o
    a+)h,  ã                   @   sL   d dl Z d dlZd dlmZmZ ddlmZmZ e d¡Z	G dd„ dƒZ
dS )é    N)ÚOptionalÚUnioné   )ÚLanguageFilterÚProbingStates%   [a-zA-Z]*[€-ÿ]+[a-zA-Z]*[^a-zA-Z€-ÿ]?c                   @   sò   e Zd ZdZejfdeddfdd„Zddd„Zede	e
 fd	d
„ƒZede	e
 fdd„ƒZdeeef defdd„Zedefdd„ƒZdefdd„Zedeeef defdd„ƒZedeeef defdd„ƒZedeeef defdd„ƒZdS )ÚCharSetProbergffffffî?Úlang_filterÚreturnNc                 C   s$   t j| _d| _|| _t t¡| _d S )NT)	r   Ú	DETECTINGÚ_stateÚactiver   ÚloggingÚ	getLoggerÚ__name__Úlogger)Úselfr   © r   ú`C:\Users\User\Downloads\Proyecto_IoT\venv\Lib\site-packages\pip/_vendor/chardet/charsetprober.pyÚ__init__,   s   zCharSetProber.__init__c                 C   s   t j| _d S ©N)r   r
   r   ©r   r   r   r   Úreset2   s   zCharSetProber.resetc                 C   s   d S r   r   r   r   r   r   Úcharset_name5   ó   zCharSetProber.charset_namec                 C   ó   t ‚r   ©ÚNotImplementedErrorr   r   r   r   Úlanguage9   r   zCharSetProber.languageÚbyte_strc                 C   r   r   r   )r   r   r   r   r   Úfeed=   ó   zCharSetProber.feedc                 C   s   | j S r   )r   r   r   r   r   Ústate@   s   zCharSetProber.statec                 C   s   dS )Ng        r   r   r   r   r   Úget_confidenceD   r    zCharSetProber.get_confidenceÚbufc                 C   s   t  dd| ¡} | S )Ns   ([ -])+ó    )ÚreÚsub)r#   r   r   r   Úfilter_high_byte_onlyG   s   z#CharSetProber.filter_high_byte_onlyc                 C   sZ   t ƒ }t | ¡}|D ] }| |dd… ¡ |dd… }| ¡ s%|dk r%d}| |¡ q
|S )u7  
        We define three types of bytes:
        alphabet: english alphabets [a-zA-Z]
        international: international characters [Â€-Ã¿]
        marker: everything else [^a-zA-ZÂ€-Ã¿]
        The input buffer can be thought to contain a series of words delimited
        by markers. This function works to filter all words that contain at
        least one international character. All contiguous sequences of markers
        are replaced by a single space ascii character.
        This filter applies to all scripts which do not use English characters.
        Néÿÿÿÿó   €r$   )Ú	bytearrayÚINTERNATIONAL_WORDS_PATTERNÚfindallÚextendÚisalpha)r#   ÚfilteredÚwordsÚwordÚ	last_charr   r   r   Úfilter_international_wordsL   s   
z(CharSetProber.filter_international_wordsc                 C   s’   t ƒ }d}d}t| ƒ d¡} t| ƒD ])\}}|dkr!|d }d}q|dkr;||kr9|s9| | ||… ¡ | d¡ d}q|sG| | |d	… ¡ |S )
a[  
        Returns a copy of ``buf`` that retains only the sequences of English
        alphabet and high byte characters that are not between <> characters.
        This filter can be applied to all scripts which contain both English
        characters and extended ASCII characters, but is currently only used by
        ``Latin1Prober``.
        Fr   Úcó   >r   ó   <r$   TN)r*   Ú
memoryviewÚcastÚ	enumerater-   )r#   r/   Úin_tagÚprevÚcurrÚbuf_charr   r   r   Úremove_xml_tagsn   s"   	
€zCharSetProber.remove_xml_tags)r	   N)r   Ú
__module__Ú__qualname__ÚSHORTCUT_THRESHOLDr   ÚNONEr   r   Úpropertyr   Ústrr   r   r   Úbytesr*   r   r   r!   Úfloatr"   Ústaticmethodr'   r3   r>   r   r   r   r   r   (   s$    
! r   )r   r%   Útypingr   r   Úenumsr   r   Úcompiler+   r   r   r   r   r   Ú<module>   s   ÿ