U
    dJ                     @   s  d dl Z d dlZd dlmZ d dlmZmZ d dlmZm	Z	m
Z
mZmZ ddlmZmZmZmZ ddlmZmZmZmZ ddlmZ dd	lmZmZ dd
lmZmZmZm Z m!Z!m"Z"m#Z# e $dZ%e & Z'e'(e )d de*e+e+e,ee
e-  ee
e-  e.e.ed	ddZ/d e	e+e+e,ee
e-  ee
e-  e.e.ed	ddZ0d!de+e+e,ee
e-  ee
e-  e.e.ed	ddZ1d"de+e+e,ee
e-  ee
e-  e.edddZ2dS )#    N)PathLike)basenamesplitext)AnyBinaryIOListOptionalSet   )coherence_ratioencoding_languagesmb_encoding_languagesmerge_coherence_ratios)IANA_SUPPORTEDTOO_BIG_SEQUENCETOO_SMALL_SEQUENCETRACE)
mess_ratio)CharsetMatchCharsetMatches)any_specified_encodingcut_sequence_chunks	iana_nameidentify_sig_or_bomis_cp_similaris_multi_byte_encodingshould_strip_sig_or_bomZcharset_normalizerz)%(asctime)s | %(levelname)s | %(message)s      皙?TF)		sequencessteps
chunk_size	thresholdcp_isolationcp_exclusionpreemptive_behaviourexplainreturnc           -      C   s  t | ttfs tdt| |r>tj}tt	 t
t t| }	|	dkrtd |rvtt	 t
|prtj tt| dddg dgS |dk	rttd	d
| dd |D }ng }|dk	rttdd
| dd |D }ng }|	|| krttd|||	 d}|	}|dkr:|	| |k r:t|	| }t| tk }
t| tk}|
rlttd|	 n|rttd|	 g }|rt| nd}|dk	r|| ttd| t }g }g }d}d}d}t }t| \}}|dk	r|| ttdt|| |d d|kr.|d |t D ]}|rP||krPq6|rd||krdq6||krrq6|| d}||k}|ot|}|dkr|sttd| q6zt|}W n. t t!fk
r   ttd| Y q6Y nX zr|r>|dkr>t"|dkr"| dtd n| t|td |d n&t"|dkrN| n| t|d |d}W n\ t#t$fk
r } z8t |t$sttd|t"| || W Y q6W 5 d}~X Y nX d}|D ]}t%||rd} qq|rttd|| q6t&|sdnt||	t|	| }|o@|dk	o@t||	k } | rVttd| tt|d }!t'|!d }!d}"d}#g }$g }%ztt(| ||||||||	D ]V}&|$|& |%t)|&| |%d! |kr|"d7 }"|"|!ks|r|dkr qqW n@ t#k
r4 } z ttd"|t"| |!}"d}#W 5 d}~X Y nX |#s|r|sz| td#d j*|d$d% W nL t#k
r } z,ttd&|t"| || W Y q6W 5 d}~X Y nX |%rt+|%t|% nd}'|'|ks|"|!krZ|| ttd'||"t,|'d( d)d* |dd|fkr6|#s6t| ||dg |}(||krB|(}n|dkrR|(}n|(}q6ttd+|t,|'d( d)d* |st-|})nt.|})|)rttd,|t"|) g }*|dkr|$D ],}&t/|&d-|)rd.|)nd}+|*|+ qt0|*},|,rttd/|,| |t| ||'||,| ||ddfkrx|'d-k rxtd0| |rftt	 t
| t|| g  S ||kr6td1| |rtt	 t
| t|| g  S q6t|dkrn|s|s|rttd2 |r
td3|j1 || nd|r|dks>|r4|r4|j2|j2ks>|dk	rTtd4 || n|rntd5 || |rtd6|3 j1t|d  n
td7 |rtt	 t
| |S )8ae  
    Given a raw bytes sequence, return the best possibles charset usable to render str objects.
    If there is no results, it is a strong indicator that the source is binary/not text.
    By default, the process will extract 5 blocs of 512o each to assess the mess and coherence of a given sequence.
    And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.

    The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
    but never take it for granted. Can improve the performance.

    You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
    purpose.

    This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
    By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
    toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
    Custom logging format and handler can be set manually.
    z4Expected object of type bytes or bytearray, got: {0}r   z<Encoding detection on empty bytes, assuming utf_8 intention.utf_8g        F Nz`cp_isolation is set. use this flag for debugging purpose. limited list of encoding allowed : %s.z, c                 S   s   g | ]}t |d qS Fr   .0cp r0   :/tmp/pip-unpacked-wheel-b4wixufl/charset_normalizer/api.py
<listcomp>[   s     zfrom_bytes.<locals>.<listcomp>zacp_exclusion is set. use this flag for debugging purpose. limited list of encoding excluded : %s.c                 S   s   g | ]}t |d qS r+   r,   r-   r0   r0   r1   r2   f   s     z^override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.r
   z>Trying to detect encoding from a tiny portion of ({}) byte(s).zIUsing lazy str decoding because the payload is quite large, ({}) byte(s).z@Detected declarative mark in sequence. Priority +1 given for %s.zIDetected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.ascii>   utf_16utf_32z[Encoding %s wont be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.z2Encoding %s does not provide an IncrementalDecoderg    A)encodingz9Code page %s does not fit given bytes sequence at ALL. %sTzW%s is deemed too similar to code page %s and was consider unsuited already. Continuing!zpCode page %s is a multi byte encoding table and it appear that at least one character was encoded using n-bytes.      zaLazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %sg     j@strict)errorsz^LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %szc%s was excluded because of initial chaos probing. Gave up %i time(s). Computed mean chaos is %f %%.d      )ndigitsz=%s passed initial chaos probing. Mean measured chaos is %f %%z&{} should target any language(s) of {}g?,z We detected language {} using {}z.Encoding detection: %s is most likely the one.zoEncoding detection: %s is most likely the one as we detected a BOM or SIG within the beginning of the sequence.zONothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.z7Encoding detection: %s will be used as a fallback matchz:Encoding detection: utf_8 will be used as a fallback matchz:Encoding detection: ascii will be used as a fallback matchz]Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.z=Encoding detection: Unable to determine any suitable charset.)4
isinstance	bytearraybytes	TypeErrorformattypeloggerlevel
addHandlerexplain_handlersetLevelr   lendebugremoveHandlerloggingWARNINGr   r   logjoinintr   r   r   appendsetr   r   addr   r   ModuleNotFoundErrorImportErrorstrUnicodeDecodeErrorLookupErrorr   rangemaxr   r   decodesumroundr   r   r   r   r6   fingerprintbest)-r    r!   r"   r#   r$   r%   r&   r'   Zprevious_logger_levellengthZis_too_small_sequenceZis_too_large_sequenceZprioritized_encodingsZspecified_encodingZtestedZtested_but_hard_failureZtested_but_soft_failureZfallback_asciiZfallback_u8Zfallback_specifiedresultsZsig_encodingZsig_payloadZencoding_ianaZdecoded_payloadZbom_or_sig_availableZstrip_sig_or_bomZis_multi_byte_decodereZsimilar_soft_failure_testZencoding_soft_failedZr_Zmulti_byte_bonusZmax_chunk_gave_upZearly_stop_countZlazy_str_hard_failureZ	md_chunksZ	md_ratioschunkZmean_mess_ratioZfallback_entryZtarget_languagesZ	cd_ratiosZchunk_languagesZcd_ratios_mergedr0   r0   r1   
from_bytes#   s   























     


 
    





	






rf   )	fpr!   r"   r#   r$   r%   r&   r'   r(   c              	   C   s   t |  |||||||S )z
    Same thing than the function from_bytes but using a file pointer that is already ready.
    Will not close the file pointer.
    )rf   read)rg   r!   r"   r#   r$   r%   r&   r'   r0   r0   r1   from_fp  s    ri   zPathLike[Any])	pathr!   r"   r#   r$   r%   r&   r'   r(   c           	   
   C   s8   t | d$}t||||||||W  5 Q R  S Q R X dS )z
    Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
    Can raise IOError.
    rbN)openri   )	rj   r!   r"   r#   r$   r%   r&   r'   rg   r0   r0   r1   	from_path  s    rm   )rj   r!   r"   r#   r$   r%   r&   r(   c              	   C   s   t dt t| ||||||}t| }tt|}	t|dkrNtd	||
 }
|	d  d|
j 7  < td	t| |d|	d}||
  W 5 Q R X |
S )zi
    Take a (text-based) file path and try to create another file next to it, this time using UTF-8.
    z2normalize is deprecated and will be removed in 3.0r   z;Unable to normalize "{}", no encoding charset seems to fit.-z{}r*   wb)warningswarnDeprecationWarningrm   r   listr   rK   IOErrorrD   ra   r6   rl   rX   replacerQ   writeoutput)rj   r!   r"   r#   r$   r%   r&   rc   filenameZtarget_extensionsresultrg   r0   r0   r1   	normalize  s<    
 rz   )r   r   r   NNTF)r   r   r   NNTF)r   r   r   NNTF)r   r   r   NNT)3rN   rp   osr   os.pathr   r   typingr   r   r   r   r	   Zcdr   r   r   r   Zconstantr   r   r   r   Zmdr   modelsr   r   utilsr   r   r   r   r   r   r   	getLoggerrF   StreamHandlerrI   setFormatter	FormatterrB   rR   floatrX   boolrf   ri   rm   rz   r0   r0   r0   r1   <module>   s   $
       

   G       

       

      

