^jn JUdZddlmZddlZddlZddlZddlZddlmZddl m Z ddl m Z ddl mZe dZd Zged Zd Zd Zd ZdZdZej.ddGddZej2d d ddZgeddej6ddeddej6ddeddej6dded d!ej6dded"d#ej6dded$d%ej6dded&d'ej6dded(d)ej6dded*d+ej6dded,d-ej8dded.d/ej6dd0ed1d2ej6dd3ed4d5ej6dd6ed7d8ej6dd3ed9d:ej6dd6ed;dej8dd0ed?d@ej6dd3edAdBej6dd3edCdDej6dd3edEdFej8dd6edGdHej6dd3edIdJej6ddKedLdMej6dgedNedOdPej6deedQdRej6deedSdTej6ddUedVdWej6ddXedYdZej6dd[ed\d]ej6deed^d_ej6deed`daej6ddbedcddej6ddeedfdgej6ddhedidjej6ddKedkdlej:deedmdnej:deedodpej:ddqedrdsej:deedtduej:deedvdwej:deedxdyej:ddUedzd{ej:dd[ed|d}ej:ddXed~dej:ddeddej:deeddej:ddeddej:deeddej:ddeddej:dd6eddej<deeddej<ddUeddej<ddeddej<deeddej<deeddej<ddXeddej8deeddej8ddeddej8ddheddej8ddeddej8ddeddej8ddeddej8deeddej>ddeddej>ddUeddej>deeddej>deeddej>deeddej>deeddej>dd[eddej>ddXeddej>deeddej>ddeddej>ddeddej>dd[eddej>ddǬeddej>ddʬeddej>ddͬeddej>deeddej>ddUeddej@deeddej@dd[eddej@deeddej@ddUeddej@ddXeddej@ddެZ!e e!Dcic]}|jD|c}Z#de$d<ej2dddZ%ddZ& ddZ'ycc}w)zz!get_candidates..sD#cggm#Dsc3@K|]}|jvs|ywrr)rrinclude_encodingss rrz!get_candidates..sQc388?P3PcQc3@K|]}|jvs|ywrr)rrexclude_encodingss rrz!get_candidates..sUc388CT3TcUr)REGISTRYvaluestuple)rrr candidatess``` rget_candidatesrsBE!2DJ$QZQ $UZU  rr)zus-asciiFr)rrrrrr\)r\utf8csutf8zunicode-1-1-utf-8 unicode11utf8 unicode20utf8zx-unicode20utf8r])z UTF-8-SIGz utf-8-bomrU)zUTF-16utf16csutf16rV)z UTF-16-BEzutf-16be csutf16berW)z UTF-16-LEzutf-16le csutf16lerX)zUTF-32utf32csutf32rY)z UTF-32-BEzutf-32be csutf32berZ)z UTF-32-LEzutf-32le csutf32ler[)zUTF-7utf7csutf7r ) z Big5-HKSCS Big5HKSCSbig5zbig5-twcsbig5cp950zcn-big5zx-x-big5 csbig5hkscs)zhr.)CP932ms932mskanjizms-kanji cswindows31jz windows-31j)jar/) CP949ms949uhcz windows-949 csksc56011987z iso-ir-149zks_c_5601-1987zks_c_5601-1989ksc5601ksc_5601)kor0)z EUC-JIS-2004zeuc-jpeucjpujiszu-jisz euc-jisx0213cseucpkdfmtjapanesezx-euc-jpr1)zEUC-KReuckrcseuckrr2)GB18030zgb-18030gb2312gbkcsgb2312gb_2312z gb_2312-80zx-gbkcsiso58gb231280z iso-ir-58 csgb18030csgbkcp936ms936z windows-936r4)z HZ-GB-2312r4r5)z ISO-2022-JP-2z iso-2022-jp csiso2022jpz iso2022-jp-1 csiso2022jp2r6)zISO-2022-JP-2004z iso2022-jp-3r7)zISO-2022-JP-EXTr8)z ISO-2022-KR csiso2022krrS) zShift-JIS-2004Shift_JIS_2004 shift_jissjisshiftjiss_jiszshift-jisx0213zx-sjis csshiftjisms_kanjir,)CP874z windows-874zdos-874)thr)z Windows-1250rzx-cp1250 cswindows1250rsr)z Windows-1251rzx-cp1251 cswindows1251r)z Windows-1252rzx-cp1252 cswindows1252r)z Windows-1253rzx-cp1253 cswindows1253)elr)z Windows-1254rzx-cp1254 cswindows1254)ror)z Windows-1255rzx-cp1255 cswindows1255)her)z Windows-1256rzx-cp1256 cswindows1256r)z Windows-1257rzx-cp1257 cswindows1257r)z Windows-1258rzx-cp1258 cswindows1258)virH)zKOI8-Rkoi8rkoikoi8cskoi8r)rprJ)zKOI8-Ukoi8uzkoi8-rucskoi8u)rrrT)zTIS-620tis620z iso-8859-11z iso8859-11 iso885911cstis620r9)z ISO-8859-1zlatin-1latin1r9iso88591r?)z ISO-8859-2zlatin-2latin2r?iso88592r@)z ISO-8859-3zlatin-3latin3r@iso88593)eomtrorA)z ISO-8859-4zlatin-4latin4rAiso88594rB)z ISO-8859-5rBcyrilliciso88595rC)z ISO-8859-6rCarabiciso88596z iso-8859-6-ez iso-8859-6-i csiso88596e csiso88596irD)z ISO-8859-7rDgreekiso88597 sun_eu_greekrE) z ISO-8859-8rEhebrewiso88598z iso-8859-8-ez iso-8859-8-i csiso88598e csiso88598ivisuallogicalrF)z ISO-8859-9zlatin-5latin5rFiso88599r:)z ISO-8859-10zlatin-6latin6r: iso885910)rhrdr;)z ISO-8859-13zlatin-7latin7r; iso885913 csiso885913r<) z ISO-8859-14zlatin-8latin8r< iso885914 csiso885914z iso-ir-199z iso-celticl8)r_rfr^gdr=)z ISO-8859-15zlatin-9latin9r= iso885915 csisolatin9 csiso885915l9r>)z ISO-8859-16zlatin-10latin10r> iso885916 csiso885916z iso-ir-226l10)rzrvryrxr{r|rG)JohabrL)z Mac-Cyrillic MacCyrillic maccyrilliczx-mac-cyrilliczx-mac-ukrainianrM)z Mac-GreekMacGreekmacgreekrN)z Mac-Iceland MacIceland maciceland)rhrO)z Mac-Latin2 MacLatin2 maclatin2maccentraleuroperP)z Mac-RomanMacRomanmacroman macintosh csmacintoshmacz x-mac-romanrQ)z Mac-Turkish MacTurkish macturkishr)CP720r )CP1006)urr )CP1125rI)zKOI8-T)tgrK)zKZ-1048rKz strk1048-2002rk1048)kkrR)PTCP154pt154cp154r3)z HP-Roman8roman8r8 csHPRoman8r)CP437) rbrerarcrmrirkr`rnrdrfr)CP737r)CP775r)CP850r)CP852r )CP855r!)CP856r")CP857r#)CP858r$)CP860)rmr%)CP861r&)CP862r')CP863)rer()CP864)rr))CP865)r`rlr*)CP866r+)CP869r )CP1140cp037cp01140ibm01140ibm1140 csibm01140r)CP424r)CP500r-)CP875r )CP1026r)CP273)raz#MappingProxyType[str, EncodingInfo]ric|j}tjD]S}|j|k(r|jcS|jD]%}|j|k(s|jccSU t j |j}||k7r t|Sy#ttf$rYywxYw)zConvert an encoding name string to the canonical EncodingName. Handles arbitrary casing, aliases, and Python codec names. :param name: Any encoding name string. :returns: The canonical :data:`EncodingName`, or ``None`` if unknown. N) lowerrrrrcodecslookup LookupError ValueErrorlookup_encoding)rloweredentryalias codec_names rrprpsjjlG"" :: :: ]] "E{{}'zz! ""]]4(-- Wz**   $s<B,,B>=B>cFt|}|d|d|}t||S)aValidate and normalize a single encoding name. :param name: The encoding name to validate. :param param_name: Parameter name for error messages. :returns: The canonical encoding name. :raises ValueError: If the encoding name is unknown. zUnknown encoding z in )rpro)r param_name canonicalmsgs r_validate_encodingrys6 %I!$j\:o rcZ|ytfd|D}|sd}t||S)a8Normalize an iterable of encoding names to canonical forms. :param encodings: Encoding names to normalize, or ``None``. :param param_name: Parameter name for error messages. :returns: A frozenset of canonical encoding names, or ``None``. :raises ValueError: If any encoding name is unknown. Nc36K|]}t|ywr)ry)rrrvs rrz&normalize_encodings..sR)$ ;RszG must not be empty; omit the argument or pass None to disable filtering) frozensetro) encodingsrvresultrxs ` rnormalize_encodingsrs= R R RF  cdo Mr)NN)rrrfrozenset[str] | Nonerrrztuple[EncodingInfo, ...])rstrrzEncodingName | None)rrrvrrr)r}zIterable[str] | Nonervrrr)(r __future__rrl dataclasses functoolsrcollections.abcrtypesrtypingr chardet.enumsrr_WESTERN _WESTERN_TR _CYRILLIC _CENTRAL_EU_CENTRAL_EU_NO_RO_BALTIC_ARABIC dataclassr lru_cacher MODERN_WEBLEGACY_REGIONAL LEGACY_ISO LEGACY_MACDOS MAINFRAME_REGISTRY_ENTRIESrrrrpryr)es0rrsB" $"%UW t & $ 0 8 8  d$/%%0%:S!04/3 ,- "0c    " " c     " "c 0 *  " " 1c > .  " " ?c L 6  " " Mc Z 6  " " [c h .  " " ic v 6  " " wc D 6  " " Ec R +  ' ' Sc b     " "cc D    " " Ec `     " ")ac L     " "Mc l .  " " mc z "  " "9{c v $  ' ' wc D    " " Ec ^ 4  " " _c l $  " " mc z .  ' ' {c H     " "!Ic n 3  " " oc | G  " "&K&& }c J G  " " Kc X G  " " Yc f G  " " gc t G  " " uc B  G  " " C c P  G  " " Q c ^  G  " " _ c l  G  " " m c |  =  " " } c J  9  " " K c Z     " " [ c x  L  " " y c F  L  " " G c T  L  " "$ U c b  L  " " c c p  C  " " q c ~      " "' c h     " " i c B      " "+C c p  L  " " q c ~  O  " "  c L    " " Mc h     " "*!ic L     " "Mc l     " "6mc N   " " Oc ^    " " _c x 5  " " yc F ;  " " Gc T L  " "# Uc b    " "cc @ ;  " " Ac P   ' ' Qc ^   ' ' _c l   ' ' mc z   ' ' {c H @  ' ' Ic V -  ' ' Wc d ;  ' ' ec t  OOT uc B  OO Cc P  OO Qc ^  OO _c l  OO mc z  OO {c H  OO Ic V  OO Wc d  OO ec r  OO sc @  OO Ac N  OO Oc \  OO ]c j  OO kc x  OO yc F  OO Gc T  OO Uc d    ! ! ec @   ! ! Ac N   ! ! Oc \   ! ! ]c j   ! ! kc x   ! ! yc J1A)*1QVVQY*1 -T"#2 #a+sb