????

Your IP : 3.144.37.229


Current Path : /lib/python3.9/site-packages/chardet/__pycache__/
Upload File :
Current File : //lib/python3.9/site-packages/chardet/__pycache__/charsetprober.cpython-39.pyc

a

��=b��@s0ddlZddlZddlmZGdd�de�ZdS)�N�)�ProbingStatec@sneZdZdZddd�Zdd�Zedd��Zd	d
�Zedd��Z	d
d�Z
edd��Zedd��Z
edd��ZdS)�
CharSetProbergffffff�?NcCsd|_||_t�t�|_dS�N)�_state�lang_filter�loggingZ	getLogger�__name__�logger)�selfr�r�9/usr/lib/python3.9/site-packages/chardet/charsetprober.py�__init__'szCharSetProber.__init__cCstj|_dSr)rZ	DETECTINGr�rrrr
�reset,szCharSetProber.resetcCsdSrrrrrr
�charset_name/szCharSetProber.charset_namecCsdSrr)r�bufrrr
�feed3szCharSetProber.feedcCs|jSr)rrrrr
�state6szCharSetProber.statecCsdS)Ngrrrrr
�get_confidence:szCharSetProber.get_confidencecCst�dd|�}|S)Ns([-])+� )�re�sub)rrrr
�filter_high_byte_only=sz#CharSetProber.filter_high_byte_onlycCs\t�}t�d|�}|D]@}|�|dd��|dd�}|��sL|dkrLd}|�|�q|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�wordsZwordZ	last_charrrr
�filter_international_wordsBs�z(CharSetProber.filter_international_wordscCs�t�}d}d}tt|��D]n}|||d�}|dkr<d}n|dkrHd}|dkr|��s||kr�|s�|�|||��|�d�|d}q|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�>�<TrrN)r�range�lenrr)rr Zin_tag�prevZcurrZbuf_charrrr
�filter_with_english_lettersgs"

z)CharSetProber.filter_with_english_letters)N)r	�
__module__�__qualname__ZSHORTCUT_THRESHOLDrr�propertyrrrr�staticmethodrr"r(rrrr
r#s




$r)rrZenumsr�objectrrrrr
�<module>s