tjMddlZddlZddlZddlmZddlmZmZmZm Z ddl m Z e j e ZddiZdZGd d ZGd d Zd ZGddeZdgZdS)N)Iterable)PreTrainedTokenizer _is_control_is_punctuation_is_whitespace)logging vocab_filezprophetnet.tokenizerc^|}|sgS|}|S)z@Runs basic whitespace cleaning and splitting on a piece of text.)stripsplit)texttokenss t/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/prophetnet/tokenization_prophetnet.pywhitespace_tokenizers. ::<>>SWSc %%  & 6//55D"-"7t"D"D)*ABB    M MEK''%;!KKMME)66 $ 7 7 > >'; 33E::E    7 7{ K K L L L L+CHH\,B,BCC rctjd|}g}|D]2}tj|}|dkr||3d|S)z$Strips accents from a piece of text.NFDMn)r%r&categoryappendr+)rroutputcharcats rr(z!BasicTokenizer._run_strip_accentsssi$UD11  D&t,,Cd{{ MM$    wwvrc|jr|||vr|gSt|}d}d}g}|t|kr|||}t|r||gd}n4|r|gd}|d||dz }|t|k|d|DS)z&Splits punctuation on a piece of text.NrTFc8g|]}d|S)r5)r+).0xs r z5BasicTokenizer._run_split_on_punc..s"+++q +++r)rlistlenrr7)rrrcharsistart_new_wordr8r9s rr*z!BasicTokenizer._run_split_on_punc~s$ )@T[EXEX6MT  #e**nn8Dt$$ ( tf%%%!%!&MM"%%%!&r !!$''' FA#e**nn,+F++++rc,g}|D]{}t|}||r@|d|||df|||d|S)z)Adds whitespace around any CJK character.r!r5)ord_is_chinese_charr7r+rrr8r9cps rr$z&BasicTokenizer._tokenize_chinese_charss $ $DTB$$R(( $ c""" d### c"""" d####wwvrc|dkr|dksT|dkr|dksH|dkr|dks<|dkr|dks0|d kr|d ks$|d kr|d ks|d kr|dks |dkr|dkrdSdS)z6Checks whether CP is the codepoint of a CJK character.iNii4iMiiߦii?i@ii iiiiiTF)rrKs rrIzBasicTokenizer._is_chinese_chars6\\bFllf vg "--g "--g "--g "--f vg "--4urcg}|D]g}t|}|dks|dkst|r-t|r|dR||hd|S)zBPerforms invalid character removal and whitespace cleanup on text.rir!r5)rHrrr7r+rJs rr#zBasicTokenizer._clean_texts $ $DTBQww",,+d*;*;,d## $ c"""" d####wwvr)TNTNTr) __name__ __module__ __qualname____doc__rr1r(r*r$rIr#rMrrrr&s0# 1111 $$$$L   ,,,,,   0     rrc eZdZdZddZdZdS)WordpieceTokenizerzRuns WordPiece tokenization.dc0||_||_||_dSr)vocab unk_tokenmax_input_chars_per_word)rrWrXrYs rrzWordpieceTokenizer.__init__s "(@%%%rcXg}t|D]}t|}t||jkr||jEd}d}g}|t|krt|}d} ||kr?d|||} |dkrd| z} | |jvr| } n |dz}||k?| d}n*|| |}|t|k|r||j|||S)a Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the given vocabulary. For example, `input = "unaffable"` will return as output `["un", "##aff", "##able"]`. Args: text: A single token or whitespace separated tokens. This should have already been passed through *BasicTokenizer*. Returns: A list of wordpiece tokens. FrNr5z##r=T) rrBrCrYr7rXr+rWr)) rrr0r/rDis_badstart sub_tokensend cur_substrsubstrs rr1zWordpieceTokenizer.tokenizesb (.. 1 1EKKE5zzD999$$T^444FEJ#e**$$%jj! ckkWWU59%566Fqyy!%++%+ 1HCckk%!F!!*---#e**$$" 1$$T^4444$$Z0000rN)rU)rOrPrQrRrr1rMrrrTrTsA&&AAAA .....rrTctj}t|dd5}|}dddn #1swxYwYt |D]\}}|d}|||< |S)z*Loads a vocabulary file into a dictionary.rutf-8encodingN ) collections OrderedDictopen readlines enumeraterstrip)r rWreaderrindexr/s r load_vocabros  # % %E j# 0 0 0$F!!##$$$$$$$$$$$$$$$!&)) u T""e LsAA A ceZdZUdZeZddgZeee d< d,d ed e dzde dzde dzdedzdedzdedzdedzdedzde dzde dzde ffd Z e dZdZdZdefdZdefdZd efd!Z d-d#eed$eedzd%e dzd&eeffd' Zd.d(ed)edzd&eefd*Z d.d#eed$eedzd&eefd+ZxZS)/ProphetNetTokenizera Construct a ProphetNetTokenizer. Based on WordPiece. 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`): File containing the vocabulary. do_lower_case (`bool`, *optional*, defaults to `True`): Whether or not to lowercase the input when tokenizing. do_basic_tokenize (`bool`, *optional*, defaults to `True`): Whether or not to do basic tokenization before WordPiece. never_split (`Iterable`, *optional*): Collection of tokens which will never be split during tokenization. Only has an effect when `do_basic_tokenize=True` 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. x_sep_token (`str`, *optional*, defaults to `"[X_SEP]"`): Special second separator token, which can be generated by [`ProphetNetForConditionalGeneration`]. It is used to separate bullet-point like sentences in summarization, *e.g.*. pad_token (`str`, *optional*, defaults to `"[PAD]"`): The token used for padding, for example when batching sequences of different lengths. 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. 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). clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`): Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like extra spaces. input_idsattention_maskmodel_input_namesTN[UNK][SEP][X_SEP][PAD][MASK]r rdo_basic_tokenizerrX sep_token x_sep_token pad_token mask_tokenrrclean_up_tokenization_spacesc  tj|std|dt ||_t jd|jD|_ ||_ |rt||| | |_ t|jt||_t!jd|||||||| | | | d | dS)Nz&Can't find a vocabulary file at path 'z'. To load the vocabulary from a Google pretrained model use `tokenizer = AutoTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`cg|] \}}||f SrMrM)r?tokidss rrAz0ProphetNetTokenizer.__init__..Us 5d5d5dXS#sCj5d5d5dr)rrrr)rWrX) rrzrrXr{r|r}r~rrrrM)ospathisfile ValueErrorrorWrgrhitems ids_to_tokensrzrbasic_tokenizerrTstrwordpiece_tokenizersuperr)rr rrzrrXr{r|r}r~rrrkwargs __class__s rrzProphetNetTokenizer.__init__?s: w~~j)) ````  ++ (45d5dQUQ[QaQaQcQc5d5d5dee!2  #1+''=+ $$$D $6DJRUV_R`R`#a#a#a  '/##!#9')E  rc*t|jSr)rCrWrs r vocab_sizezProphetNetTokenizer.vocab_sizeos4:rc0t|jfi|jSr)dictrWadded_tokens_encoderrs r get_vocabzProphetNetTokenizer.get_vocabssDJ<<$";<<>@@ rF token_ids_0 token_ids_1already_has_special_tokensreturnc|r$t||dS|dgt|zdgzSdgt|zdgzdgt|zzdgzS)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)rrrNrr=)rget_special_tokens_maskrC)rrrrrs rrz+ProphetNetTokenizer.get_special_tokens_masks* & 7722'[]a3   C#k***qc1 1c+&&&1#-!s;7G7G1GHA3NNrsave_directoryfilename_prefixcd}tj|r6tj||r|dzndtdz}n |r|dznd|z}t |dd5}t |jd D]H\}}||kr t d |d |}| |d z|d z }I dddn #1swxYwY|fS)Nr-r5r wrcrdc|dS)Nr=rM)kvs rz5ProphetNetTokenizer.save_vocabulary..s PRSTPUr)keyzSaving vocabulary to z\: vocabulary indices are not consecutive. Please check that the vocabulary is not corrupted!rfr=) rrisdirr+VOCAB_FILES_NAMESrisortedrWrloggerwarningwrite)rrrrnr writerr/ token_indexs rsave_vocabularyz#ProphetNetTokenizer.save_vocabularys} 7== ( ( ]/!Q3!6!6rUfgsUt tJJ4CJ/C//n\J *cG 4 4 4 &,TZ-=-=-?-?EUEU&V&V&V  "{K''NNN NNN(E UT\***                 }s6A3C66C:=C:cB| ||jgzS|jg}||z|z|zS)a Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A BERT sequence has the following format: - single sequence: `[CLS] X [SEP]` - pair of sequences: `[CLS] A [SEP] B [SEP]` 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. ) sep_token_id)rrrseps r build_inputs_with_special_tokensz4ProphetNetTokenizer.build_inputs_with_special_tokenss;&  $"3!44 4 !S ;.44r) TTNrurvrwrxryTNT)NFr)rOrPrQrRrvocab_files_namesrtrBr__annotations__boolrrpropertyrrrrintrrrtuplerr __classcell__)rs@rrqrq s**X* %01A#BtCyBBB &*)-'+ ' '"+ '!).2%)-1. . . d{.  $; . _ . : . :. 4Z. :. $J. !%t . d{. '+. . . . . . `X===   E#EEEE=#====s)-27 OO#YO#Y%O%)4K O c OOOOOO<cC$JZ_`cZd*GK5595379t3C5 c55555555rrq)rgrr%collections.abcrtokenization_pythonrrrrutilsr get_loggerrOrrrrrTrorq__all__rMrrrsJ $$$$$$dddddddddddd  H % %!#9:^^^^^^^^B66666666rM5M5M5M5M5-M5M5M5` ! !r