$13 GRAYBYTE WORDPRESS FILE MANAGER $41

�

q�;f���>�dd
lZdd
l
Z
ddlmZ
Gd�de��Zd
S)�N�
)
�ProbingStatec��eZ
dZd
Zdd�
Zd�Zed���Zd�Zed���Z	d�Z
ed	���Zed
���Z
ed���ZdS)
�
CharSetProbergffffff�?Nc�^�d|_|
|_
tjt�
�
|_dS�
N)�_state�lang_filter�logging�	getLogger�__name__�logger)�selfr
s  �H/opt/alt/python311/lib/python3.11/site-packages/chardet/charsetprober.py�__init__zCharSetProber.__init__'s'�����&����'��1�1�����c
�(�tj
|_dSr)r�	DETECTINGr	�
rs
 r�resetzCharSetProber.reset,s��"�,����rc

��dSr�rs
 r�charset_namezCharSetProber.charset_name/s���trc
��dSrr)r�bufs  r�feedzCharSetProber.feed3s���rc

��|jSr)
r	rs
 r�statezCharSetProber.state6s
���{�rc

��d
S)Ngrrs
 r�get_confidencezCharSetProber.get_confidence:s���src
�2�t
j
d
d|��}|S)Ns([-])+�
 )�re�sub)
rs
 r�filter_high_byte_onlyz#CharSetProber.filter_high_byte_only=s���f�&��c�2�2���
rc
�
�t
��}
tjd
|��}|D]Z}|
�|dd��
�

|dd�}|���s|dkrd}|
�|�
�

�[|
S)u9
        We define three types of bytes:
        alphabet: english alphabets [a-zA-Z]
        international: international characters [€-ÿ]
        marker: everything else [^a-zA-Z€-ÿ]

        The input buffer can be thought to contain a series of words delimited
        by markers. This function works to filter all words that contain at
        least one international character. All contiguous sequences of markers
        are replaced by a single space ascii character.

        This filter applies to all scripts which do not use English characters.
        s%[a-zA-Z]*[�-�]+[a-zA-Z]*[^a-zA-Z�-�]?N����
�r")�	bytearrayr#�findall�extend�isalpha)r�filtered�words�word�	last_chars     r�filter_international_wordsz(CharSetProber.filter_international_wordsBs����;�;��
�
�O��
 �
 ���
	'�
	'�D��O�O�D��"��I�&�&�&��R�S�S�	�I��$�$�&�&�

!�9�w�+>�+>� �	��O�O�I�&�&�&�&��rc
�
�t
��}
d
}d}tt|�
�
�
�
D]y}|||dz�}|dkrd
}n|dkrd}|dkrS|���s?||kr4|s2|
�|||��
�

|
�d�
�

|dz}�z|s|
�||d	��
�

|
S)
a�

        Returns a copy of ``buf`` that retains only the sequences of English
        alphabet and high byte characters that are not between <> characters.
        Also retains English alphabet and high byte characters immediately
        before occurrences of >.

        This filter can be applied to all scripts which contain both English
        characters and extended ASCII characters, but is currently only used by
        ``Latin1Prober``.
        Frr�
>�
<Tr(r"N)r)�range�lenr,r+)rr-�in_tag�prev�curr�buf_chars      r�filter_with_english_lettersz)CharSetProber.filter_with_english_lettersgs����;�;�������#�c�(�(�O�O�	 �	 �D��4��q��=�)�H��4�������T�!�!����'�!�!�(�*:�*:�*<�*<�!��$�;�;�v�;��O�O�C��T�	�N�3�3�3��O�O�D�)�)�)��a�x����	(�
�O�O�C����J�'�'�'��rr)r
�
__module__�__qualname__�SHORTCUT_THRESHOLDrr�propertyrrrr �staticmethodr%r1r;rrrrr#s���������2�2�2�2�

-�
-�
-��
�
��X�
�

�

�

��
�
��X�
�
�
�
�����\���"�"��\�"�H
�)�)��\�)�)�)rr)rr#�enumsr�objectrrrr�<module>rC
si�


�:
����	�	�	�	�������n

�n

�n

�n

�n

�F�n

�n

�n

�n

�n

r