+ 3i,n^RIt^RIt^RIHtHt^RIHtHt]P!R4t !RR4t R#)N)OptionalUnion)LanguageFilter ProbingStates%[a-zA-Z]*[-]+[a-zA-Z]*[^a-zA-Z-]?c.a]tRt^(toRt]P 3V3RlRlltV3RlRlt] V3RlRl4t ] V3RlR l4t V3R lR lt ] V3R lR l4t V3RlRlt]V3RlRl4t]V3RlRl4t]V3RlRl4tRtVtR#) CharSetProbergffffff?c$<V^8dQhRS[RR/#) lang_filterreturnN)r)format __classdict__s"7/usr/lib/python3/dist-packages/chardet/charsetprober.py __annotate__CharSetProber.__annotate__,s22N2T2c\PVnRVnWn\ P !\4VnR#)TN) r DETECTING_stateactiver logging getLogger__name__logger)selfr s&&r__init__CharSetProber.__init__,s.",,  &''1 rc<V^8dQhRR/#)r r N)r rs"rrr2s--t-rc0\PVnR#N)rrrrs&rresetCharSetProber.reset2s",, rc0<V^8dQhRS[S[,/#r r rstr)r rs"rrr6shsmrcR#r!rr"s&r charset_nameCharSetProber.charset_name5src0<V^8dQhRS[S[,/#r&r')r rs"rrr:s""(3-"rc\hr!NotImplementedErrorr"s&rlanguageCharSetProber.language9s!!rc<<V^8dQhRS[S[S[3,RS[/#)r byte_strr )rbytes bytearrayr)r rs"rrr=s%""U5)#34""rc\hr!r.)rr3s&&rfeedCharSetProber.feed=s!!rc <V^8dQhRS[/#r&)r)r rs"rrrAs|rcVP#r!)rr"s&rstateCharSetProber.state@s {{rc <V^8dQhRS[/#r&)float)r rs"rrrDsrcR#)grr"s&rget_confidenceCharSetProber.get_confidenceDsrc<<V^8dQhRS[S[S[3,RS[/#r bufr rr4r5)r rs"rrrHs%5 )9#:urc6\P!RRV4pV#)s([-])+ )resub)rDs&rfilter_high_byte_only#CharSetProber.filter_high_byte_onlyGsff&c2 rc<<V^8dQhRS[S[S[3,RS[/#rCrE)r rs"rrrMs%eY.>(?Irc \4p\PV4pVFLpVPVRR4VRRpVP 4'g VR8dRpVPV4KN V#)u 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. NrG)r5INTERNATIONAL_WORDS_PATTERNfindallextendisalpha)rDfilteredwordsword last_chars& rfilter_international_words(CharSetProber.filter_international_wordsLst; ,33C8D OOD"I & RS I$$&&9w+> OOI &rc<<V^8dQhRS[S[S[3,RS[/#rCrE)r rs"rrros%$$U5)#34$$rc V\4pRp^p\V4PR4p\V4FVwrEVR8XdV^,pRpKVR8XgK"WC8d-V'g%VP WV4VP R4RpKX V'gVP WR4V#)a+ Returns a copy of ``buf`` that retains only the sequences of English alphabet and high byte characters that are not between <> characters. This filter can be applied to all scripts which contain both English characters and extended ASCII characters, but is currently only used by ``Latin1Prober``. Fc>rts1: "/ jj8 kkr