File manager - Edit - /home/u478019808/domains/bestandroidphones.store/public_html/static/img/logo/charset_normalizer.zip
Back
PK -�Z>9^+�. �. ! __pycache__/models.cpython-39.pycnu �[��� a g�0 � @ s� d dl mZ d dlmZ d dlmZ d dlmZ d dlm Z m Z m Z m Z m Z mZmZ ddlmZmZ ddlmZmZmZ G d d � d �ZG d d � d �Zeeef Ze e Z G d d� d�Z dS )� )�aliases)�sha256)�dumps)�sub)�Any�Dict�Iterator�List�Optional�Tuple�Union� )� RE_POSSIBLE_ENCODING_INDICATION�TOO_BIG_SEQUENCE)� iana_name�is_multi_byte_encoding� unicode_rangec @ s� e Zd Zd8eeeedee ee d�dd�Ze ed�dd�Z e ed�d d �Z e ed �d d ��Z ed �dd�Zed �dd�Zd dd�dd�Ze ed �dd��Ze ee d �dd��Ze ed �dd��Ze ed �dd��Ze ee d �d d ��Ze ed �d d ��Ze ed �d d!��Ze ed �d"d#��Ze ed �d$d%��Ze ed �d&d'��Ze ed �d(d)��Z e ed d �d*d+��Z e ed �d,d-��Z e ee d �d.d/��Z e ee d �d0d1��Z d9eed3�d4d5�Z!e ed �d6d7��Z"dS ):� CharsetMatchN�CoherenceMatches)�payload�guessed_encoding�mean_mess_ratio�has_sig_or_bom� languages�decoded_payload�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) �G/opt/gsutil/third_party/charset_normalizer/charset_normalizer/models.py�__init__ s zCharsetMatch.__init__)�other�returnc C s> t |t�s&t |t�r"t|�| jkS dS | j|jko<| j|jkS )NF)� isinstancer �strr �encoding� fingerprint�r( r, r) r) r* �__eq__( s zCharsetMatch.__eq__c C s� t |t�st�t| j|j �}t| j|j �}|dk rJ|dkrJ| j|jkS |dk r�|dkr�t| j�tkrt| j|jk S | j |j kS | j|jk S )zQ Implemented to make sorted available upon CharsetMatches items. g{�G�z�?g{�G�z�?) r. r � ValueError�abs�chaos� coherence�lenr r �multi_byte_usage)r( r, Zchaos_differenceZcoherence_differencer) r) r* �__lt__/ s zCharsetMatch.__lt__�r- c C s dt t| ��t | j� S )Ng �?)r8 r/ �raw�r( r) r) r* r9 E s z CharsetMatch.multi_byte_usagec C s" | j d u r t| j| jd�| _ | j S )N�strict)r& r/ r r r= r) r) r* �__str__I s zCharsetMatch.__str__c C s d� | j| j�S )Nz <CharsetMatch '{}' bytes({})>)�formatr0 r1 r= r) r) r* �__repr__O s zCharsetMatch.__repr__c C s8 t |t�r|| kr"td�|j���d |_| j�|� d S )Nz;Unable to add instance <{}> as a submatch of a CharsetMatch)r. r r4 r@ � __class__r& r# �appendr2 r) r) r* � add_submatchR s ��zCharsetMatch.add_submatchc C s | j S �N)r r= r) r) r* r0 ] s zCharsetMatch.encodingc C sD g }t �� D ]2\}}| j|kr*|�|� q | j|kr |�|� 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 �itemsr0 rC )r( Z also_known_as�u�pr) r) r* �encoding_aliasesa s z CharsetMatch.encoding_aliasesc C s | j S rE �r! r= r) r) r* �bomn s zCharsetMatch.bomc C s | j S rE rJ r= r) r) r* �byte_order_markr s z CharsetMatch.byte_order_markc C s dd� | 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 �qS )r r) )�.0�er) r) r* � <listcomp>| � z*CharsetMatch.languages.<locals>.<listcomp>�r r= r) r) r* r v s zCharsetMatch.languagesc C sp | j sbd| jv rdS ddlm}m} t| j�r8|| j�n|| j�}t|�dksVd|v rZdS |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". �ascii�Englishr )�encoding_languages�mb_encoding_languagesz Latin Based�Unknown)r �could_be_from_charsetZcharset_normalizer.cdrT rU r r0 r8 )r( rT rU r r) r) r* �language~ s � �zCharsetMatch.languagec C s | j S rE )r r= r) r) r* r6 � s zCharsetMatch.chaosc C s | j s dS | j d d S )Nr r r rQ r= r) r) r* r7 � s zCharsetMatch.coherencec C s t | jd dd�S �N�d � )�ndigits)�roundr6 r= r) r) r* � percent_chaos� s zCharsetMatch.percent_chaosc C s t | jd dd�S rY )r] r7 r= r) r) r* �percent_coherence� s z CharsetMatch.percent_coherencec C s | j S )z+ Original untouched bytes. )r r= r) r) r* r< � s zCharsetMatch.rawc C s | j S rE )r# r= r) r) r* �submatch� s zCharsetMatch.submatchc C s t | j�dkS �Nr )r8 r# r= r) r) r* � has_submatch� s zCharsetMatch.has_submatchc C s@ | j d ur| j S dd� t| �D �}ttdd� |D ���| _ | j S )Nc S s g | ] }t |��qS r) )r )rM �charr) r) r* rO � s z*CharsetMatch.alphabets.<locals>.<listcomp>c S s h | ] }|r|�qS r) r) )rM �rr) r) r* � <setcomp>� rP z)CharsetMatch.alphabets.<locals>.<setcomp>)r" r/ �sorted�list)r( Zdetected_rangesr) r) r* � alphabets� s �zCharsetMatch.alphabetsc C s | j gdd� | jD � 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 �qS r) )r0 )rM �mr) r) r* rO � rP z6CharsetMatch.could_be_from_charset.<locals>.<listcomp>)r r# r= r) r) r* rW � s z"CharsetMatch.could_be_from_charset�utf_8)r0 r- c s| � j du s� j |krv|� _ t� �}� jdurh� j�� dvrhtt� fdd�|dd� d�}||dd� }|�|d�� _� jS )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)zutf-8�utf8rj c s4 | j | �� d | �� d � �| �� d t� j��S )Nr r )�string�span�replace�groupsr r% )ri r= r) r* �<lambda>� s �z%CharsetMatch.output.<locals>.<lambda>i r rn )r% r/ r' �lowerr r �encoder$ )r( r0 �decoded_stringZpatched_headerr) r= r* �output� s$ ��� � zCharsetMatch.outputc C s t | �� ��� S )zw Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one. )r rt � hexdigestr= r) r) r* r1 � s zCharsetMatch.fingerprint)NN)rj )#�__name__� __module__� __qualname__�bytesr/ �float�boolr r+ �objectr3 r: �propertyr9 r? rA rD r0 r rI rK rL r rX r6 r7 r^ r_ r< r` rb rh rW rt r1 r) r) r) r* r sf �� r c @ s� e Zd ZdZdeee d�dd�Zee d�dd�Z e e e f ed �d d �Z e d�d d �Zed�dd�Zedd �dd�Zed d�dd�Zed d�dd�ZdS )�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)�resultsc C s |r t |�ng | _d S rE )rf �_results)r( r r) r) r* r+ � s zCharsetMatches.__init__r; c c s | j E d H d S rE �r� r= r) r) r* �__iter__� s zCharsetMatches.__iter__)�itemr- c C sN t |t�r| j| S t |t�rFt|d�}| jD ]}||jv r.| S q.t�dS )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. FN)r. �intr� r/ r rW �KeyError)r( r� �resultr) r) r* � __getitem__ s zCharsetMatches.__getitem__c C s t | j�S rE �r8 r� r= r) r) r* �__len__ s zCharsetMatches.__len__c C s t | j�dkS ra r� r= r) r) r* �__bool__ s zCharsetMatches.__bool__c C s| t |t�s td�t|j����t|j�tk r`| j D ],}|j |j kr2|j |j kr2|� |� dS q2| j � |� t| j �| _ dS )z~ Insert a single match. Will be inserted accordingly to preserve sort. Can be inserted as a submatch. z-Cannot append instance '{}' to CharsetMatchesN)r. r r4 r@ r/ rB r8 r< r r� r1 r6 rD rC rf )r( r� �matchr) r) r* rC s �� zCharsetMatches.appendr c C s | j s dS | j d S )zQ Simply return the first match. Strict equivalent to matches[0]. Nr r� r= r) r) r* �best( s zCharsetMatches.bestc C s | � � S )zP Redundant method, call the method best(). Kept for BC reasons. )r� r= r) r) r* �first0 s zCharsetMatches.first)N)rv rw rx �__doc__r r r r+ r r� r r� r/ r� r� r{ r� rC r� r� r) r) r) r* r~ � s r~ c @ sj e Zd Zeee ee ee eee eeeee ed� dd�Ze e ee f d�dd��Z ed�dd�Z d S ) �CliDetectionResult� �pathr0 rI �alternative_encodingsrX rh r r6 r7 � unicode_path� is_preferredc C sF || _ | | _|| _|| _|| _|| _|| _|| _|| _| | _ | | _ d S rE ) r� r� r0 rI r� rX rh r r6 r7 r� ) r( r� r0 rI r� rX rh r r6 r7 r� r� r) r) r* r+ < s zCliDetectionResult.__init__r; c C s2 | j | j| j| j| j| j| j| j| j| j | j d� S )Nr� r� r= r) r) r* �__dict__V s �zCliDetectionResult.__dict__c C s t | jddd�S )NT� )� ensure_ascii�indent)r r� r= r) r) r* �to_jsonf s zCliDetectionResult.to_jsonN)rv rw rx r/ r r r{ rz r+ r} r r r� r� r) r) r) r* r� ; s � r� N) Zencodings.aliasesr �hashlibr �jsonr �rer �typingr r r r r r r �constantr r �utilsr r r r r~ r/ rz ZCoherenceMatchr r� r) r) r) r* �<module> s $ jC PK -�Zv����- �- __pycache__/api.cpython-39.pycnu �[��� a g X � @ s� d dl Z d dlmZ d dlmZmZmZmZmZ ddl m Z m Z m Z m Z ddlmZmZmZmZ ddlmZ ddlmZmZ dd lmZmZmZm Z m Z m Z m Z e � d �Z!e �"� Z#e#�$e �%d �� d ee&e'f e(e(e)eee* eee* e+e+e)e+ed� dd�Z,d ee(e(e)eee* eee* e+e+e)e+ed� dd�Z-d ee*e&ef e(e(e)eee* eee* e+e+e)e+ed� dd�Z.d!eee*ee&f e(e(e)eee* eee* e+e+e)e+e+d� d d �Z/dS )"� N)�PathLike)�BinaryIO�List�Optional�Set�Union� )�coherence_ratio�encoding_languages�mb_encoding_languages�merge_coherence_ratios)�IANA_SUPPORTED�TOO_BIG_SEQUENCE�TOO_SMALL_SEQUENCE�TRACE)� mess_ratio)� CharsetMatch�CharsetMatches)�any_specified_encoding�cut_sequence_chunks� iana_name�identify_sig_or_bom� is_cp_similar�is_multi_byte_encoding�should_strip_sig_or_bom�charset_normalizerz)%(asctime)s | %(levelname)s | %(message)s� � 皙�����?TF皙�����?) � sequences�steps� chunk_size� threshold� cp_isolation� cp_exclusion�preemptive_behaviour�explain�language_threshold�enable_fallback�returnc 2 C s� t | ttf�s td�t| ����|r>tj} t�t � t� t � t | �} | dkr�t� d� |rvt�t � t� | prtj� tt| dddg d�g�S |dur�t�t d d �|�� d d � |D �}ng }|dur�t�t d d �|�� dd � |D �}ng }| || k�rt�t d||| � d}| }|dk�r:| | |k �r:t| | �}t | �tk } t | �tk} | �rlt�t d�| �� n| �r�t�t d�| �� g }|�r�t| �nd}|du�r�|�|� t�t d|� t� }g }g }d}d}d}t� }t� }t| �\}}|du�r|�|� t�t dt |�|� |�d� d|v�r4|�d� |t D �]�}|�rV||v�rV�q<|�rj||v �rj�q<||v �rx�q<|� |� d}||k} | �o�t |�} |dv �r�| �s�t�t d|� �q<|dv �r�| �s�t�t d|� �q<z t |�} W n, t t!f�y t�t d|� Y �q<Y n0 zr| �rd| du �rdt"| du �rH| dtd�� n| t |�td�� |d � n&t"| du �rt| n| t |�d� |d �}W nb t#t$f�y� } zDt | t$��s�t�t d |t"| �� |�|� W Y d} ~ �q<W Y d} ~ n d} ~ 0 0 d} |D ] }!t%||!��r�d } �q�q�| �r0t�t d ||!� �q<t&| �s<dnt |�| t| | ��}"| �ol|du�olt |�| k }#|#�r�t�t d |� tt |"�d! �}$t'|$d"�}$d}%d}&g }'g }(z�t(| ||"|| | || |� D ]|})|'�|)� |(�t)|)||d u �odt |� k�o d"kn �� |(d# |k�r |%d7 }%|%|$k�s:| �r�| du �r� �qD�q�W nB t#�y� } z(t�t d$|t"| �� |$}%d }&W Y d} ~ n d} ~ 0 0 |&�s| �r| �sz | td%�d� j*|d&d'� W nR t#�y } z8t�t d(|t"| �� |�|� W Y d} ~ �q<W Y d} ~ n d} ~ 0 0 |(�r$t+|(�t |(� nd}*|*|k�s<|%|$k�r�|�|� t�t d)||%t,|*d* d+d,�� | �r<|dd|fv �r<|&�s<t| ||dg ||d-�}+||k�r�|+}n|dk�r�|+}n|+}�q<t�t d.|t,|*d* d+d,�� | �s�t-|�},nt.|�},|,�rt�t d/�|t"|,��� g }-|dk�rP|'D ],})t/|)||,�r<d0�|,�nd�}.|-�|.� �q"t0|-�}/|/�rrt�t d1�|/|�� t| ||*| |/| du �s�||ddfv �r�|nd|d-�}0|�|0� ||ddfv �r|*d2k �r|*dk�r t� d3|0j1� |�r�t�t � t� | � t|0g� S |�|0� t |��r�|du �s2||v �r�d|v �r�d|v �r�|�2� }1t� d3|1j1� |�rvt�t � t� | � t|1g� S ||k�r<t� d4|� |�r�t�t � t� | � t|| g� S �q<t |�dk� rz|�s�|�s�|�r�t�t d5� |� rt� d6|j1� |�|� nd|� r&|du � sJ|� r@|� r@|j3|j3k� sJ|du� r`t� d7� |�|� n|� rzt� d8� |�|� |� r�t� d9|�2� j1t |�d � n t� d:� |� r�t�t � t� | � |S );af 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 blocks 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 ��qS �F�r ��.0�cp� r2 �D/opt/gsutil/third_party/charset_normalizer/charset_normalizer/api.py� <listcomp>[ � 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 ��qS r- r. r/ r2 r2 r3 r4 f r5 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_32�utf_16z\Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.> �utf_7zREncoding %s won't be tested as-is because detection is unreliable without BOM/SIG.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 � )�ndigits)Zpreemptive_declarationz=%s passed initial chaos probing. Mean measured chaos is %f %%z&{} should target any language(s) of {}�,z We detected language {} using {}r 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 r: �best� fingerprint)2r r! r" r# r$ r% r& r' r( r) Zprevious_logger_level�lengthZis_too_small_sequenceZis_too_large_sequenceZprioritized_encodingsZspecified_encodingZtestedZtested_but_hard_failureZtested_but_soft_failureZfallback_asciiZ fallback_u8Zfallback_specified�resultsZearly_stop_resultsZ sig_encodingZ sig_payloadZ encoding_ianaZdecoded_payloadZbom_or_sig_availableZstrip_sig_or_bomZis_multi_byte_decoder�eZsimilar_soft_failure_testZencoding_soft_failedZr_Zmulti_byte_bonusZmax_chunk_gave_upZearly_stop_countZlazy_str_hard_failureZ md_chunksZ md_ratios�chunkZmean_mess_ratioZfallback_entryZtarget_languagesZ cd_ratiosZchunk_languagesZcd_ratios_mergedZ current_matchZprobable_resultr2 r2 r3 � from_bytes! s$ �� ��� ����� � � ��� � �� �� � $ � �� �� � &�� ��� ���� � $ � � ��� � �� ���� �� �� � ������ � �� ���� �� � rj ) �fpr! r" r# 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. )rj �read) rk r! r" r# r$ r% r& r' r( r) r2 r2 r3 �from_fp s �rm ) �pathr! r" r# r$ r% r& r' r( r) r* c C sH t | d��*} t| ||||||||| � W d � S 1 s:0 Y dS )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)�openrm ) rn r! r" r# r$ r% r& r' r( r) rk r2 r2 r3 � from_path> s �rq ) �fp_or_path_or_payloadr! r" r# r$ r% r& r' r( r) r* c C sz t | ttf�r,t| ||||||||| d� } nHt | ttf�rXt| ||||||||| d� } n t| ||||||||| d� } | S )a) Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string. Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match are disabled to be stricter around ASCII-compatible but unlikely to be a string. ) r! r" r# r$ r% r& r' r( r) )rD r\ r rq rF rE rj rm ) rr r! r" r# r$ r% r& r' r( r) Zguessesr2 r2 r3 � is_binary] sX � ��� � rs ) r r r NNTFr T) r r r NNTFr T) r r r NNTFr T) r r r NNTFr F)0rR �osr �typingr r r r r �cdr r r r Zconstantr r r r �mdr �modelsr r �utilsr r r r r r r � getLoggerrJ � StreamHandlerrM � setFormatter� FormatterrF rE rV �floatr\ �boolrj rm rq rs r2 r2 r2 r3 �<module> s� $ � � � � � � � ! � �PK -�Z33�@ # __pycache__/__init__.cpython-39.pycnu �[��� a g) � @ sx d Z ddlZddlmZmZmZmZ ddlmZ ddl m Z m Z ddl m Z ddlmZmZ d Ze�d ��e�� � dS ) u� Charset-Normalizer ~~~~~~~~~~~~~~ The Real First Universal Charset Detector. A library that helps you read text from an unknown charset encoding. Motivated by chardet, This package is trying to resolve the issue by taking a new approach. All IANA character set names for which the Python core library provides codecs are supported. Basic usage: >>> from charset_normalizer import from_bytes >>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8')) >>> best_guess = results.best() >>> str(best_guess) 'Bсеки човек има право на образование. Oбразованието!' Others methods and usages are available - see the full documentation at <https://github.com/Ousret/charset_normalizer>. :copyright: (c) 2021 by Ahmed TAHRI :license: MIT, see LICENSE for more details. � N� )� from_bytes�from_fp� from_path� is_binary)�detect)� CharsetMatch�CharsetMatches)�set_logging_handler)�VERSION� __version__) r r r r r r r r r r �charset_normalizer)�__doc__�logging�apir r r r Zlegacyr �modelsr r �utilsr �versionr r �__all__� getLogger� addHandler� NullHandler� r r �I/opt/gsutil/third_party/charset_normalizer/charset_normalizer/__init__.py�<module> s PK -�Zʑ���A �A __pycache__/md.cpython-39.pycnu �[��� a g�N � @ sn d dl mZ d dlmZ d dlmZmZ ddlmZm Z m Z ddl m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZmZmZm Z G dd� d�Z G d d � d e �Z G d d � d e �Z G d d� de �Z G dd� de �Z!G dd� de �Z"G dd� de �Z#G dd� de �Z$G dd� de �Z%G dd� de �Z&edd �ee' ee' e(d �d d ��Z)ed d �d'e'e*e(e*d#�d$d%��Z+d&S )(� )� lru_cache)� getLogger)�List�Optional� )� COMMON_SAFE_ASCII_CHARACTERS�TRACE� UNICODE_SECONDARY_RANGE_KEYWORD)�is_accentuated� is_arabic�is_arabic_isolated_form�is_case_variable�is_cjk� is_emoticon� is_hangul� is_hiragana� is_katakana�is_latin�is_punctuation� is_separator� is_symbol�is_thai�is_unprintable� remove_accent� unicode_rangec @ sP e Zd ZdZeed�dd�Zedd�dd�Zdd�d d �Ze e d�d d ��Z dS ) �MessDetectorPluginzy Base abstract class used for mess detection plugins. All detectors MUST extend and implement given methods. �� character�returnc C s t �dS )z@ Determine if given character should be fed in. N��NotImplementedError��selfr � r# �C/opt/gsutil/third_party/charset_normalizer/charset_normalizer/md.py�eligible% s zMessDetectorPlugin.eligibleNc C s t �dS )z� The main routine to be executed upon character. Insert the logic in witch the text would be considered chaotic. Nr r! r# r# r$ �feed+ s zMessDetectorPlugin.feed�r c C s t �dS )zB Permit to reset the plugin to the initial state. Nr �r" r# r# r$ �reset2 s zMessDetectorPlugin.resetc C s t �dS )z� Compute the chaos ratio based on what your feed() has seen. Must NOT be lower than 0.; No restriction gt 0. Nr r( r# r# r$ �ratio8 s zMessDetectorPlugin.ratio) �__name__� __module__� __qualname__�__doc__�str�boolr% r& r) �property�floatr* r# r# r# r$ r s r c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )� TooManySymbolOrPunctuationPluginNr' c C s" d| _ d| _d| _d | _d| _d S )Nr F)�_punctuation_count� _symbol_count�_character_count�_last_printable_charZ_frenzy_symbol_in_wordr( r# r# r$ �__init__B s z)TooManySymbolOrPunctuationPlugin.__init__r c C s |� � S �N�� isprintabler! r# r# r$ r% J s z)TooManySymbolOrPunctuationPlugin.eligiblec C sp | j d7 _ || jkrf|tvrft|�r8| jd7 _n.|�� du rft|�rft|�du rf| jd7 _|| _d S )Nr F� ) r6 r7 r r r4 �isdigitr r r5 r! r# r# r$ r& M s �� �� �z%TooManySymbolOrPunctuationPlugin.feedc C s d| _ d| _d| _d S �Nr )r4 r6 r5 r( r# r# r$ r) _ s z&TooManySymbolOrPunctuationPlugin.resetc C s0 | j dkrdS | j| j | j }|dkr,|S dS )Nr � �333333�?)r6 r4 r5 )r" Zratio_of_punctuationr# r# r$ r* d s �z&TooManySymbolOrPunctuationPlugin.ratio� r+ r, r- r8 r/ r0 r% r& r) r1 r2 r* r# r# r# r$ r3 A s r3 c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )�TooManyAccentuatedPluginNr' c C s d| _ d| _d S r> �r6 �_accentuated_countr( r# r# r$ r8 q s z!TooManyAccentuatedPlugin.__init__r c C s |� � S r9 )�isalphar! r# r# r$ r% u s z!TooManyAccentuatedPlugin.eligiblec C s( | j d7 _ t|�r$| jd7 _d S �Nr )r6 r rD r! r# r# r$ r& x s z TooManyAccentuatedPlugin.feedc C s d| _ d| _d S r> rC r( r# r# r$ r) ~ s z TooManyAccentuatedPlugin.resetc C s* | j dk rdS | j| j }|dkr&|S dS )N� r? gffffff�?rC )r" Zratio_of_accentuationr# r# r$ r* � s z TooManyAccentuatedPlugin.ratiorA r# r# r# r$ rB p s rB c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )�UnprintablePluginNr' c C s d| _ d| _d S r> )�_unprintable_countr6 r( r# r# r$ r8 � s zUnprintablePlugin.__init__r c C s dS �NTr# r! r# r# r$ r% � s zUnprintablePlugin.eligiblec C s( t |�r| jd7 _| jd7 _d S rF )r rI r6 r! r# r# r$ r& � s zUnprintablePlugin.feedc C s d| _ d S r> )rI r( r# r# r$ r) � s zUnprintablePlugin.resetc C s | j dkrdS | jd | j S )Nr r? rG )r6 rI r( r# r# r$ r* � s zUnprintablePlugin.ratiorA r# r# r# r$ rH � s rH c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )� SuspiciousDuplicateAccentPluginNr' c C s d| _ d| _d | _d S r> ��_successive_countr6 �_last_latin_characterr( r# r# r$ r8 � s z(SuspiciousDuplicateAccentPlugin.__init__r c C s |� � ot|�S r9 )rE r r! r# r# r$ r% � s z(SuspiciousDuplicateAccentPlugin.eligiblec C st | j d7 _ | jd urjt|�rjt| j�rj|�� rJ| j�� rJ| jd7 _t|�t| j�krj| jd7 _|| _d S rF )r6 rN r �isupperrM r r! r# r# r$ r& � s ���z$SuspiciousDuplicateAccentPlugin.feedc C s d| _ d| _d | _d S r> rL r( r# r# r$ r) � s z%SuspiciousDuplicateAccentPlugin.resetc C s | j dkrdS | jd | j S )Nr r? r< )r6 rM r( r# r# r$ r* � s z%SuspiciousDuplicateAccentPlugin.ratiorA r# r# r# r$ rK � s rK c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )�SuspiciousRangeNr' c C s d| _ d| _d | _d S r> )�"_suspicious_successive_range_countr6 �_last_printable_seenr( r# r# r$ r8 � s zSuspiciousRange.__init__r c C s |� � S r9 r: r! r# r# r$ r% � s zSuspiciousRange.eligiblec C sx | j d7 _ |�� s&t|�s&|tv r0d | _d S | jd u rD|| _d S t| j�}t|�}t||�rn| jd7 _|| _d S rF )r6 �isspacer r rR r � is_suspiciously_successive_rangerQ )r" r �unicode_range_a�unicode_range_br# r# r$ r& � s" ��� zSuspiciousRange.feedc C s d| _ d| _d | _d S r> )r6 rQ rR r( r# r# r$ r) � s zSuspiciousRange.resetc C s" | j dkrdS | jd | j }|S )N� r? r< )r6 rQ )r" Z ratio_of_suspicious_range_usager# r# r$ r* � s �zSuspiciousRange.ratiorA r# r# r# r$ rP � s rP c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )�SuperWeirdWordPluginNr' c C s@ d| _ d| _d| _d| _d| _d| _d| _d| _d| _d| _ d S )Nr F� ) � _word_count�_bad_word_count�_foreign_long_count�_is_current_word_bad�_foreign_long_watchr6 �_bad_character_count�_buffer�_buffer_accent_count�_buffer_glyph_countr( r# r# r$ r8 � s z SuperWeirdWordPlugin.__init__r c C s dS rJ r# r! r# r# r$ r% s z SuperWeirdWordPlugin.eligiblec C s� |� � r�| j|7 _t|�r,| jd7 _| jdu r�t|�du sJt|�r�t|�du r�t|�du r�t|�du r�t |�du r�t |�du r�d| _t|�s�t|�s�t|�s�t |�s�t |�r�| j d7 _ d S | js�d S |� � s�t |�s�t|��r\| j�r\| jd7 _t| j�}| j|7 _|dk�r�| j| dk�r:d| _npt| jd ��r�| jd �� �r�tdd� | jD ��du �r�| jd7 _d| _n | j dk�r�d| _| jd7 _|d k�r| j�rd d � t| jtd |��D �}d}|�r�t|�| d k�r�d}|�s| jd7 _d| _| j�rB| jd7 _| jt| j�7 _d| _d| _d| _d | _d | _ n6|dv�r�|�� du �r�t|��r�d| _| j|7 _d S )Nr FT� g �?���c s s | ]}|� � V qd S r9 �rO )�.0�_r# r# r$ � <genexpr>6 � z,SuperWeirdWordPlugin.feed.<locals>.<genexpr>� c S s g | ]\}}|� � r|�qS r# re )rf �c�ir# r# r$ � <listcomp>> s �z-SuperWeirdWordPlugin.feed.<locals>.<listcomp>r r@ rY > rg �-�|�<�>�=�~) rE r` r ra r^ r r r r r r rb rS r r rZ �lenr6 r] rO �allr\ �zip�ranger[ r_ r= r )r" r � buffer_lengthZcamel_case_dstZprobable_camel_casedr# r# r$ r& s� � �� � � � � � ��������� � �� �� ��zSuperWeirdWordPlugin.feedc C s4 d| _ d| _d| _d| _d| _d| _d| _d| _d S )NrY Fr )r` r] r^ r[ rZ r6 r_ r\ r( r# r# r$ r) ] s zSuperWeirdWordPlugin.resetc C s$ | j dkr| jdkrdS | j| j S )N� r r? )rZ r\ r_ r6 r( r# r# r$ r* g s zSuperWeirdWordPlugin.ratiorA r# r# r# r$ rX � s Q rX c @ s^ e Zd ZdZdd�dd�Zeed�dd�Zedd�d d �Zdd�d d �Z e e d�d d��Z dS )�CjkInvalidStopPluginu� GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and can be easily detected. Searching for the overuse of '丅' and '丄'. Nr' c C s d| _ d| _d S r> ��_wrong_stop_count�_cjk_character_countr( r# r# r$ r8 u s z CjkInvalidStopPlugin.__init__r c C s dS rJ r# r! r# r# r$ r% y s z CjkInvalidStopPlugin.eligiblec C s4 |dv r| j d7 _ d S t|�r0| jd7 _d S )N> u 丄u 丅r )r| r r} r! r# r# r$ r& | s zCjkInvalidStopPlugin.feedc C s d| _ d| _d S r> r{ r( r# r# r$ r) � s zCjkInvalidStopPlugin.resetc C s | j dk rdS | j| j S )N� r? )r} r| r( r# r# r$ r* � s zCjkInvalidStopPlugin.ratio) r+ r, r- r. r8 r/ r0 r% r& r) r1 r2 r* r# r# r# r$ rz o s rz c @ sZ e Zd Zdd�dd�Zeed�dd�Zedd�dd �Zdd�d d �Ze e d�d d ��Z dS )�ArchaicUpperLowerPluginNr' c C s. d| _ d| _d| _d| _d| _d | _d| _d S )NFr T)�_buf� _character_count_since_last_sep� _successive_upper_lower_count�#_successive_upper_lower_count_finalr6 �_last_alpha_seen�_current_ascii_onlyr( r# r# r$ r8 � s z ArchaicUpperLowerPlugin.__init__r c C s dS rJ r# r! r# r# r$ r% � s z ArchaicUpperLowerPlugin.eligiblec C s$ |� � ot|�}|du }|r�| jdkr�| jdkrV|�� du rV| jdu rV| j| j7 _d| _d| _d | _d| _| j d7 _ d| _d S | jdu r�|� � du r�d| _| jd ur�|� � r�| j� � s�|� � r�| j� � r�| jdu r�| jd7 _d| _q�d| _nd| _| j d7 _ | jd7 _|| _d S )NFr �@ r Tr< ) rE r r� r= r� r� r� r� r� r6 �isasciirO �islower)r" r Z is_concernedZ chunk_sepr# r# r$ r& � sF � ��� �� z ArchaicUpperLowerPlugin.feedc C s. d| _ d| _d| _d| _d | _d| _d| _d S )Nr FT)r6 r� r� r� r� r� r� r( r# r# r$ r) � s z ArchaicUpperLowerPlugin.resetc C s | j dkrdS | j| j S )Nr r? )r6 r� r( r# r# r$ r* � s z ArchaicUpperLowerPlugin.ratiorA r# r# r# r$ r � s * r c @ sZ e Zd Zdd�dd�Zdd�dd�Zeed�dd �Zedd�d d �Ze e d�d d ��Z dS )�ArabicIsolatedFormPluginNr' c C s d| _ d| _d S r> �r6 �_isolated_form_countr( r# r# r$ r8 � s z!ArabicIsolatedFormPlugin.__init__c C s d| _ d| _d S r> r� r( r# r# r$ r) � s z ArabicIsolatedFormPlugin.resetr c C s t |�S r9 )r r! r# r# r$ r% � s z!ArabicIsolatedFormPlugin.eligiblec C s( | j d7 _ t|�r$| jd7 _d S rF )r6 r r� r! r# r# r$ r& � s z ArabicIsolatedFormPlugin.feedc C s | j dk rdS | j| j }|S )NrG r? r� )r" Zisolated_form_usager# r# r$ r* � s z ArabicIsolatedFormPlugin.ratio) r+ r, r- r8 r) r/ r0 r% r& r1 r2 r* r# r# r# r$ r� � s r� � )�maxsize)rU rV r c C s� | du s|du rdS | |kr dS d| v r4d|v r4dS d| v sDd|v rHdS d| v sXd|v rld| v shd|v rldS | � d�|� d� }}|D ] }|tv r�q�||v r� dS q�| dv |dv }}|s�|r�d | v s�d |v r�dS |r�|r�dS d | v s�d |v �r d | v �sd |v �rdS | d k�s |d k�r dS d | v �sHd |v �sH| d v �r�|d v �r�d | v �s\d |v �r`dS d| v �std|v �rxdS | d k�s�|d k�r�dS dS )za Determine if two Unicode range seen next to each other can be considered as suspicious. NTF�LatinZ EmoticonsZ Combining� )�Hiragana�Katakana�CJK�Hangulz Basic Latin)r� r� � Punctuation�Forms)�splitr )rU rV Zkeywords_range_aZkeywords_range_b�elZrange_a_jp_charsZrange_b_jp_charsr# r# r$ rT � sl ����������rT i 皙�����?F)�decoded_sequence�maximum_threshold�debugr c C sX dd� t �� D �}t| �d }d}|dk r0d}n|dkr>d}nd }t| d t|��D ]d\}}|D ]} | �|�r`| �|� q`|d kr�|| d ks�||d krTtd d � |D ��}||krT q�qT|�rNtd�} | � t d|� d|� d|� �� t| �dk�r(| � t d| dd� � �� | � t d| dd� � �� |D ] } | � t | j � d| j � �� �q,t |d�S )zw Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier. c S s g | ] }|� �qS r# r# )rf Zmd_classr# r# r$ rm G s z mess_ratio.<locals>.<listcomp>r r? i � r� r� � � r c s s | ] }|j V qd S r9 )r* )rf �dtr# r# r$ rh ^ ri z mess_ratio.<locals>.<genexpr>�charset_normalizerzIMess-detector extended-analysis start. intermediary_mean_mess_ratio_calc=z mean_mess_ratio=z maximum_threshold=r~ zStarting with: Nz Ending with: i�z: � )r �__subclasses__rt rv rw r% r& �sumr �logr � __class__r* �round) r� r� r� Z detectors�length�mean_mess_ratioZ!intermediary_mean_mess_ratio_calcr �index�detector�loggerr� r# r# r$ � mess_ratio? sR � � � ����� r� N)r� F),� functoolsr �loggingr �typingr r �constantr r r �utilsr r r r r r r r r r r r r r r r r r r3 rB rH rK rP rX rz r r� r/ r0 rT r2 r� r# r# r# r$ �<module> s0 L"/%1v L �H ��PK -�ZvُУ% �% __pycache__/cd.cpython-39.pycnu �[��� a g1 � @ s� d dl Z d dlmZ d dlmZ d dlmZ d dlmZm Z m Z m Z m Z ddl mZmZmZmZmZ ddlmZ dd lmZ dd lmZmZmZmZm Z e e e d �d d �Z e e e d�dd�Z e� e e e d �dd��Z e� e e e d �dd��Z!eed�e e e"e"f d�dd��Z#d-e e e"e e d�dd �Z$e e e e%d �d d �Z&e e e d �d!d"�Z'e e ed#�d$d%�Z(eed#�d&d'�Z)ed(d�d.e e%e e ed*�d+d,��Z*dS )/� N)�IncrementalDecoder)�Counter)� lru_cache)r �Dict�List�Optional�Tuple� )� FREQUENCIES�KO_NAMES�LANGUAGE_SUPPORTED_COUNT�TOO_SMALL_SEQUENCE�ZH_NAMES)� is_suspiciously_successive_range)�CoherenceMatches)�is_accentuated�is_latin�is_multi_byte_encoding�is_unicode_range_secondary� unicode_range)� iana_name�returnc s� t | �rtd��t�d�| ��j}|dd�}i �d� tdd�D ]^}|�t|g��}|r>t |�}|du rhq>t |�d u r>|�vr�d�|< �| d 7 < � d 7 � q>t � �fd d ��D ��S ) zF Return associated unicode ranges in a single byte code page. z.Function not supported on multi-byte code pagez encodings.{}�ignore)�errorsr �@ � NFr c s g | ]}�| � d kr|�qS )g333333�?� )�.0�character_range��character_countZ seen_rangesr �C/opt/gsutil/third_party/charset_normalizer/charset_normalizer/cd.py� <listcomp>8 s �z*encoding_unicode_range.<locals>.<listcomp>) r �IOError� importlib� import_module�formatr �range�decode�bytesr r �sorted)r �decoder�p�i�chunkr r r r! �encoding_unicode_range s0 � ��r/ )� primary_ranger c C s> g }t �� D ],\}}|D ] }t|�| kr|�|� q qq |S )z> Return inferred languages used with a unicode range. )r �itemsr �append)r0 � languages�language� characters� characterr r r! �unicode_range_languages@ s r7 c C s< t | �}d}|D ]}d|vr|} q&q|du r4dgS t|�S )z� Single-byte encoding language association. Some code page are heavily linked to particular language(s). This function does the correspondence. NZLatin� Latin Based)r/ r7 )r Zunicode_rangesr0 Zspecified_ranger r r! �encoding_languagesO s r9 c C s` | � d�s&| � d�s&| � d�s&| dkr,dgS | � d�s>| tv rDdgS | � d�sV| tv r\d gS g S ) z� Multi-byte encoding language association. Some code page are heavily linked to particular language(s). This function does the correspondence. Zshift_� iso2022_jpZeuc_j�cp932�JapaneseZgb�Chinese� iso2022_kr�Korean)� startswithr r )r r r r! �mb_encoding_languagesc s ����rA )�maxsize)r4 r c C sB d}d}t | D ](}|s$t|�r$d}|rt|�du rd}q||fS )zg Determine main aspects from a supported language if it contains accents and if is pure Latin. FT)r r r )r4 �target_have_accents�target_pure_latinr6 r r r! �get_target_featuresx s rE F)r5 �ignore_non_latinr c s� g }t dd� � D ��}t�� D ]l\}}t|�\}}|r@|du r@q |du rN|rNq t|�}t� fdd�|D ��} | | } | dkr |�|| f� q t|dd� d d �}d d� |D �S ) zE Return associated languages associated to given characters. c s s | ]}t |�V qd S �N)r )r r6 r r r! � <genexpr>� � z%alphabet_languages.<locals>.<genexpr>Fc s g | ]}|� v r|�qS r r )r �c�r5 r r! r" � rI z&alphabet_languages.<locals>.<listcomp>g�������?c S s | d S �Nr r ��xr r r! �<lambda>� rI z$alphabet_languages.<locals>.<lambda>T��key�reversec S s g | ] }|d �qS )r r )r Zcompatible_languager r r! r" � rI )�anyr r1 rE �lenr2 r* ) r5 rF r3 Zsource_have_accentsr4 Zlanguage_charactersrC rD r Zcharacter_match_count�ratior rK r! �alphabet_languages� s" �rV )r4 �ordered_charactersr c C s� | t vrtd�| ���d}tt | �}t|�}tt | �}|dk}t|td|��D �]D\}}||vrfqRt | �|�} || } t|| �} |du r�t | | �dkr�qR|du r�t | | �|d k r�|d7 }qRt | d| � } t | | d � } |d|� }||d � }tt|�t| �@ �}tt|�t| �@ �}t| �dk�rJ|dk�rJ|d7 }qRt| �dk�rl|dk�rl|d7 }qR|t| � d k�s�|t| � d krR|d7 }qRqR|t|� S ) aN Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language. The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit). Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.) z{} not availabler � F� T� r Ng�������?) r � ValueErrorr& �setrT �zipr' �index�int�abs)r4 rW Zcharacter_approved_countZFREQUENCIES_language_setZordered_characters_countZ target_language_characters_countZlarge_alphabetr6 Zcharacter_rankZcharacter_rank_in_languageZexpected_projection_ratioZcharacter_rank_projectionZcharacters_before_sourceZcharacters_after_sourceZcharacters_beforeZcharacters_afterZbefore_match_countZafter_match_countr r r! � characters_popularity_compare� sp �� ��� ���� ����ra )�decoded_sequencer c C s� i }| D ]~}|� � du rqt|�}|du r,qd}|D ]}t||�du r4|} qPq4|du r\|}||vrr|�� ||< q|| |�� 7 < qt|�� �S )a Given a decoded text sequence, return a list of str. Unicode range / alphabet separation. Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list; One containing the latin letters and the other hebrew. FN)�isalphar r �lower�list�values)rb Zlayersr6 r Zlayer_target_rangeZdiscovered_ranger r r! �alpha_unicode_split� s, �� rg )�resultsr c sf i � | D ]8}|D ].}|\}}|� vr0|g� |< q� | � |� qq� fdd�� D �}t|dd� dd�S )z� This function merge results previously given by the function coherence_ratio. The return type is the same as coherence_ratio. c s. g | ]&}|t t� | �t� | � d �f�qS )rY )�round�sumrT )r r4 �Zper_language_ratiosr r! r" 1 s ���z*merge_coherence_ratios.<locals>.<listcomp>c S s | d S rL r rM r r r! rO < rI z(merge_coherence_ratios.<locals>.<lambda>TrP )r2 r* )rh �resultZ sub_resultr4 rU �merger rk r! �merge_coherence_ratios# s � rn c s� t � � | D ]6}|\}}|�dd�}|� vr2g � |< � | �|� q t� fdd�� D ��r�g }� D ]}|�|t� | �f� q`|S | S )u� We shall NOT return "English—" in CoherenceMatches because it is an alternative of "English". This function only keeps the best match and remove the em-dash in it. u —� c 3 s | ]}t � | �d kV qdS )r N)rT )r �e�Z index_resultsr r! rH O rI z/filter_alt_coherence_matches.<locals>.<genexpr>)�dict�replacer2 rS �max)rh rl r4 rU Z no_em_nameZfiltered_resultsr rq r! � filter_alt_coherence_matches? s ru i 皙�����?)rb � threshold� lg_inclusionr c C s� g }d}d}|dur |� d�ng }d|v r8d}|�d� t| �D ]�}t|�}|�� } tdd� | D ��} | tkrpq@d d � | D �} |p�t| |�D ]J} t| | �} | |k r�q�n| d kr�|d 7 }|� | t | d �f� |dkr� q@q�q@t t |�dd� dd�S )z� Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers. A layer = Character extraction by alphabets/ranges. Fr N�,r8 Tc s s | ]\}}|V qd S rG r �r rJ �or r r! rH q rI z"coherence_ratio.<locals>.<genexpr>c S s g | ] \}}|�qS r r rz r r r! r" v rI z#coherence_ratio.<locals>.<listcomp>g�������?r rY rZ c S s | d S rL r rM r r r! rO � rI z!coherence_ratio.<locals>.<lambda>rP ) �split�removerg r � most_commonrj r rV ra r2 ri r* ru )rb rw rx rh rF Zsufficient_match_countZlg_inclusion_listZlayerZsequence_frequenciesr~ r Zpopular_character_orderedr4 rU r r r! �coherence_ratioZ s< ���r )F)rv N)+r$ �codecsr � collectionsr � functoolsr �typingZ TypeCounterr r r r �constantr r r r r �mdr �modelsr �utilsr r r r r �strr/ r7 r9 rA �boolrE rV �floatra rg rn ru r r r r r! �<module> sB ' �� $� P' � �PK -�Z!�b �b # __pycache__/constant.cpython-39.pycnu �[��� a g3� � J @ s� U d dl mZmZmZmZmZ d dlmZ d dlm Z m Z d dl m Z mZmZmZ eg d�deegeegd�Ze eeeee f f ed< d Zeed < ed �Zeed < d Zeed< ed �ed d�edd�edd�edd�edd�edd�edd�edd�edd�edd�edd�edd�edd�edd �ed d �ed d �ed d �ed d �ed d!�ed!d"�ed"d#�ed#d$�ed$d%�ed%d&�ed&d'�ed'd(�ed(d)�ed)d*�ed*d+�ed+d,�ed,d-�ed-d.�ed.d/�ed/d0�ed0d1�ed1d2�ed2d3�ed3d4�ed4d5�ed5d6�ed6d7�ed7d8�ed8d9�ed9d:�ed:d;�ed;d<�ed<d=�ed=d>�ed>d?�ed?d@�ed@dA�edAdB�edBdC�edCdD�edDdE�edEdF�edFdG�edGdH�edHdI�edIdJ�edJdK�edKdL�edLdM�edMdN�edNdO�edOdP�edPdQ�edQdR�edRdS�edSdT�edTdU�edUdV�edVdW�edWdX�edXdY�edYdZ�edZd[�ed[d\�ed\d]�ed]d^�ed^d_�ed_d`�ed`da�edadb�edbdc�edcdd�eddde�ededf�edfdg�edgdh�edhdi�edidj�edjdk�edkdl�edldm�edmdn�edndo�edodp�edpdq�edqdr�edrds�edsdt�edtdu�edudv�edvdw�edwdx�edydz�edzd{�ed{d|�ed|d}�ed}d~�ed~d�edd��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�ded�dăed�dŃed�dƃed�dǃed�dȃed�dɃed�dʃed�d̃ed�d̓ed�dσed�dЃed�dуed�d҃ed�dԃed�dՃed�dփed�ded�dكed�dڃed�dۃed�d܃ed�dރed�d߃ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d�ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��ed�d��e�d �d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d �d �e�d �d �e�d �d �e�d �d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d�d�e�d �d �e�d �d �e�d �d �e�d �d �e�d �d!�e�d"�d#�e�d#�d$�e�d$�d%�e�d&�d'�e�d(�d)�e�d)�d*�e�d*�d+�e�d+�d,�e�d,�d-�e�d.�d/�e�d0�d1�e�d2�d3�e�d3�d4�e�d4�d5�e�d5�d6�e�d6�d7�e�d8�d9�e�d9�d:�e�d:�d;�e�d;�d<�e�d<�d=�e�d>�d?�e�d?�d@�e�dA�dB�e�dC�dD�e�dD�dE�e�dE�dF�e�dG�dH�e�dH�dI�e�dI�dJ�e�dJ�dK�e�dL�dM�e�dM�dN�e�dO�dP�e�dP�dQ�e�dQ�dR�e�dS�dT�e�dU�dV�e�dV�dW�e�dX�dY�e�dZ�d[�e�d[�d\�e�d]�d^�e�d_�d`�e�da�db�e�dc�dd�e�de�df�e�df�dg�e�dg�dh�e�dh�di�e�di�dj�e�dj�dk�e�dk�dl�e�dl�dm�e�dm�dn�e�dn�do�e�do�dp�e�dp�dq�e�dq�dr�e�dr�ds�e�ds�dt�e�dt�du�e�dv�dw�e�dx�dy�e�dy�dz�e�dz�d{�e�d{�d|�e�d}�d~�e�d�d��e�d��d��e�d��d��e�d��d��e�d��d��e�d��d���d���HZe eef e�d�< g �d��Zee e�d�< e �d�e �Z g �d��Z e e �d��d�� e e!e�"� ��e ��Z#ee e�d�< e$e#�Z%ee�d�< g �d��g �d���d�gg �d���d�g�d��d�gg �d���d�gg �d���d�gg �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d���d�gg �d���d�g�d�gg �d��g �d��g �d��g �d��g �d��g �d���d�gg �d���d��d�gg �d���d��d�g�d��d�g�d��d�g�d��d�g�d�g�d��(Z&e eee f e�d�< �d��d��d��d��d��d��ddÐdĐdŐdƐdǐdȐdɐdʐdːd̐d͐dΐdϐdАdѐdҐdӐdԐdՐddאdؐdِdڐdېdܜ Z'e eef e�d�< h �dޣZ(ee e�d�< h �d�Z)ee e�d�< h �d�Z*ee e�d�< �d�Z+ee�d�< g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d��g �d �g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d�g �d �g �d �g �d �g �d �g �d �g �d��d�)Z,e eee f e�d< e$e,�Z-ee�d< �dS ( � )�BOM_UTF8� BOM_UTF16_BE� BOM_UTF16_LE� BOM_UTF32_BE� BOM_UTF32_LE)�aliases)� IGNORECASE�compile)�Dict�List�Set�Union)s +/v8s +/v9s +/v+s +/v/s +/v8-s �1�3)�utf_8�utf_7�gb18030�utf_32�utf_16�ENCODING_MARKS� �TOO_SMALL_SEQUENCEg �cA�TOO_BIG_SEQUENCEi � �UTF8_MAXIMAL_ALLOCATION� � i� iP i� i ip i i i0 i� i i iP i� i� i i@ i` ip i� i i� i i� i i� i i� i i� i i� i i i� i i i� i� i i� i� i i i@ i` i� i i� i iP i� i� i i i� i i� i� i iP i� i� i� i� i i� i� i i i ip i� i� i ! iP! i�! i " i # i $ i@$ i`$ i % i�% i�% i & i ' i�' i�' i ( i ) i�) i * i + i , i`, i�, i - i0- i�- i�- i . i�. i / i�/ i�/ i 0 i@0 i�0 i 1 i01 i�1 i�1 i�1 i�1 i 2 i 3 i 4 i�M i N i � i�� iФ i � i@� i�� i � i � i � i0� i@� i�� i� i � i0� i`� i�� i� i � i`� i�� i� i � i0� ip� i�� i � i�� i � i�� i � i � i � i � iP� i � i� i � i0� iP� ip� i � i� i i� i i@ i� i� i i� i� i� i i0 iP i� i� i� i iP i� i� i i0 ip i� i i� i� i i@ i` i� i� i� i i i@ i� i� i i` i� i� i� i i@ i` i� i� i iP i� i i@ i` i� i� i i0 ip i� i� i i� i� i iP i� i� i iP i� i� i i� i i� i� i� i i` i� i� i iP i iP i� i i` i� i iP i� i� i i` i ip i� i i` i� i� i i` i� i� i i $ i�$ iP% i�/ i 0 i04 i`4 i D i�F i h i@j ipj i�j i k i�k i@n i�n i o i�o i�o i p i � i � i � i�� i� i � i � i0� ip� i � i � i�� i�� i � i�� i � i � i � iP� i�� i�� i � i`� i�� i � i � i�� i � i � i0� i�� i � iP� i�� i�� i � i�� i � i�� i � i�� i � i`� ip� i�� i � iP� i � i � i � i0� i�� i � i � i � i � iP� i�� i � i�� i � i � i � ip� i � i � i i� i � i@� i � i�� i�� i � i � i iP i�# i i� i i� i i i (H zControl characterz Basic LatinzLatin-1 SupplementzLatin Extended-AzLatin Extended-BzIPA ExtensionszSpacing Modifier LetterszCombining Diacritical MarkszGreek and Coptic�CyrilliczCyrillic SupplementZArmenian�Hebrew�ArabicZSyriaczArabic SupplementZThaanaZNKoZ SamaritanZMandaiczSyriac SupplementzArabic Extended-BzArabic Extended-A� DevanagariZBengaliZGurmukhiZGujaratiZOriya�TamilZTeluguZKannadaZ MalayalamZSinhala�ThaiZLaoZTibetanZMyanmarZGeorgianz Hangul JamoZEthiopiczEthiopic SupplementZCherokeez%Unified Canadian Aboriginal SyllabicsZOghamZRunicZTagalogZHanunooZBuhidZTagbanwaZKhmerZ Mongolianz.Unified Canadian Aboriginal Syllabics ExtendedZLimbuzTai Lez New Tai Luez Khmer SymbolsZBuginesezTai Thamz$Combining Diacritical Marks ExtendedZBalineseZ SundaneseZBatakZLepchazOl ChikizCyrillic Extended-CzGeorgian ExtendedzSundanese SupplementzVedic ExtensionszPhonetic Extensionsz Phonetic Extensions Supplementz&Combining Diacritical Marks SupplementzLatin Extended AdditionalzGreek ExtendedzGeneral PunctuationzSuperscripts and SubscriptszCurrency Symbolsz'Combining Diacritical Marks for SymbolszLetterlike Symbolsz Number FormsZArrowszMathematical OperatorszMiscellaneous TechnicalzControl Picturesz Optical Character RecognitionzEnclosed Alphanumericsz Box DrawingzBlock ElementszGeometric ShapeszMiscellaneous SymbolsZDingbatsz$Miscellaneous Mathematical Symbols-AzSupplemental Arrows-AzBraille PatternszSupplemental Arrows-Bz$Miscellaneous Mathematical Symbols-Bz#Supplemental Mathematical Operatorsz Miscellaneous Symbols and ArrowsZ GlagoliticzLatin Extended-CZCopticzGeorgian SupplementZTifinaghzEthiopic ExtendedzCyrillic Extended-AzSupplemental PunctuationzCJK Radicals SupplementzKangxi Radicalsz"Ideographic Description CharacterszCJK Symbols and Punctuation�Hiragana�KatakanaZBopomofozHangul Compatibility JamoZKanbunzBopomofo Extendedz CJK Strokesz Katakana Phonetic Extensionsz Enclosed CJK Letters and MonthszCJK Compatibilityz"CJK Unified Ideographs Extension AzYijing Hexagram SymbolszCJK Unified Ideographsz Yi Syllablesz Yi RadicalsZLisuZVaizCyrillic Extended-BZBamumzModifier Tone LetterszLatin Extended-Dz Syloti NagrizCommon Indic Number FormszPhags-paZ SaurashtrazDevanagari ExtendedzKayah LiZRejangzHangul Jamo Extended-AZJavanesezMyanmar Extended-BZChamzMyanmar Extended-AzTai VietzMeetei Mayek ExtensionszEthiopic Extended-AzLatin Extended-EzCherokee Supplementz Meetei MayekzHangul SyllableszHangul Jamo Extended-BzHigh SurrogateszHigh Private Use SurrogateszLow SurrogateszPrivate Use Areaz CJK Compatibility Ideographsz Alphabetic Presentation FormszArabic Presentation Forms-AzVariation SelectorszVertical FormszCombining Half MarkszCJK Compatibility FormszSmall Form VariantszArabic Presentation Forms-Bz Halfwidth and Fullwidth FormsZSpecialszLinear B SyllabaryzLinear B IdeogramszAegean NumberszAncient Greek NumberszAncient Symbolsz Phaistos DiscZLycianZCarianzCoptic Epact Numbersz Old ItalicZGothicz Old PermicZUgariticz Old PersianZDeseretZShavianZOsmanyaZOsageZElbasanzCaucasian AlbanianZVithkuqizLinear AzLatin Extended-FzCypriot SyllabaryzImperial AramaicZ PalmyreneZ NabataeanZHatranZ PhoenicianZLydianzMeroitic HieroglyphszMeroitic CursiveZ KharoshthizOld South ArabianzOld North ArabianZ ManichaeanZAvestanzInscriptional ParthianzInscriptional PahlavizPsalter Pahlaviz Old Turkicz Old HungarianzHanifi RohingyazRumi Numeral SymbolsZYezidizArabic Extended-Cz Old SogdianZSogdianz Old UyghurZ ChorasmianZElymaicZBrahmiZKaithiz Sora SompengZChakmaZMahajaniZSharadazSinhala Archaic NumbersZKhojkiZMultaniZ KhudawadiZGranthaZNewaZTirhutaZSiddhamZModizMongolian SupplementZTakriZAhomZDograz Warang Citiz Dives AkuruZ NandinagarizZanabazar SquareZSoyomboz0Unified Canadian Aboriginal Syllabics Extended-Az Pau Cin HauzDevanagari Extended-AZ BhaiksukiZMarchenz Masaram Gondiz Gunjala GondiZMakasarZKawizLisu SupplementzTamil SupplementZ Cuneiformz!Cuneiform Numbers and PunctuationzEarly Dynastic Cuneiformz Cypro-MinoanzEgyptian Hieroglyphsz#Egyptian Hieroglyph Format ControlszAnatolian HieroglyphszBamum SupplementZMroZTangsaz Bassa Vahz Pahawh HmongZ MedefaidrinZMiaoz#Ideographic Symbols and PunctuationZTangutzTangut ComponentszKhitan Small ScriptzTangut SupplementzKana Extended-BzKana SupplementzKana Extended-AzSmall Kana ExtensionZNushuZDuployanzShorthand Format ControlszZnamenny Musical NotationzByzantine Musical SymbolszMusical Symbolsz Ancient Greek Musical NotationzKaktovik NumeralszMayan NumeralszTai Xuan Jing SymbolszCounting Rod Numeralsz!Mathematical Alphanumeric SymbolszSutton SignWritingzLatin Extended-GzGlagolitic SupplementzCyrillic Extended-DzNyiakeng Puachue HmongZTotoZWanchoz Nag MundarizEthiopic Extended-Bz Mende KikakuiZAdlamzIndic Siyaq NumberszOttoman Siyaq Numbersz&Arabic Mathematical Alphabetic Symbolsz Mahjong Tilesz Domino Tilesz Playing Cardsz Enclosed Alphanumeric Supplementz Enclosed Ideographic Supplementz%Miscellaneous Symbols and PictographszEmoticons range(Emoji)zOrnamental DingbatszTransport and Map SymbolszAlchemical SymbolszGeometric Shapes ExtendedzSupplemental Arrows-Cz$Supplemental Symbols and Pictographsz Chess Symbolsz"Symbols and Pictographs Extended-Az Symbols for Legacy Computingz"CJK Unified Ideographs Extension Bz"CJK Unified Ideographs Extension Cz"CJK Unified Ideographs Extension Dz"CJK Unified Ideographs Extension Ez"CJK Unified Ideographs Extension Fz'CJK Compatibility Ideographs Supplementz"CJK Unified Ideographs Extension Gz"CJK Unified Ideographs Extension H�Tagsz Variation Selectors Supplementz Supplementary Private Use Area-Az Supplementary Private Use Area-B�UNICODE_RANGES_COMBINED)Z SupplementZExtended� ExtensionsZModifierZMarksZ PunctuationZSymbolsZFormsZ OperatorsZ MiscellaneousZDrawingZBlockZShapesZ Supplementalr" � UNICODE_SECONDARY_RANGE_KEYWORDz^(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)) Zcp720Zcp737Zcp856Zcp874Zcp875Zcp1006�koi8_r�koi8_t�koi8_uc C s | � d�du o| dvS )NZ_codecF> �tactis�rot_13�mbcs)�endswith)�x� r. �I/opt/gsutil/third_party/charset_normalizer/charset_normalizer/constant.py�<lambda>� s r0 �IANA_SUPPORTED�IANA_SUPPORTED_COUNT)�cp1026�cp1140�cp273�cp500)�cp037r4 r5 r6 �cp866)r7 r3 r5 r6 � iso8859_2�kz1048�ptcp154)� iso8859_15� iso8859_9�latin_1� iso8859_7� iso8859_13)r7 r3 r4 r6 )�cp850�cp858�cp860�cp861�cp862�cp863�cp865)r7 r3 r4 r5 )�cp437�cp857rB rG )rA rB rG )rH rA rI rG )rH rD rE rF rG )rH rC rE rF rG )rH rC rD rF rG )rH rC rD rE rG )rH rA rI rB rC rD rE rF �cp1125)� iso8859_14r< � iso8859_4r= r> �tis_620�cp1257)� iso8859_10r< � iso8859_16� iso8859_3r= r> )�cp1252�cp1254rO rK rP rQ r= r> )rK r< r9 rQ r= r> )�cp1250rP rL )rK r< rP r= r> )rO r9 r= r> �cp1253) rR rS �cp1258rO rK r< rP rQ rL r> �cp1251) rR rS rV rO rK r< rP rQ rL r= � mac_roman� mac_turkish� mac_iceland� iso8859_11)(r7 r3 rJ r4 rT rW rR rU rS rN r5 rH r6 rA rI rB rC rD rE rF rG r8 rO r[ r@ rK r< rP r9 rQ rL r? r= r: r> rZ rX rY r; rM �IANA_SUPPORTED_SIMILARz ISO-2022-KRz ISO-2022-JPzEUC-KRzTIS-620zUTF-32zEUC-JPzKOI8-Rz ISO-8859-1z ISO-8859-2z ISO-8859-5z ISO-8859-6z ISO-8859-7z ISO-8859-8zUTF-16�IBM855� MacCyrillic�GB2312�GB18030�CP932�IBM866zutf-8z UTF-8-SIG� SHIFT_JIS�Big5z windows-1250z windows-1251z Windows-1252z windows-1253z windows-1255z windows-1256z Windows-1254�CP949) � iso2022_kr� iso2022_jp�euc_krrM r �euc_jpr& � iso8859_1r9 � iso8859_5� iso8859_6r? � iso8859_8r �cp855� mac_cyrillic�gb2312r �cp932r8 r Z utf_8_sig� shift_jis�big5rT rW rR rU �cp1255�cp1256rS �cp949�CHARDET_CORRESPONDENCE> �{�[�:�,�<�|�-�;�)�>�=�/�&�"�(�]�}� COMMON_SAFE_ASCII_CHARACTERS> �johabrv rh �KO_NAMES> � big5hkscs�cp950�hzrs �ZH_NAMES� �TRACE)�e�a�t�i�o�n�s�r�h�l�d�c�u�m�f�p�g�w�y�b�v�kr- �j�z�q)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r- r� r� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ü� ä� ör� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ér� r� r� r� r� r� � àr- � èr� r� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r- � ë)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ò)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� u łr� r� r� � ąu ę� ó)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ír� r� � á)� о� а� е� и� н� с� т� р� в� л� к� м� д� п� у� г� я� ы� з� б� й� ь� ч� х� ж� ц)d� 人� 一� 大u 亅u 丁u 丨u 竹u 笑u 口u 日u 今u 二u 彳� 行u 十u 土u 丶u 寸u 寺u 時u 乙u 丿u 乂u 气u 気u 冂u 巾u 亠u 市u 目u 儿u 見u 八� 小u 凵u 県u 月u 彐u 門u 間u 木u 東u 山� 出� 本� 中u 刀� 分u 耳u 又u 取u 最u 言u 田� 心u 思u 刂� 前u 京u 尹� 事� 生u 厶u 云� 会u 未� 来u 白u 冫u 楽u 灬u 馬u 尸u 尺u 駅u 明u 耂u 者� 了u 阝� 都u 高u 卜u 占u 厂u 广u 店� 子u 申u 奄u 亻u 俺� 上� 方u 冖� 学u 衣u 艮u 食� 自)`u ーu ンu スu ・u ルu トu リu イu アu ラu ッu クu ドu シu レu ジu タu フu ロu カu テu マu ィu グu バu ムu プu オu コu デu ニu ウu メu サu ビu ナu ブu ャu エu ュu チu キu ズu ダu パu ミu ェu ョu ハu セu ベu ガu モu ツu ネu ボu ソu ノu ァu ヴu ワu ポu ペu ピu ケu ゴu ギu ザu ホu ゲu ォu ヤu ヒu ユu ヨu ヘu ゼu ヌu ゥu ゾu ヶu ヂu ヲu ヅu ヵu ヱu ヰu ヮu ヽu ゠u ヾu ヷu ヿu ヸu ヹu ヺ)]u のu にu るu たu とu はu しu いu をu でu てu がu なu れu かu らu さu っu りu すu あu もu こu まu うu くu よu きu んu めu おu けu そu つu だu やu えu どu わu ちu みu せu じu ばu へu びu ずu ろu ほu げu むu べu ひu ょu ゆu ぶu ごu ゃu ねu ふu ぐu ぎu ぼu ゅu づu ざu ぞu ぬu ぜu ぱu ぽu ぷu ぴu ぃu ぁu ぇu ぺu ゞu ぢu ぉu ぅu ゐu ゝu ゑu ゛u ゜u ゎu ゔu ゚u ゟu ゙u ゕu ゖ)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ãr� r� � çr� r� r� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � år� r� r- )du 的r� u 是u 不r� u 在r� u 有u 我u 他u 这u 个u 们r� r� r� r� u 为u 和u 国u 地u 到u 以u 说u 时u 要u 就r� r� u 可u 也u 你u 对r� u 能u 而r� u 那u 得u 于u 着u 下r� u 之u 年u 过u 发u 后u 作u 里u 用u 道r� u 所u 然u 家u 种r� u 成r� u 多u 经u 么u 去u 法r� u 如r� u 同u 现u 当u 没u 动u 面u 起u 看u 定u 天r� u 还u 进u 好r� u 部u 其u 些u 主u 样u 理r� u 她r� r� u 开u 但u 因u 只u 从u 想u 实)r� r� r� � іr� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� u ї)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ør� � ær� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� )r� r� r� r� r� r� r� r� r� r� r� r� r� u đr� r� r� r� r� r� u ưr� r� r� u ộu ế)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� u ěr� u ř)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� )u 이u 다u 에u 의u 는u 로u 하u 을u 가u 고u 지u 서u 한u 은u 기u 으u 년u 대u 사u 시u 를u 리u 도u 인u 스u 일)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r- r� )r� r� r� r� r� r� u ır� r� r� r� r� r� r� r� r� r� u şr� r� r� r� r� r� r� u ğ)r� r� r� r� r� r� r� r� r� r� r� r� r� r� u ăr� r� � îr� r� u șu țr� r� � âr� )� اu ی� ر� د� ن� ه� و� م� ت� ب� س� لu ک� شu ز� فu گ� ع� خ� ق� جu آu پ� ح� ط� ص)r� r� u يr� r� r� r� r� r� u ةr� r� r� r� r� u كr� u أr r� r� r r u ىr� u إ)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� )r� r� r� r� r� r� r� r� r� r� u јr� r� r� r� r� r� r� r� r� r� r� r� r� r� � ш)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� u ėr� r� u ų� š� žr� r� u į)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � čr� r r r� r� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � ýr� r r� )u יu וu הu לu רu בu תu מu אu שu נu עu םu דu קu חu פu סu כu גu טu צu ןu זu ך)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� u ъr� r� r� r� r� r� u щr� )r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r r� r r u ćr� )u कu रu सu नu तu मu हu पu यu लu वu जu दu गu बu शu टu अu एu थu भu डu चu धu षu इ)r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� r� � õr� r� r� r� r� )u าu นu รu อu กu เu งu มu ยu ลu วu ดu ทu สu ตu ะu ปu บu คu หu แu จu พu ชu ขu ใ)u αu τu οu ιu εu νu ρu σu κu ηu πu ςu υu μu λu ίu όu άu γu έu δu ήu ωu χu θu ύ)u கu தu பu டu ரu மu லu னu வu றu யu ளu சu நu இu ணu அu ஆu ழu ஙu எu உu ஒu ஸ)r� r� r� r� r� r� r� r� r� r� r� u қr� r� r� r� r� u ғr� u ңr� r r� r� r� u ө))ZEnglishu English—ZGermanZFrenchZDutchZItalianZPolishZSpanish�Russian�Japaneseu Japanese—u Japanese——Z PortugueseZSwedish�ChineseZ UkrainianZ NorwegianZFinnishZ VietnameseZCzechZ Hungarian�KoreanZ Indonesian�TurkishZRomanianZFarsir ZDanishZSerbianZ LithuanianZSloveneZSlovakr � BulgarianZCroatianZHindiZEstonianr �Greekr ZKazakh� FREQUENCIES�LANGUAGE_SUPPORTED_COUNTN).�codecsr r r r r Zencodings.aliasesr �rer r � re_compile�typingr r r r r �str�bytes�__annotations__r �intr r �ranger# r% Z RE_POSSIBLE_ENCODING_INDICATIONZIANA_NO_ALIASES�sorted�filter�list�set�valuesr1 �lenr2 r\ rw r� r� r� r� r r r. r. r. r/ �<module> s� �" � � � N� �� � Z�$ gc_ f � � � � � � � � � � � 'PK -�Z���;W W ! __pycache__/legacy.cpython-39.pycnu �[��� a g � @ s~ d dl mZ d dlmZmZmZ d dlmZ ddlm Z ddl m Z erdd dl m Z G dd � d e �Zdd d d d d�dd�ZdS )� )� annotations)� TYPE_CHECKING�Any�Optional)�warn� )� from_bytes)�CHARDET_CORRESPONDENCE)� TypedDictc @ s& e Zd ZU ded< ded< ded< dS )� ResultDictz Optional[str]�encoding�str�languagezOptional[float]� confidenceN)�__name__� __module__� __qualname__�__annotations__� r r �G/opt/gsutil/third_party/charset_normalizer/charset_normalizer/legacy.pyr s r F�bytes�boolr )�byte_str�should_rename_legacy�kwargs�returnc K s� t |�r&tdd�t|�� ��� d�� t| ttf�sFtd� t | ����t| t�rXt| �} t | �� � }|durr|j nd}|dur�|jdkr�|jnd}|dur�d|j nd}|dur�|d kr�|jr�|d 7 }|d u r�|tv r�t| }|||d �S ) aJ chardet legacy method Detect the encoding of the given byte string. It should be mostly backward-compatible. Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it) This function is deprecated and should be used to migrate your project easily, consult the documentation for further information. Not planned for removal. :param byte_str: The byte sequence to examine. :param should_rename_legacy: Should we rename legacy encodings to their more modern equivalents? z(charset-normalizer disregard arguments '�,z ' in legacy function detect()z4Expected object of type bytes or bytearray, got: {0}N�Unknown� g �?�utf_8Z_sigF)r r r )�lenr �join�list�keys� isinstance� bytearrayr � TypeError�format�typer �bestr r �chaos�bomr )r r r �rr r r r r r �detect s0 ��� �r- N)F)� __future__r �typingr r r �warningsr �apir �constantr Ztyping_extensionsr r r- r r r r �<module> s �PK -�Z��Ō� � " __pycache__/version.cpython-39.pycnu �[��� a gO � @ s d Z dZe�d�ZdS )z Expose version z3.4.0�.N)�__doc__� __version__�split�VERSION� r r �H/opt/gsutil/third_party/charset_normalizer/charset_normalizer/version.py�<module> s PK -�Z����# �# __pycache__/utils.cpython-39.pycnu �[��� a gv. � @ sl d dl Z d dlZd dlZd dlmZ d dlmZ d dlmZ d dl m Z d dl m Z m Z mZmZmZmZ d dlmZ dd lmZmZmZmZmZmZ eed �ee d �d d ��Z eed �eed �dd��Z eed �eee d �dd��Z eed �ee d �dd��Z eed �ee d �dd��Z!eed �ee d �dd��Z"eed �ee d �dd��Z#eed �ee d �dd��Z$eed �ee d �d d ��Z%eed �ee d �d d ��Z&eed �ee d �d d!��Z'eed �ee d �d"d#��Z(eed �ee d �d$d%��Z)eed �ee d �d&d'��Z*eed �ee d �d(d)��Z+eed �ee d �d*d+��Z,ee-e�d �ee d,�d-d.��Z.eed �ee d �d/d0��Z/dSe0e1ee d2�d3d4�Z2ed5d �ee d6�d7d8��Z3e0eee e0f d9�d:d;�Z4ee d<�d=d>�Z5dTee ed@�dAdB�Z6ee e dC�dDdE�Z7eee8dF�dGdH�Z9eee dF�dIdJ�Z:dKej;dLfee1eddM�dNdO�Z<dUe0ee=e1e e e0e ee e eddf dP� dQdR�Z>dS )V� N)�IncrementalDecoder)�aliases)� lru_cache)�findall)� Generator�List�Optional�Set�Tuple�Union)�MultibyteIncrementalDecoder� )�ENCODING_MARKS�IANA_SUPPORTED_SIMILAR� RE_POSSIBLE_ENCODING_INDICATION�UNICODE_RANGES_COMBINED� UNICODE_SECONDARY_RANGE_KEYWORD�UTF8_MAXIMAL_ALLOCATION)�maxsize)� character�returnc C sd zt �| �}W n ty" Y dS 0 d|v pbd|v pbd|v pbd|v pbd|v pbd|v pbd|v pbd |v S ) NFz WITH GRAVEz WITH ACUTEz WITH CEDILLAzWITH DIAERESISzWITH CIRCUMFLEXz WITH TILDEz WITH MACRONzWITH RING ABOVE�� unicodedata�name� ValueError�r � description� r �F/opt/gsutil/third_party/charset_normalizer/charset_normalizer/utils.py�is_accentuated s& �������r c C s. t �| �}|s| S |�d�}tt|d d��S )N� r � )r � decomposition�split�chr�int)r Z decomposed�codesr r r � remove_accent( s r' c C s. t | �}t�� D ]\}}||v r| S qdS )zK Retrieve the Unicode range official name from a single character. N)�ordr �items)r Z character_ord� range_nameZ ord_ranger r r � unicode_range3 s r+ c C s, zt �| �}W n ty" Y dS 0 d|v S )NFZLATINr r r r r �is_latinA s r, c C s2 t �| �}d|v rdS t| �}|d u r*dS d|v S )N�PTF� Punctuation�r �categoryr+ �r �character_category�character_ranger r r �is_punctuationJ s r4 c C sB t �| �}d|v sd|v r dS t| �}|d u r2dS d|v o@|dkS )N�S�NTF�FormsZLor/ r1 r r r � is_symbolY s r8 c C s$ t | �}|d u rdS d|v p"d|v S )NF� EmoticonsZ Pictographs)r+ )r r3 r r r � is_emoticonh s r: c C s. | � � s| dv rdS t�| �}d|v p,|dv S )N> �<u ｜�>�+T�Z> ZPoZPdZPc)�isspacer r0 )r r2 r r r � is_separatorr s r@ c C s | � � | �� kS �N)�islower�isupper�r r r r �is_case_variable| s rE c C s, zt �| �}W n ty" Y dS 0 d|v S )NF�CJKr �r Zcharacter_namer r r �is_cjk� s rH c C s, zt �| �}W n ty" Y dS 0 d|v S )NFZHIRAGANAr rG r r r � is_hiragana� s rI c C s, zt �| �}W n ty" Y dS 0 d|v S )NFZKATAKANAr rG r r r � is_katakana� s rJ c C s, zt �| �}W n ty" Y dS 0 d|v S )NFZHANGULr rG r r r � is_hangul� s rK c C s, zt �| �}W n ty" Y dS 0 d|v S )NFZTHAIr rG r r r �is_thai� s rL c C s, zt �| �}W n ty" Y dS 0 d|v S )NF�ARABICr rG r r r � is_arabic� s rN c C s4 zt �| �}W n ty" Y dS 0 d|v o2d|v S )NFrM z ISOLATED FORMr rG r r r �is_arabic_isolated_form� s rO )r* r c s t � fdd�tD ��S )Nc 3 s | ]}|� v V qd S rA r )�.0�keyword�r* r r � <genexpr>� � z-is_unicode_range_secondary.<locals>.<genexpr>)�anyr rR r rR r �is_unicode_range_secondary� s rV c C s( | � � du o&| �� du o&| dko&| dkS )NF�u )r? � isprintablerD r r r �is_unprintable� s ���rY � )�sequence� search_zoner c C s� t | t�st�t| �}tt| dt||�� jddd��}t|�dkrHdS |D ]N}|�� � dd�}t � � D ]0\}}||kr�| S ||krh| S qhqLdS )zW Extract using ASCII-only decoder any specified encoding in the first n-bytes. N�ascii�ignore��errorsr �-�_) � isinstance�bytes� TypeError�lenr r �min�decode�lower�replacer r) )r[ r\ Zseq_len�results�specified_encoding�encoding_alias� encoding_ianar r r �any_specified_encoding� s" � ro � )r r c C s | dv p t t�d�| ��jt�S )zQ Verify is a specific encoding is a multi byte one based on it IANA name > � utf_32_le� utf_32_be�utf_32� utf_16_be� utf_8_sig�utf_7�utf_8�utf_16� utf_16_le� encodings.{})� issubclass� importlib� import_module�formatr r )r r r r �is_multi_byte_encoding� s ��r )r[ r c C sJ t D ]@}t | }t|t�r |g}|D ] }| �|�r$||f S q$qdS )z9 Identify and extract SIG/BOM in given sequence. )NrT )r rc rd � startswith)r[ � iana_encodingZmarks�markr r r �identify_sig_or_bom s r� )r� r c C s | dvS )N> rs rx r )r� r r r �should_strip_sig_or_bom s r� T)�cp_name�strictr c C sL | � � �dd�} t�� D ] \}}| ||fv r| S q|rHtd�| ���| S )Nra rb z Unable to retrieve IANA for '{}')ri rj r r) r r~ )r� r� rm rn r r r � iana_name" s r� )�decoded_sequencer c C s4 t � }| D ] }t|�}|d u r q |�|� q t|�S rA )�setr+ �add�list)r� Zrangesr r3 r r r � range_scan2 s r� )� iana_name_a� iana_name_br c C s� t | �st |�rdS t�d�| ��j}t�d�|��j}|dd�}|dd�}d}td�D ]*}t|g�}|�|�|�|�krX|d7 }qX|d S ) Ng rz r^ r_ r � r � )r r| r} r~ r �rangerd rh ) r� r� Z decoder_aZ decoder_bZid_aZid_b�character_match_count�iZ to_be_decodedr r r � cp_similarity@ s �� r� c C s | t v o|t | v S )z� Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using the function cp_similarity. )r )r� r� r r r � is_cp_similarX s �r� �charset_normalizerz)%(asctime)s | %(levelname)s | %(message)s)r �level� format_stringr c C s: t �| �}|�|� t �� }|�t �|�� |�|� d S rA )�logging� getLogger�setLevel� StreamHandler� setFormatter� Formatter� addHandler)r r� r� �logger�handlerr r r �set_logging_handlerc s r� ) � sequencesrn �offsets� chunk_size�bom_or_sig_available�strip_sig_or_bom� sig_payload�is_multi_byte_decoder�decoded_payloadr c c s* |r6|du r6|D ]"} || | | � } | s, q4| V qn�|D ]�} | | } | t | �d krXq:| | | | � } |r||du r||| } | j||r�dndd�} |�r | dk�r t|d�} |�r | d | � |v�r t| | d d �D ]H}| || � } |r�|du r�|| } | j|dd�} | d | � |v r� �q q�| V q:d S ) NF� r^ r� r_ r r! � ���)rf rh rg r� )r� rn r� r� r� r� r� r� r� r� �chunkZ chunk_endZ cut_sequenceZchunk_partial_size_chk�jr r r �cut_sequence_chunksp s> � �� r� )rZ )T)N)?r| r� r �codecsr Zencodings.aliasesr � functoolsr �rer �typingr r r r r r Z_multibytecodecr �constantr r r r r r �str�boolr r' r+ r, r4 r8 r: r@ rE rH rI rJ rK rL rN rO rf rV rY rd r% ro r r� r� r� r� �floatr� r� �INFOr� r� r� r r r r �<module> s� �� � �PK -�Z py.typednu �[��� PK -�Zb��ݪN �N md.pynu �[��� from functools import lru_cache from logging import getLogger from typing import List, Optional from .constant import ( COMMON_SAFE_ASCII_CHARACTERS, TRACE, UNICODE_SECONDARY_RANGE_KEYWORD, ) from .utils import ( is_accentuated, is_arabic, is_arabic_isolated_form, is_case_variable, is_cjk, is_emoticon, is_hangul, is_hiragana, is_katakana, is_latin, is_punctuation, is_separator, is_symbol, is_thai, is_unprintable, remove_accent, unicode_range, ) class MessDetectorPlugin: """ Base abstract class used for mess detection plugins. All detectors MUST extend and implement given methods. """ def eligible(self, character: str) -> bool: """ Determine if given character should be fed in. """ raise NotImplementedError # pragma: nocover def feed(self, character: str) -> None: """ The main routine to be executed upon character. Insert the logic in witch the text would be considered chaotic. """ raise NotImplementedError # pragma: nocover def reset(self) -> None: # pragma: no cover """ Permit to reset the plugin to the initial state. """ raise NotImplementedError @property def ratio(self) -> float: """ Compute the chaos ratio based on what your feed() has seen. Must NOT be lower than 0.; No restriction gt 0. """ raise NotImplementedError # pragma: nocover class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin): def __init__(self) -> None: self._punctuation_count: int = 0 self._symbol_count: int = 0 self._character_count: int = 0 self._last_printable_char: Optional[str] = None self._frenzy_symbol_in_word: bool = False def eligible(self, character: str) -> bool: return character.isprintable() def feed(self, character: str) -> None: self._character_count += 1 if ( character != self._last_printable_char and character not in COMMON_SAFE_ASCII_CHARACTERS ): if is_punctuation(character): self._punctuation_count += 1 elif ( character.isdigit() is False and is_symbol(character) and is_emoticon(character) is False ): self._symbol_count += 2 self._last_printable_char = character def reset(self) -> None: # pragma: no cover self._punctuation_count = 0 self._character_count = 0 self._symbol_count = 0 @property def ratio(self) -> float: if self._character_count == 0: return 0.0 ratio_of_punctuation: float = ( self._punctuation_count + self._symbol_count ) / self._character_count return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0 class TooManyAccentuatedPlugin(MessDetectorPlugin): def __init__(self) -> None: self._character_count: int = 0 self._accentuated_count: int = 0 def eligible(self, character: str) -> bool: return character.isalpha() def feed(self, character: str) -> None: self._character_count += 1 if is_accentuated(character): self._accentuated_count += 1 def reset(self) -> None: # pragma: no cover self._character_count = 0 self._accentuated_count = 0 @property def ratio(self) -> float: if self._character_count < 8: return 0.0 ratio_of_accentuation: float = self._accentuated_count / self._character_count return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0 class UnprintablePlugin(MessDetectorPlugin): def __init__(self) -> None: self._unprintable_count: int = 0 self._character_count: int = 0 def eligible(self, character: str) -> bool: return True def feed(self, character: str) -> None: if is_unprintable(character): self._unprintable_count += 1 self._character_count += 1 def reset(self) -> None: # pragma: no cover self._unprintable_count = 0 @property def ratio(self) -> float: if self._character_count == 0: return 0.0 return (self._unprintable_count * 8) / self._character_count class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin): def __init__(self) -> None: self._successive_count: int = 0 self._character_count: int = 0 self._last_latin_character: Optional[str] = None def eligible(self, character: str) -> bool: return character.isalpha() and is_latin(character) def feed(self, character: str) -> None: self._character_count += 1 if ( self._last_latin_character is not None and is_accentuated(character) and is_accentuated(self._last_latin_character) ): if character.isupper() and self._last_latin_character.isupper(): self._successive_count += 1 # Worse if its the same char duplicated with different accent. if remove_accent(character) == remove_accent(self._last_latin_character): self._successive_count += 1 self._last_latin_character = character def reset(self) -> None: # pragma: no cover self._successive_count = 0 self._character_count = 0 self._last_latin_character = None @property def ratio(self) -> float: if self._character_count == 0: return 0.0 return (self._successive_count * 2) / self._character_count class SuspiciousRange(MessDetectorPlugin): def __init__(self) -> None: self._suspicious_successive_range_count: int = 0 self._character_count: int = 0 self._last_printable_seen: Optional[str] = None def eligible(self, character: str) -> bool: return character.isprintable() def feed(self, character: str) -> None: self._character_count += 1 if ( character.isspace() or is_punctuation(character) or character in COMMON_SAFE_ASCII_CHARACTERS ): self._last_printable_seen = None return if self._last_printable_seen is None: self._last_printable_seen = character return unicode_range_a: Optional[str] = unicode_range(self._last_printable_seen) unicode_range_b: Optional[str] = unicode_range(character) if is_suspiciously_successive_range(unicode_range_a, unicode_range_b): self._suspicious_successive_range_count += 1 self._last_printable_seen = character def reset(self) -> None: # pragma: no cover self._character_count = 0 self._suspicious_successive_range_count = 0 self._last_printable_seen = None @property def ratio(self) -> float: if self._character_count <= 13: return 0.0 ratio_of_suspicious_range_usage: float = ( self._suspicious_successive_range_count * 2 ) / self._character_count return ratio_of_suspicious_range_usage class SuperWeirdWordPlugin(MessDetectorPlugin): def __init__(self) -> None: self._word_count: int = 0 self._bad_word_count: int = 0 self._foreign_long_count: int = 0 self._is_current_word_bad: bool = False self._foreign_long_watch: bool = False self._character_count: int = 0 self._bad_character_count: int = 0 self._buffer: str = "" self._buffer_accent_count: int = 0 self._buffer_glyph_count: int = 0 def eligible(self, character: str) -> bool: return True def feed(self, character: str) -> None: if character.isalpha(): self._buffer += character if is_accentuated(character): self._buffer_accent_count += 1 if ( self._foreign_long_watch is False and (is_latin(character) is False or is_accentuated(character)) and is_cjk(character) is False and is_hangul(character) is False and is_katakana(character) is False and is_hiragana(character) is False and is_thai(character) is False ): self._foreign_long_watch = True if ( is_cjk(character) or is_hangul(character) or is_katakana(character) or is_hiragana(character) or is_thai(character) ): self._buffer_glyph_count += 1 return if not self._buffer: return if ( character.isspace() or is_punctuation(character) or is_separator(character) ) and self._buffer: self._word_count += 1 buffer_length: int = len(self._buffer) self._character_count += buffer_length if buffer_length >= 4: if self._buffer_accent_count / buffer_length >= 0.5: self._is_current_word_bad = True # Word/Buffer ending with an upper case accentuated letter are so rare, # that we will consider them all as suspicious. Same weight as foreign_long suspicious. elif ( is_accentuated(self._buffer[-1]) and self._buffer[-1].isupper() and all(_.isupper() for _ in self._buffer) is False ): self._foreign_long_count += 1 self._is_current_word_bad = True elif self._buffer_glyph_count == 1: self._is_current_word_bad = True self._foreign_long_count += 1 if buffer_length >= 24 and self._foreign_long_watch: camel_case_dst = [ i for c, i in zip(self._buffer, range(0, buffer_length)) if c.isupper() ] probable_camel_cased: bool = False if camel_case_dst and (len(camel_case_dst) / buffer_length <= 0.3): probable_camel_cased = True if not probable_camel_cased: self._foreign_long_count += 1 self._is_current_word_bad = True if self._is_current_word_bad: self._bad_word_count += 1 self._bad_character_count += len(self._buffer) self._is_current_word_bad = False self._foreign_long_watch = False self._buffer = "" self._buffer_accent_count = 0 self._buffer_glyph_count = 0 elif ( character not in {"<", ">", "-", "=", "~", "|", "_"} and character.isdigit() is False and is_symbol(character) ): self._is_current_word_bad = True self._buffer += character def reset(self) -> None: # pragma: no cover self._buffer = "" self._is_current_word_bad = False self._foreign_long_watch = False self._bad_word_count = 0 self._word_count = 0 self._character_count = 0 self._bad_character_count = 0 self._foreign_long_count = 0 @property def ratio(self) -> float: if self._word_count <= 10 and self._foreign_long_count == 0: return 0.0 return self._bad_character_count / self._character_count class CjkInvalidStopPlugin(MessDetectorPlugin): """ GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and can be easily detected. Searching for the overuse of '丅' and '丄'. """ def __init__(self) -> None: self._wrong_stop_count: int = 0 self._cjk_character_count: int = 0 def eligible(self, character: str) -> bool: return True def feed(self, character: str) -> None: if character in {"丅", "丄"}: self._wrong_stop_count += 1 return if is_cjk(character): self._cjk_character_count += 1 def reset(self) -> None: # pragma: no cover self._wrong_stop_count = 0 self._cjk_character_count = 0 @property def ratio(self) -> float: if self._cjk_character_count < 16: return 0.0 return self._wrong_stop_count / self._cjk_character_count class ArchaicUpperLowerPlugin(MessDetectorPlugin): def __init__(self) -> None: self._buf: bool = False self._character_count_since_last_sep: int = 0 self._successive_upper_lower_count: int = 0 self._successive_upper_lower_count_final: int = 0 self._character_count: int = 0 self._last_alpha_seen: Optional[str] = None self._current_ascii_only: bool = True def eligible(self, character: str) -> bool: return True def feed(self, character: str) -> None: is_concerned = character.isalpha() and is_case_variable(character) chunk_sep = is_concerned is False if chunk_sep and self._character_count_since_last_sep > 0: if ( self._character_count_since_last_sep <= 64 and character.isdigit() is False and self._current_ascii_only is False ): self._successive_upper_lower_count_final += ( self._successive_upper_lower_count ) self._successive_upper_lower_count = 0 self._character_count_since_last_sep = 0 self._last_alpha_seen = None self._buf = False self._character_count += 1 self._current_ascii_only = True return if self._current_ascii_only is True and character.isascii() is False: self._current_ascii_only = False if self._last_alpha_seen is not None: if (character.isupper() and self._last_alpha_seen.islower()) or ( character.islower() and self._last_alpha_seen.isupper() ): if self._buf is True: self._successive_upper_lower_count += 2 self._buf = False else: self._buf = True else: self._buf = False self._character_count += 1 self._character_count_since_last_sep += 1 self._last_alpha_seen = character def reset(self) -> None: # pragma: no cover self._character_count = 0 self._character_count_since_last_sep = 0 self._successive_upper_lower_count = 0 self._successive_upper_lower_count_final = 0 self._last_alpha_seen = None self._buf = False self._current_ascii_only = True @property def ratio(self) -> float: if self._character_count == 0: return 0.0 return self._successive_upper_lower_count_final / self._character_count class ArabicIsolatedFormPlugin(MessDetectorPlugin): def __init__(self) -> None: self._character_count: int = 0 self._isolated_form_count: int = 0 def reset(self) -> None: # pragma: no cover self._character_count = 0 self._isolated_form_count = 0 def eligible(self, character: str) -> bool: return is_arabic(character) def feed(self, character: str) -> None: self._character_count += 1 if is_arabic_isolated_form(character): self._isolated_form_count += 1 @property def ratio(self) -> float: if self._character_count < 8: return 0.0 isolated_form_usage: float = self._isolated_form_count / self._character_count return isolated_form_usage @lru_cache(maxsize=1024) def is_suspiciously_successive_range( unicode_range_a: Optional[str], unicode_range_b: Optional[str] ) -> bool: """ Determine if two Unicode range seen next to each other can be considered as suspicious. """ if unicode_range_a is None or unicode_range_b is None: return True if unicode_range_a == unicode_range_b: return False if "Latin" in unicode_range_a and "Latin" in unicode_range_b: return False if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b: return False # Latin characters can be accompanied with a combining diacritical mark # eg. Vietnamese. if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and ( "Combining" in unicode_range_a or "Combining" in unicode_range_b ): return False keywords_range_a, keywords_range_b = unicode_range_a.split( " " ), unicode_range_b.split(" ") for el in keywords_range_a: if el in UNICODE_SECONDARY_RANGE_KEYWORD: continue if el in keywords_range_b: return False # Japanese Exception range_a_jp_chars, range_b_jp_chars = ( unicode_range_a in ( "Hiragana", "Katakana", ), unicode_range_b in ("Hiragana", "Katakana"), ) if (range_a_jp_chars or range_b_jp_chars) and ( "CJK" in unicode_range_a or "CJK" in unicode_range_b ): return False if range_a_jp_chars and range_b_jp_chars: return False if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b: if "CJK" in unicode_range_a or "CJK" in unicode_range_b: return False if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin": return False # Chinese/Japanese use dedicated range for punctuation and/or separators. if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or ( unicode_range_a in ["Katakana", "Hiragana"] and unicode_range_b in ["Katakana", "Hiragana"] ): if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b: return False if "Forms" in unicode_range_a or "Forms" in unicode_range_b: return False if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin": return False return True @lru_cache(maxsize=2048) def mess_ratio( decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False ) -> float: """ Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier. """ detectors: List[MessDetectorPlugin] = [ md_class() for md_class in MessDetectorPlugin.__subclasses__() ] length: int = len(decoded_sequence) + 1 mean_mess_ratio: float = 0.0 if length < 512: intermediary_mean_mess_ratio_calc: int = 32 elif length <= 1024: intermediary_mean_mess_ratio_calc = 64 else: intermediary_mean_mess_ratio_calc = 128 for character, index in zip(decoded_sequence + "\n", range(length)): for detector in detectors: if detector.eligible(character): detector.feed(character) if ( index > 0 and index % intermediary_mean_mess_ratio_calc == 0 ) or index == length - 1: mean_mess_ratio = sum(dt.ratio for dt in detectors) if mean_mess_ratio >= maximum_threshold: break if debug: logger = getLogger("charset_normalizer") logger.log( TRACE, "Mess-detector extended-analysis start. " f"intermediary_mean_mess_ratio_calc={intermediary_mean_mess_ratio_calc} mean_mess_ratio={mean_mess_ratio} " f"maximum_threshold={maximum_threshold}", ) if len(decoded_sequence) > 16: logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}") logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}") for dt in detectors: # pragma: nocover logger.log(TRACE, f"{dt.__class__}: {dt.ratio}") return round(mean_mess_ratio, 3) PK -�Z�I��I I __main__.pynu �[��� from .cli import cli_detect if __name__ == "__main__": cli_detect() PK -�ZB'�0 �0 models.pynu �[��� from encodings.aliases import aliases from hashlib import sha256 from json import dumps from re import sub from typing import Any, Dict, Iterator, List, Optional, Tuple, Union from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE from .utils import iana_name, is_multi_byte_encoding, unicode_range class CharsetMatch: def __init__( self, payload: bytes, guessed_encoding: str, mean_mess_ratio: float, has_sig_or_bom: bool, languages: "CoherenceMatches", decoded_payload: Optional[str] = None, preemptive_declaration: Optional[str] = None, ): self._payload: bytes = payload self._encoding: str = guessed_encoding self._mean_mess_ratio: float = mean_mess_ratio self._languages: CoherenceMatches = languages self._has_sig_or_bom: bool = has_sig_or_bom self._unicode_ranges: Optional[List[str]] = None self._leaves: List[CharsetMatch] = [] self._mean_coherence_ratio: float = 0.0 self._output_payload: Optional[bytes] = None self._output_encoding: Optional[str] = None self._string: Optional[str] = decoded_payload self._preemptive_declaration: Optional[str] = preemptive_declaration def __eq__(self, other: object) -> bool: if not isinstance(other, CharsetMatch): if isinstance(other, str): return iana_name(other) == self.encoding return False return self.encoding == other.encoding and self.fingerprint == other.fingerprint def __lt__(self, other: object) -> bool: """ Implemented to make sorted available upon CharsetMatches items. """ if not isinstance(other, CharsetMatch): raise ValueError chaos_difference: float = abs(self.chaos - other.chaos) coherence_difference: float = abs(self.coherence - other.coherence) # Below 1% difference --> Use Coherence if chaos_difference < 0.01 and coherence_difference > 0.02: return self.coherence > other.coherence elif chaos_difference < 0.01 and coherence_difference <= 0.02: # When having a difficult decision, use the result that decoded as many multi-byte as possible. # preserve RAM usage! if len(self._payload) >= TOO_BIG_SEQUENCE: return self.chaos < other.chaos return self.multi_byte_usage > other.multi_byte_usage return self.chaos < other.chaos @property def multi_byte_usage(self) -> float: return 1.0 - (len(str(self)) / len(self.raw)) def __str__(self) -> str: # Lazy Str Loading if self._string is None: self._string = str(self._payload, self._encoding, "strict") return self._string def __repr__(self) -> str: return "<CharsetMatch '{}' bytes({})>".format(self.encoding, self.fingerprint) def add_submatch(self, other: "CharsetMatch") -> None: if not isinstance(other, CharsetMatch) or other == self: raise ValueError( "Unable to add instance <{}> as a submatch of a CharsetMatch".format( other.__class__ ) ) other._string = None # Unload RAM usage; dirty trick. self._leaves.append(other) @property def encoding(self) -> str: return self._encoding @property def encoding_aliases(self) -> List[str]: """ Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855. """ also_known_as: List[str] = [] for u, p in aliases.items(): if self.encoding == u: also_known_as.append(p) elif self.encoding == p: also_known_as.append(u) return also_known_as @property def bom(self) -> bool: return self._has_sig_or_bom @property def byte_order_mark(self) -> bool: return self._has_sig_or_bom @property def languages(self) -> List[str]: """ 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'. """ return [e[0] for e in self._languages] @property def language(self) -> str: """ Most probable language found in decoded sequence. If none were detected or inferred, the property will return "Unknown". """ if not self._languages: # Trying to infer the language based on the given encoding # Its either English or we should not pronounce ourselves in certain cases. if "ascii" in self.could_be_from_charset: return "English" # doing it there to avoid circular import from charset_normalizer.cd import encoding_languages, mb_encoding_languages languages = ( mb_encoding_languages(self.encoding) if is_multi_byte_encoding(self.encoding) else encoding_languages(self.encoding) ) if len(languages) == 0 or "Latin Based" in languages: return "Unknown" return languages[0] return self._languages[0][0] @property def chaos(self) -> float: return self._mean_mess_ratio @property def coherence(self) -> float: if not self._languages: return 0.0 return self._languages[0][1] @property def percent_chaos(self) -> float: return round(self.chaos * 100, ndigits=3) @property def percent_coherence(self) -> float: return round(self.coherence * 100, ndigits=3) @property def raw(self) -> bytes: """ Original untouched bytes. """ return self._payload @property def submatch(self) -> List["CharsetMatch"]: return self._leaves @property def has_submatch(self) -> bool: return len(self._leaves) > 0 @property def alphabets(self) -> List[str]: if self._unicode_ranges is not None: return self._unicode_ranges # list detected ranges detected_ranges: List[Optional[str]] = [ unicode_range(char) for char in str(self) ] # filter and sort self._unicode_ranges = sorted(list({r for r in detected_ranges if r})) return self._unicode_ranges @property def could_be_from_charset(self) -> List[str]: """ 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'. """ return [self._encoding] + [m.encoding for m in self._leaves] def output(self, encoding: str = "utf_8") -> bytes: """ 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. """ if self._output_encoding is None or self._output_encoding != encoding: self._output_encoding = encoding decoded_string = str(self) if ( self._preemptive_declaration is not None and self._preemptive_declaration.lower() not in ["utf-8", "utf8", "utf_8"] ): patched_header = sub( RE_POSSIBLE_ENCODING_INDICATION, lambda m: m.string[m.span()[0] : m.span()[1]].replace( m.groups()[0], iana_name(self._output_encoding) # type: ignore[arg-type] ), decoded_string[:8192], 1, ) decoded_string = patched_header + decoded_string[8192:] self._output_payload = decoded_string.encode(encoding, "replace") return self._output_payload # type: ignore @property def fingerprint(self) -> str: """ Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one. """ return sha256(self.output()).hexdigest() class CharsetMatches: """ 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. """ def __init__(self, results: Optional[List[CharsetMatch]] = None): self._results: List[CharsetMatch] = sorted(results) if results else [] def __iter__(self) -> Iterator[CharsetMatch]: yield from self._results def __getitem__(self, item: Union[int, str]) -> CharsetMatch: """ 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. """ if isinstance(item, int): return self._results[item] if isinstance(item, str): item = iana_name(item, False) for result in self._results: if item in result.could_be_from_charset: return result raise KeyError def __len__(self) -> int: return len(self._results) def __bool__(self) -> bool: return len(self._results) > 0 def append(self, item: CharsetMatch) -> None: """ Insert a single match. Will be inserted accordingly to preserve sort. Can be inserted as a submatch. """ if not isinstance(item, CharsetMatch): raise ValueError( "Cannot append instance '{}' to CharsetMatches".format( str(item.__class__) ) ) # We should disable the submatch factoring when the input file is too heavy (conserve RAM usage) if len(item.raw) < TOO_BIG_SEQUENCE: for match in self._results: if match.fingerprint == item.fingerprint and match.chaos == item.chaos: match.add_submatch(item) return self._results.append(item) self._results = sorted(self._results) def best(self) -> Optional["CharsetMatch"]: """ Simply return the first match. Strict equivalent to matches[0]. """ if not self._results: return None return self._results[0] def first(self) -> Optional["CharsetMatch"]: """ Redundant method, call the method best(). Kept for BC reasons. """ return self.best() CoherenceMatch = Tuple[str, float] CoherenceMatches = List[CoherenceMatch] class CliDetectionResult: def __init__( self, path: str, encoding: Optional[str], encoding_aliases: List[str], alternative_encodings: List[str], language: str, alphabets: List[str], has_sig_or_bom: bool, chaos: float, coherence: float, unicode_path: Optional[str], is_preferred: bool, ): self.path: str = path self.unicode_path: Optional[str] = unicode_path self.encoding: Optional[str] = encoding self.encoding_aliases: List[str] = encoding_aliases self.alternative_encodings: List[str] = alternative_encodings self.language: str = language self.alphabets: List[str] = alphabets self.has_sig_or_bom: bool = has_sig_or_bom self.chaos: float = chaos self.coherence: float = coherence self.is_preferred: bool = is_preferred @property def __dict__(self) -> Dict[str, Any]: # type: ignore return { "path": self.path, "encoding": self.encoding, "encoding_aliases": self.encoding_aliases, "alternative_encodings": self.alternative_encodings, "language": self.language, "alphabets": self.alphabets, "has_sig_or_bom": self.has_sig_or_bom, "chaos": self.chaos, "coherence": self.coherence, "unicode_path": self.unicode_path, "is_preferred": self.is_preferred, } def to_json(self) -> str: return dumps(self.__dict__, ensure_ascii=True, indent=4) PK -�Z%��1 1 cd.pynu �[��� import importlib from codecs import IncrementalDecoder from collections import Counter from functools import lru_cache from typing import Counter as TypeCounter, Dict, List, Optional, Tuple from .constant import ( FREQUENCIES, KO_NAMES, LANGUAGE_SUPPORTED_COUNT, TOO_SMALL_SEQUENCE, ZH_NAMES, ) from .md import is_suspiciously_successive_range from .models import CoherenceMatches from .utils import ( is_accentuated, is_latin, is_multi_byte_encoding, is_unicode_range_secondary, unicode_range, ) def encoding_unicode_range(iana_name: str) -> List[str]: """ Return associated unicode ranges in a single byte code page. """ if is_multi_byte_encoding(iana_name): raise IOError("Function not supported on multi-byte code page") decoder = importlib.import_module( "encodings.{}".format(iana_name) ).IncrementalDecoder p: IncrementalDecoder = decoder(errors="ignore") seen_ranges: Dict[str, int] = {} character_count: int = 0 for i in range(0x40, 0xFF): chunk: str = p.decode(bytes([i])) if chunk: character_range: Optional[str] = unicode_range(chunk) if character_range is None: continue if is_unicode_range_secondary(character_range) is False: if character_range not in seen_ranges: seen_ranges[character_range] = 0 seen_ranges[character_range] += 1 character_count += 1 return sorted( [ character_range for character_range in seen_ranges if seen_ranges[character_range] / character_count >= 0.15 ] ) def unicode_range_languages(primary_range: str) -> List[str]: """ Return inferred languages used with a unicode range. """ languages: List[str] = [] for language, characters in FREQUENCIES.items(): for character in characters: if unicode_range(character) == primary_range: languages.append(language) break return languages @lru_cache() def encoding_languages(iana_name: str) -> List[str]: """ Single-byte encoding language association. Some code page are heavily linked to particular language(s). This function does the correspondence. """ unicode_ranges: List[str] = encoding_unicode_range(iana_name) primary_range: Optional[str] = None for specified_range in unicode_ranges: if "Latin" not in specified_range: primary_range = specified_range break if primary_range is None: return ["Latin Based"] return unicode_range_languages(primary_range) @lru_cache() def mb_encoding_languages(iana_name: str) -> List[str]: """ Multi-byte encoding language association. Some code page are heavily linked to particular language(s). This function does the correspondence. """ if ( iana_name.startswith("shift_") or iana_name.startswith("iso2022_jp") or iana_name.startswith("euc_j") or iana_name == "cp932" ): return ["Japanese"] if iana_name.startswith("gb") or iana_name in ZH_NAMES: return ["Chinese"] if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES: return ["Korean"] return [] @lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT) def get_target_features(language: str) -> Tuple[bool, bool]: """ Determine main aspects from a supported language if it contains accents and if is pure Latin. """ target_have_accents: bool = False target_pure_latin: bool = True for character in FREQUENCIES[language]: if not target_have_accents and is_accentuated(character): target_have_accents = True if target_pure_latin and is_latin(character) is False: target_pure_latin = False return target_have_accents, target_pure_latin def alphabet_languages( characters: List[str], ignore_non_latin: bool = False ) -> List[str]: """ Return associated languages associated to given characters. """ languages: List[Tuple[str, float]] = [] source_have_accents = any(is_accentuated(character) for character in characters) for language, language_characters in FREQUENCIES.items(): target_have_accents, target_pure_latin = get_target_features(language) if ignore_non_latin and target_pure_latin is False: continue if target_have_accents is False and source_have_accents: continue character_count: int = len(language_characters) character_match_count: int = len( [c for c in language_characters if c in characters] ) ratio: float = character_match_count / character_count if ratio >= 0.2: languages.append((language, ratio)) languages = sorted(languages, key=lambda x: x[1], reverse=True) return [compatible_language[0] for compatible_language in languages] def characters_popularity_compare( language: str, ordered_characters: List[str] ) -> float: """ Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language. The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit). Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.) """ if language not in FREQUENCIES: raise ValueError("{} not available".format(language)) character_approved_count: int = 0 FREQUENCIES_language_set = set(FREQUENCIES[language]) ordered_characters_count: int = len(ordered_characters) target_language_characters_count: int = len(FREQUENCIES[language]) large_alphabet: bool = target_language_characters_count > 26 for character, character_rank in zip( ordered_characters, range(0, ordered_characters_count) ): if character not in FREQUENCIES_language_set: continue character_rank_in_language: int = FREQUENCIES[language].index(character) expected_projection_ratio: float = ( target_language_characters_count / ordered_characters_count ) character_rank_projection: int = int(character_rank * expected_projection_ratio) if ( large_alphabet is False and abs(character_rank_projection - character_rank_in_language) > 4 ): continue if ( large_alphabet is True and abs(character_rank_projection - character_rank_in_language) < target_language_characters_count / 3 ): character_approved_count += 1 continue characters_before_source: List[str] = FREQUENCIES[language][ 0:character_rank_in_language ] characters_after_source: List[str] = FREQUENCIES[language][ character_rank_in_language: ] characters_before: List[str] = ordered_characters[0:character_rank] characters_after: List[str] = ordered_characters[character_rank:] before_match_count: int = len( set(characters_before) & set(characters_before_source) ) after_match_count: int = len( set(characters_after) & set(characters_after_source) ) if len(characters_before_source) == 0 and before_match_count <= 4: character_approved_count += 1 continue if len(characters_after_source) == 0 and after_match_count <= 4: character_approved_count += 1 continue if ( before_match_count / len(characters_before_source) >= 0.4 or after_match_count / len(characters_after_source) >= 0.4 ): character_approved_count += 1 continue return character_approved_count / len(ordered_characters) def alpha_unicode_split(decoded_sequence: str) -> List[str]: """ Given a decoded text sequence, return a list of str. Unicode range / alphabet separation. Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list; One containing the latin letters and the other hebrew. """ layers: Dict[str, str] = {} for character in decoded_sequence: if character.isalpha() is False: continue character_range: Optional[str] = unicode_range(character) if character_range is None: continue layer_target_range: Optional[str] = None for discovered_range in layers: if ( is_suspiciously_successive_range(discovered_range, character_range) is False ): layer_target_range = discovered_range break if layer_target_range is None: layer_target_range = character_range if layer_target_range not in layers: layers[layer_target_range] = character.lower() continue layers[layer_target_range] += character.lower() return list(layers.values()) def merge_coherence_ratios(results: List[CoherenceMatches]) -> CoherenceMatches: """ This function merge results previously given by the function coherence_ratio. The return type is the same as coherence_ratio. """ per_language_ratios: Dict[str, List[float]] = {} for result in results: for sub_result in result: language, ratio = sub_result if language not in per_language_ratios: per_language_ratios[language] = [ratio] continue per_language_ratios[language].append(ratio) merge = [ ( language, round( sum(per_language_ratios[language]) / len(per_language_ratios[language]), 4, ), ) for language in per_language_ratios ] return sorted(merge, key=lambda x: x[1], reverse=True) def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches: """ We shall NOT return "English—" in CoherenceMatches because it is an alternative of "English". This function only keeps the best match and remove the em-dash in it. """ index_results: Dict[str, List[float]] = dict() for result in results: language, ratio = result no_em_name: str = language.replace("—", "") if no_em_name not in index_results: index_results[no_em_name] = [] index_results[no_em_name].append(ratio) if any(len(index_results[e]) > 1 for e in index_results): filtered_results: CoherenceMatches = [] for language in index_results: filtered_results.append((language, max(index_results[language]))) return filtered_results return results @lru_cache(maxsize=2048) def coherence_ratio( decoded_sequence: str, threshold: float = 0.1, lg_inclusion: Optional[str] = None ) -> CoherenceMatches: """ Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers. A layer = Character extraction by alphabets/ranges. """ results: List[Tuple[str, float]] = [] ignore_non_latin: bool = False sufficient_match_count: int = 0 lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else [] if "Latin Based" in lg_inclusion_list: ignore_non_latin = True lg_inclusion_list.remove("Latin Based") for layer in alpha_unicode_split(decoded_sequence): sequence_frequencies: TypeCounter[str] = Counter(layer) most_common = sequence_frequencies.most_common() character_count: int = sum(o for c, o in most_common) if character_count <= TOO_SMALL_SEQUENCE: continue popular_character_ordered: List[str] = [c for c, o in most_common] for language in lg_inclusion_list or alphabet_languages( popular_character_ordered, ignore_non_latin ): ratio: float = characters_popularity_compare( language, popular_character_ordered ) if ratio < threshold: continue elif ratio >= 0.8: sufficient_match_count += 1 results.append((language, round(ratio, 4))) if sufficient_match_count >= 3: break return sorted( filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True ) PK -�Z !?FO O version.pynu �[��� """ Expose version """ __version__ = "3.4.0" VERSION = __version__.split(".") PK -�Z����v. v. utils.pynu �[��� import importlib import logging import unicodedata from codecs import IncrementalDecoder from encodings.aliases import aliases from functools import lru_cache from re import findall from typing import Generator, List, Optional, Set, Tuple, Union from _multibytecodec import MultibyteIncrementalDecoder from .constant import ( ENCODING_MARKS, IANA_SUPPORTED_SIMILAR, RE_POSSIBLE_ENCODING_INDICATION, UNICODE_RANGES_COMBINED, UNICODE_SECONDARY_RANGE_KEYWORD, UTF8_MAXIMAL_ALLOCATION, ) @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_accentuated(character: str) -> bool: try: description: str = unicodedata.name(character) except ValueError: return False return ( "WITH GRAVE" in description or "WITH ACUTE" in description or "WITH CEDILLA" in description or "WITH DIAERESIS" in description or "WITH CIRCUMFLEX" in description or "WITH TILDE" in description or "WITH MACRON" in description or "WITH RING ABOVE" in description ) @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def remove_accent(character: str) -> str: decomposed: str = unicodedata.decomposition(character) if not decomposed: return character codes: List[str] = decomposed.split(" ") return chr(int(codes[0], 16)) @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def unicode_range(character: str) -> Optional[str]: """ Retrieve the Unicode range official name from a single character. """ character_ord: int = ord(character) for range_name, ord_range in UNICODE_RANGES_COMBINED.items(): if character_ord in ord_range: return range_name return None @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_latin(character: str) -> bool: try: description: str = unicodedata.name(character) except ValueError: return False return "LATIN" in description @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_punctuation(character: str) -> bool: character_category: str = unicodedata.category(character) if "P" in character_category: return True character_range: Optional[str] = unicode_range(character) if character_range is None: return False return "Punctuation" in character_range @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_symbol(character: str) -> bool: character_category: str = unicodedata.category(character) if "S" in character_category or "N" in character_category: return True character_range: Optional[str] = unicode_range(character) if character_range is None: return False return "Forms" in character_range and character_category != "Lo" @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_emoticon(character: str) -> bool: character_range: Optional[str] = unicode_range(character) if character_range is None: return False return "Emoticons" in character_range or "Pictographs" in character_range @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_separator(character: str) -> bool: if character.isspace() or character in {"｜", "+", "<", ">"}: return True character_category: str = unicodedata.category(character) return "Z" in character_category or character_category in {"Po", "Pd", "Pc"} @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_case_variable(character: str) -> bool: return character.islower() != character.isupper() @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_cjk(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "CJK" in character_name @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_hiragana(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "HIRAGANA" in character_name @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_katakana(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "KATAKANA" in character_name @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_hangul(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "HANGUL" in character_name @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_thai(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "THAI" in character_name @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_arabic(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "ARABIC" in character_name @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_arabic_isolated_form(character: str) -> bool: try: character_name = unicodedata.name(character) except ValueError: return False return "ARABIC" in character_name and "ISOLATED FORM" in character_name @lru_cache(maxsize=len(UNICODE_RANGES_COMBINED)) def is_unicode_range_secondary(range_name: str) -> bool: return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD) @lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) def is_unprintable(character: str) -> bool: return ( character.isspace() is False # includes \n \t \r \v and character.isprintable() is False and character != "\x1A" # Why? Its the ASCII substitute character. and character != "\ufeff" # bug discovered in Python, # Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space. ) def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> Optional[str]: """ Extract using ASCII-only decoder any specified encoding in the first n-bytes. """ if not isinstance(sequence, bytes): raise TypeError seq_len: int = len(sequence) results: List[str] = findall( RE_POSSIBLE_ENCODING_INDICATION, sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"), ) if len(results) == 0: return None for specified_encoding in results: specified_encoding = specified_encoding.lower().replace("-", "_") encoding_alias: str encoding_iana: str for encoding_alias, encoding_iana in aliases.items(): if encoding_alias == specified_encoding: return encoding_iana if encoding_iana == specified_encoding: return encoding_iana return None @lru_cache(maxsize=128) def is_multi_byte_encoding(name: str) -> bool: """ Verify is a specific encoding is a multi byte one based on it IANA name """ return name in { "utf_8", "utf_8_sig", "utf_16", "utf_16_be", "utf_16_le", "utf_32", "utf_32_le", "utf_32_be", "utf_7", } or issubclass( importlib.import_module("encodings.{}".format(name)).IncrementalDecoder, MultibyteIncrementalDecoder, ) def identify_sig_or_bom(sequence: bytes) -> Tuple[Optional[str], bytes]: """ Identify and extract SIG/BOM in given sequence. """ for iana_encoding in ENCODING_MARKS: marks: Union[bytes, List[bytes]] = ENCODING_MARKS[iana_encoding] if isinstance(marks, bytes): marks = [marks] for mark in marks: if sequence.startswith(mark): return iana_encoding, mark return None, b"" def should_strip_sig_or_bom(iana_encoding: str) -> bool: return iana_encoding not in {"utf_16", "utf_32"} def iana_name(cp_name: str, strict: bool = True) -> str: cp_name = cp_name.lower().replace("-", "_") encoding_alias: str encoding_iana: str for encoding_alias, encoding_iana in aliases.items(): if cp_name in [encoding_alias, encoding_iana]: return encoding_iana if strict: raise ValueError("Unable to retrieve IANA for '{}'".format(cp_name)) return cp_name def range_scan(decoded_sequence: str) -> List[str]: ranges: Set[str] = set() for character in decoded_sequence: character_range: Optional[str] = unicode_range(character) if character_range is None: continue ranges.add(character_range) return list(ranges) def cp_similarity(iana_name_a: str, iana_name_b: str) -> float: if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b): return 0.0 decoder_a = importlib.import_module( "encodings.{}".format(iana_name_a) ).IncrementalDecoder decoder_b = importlib.import_module( "encodings.{}".format(iana_name_b) ).IncrementalDecoder id_a: IncrementalDecoder = decoder_a(errors="ignore") id_b: IncrementalDecoder = decoder_b(errors="ignore") character_match_count: int = 0 for i in range(255): to_be_decoded: bytes = bytes([i]) if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded): character_match_count += 1 return character_match_count / 254 def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool: """ Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using the function cp_similarity. """ return ( iana_name_a in IANA_SUPPORTED_SIMILAR and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a] ) def set_logging_handler( name: str = "charset_normalizer", level: int = logging.INFO, format_string: str = "%(asctime)s | %(levelname)s | %(message)s", ) -> None: logger = logging.getLogger(name) logger.setLevel(level) handler = logging.StreamHandler() handler.setFormatter(logging.Formatter(format_string)) logger.addHandler(handler) def cut_sequence_chunks( sequences: bytes, encoding_iana: str, offsets: range, chunk_size: int, bom_or_sig_available: bool, strip_sig_or_bom: bool, sig_payload: bytes, is_multi_byte_decoder: bool, decoded_payload: Optional[str] = None, ) -> Generator[str, None, None]: if decoded_payload and is_multi_byte_decoder is False: for i in offsets: chunk = decoded_payload[i : i + chunk_size] if not chunk: break yield chunk else: for i in offsets: chunk_end = i + chunk_size if chunk_end > len(sequences) + 8: continue cut_sequence = sequences[i : i + chunk_size] if bom_or_sig_available and strip_sig_or_bom is False: cut_sequence = sig_payload + cut_sequence chunk = cut_sequence.decode( encoding_iana, errors="ignore" if is_multi_byte_decoder else "strict", ) # multi-byte bad cutting detector and adjustment # not the cleanest way to perform that fix but clever enough for now. if is_multi_byte_decoder and i > 0: chunk_partial_size_chk: int = min(chunk_size, 16) if ( decoded_payload and chunk[:chunk_partial_size_chk] not in decoded_payload ): for j in range(i, i - 4, -1): cut_sequence = sequences[j:chunk_end] if bom_or_sig_available and strip_sig_or_bom is False: cut_sequence = sig_payload + cut_sequence chunk = cut_sequence.decode(encoding_iana, errors="ignore") if chunk[:chunk_partial_size_chk] in decoded_payload: break yield chunk PK -�Z ^� legacy.pynu �[��� from __future__ import annotations from typing import TYPE_CHECKING, Any, Optional from warnings import warn from .api import from_bytes from .constant import CHARDET_CORRESPONDENCE # TODO: remove this check when dropping Python 3.7 support if TYPE_CHECKING: from typing_extensions import TypedDict class ResultDict(TypedDict): encoding: Optional[str] language: str confidence: Optional[float] def detect( byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any ) -> ResultDict: """ chardet legacy method Detect the encoding of the given byte string. It should be mostly backward-compatible. Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it) This function is deprecated and should be used to migrate your project easily, consult the documentation for further information. Not planned for removal. :param byte_str: The byte sequence to examine. :param should_rename_legacy: Should we rename legacy encodings to their more modern equivalents? """ if len(kwargs): warn( f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()" ) if not isinstance(byte_str, (bytearray, bytes)): raise TypeError( # pragma: nocover "Expected object of type bytes or bytearray, got: " "{0}".format(type(byte_str)) ) if isinstance(byte_str, bytearray): byte_str = bytes(byte_str) r = from_bytes(byte_str).best() encoding = r.encoding if r is not None else None language = r.language if r is not None and r.language != "Unknown" else "" confidence = 1.0 - r.chaos if r is not None else None # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process # but chardet does return 'utf-8-sig' and it is a valid codec name. if r is not None and encoding == "utf_8" and r.bom: encoding += "_sig" if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE: encoding = CHARDET_CORRESPONDENCE[encoding] return { "encoding": encoding, "language": language, "confidence": confidence, } PK -�ZJO3��( �( cli/__main__.pynu �[��� import argparse import sys from json import dumps from os.path import abspath, basename, dirname, join, realpath from platform import python_version from typing import List, Optional from unicodedata import unidata_version import charset_normalizer.md as md_module from charset_normalizer import from_fp from charset_normalizer.models import CliDetectionResult from charset_normalizer.version import __version__ def query_yes_no(question: str, default: str = "yes") -> bool: """Ask a yes/no question via input() and return their answer. "question" is a string that is presented to the user. "default" is the presumed answer if the user just hits <Enter>. It must be "yes" (the default), "no" or None (meaning an answer is required of the user). The "answer" return value is True for "yes" or False for "no". Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input """ valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False} if default is None: prompt = " [y/n] " elif default == "yes": prompt = " [Y/n] " elif default == "no": prompt = " [y/N] " else: raise ValueError("invalid default answer: '%s'" % default) while True: sys.stdout.write(question + prompt) choice = input().lower() if default is not None and choice == "": return valid[default] elif choice in valid: return valid[choice] else: sys.stdout.write("Please respond with 'yes' or 'no' " "(or 'y' or 'n').\n") def cli_detect(argv: Optional[List[str]] = None) -> int: """ CLI assistant using ARGV and ArgumentParser :param argv: :return: 0 if everything is fine, anything else equal trouble """ parser = argparse.ArgumentParser( description="The Real First Universal Charset Detector. " "Discover originating encoding used on text file. " "Normalize text to unicode." ) parser.add_argument( "files", type=argparse.FileType("rb"), nargs="+", help="File(s) to be analysed" ) parser.add_argument( "-v", "--verbose", action="store_true", default=False, dest="verbose", help="Display complementary information about file if any. " "Stdout will contain logs about the detection process.", ) parser.add_argument( "-a", "--with-alternative", action="store_true", default=False, dest="alternatives", help="Output complementary possibilities if any. Top-level JSON WILL be a list.", ) parser.add_argument( "-n", "--normalize", action="store_true", default=False, dest="normalize", help="Permit to normalize input file. If not set, program does not write anything.", ) parser.add_argument( "-m", "--minimal", action="store_true", default=False, dest="minimal", help="Only output the charset detected to STDOUT. Disabling JSON output.", ) parser.add_argument( "-r", "--replace", action="store_true", default=False, dest="replace", help="Replace file when trying to normalize it instead of creating a new one.", ) parser.add_argument( "-f", "--force", action="store_true", default=False, dest="force", help="Replace file without asking if you are sure, use this flag with caution.", ) parser.add_argument( "-i", "--no-preemptive", action="store_true", default=False, dest="no_preemptive", help="Disable looking at a charset declaration to hint the detector.", ) parser.add_argument( "-t", "--threshold", action="store", default=0.2, type=float, dest="threshold", help="Define a custom maximum amount of chaos allowed in decoded content. 0. <= chaos <= 1.", ) parser.add_argument( "--version", action="version", version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format( __version__, python_version(), unidata_version, "OFF" if md_module.__file__.lower().endswith(".py") else "ON", ), help="Show version information and exit.", ) args = parser.parse_args(argv) if args.replace is True and args.normalize is False: if args.files: for my_file in args.files: my_file.close() print("Use --replace in addition of --normalize only.", file=sys.stderr) return 1 if args.force is True and args.replace is False: if args.files: for my_file in args.files: my_file.close() print("Use --force in addition of --replace only.", file=sys.stderr) return 1 if args.threshold < 0.0 or args.threshold > 1.0: if args.files: for my_file in args.files: my_file.close() print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr) return 1 x_ = [] for my_file in args.files: matches = from_fp( my_file, threshold=args.threshold, explain=args.verbose, preemptive_behaviour=args.no_preemptive is False, ) best_guess = matches.best() if best_guess is None: print( 'Unable to identify originating encoding for "{}". {}'.format( my_file.name, ( "Maybe try increasing maximum amount of chaos." if args.threshold < 1.0 else "" ), ), file=sys.stderr, ) x_.append( CliDetectionResult( abspath(my_file.name), None, [], [], "Unknown", [], False, 1.0, 0.0, None, True, ) ) else: x_.append( CliDetectionResult( abspath(my_file.name), best_guess.encoding, best_guess.encoding_aliases, [ cp for cp in best_guess.could_be_from_charset if cp != best_guess.encoding ], best_guess.language, best_guess.alphabets, best_guess.bom, best_guess.percent_chaos, best_guess.percent_coherence, None, True, ) ) if len(matches) > 1 and args.alternatives: for el in matches: if el != best_guess: x_.append( CliDetectionResult( abspath(my_file.name), el.encoding, el.encoding_aliases, [ cp for cp in el.could_be_from_charset if cp != el.encoding ], el.language, el.alphabets, el.bom, el.percent_chaos, el.percent_coherence, None, False, ) ) if args.normalize is True: if best_guess.encoding.startswith("utf") is True: print( '"{}" file does not need to be normalized, as it already came from unicode.'.format( my_file.name ), file=sys.stderr, ) if my_file.closed is False: my_file.close() continue dir_path = dirname(realpath(my_file.name)) file_name = basename(realpath(my_file.name)) o_: List[str] = file_name.split(".") if args.replace is False: o_.insert(-1, best_guess.encoding) if my_file.closed is False: my_file.close() elif ( args.force is False and query_yes_no( 'Are you sure to normalize "{}" by replacing it ?'.format( my_file.name ), "no", ) is False ): if my_file.closed is False: my_file.close() continue try: x_[0].unicode_path = join(dir_path, ".".join(o_)) with open(x_[0].unicode_path, "wb") as fp: fp.write(best_guess.output()) except IOError as e: print(str(e), file=sys.stderr) if my_file.closed is False: my_file.close() return 2 if my_file.closed is False: my_file.close() if args.minimal is False: print( dumps( [el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__, ensure_ascii=True, indent=4, ) ) else: for my_file in args.files: print( ", ".join( [ el.encoding or "undefined" for el in x_ if el.path == abspath(my_file.name) ] ) ) return 0 if __name__ == "__main__": cli_detect() PK -�Z�P��d d cli/__init__.pynu �[��� from .__main__ import cli_detect, query_yes_no __all__ = ( "cli_detect", "query_yes_no", ) PK -�Z��D) ) __init__.pynu �[��� # -*- coding: utf-8 -*- """ Charset-Normalizer ~~~~~~~~~~~~~~ The Real First Universal Charset Detector. A library that helps you read text from an unknown charset encoding. Motivated by chardet, This package is trying to resolve the issue by taking a new approach. All IANA character set names for which the Python core library provides codecs are supported. Basic usage: >>> from charset_normalizer import from_bytes >>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8')) >>> best_guess = results.best() >>> str(best_guess) 'Bсеки човек има право на образование. Oбразованието!' Others methods and usages are available - see the full documentation at <https://github.com/Ousret/charset_normalizer>. :copyright: (c) 2021 by Ahmed TAHRI :license: MIT, see LICENSE for more details. """ import logging from .api import from_bytes, from_fp, from_path, is_binary from .legacy import detect from .models import CharsetMatch, CharsetMatches from .utils import set_logging_handler from .version import VERSION, __version__ __all__ = ( "from_fp", "from_path", "from_bytes", "is_binary", "detect", "CharsetMatch", "CharsetMatches", "__version__", "VERSION", "set_logging_handler", ) # Attach a NullHandler to the top level logger by default # https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library logging.getLogger("charset_normalizer").addHandler(logging.NullHandler()) PK -�ZH�Y X X api.pynu �[��� import logging from os import PathLike from typing import BinaryIO, List, Optional, Set, Union from .cd import ( coherence_ratio, encoding_languages, mb_encoding_languages, merge_coherence_ratios, ) from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE from .md import mess_ratio from .models import CharsetMatch, CharsetMatches from .utils import ( any_specified_encoding, cut_sequence_chunks, iana_name, identify_sig_or_bom, is_cp_similar, is_multi_byte_encoding, should_strip_sig_or_bom, ) # Will most likely be controversial # logging.addLevelName(TRACE, "TRACE") logger = logging.getLogger("charset_normalizer") explain_handler = logging.StreamHandler() explain_handler.setFormatter( logging.Formatter("%(asctime)s | %(levelname)s | %(message)s") ) def from_bytes( sequences: Union[bytes, bytearray], steps: int = 5, chunk_size: int = 512, threshold: float = 0.2, cp_isolation: Optional[List[str]] = None, cp_exclusion: Optional[List[str]] = None, preemptive_behaviour: bool = True, explain: bool = False, language_threshold: float = 0.1, enable_fallback: bool = True, ) -> CharsetMatches: """ 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 blocks 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. """ if not isinstance(sequences, (bytearray, bytes)): raise TypeError( "Expected object of type bytes or bytearray, got: {0}".format( type(sequences) ) ) if explain: previous_logger_level: int = logger.level logger.addHandler(explain_handler) logger.setLevel(TRACE) length: int = len(sequences) if length == 0: logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.") if explain: logger.removeHandler(explain_handler) logger.setLevel(previous_logger_level or logging.WARNING) return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")]) if cp_isolation is not None: logger.log( TRACE, "cp_isolation is set. use this flag for debugging purpose. " "limited list of encoding allowed : %s.", ", ".join(cp_isolation), ) cp_isolation = [iana_name(cp, False) for cp in cp_isolation] else: cp_isolation = [] if cp_exclusion is not None: logger.log( TRACE, "cp_exclusion is set. use this flag for debugging purpose. " "limited list of encoding excluded : %s.", ", ".join(cp_exclusion), ) cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion] else: cp_exclusion = [] if length <= (chunk_size * steps): logger.log( TRACE, "override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.", steps, chunk_size, length, ) steps = 1 chunk_size = length if steps > 1 and length / steps < chunk_size: chunk_size = int(length / steps) is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE if is_too_small_sequence: logger.log( TRACE, "Trying to detect encoding from a tiny portion of ({}) byte(s).".format( length ), ) elif is_too_large_sequence: logger.log( TRACE, "Using lazy str decoding because the payload is quite large, ({}) byte(s).".format( length ), ) prioritized_encodings: List[str] = [] specified_encoding: Optional[str] = ( any_specified_encoding(sequences) if preemptive_behaviour else None ) if specified_encoding is not None: prioritized_encodings.append(specified_encoding) logger.log( TRACE, "Detected declarative mark in sequence. Priority +1 given for %s.", specified_encoding, ) tested: Set[str] = set() tested_but_hard_failure: List[str] = [] tested_but_soft_failure: List[str] = [] fallback_ascii: Optional[CharsetMatch] = None fallback_u8: Optional[CharsetMatch] = None fallback_specified: Optional[CharsetMatch] = None results: CharsetMatches = CharsetMatches() early_stop_results: CharsetMatches = CharsetMatches() sig_encoding, sig_payload = identify_sig_or_bom(sequences) if sig_encoding is not None: prioritized_encodings.append(sig_encoding) logger.log( TRACE, "Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.", len(sig_payload), sig_encoding, ) prioritized_encodings.append("ascii") if "utf_8" not in prioritized_encodings: prioritized_encodings.append("utf_8") for encoding_iana in prioritized_encodings + IANA_SUPPORTED: if cp_isolation and encoding_iana not in cp_isolation: continue if cp_exclusion and encoding_iana in cp_exclusion: continue if encoding_iana in tested: continue tested.add(encoding_iana) decoded_payload: Optional[str] = None bom_or_sig_available: bool = sig_encoding == encoding_iana strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom( encoding_iana ) if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available: logger.log( TRACE, "Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.", encoding_iana, ) continue if encoding_iana in {"utf_7"} and not bom_or_sig_available: logger.log( TRACE, "Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.", encoding_iana, ) continue try: is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana) except (ModuleNotFoundError, ImportError): logger.log( TRACE, "Encoding %s does not provide an IncrementalDecoder", encoding_iana, ) continue try: if is_too_large_sequence and is_multi_byte_decoder is False: str( ( sequences[: int(50e4)] if strip_sig_or_bom is False else sequences[len(sig_payload) : int(50e4)] ), encoding=encoding_iana, ) else: decoded_payload = str( ( sequences if strip_sig_or_bom is False else sequences[len(sig_payload) :] ), encoding=encoding_iana, ) except (UnicodeDecodeError, LookupError) as e: if not isinstance(e, LookupError): logger.log( TRACE, "Code page %s does not fit given bytes sequence at ALL. %s", encoding_iana, str(e), ) tested_but_hard_failure.append(encoding_iana) continue similar_soft_failure_test: bool = False for encoding_soft_failed in tested_but_soft_failure: if is_cp_similar(encoding_iana, encoding_soft_failed): similar_soft_failure_test = True break if similar_soft_failure_test: logger.log( TRACE, "%s is deemed too similar to code page %s and was consider unsuited already. Continuing!", encoding_iana, encoding_soft_failed, ) continue r_ = range( 0 if not bom_or_sig_available else len(sig_payload), length, int(length / steps), ) multi_byte_bonus: bool = ( is_multi_byte_decoder and decoded_payload is not None and len(decoded_payload) < length ) if multi_byte_bonus: logger.log( TRACE, "Code page %s is a multi byte encoding table and it appear that at least one character " "was encoded using n-bytes.", encoding_iana, ) max_chunk_gave_up: int = int(len(r_) / 4) max_chunk_gave_up = max(max_chunk_gave_up, 2) early_stop_count: int = 0 lazy_str_hard_failure = False md_chunks: List[str] = [] md_ratios = [] try: for chunk in cut_sequence_chunks( sequences, encoding_iana, r_, chunk_size, bom_or_sig_available, strip_sig_or_bom, sig_payload, is_multi_byte_decoder, decoded_payload, ): md_chunks.append(chunk) md_ratios.append( mess_ratio( chunk, threshold, explain is True and 1 <= len(cp_isolation) <= 2, ) ) if md_ratios[-1] >= threshold: early_stop_count += 1 if (early_stop_count >= max_chunk_gave_up) or ( bom_or_sig_available and strip_sig_or_bom is False ): break except ( UnicodeDecodeError ) as e: # Lazy str loading may have missed something there logger.log( TRACE, "LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s", encoding_iana, str(e), ) early_stop_count = max_chunk_gave_up lazy_str_hard_failure = True # We might want to check the sequence again with the whole content # Only if initial MD tests passes if ( not lazy_str_hard_failure and is_too_large_sequence and not is_multi_byte_decoder ): try: sequences[int(50e3) :].decode(encoding_iana, errors="strict") except UnicodeDecodeError as e: logger.log( TRACE, "LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s", encoding_iana, str(e), ) tested_but_hard_failure.append(encoding_iana) continue mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0 if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up: tested_but_soft_failure.append(encoding_iana) logger.log( TRACE, "%s was excluded because of initial chaos probing. Gave up %i time(s). " "Computed mean chaos is %f %%.", encoding_iana, early_stop_count, round(mean_mess_ratio * 100, ndigits=3), ) # Preparing those fallbacks in case we got nothing. if ( enable_fallback and encoding_iana in ["ascii", "utf_8", specified_encoding] and not lazy_str_hard_failure ): fallback_entry = CharsetMatch( sequences, encoding_iana, threshold, False, [], decoded_payload, preemptive_declaration=specified_encoding, ) if encoding_iana == specified_encoding: fallback_specified = fallback_entry elif encoding_iana == "ascii": fallback_ascii = fallback_entry else: fallback_u8 = fallback_entry continue logger.log( TRACE, "%s passed initial chaos probing. Mean measured chaos is %f %%", encoding_iana, round(mean_mess_ratio * 100, ndigits=3), ) if not is_multi_byte_decoder: target_languages: List[str] = encoding_languages(encoding_iana) else: target_languages = mb_encoding_languages(encoding_iana) if target_languages: logger.log( TRACE, "{} should target any language(s) of {}".format( encoding_iana, str(target_languages) ), ) cd_ratios = [] # We shall skip the CD when its about ASCII # Most of the time its not relevant to run "language-detection" on it. if encoding_iana != "ascii": for chunk in md_chunks: chunk_languages = coherence_ratio( chunk, language_threshold, ",".join(target_languages) if target_languages else None, ) cd_ratios.append(chunk_languages) cd_ratios_merged = merge_coherence_ratios(cd_ratios) if cd_ratios_merged: logger.log( TRACE, "We detected language {} using {}".format( cd_ratios_merged, encoding_iana ), ) current_match = CharsetMatch( sequences, encoding_iana, mean_mess_ratio, bom_or_sig_available, cd_ratios_merged, ( decoded_payload if ( is_too_large_sequence is False or encoding_iana in [specified_encoding, "ascii", "utf_8"] ) else None ), preemptive_declaration=specified_encoding, ) results.append(current_match) if ( encoding_iana in [specified_encoding, "ascii", "utf_8"] and mean_mess_ratio < 0.1 ): # If md says nothing to worry about, then... stop immediately! if mean_mess_ratio == 0.0: logger.debug( "Encoding detection: %s is most likely the one.", current_match.encoding, ) if explain: logger.removeHandler(explain_handler) logger.setLevel(previous_logger_level) return CharsetMatches([current_match]) early_stop_results.append(current_match) if ( len(early_stop_results) and (specified_encoding is None or specified_encoding in tested) and "ascii" in tested and "utf_8" in tested ): probable_result: CharsetMatch = early_stop_results.best() # type: ignore[assignment] logger.debug( "Encoding detection: %s is most likely the one.", probable_result.encoding, ) if explain: logger.removeHandler(explain_handler) logger.setLevel(previous_logger_level) return CharsetMatches([probable_result]) if encoding_iana == sig_encoding: logger.debug( "Encoding detection: %s is most likely the one as we detected a BOM or SIG within " "the beginning of the sequence.", encoding_iana, ) if explain: logger.removeHandler(explain_handler) logger.setLevel(previous_logger_level) return CharsetMatches([results[encoding_iana]]) if len(results) == 0: if fallback_u8 or fallback_ascii or fallback_specified: logger.log( TRACE, "Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.", ) if fallback_specified: logger.debug( "Encoding detection: %s will be used as a fallback match", fallback_specified.encoding, ) results.append(fallback_specified) elif ( (fallback_u8 and fallback_ascii is None) or ( fallback_u8 and fallback_ascii and fallback_u8.fingerprint != fallback_ascii.fingerprint ) or (fallback_u8 is not None) ): logger.debug("Encoding detection: utf_8 will be used as a fallback match") results.append(fallback_u8) elif fallback_ascii: logger.debug("Encoding detection: ascii will be used as a fallback match") results.append(fallback_ascii) if results: logger.debug( "Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.", results.best().encoding, # type: ignore len(results) - 1, ) else: logger.debug("Encoding detection: Unable to determine any suitable charset.") if explain: logger.removeHandler(explain_handler) logger.setLevel(previous_logger_level) return results def from_fp( fp: BinaryIO, steps: int = 5, chunk_size: int = 512, threshold: float = 0.20, cp_isolation: Optional[List[str]] = None, cp_exclusion: Optional[List[str]] = None, preemptive_behaviour: bool = True, explain: bool = False, language_threshold: float = 0.1, enable_fallback: bool = True, ) -> CharsetMatches: """ Same thing than the function from_bytes but using a file pointer that is already ready. Will not close the file pointer. """ return from_bytes( fp.read(), steps, chunk_size, threshold, cp_isolation, cp_exclusion, preemptive_behaviour, explain, language_threshold, enable_fallback, ) def from_path( path: Union[str, bytes, PathLike], # type: ignore[type-arg] steps: int = 5, chunk_size: int = 512, threshold: float = 0.20, cp_isolation: Optional[List[str]] = None, cp_exclusion: Optional[List[str]] = None, preemptive_behaviour: bool = True, explain: bool = False, language_threshold: float = 0.1, enable_fallback: bool = True, ) -> CharsetMatches: """ Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode. Can raise IOError. """ with open(path, "rb") as fp: return from_fp( fp, steps, chunk_size, threshold, cp_isolation, cp_exclusion, preemptive_behaviour, explain, language_threshold, enable_fallback, ) def is_binary( fp_or_path_or_payload: Union[PathLike, str, BinaryIO, bytes], # type: ignore[type-arg] steps: int = 5, chunk_size: int = 512, threshold: float = 0.20, cp_isolation: Optional[List[str]] = None, cp_exclusion: Optional[List[str]] = None, preemptive_behaviour: bool = True, explain: bool = False, language_threshold: float = 0.1, enable_fallback: bool = False, ) -> bool: """ Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string. Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match are disabled to be stricter around ASCII-compatible but unlikely to be a string. """ if isinstance(fp_or_path_or_payload, (str, PathLike)): guesses = from_path( fp_or_path_or_payload, steps=steps, chunk_size=chunk_size, threshold=threshold, cp_isolation=cp_isolation, cp_exclusion=cp_exclusion, preemptive_behaviour=preemptive_behaviour, explain=explain, language_threshold=language_threshold, enable_fallback=enable_fallback, ) elif isinstance( fp_or_path_or_payload, ( bytes, bytearray, ), ): guesses = from_bytes( fp_or_path_or_payload, steps=steps, chunk_size=chunk_size, threshold=threshold, cp_isolation=cp_isolation, cp_exclusion=cp_exclusion, preemptive_behaviour=preemptive_behaviour, explain=explain, language_threshold=language_threshold, enable_fallback=enable_fallback, ) else: guesses = from_fp( fp_or_path_or_payload, steps=steps, chunk_size=chunk_size, threshold=threshold, cp_isolation=cp_isolation, cp_exclusion=cp_exclusion, preemptive_behaviour=preemptive_behaviour, explain=explain, language_threshold=language_threshold, enable_fallback=enable_fallback, ) return not guesses PK -�ZAAO�3� 3� constant.pynu �[��� # -*- coding: utf-8 -*- from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE from encodings.aliases import aliases from re import IGNORECASE, compile as re_compile from typing import Dict, List, Set, Union # Contain for each eligible encoding a list of/item bytes SIG/BOM ENCODING_MARKS: Dict[str, Union[bytes, List[bytes]]] = { "utf_8": BOM_UTF8, "utf_7": [ b"\x2b\x2f\x76\x38", b"\x2b\x2f\x76\x39", b"\x2b\x2f\x76\x2b", b"\x2b\x2f\x76\x2f", b"\x2b\x2f\x76\x38\x2d", ], "gb18030": b"\x84\x31\x95\x33", "utf_32": [BOM_UTF32_BE, BOM_UTF32_LE], "utf_16": [BOM_UTF16_BE, BOM_UTF16_LE], } TOO_SMALL_SEQUENCE: int = 32 TOO_BIG_SEQUENCE: int = int(10e6) UTF8_MAXIMAL_ALLOCATION: int = 1_112_064 # Up-to-date Unicode ucd/15.0.0 UNICODE_RANGES_COMBINED: Dict[str, range] = { "Control character": range(32), "Basic Latin": range(32, 128), "Latin-1 Supplement": range(128, 256), "Latin Extended-A": range(256, 384), "Latin Extended-B": range(384, 592), "IPA Extensions": range(592, 688), "Spacing Modifier Letters": range(688, 768), "Combining Diacritical Marks": range(768, 880), "Greek and Coptic": range(880, 1024), "Cyrillic": range(1024, 1280), "Cyrillic Supplement": range(1280, 1328), "Armenian": range(1328, 1424), "Hebrew": range(1424, 1536), "Arabic": range(1536, 1792), "Syriac": range(1792, 1872), "Arabic Supplement": range(1872, 1920), "Thaana": range(1920, 1984), "NKo": range(1984, 2048), "Samaritan": range(2048, 2112), "Mandaic": range(2112, 2144), "Syriac Supplement": range(2144, 2160), "Arabic Extended-B": range(2160, 2208), "Arabic Extended-A": range(2208, 2304), "Devanagari": range(2304, 2432), "Bengali": range(2432, 2560), "Gurmukhi": range(2560, 2688), "Gujarati": range(2688, 2816), "Oriya": range(2816, 2944), "Tamil": range(2944, 3072), "Telugu": range(3072, 3200), "Kannada": range(3200, 3328), "Malayalam": range(3328, 3456), "Sinhala": range(3456, 3584), "Thai": range(3584, 3712), "Lao": range(3712, 3840), "Tibetan": range(3840, 4096), "Myanmar": range(4096, 4256), "Georgian": range(4256, 4352), "Hangul Jamo": range(4352, 4608), "Ethiopic": range(4608, 4992), "Ethiopic Supplement": range(4992, 5024), "Cherokee": range(5024, 5120), "Unified Canadian Aboriginal Syllabics": range(5120, 5760), "Ogham": range(5760, 5792), "Runic": range(5792, 5888), "Tagalog": range(5888, 5920), "Hanunoo": range(5920, 5952), "Buhid": range(5952, 5984), "Tagbanwa": range(5984, 6016), "Khmer": range(6016, 6144), "Mongolian": range(6144, 6320), "Unified Canadian Aboriginal Syllabics Extended": range(6320, 6400), "Limbu": range(6400, 6480), "Tai Le": range(6480, 6528), "New Tai Lue": range(6528, 6624), "Khmer Symbols": range(6624, 6656), "Buginese": range(6656, 6688), "Tai Tham": range(6688, 6832), "Combining Diacritical Marks Extended": range(6832, 6912), "Balinese": range(6912, 7040), "Sundanese": range(7040, 7104), "Batak": range(7104, 7168), "Lepcha": range(7168, 7248), "Ol Chiki": range(7248, 7296), "Cyrillic Extended-C": range(7296, 7312), "Georgian Extended": range(7312, 7360), "Sundanese Supplement": range(7360, 7376), "Vedic Extensions": range(7376, 7424), "Phonetic Extensions": range(7424, 7552), "Phonetic Extensions Supplement": range(7552, 7616), "Combining Diacritical Marks Supplement": range(7616, 7680), "Latin Extended Additional": range(7680, 7936), "Greek Extended": range(7936, 8192), "General Punctuation": range(8192, 8304), "Superscripts and Subscripts": range(8304, 8352), "Currency Symbols": range(8352, 8400), "Combining Diacritical Marks for Symbols": range(8400, 8448), "Letterlike Symbols": range(8448, 8528), "Number Forms": range(8528, 8592), "Arrows": range(8592, 8704), "Mathematical Operators": range(8704, 8960), "Miscellaneous Technical": range(8960, 9216), "Control Pictures": range(9216, 9280), "Optical Character Recognition": range(9280, 9312), "Enclosed Alphanumerics": range(9312, 9472), "Box Drawing": range(9472, 9600), "Block Elements": range(9600, 9632), "Geometric Shapes": range(9632, 9728), "Miscellaneous Symbols": range(9728, 9984), "Dingbats": range(9984, 10176), "Miscellaneous Mathematical Symbols-A": range(10176, 10224), "Supplemental Arrows-A": range(10224, 10240), "Braille Patterns": range(10240, 10496), "Supplemental Arrows-B": range(10496, 10624), "Miscellaneous Mathematical Symbols-B": range(10624, 10752), "Supplemental Mathematical Operators": range(10752, 11008), "Miscellaneous Symbols and Arrows": range(11008, 11264), "Glagolitic": range(11264, 11360), "Latin Extended-C": range(11360, 11392), "Coptic": range(11392, 11520), "Georgian Supplement": range(11520, 11568), "Tifinagh": range(11568, 11648), "Ethiopic Extended": range(11648, 11744), "Cyrillic Extended-A": range(11744, 11776), "Supplemental Punctuation": range(11776, 11904), "CJK Radicals Supplement": range(11904, 12032), "Kangxi Radicals": range(12032, 12256), "Ideographic Description Characters": range(12272, 12288), "CJK Symbols and Punctuation": range(12288, 12352), "Hiragana": range(12352, 12448), "Katakana": range(12448, 12544), "Bopomofo": range(12544, 12592), "Hangul Compatibility Jamo": range(12592, 12688), "Kanbun": range(12688, 12704), "Bopomofo Extended": range(12704, 12736), "CJK Strokes": range(12736, 12784), "Katakana Phonetic Extensions": range(12784, 12800), "Enclosed CJK Letters and Months": range(12800, 13056), "CJK Compatibility": range(13056, 13312), "CJK Unified Ideographs Extension A": range(13312, 19904), "Yijing Hexagram Symbols": range(19904, 19968), "CJK Unified Ideographs": range(19968, 40960), "Yi Syllables": range(40960, 42128), "Yi Radicals": range(42128, 42192), "Lisu": range(42192, 42240), "Vai": range(42240, 42560), "Cyrillic Extended-B": range(42560, 42656), "Bamum": range(42656, 42752), "Modifier Tone Letters": range(42752, 42784), "Latin Extended-D": range(42784, 43008), "Syloti Nagri": range(43008, 43056), "Common Indic Number Forms": range(43056, 43072), "Phags-pa": range(43072, 43136), "Saurashtra": range(43136, 43232), "Devanagari Extended": range(43232, 43264), "Kayah Li": range(43264, 43312), "Rejang": range(43312, 43360), "Hangul Jamo Extended-A": range(43360, 43392), "Javanese": range(43392, 43488), "Myanmar Extended-B": range(43488, 43520), "Cham": range(43520, 43616), "Myanmar Extended-A": range(43616, 43648), "Tai Viet": range(43648, 43744), "Meetei Mayek Extensions": range(43744, 43776), "Ethiopic Extended-A": range(43776, 43824), "Latin Extended-E": range(43824, 43888), "Cherokee Supplement": range(43888, 43968), "Meetei Mayek": range(43968, 44032), "Hangul Syllables": range(44032, 55216), "Hangul Jamo Extended-B": range(55216, 55296), "High Surrogates": range(55296, 56192), "High Private Use Surrogates": range(56192, 56320), "Low Surrogates": range(56320, 57344), "Private Use Area": range(57344, 63744), "CJK Compatibility Ideographs": range(63744, 64256), "Alphabetic Presentation Forms": range(64256, 64336), "Arabic Presentation Forms-A": range(64336, 65024), "Variation Selectors": range(65024, 65040), "Vertical Forms": range(65040, 65056), "Combining Half Marks": range(65056, 65072), "CJK Compatibility Forms": range(65072, 65104), "Small Form Variants": range(65104, 65136), "Arabic Presentation Forms-B": range(65136, 65280), "Halfwidth and Fullwidth Forms": range(65280, 65520), "Specials": range(65520, 65536), "Linear B Syllabary": range(65536, 65664), "Linear B Ideograms": range(65664, 65792), "Aegean Numbers": range(65792, 65856), "Ancient Greek Numbers": range(65856, 65936), "Ancient Symbols": range(65936, 66000), "Phaistos Disc": range(66000, 66048), "Lycian": range(66176, 66208), "Carian": range(66208, 66272), "Coptic Epact Numbers": range(66272, 66304), "Old Italic": range(66304, 66352), "Gothic": range(66352, 66384), "Old Permic": range(66384, 66432), "Ugaritic": range(66432, 66464), "Old Persian": range(66464, 66528), "Deseret": range(66560, 66640), "Shavian": range(66640, 66688), "Osmanya": range(66688, 66736), "Osage": range(66736, 66816), "Elbasan": range(66816, 66864), "Caucasian Albanian": range(66864, 66928), "Vithkuqi": range(66928, 67008), "Linear A": range(67072, 67456), "Latin Extended-F": range(67456, 67520), "Cypriot Syllabary": range(67584, 67648), "Imperial Aramaic": range(67648, 67680), "Palmyrene": range(67680, 67712), "Nabataean": range(67712, 67760), "Hatran": range(67808, 67840), "Phoenician": range(67840, 67872), "Lydian": range(67872, 67904), "Meroitic Hieroglyphs": range(67968, 68000), "Meroitic Cursive": range(68000, 68096), "Kharoshthi": range(68096, 68192), "Old South Arabian": range(68192, 68224), "Old North Arabian": range(68224, 68256), "Manichaean": range(68288, 68352), "Avestan": range(68352, 68416), "Inscriptional Parthian": range(68416, 68448), "Inscriptional Pahlavi": range(68448, 68480), "Psalter Pahlavi": range(68480, 68528), "Old Turkic": range(68608, 68688), "Old Hungarian": range(68736, 68864), "Hanifi Rohingya": range(68864, 68928), "Rumi Numeral Symbols": range(69216, 69248), "Yezidi": range(69248, 69312), "Arabic Extended-C": range(69312, 69376), "Old Sogdian": range(69376, 69424), "Sogdian": range(69424, 69488), "Old Uyghur": range(69488, 69552), "Chorasmian": range(69552, 69600), "Elymaic": range(69600, 69632), "Brahmi": range(69632, 69760), "Kaithi": range(69760, 69840), "Sora Sompeng": range(69840, 69888), "Chakma": range(69888, 69968), "Mahajani": range(69968, 70016), "Sharada": range(70016, 70112), "Sinhala Archaic Numbers": range(70112, 70144), "Khojki": range(70144, 70224), "Multani": range(70272, 70320), "Khudawadi": range(70320, 70400), "Grantha": range(70400, 70528), "Newa": range(70656, 70784), "Tirhuta": range(70784, 70880), "Siddham": range(71040, 71168), "Modi": range(71168, 71264), "Mongolian Supplement": range(71264, 71296), "Takri": range(71296, 71376), "Ahom": range(71424, 71504), "Dogra": range(71680, 71760), "Warang Citi": range(71840, 71936), "Dives Akuru": range(71936, 72032), "Nandinagari": range(72096, 72192), "Zanabazar Square": range(72192, 72272), "Soyombo": range(72272, 72368), "Unified Canadian Aboriginal Syllabics Extended-A": range(72368, 72384), "Pau Cin Hau": range(72384, 72448), "Devanagari Extended-A": range(72448, 72544), "Bhaiksuki": range(72704, 72816), "Marchen": range(72816, 72896), "Masaram Gondi": range(72960, 73056), "Gunjala Gondi": range(73056, 73136), "Makasar": range(73440, 73472), "Kawi": range(73472, 73568), "Lisu Supplement": range(73648, 73664), "Tamil Supplement": range(73664, 73728), "Cuneiform": range(73728, 74752), "Cuneiform Numbers and Punctuation": range(74752, 74880), "Early Dynastic Cuneiform": range(74880, 75088), "Cypro-Minoan": range(77712, 77824), "Egyptian Hieroglyphs": range(77824, 78896), "Egyptian Hieroglyph Format Controls": range(78896, 78944), "Anatolian Hieroglyphs": range(82944, 83584), "Bamum Supplement": range(92160, 92736), "Mro": range(92736, 92784), "Tangsa": range(92784, 92880), "Bassa Vah": range(92880, 92928), "Pahawh Hmong": range(92928, 93072), "Medefaidrin": range(93760, 93856), "Miao": range(93952, 94112), "Ideographic Symbols and Punctuation": range(94176, 94208), "Tangut": range(94208, 100352), "Tangut Components": range(100352, 101120), "Khitan Small Script": range(101120, 101632), "Tangut Supplement": range(101632, 101760), "Kana Extended-B": range(110576, 110592), "Kana Supplement": range(110592, 110848), "Kana Extended-A": range(110848, 110896), "Small Kana Extension": range(110896, 110960), "Nushu": range(110960, 111360), "Duployan": range(113664, 113824), "Shorthand Format Controls": range(113824, 113840), "Znamenny Musical Notation": range(118528, 118736), "Byzantine Musical Symbols": range(118784, 119040), "Musical Symbols": range(119040, 119296), "Ancient Greek Musical Notation": range(119296, 119376), "Kaktovik Numerals": range(119488, 119520), "Mayan Numerals": range(119520, 119552), "Tai Xuan Jing Symbols": range(119552, 119648), "Counting Rod Numerals": range(119648, 119680), "Mathematical Alphanumeric Symbols": range(119808, 120832), "Sutton SignWriting": range(120832, 121520), "Latin Extended-G": range(122624, 122880), "Glagolitic Supplement": range(122880, 122928), "Cyrillic Extended-D": range(122928, 123024), "Nyiakeng Puachue Hmong": range(123136, 123216), "Toto": range(123536, 123584), "Wancho": range(123584, 123648), "Nag Mundari": range(124112, 124160), "Ethiopic Extended-B": range(124896, 124928), "Mende Kikakui": range(124928, 125152), "Adlam": range(125184, 125280), "Indic Siyaq Numbers": range(126064, 126144), "Ottoman Siyaq Numbers": range(126208, 126288), "Arabic Mathematical Alphabetic Symbols": range(126464, 126720), "Mahjong Tiles": range(126976, 127024), "Domino Tiles": range(127024, 127136), "Playing Cards": range(127136, 127232), "Enclosed Alphanumeric Supplement": range(127232, 127488), "Enclosed Ideographic Supplement": range(127488, 127744), "Miscellaneous Symbols and Pictographs": range(127744, 128512), "Emoticons range(Emoji)": range(128512, 128592), "Ornamental Dingbats": range(128592, 128640), "Transport and Map Symbols": range(128640, 128768), "Alchemical Symbols": range(128768, 128896), "Geometric Shapes Extended": range(128896, 129024), "Supplemental Arrows-C": range(129024, 129280), "Supplemental Symbols and Pictographs": range(129280, 129536), "Chess Symbols": range(129536, 129648), "Symbols and Pictographs Extended-A": range(129648, 129792), "Symbols for Legacy Computing": range(129792, 130048), "CJK Unified Ideographs Extension B": range(131072, 173792), "CJK Unified Ideographs Extension C": range(173824, 177984), "CJK Unified Ideographs Extension D": range(177984, 178208), "CJK Unified Ideographs Extension E": range(178208, 183984), "CJK Unified Ideographs Extension F": range(183984, 191472), "CJK Compatibility Ideographs Supplement": range(194560, 195104), "CJK Unified Ideographs Extension G": range(196608, 201552), "CJK Unified Ideographs Extension H": range(201552, 205744), "Tags": range(917504, 917632), "Variation Selectors Supplement": range(917760, 918000), "Supplementary Private Use Area-A": range(983040, 1048576), "Supplementary Private Use Area-B": range(1048576, 1114112), } UNICODE_SECONDARY_RANGE_KEYWORD: List[str] = [ "Supplement", "Extended", "Extensions", "Modifier", "Marks", "Punctuation", "Symbols", "Forms", "Operators", "Miscellaneous", "Drawing", "Block", "Shapes", "Supplemental", "Tags", ] RE_POSSIBLE_ENCODING_INDICATION = re_compile( r"(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)", IGNORECASE, ) IANA_NO_ALIASES = [ "cp720", "cp737", "cp856", "cp874", "cp875", "cp1006", "koi8_r", "koi8_t", "koi8_u", ] IANA_SUPPORTED: List[str] = sorted( filter( lambda x: x.endswith("_codec") is False and x not in {"rot_13", "tactis", "mbcs"}, list(set(aliases.values())) + IANA_NO_ALIASES, ) ) IANA_SUPPORTED_COUNT: int = len(IANA_SUPPORTED) # pre-computed code page that are similar using the function cp_similarity. IANA_SUPPORTED_SIMILAR: Dict[str, List[str]] = { "cp037": ["cp1026", "cp1140", "cp273", "cp500"], "cp1026": ["cp037", "cp1140", "cp273", "cp500"], "cp1125": ["cp866"], "cp1140": ["cp037", "cp1026", "cp273", "cp500"], "cp1250": ["iso8859_2"], "cp1251": ["kz1048", "ptcp154"], "cp1252": ["iso8859_15", "iso8859_9", "latin_1"], "cp1253": ["iso8859_7"], "cp1254": ["iso8859_15", "iso8859_9", "latin_1"], "cp1257": ["iso8859_13"], "cp273": ["cp037", "cp1026", "cp1140", "cp500"], "cp437": ["cp850", "cp858", "cp860", "cp861", "cp862", "cp863", "cp865"], "cp500": ["cp037", "cp1026", "cp1140", "cp273"], "cp850": ["cp437", "cp857", "cp858", "cp865"], "cp857": ["cp850", "cp858", "cp865"], "cp858": ["cp437", "cp850", "cp857", "cp865"], "cp860": ["cp437", "cp861", "cp862", "cp863", "cp865"], "cp861": ["cp437", "cp860", "cp862", "cp863", "cp865"], "cp862": ["cp437", "cp860", "cp861", "cp863", "cp865"], "cp863": ["cp437", "cp860", "cp861", "cp862", "cp865"], "cp865": ["cp437", "cp850", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863"], "cp866": ["cp1125"], "iso8859_10": ["iso8859_14", "iso8859_15", "iso8859_4", "iso8859_9", "latin_1"], "iso8859_11": ["tis_620"], "iso8859_13": ["cp1257"], "iso8859_14": [ "iso8859_10", "iso8859_15", "iso8859_16", "iso8859_3", "iso8859_9", "latin_1", ], "iso8859_15": [ "cp1252", "cp1254", "iso8859_10", "iso8859_14", "iso8859_16", "iso8859_3", "iso8859_9", "latin_1", ], "iso8859_16": [ "iso8859_14", "iso8859_15", "iso8859_2", "iso8859_3", "iso8859_9", "latin_1", ], "iso8859_2": ["cp1250", "iso8859_16", "iso8859_4"], "iso8859_3": ["iso8859_14", "iso8859_15", "iso8859_16", "iso8859_9", "latin_1"], "iso8859_4": ["iso8859_10", "iso8859_2", "iso8859_9", "latin_1"], "iso8859_7": ["cp1253"], "iso8859_9": [ "cp1252", "cp1254", "cp1258", "iso8859_10", "iso8859_14", "iso8859_15", "iso8859_16", "iso8859_3", "iso8859_4", "latin_1", ], "kz1048": ["cp1251", "ptcp154"], "latin_1": [ "cp1252", "cp1254", "cp1258", "iso8859_10", "iso8859_14", "iso8859_15", "iso8859_16", "iso8859_3", "iso8859_4", "iso8859_9", ], "mac_iceland": ["mac_roman", "mac_turkish"], "mac_roman": ["mac_iceland", "mac_turkish"], "mac_turkish": ["mac_iceland", "mac_roman"], "ptcp154": ["cp1251", "kz1048"], "tis_620": ["iso8859_11"], } CHARDET_CORRESPONDENCE: Dict[str, str] = { "iso2022_kr": "ISO-2022-KR", "iso2022_jp": "ISO-2022-JP", "euc_kr": "EUC-KR", "tis_620": "TIS-620", "utf_32": "UTF-32", "euc_jp": "EUC-JP", "koi8_r": "KOI8-R", "iso8859_1": "ISO-8859-1", "iso8859_2": "ISO-8859-2", "iso8859_5": "ISO-8859-5", "iso8859_6": "ISO-8859-6", "iso8859_7": "ISO-8859-7", "iso8859_8": "ISO-8859-8", "utf_16": "UTF-16", "cp855": "IBM855", "mac_cyrillic": "MacCyrillic", "gb2312": "GB2312", "gb18030": "GB18030", "cp932": "CP932", "cp866": "IBM866", "utf_8": "utf-8", "utf_8_sig": "UTF-8-SIG", "shift_jis": "SHIFT_JIS", "big5": "Big5", "cp1250": "windows-1250", "cp1251": "windows-1251", "cp1252": "Windows-1252", "cp1253": "windows-1253", "cp1255": "windows-1255", "cp1256": "windows-1256", "cp1254": "Windows-1254", "cp949": "CP949", } COMMON_SAFE_ASCII_CHARACTERS: Set[str] = { "<", ">", "=", ":", "/", "&", ";", "{", "}", "[", "]", ",", "|", '"', "-", "(", ")", } KO_NAMES: Set[str] = {"johab", "cp949", "euc_kr"} ZH_NAMES: Set[str] = {"big5", "cp950", "big5hkscs", "hz"} # Logging LEVEL below DEBUG TRACE: int = 5 # Language label that contain the em dash "—" # character are to be considered alternative seq to origin FREQUENCIES: Dict[str, List[str]] = { "English": [ "e", "a", "t", "i", "o", "n", "s", "r", "h", "l", "d", "c", "u", "m", "f", "p", "g", "w", "y", "b", "v", "k", "x", "j", "z", "q", ], "English—": [ "e", "a", "t", "i", "o", "n", "s", "r", "h", "l", "d", "c", "m", "u", "f", "p", "g", "w", "b", "y", "v", "k", "j", "x", "z", "q", ], "German": [ "e", "n", "i", "r", "s", "t", "a", "d", "h", "u", "l", "g", "o", "c", "m", "b", "f", "k", "w", "z", "p", "v", "ü", "ä", "ö", "j", ], "French": [ "e", "a", "s", "n", "i", "t", "r", "l", "u", "o", "d", "c", "p", "m", "é", "v", "g", "f", "b", "h", "q", "à", "x", "è", "y", "j", ], "Dutch": [ "e", "n", "a", "i", "r", "t", "o", "d", "s", "l", "g", "h", "v", "m", "u", "k", "c", "p", "b", "w", "j", "z", "f", "y", "x", "ë", ], "Italian": [ "e", "i", "a", "o", "n", "l", "t", "r", "s", "c", "d", "u", "p", "m", "g", "v", "f", "b", "z", "h", "q", "è", "à", "k", "y", "ò", ], "Polish": [ "a", "i", "o", "e", "n", "r", "z", "w", "s", "c", "t", "k", "y", "d", "p", "m", "u", "l", "j", "ł", "g", "b", "h", "ą", "ę", "ó", ], "Spanish": [ "e", "a", "o", "n", "s", "r", "i", "l", "d", "t", "c", "u", "m", "p", "b", "g", "v", "f", "y", "ó", "h", "q", "í", "j", "z", "á", ], "Russian": [ "о", "а", "е", "и", "н", "с", "т", "р", "в", "л", "к", "м", "д", "п", "у", "г", "я", "ы", "з", "б", "й", "ь", "ч", "х", "ж", "ц", ], # Jap-Kanji "Japanese": [ "人", "一", "大", "亅", "丁", "丨", "竹", "笑", "口", "日", "今", "二", "彳", "行", "十", "土", "丶", "寸", "寺", "時", "乙", "丿", "乂", "气", "気", "冂", "巾", "亠", "市", "目", "儿", "見", "八", "小", "凵", "県", "月", "彐", "門", "間", "木", "東", "山", "出", "本", "中", "刀", "分", "耳", "又", "取", "最", "言", "田", "心", "思", "刂", "前", "京", "尹", "事", "生", "厶", "云", "会", "未", "来", "白", "冫", "楽", "灬", "馬", "尸", "尺", "駅", "明", "耂", "者", "了", "阝", "都", "高", "卜", "占", "厂", "广", "店", "子", "申", "奄", "亻", "俺", "上", "方", "冖", "学", "衣", "艮", "食", "自", ], # Jap-Katakana "Japanese—": [ "ー", "ン", "ス", "・", "ル", "ト", "リ", "イ", "ア", "ラ", "ッ", "ク", "ド", "シ", "レ", "ジ", "タ", "フ", "ロ", "カ", "テ", "マ", "ィ", "グ", "バ", "ム", "プ", "オ", "コ", "デ", "ニ", "ウ", "メ", "サ", "ビ", "ナ", "ブ", "ャ", "エ", "ュ", "チ", "キ", "ズ", "ダ", "パ", "ミ", "ェ", "ョ", "ハ", "セ", "ベ", "ガ", "モ", "ツ", "ネ", "ボ", "ソ", "ノ", "ァ", "ヴ", "ワ", "ポ", "ペ", "ピ", "ケ", "ゴ", "ギ", "ザ", "ホ", "ゲ", "ォ", "ヤ", "ヒ", "ユ", "ヨ", "ヘ", "ゼ", "ヌ", "ゥ", "ゾ", "ヶ", "ヂ", "ヲ", "ヅ", "ヵ", "ヱ", "ヰ", "ヮ", "ヽ", "゠", "ヾ", "ヷ", "ヿ", "ヸ", "ヹ", "ヺ", ], # Jap-Hiragana "Japanese——": [ "の", "に", "る", "た", "と", "は", "し", "い", "を", "で", "て", "が", "な", "れ", "か", "ら", "さ", "っ", "り", "す", "あ", "も", "こ", "ま", "う", "く", "よ", "き", "ん", "め", "お", "け", "そ", "つ", "だ", "や", "え", "ど", "わ", "ち", "み", "せ", "じ", "ば", "へ", "び", "ず", "ろ", "ほ", "げ", "む", "べ", "ひ", "ょ", "ゆ", "ぶ", "ご", "ゃ", "ね", "ふ", "ぐ", "ぎ", "ぼ", "ゅ", "づ", "ざ", "ぞ", "ぬ", "ぜ", "ぱ", "ぽ", "ぷ", "ぴ", "ぃ", "ぁ", "ぇ", "ぺ", "ゞ", "ぢ", "ぉ", "ぅ", "ゐ", "ゝ", "ゑ", "゛", "゜", "ゎ", "ゔ", "゚", "ゟ", "゙", "ゕ", "ゖ", ], "Portuguese": [ "a", "e", "o", "s", "i", "r", "d", "n", "t", "m", "u", "c", "l", "p", "g", "v", "b", "f", "h", "ã", "q", "é", "ç", "á", "z", "í", ], "Swedish": [ "e", "a", "n", "r", "t", "s", "i", "l", "d", "o", "m", "k", "g", "v", "h", "f", "u", "p", "ä", "c", "b", "ö", "å", "y", "j", "x", ], "Chinese": [ "的", "一", "是", "不", "了", "在", "人", "有", "我", "他", "这", "个", "们", "中", "来", "上", "大", "为", "和", "国", "地", "到", "以", "说", "时", "要", "就", "出", "会", "可", "也", "你", "对", "生", "能", "而", "子", "那", "得", "于", "着", "下", "自", "之", "年", "过", "发", "后", "作", "里", "用", "道", "行", "所", "然", "家", "种", "事", "成", "方", "多", "经", "么", "去", "法", "学", "如", "都", "同", "现", "当", "没", "动", "面", "起", "看", "定", "天", "分", "还", "进", "好", "小", "部", "其", "些", "主", "样", "理", "心", "她", "本", "前", "开", "但", "因", "只", "从", "想", "实", ], "Ukrainian": [ "о", "а", "н", "і", "и", "р", "в", "т", "е", "с", "к", "л", "у", "д", "м", "п", "з", "я", "ь", "б", "г", "й", "ч", "х", "ц", "ї", ], "Norwegian": [ "e", "r", "n", "t", "a", "s", "i", "o", "l", "d", "g", "k", "m", "v", "f", "p", "u", "b", "h", "å", "y", "j", "ø", "c", "æ", "w", ], "Finnish": [ "a", "i", "n", "t", "e", "s", "l", "o", "u", "k", "ä", "m", "r", "v", "j", "h", "p", "y", "d", "ö", "g", "c", "b", "f", "w", "z", ], "Vietnamese": [ "n", "h", "t", "i", "c", "g", "a", "o", "u", "m", "l", "r", "à", "đ", "s", "e", "v", "p", "b", "y", "ư", "d", "á", "k", "ộ", "ế", ], "Czech": [ "o", "e", "a", "n", "t", "s", "i", "l", "v", "r", "k", "d", "u", "m", "p", "í", "c", "h", "z", "á", "y", "j", "b", "ě", "é", "ř", ], "Hungarian": [ "e", "a", "t", "l", "s", "n", "k", "r", "i", "o", "z", "á", "é", "g", "m", "b", "y", "v", "d", "h", "u", "p", "j", "ö", "f", "c", ], "Korean": [ "이", "다", "에", "의", "는", "로", "하", "을", "가", "고", "지", "서", "한", "은", "기", "으", "년", "대", "사", "시", "를", "리", "도", "인", "스", "일", ], "Indonesian": [ "a", "n", "e", "i", "r", "t", "u", "s", "d", "k", "m", "l", "g", "p", "b", "o", "h", "y", "j", "c", "w", "f", "v", "z", "x", "q", ], "Turkish": [ "a", "e", "i", "n", "r", "l", "ı", "k", "d", "t", "s", "m", "y", "u", "o", "b", "ü", "ş", "v", "g", "z", "h", "c", "p", "ç", "ğ", ], "Romanian": [ "e", "i", "a", "r", "n", "t", "u", "l", "o", "c", "s", "d", "p", "m", "ă", "f", "v", "î", "g", "b", "ș", "ț", "z", "h", "â", "j", ], "Farsi": [ "ا", "ی", "ر", "د", "ن", "ه", "و", "م", "ت", "ب", "س", "ل", "ک", "ش", "ز", "ف", "گ", "ع", "خ", "ق", "ج", "آ", "پ", "ح", "ط", "ص", ], "Arabic": [ "ا", "ل", "ي", "م", "و", "ن", "ر", "ت", "ب", "ة", "ع", "د", "س", "ف", "ه", "ك", "ق", "أ", "ح", "ج", "ش", "ط", "ص", "ى", "خ", "إ", ], "Danish": [ "e", "r", "n", "t", "a", "i", "s", "d", "l", "o", "g", "m", "k", "f", "v", "u", "b", "h", "p", "å", "y", "ø", "æ", "c", "j", "w", ], "Serbian": [ "а", "и", "о", "е", "н", "р", "с", "у", "т", "к", "ј", "в", "д", "м", "п", "л", "г", "з", "б", "a", "i", "e", "o", "n", "ц", "ш", ], "Lithuanian": [ "i", "a", "s", "o", "r", "e", "t", "n", "u", "k", "m", "l", "p", "v", "d", "j", "g", "ė", "b", "y", "ų", "š", "ž", "c", "ą", "į", ], "Slovene": [ "e", "a", "i", "o", "n", "r", "s", "l", "t", "j", "v", "k", "d", "p", "m", "u", "z", "b", "g", "h", "č", "c", "š", "ž", "f", "y", ], "Slovak": [ "o", "a", "e", "n", "i", "r", "v", "t", "s", "l", "k", "d", "m", "p", "u", "c", "h", "j", "b", "z", "á", "y", "ý", "í", "č", "é", ], "Hebrew": [ "י", "ו", "ה", "ל", "ר", "ב", "ת", "מ", "א", "ש", "נ", "ע", "ם", "ד", "ק", "ח", "פ", "ס", "כ", "ג", "ט", "צ", "ן", "ז", "ך", ], "Bulgarian": [ "а", "и", "о", "е", "н", "т", "р", "с", "в", "л", "к", "д", "п", "м", "з", "г", "я", "ъ", "у", "б", "ч", "ц", "й", "ж", "щ", "х", ], "Croatian": [ "a", "i", "o", "e", "n", "r", "j", "s", "t", "u", "k", "l", "v", "d", "m", "p", "g", "z", "b", "c", "č", "h", "š", "ž", "ć", "f", ], "Hindi": [ "क", "र", "स", "न", "त", "म", "ह", "प", "य", "ल", "व", "ज", "द", "ग", "ब", "श", "ट", "अ", "ए", "थ", "भ", "ड", "च", "ध", "ष", "इ", ], "Estonian": [ "a", "i", "e", "s", "t", "l", "u", "n", "o", "k", "r", "d", "m", "v", "g", "p", "j", "h", "ä", "b", "õ", "ü", "f", "c", "ö", "y", ], "Thai": [ "า", "น", "ร", "อ", "ก", "เ", "ง", "ม", "ย", "ล", "ว", "ด", "ท", "ส", "ต", "ะ", "ป", "บ", "ค", "ห", "แ", "จ", "พ", "ช", "ข", "ใ", ], "Greek": [ "α", "τ", "ο", "ι", "ε", "ν", "ρ", "σ", "κ", "η", "π", "ς", "υ", "μ", "λ", "ί", "ό", "ά", "γ", "έ", "δ", "ή", "ω", "χ", "θ", "ύ", ], "Tamil": [ "க", "த", "ப", "ட", "ர", "ம", "ல", "ன", "வ", "ற", "ய", "ள", "ச", "ந", "இ", "ண", "அ", "ஆ", "ழ", "ங", "எ", "உ", "ஒ", "ஸ", ], "Kazakh": [ "а", "ы", "е", "н", "т", "р", "л", "і", "д", "с", "м", "қ", "к", "о", "б", "и", "у", "ғ", "ж", "ң", "з", "ш", "й", "п", "г", "ө", ], } LANGUAGE_SUPPORTED_COUNT: int = len(FREQUENCIES) PK -�Z>9^+�. �. ! __pycache__/models.cpython-39.pycnu �[��� PK -�Zv����- �- �. __pycache__/api.cpython-39.pycnu �[��� PK -�Z33�@ # ] __pycache__/__init__.cpython-39.pycnu �[��� PK -�Zʑ���A �A �c __pycache__/md.cpython-39.pycnu �[��� PK -�ZvُУ% �% �� __pycache__/cd.cpython-39.pycnu �[��� PK -�Z!�b �b # s� __pycache__/constant.cpython-39.pycnu �[��� PK -�Z���;W W ! b. __pycache__/legacy.cpython-39.pycnu �[��� PK -�Z��Ō� � " 7 __pycache__/version.cpython-39.pycnu �[��� PK -�Z����# �# T8 __pycache__/utils.cpython-39.pycnu �[��� PK -�Z d\ py.typednu �[��� PK -�Zb��ݪN �N �\ md.pynu �[��� PK -�Z�I��I I {� __main__.pynu �[��� PK -�ZB'�0 �0 �� models.pynu �[��� PK -�Z%��1 1 �� cd.pynu �[��� PK -�Z !?FO O version.pynu �[��� PK -�Z����v. v. � utils.pynu �[��� PK -�Z ^� == legacy.pynu �[��� PK -�ZJO3��( �( �F cli/__main__.pynu �[��� PK -�Z�P��d d wo cli/__init__.pynu �[��� PK -�Z��D) ) p __init__.pynu �[��� PK -�ZH�Y X X ~v api.pynu �[��� PK -�ZAAO�3� 3� �� constant.pynu �[��� PK Am
| ver. 1.4 |
Github
|
.
| PHP 8.2.28 | Generation time: 0.02 |
proxy
|
phpinfo
|
Settings