
    -:jP                     Z   d Z ddlmZ ddlmZmZmZ eeef   Ze	Z
	 eee	   ee	   f   Z	 ee
ee
e
f   ee
   f   Z	 eeeeef   ee   f   Z	 ee
ef   Z	 eeef   Z	  G d de      Z G d de      Z G d d	e      Zd
dlmZmZmZmZmZmZmZmZmZmZmZmZm Z m!Z! d
dl"m#Z#m$Z$m%Z%m&Z&m'Z' y)u  Tokenizers — fast, batteries-included tokenization library.

Free-threaded Python (3.14t) note:
    Wheels built against free-threaded CPython declare ``Py_MOD_GIL_NOT_USED``
    and use ``RwLock``-guarded interior mutability so component setters are
    safe to call from multiple threads. Compound mutations
    (``tokenizer.post_processor.special_tokens = …``) are still not atomic —
    use a Python lock if you need the read-then-write to be serialized.
    See ``docs/free-threading-audit.md`` for the full analysis.
    )Enum)ListTupleUnionc                       e Zd ZdZdZy)OffsetReferentialoriginal
normalizedN)__name__
__module____qualname__ORIGINAL
NORMALIZED     U/var/www/html/tokenscope/api/venv/lib/python3.12/site-packages/tokenizers/__init__.pyr   r   G   s    HJr   r   c                       e Zd ZdZdZy)
OffsetTypebytecharN)r   r   r   BYTECHARr   r   r   r   r   L   s    DDr   r   c                        e Zd ZdZdZdZdZdZy)SplitDelimiterBehaviorremovedisolatedmerged_with_previousmerged_with_next
contiguousN)r   r   r   REMOVEDISOLATEDMERGED_WITH_PREVIOUSMERGED_WITH_NEXT
CONTIGUOUSr   r   r   r   r   Q   s    GH1)Jr   r      )
AddedTokenEncodingNormalizedStringPreTokenizedStringRegexToken	Tokenizerdecodersmodelsnormalizerspre_tokenizers
processorstrainers__version__)BertWordPieceTokenizerByteLevelBPETokenizerCharBPETokenizerSentencePieceBPETokenizerSentencePieceUnigramTokenizerN)(__doc__enumr   typingr   r   r   intOffsetsstrTextInputSequencePreTokenizedInputSequenceTextEncodeInputPreTokenizedEncodeInputInputSequenceEncodeInputr   r   r   
tokenizersr&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   implementationsr4   r5   r6   r7   r8   r   r   r   <module>rG      s  	  % % S/  5!$s)U3Z"78  	
.
./	
  	
#%>
>?	"#% 
 ')BBC O%<<= 
 
T      r   