/usr/lib/python3/dist-packages/chardet/__pycache__
Edit: /usr/lib/python3/dist-packages/chardet/__pycache__/charsetprober.cpython-310.pyc (3434B)
o
-åÏ_ö ã @ s0 d dl Z d dlZddlmZ G dd„ deƒZdS )é Né )Ú ProbingStatec @ sn e Zd ZdZddd„Zdd„ Zedd„ ƒZd d
„ Zed d „ ƒZ d
d„ Z
e dd„ ƒZ e dd„ ƒZ
e dd„ ƒZdS )Ú
CharSetProbergffffffî?Nc C s d | _ || _t t¡| _d S ©N)Ú_stateÚ lang_filterÚloggingÚ getLoggerÚ__name__Úlogger)Úselfr © r
ú7/usr/lib/python3/dist-packages/chardet/charsetprober.pyÚ__init__' s zCharSetProber.__init__c C s t j| _d S r )r Ú DETECTINGr ©r r
r
r Úreset, s zCharSetProber.resetc C ó d S r r
r r
r
r Ú charset_name/ s zCharSetProber.charset_namec C r r r
)r Úbufr
r
r Úfeed3 ó zCharSetProber.feedc C s | j S r )r r r
r
r Ústate6 s zCharSetProber.statec C s dS )Ng r
r r
r
r Úget_confidence: r z CharSetProber.get_confidencec C s t dd| ¡} | S )Ns ([ -])+ó )ÚreÚsub)r r
r
r Úfilter_high_byte_only= s z#CharSetProber.filter_high_byte_onlyc C s\ t ƒ }t d| ¡}|D ] }| |dd… ¡ |dd… }| ¡ s&|dk r&d}| |¡ 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]*[€-ÿ]+[a-zA-Z]*[^a-zA-Z€-ÿ]?Néÿÿÿÿó €r )Ú bytearrayr ÚfindallÚextendÚisalpha)r ÚfilteredÚwordsÚwordÚ last_charr
r
r Úfilter_international_wordsB s ÿ z(CharSetProber.filter_international_wordsc C s¤ t ƒ }d}d}tt| ƒƒD ]7}| ||d … }|dkr d}n|dkr$d}|dk rD| ¡ sD||kr@|s@| | ||… ¡ | d¡ |d }q
|sP| | |d … ¡ |S )
aÈ
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``.
Fr r ó >ó
s