sgji J d Z ddlZddlZddlZddlmZ ddlmZmZm Z ddl
Z
ddl m Z ddl
mZ ej e Zdd d
Zd Z G d d
e Z dZdZededdddddf Z e
j0 ddj3 e z e
j4 e
j6 z e
j8 z Z e
j0 d Z e
j0 ee
j4 e
j6 z e
j8 z Z e
j0 d Z d"dZ!d#d Z" G d d Z#d Z$d Z%d$d!Z&y)%z!Tokenization classes for BERTweet N)copyfile)ListOptionalTuple )PreTrainedTokenizer)loggingz vocab.txtz bpe.codes)
vocab_file merges_filec x t }| d }| dd D ] }|j ||f |} t | }|S )z
Return set of symbol pairs in a word.
Word is represented as tuple of symbols (symbols being variable-length strings).
r N)setadd)wordpairs prev_charchars e/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bertweet/tokenization_bertweet.py get_pairsr & sO
EEQIQR
9d#$
JE L c
8 e Zd ZdZeZ d fd Z ddee de ee dee fdZ
ddee de ee de dee f fd
Z ddee de ee dee fd Z
ed
Zd Zd Zd
Zd Zd Zd Zd Zd Zddede e dee fdZd Z xZ S )BertweetTokenizera
Constructs a BERTweet tokenizer, using 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`):
Path to the merges file.
normalization (`bool`, *optional*, defaults to `False`):
Whether or not to apply a normalization preprocess.
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.
cls_token (`str`, *optional*, defaults to `""`):
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.
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 masked language
modeling. This is the token which the model will try to predict.
c ddl m} | | _ || _ || _ i | _ d| j t | < d| j t | < d| j t | < d| j t | < | j | | j j D
ci c] \ }
}||
c}}
| _ t |d 5 }|j j d d d
}d d d D cg c] }t! |j d d
}}t# t% |t' t) | | _ i | _ || _ t1 | _ d d d
| _ t7 | p d||||||| |
d| y # t $ r t j d d | _ Y w xY wc c}}
w # 1 sw Y xY wc c}w )Nr )demojizezsemoji is not installed, thus not converting emoticons or emojis into text. Install emoji: pip3 install emoji==0.6.0r
r utf-8encoding
'z...)u ’u …)
normalization bos_token eos_token sep_token cls_token unk_token pad_token
mask_token ) emojir demojizer ImportErrorloggerwarningr
r encoderstr
add_from_fileitemsdecoderopenreadsplittupledictziprangelen bpe_rankscacher" TweetTokenizertweetPreprocessorspecial_punctssuper__init__)selfr
r r" r# r$ r% r& r' r( r) kwargsr kv
merges_handlemergesmerge __class__s r rC zBertweetTokenizer.__init__k s " & %DN %& '( S^$'( S^$'( S^$'( S^$ :&)- ););)=>A1>
+
0 ;M"'')//5cr:F ;9?@%
cr*+@@ c&%F *< =>
*!/!1 &)% 8
' !
= " NN(
"DN "$ ? ; ;@s)
F 3
G#G#G%F?>F?G token_ids_0 token_ids_1returnc | | j g|z | j gz S | j g}| j g}||z |z |z |z |z S )a
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
adding special tokens. A BERTweet 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.
) cls_token_id sep_token_id)rD rL rM clsseps r build_inputs_with_special_tokensz2BertweetTokenizer.build_inputs_with_special_tokens sg ( %%&48I8I7JJ J ! ![ 3&,{:S@@r already_has_special_tokensc |rt | ||d S |dgdgt | z z dgz S dgdgt | z z ddgz dgt | z z dgz 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)rL rM rU r
r )rB get_special_tokens_maskr< )rD rL rM rU rK s r rW z)BertweetTokenizer.get_special_tokens_mask s & &72 '[]a 3
31#K 001QC7 7sqcC ,,-A61#K@P:PQUVTWWWr c | j g}| j g}|t ||z |z dgz S t ||z |z |z |z |z dgz S )a
Create a mask from the two sequences passed to be used in a sequence-pair classification task. BERTweet 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.
r )rQ rP r< )rD rL rM rS rR s r $create_token_type_ids_from_sequencesz6BertweetTokenizer.create_token_type_ids_from_sequences sm " ! ! s[(3./1#5 53$s*S0;>DEKKr c , t | j S N)r< r0 rD s r
vocab_sizez BertweetTokenizer.vocab_size s 4<< r c B t | j fi | j S r[ )r9 r0 added_tokens_encoderr\ s r get_vocabzBertweetTokenizer.get_vocab s DLL>D$=$=>>r c $ | j v r j | S t | }t t |d d |d dz gz }t | }|s|S t | fd }| j
vrn|\ }}g }d}|t
| k r |j || } |j ||| | }|| |k( r6|t
| dz
k r%||dz |k( r|j ||z |dz
}n|j || |dz
}|t
| k rt | }|}t
| dk( rn t | }dj | }|d d }| j |< |S # t $ r |j ||d Y nw xY w)
Nr zc N j j | t d S )Ninf)r= getfloat)pairrD s r z'BertweetTokenizer.bpe.. s 1C1CD%PU,1W r )keyr r
r @@ ) r> r8 listr minr= r< indexextend
ValueErrorappendjoin)
rD tokenr r bigramfirstsecondnew_wordijs
` r bpezBertweetTokenizer.bpe s DJJ ::e$ $U|T$s)_R6(9'::;$L$WXFT^^+ "ME6HAc$i-
5!,A
OOD1I.A7e#CIM(9d1q5kV>S OOEFN3FA OODG,FA c$i- XHD4yA~!$9 : zz$ CRy
5 - " OODH-s E/ / FFc | j r| j | }g }t j d| }|D ]: }|j t | j
| j d < |S )zTokenize a string.z\S+\n? )r" normalizeTweetrefindallrn rk ry r7 )rD text split_tokenswordsrr s r _tokenizezBertweetTokenizer._tokenize( sm &&t,D
9d+ BE TXXe_%:%:3%? @ A Br c ( | j D ]! }|j || j | }# | j j | }dj |D cg c] }| j | c} }|j dd j dd j dd j dd j d d
}|j d d j d
d j dd j dd j dd j dd }|j dd j dd j dd j d d }dj |j
S c c}w ) z'
Normalize a raw Tweet
r{ zcannot zcan not zn't z n't zn 't zca n'tzcan'tzai n'tzain'tz'm z 'm z're z 're z's z 's z'll z 'll z'd z 'd z've z 've z p . m .z p.m.z p . m z p.m z a . m .z a.m.z a . m z a.m )rA replacer@ tokenizerq normalizeTokenr7 )rD tweetpuncttokensrr normTweets r r| z BertweetTokenizer.normalizeTweet3 se (( EEMM%)<)>@
r save_directoryfilename_prefixc t j j | st j d| d y t j j ||r|dz ndt d z }t j j ||r|dz ndt d z }t j j | j t j j | k7 r@t j j | j rt | j | nit j j | j s@t |d 5 }| j j }|j | d d d t j j | j t j j | k7 rt | j | ||fS # 1 sw Y lxY w)NzVocabulary path (z) should be a directory-r r
r wb)ospathisdirr. errorrq VOCAB_FILES_NAMESabspathr
isfiler r5 sp_modelserialized_model_protowriter )rD r r out_vocab_fileout_merge_fileficontent_spiece_models r save_vocabularyz!BertweetTokenizer.save_vocabularyu sr ww}}^, LL,^,< ')
isinstancer1 r5 r2 FileNotFoundError UnicodeError Exception readlinesr rfindro r< r0 ) rD ffdfnfelineslineTmplineidxr s r r2 z BertweetTokenizer.add_from_file s a
c!S73 +r&&r*+
3G==?D**S/Cby !XYY:D!$T\\!2DLL
3+
%
c "A!D` abb
cs3 B7 B+B7 +B40B7 4B7 7 C C C )F