File: //opt/alt/python37/lib/python3.7/site-packages/charset_normalizer/__pycache__/utils.cpython-37.pyc
B
�b\$ � @ s, y d dl ZW n ek
r( d dlZY nX d dlZd dlZd dlmZ d dlmZ d dl m
Z
d dl m Z d dl
mZmZmZmZmZ d dlmZ dd lmZmZmZmZmZmZ e
ed
�e e d �d d
��Z e
ed
�e e d �dd��Z e
ed
�e ee d �dd��Z e
ed
�e e d �dd��Z!e e d �dd�Z"e
ed
�e e d �dd��Z#e
ed
�e e d �dd��Z$e
ed
�e e d �dd��Z%e
ed
�e e d �d d ��Z&e
ed
�e e d �d d ��Z'e e d �d d!�Z(e
ed
�e e d �d"d#��Z)e
ed
�e e d �d$d%��Z*e
ed
�e e d �d&d'��Z+e
ed
�e e d �d(d)��Z,e
ed
�e e d �d*d+��Z-e
e.e�d
�e e d,�d-d.��Z/dNe0e1ee d0�d1d2�Z2e
d3d
�e e d4�d5d6��Z3e0eee e0f d7�d8d9�Z4e e d:�d;d<�Z5dOe e e d>�d?d@�Z6e ee dA�dBdC�Z7e e e8dD�dEdF�Z9e e e dD�dGdH�Z:dIej;dJfe e1e ddK�dLdM�Z<dS )P� N)�IncrementalDecoder)�aliases)� lru_cache)�findall)�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 sT yt �| �}W n tk
r" dS X d|kpRd|kpRd|kpRd|kpRd|kpRd|kS )NFz
WITH GRAVEz
WITH ACUTEz WITH CEDILLAzWITH DIAERESISzWITH CIRCUMFLEXz
WITH TILDE)� unicodedata�name�
ValueError)r � description� r �I/opt/alt/python37/lib/python3.7/site-packages/charset_normalizer/utils.py�is_accentuated s r c C s. t �| �}|s| S |�d�}tt|d d��S )N� r � )r Z
decomposition�split�chr�int)r Z
decomposed�codesr r r �
remove_accent* s
r# c C s. t | �}x t�� D ]\}}||kr|S qW dS )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_range5 s
r' c C s, yt �| �}W n tk
r" dS X d|kS )NFZLATIN)r r r )r r r r r �is_latinC s
r( c C s( y| � d� W n tk
r" dS X dS )N�asciiFT)�encode�UnicodeEncodeError)r r r r �is_asciiL s
r, c C s2 t �| �}d|krdS t| �}|d kr*dS d|kS )N�PTFZ Punctuation)r �categoryr' )r �character_category�character_ranger r r �is_punctuationT s
r1 c C s: t �| �}d|ksd|kr dS t| �}|d kr2dS d|kS )N�S�NTFZForms)r r. r' )r r/ r0 r r r � is_symbolc s
r4 c C s t | �}|d krdS d|kS )NFZ Emoticons)r' )r r0 r r r � is_emoticonr s r5 c C s& | � � s| dkrdS t�| �}d|kS )N> �<� ｜�>�;�+�,T�Z)�isspacer r. )r r/ r r r � is_separator| s
r> c C s | � � | �� kS )N)�islower�isupper)r r r r �is_case_variable� s rA c C s t �| �}|dkS )NZCo)r r. )r r/ r r r �is_private_use_only� s
rB c C s, yt �| �}W n tk
r" dS X d|kS )NFZCJK)r r r )r �character_namer r r �is_cjk� s
rD c C s, yt �| �}W n tk
r" dS X d|kS )NFZHIRAGANA)r r r )r rC r r r � is_hiragana� s
rE c C s, yt �| �}W n tk
r" dS X d|kS )NFZKATAKANA)r r r )r rC r r r � is_katakana� s
rF c C s, yt �| �}W n tk
r" dS X d|kS )NFZHANGUL)r r r )r rC r r r � is_hangul� s
rG c C s, yt �| �}W n tk
r" dS X d|kS )NFZTHAI)r r r )r rC r r r �is_thai� s
rH )r& r c s t � fdd�tD ��S )Nc 3 s | ]}|� kV qd S )Nr )�.0�keyword)r& r r � <genexpr>� s z-is_unicode_range_secondary.<locals>.<genexpr>)�anyr )r& r )r& r �is_unicode_range_secondary� s rM � )�sequence� search_zoner c C s� t | t�st�t| �}tt| dt||�� jddd��}t|�dkrHdS xJ|D ]B}|�� � dd�}x,t
� � D ] \}}||kr�|S ||krl|S qlW qNW dS )zW
Extract using ASCII-only decoder any specified encoding in the first n-bytes.
Nr) �ignore)�errorsr �-�_) �
isinstance�bytes� TypeError�lenr r �min�decode�lower�replacer r% )rO rP Zseq_len�resultsZspecified_encoding�encoding_alias�
encoding_ianar r r �any_specified_encoding� s
r` � )r r c C s | dkp t t�d�| ��jt�S )zQ
Verify is a specific encoding is a multi byte one based on it IANA name
> �utf_8� utf_32_be�utf_16� utf_32_le�utf_7� utf_8_sig�utf_32� utf_16_le� utf_16_bez encodings.{})�
issubclass� importlib�
import_module�formatr r )r r r r �is_multi_byte_encoding� s
ro )rO r c C sJ xDt D ]<}t | }t|t�r"|g}x |D ]}| �|�r(||fS q(W qW dS )z9
Identify and extract SIG/BOM in given sequence.
)N� )r
rU rV �
startswith)rO �
iana_encodingZmarksZmarkr r r �identify_sig_or_bom� s
rs )rr r c C s | dkS )N> rh rd r )rr r r r �should_strip_sig_or_bom s rt T)�cp_name�strictr c C sL | � � �dd�} x$t�� D ]\}}| ||gkr|S qW |rHtd�| ���| S )NrS rT z Unable to retrieve IANA for '{}')r[ r\ r r% r rn )ru rv r^ r_ r r r � iana_name s rw )�decoded_sequencer c C s8 t � }x(| D ] }t|�}|d kr"q |�|� q W t|�S )N)�setr' �add�list)rx Zrangesr r0 r r r �
range_scan s
r| )� iana_name_a� iana_name_br c C s� t | �st |�rdS t�d�| ��j}t�d�|��j}|dd�}|dd�}d}x6td�D ]*}t|g�}|�|�|�|�krZ|d7 }qZW |d S ) Ng z encodings.{}rQ )rR r � r � )ro rl rm rn r �rangerV rZ ) r} r~ Z decoder_aZ decoder_bZid_aZid_bZcharacter_match_count�iZ
to_be_decodedr r r �
cp_similarity+ s
r� c C s | t ko|t | kS )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_similar@ s r� �charset_normalizerz)%(asctime)s | %(levelname)s | %(message)s)r �level�
format_stringr c C s: t �| �}|�|� t �� }|�t �|�� |�|� d S )N)�logging� getLogger�setLevel�
StreamHandler� setFormatter� Formatter�
addHandler)r r� r� �logger�handlerr r r �set_logging_handlerK s
r� )rN )T)=� unicodedata2r � ImportErrorrl r� �codecsr Zencodings.aliasesr � functoolsr �rer �typingr r r r r
Z_multibytecodecr Zconstantr
r r r r r �str�boolr r# r' r( r, r1 r4 r5 r> rA rB rD rE rF rG rH rX rM rV r! r` ro rs rt rw r| �floatr� r� �INFOr� r r r r �<module> sr