U
,-eaX @ s d Z ddlZddlZddlZddlmZmZmZ ddlm Z m
Z
m Z m Z m
Z
ddlmZ eeZddiZdd d
iiZd d iZd d d
iiZdd Zdd ZG dd de
ZG dd deZG dd deZ dS )z Tokenization classes for MPNet. N)ListOptionalTuple )
AddedTokenPreTrainedTokenizer _is_control_is_punctuation_is_whitespace)logging
vocab_filez vocab.txtzmicrosoft/mpnet-basezBhttps://huggingface.co/microsoft/mpnet-base/resolve/main/vocab.txti
do_lower_caseTc C sR t }t| ddd}| }W 5 Q R X t|D ]\}}|d}|||< q2|S )z*Loads a vocabulary file into a dictionary.rutf-8encoding
) collections OrderedDictopen readlines enumeraterstrip)r vocabreadertokensindextoken r m/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/mpnet/tokenization_mpnet.py
load_vocab. s
r c C s | } | sg S | }|S )z@Runs basic whitespace cleaning and splitting on a piece of text.)stripsplit)textr r r r whitespace_tokenize9 s
r$ c s e Zd ZdZeZeZeZ e
Z ddgZ d' fd d Z
ed
d Zedd Zdd Zdd Zdd Zdd Zdd Zd(ee eee ee dd d Zd)ee eee eee d fd d!
Zd*ee eee ee dd"d#Z d+e ee e e d$d%d&Z Z S ),MPNetTokenizeraz
This tokenizer inherits from [`BertTokenizer`] which contains most of the methods. Users should refer to the
superclass for more information regarding methods.
Args:
vocab_file (`str`):
Path to the vocabulary file.
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`
bos_token (`str`, *optional*, defaults to `""`):
The beginning of sequence token that was used during pre-training. 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 `"[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.
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.
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).
Z input_idsZattention_maskTN 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) cls_token_id sep_token_id)rH r_ r` clssepr r r build_inputs_with_special_tokens s
z/MPNetTokenizer.build_inputs_with_special_tokensF)r_ r` already_has_special_tokensra c sh |rt j||ddS |dkr8dgdgt| dg S dgdgt| ddg dgt| dg S )a
Retrieves 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` methods.
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`):
Set to True if 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)r_ r` rg N r )rF get_special_tokens_maskrN )rH r_ r` rg rJ r r ri s z&MPNetTokenizer.get_special_tokens_maskc C sP | j g}| jg}|dkr.t|| | dg S t|| | | | | dg S )a
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. MPNet 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 )rc rb rN )rH r_ r` re rd r r r $create_token_type_ids_from_sequences s
z3MPNetTokenizer.create_token_type_ids_from_sequences)save_directoryfilename_prefixra c C s d}t j|r4t j||r$|d ndtd }n|r@|d nd| }t|dddZ}t| j dd d
D ]<\}}||krt
d | d |}| |d
|d7 }qnW 5 Q R X |fS )Nr -r[ r wr r c S s | d S )Nrh r )kvr r r < z0MPNetTokenizer.save_vocabulary..)keyzSaving vocabulary to z\: vocabulary indices are not consecutive. Please check that the vocabulary is not corrupted!r rh ) r< r= isdirr\ VOCAB_FILES_NAMESr sortedr r@ loggerwarningwrite)rH rk rl r r writerr Z token_indexr r r save_vocabulary3 s"
z MPNetTokenizer.save_vocabulary) TTNr& r' r' r& r( r) r* TN)N)NF)N)N)!__name__
__module__ __qualname____doc__rt Zvocab_files_namesPRETRAINED_VOCAB_FILES_MAPZpretrained_vocab_files_map PRETRAINED_INIT_CONFIGURATIONZ pretrained_init_configuration&PRETRAINED_POSITIONAL_EMBEDDINGS_SIZESZmax_model_input_sizesZmodel_input_namesrG propertyr
rO rR rV rX rY r^ r intr rf boolri rj r; r rz
__classcell__r r rJ r r% B sb < <
r% c @ sN e Zd ZdZdddZdddZdd Zdd
d Zd d
Zdd Z dd Z
dS )rB a
Constructs a BasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).
Args:
do_lower_case (`bool`, *optional*, defaults to `True`):
Whether or not to lowercase the input when tokenizing.
never_split (`Iterable`, *optional*):
Collection of tokens which will never be split during tokenization. Only has an effect when
`do_basic_tokenize=True`
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).
do_split_on_punc (`bool`, *optional*, defaults to `True`):
In some instances we want to skip the basic punctuation splitting so that later tokenization can capture
the full context of the words, such as contractions.
TNc C s2 |d kr g }|| _ t|| _|| _|| _|| _d S rL )r
setr/ r0 r1 do_split_on_punc)rH r
r/ r0 r1 r r r r rG ` s
zBasicTokenizer.__init__c C s |r| j t|n| j }| |}| jr4| |}td|}t|}g }|D ]R}||kr| j r|
}| j dk r| |}n| j r| |}|
| || qPtd|}|S )aj
Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer.
Args:
never_split (`List[str]`, *optional*)
Kept for backward compatibility purposes. Now implemented directly at the base class level (see
[`PreTrainedTokenizer.tokenize`]) List of token not to split.
NFCFrZ )r/ unionr _clean_textr0 _tokenize_chinese_chars unicodedata normalizer$ r
lowerr1 _run_strip_accentsextend_run_split_on_puncr\ )rH r# r/ Zunicode_normalized_textZ orig_tokensrU r
output_tokensr r r rS p s$
zBasicTokenizer.tokenizec C sB t d|}g }|D ]"}t |}|dkr,q|| qd|S )z$Strips accents from a piece of text.ZNFDZMnr[ )r r categoryrT r\ )rH r# outputcharcatr r r r s
z!BasicTokenizer._run_strip_accentsc C s | j r|dk r ||kr |gS t|}d}d}g }|t|k r|| }t|r^||g d}n |rl|g d}|d | |d7 }q0dd |D S ) z&Splits punctuation on a piece of text.Nr TFrh c S s g | ]}d |qS )r[ )r\ )r, xr r r r. s z5BasicTokenizer._run_split_on_punc..)r listrN r rT )rH r# r/ charsiZstart_new_wordr r r r r r s"
z!BasicTokenizer._run_split_on_puncc C sT g }|D ]@}t |}| |r>|d || |d q|| qd|S )z)Adds whitespace around any CJK character.rZ r[ )ord_is_chinese_charrT r\ rH r# r r cpr r r r s
z&BasicTokenizer._tokenize_chinese_charsc C s |dkr|dks|dkr |dks|dkr0|dks|dkr@|dks|d krP|d
ks|d kr`|d ks|d
krp|dks|dkr|dkrdS dS )z6Checks whether CP is the codepoint of a CJK character.i N i i 4 iM i iߦ i i? i@ i i i i i i i TFr )rH r r r r r sD
z BasicTokenizer._is_chinese_charc C sX g }|D ]D}t |}|dks|dkst|r.qt|rB|d q|| qd|S )zBPerforms invalid character removal and whitespace cleanup on text.r i rZ r[ )r r r
rT r\ r r r r r s zBasicTokenizer._clean_text)TNTNT)N)N) r{ r| r} r~ rG rS r r r r r r r r r rB I s
&
rB c @ s" e Zd ZdZdddZdd ZdS ) rD z Runs WordPiece tokenization.d c C s || _ || _|| _d S rL )r r2 max_input_chars_per_word)rH r r2 r r r r rG s zWordpieceTokenizer.__init__c C s g }t |D ]}t|}t|| jkr4|| j q d}d}g }|t|k rt|}d} ||k rd||| }
|dkrd|
}
|
| jkr|
} q|d8 }qX| dkrd}q|| |}q@|r|| j q || q |S )a
Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
tokenization using the given vocabulary.
For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.
Args:
text: A single token or whitespace separated tokens. This should have
already been passed through *BasicTokenizer*.
Returns:
A list of wordpiece tokens.
Fr Nr[ z##rh T) r$ r rN r rT r2 r\ r r ) rH r# r r r Zis_badstartZ
sub_tokensendZ
cur_substrsubstrr r r rS s:
zWordpieceTokenizer.tokenizeN)r )r{ r| r} r~ rG rS r r r r rD s
rD ) r~ r r< r typingr r r Ztokenization_utilsr r r r r
utilsr Z
get_loggerr{ rv rt r r r r r$ r% objectrB rD r r r r s6
#