huggingface.co/uclanlp/plbart-base/resolve/main/sentencepiece.bpe.modelzahttps://huggingface.co/uclanlp/plbart-c-cpp-defect-detection/resolve/main/sentencepiece.bpe.modelzRhttps://huggingface.co/uclanlp/plbart-cs-java/resolve/main/sentencepiece.bpe.modelzUhttps://huggingface.co/uclanlp/plbart-en_XX-java/resolve/main/sentencepiece.bpe.modelzShttps://huggingface.co/uclanlp/plbart-go-en_XX/resolve/main/sentencepiece.bpe.modelz_https://huggingface.co/uclanlp/plbart-java-clone-detection/resolve/main/sentencepiece.bpe.modelzRhttps://huggingface.co/uclanlp/plbart-java-cs/resolve/main/sentencepiece.bpe.modelzUhttps://huggingface.co/uclanlp/plbart-java-en_XX/resolve/main/sentencepiece.bpe.modelz[https://huggingface.co/uclanlp/plbart-javascript-en_XX/resolve/main/sentencepiece.bpe.modelzThttps://huggingface.co/uclanlp/plbart-php-en_XX/resolve/main/sentencepiece.bpe.modelzWhttps://huggingface.co/uclanlp/plbart-python-en_XX/resolve/main/sentencepiece.bpe.modelz]https://huggingface.co/uclanlp/plbart-refine-java-medium/resolve/main/sentencepiece.bpe.modelz\https://huggingface.co/uclanlp/plbart-refine-java-small/resolve/main/sentencepiece.bpe.modelzUhttps://huggingface.co/uclanlp/plbart-ruby-en_XX/resolve/main/sentencepiece.bpe.model)zuclanlp/plbart-basez%uclanlp/plbart-c-cpp-defect-detectionzuclanlp/plbart-cs-javazuclanlp/plbart-en_XX-javazuclanlp/plbart-go-en_XXz#uclanlp/plbart-java-clone-detectionzuclanlp/plbart-java-cszuclanlp/plbart-java-en_XXzuclanlp/plbart-javascript-en_XXzuclanlp/plbart-php-en_XXzuclanlp/plbart-python-en_XXz!uclanlp/plbart-refine-java-mediumz uclanlp/plbart-refine-java-smallzuclanlp/plbart-ruby-en_XXi)__java__ __python__ __en_XX__)rrr__javascript____php____ruby____go__)basemultirrrrrrr)javapythonen_XX javascriptphprubygoc s8eZdZUdZeZeZeZ ddgZ gZ e e ed<gZe e ed<      dJd eeeefffdd ZddZddZeddZedefddZejdedd fddZ dKde e dee e dede e ffdd Z dLde e dee e de e fd!d"Z dLde e dee e de e fd#d$Zd%ed&eed'eefd(d)Zd*d+Z d,ede efd-d.Z!d/d0Z"d1d2Z#d3d4Z$dLd5ed6eede%efd7d8Z& 9 :dMd;e ed&ed Z(d?d@Z)dAdBZ*dNdCdDZ+dEedd fdFdGZ,dEedefdHdIZ-Z.S)OPLBartTokenizera Construct an PLBART tokenizer. Adapted from [`RobertaTokenizer`] and [`XLNetTokenizer`]. Based on [SentencePiece](https://github.com/google/sentencepiece). The tokenization method is ` ` for source language documents, and ` ` for target language documents. Args: vocab_file (`str`): Path to the vocabulary file. src_lang (`str`, *optional*): A string representing the source language. tgt_lang (`str`, *optional*): A string representing the target language. bos_token (`str`, *optional*, defaults to `""`): The start of sequence token. eos_token (`str`, *optional*, defaults to `""`): The end of sequence 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. cls_token (`str`, *optional*, defaults to `""`): The cls token, which is a special token used as the first token for all tasks. 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. pad_token (`str`, *optional*, defaults to `""`): The token used for padding, for example when batching sequences of different lengths. mask_token(`str`, *optional*, defaults to `""`): The token used for masking values. This is the token used when training this model with masking tasks. This is only used in the `"base"` tokenizer type. For `"multi"` tokenizer, masking is never done for the downstream tasks. language_codes (`str`, *optional*, defaults to `"base"`): What language codes to use. Should be one of `"base"` or `"multi"`. sp_model_kwargs (`dict`, *optional*): Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things, to set: - `enable_sampling`: Enable subword regularization. - `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout. - `nbest_size = {0,1}`: No sampling is performed. - `nbest_size > 1`: samples from the nbest_size results. - `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice) using forward-filtering-and-backward-sampling algorithm. - `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for BPE-dropout. Examples: ```python >>> from transformers import PLBartTokenizer >>> tokenizer = PLBartTokenizer.from_pretrained("uclanlp/plbart-python-en_XX", src_lang="python", tgt_lang="en_XX") >>> example_python_phrase = "def maximum(a,b,c):NEW_LINE_INDENTreturn max([a,b,c])" >>> expected_translation_english = "Returns the maximum value of a b c." >>> inputs = tokenizer(example_python_phrase, text_target=expected_translation_english, return_tensors="pt") ``` input_idsattention_mask prefix_tokens suffix_tokensrNsp_model_kwargsc st|tr t|dddn|}| durin| _| } | } tjdij_jt||_ | _ t j }ddddd_ d_ tj_fd d t|D_d d jD_j d kr{tjtjj j d <j jdd j D_tj|durfdd|Dj d kr| _jdurjjnj_n| dur| nd_jj_tjd|||||||| | | | jd || _jdS)NTF)lstriprstriprr)r$r'r%r&cs"i|] \}}|j|jqS) sp_model_sizefairseq_offset).0icodeselfr.d/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/plbart/tokenization_plbart.py sz,PLBartTokenizer.__init__..cSi|]\}}||qSr.r.r1kvr.r.r6r7rr(cSr8r.r.r9r.r.r6r7r<csg|]}|vr|qSr.r.)r1t)_additional_special_tokensr.r6 z,PLBartTokenizer.__init__..r) bos_token eos_token unk_token sep_token cls_token pad_token mask_tokenlanguage_codesrsrc_langtgt_langadditional_special_tokensr)r.) isinstancestrr r)!_convert_lang_code_special_formatspmSentencePieceProcessorsp_modelLoadr rHFAIRSEQ_LANGUAGE_CODESfairseq_tokens_to_idsr0lenr/ enumeratelang_code_to_iditemsid_to_lang_codeupdatefairseq_ids_to_tokenslistkeysextend _src_langcur_lang_code_idsuper__init__rJset_src_lang_special_tokens)r5r rArBrDrErCrFrGrHrrIrJr)rKkwargsfairseq_language_codes __class__)r>r5r6rbsd         zPLBartTokenizer.__init__cCs$|j}d|d<|j|d<|S)NrQsp_model_proto)__dict__copyrQserialized_model_proto)r5stater.r.r6 __getstate__ s zPLBartTokenizer.__getstate__cCs<||_t|ds i|_tjdi|j|_|j|jdS)Nr)r.)rihasattrr)rOrPrQLoadFromSerializedProtorh)r5dr.r.r6 __setstate__s  zPLBartTokenizer.__setstate__cCsB|jdkrt|jt|j|jdSt|jt|j|jS)Nrr,)rHrUrQrWr0r4r.r.r6 vocab_sizes zPLBartTokenizer.vocab_sizereturncCs|jSN)r_r4r.r.r6rI%szPLBartTokenizer.src_lang new_src_langcCs ||}||_||jdSrt)rNr_rc)r5rur.r.r6rI)s F token_ids_0 token_ids_1already_has_special_tokenscsx|r tj||ddSdgt|j}dgt|j}|dur*|dgt||S|dgt|dgt||S)a Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` method. Args: token_ids_0 (`List[int]`): List of IDs. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. T)rvrwrxr,Nr)raget_special_tokens_maskrUr"r#)r5rvrwrx prefix_ones suffix_onesrfr.r6ry/s$z'PLBartTokenizer.get_special_tokens_maskcCs,|dur |j||jS|j|||jS)ac Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. An PLBART sequence has the following format, where `X` represents the sequence: - `input_ids` (for encoder) `X [eos, src_lang_code]` - `decoder_input_ids`: (for decoder) `X [eos, tgt_lang_code]` BOS is never used. Pairs of sequences are not the expected use case, but they will be handled without a separator. 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)r"r#)r5rvrwr.r.r6 build_inputs_with_special_tokensMsz0PLBartTokenizer.build_inputs_with_special_tokenscCsP|jg}|jg}|durt|||dgSt||||||dgS)a Create a mask from the two sequences passed to be used in a sequence-pair classification task. PLBart does not make use of token type ids, therefore a list of zeros is returned. 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 zeros. Nr) sep_token_id cls_token_idrU)r5rvrwsepclsr.r.r6$create_token_type_ids_from_sequenceshs "z4PLBartTokenizer.create_token_type_ids_from_sequencesreturn_tensorsrIrJcKs^|dus|dur td|||_|||_||fd|d|}||j}||d<|S)zIUsed by translation pipeline, to prepare inputs for the generate functionNzATranslation requires a `src_lang` and a `tgt_lang` for this modelT)add_special_tokensrforced_bos_token_id) ValueErrorrNrIrJconvert_tokens_to_ids)r5 raw_inputsrrIrJ extra_kwargsinputs tgt_lang_idr.r.r6_build_translation_inputss   z)PLBartTokenizer._build_translation_inputscs(fddtjD}|j|S)Ncsi|]}||qSr.)convert_ids_to_tokens)r1r2r4r.r6r7r@z-PLBartTokenizer.get_vocab..)rangerrrZadded_tokens_encoder)r5vocabr.r4r6 get_vocabs zPLBartTokenizer.get_vocabtextcCs|jj|tdS)N)out_type)rQencoderM)r5rr.r.r6 _tokenizeszPLBartTokenizer._tokenizecCs4||jvr |j|S|j|}|r||jS|jS)z0Converts a token (str) in an id using the vocab.)rTrQ PieceToIdr0 unk_token_id)r5tokenspm_idr.r.r6_convert_token_to_ids   z$PLBartTokenizer._convert_token_to_idcCs&||jvr |j|S|j||jS)z=Converts an index (integer) in a token (str) using the vocab.)r[rQ IdToPiecer0)r5indexr.r.r6_convert_id_to_tokens  z$PLBartTokenizer._convert_id_to_tokencCsd|td}|S)zIConverts a sequence of tokens (strings for sub-words) in a single string. )joinreplaceSPIECE_UNDERLINEstrip)r5tokens out_stringr.r.r6convert_tokens_to_stringsz(PLBartTokenizer.convert_tokens_to_stringsave_directoryfilename_prefixcCstj|std|ddStj||r|dndtd}tj|jtj|kr?tj |jr?t |j||fStj |jsgt |d}|j }||Wd|fS1sbwY|fS)NzVocabulary path (z) should be a directory-rr wb)ospathisdirloggererrorrVOCAB_FILES_NAMESabspathr isfileropenrQrkwrite)r5rrout_vocab_fileficontent_spiece_modelr.r.r6save_vocabularys" (     zPLBartTokenizer.save_vocabularyrr src_texts tgt_textsc s.|||_|||_tj||fi|Srt)rNrIrJraprepare_seq2seq_batch)r5rrIrrJrdrfr.r6rs  z%PLBartTokenizer.prepare_seq2seq_batchcC ||jSrt)rcrIr4r.r.r6_switch_to_input_mode z%PLBartTokenizer._switch_to_input_modecCrrt)set_tgt_lang_special_tokensrJr4r.r.r6_switch_to_target_moderz&PLBartTokenizer._switch_to_target_modecCR||}|dur|j|nd|_g|_|jdur"|j|jg|_dS|jg|_dS)z_Reset the special tokens to the source lang setting. No prefix and suffix=[eos, src_lang_code].NrNrW cur_lang_coder" eos_token_idr#)r5rIr.r.r6rcs  z+PLBartTokenizer.set_src_lang_special_tokenslangcCr)zcReset the special tokens to the target language setting. No prefix and suffix=[eos, tgt_lang_code].Nrr5rr.r.r6rs  z+PLBartTokenizer.set_tgt_lang_special_tokenscCs |tvr t|}|S|}|S)z;Convert Language Codes to format tokenizer uses if required)FAIRSEQ_LANGUAGE_CODES_MAPr]rr.r.r6rNsz1PLBartTokenizer._convert_lang_code_special_format) r$r%r%r$r&r'r(rNNNNN)NFrt)rNr)rsN)/__name__ __module__ __qualname____doc__rvocab_files_names&PRETRAINED_POSITIONAL_EMBEDDINGS_SIZESmax_model_input_sizesPRETRAINED_VOCAB_FILES_MAPpretrained_vocab_files_mapmodel_input_namesr"rint__annotations__r#rrrMrrbrmrqpropertyrrrIsetterboolryr|rrrrrrrrrr rrrrcrrN __classcell__r.r.rfr6rjs =\               r)rshutilrtypingrrrrr sentencepiecerOtokenization_utilsr r r utilsr get_loggerrrrrrrrSrrr.r.r.r6sj    *