a ¦OcÁã@s8ddlZddlZddlmZe d¡ZGdd„dƒZdS)éNé)Ú ProbingStates%[a-zA-Z]*[€-ÿ]+[a-zA-Z]*[^a-zA-Z€-ÿ]?c@sneZdZdZddd„Zdd„Zedd„ƒZd d „Zed d „ƒZ d d„Z e dd„ƒZ e dd„ƒZ e dd„ƒZdS)Ú CharSetProbergffffffî?NcCsd|_||_t t¡|_dS©N)Ú_stateÚ lang_filterÚloggingÚ getLoggerÚ__name__Úlogger)Úselfr©r úY/var/www/html/megastudio/lib/python3.9/site-packages/pip/_vendor/chardet/charsetprober.pyÚ__init__+szCharSetProber.__init__cCs tj|_dSr)rÚ DETECTINGr©r r r rÚreset0szCharSetProber.resetcCsdSrr rr r rÚ charset_name3szCharSetProber.charset_namecCst‚dSr)ÚNotImplementedError)r Úbyte_strr r rÚfeed7szCharSetProber.feedcCs|jSr)rrr r rÚstate:szCharSetProber.statecCsdS)Ngr rr r rÚget_confidence>szCharSetProber.get_confidencecCst dd|¡}|S)Ns([-])+ó )ÚreÚsub)Úbufr r rÚfilter_high_byte_onlyAsz#CharSetProber.filter_high_byte_onlycCsZtƒ}t |¡}|D]@}| |dd…¡|dd…}| ¡sJ|dkrJd}| |¡q|S)u7 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. Néÿÿÿÿó€r)Ú bytearrayÚINTERNATIONAL_WORDS_PATTERNÚfindallÚextendÚisalpha)rÚfilteredÚwordsÚwordZ last_charr r rÚfilter_international_wordsFs    z(CharSetProber.filter_international_wordscCs’tƒ}d}d}t|ƒ d¡}t|ƒD]R\}}|dkrB|d}d}q$|dkr$||krr|sr| |||…¡| d¡d}q$|sŽ| ||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. This filter can be applied to all scripts which contain both English characters and extended ASCII characters, but is currently only used by ``Latin1Prober``. FrÚcó>rós  ÿ