o
    ;)h1                     @  s   d dl mZ d dlmZ d dlmZ d dlmZ d dlm	Z	 d dl
mZmZmZmZ ddlmZmZ dd	lmZmZmZ G d
d dZG dd dZeeef Zee ZG dd dZdS )    )annotations)aliases)sha256)dumps)sub)AnyIteratorListTuple   )RE_POSSIBLE_ENCODING_INDICATIONTOO_BIG_SEQUENCE)	iana_nameis_multi_byte_encodingunicode_rangec                   @  sH  e Zd Z		dGdHddZdIddZdIddZedJddZdKddZdKddZ	dLdd Z
edKd!d"ZedMd$d%ZedNd&d'ZedNd(d)ZedMd*d+ZedKd,d-ZedJd.d/ZedJd0d1ZedJd2d3ZedJd4d5ZedOd6d7ZedPd9d:ZedNd;d<ZedMd=d>ZedMd?d@ZdQdRdCdDZedKdEdFZdS )SCharsetMatchNpayloadbytesguessed_encodingstrmean_mess_ratiofloathas_sig_or_bombool	languagesCoherenceMatchesdecoded_payload
str | Nonepreemptive_declarationc                 C  sL   || _ || _|| _|| _|| _d | _g | _d| _d | _d | _	|| _
|| _d S )N        )_payload	_encoding_mean_mess_ratio
_languages_has_sig_or_bom_unicode_ranges_leavesZ_mean_coherence_ratio_output_payload_output_encoding_string_preemptive_declaration)selfr   r   r   r   r   r   r    r,   XC:\Users\User\Downloads\Proyecto_IoT\venv\Lib\site-packages\charset_normalizer/models.py__init__   s   

zCharsetMatch.__init__otherobjectreturnc                 C  s>   t |tst |trt|| jkS dS | j|jko| j|jkS )NF)
isinstancer   r   r   encodingfingerprintr+   r/   r,   r,   r-   __eq__*   s
   

zCharsetMatch.__eq__c                 C  s   t |tstt| j|j }t| j|j }|dk r%|dkr%| j|jkS |dk r@|dkr@t| jtkr:| j|jk S | j	|j	kS | j|jk S )zQ
        Implemented to make sorted available upon CharsetMatches items.
        g{Gz?g{Gz?)
r2   r   
ValueErrorabschaos	coherencelenr    r   multi_byte_usage)r+   r/   Zchaos_differenceZcoherence_differencer,   r,   r-   __lt__1   s   
zCharsetMatch.__lt__c                 C  s   dt t| t | j  S )Ng      ?)r;   r   rawr+   r,   r,   r-   r<   G   s   zCharsetMatch.multi_byte_usagec                 C  s"   | j d u rt| j| jd| _ | j S )Nstrict)r)   r   r    r!   r?   r,   r,   r-   __str__K   s   
zCharsetMatch.__str__c                 C  s   d| j  d| j dS )Nz<CharsetMatch 'z' bytes(z)>)r3   r4   r?   r,   r,   r-   __repr__Q   s   zCharsetMatch.__repr__Nonec                 C  s8   t |tr	|| krtd|jd |_| j| d S )Nz;Unable to add instance <{}> as a submatch of a CharsetMatch)r2   r   r7   format	__class__r)   r&   appendr5   r,   r,   r-   add_submatchT   s   zCharsetMatch.add_submatchc                 C     | j S N)r!   r?   r,   r,   r-   r3   _      zCharsetMatch.encoding	list[str]c                 C  sD   g }t  D ]\}}| j|kr|| q| j|kr|| q|S )z
        Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
        )r   itemsr3   rF   )r+   Zalso_known_asupr,   r,   r-   encoding_aliasesc   s   


zCharsetMatch.encoding_aliasesc                 C  rH   rI   r$   r?   r,   r,   r-   bomp   rJ   zCharsetMatch.bomc                 C  rH   rI   rP   r?   r,   r,   r-   byte_order_markt   rJ   zCharsetMatch.byte_order_markc                 C  s   dd | j D S )z
        Return the complete list of possible languages found in decoded sequence.
        Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
        c                 S  s   g | ]}|d  qS )r   r,   ).0er,   r,   r-   
<listcomp>~       z*CharsetMatch.languages.<locals>.<listcomp>r#   r?   r,   r,   r-   r   x   s   zCharsetMatch.languagesc                 C  sp   | j s1d| jv r
dS ddlm}m} t| jr|| jn|| j}t|dks+d|v r-dS |d S | j d d S )z
        Most probable language found in decoded sequence. If none were detected or inferred, the property will return
        "Unknown".
        asciiZEnglishr   )encoding_languagesmb_encoding_languageszLatin BasedUnknown)r#   could_be_from_charsetZcharset_normalizer.cdrY   rZ   r   r3   r;   )r+   rY   rZ   r   r,   r,   r-   language   s   
zCharsetMatch.languagec                 C  rH   rI   )r"   r?   r,   r,   r-   r9      rJ   zCharsetMatch.chaosc                 C  s   | j sdS | j d d S )Nr   r   r   rW   r?   r,   r,   r-   r:      s   zCharsetMatch.coherencec                 C     t | jd ddS Nd      )ndigits)roundr9   r?   r,   r,   r-   percent_chaos      zCharsetMatch.percent_chaosc                 C  r^   r_   )rc   r:   r?   r,   r,   r-   percent_coherence   re   zCharsetMatch.percent_coherencec                 C  rH   )z+
        Original untouched bytes.
        )r    r?   r,   r,   r-   r>      s   zCharsetMatch.rawlist[CharsetMatch]c                 C  rH   rI   )r&   r?   r,   r,   r-   submatch   rJ   zCharsetMatch.submatchc                 C     t | jdkS Nr   )r;   r&   r?   r,   r,   r-   has_submatch   s   zCharsetMatch.has_submatchc                 C  s@   | j d ur| j S dd t| D }ttdd |D | _ | j S )Nc                 S  s   g | ]}t |qS r,   )r   )rS   charr,   r,   r-   rU      rV   z*CharsetMatch.alphabets.<locals>.<listcomp>c                 S  s   h | ]}|r|qS r,   r,   )rS   rr,   r,   r-   	<setcomp>   rV   z)CharsetMatch.alphabets.<locals>.<setcomp>)r%   r   sortedlist)r+   Zdetected_rangesr,   r,   r-   	alphabets   s
   
zCharsetMatch.alphabetsc                 C  s   | j gdd | jD  S )z
        The complete list of encoding that output the exact SAME str result and therefore could be the originating
        encoding.
        This list does include the encoding available in property 'encoding'.
        c                 S  s   g | ]}|j qS r,   )r3   )rS   mr,   r,   r-   rU      s    z6CharsetMatch.could_be_from_charset.<locals>.<listcomp>)r!   r&   r?   r,   r,   r-   r\      s   z"CharsetMatch.could_be_from_charsetutf_8r3   c                   s~    j du s
 j |kr<| _ t } jdur5 j dvr5tt fdd|dd dd}||dd  }||d _ jS )	z
        Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
        Any errors will be simply ignored by the encoder NOT replaced.
        N)zutf-8utf8rs   c                   s<   | j |  d |  d  |  d t jddS )Nr   r   _-)stringspanreplacegroupsr   r(   )rr   r?   r,   r-   <lambda>   s    
z%CharsetMatch.output.<locals>.<lambda>i    r   )country   )r(   r   r*   lowerr   r   encoder'   )r+   r3   decoded_stringZpatched_headerr,   r?   r-   output   s    



zCharsetMatch.outputc                 C  s   t |   S )zw
        Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
        )r   r   	hexdigestr?   r,   r,   r-   r4      s   zCharsetMatch.fingerprint)NN)r   r   r   r   r   r   r   r   r   r   r   r   r   r   )r/   r0   r1   r   )r1   r   r1   r   )r/   r   r1   rC   )r1   rK   r1   r   )r1   r   )r1   rg   )rs   )r3   r   r1   r   )__name__
__module____qualname__r.   r6   r=   propertyr<   rA   rB   rG   r3   rO   rQ   rR   r   r]   r9   r:   rd   rf   r>   rh   rk   rq   r\   r   r4   r,   r,   r,   r-   r      sX    




	r   c                   @  sb   e Zd ZdZddddZd d	d
Zd!ddZd"ddZd#ddZd$ddZ	d%ddZ
d%ddZdS )&CharsetMatchesz
    Container with every CharsetMatch items ordered by default from most probable to the less one.
    Act like a list(iterable) but does not implements all related methods.
    Nresultslist[CharsetMatch] | Nonec                 C  s   |r	t || _d S g | _d S rI   )ro   _results)r+   r   r,   r,   r-   r.      s   zCharsetMatches.__init__r1   Iterator[CharsetMatch]c                 c  s    | j E d H  d S rI   r   r?   r,   r,   r-   __iter__   s   zCharsetMatches.__iter__item	int | strr   c                 C  sJ   t |tr
| j| S t |tr#t|d}| jD ]}||jv r"|  S qt)z
        Retrieve a single item either by its position or encoding name (alias may be used here).
        Raise KeyError upon invalid index or encoding not present in results.
        F)r2   intr   r   r   r\   KeyError)r+   r   resultr,   r,   r-   __getitem__  s   





zCharsetMatches.__getitem__r   c                 C  s
   t | jS rI   r;   r   r?   r,   r,   r-   __len__  s   
zCharsetMatches.__len__r   c                 C  ri   rj   r   r?   r,   r,   r-   __bool__  s   zCharsetMatches.__bool__rC   c                 C  s|   t |tstdt|jt|jtk r0| j	D ]}|j
|j
kr/|j|jkr/||  dS q| j	| t| j	| _	dS )z~
        Insert a single match. Will be inserted accordingly to preserve sort.
        Can be inserted as a submatch.
        z-Cannot append instance '{}' to CharsetMatchesN)r2   r   r7   rD   r   rE   r;   r>   r   r   r4   r9   rG   rF   ro   )r+   r   matchr,   r,   r-   rF     s   


zCharsetMatches.appendCharsetMatch | Nonec                 C  s   | j sdS | j d S )zQ
        Simply return the first match. Strict equivalent to matches[0].
        Nr   r   r?   r,   r,   r-   best)  s   
zCharsetMatches.bestc                 C  s   |   S )zP
        Redundant method, call the method best(). Kept for BC reasons.
        )r   r?   r,   r,   r-   first1  s   zCharsetMatches.firstrI   )r   r   )r1   r   )r   r   r1   r   )r1   r   r   )r   r   r1   rC   )r1   r   )r   r   r   __doc__r.   r   r   r   r   rF   r   r   r,   r,   r,   r-   r      s    





r   c                   @  s.   e Zd ZdddZedddZdddZdS )CliDetectionResultpathr   r3   r   rO   rK   alternative_encodingsr]   rq   r   r   r9   r   r:   unicode_pathis_preferredc                 C  sF   || _ |
| _|| _|| _|| _|| _|| _|| _|| _|	| _	|| _
d S rI   )r   r   r3   rO   r   r]   rq   r   r9   r:   r   )r+   r   r3   rO   r   r]   rq   r   r9   r:   r   r   r,   r,   r-   r.   =  s   
zCliDetectionResult.__init__r1   dict[str, Any]c                 C  s2   | j | j| j| j| j| j| j| j| j| j	| j
dS )Nr   r3   rO   r   r]   rq   r   r9   r:   r   r   r   r?   r,   r,   r-   __dict__W  s   zCliDetectionResult.__dict__c                 C  s   t | jdddS )NT   )ensure_asciiindent)r   r   r?   r,   r,   r-   to_jsong  s   zCliDetectionResult.to_jsonN)r   r   r3   r   rO   rK   r   rK   r]   r   rq   rK   r   r   r9   r   r:   r   r   r   r   r   )r1   r   r   )r   r   r   r.   r   r   r   r,   r,   r,   r-   r   <  s
    
r   N)
__future__r   Zencodings.aliasesr   hashlibr   jsonr   rer   typingr   r   r	   r
   Zconstantr   r   utilsr   r   r   r   r   r   r   ZCoherenceMatchr   r   r,   r,   r,   r-   <module>   s     iC