....................................../////.===Shadow-Here===./////................................................ > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < ------------------------------------------------------------------------------------------------------------------- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////// RIFF¤ WEBPVP8 ˜ ðÑ *ôô>‘HŸK¥¤"§£±¨àð enü¹%½_F‘åè¿2ºQú³íªú`N¿­3ÿƒügµJžaÿ¯ÿ°~¼ÎùnúîÞÖô•òíôÁÉß®Sm¥Ü/ ‡ó˜f£Ùà<˜„xëJ¢Ù€SO3x<ªÔ©4¿+ç¶A`q@Ì“Úñè™ÍÿJÌ´ª-˜ÆtÊÛL]Ïq*‘Ý”ì#ŸÌÏãY]@ê`¿ /ªfkØB4·®£ó z—Üw¥Pxù–ÞLШKÇN¾AkÙTf½è'‰g gÆv›Øuh~ a˜Z— ïj*á¥t d£“uÒ ¨`K˜¹ßþ]b>˜]_ÏÔ6W—è2r4x•íÖ…"ƒÖNîä!¦å Ú}ýxGøÌ —@ ;ÆÚŠ=ɾ1ý8lªË¥ô ^yf®Œ¢u&2©nÙÇ›ñÂñŒ³ aPo['½»øFùà­+4ê“$!lövlüÞ=;N®3ð‚õ›DÉKòÞ>ÄÍ ¥ˆuߤ#ˆ$6ù™¥îЇy’ÍB¼ çxÛ;X"WL£R÷͝*ó-¶Zu}º.s¸sšXqù–DþÿvªhüïwyŸ ¯é³lÀ:KCûÄ£Ëá\…­ ~—ýóî ¼ûûÜTÓüÇy…ŽÆvc»¾×U ñ¸žþоP÷¦ó:Ò¨¨5;Ð#&#ÖúñläÿÁœ GxÉ­/ñ‡áQðìYÉtÒw޼GÔ´zàÒò ð*ëzƒ•4~H]Ø‹f ñÓÈñ`NåWçs'ÆÏW^ø¹!XžµmQ5ÃËoLœÎ: ÞËÍ¥J ù…î èo£ßPÎñ¶ž8.Œ]ʵ~5›ÙË-ù*8ÙÖß±~ ©¹rÓê‚j¶d¸{^Q'˜±Crß ÚH—#¥¥QlÀ×ëã‡DÜ«èî þ&Çæžî;ŽÏºò6ÒLÃXy&ZŒ'j‚¢Ù€IßÚù+–MGi‰*jE€‘JcÜ ÓÌ EÏÚj]o˜ Þr <¾U ûŪæÍ/šÝH¥˜b”¼ ÁñßX GP›ï2›4WŠÏà×£…íÓk†¦H·ÅíMh–*nó÷à]ÁjCº€b7<ب‹¨5車bp2:Á[UªM„QŒçiNMa#<5›áËó¸HýÊ"…×Éw¹¦ì2º–x<›»a±¸3Weü®FÝ⑱ö–î–³|LPÈ~çð~Çå‡|º kD¢µÏàÆAI %1À% ¹Ò – ”ϝS¦‰4&¶£°à Öý”û_Ò Áw°A«Å€?mÇÛgHÉ/8)á¾ÛìáöŽP í¨PŸNÙµº¦‡§Ùš"ÿ«>+ªÕ`Ê÷‡‚ß Õû˜þãÇ-PÍ.¾XV‘€ dÜ"þ4¹ ±Oú‘©t¥¦FªÄÃÄ•b‚znýu½—#cDs˜ÃiÑOˆñ×QO=*IAÊ,¶ŽZƒ;‡wøXè%EÐk:F±Ú” .Ѽ+Áu&Ç`."pÈÉw o&¿dE6‘’EqTuK@Ì¥ã™À(Êk(h‰,H}RÀIXÛš3µ1©_OqÚÒJAñ$ÊÙÜ;D3çŒ[þùœh¬Ã³™ö6ç†NY".Ú‰ï[ªŸŒ '²Ð öø_¨ÂÉ9ué¶³ÒŠõTàîMØ#û¯gN‡bÙ놚X„ö …ÉeüÌ^J ‹€.œ$Æ)βÄeæW#óüßĺŸ€ ÀzwV 9oä»f4V*uB «Ë†¹ì¯žR霓æHXa=&“I4K;¯ç‹h×·"UŠ~<•╪Vêª&ÍSÃÆÅ?ÔqÎ*mTM ˜›µwêd#[C¡©§‘D<©àb†–ÁœøvH/,í:¯( ²£|4-„Æövv„Yͼ™^Á$ˆ„¢Û[6yB.åH*V¨æ?$=˜Ñ€•ñ·­(VlŸ‘ nÀt8W÷´Bûba?q9ú¶Xƒl«ÿ\ù¶’þòUÐj/õ¢Ìµ³g$ƒÎR!¸»|Oߍë’BhîÚÑ¢ñåŒJ„®„£2Ð3•ô02Nt…!£Í]Ïc½Qÿ?ˆ<&ÃA¾Ú,JˆijÌ#5yz„‰Î|ÊŽ5QÏ:‹ÐaóVÔxW—CpeÏzÐïíçôÿÅ_[hãsÐ_/ŽTÝ?BîˆííV$<¿i>²F¬_Eß¿ †bÊŒº­ÿ®Z H“C}”¬,Mp ý/Bá£w>˜YV°aƒúh+cŠ- r/[%|üUMHäQ°X»|û/@|°¥Ð !BÔ Ç¢Ä©š+Õì D«7ìN¶ŽðÔ " ƶ’ÖçtA‰Û×}{tþz­¾GÍ›k¹OEJR$ Â׃ «ëÁ"oÉôž$oUK(Ä)Ãz³Ê-‹êN[Ò3Œñbï8P 4ƒ×q¢bo|?<ÛX¬òÄͰL–±›(™ûG?ýË©ÚÄ–ÂDØÐ_Ç¡ô ¾–ÄÏø ×e8Ë©$ÄF¹Å‹ì[©óìl:F¾f´‹‹Xì²ï®\¬ôùƒ ÿat¥óèÒùHß0äe‚;ü×h:ÆWðHž=Ã8骣"kœ'Y?³}Tûè€>?0l›e1Lòñ„aæKÆw…hÖŠùW…ÈÆÄ0ši·›[pcwËþñiêíY/~-Á5˜!¿†A›™Mÿþ(±“t@â“ö2­´TG5yé]çå僳 .·ÍïçÝ7UÚ±Ð/Nè»,_Ï ùdj7\ï Wì4›„»c¸àešg#ÒÊ⥭áØo5‘?ÌdÝô¯ ¹kzsƒ=´#ëÉK›Ø´±-¥eW?‡çßtòTã…$Ý+qÿ±ƒ÷_3Ô¥í÷:æ–ž<·Ö‡‰Å¢ š‡%Ô—utÌÈìðžgÖÀz²À—ï÷Óîäõ{K'´È÷³yaÏÁjƒô}ž§®æÊydÕÈë5¯èˆõvÕ©ã*çD„ “z„Ó‡^^xÂ3M§A´JG‚öï 3W'ˆ.OvXè¡ÊÕª?5º7†˜(˜Ç¶#çê’¶!ÌdZK§æ 0fãaN]òY³RV ™î$®K2R¨`W!1Ôó\;Ý ýB%qæK•&ÓÈe9È0êI±žeŸß -ú@žQr¦ ö4»M¼Áè¹µmw 9 EÆE_°2ó„ŸXKWÁ×Hóì^´²GѝF©óäR†¦‰ç"V»eØ<3ùd3ÿÚ¤Žú“Gi" —‘_ÙËÎ~Üö¯¥½Î»üŸEÚŽåmÞþí ;ÞólËΦMzA"Âf(´òá;Éï(/7½ûñÌ­cïÕçлþÝz¾-ÍvÑ“pH­–ðÓj$¸Äû¤‚‘ãUBË-n“2åPkS5&‹Â|+g^œ®Ì͆d!OïäîU«c;{Û!ÅŽ«ëZ9Ókóˆ]¯ƒ›né `ÇÒ+tÆš (ØKá¾—=3œ®•vuMñg²\ï Ec€ 05±d™‡×iÇ×›UúvÌ¢£Èþ¡ÕØô¶ßÎA"ß±#Ö²ˆÊŸ¦*Ä~ij|àø.-¼'»Ú¥£h ofº¦‡VsR=N½„Î v˜Z*SÌ{=jÑB‹tê…;’HžH¯8–îDù8ñ¢|Q•bÛçš–‹m³“ê¨ åÏ^m¬Žãþ©ïêO‡½6] µÆ„Ooòü ²x}N¦Ë3ïé¿»€›HA˜m%çÞ/¿í7Fø“‹léUk)É°Œµ8Q8›:ÀŠeT*šõ~ôڝG6 ¢}`ùH­–”¡k ‰P1>š†®9z11!X wKfmÁ¦xÑ,N1Q”–æB¶M…ÒÃv6SMˆhU¬ÊPŽï‘öj=·CŒ¯u¹ƒVIЃsx4’ömÛýcå¡¶7ßŠß 57^\wÒÐÆ k§h,Œý î«q^R½3]J¸ÇðN ‚çU¬ôº^Áì} ³f©Õœ§ˆã:FÄÈ‚é(€™?àýÓüè1Gô£¼éj‚OÅñ  #>×—ßtà 0G¥Åa뀐kßhc™À_ÉñÞ#±)GD" YîäË-ÿÙ̪ ¹™a¯´¢E\ÝÒö‚;™„ë]_ p8‰o¡ñ+^÷ 3‘'dT4œŽ ðVë½° :¬víÑ«£tßÚS-3¶“þ2 †üüʨòrš¹M{É_¤`Û¨0ìjœøJ‡:÷ÃáZ˜†@GP&œÑDGÏs¡þ¦þDGú‘1Yá9Ôþ¼ ûø…§÷8&–ÜÑnÄ_m®^üÆ`;ÉVÁJ£?â€-ßê}suÍ2sõA NÌúA磸‘îÿÚ»ƒìö·á¿±tÑÐ"Tÿü˜[@/äj¬€uüªìù¥Ý˜á8Ý´sõj 8@rˆð äþZÇD®ÿUÏ2ùôõrBzÆÏÞž>Ì™xœ“ wiÎ×7_… ¸ \#€MɁV¶¥üÕÿPÔ9Z‡ø§É8#H:ƒ5ÀÝå9ÍIŒ5åKÙŠ÷qÄ>1AÈøžj"µÂд/ªnÀ qªã}"iŸBå˜ÓÛŽ¦…&ݧ;G@—³b¯“•"´4í¨ôM¨åñC‹ïùÉó¯ÓsSH2Ý@ßáM‡ˆKÀªÛUeø/4\gnm¥‹ŸŒ qÄ b9ÞwÒNÏ_4Ég³ú=܆‚´ •â¥õeíþkjz>éÚyU«Íӝ݃6"8/ø{=Ô¢»G¥ äUw°W«,ô—¿ãㆅү¢³xŠUû™yŒ (øSópÐ 9\åTâ»—*oG$/×ÍT†Y¿1¤Þ¢_‡ ¼ „±ÍçèSaÓ 3ÛMÁBkxs‰’R/¡¤ˆÙçª(*õ„üXÌ´ƒ E§´¬EF"Ù”R/ÐNyÆÂ^°?™6¡œïJ·±$§?º>ÖüœcNÌù¯G ‹ñ2ЁBB„^·úìaz¨k:#¨Æ¨8LÎõލ£^§S&cŒÐU€ü(‡F±Š¼&P>8ÙÁ ‰ p5?0ÊÆƒZl¸aô š¼¡}gÿ¶zÆC²¹¬ÎÖG*HB¡O<º2#ñŒAƒ–¡B˜´É$¥›É:FÀÔx¾u?XÜÏÓvN©RS{2ʈãk9rmP¼Qq̳ è¼ÐFׄ^¡Öì fE“F4A…!ì/…¦Lƒ… … $%´¾yã@CI¬ á—3PþBÏNÿ<ý°4Ü ËÃ#ØÍ~âW«rEñw‹eùMMHß²`¬Öó½íf³:‹k˜¯÷}Z!ã¿<¥,\#öµÀ¯aÒNÆIé,Ћ–lŽ#Àæ9ÀÒS·I’½-Ïp Äz¤Š Â* ­íÄ9­< h>׍3ZkËU¹§˜ŒŠ±f­’¤º³Q ÏB?‹#µíÃ¥®@(Gs«†vI¥Mµ‹Á©e~2ú³ÁP4ìÕi‚²Ê^ö@-DþÓàlÜOÍ]n"µã:žpsŽ¢:! Aõ.ç~ÓBûH÷JCÌ]õVƒd «ú´QÙEA–¯¯Œ!.ˆˆëQ±ù œ·Ì!Õâ )ùL„ÅÀlÚè5@B…o´Æ¸XÓ&Û…O«˜”_#‡ƒ„ûÈt!¤ÁÏ›ÎÝŠ?c9 â\>lÓÁVÄÑ™£eØY]:fÝ–—ù+p{™ðè û³”g±OƒÚSù£áÁÊ„ä,ï7š²G ÕÌBk)~ÑiCµ|h#u¤¶îK¨² #²vݯGãeÖ϶ú…¾múÀ¶þÔñ‚Š9'^($¤§ò “š½{éúp÷J›ušS¹áªCÂubÃH9™D™/ZöØÁ‡¦ÝÙŸ·kð*_”.C‹{áXó€‡c¡c€§/šò/&éš÷,àéJþ‰X›fµ“C¨œ®r¬"kL‰Â_q…Z–.ÉL~O µ›zn‚¹À¦Öª7\àHµšÖ %»ÇníV[¥*Õ;ƒ#½¾HK-ÖIÊdÏEÚ#=o÷Óò³´Š: Ç?{¾+9›–‘OEáU·S€˜j"ÄaÜ ŒÛWt› á–c#a»pÔZÞdŽtWê=9éöÊ¢µ~ ë ;Öe‡Œ®:bî3±ýê¢wà¼îpêñ¹¾4 zc¾ðÖÿzdêŒÑÒŝÀ‰s6¤í³ÎÙB¿OZ”+F¤á‡3@Ñëäg©·Ž ˆèª<ù@É{&S„œÕúÀA)‰h:YÀ5^ÂÓŒ°õäU\ ùËÍû#²?Xe¬tu‰^zÒÔãë¼ÛWtEtû …‚g¶Úüâî*moGè¨7%u!]PhÏd™Ý%Îx: VÒ¦ôÊD3ÀŽKÛËãvÆî…N¯ä>Eró–ð`5 Œ%u5XkñÌ*NU%¶áœÊ:Qÿú»“úzyÏ6å-၇¾ ´ ÒÊ]y žO‘w2Äøæ…H’²f±ÎÇ.ª|¥'gîV•Ü .̘¯€šòü¤U~Ù†*¢!?ò wý,}´°ÔÞnïoKq5µb!áÓ3"vAßH¡³¡·G(ÐÎ0Îò¼MG!/ài®@—¬04*`…«é8ªøøló“ˆÊ”èù¤…ßÊoÿé'ËuÌÖ5×È¡§ˆˆfŽë9}hìâ_!!¯  B&Ëö¶‰ÀAÙNVŸ Wh›¸®XÑJì¨ú“¿÷3uj²˜¨ÍÎìë±aúŠÝå¯ð*Ó¨ôJ“yºØ)m°WýOè68†ŸÏ2—‰Ïüꪫٚ¥‹l1 ø ÏÄFjêµvÌbü¦èÝx:X±¢H=MÐß—,ˆÉÇ´(9ú¾^ÅÚ4¿m‡$âX‘å%(AlZo@½¨UOÌÕ”1ø¸jÎÀÃÃ_ µ‘Ü.œº¦Ut: Æï’!=¯uwû#,“pþÇúŒø(é@?³ü¥‘Mo §—s@Œ#)§ŒùkL}NOÆêA›¸~r½¼ÙA—HJ«eˆÖ´*¡ÓpÌŸö.m<-"³ûÈ$¬_6­åf£ïÚâj1y§ÕJ½@dÞÁr&Í\Z%D£Íñ·AZ Û³øüd/ªAi†/Й~  ‡âĮҮÏh§°b—›Û«mJžòG'[ÈYýŒ¦9psl ýÁ ®±f¦x,‰½tN ‚Xª9 ÙÖH.«Lo0×?͹m¡å†Ѽ+›2ƒF ±Ê8 7Hցϓ²Æ–m9…òŸï]Â1äN†VLâCˆU .ÿ‰Ts +ÅÎx(%¦u]6AF Š ØF鈄‘ |¢¶c±soŒ/t[a¾–û:s·`i햍ê›ËchÈ…8ßÀUÜewŒðNOƒõD%q#éû\9¤x¹&UE×G¥ Í—™$ð E6-‡¼!ýpãÔM˜ Âsìe¯ñµK¢Ç¡ùôléœ4Ö£”À Š®Ðc ^¨À}ÙËŸ§›ºê{ÊuÉC ×Sr€¤’fÉ*j!úÓ’Gsùìoîßîn%ò· àc Wp÷$¨˜)û»H ×8ŽÒ€Zj¤3ÀÙºY'Ql¦py{-6íÔCeiØp‘‡XÊîÆUߢ܂ž£Xé¼Y8þ©ëgñß}é.ÎógÒ„ÃØËø¯»™§Xýy M%@NŠ À(~áÐvu7&•,Ù˜ó€uP‡^^®=_E„jt’ 403WebShell
403Webshell
Server IP : 198.54.126.4  /  Your IP : 216.73.216.85
Web Server : Apache
System : Linux host55.registrar-servers.com 4.18.0-513.18.1.lve.2.el8.x86_64 #1 SMP Sat Mar 30 15:36:11 UTC 2024 x86_64
User : aeaw ( 7508)
PHP Version : 8.1.33
Disable Function : NONE
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : ON  |  Sudo : OFF  |  Pkexec : OFF
Directory :  /opt/cloudlinux/venv/lib/python3.11/site-packages/charset_normalizer/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :


[ Back ]     

Current File : /opt/cloudlinux/venv/lib/python3.11/site-packages/charset_normalizer/constant.py
from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE
from encodings.aliases import aliases
from re import IGNORECASE, compile as re_compile
from typing import Dict, List, Set, Union

from .assets import FREQUENCIES

# Contain for each eligible encoding a list of/item bytes SIG/BOM
ENCODING_MARKS: Dict[str, Union[bytes, List[bytes]]] = {
    "utf_8": BOM_UTF8,
    "utf_7": [
        b"\x2b\x2f\x76\x38",
        b"\x2b\x2f\x76\x39",
        b"\x2b\x2f\x76\x2b",
        b"\x2b\x2f\x76\x2f",
        b"\x2b\x2f\x76\x38\x2d",
    ],
    "gb18030": b"\x84\x31\x95\x33",
    "utf_32": [BOM_UTF32_BE, BOM_UTF32_LE],
    "utf_16": [BOM_UTF16_BE, BOM_UTF16_LE],
}

TOO_SMALL_SEQUENCE: int = 32
TOO_BIG_SEQUENCE: int = int(10e6)

UTF8_MAXIMAL_ALLOCATION: int = 1112064

UNICODE_RANGES_COMBINED: Dict[str, range] = {
    "Control character": range(31 + 1),
    "Basic Latin": range(32, 127 + 1),
    "Latin-1 Supplement": range(128, 255 + 1),
    "Latin Extended-A": range(256, 383 + 1),
    "Latin Extended-B": range(384, 591 + 1),
    "IPA Extensions": range(592, 687 + 1),
    "Spacing Modifier Letters": range(688, 767 + 1),
    "Combining Diacritical Marks": range(768, 879 + 1),
    "Greek and Coptic": range(880, 1023 + 1),
    "Cyrillic": range(1024, 1279 + 1),
    "Cyrillic Supplement": range(1280, 1327 + 1),
    "Armenian": range(1328, 1423 + 1),
    "Hebrew": range(1424, 1535 + 1),
    "Arabic": range(1536, 1791 + 1),
    "Syriac": range(1792, 1871 + 1),
    "Arabic Supplement": range(1872, 1919 + 1),
    "Thaana": range(1920, 1983 + 1),
    "NKo": range(1984, 2047 + 1),
    "Samaritan": range(2048, 2111 + 1),
    "Mandaic": range(2112, 2143 + 1),
    "Syriac Supplement": range(2144, 2159 + 1),
    "Arabic Extended-A": range(2208, 2303 + 1),
    "Devanagari": range(2304, 2431 + 1),
    "Bengali": range(2432, 2559 + 1),
    "Gurmukhi": range(2560, 2687 + 1),
    "Gujarati": range(2688, 2815 + 1),
    "Oriya": range(2816, 2943 + 1),
    "Tamil": range(2944, 3071 + 1),
    "Telugu": range(3072, 3199 + 1),
    "Kannada": range(3200, 3327 + 1),
    "Malayalam": range(3328, 3455 + 1),
    "Sinhala": range(3456, 3583 + 1),
    "Thai": range(3584, 3711 + 1),
    "Lao": range(3712, 3839 + 1),
    "Tibetan": range(3840, 4095 + 1),
    "Myanmar": range(4096, 4255 + 1),
    "Georgian": range(4256, 4351 + 1),
    "Hangul Jamo": range(4352, 4607 + 1),
    "Ethiopic": range(4608, 4991 + 1),
    "Ethiopic Supplement": range(4992, 5023 + 1),
    "Cherokee": range(5024, 5119 + 1),
    "Unified Canadian Aboriginal Syllabics": range(5120, 5759 + 1),
    "Ogham": range(5760, 5791 + 1),
    "Runic": range(5792, 5887 + 1),
    "Tagalog": range(5888, 5919 + 1),
    "Hanunoo": range(5920, 5951 + 1),
    "Buhid": range(5952, 5983 + 1),
    "Tagbanwa": range(5984, 6015 + 1),
    "Khmer": range(6016, 6143 + 1),
    "Mongolian": range(6144, 6319 + 1),
    "Unified Canadian Aboriginal Syllabics Extended": range(6320, 6399 + 1),
    "Limbu": range(6400, 6479 + 1),
    "Tai Le": range(6480, 6527 + 1),
    "New Tai Lue": range(6528, 6623 + 1),
    "Khmer Symbols": range(6624, 6655 + 1),
    "Buginese": range(6656, 6687 + 1),
    "Tai Tham": range(6688, 6831 + 1),
    "Combining Diacritical Marks Extended": range(6832, 6911 + 1),
    "Balinese": range(6912, 7039 + 1),
    "Sundanese": range(7040, 7103 + 1),
    "Batak": range(7104, 7167 + 1),
    "Lepcha": range(7168, 7247 + 1),
    "Ol Chiki": range(7248, 7295 + 1),
    "Cyrillic Extended C": range(7296, 7311 + 1),
    "Sundanese Supplement": range(7360, 7375 + 1),
    "Vedic Extensions": range(7376, 7423 + 1),
    "Phonetic Extensions": range(7424, 7551 + 1),
    "Phonetic Extensions Supplement": range(7552, 7615 + 1),
    "Combining Diacritical Marks Supplement": range(7616, 7679 + 1),
    "Latin Extended Additional": range(7680, 7935 + 1),
    "Greek Extended": range(7936, 8191 + 1),
    "General Punctuation": range(8192, 8303 + 1),
    "Superscripts and Subscripts": range(8304, 8351 + 1),
    "Currency Symbols": range(8352, 8399 + 1),
    "Combining Diacritical Marks for Symbols": range(8400, 8447 + 1),
    "Letterlike Symbols": range(8448, 8527 + 1),
    "Number Forms": range(8528, 8591 + 1),
    "Arrows": range(8592, 8703 + 1),
    "Mathematical Operators": range(8704, 8959 + 1),
    "Miscellaneous Technical": range(8960, 9215 + 1),
    "Control Pictures": range(9216, 9279 + 1),
    "Optical Character Recognition": range(9280, 9311 + 1),
    "Enclosed Alphanumerics": range(9312, 9471 + 1),
    "Box Drawing": range(9472, 9599 + 1),
    "Block Elements": range(9600, 9631 + 1),
    "Geometric Shapes": range(9632, 9727 + 1),
    "Miscellaneous Symbols": range(9728, 9983 + 1),
    "Dingbats": range(9984, 10175 + 1),
    "Miscellaneous Mathematical Symbols-A": range(10176, 10223 + 1),
    "Supplemental Arrows-A": range(10224, 10239 + 1),
    "Braille Patterns": range(10240, 10495 + 1),
    "Supplemental Arrows-B": range(10496, 10623 + 1),
    "Miscellaneous Mathematical Symbols-B": range(10624, 10751 + 1),
    "Supplemental Mathematical Operators": range(10752, 11007 + 1),
    "Miscellaneous Symbols and Arrows": range(11008, 11263 + 1),
    "Glagolitic": range(11264, 11359 + 1),
    "Latin Extended-C": range(11360, 11391 + 1),
    "Coptic": range(11392, 11519 + 1),
    "Georgian Supplement": range(11520, 11567 + 1),
    "Tifinagh": range(11568, 11647 + 1),
    "Ethiopic Extended": range(11648, 11743 + 1),
    "Cyrillic Extended-A": range(11744, 11775 + 1),
    "Supplemental Punctuation": range(11776, 11903 + 1),
    "CJK Radicals Supplement": range(11904, 12031 + 1),
    "Kangxi Radicals": range(12032, 12255 + 1),
    "Ideographic Description Characters": range(12272, 12287 + 1),
    "CJK Symbols and Punctuation": range(12288, 12351 + 1),
    "Hiragana": range(12352, 12447 + 1),
    "Katakana": range(12448, 12543 + 1),
    "Bopomofo": range(12544, 12591 + 1),
    "Hangul Compatibility Jamo": range(12592, 12687 + 1),
    "Kanbun": range(12688, 12703 + 1),
    "Bopomofo Extended": range(12704, 12735 + 1),
    "CJK Strokes": range(12736, 12783 + 1),
    "Katakana Phonetic Extensions": range(12784, 12799 + 1),
    "Enclosed CJK Letters and Months": range(12800, 13055 + 1),
    "CJK Compatibility": range(13056, 13311 + 1),
    "CJK Unified Ideographs Extension A": range(13312, 19903 + 1),
    "Yijing Hexagram Symbols": range(19904, 19967 + 1),
    "CJK Unified Ideographs": range(19968, 40959 + 1),
    "Yi Syllables": range(40960, 42127 + 1),
    "Yi Radicals": range(42128, 42191 + 1),
    "Lisu": range(42192, 42239 + 1),
    "Vai": range(42240, 42559 + 1),
    "Cyrillic Extended-B": range(42560, 42655 + 1),
    "Bamum": range(42656, 42751 + 1),
    "Modifier Tone Letters": range(42752, 42783 + 1),
    "Latin Extended-D": range(42784, 43007 + 1),
    "Syloti Nagri": range(43008, 43055 + 1),
    "Common Indic Number Forms": range(43056, 43071 + 1),
    "Phags-pa": range(43072, 43135 + 1),
    "Saurashtra": range(43136, 43231 + 1),
    "Devanagari Extended": range(43232, 43263 + 1),
    "Kayah Li": range(43264, 43311 + 1),
    "Rejang": range(43312, 43359 + 1),
    "Hangul Jamo Extended-A": range(43360, 43391 + 1),
    "Javanese": range(43392, 43487 + 1),
    "Myanmar Extended-B": range(43488, 43519 + 1),
    "Cham": range(43520, 43615 + 1),
    "Myanmar Extended-A": range(43616, 43647 + 1),
    "Tai Viet": range(43648, 43743 + 1),
    "Meetei Mayek Extensions": range(43744, 43775 + 1),
    "Ethiopic Extended-A": range(43776, 43823 + 1),
    "Latin Extended-E": range(43824, 43887 + 1),
    "Cherokee Supplement": range(43888, 43967 + 1),
    "Meetei Mayek": range(43968, 44031 + 1),
    "Hangul Syllables": range(44032, 55215 + 1),
    "Hangul Jamo Extended-B": range(55216, 55295 + 1),
    "High Surrogates": range(55296, 56191 + 1),
    "High Private Use Surrogates": range(56192, 56319 + 1),
    "Low Surrogates": range(56320, 57343 + 1),
    "Private Use Area": range(57344, 63743 + 1),
    "CJK Compatibility Ideographs": range(63744, 64255 + 1),
    "Alphabetic Presentation Forms": range(64256, 64335 + 1),
    "Arabic Presentation Forms-A": range(64336, 65023 + 1),
    "Variation Selectors": range(65024, 65039 + 1),
    "Vertical Forms": range(65040, 65055 + 1),
    "Combining Half Marks": range(65056, 65071 + 1),
    "CJK Compatibility Forms": range(65072, 65103 + 1),
    "Small Form Variants": range(65104, 65135 + 1),
    "Arabic Presentation Forms-B": range(65136, 65279 + 1),
    "Halfwidth and Fullwidth Forms": range(65280, 65519 + 1),
    "Specials": range(65520, 65535 + 1),
    "Linear B Syllabary": range(65536, 65663 + 1),
    "Linear B Ideograms": range(65664, 65791 + 1),
    "Aegean Numbers": range(65792, 65855 + 1),
    "Ancient Greek Numbers": range(65856, 65935 + 1),
    "Ancient Symbols": range(65936, 65999 + 1),
    "Phaistos Disc": range(66000, 66047 + 1),
    "Lycian": range(66176, 66207 + 1),
    "Carian": range(66208, 66271 + 1),
    "Coptic Epact Numbers": range(66272, 66303 + 1),
    "Old Italic": range(66304, 66351 + 1),
    "Gothic": range(66352, 66383 + 1),
    "Old Permic": range(66384, 66431 + 1),
    "Ugaritic": range(66432, 66463 + 1),
    "Old Persian": range(66464, 66527 + 1),
    "Deseret": range(66560, 66639 + 1),
    "Shavian": range(66640, 66687 + 1),
    "Osmanya": range(66688, 66735 + 1),
    "Osage": range(66736, 66815 + 1),
    "Elbasan": range(66816, 66863 + 1),
    "Caucasian Albanian": range(66864, 66927 + 1),
    "Linear A": range(67072, 67455 + 1),
    "Cypriot Syllabary": range(67584, 67647 + 1),
    "Imperial Aramaic": range(67648, 67679 + 1),
    "Palmyrene": range(67680, 67711 + 1),
    "Nabataean": range(67712, 67759 + 1),
    "Hatran": range(67808, 67839 + 1),
    "Phoenician": range(67840, 67871 + 1),
    "Lydian": range(67872, 67903 + 1),
    "Meroitic Hieroglyphs": range(67968, 67999 + 1),
    "Meroitic Cursive": range(68000, 68095 + 1),
    "Kharoshthi": range(68096, 68191 + 1),
    "Old South Arabian": range(68192, 68223 + 1),
    "Old North Arabian": range(68224, 68255 + 1),
    "Manichaean": range(68288, 68351 + 1),
    "Avestan": range(68352, 68415 + 1),
    "Inscriptional Parthian": range(68416, 68447 + 1),
    "Inscriptional Pahlavi": range(68448, 68479 + 1),
    "Psalter Pahlavi": range(68480, 68527 + 1),
    "Old Turkic": range(68608, 68687 + 1),
    "Old Hungarian": range(68736, 68863 + 1),
    "Rumi Numeral Symbols": range(69216, 69247 + 1),
    "Brahmi": range(69632, 69759 + 1),
    "Kaithi": range(69760, 69839 + 1),
    "Sora Sompeng": range(69840, 69887 + 1),
    "Chakma": range(69888, 69967 + 1),
    "Mahajani": range(69968, 70015 + 1),
    "Sharada": range(70016, 70111 + 1),
    "Sinhala Archaic Numbers": range(70112, 70143 + 1),
    "Khojki": range(70144, 70223 + 1),
    "Multani": range(70272, 70319 + 1),
    "Khudawadi": range(70320, 70399 + 1),
    "Grantha": range(70400, 70527 + 1),
    "Newa": range(70656, 70783 + 1),
    "Tirhuta": range(70784, 70879 + 1),
    "Siddham": range(71040, 71167 + 1),
    "Modi": range(71168, 71263 + 1),
    "Mongolian Supplement": range(71264, 71295 + 1),
    "Takri": range(71296, 71375 + 1),
    "Ahom": range(71424, 71487 + 1),
    "Warang Citi": range(71840, 71935 + 1),
    "Zanabazar Square": range(72192, 72271 + 1),
    "Soyombo": range(72272, 72367 + 1),
    "Pau Cin Hau": range(72384, 72447 + 1),
    "Bhaiksuki": range(72704, 72815 + 1),
    "Marchen": range(72816, 72895 + 1),
    "Masaram Gondi": range(72960, 73055 + 1),
    "Cuneiform": range(73728, 74751 + 1),
    "Cuneiform Numbers and Punctuation": range(74752, 74879 + 1),
    "Early Dynastic Cuneiform": range(74880, 75087 + 1),
    "Egyptian Hieroglyphs": range(77824, 78895 + 1),
    "Anatolian Hieroglyphs": range(82944, 83583 + 1),
    "Bamum Supplement": range(92160, 92735 + 1),
    "Mro": range(92736, 92783 + 1),
    "Bassa Vah": range(92880, 92927 + 1),
    "Pahawh Hmong": range(92928, 93071 + 1),
    "Miao": range(93952, 94111 + 1),
    "Ideographic Symbols and Punctuation": range(94176, 94207 + 1),
    "Tangut": range(94208, 100351 + 1),
    "Tangut Components": range(100352, 101119 + 1),
    "Kana Supplement": range(110592, 110847 + 1),
    "Kana Extended-A": range(110848, 110895 + 1),
    "Nushu": range(110960, 111359 + 1),
    "Duployan": range(113664, 113823 + 1),
    "Shorthand Format Controls": range(113824, 113839 + 1),
    "Byzantine Musical Symbols": range(118784, 119039 + 1),
    "Musical Symbols": range(119040, 119295 + 1),
    "Ancient Greek Musical Notation": range(119296, 119375 + 1),
    "Tai Xuan Jing Symbols": range(119552, 119647 + 1),
    "Counting Rod Numerals": range(119648, 119679 + 1),
    "Mathematical Alphanumeric Symbols": range(119808, 120831 + 1),
    "Sutton SignWriting": range(120832, 121519 + 1),
    "Glagolitic Supplement": range(122880, 122927 + 1),
    "Mende Kikakui": range(124928, 125151 + 1),
    "Adlam": range(125184, 125279 + 1),
    "Arabic Mathematical Alphabetic Symbols": range(126464, 126719 + 1),
    "Mahjong Tiles": range(126976, 127023 + 1),
    "Domino Tiles": range(127024, 127135 + 1),
    "Playing Cards": range(127136, 127231 + 1),
    "Enclosed Alphanumeric Supplement": range(127232, 127487 + 1),
    "Enclosed Ideographic Supplement": range(127488, 127743 + 1),
    "Miscellaneous Symbols and Pictographs": range(127744, 128511 + 1),
    "Emoticons range(Emoji)": range(128512, 128591 + 1),
    "Ornamental Dingbats": range(128592, 128639 + 1),
    "Transport and Map Symbols": range(128640, 128767 + 1),
    "Alchemical Symbols": range(128768, 128895 + 1),
    "Geometric Shapes Extended": range(128896, 129023 + 1),
    "Supplemental Arrows-C": range(129024, 129279 + 1),
    "Supplemental Symbols and Pictographs": range(129280, 129535 + 1),
    "CJK Unified Ideographs Extension B": range(131072, 173791 + 1),
    "CJK Unified Ideographs Extension C": range(173824, 177983 + 1),
    "CJK Unified Ideographs Extension D": range(177984, 178207 + 1),
    "CJK Unified Ideographs Extension E": range(178208, 183983 + 1),
    "CJK Unified Ideographs Extension F": range(183984, 191471 + 1),
    "CJK Compatibility Ideographs Supplement": range(194560, 195103 + 1),
    "Tags": range(917504, 917631 + 1),
    "Variation Selectors Supplement": range(917760, 917999 + 1),
}


UNICODE_SECONDARY_RANGE_KEYWORD: List[str] = [
    "Supplement",
    "Extended",
    "Extensions",
    "Modifier",
    "Marks",
    "Punctuation",
    "Symbols",
    "Forms",
    "Operators",
    "Miscellaneous",
    "Drawing",
    "Block",
    "Shapes",
    "Supplemental",
    "Tags",
]

RE_POSSIBLE_ENCODING_INDICATION = re_compile(
    r"(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)",
    IGNORECASE,
)

IANA_SUPPORTED: List[str] = sorted(
    filter(
        lambda x: x.endswith("_codec") is False
        and x not in {"rot_13", "tactis", "mbcs"},
        list(set(aliases.values())),
    )
)

IANA_SUPPORTED_COUNT: int = len(IANA_SUPPORTED)

# pre-computed code page that are similar using the function cp_similarity.
IANA_SUPPORTED_SIMILAR: Dict[str, List[str]] = {
    "cp037": ["cp1026", "cp1140", "cp273", "cp500"],
    "cp1026": ["cp037", "cp1140", "cp273", "cp500"],
    "cp1125": ["cp866"],
    "cp1140": ["cp037", "cp1026", "cp273", "cp500"],
    "cp1250": ["iso8859_2"],
    "cp1251": ["kz1048", "ptcp154"],
    "cp1252": ["iso8859_15", "iso8859_9", "latin_1"],
    "cp1253": ["iso8859_7"],
    "cp1254": ["iso8859_15", "iso8859_9", "latin_1"],
    "cp1257": ["iso8859_13"],
    "cp273": ["cp037", "cp1026", "cp1140", "cp500"],
    "cp437": ["cp850", "cp858", "cp860", "cp861", "cp862", "cp863", "cp865"],
    "cp500": ["cp037", "cp1026", "cp1140", "cp273"],
    "cp850": ["cp437", "cp857", "cp858", "cp865"],
    "cp857": ["cp850", "cp858", "cp865"],
    "cp858": ["cp437", "cp850", "cp857", "cp865"],
    "cp860": ["cp437", "cp861", "cp862", "cp863", "cp865"],
    "cp861": ["cp437", "cp860", "cp862", "cp863", "cp865"],
    "cp862": ["cp437", "cp860", "cp861", "cp863", "cp865"],
    "cp863": ["cp437", "cp860", "cp861", "cp862", "cp865"],
    "cp865": ["cp437", "cp850", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863"],
    "cp866": ["cp1125"],
    "iso8859_10": ["iso8859_14", "iso8859_15", "iso8859_4", "iso8859_9", "latin_1"],
    "iso8859_11": ["tis_620"],
    "iso8859_13": ["cp1257"],
    "iso8859_14": [
        "iso8859_10",
        "iso8859_15",
        "iso8859_16",
        "iso8859_3",
        "iso8859_9",
        "latin_1",
    ],
    "iso8859_15": [
        "cp1252",
        "cp1254",
        "iso8859_10",
        "iso8859_14",
        "iso8859_16",
        "iso8859_3",
        "iso8859_9",
        "latin_1",
    ],
    "iso8859_16": [
        "iso8859_14",
        "iso8859_15",
        "iso8859_2",
        "iso8859_3",
        "iso8859_9",
        "latin_1",
    ],
    "iso8859_2": ["cp1250", "iso8859_16", "iso8859_4"],
    "iso8859_3": ["iso8859_14", "iso8859_15", "iso8859_16", "iso8859_9", "latin_1"],
    "iso8859_4": ["iso8859_10", "iso8859_2", "iso8859_9", "latin_1"],
    "iso8859_7": ["cp1253"],
    "iso8859_9": [
        "cp1252",
        "cp1254",
        "cp1258",
        "iso8859_10",
        "iso8859_14",
        "iso8859_15",
        "iso8859_16",
        "iso8859_3",
        "iso8859_4",
        "latin_1",
    ],
    "kz1048": ["cp1251", "ptcp154"],
    "latin_1": [
        "cp1252",
        "cp1254",
        "cp1258",
        "iso8859_10",
        "iso8859_14",
        "iso8859_15",
        "iso8859_16",
        "iso8859_3",
        "iso8859_4",
        "iso8859_9",
    ],
    "mac_iceland": ["mac_roman", "mac_turkish"],
    "mac_roman": ["mac_iceland", "mac_turkish"],
    "mac_turkish": ["mac_iceland", "mac_roman"],
    "ptcp154": ["cp1251", "kz1048"],
    "tis_620": ["iso8859_11"],
}


CHARDET_CORRESPONDENCE: Dict[str, str] = {
    "iso2022_kr": "ISO-2022-KR",
    "iso2022_jp": "ISO-2022-JP",
    "euc_kr": "EUC-KR",
    "tis_620": "TIS-620",
    "utf_32": "UTF-32",
    "euc_jp": "EUC-JP",
    "koi8_r": "KOI8-R",
    "iso8859_1": "ISO-8859-1",
    "iso8859_2": "ISO-8859-2",
    "iso8859_5": "ISO-8859-5",
    "iso8859_6": "ISO-8859-6",
    "iso8859_7": "ISO-8859-7",
    "iso8859_8": "ISO-8859-8",
    "utf_16": "UTF-16",
    "cp855": "IBM855",
    "mac_cyrillic": "MacCyrillic",
    "gb2312": "GB2312",
    "gb18030": "GB18030",
    "cp932": "CP932",
    "cp866": "IBM866",
    "utf_8": "utf-8",
    "utf_8_sig": "UTF-8-SIG",
    "shift_jis": "SHIFT_JIS",
    "big5": "Big5",
    "cp1250": "windows-1250",
    "cp1251": "windows-1251",
    "cp1252": "Windows-1252",
    "cp1253": "windows-1253",
    "cp1255": "windows-1255",
    "cp1256": "windows-1256",
    "cp1254": "Windows-1254",
    "cp949": "CP949",
}


COMMON_SAFE_ASCII_CHARACTERS: Set[str] = {
    "<",
    ">",
    "=",
    ":",
    "/",
    "&",
    ";",
    "{",
    "}",
    "[",
    "]",
    ",",
    "|",
    '"',
    "-",
}


KO_NAMES: Set[str] = {"johab", "cp949", "euc_kr"}
ZH_NAMES: Set[str] = {"big5", "cp950", "big5hkscs", "hz"}

NOT_PRINTABLE_PATTERN = re_compile(r"[0-9\W\n\r\t]+")

LANGUAGE_SUPPORTED_COUNT: int = len(FREQUENCIES)

# Logging LEVEL bellow DEBUG
TRACE: int = 5

Youez - 2016 - github.com/yon3zu
LinuXploit