£Á°èZ¨Ä…–K§‚«“ô4“ÒÙ´dîfUÙÃÅ WKbyʦ•êŽ…È®FÒ¿ÊÎóCozá¬S@6{Í:›œêZÌ:Š•_%:¢¾¾~;‘Ã~芩ÊǍí`ÔÑ©ú뙵'5I¿fš×WO%ø9¾«¾DK|€ùÍD”Ýs]nHÕ¶êםӼ㞪éUWŸÈË%DÒÕ¬ï‘]/Åcx ‰ï2ß]ä6G[]S£Ôϯrs{úëóµmÒï#UQxo·õÞCe]"±/aÙ&Eã4ú9Jé_ÞåëdãöKë)AÞ ¯¹ægƒÛowЍø^d™ý½ßB7áyMä9ÜÖUã !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!  Re@sBddlZddlZddlmZGdddeZdS)N) ProbingStatec@seZdZdZdddZddZeddZd d Zed d Z d dZ e ddZ e ddZ e ddZdS) CharSetProbergffffff?NcCs(d|_||_tjt|_dS)N)_state lang_filterlogging getLogger__name__logger)selfrr /builddir/build/BUILDROOT/alt-python35-pip-20.2.4-5.el8.x86_64/opt/alt/python35/lib/python3.5/site-packages/pip/_vendor/chardet/charsetprober.py__init__'s  zCharSetProber.__init__cCstj|_dS)N)r DETECTINGr)r r r r reset,szCharSetProber.resetcCsdS)Nr )r r r r charset_name/szCharSetProber.charset_namecCsdS)Nr )r bufr r r feed3szCharSetProber.feedcCs|jS)N)r)r r r r state6szCharSetProber.statecCsdS)Ngr )r r r r get_confidence:szCharSetProber.get_confidencecCstjdd|}|S)Ns([-])+ )resub)rr r r filter_high_byte_only=sz#CharSetProber.filter_high_byte_onlycCst}tjd|}xa|D]Y}|j|dd|dd}|j rn|dkrnd}|j|q"W|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-]?Nrsrr) bytearrayrfindallextendisalpha)rfilteredwordsword last_charr r r filter_international_wordsBs    z(CharSetProber.filter_international_wordscCst}d}d}xtt|D]}|||d}|dkrWd}n|dkrid}|dkr(|j r(||kr| r|j||||jd|d}q(W|s|j||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>s