U
9%e?? @ s d Z ddlZddlZddlmZ ddlmZmZmZm Z m
Z
ddl Z ddl
mZmZ ddlmZmZ eeZdd iZdd
d d iZddd ZdZd
ZdZdZ dZ G dd deZ dS )z& Tokenization classes for XLNet model. N)copyfile)AnyDictListOptionalTuple )
AddedTokenPreTrainedTokenizer)SPIECE_UNDERLINElogging
vocab_filez spiece.modelzAhttps://huggingface.co/xlnet-base-cased/resolve/main/spiece.modelzBhttps://huggingface.co/xlnet-large-cased/resolve/main/spiece.model)zxlnet-base-casedzxlnet-large-cased c sd e Zd ZdZeZeZeZ dZ
dddddddd d
d d d
gdf e e e
ef dd fdd
Zedd Zdd Zdd Zdd Zdd Ze
ee
d d d Zd d Zd!d" Zd#d$ Zd3ee e e e e
d%d&d'Z d4ee e ee ee d(d)d*Z d5ee e ee e ee d+ fd,d-
Z d6ee e ee ee d(d.d/Z d7e
e e
e!e
d0d1d2Z" Z#S )8XLNetTokenizera-
Construct an XLNet tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece).
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`):
[SentencePiece](https://github.com/google/sentencepiece) file (generally has a .spm extension) that
contains the vocabulary necessary to instantiate a tokenizer.
do_lower_case (`bool`, *optional*, defaults to `True`):
Whether to lowercase the input when tokenizing.
remove_space (`bool`, *optional*, defaults to `True`):
Whether to strip the text when tokenizing (removing excess spaces before and after the string).
keep_accents (`bool`, *optional*, defaults to `False`):
Whether to keep accents when tokenizing.
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`.
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.
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.
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.
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.
additional_special_tokens (`List[str]`, *optional*, defaults to `["", ""]`):
Additional special tokens used by the tokenizer.
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.
Attributes:
sp_model (`SentencePieceProcessor`):
The *SentencePiece* processor that is used for every conversion (string, tokens and IDs).
leftFTzzzzzzzzzN)sp_model_kwargsreturnc s t | trt| dddn| } |
d kr(i n|
| _|| _|| _|| _|| _tj f | j| _
| j
| t j
f |||||||| |
| | | jd | d| _d S )NTF)lstriprstrip)
do_lower_case remove_space keep_accents bos_token eos_token unk_token sep_token pad_token cls_token
mask_tokenadditional_special_tokensr r )
isinstancestrr r r r r r
spmSentencePieceProcessorsp_modelLoadsuper__init__Z_pad_token_type_id)selfr
r r r r r r r r r r r! r kwargs __class__ k/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/xlnet/tokenization_xlnet.pyr) s2
zXLNetTokenizer.__init__c C s
t | jS )N)lenr& r* r. r. r/
vocab_size s zXLNetTokenizer.vocab_sizec s( fddt jD }| j |S )Nc s i | ]} ||qS r. )convert_ids_to_tokens).0ir1 r. r/
s z,XLNetTokenizer.get_vocab..)ranger2 updateadded_tokens_encoder)r* Zvocabr. r1 r/ get_vocab s zXLNetTokenizer.get_vocabc C s | j }d |d< |S )Nr& )__dict__copy)r* stater. r. r/ __getstate__ s
zXLNetTokenizer.__getstate__c C s8 || _ t| dsi | _tjf | j| _| j| j d S )Nr )r; hasattrr r$ r% r& r' r
)r* dr. r. r/ __setstate__ s
zXLNetTokenizer.__setstate__c C sj | j rd| }n|}|dddd}| jsXtd|}ddd |D }| jrf| }|S ) N z``"z''ZNFKD c S s g | ]}t |s|qS r. ) unicodedata combining)r4 cr. r. r/
s
z2XLNetTokenizer.preprocess_text..)
r joinstripsplitreplacer rE normalizer lower)r* inputsoutputsr. r. r/ preprocess_text s z XLNetTokenizer.preprocess_text)textr c C s | |}| jj|td}g }|D ]}t|dkr|d tdkr|d r| j|dd td}|d tkr|d d tkrt|d dkr|dd }n|d dd |d< | |d |
| q"| | q"|S ) zTokenize a string.)Zout_typer ,NrD r ) rQ r& encoder# r0 isdigitZEncodeAsPiecesrL r appendextend)r* rR piecesZ
new_piecesZpieceZ
cur_piecesr. r. r/ _tokenize s
( zXLNetTokenizer._tokenizec C s | j |S )z0Converts a token (str) in an id using the vocab.)r& Z PieceToId)r* tokenr. r. r/ _convert_token_to_id s z#XLNetTokenizer._convert_token_to_idc C s | j |S )z=Converts an index (integer) in a token (str) using the vocab.)r& Z IdToPiece)r* indexr. r. r/ _convert_id_to_token s z#XLNetTokenizer._convert_id_to_tokenc C s d |td }|S )zIConverts a sequence of tokens (strings for sub-words) in a single string.rD rB )rI rL r rJ )r* tokensZ
out_stringr. r. r/ convert_tokens_to_string s z'XLNetTokenizer.convert_tokens_to_string) token_idsskip_special_tokens clean_up_tokenization_spaces spaces_between_special_tokensr c K s | dd| _| j||d}g }g }|D ]L} |r<| | jkr `
- 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_idZ cls_token_id)r* rh ri sepclsr. r. r/ build_inputs_with_special_tokens* s
z/XLNetTokenizer.build_inputs_with_special_tokens)rh ri already_has_special_tokensr c s^ |rt j||ddS |dk rHdgt| dg dgt| ddg S dgt| ddg 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)rh ri rn Nr r )r( get_special_tokens_maskr0 )r* rh ri rn r, r. r/ ro C s *z&XLNetTokenizer.get_special_tokens_maskc C sT | j g}dg}|dkr,t|| dg | S t|| dg t|| dg | S )a
Create a mask from the two sequences passed to be used in a sequence-pair classification task. An XLNet
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).
r Nr r )rj r0 )r* rh ri rk Zcls_segment_idr. r. r/ $create_token_type_ids_from_sequences_ s
z3XLNetTokenizer.create_token_type_ids_from_sequences)save_directoryfilename_prefixr c C s t j|s"td| d d S t j||r6|d ndtd }t j| jt j|krzt j | jrzt
| j| n8t j | jst |d}| j
}|| W 5 Q R X |fS )NzVocabulary path (z) should be a directory-rD r
wb)ospathisdirloggererrorrI VOCAB_FILES_NAMESabspathr
isfiler openr& Zserialized_model_protowrite)r* rq rr Zout_vocab_filefiZcontent_spiece_modelr. r. r/ save_vocabulary} s (
z XLNetTokenizer.save_vocabulary)FNT)N)NF)N)N)$__name__
__module__ __qualname____doc__rz Zvocab_files_namesPRETRAINED_VOCAB_FILES_MAPZpretrained_vocab_files_map&PRETRAINED_POSITIONAL_EMBEDDINGS_SIZESZmax_model_input_sizesZ padding_sider r r# r r) propertyr2 r: r> rA rQ r r[ r] r_ ra intboolrg rm ro rp r r
__classcell__r. r. r, r/ r 5 s| J0
.
r ) r ru rE shutilr typingr r r r r Z
sentencepiecer$ Ztokenization_utilsr r
utilsr r Z
get_loggerr rx rz r r ZSEG_ID_AZSEG_ID_BZ
SEG_ID_CLSZ
SEG_ID_SEPZ
SEG_ID_PADr r. r. r. r/ s.