B

ŒYu‘s¶œÈã@s0dd
lZdd
l
Z
ddlmZ
Gdd„deƒZd
S)éNé
)
ÚProbingStatec@sneZ
dZd
Zddd„
Zdd„Zedd„ƒ
Zd	d
„Zedd„ƒ
Z	d
d„Z
edd„ƒ
Zedd„ƒ
Z
edd„ƒ
ZdS)Ú
CharSetProbergffffffî?NcCsd|_|
|_
t t¡
|_dS)
N)Ú_stateÚlang_filterÚloggingÚ	getLoggerÚ__name__Úlogger)Úselfr©rú:/tmp/pip-install-fdhvs41_/chardet/chardet/charsetprober.pyÚ__init__'s


zCharSetProber.__init__c

Cstj
|_dS)
N)rÚ	DETECTINGr)
rrrr
Úreset,s
zCharSetProber.resetc


CsdS)
Nr)
rrrr
Úcharset_name/szCharSetProber.charset_namec
CsdS)
Nr)rÚbufrrr
Úfeed3s
zCharSetProber.feedc


Cs|jS)
N)
r)
rrrr
Ústate6szCharSetProber.statec


Csd
S)Ngr)
rrrr
Úget_confidence:s
zCharSetProber.get_confidencec

Cst 
d
d|¡}|S)Ns([-])+ó
 )ÚreÚsub)
rrrr
Úfilter_high_byte_only=s
z#CharSetProber.filter_high_byte_onlyc
Cs`tƒ}
t
 d
|¡}xH|D]@}|
 |dd…¡

|dd…}| ¡sN|dkrNd}|
 |¡

qW|
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	bytearrayrÚfindallÚextendÚisalpha)rÚfilteredÚwordsÚwordÚ	last_charrrr
Úfilter_international_wordsBs





z(CharSetProber.filter_international_wordsc
Cs¨tƒ}
d
}d}x~t
t|ƒ
ƒ
D]n}|||d…}|dkr>d
}n|dkrJd}|dkr| ¡s||kr‚|s‚|
 |||…¡

|
 d¡

|d}qW|s¤|
 ||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
ró
>ó
<TrrN)rÚrangeÚlenrr)rr Úin_tagÚprevÚcurrÚbuf_charrrr
Úfilter_with_english_lettersgs"






z)CharSetProber.filter_with_english_letters)
N)r	Ú
__module__Ú__qualname__ÚSHORTCUT_THRESHOLDrrÚpropertyrrrrÚstaticmethodrr$r-rrrr
r#s
%r)rrÚenumsrÚobjectrrrrr
Ú<module>s