diff options
Diffstat (limited to 'unicode_match.py')
-rw-r--r-- | unicode_match.py | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/unicode_match.py b/unicode_match.py new file mode 100644 index 000000000..9f7816a37 --- /dev/null +++ b/unicode_match.py @@ -0,0 +1,19 @@ +# coding=utf8 +import sys +import unicodedata + + +def chars_from_category(category): + return ''.join([chr(num) for num in range(sys.maxunicode+1) if unicodedata.category(chr(num)) == category]) + +categories = ["Lu", "Ll", "Lt", "Lm", "Nl"] +for category in categories: + print(chars_from_category(category)) + +# Based on UCD version 9.0.0 +letter_uppercase = "ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞĀĂĄĆĈĊČĎĐĒĔĖĘĚĜĞĠĢĤĦĨĪĬĮİIJĴĶĹĻĽĿŁŃŅŇŊŌŎŐŒŔŖŘŚŜŞŠŢŤŦŨŪŬŮŰŲŴŶŸŹŻŽƁƂƄƆƇƉƊƋƎƏƐƑƓƔƖƗƘƜƝƟƠƢƤƦƧƩƬƮƯƱƲƳƵƷƸƼDŽLJNJǍǏǑǓǕǗǙǛǞǠǢǤǦǨǪǬǮDZǴǶǷǸǺǼǾȀȂȄȆȈȊȌȎȐȒȔȖȘȚȜȞȠȢȤȦȨȪȬȮȰȲȺȻȽȾɁɃɄɅɆɈɊɌɎͰͲͶͿΆΈΉΊΌΎΏΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΪΫϏϒϓϔϘϚϜϞϠϢϤϦϨϪϬϮϴϷϹϺϽϾϿЀЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎҐҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾӀӁӃӅӇӉӋӍӐӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӶӸӺӼӾԀԂԄԆԈԊԌԎԐԒԔԖԘԚԜԞԠԢԤԦԨԪԬԮԱԲԳԴԵԶԷԸԹԺԻԼԽԾԿՀՁՂՃՄՅՆՇՈՉՊՋՌՍՎՏՐՑՒՓՔՕՖႠႡႢႣႤႥႦႧႨႩႪႫႬႭႮႯႰႱႲႳႴႵႶႷႸႹႺႻႼႽႾႿჀჁჂჃჄჅჇჍᎠᎡᎢᎣᎤᎥᎦᎧᎨᎩᎪᎫᎬᎭᎮᎯᎰᎱᎲᎳᎴᎵᎶᎷᎸᎹᎺᎻᎼᎽᎾᎿᏀᏁᏂᏃᏄᏅᏆᏇᏈᏉᏊᏋᏌᏍᏎᏏᏐᏑᏒᏓᏔᏕᏖᏗᏘᏙᏚᏛᏜᏝᏞᏟᏠᏡᏢᏣᏤᏥᏦᏧᏨᏩᏪᏫᏬᏭᏮᏯᏰᏱᏲᏳᏴᏵḀḂḄḆḈḊḌḎḐḒḔḖḘḚḜḞḠḢḤḦḨḪḬḮḰḲḴḶḸḺḼḾṀṂṄṆṈṊṌṎṐṒṔṖṘṚṜṞṠṢṤṦṨṪṬṮṰṲṴṶṸṺṼṾẀẂẄẆẈẊẌẎẐẒẔẞẠẢẤẦẨẪẬẮẰẲẴẶẸẺẼẾỀỂỄỆỈỊỌỎỐỒỔỖỘỚỜỞỠỢỤỦỨỪỬỮỰỲỴỶỸỺỼỾἈἉἊἋἌἍἎἏἘἙἚἛἜἝἨἩἪἫἬἭἮἯἸἹἺἻἼἽἾἿὈὉὊὋὌὍὙὛὝὟὨὩὪὫὬὭὮὯᾸᾹᾺΆῈΈῊΉῘῙῚΊῨῩῪΎῬῸΌῺΏℂℇℋℌℍℐℑℒℕℙℚℛℜℝℤΩℨKÅℬℭℰℱℲℳℾℿⅅↃⰀⰁⰂⰃⰄⰅⰆⰇⰈⰉⰊⰋⰌⰍⰎⰏⰐⰑⰒⰓⰔⰕⰖⰗⰘⰙⰚⰛⰜⰝⰞⰟⰠⰡⰢⰣⰤⰥⰦⰧⰨⰩⰪⰫⰬⰭⰮⱠⱢⱣⱤⱧⱩⱫⱭⱮⱯⱰⱲⱵⱾⱿⲀⲂⲄⲆⲈⲊⲌⲎⲐⲒⲔⲖⲘⲚⲜⲞⲠⲢⲤⲦⲨⲪⲬⲮⲰⲲⲴⲶⲸⲺⲼⲾⳀⳂⳄⳆⳈⳊⳌⳎⳐⳒⳔⳖⳘⳚⳜⳞⳠⳢⳫⳭⳲꙀꙂꙄꙆꙈꙊꙌꙎꙐꙒꙔꙖꙘꙚꙜꙞꙠꙢꙤꙦꙨꙪꙬꚀꚂꚄꚆꚈꚊꚌꚎꚐꚒꚔꚖꚘꚚꜢꜤꜦꜨꜪꜬꜮꜲꜴꜶꜸꜺꜼꜾꝀꝂꝄꝆꝈꝊꝌꝎꝐꝒꝔꝖꝘꝚꝜꝞꝠꝢꝤꝦꝨꝪꝬꝮꝹꝻꝽꝾꞀꞂꞄꞆꞋꞍꞐꞒꞖꞘꞚꞜꞞꞠꞢꞤꞦꞨꞪꞫꞬꞭꞮꞰꞱꞲꞳꞴꞶABCDEFGHIJKLMNOPQRSTUVWXYZ" +letter_lowercase = "abcdefghijklmnopqrstuvwxyzµßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķĸĺļľŀłńņňʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżžſƀƃƅƈƌƍƒƕƙƚƛƞơƣƥƨƪƫƭưƴƶƹƺƽƾƿdžljnjǎǐǒǔǖǘǚǜǝǟǡǣǥǧǩǫǭǯǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳȴȵȶȷȸȹȼȿɀɂɇɉɋɍɏɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɩɪɫɬɭɮɯɰɱɲɳɴɵɶɷɸɹɺɻɼɽɾɿʀʁʂʃʄʅʆʇʈʉʊʋʌʍʎʏʐʑʒʓʕʖʗʘʙʚʛʜʝʞʟʠʡʢʣʤʥʦʧʨʩʪʫʬʭʮʯͱͳͷͻͼͽΐάέήίΰαβγδεζηθικλμνξοπρςστυφχψωϊϋόύώϐϑϕϖϗϙϛϝϟϡϣϥϧϩϫϭϯϰϱϲϳϵϸϻϼабвгдежзийклмнопрстуфхцчшщъыьэюяѐёђѓєѕіїјљњћќѝўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎӏӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹӻӽӿԁԃԅԇԉԋԍԏԑԓԕԗԙԛԝԟԡԣԥԧԩԫԭԯաբգդեզէըթժիլխծկհձղճմյնշոչպջռսվտրցւփքօֆևᏸᏹᏺᏻᏼᏽᲀᲁᲂᲃᲄᲅᲆᲇᲈᴀᴁᴂᴃᴄᴅᴆᴇᴈᴉᴊᴋᴌᴍᴎᴏᴐᴑᴒᴓᴔᴕᴖᴗᴘᴙᴚᴛᴜᴝᴞᴟᴠᴡᴢᴣᴤᴥᴦᴧᴨᴩᴪᴫᵫᵬᵭᵮᵯᵰᵱᵲᵳᵴᵵᵶᵷᵹᵺᵻᵼᵽᵾᵿᶀᶁᶂᶃᶄᶅᶆᶇᶈᶉᶊᶋᶌᶍᶎᶏᶐᶑᶒᶓᶔᶕᶖᶗᶘᶙᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕẖẗẘẙẚẛẜẝẟạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹỻỽỿἀἁἂἃἄἅἆἇἐἑἒἓἔἕἠἡἢἣἤἥἦἧἰἱἲἳἴἵἶἷὀὁὂὃὄὅὐὑὒὓὔὕὖὗὠὡὢὣὤὥὦὧὰάὲέὴήὶίὸόὺύὼώᾀᾁᾂᾃᾄᾅᾆᾇᾐᾑᾒᾓᾔᾕᾖᾗᾠᾡᾢᾣᾤᾥᾦᾧᾰᾱᾲᾳᾴᾶᾷιῂῃῄῆῇῐῑῒΐῖῗῠῡῢΰῤῥῦῧῲῳῴῶῷℊℎℏℓℯℴℹℼℽⅆⅇⅈⅉⅎↄⰰⰱⰲⰳⰴⰵⰶⰷⰸⰹⰺⰻⰼⰽⰾⰿⱀⱁⱂⱃⱄⱅⱆⱇⱈⱉⱊⱋⱌⱍⱎⱏⱐⱑⱒⱓⱔⱕⱖⱗⱘⱙⱚⱛⱜⱝⱞⱡⱥⱦⱨⱪⱬⱱⱳⱴⱶⱷⱸⱹⱺⱻⲁⲃⲅⲇⲉⲋⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿⳁⳃⳅⳇⳉⳋⳍⳏⳑⳓⳕⳗⳙⳛⳝⳟⳡⳣⳤⳬⳮⳳⴀⴁⴂⴃⴄⴅⴆⴇⴈⴉⴊⴋⴌⴍⴎⴏⴐⴑⴒⴓⴔⴕⴖⴗⴘⴙⴚⴛⴜⴝⴞⴟⴠⴡⴢⴣⴤⴥⴧⴭꙁꙃꙅꙇꙉꙋꙍꙏꙑꙓꙕꙗꙙꙛꙝꙟꙡꙣꙥꙧꙩꙫꙭꚁꚃꚅꚇꚉꚋꚍꚏꚑꚓꚕꚗꚙꚛꜣꜥꜧꜩꜫꜭꜯꜰꜱꜳꜵꜷꜹꜻꜽꜿꝁꝃꝅꝇꝉꝋꝍꝏꝑꝓꝕꝗꝙꝛꝝꝟꝡꝣꝥꝧꝩꝫꝭꝯꝱꝲꝳꝴꝵꝶꝷꝸꝺꝼꝿꞁꞃꞅꞇꞌꞎꞑꞓꞔꞕꞗꞙꞛꞝꞟꞡꞣꞥꞧꞩꞵꞷꟺꬰꬱꬲꬳꬴꬵꬶꬷꬸꬹꬺꬻꬼꬽꬾꬿꭀꭁꭂꭃꭄꭅꭆꭇꭈꭉꭊꭋꭌꭍꭎꭏꭐꭑꭒꭓꭔꭕꭖꭗꭘꭙꭚꭠꭡꭢꭣꭤꭥꭰꭱꭲꭳꭴꭵꭶꭷꭸꭹꭺꭻꭼꭽꭾꭿꮀꮁꮂꮃꮄꮅꮆꮇꮈꮉꮊꮋꮌꮍꮎꮏꮐꮑꮒꮓꮔꮕꮖꮗꮘꮙꮚꮛꮜꮝꮞꮟꮠꮡꮢꮣꮤꮥꮦꮧꮨꮩꮪꮫꮬꮭꮮꮯꮰꮱꮲꮳꮴꮵꮶꮷꮸꮹꮺꮻꮼꮽꮾꮿfffiflffifflſtstﬓﬔﬕﬖﬗabcdefghijklmnopqrstuvwxyz" +letter_titlecase = "DžLjNjDzᾈᾉᾊᾋᾌᾍᾎᾏᾘᾙᾚᾛᾜᾝᾞᾟᾨᾩᾪᾫᾬᾭᾮᾯᾼῌῼ" +letter_modifier = "ʰʱʲʳʴʵʶʷʸʹʺʻʼʽʾʿˀˁˆˇˈˉˊˋˌˍˎˏːˑˠˡˢˣˤˬˮʹͺՙـۥۦߴߵߺࠚࠤࠨॱๆໆჼៗᡃᪧᱸᱹᱺᱻᱼᱽᴬᴭᴮᴯᴰᴱᴲᴳᴴᴵᴶᴷᴸᴹᴺᴻᴼᴽᴾᴿᵀᵁᵂᵃᵄᵅᵆᵇᵈᵉᵊᵋᵌᵍᵎᵏᵐᵑᵒᵓᵔᵕᵖᵗᵘᵙᵚᵛᵜᵝᵞᵟᵠᵡᵢᵣᵤᵥᵦᵧᵨᵩᵪᵸᶛᶜᶝᶞᶟᶠᶡᶢᶣᶤᶥᶦᶧᶨᶩᶪᶫᶬᶭᶮᶯᶰᶱᶲᶳᶴᶵᶶᶷᶸᶹᶺᶻᶼᶽᶾᶿⁱⁿₐₑₒₓₔₕₖₗₘₙₚₛₜⱼⱽⵯⸯ々〱〲〳〴〵〻ゝゞーヽヾꀕꓸꓹꓺꓻꓼꓽꘌꙿꚜꚝꜗꜘꜙꜚꜛꜜꜝꜞꜟꝰꞈꟸꟹꧏꧦꩰꫝꫳꫴꭜꭝꭞꭟー゙゚" +number_letter = "ᛮᛯᛰⅠⅡⅢⅣⅤⅥⅦⅧⅨⅩⅪⅫⅬⅭⅮⅯⅰⅱⅲⅳⅴⅵⅶⅷⅸⅹⅺⅻⅼⅽⅾⅿↀↁↂↅↆↇↈ〇〡〢〣〤〥〦〧〨〩〸〹〺ꛦꛧꛨꛩꛪꛫꛬꛭꛮꛯ𐅀𐅁𐅂𐅃𐅄𐅅𐅆𐅇𐅈𐅉𐅊𐅋𐅌𐅍𐅎𐅏𐅐𐅑𐅒𐅓𐅔𐅕𐅖𐅗𐅘𐅙𐅚𐅛𐅜𐅝𐅞𐅟𐅠𐅡𐅢𐅣𐅤𐅥𐅦𐅧𐅨𐅩𐅪𐅫𐅬𐅭𐅮𐅯𐅰𐅱𐅲𐅳𐅴𐍁𐍊𐏑𐏒𐏓𐏔𐏕𒐀𒐁𒐂𒐃𒐄𒐅𒐆𒐇𒐈𒐉𒐊𒐋𒐌𒐍𒐎𒐏𒐐𒐑𒐒𒐓𒐔𒐕𒐖𒐗𒐘𒐙𒐚𒐛𒐜𒐝𒐞𒐟𒐠𒐡𒐢𒐣𒐤𒐥𒐦𒐧𒐨𒐩𒐪𒐫𒐬𒐭𒐮𒐯𒐰𒐱𒐲𒐳𒐴𒐵𒐶𒐷𒐸𒐹𒐺𒐻𒐼𒐽𒐾𒐿𒑀𒑁𒑂𒑃𒑄𒑅𒑆𒑇𒑈𒑉𒑊𒑋𒑌𒑍𒑎𒑏𒑐𒑑𒑒𒑓𒑔𒑕𒑖𒑗𒑘𒑙𒑚𒑛𒑜𒑝𒑞𒑟𒑠𒑡𒑢𒑣𒑤𒑥𒑦𒑧𒑨𒑩𒑪𒑫𒑬𒑭𒑮" +print(unicodedata.unidata_version)
\ No newline at end of file |