Модул:scripts/recognition data
Ин модул аломатҳои Юникодро (нуқтаҳои код) ба рамзҳои скрипти Виклюгатсия алоқаманд мекунад. Он аз ҷониби функсияи findBestScriptWithoutLang дар Module:scripts истифода мешавад.
Он тавассути як қатор функсияҳо дар Module:User:Erutuon/script recognition скрипт аз намунаҳои скрипт дар Module:scripts/data тавлид шудааст. Ҳар вақте ки намунаҳои скрипт илова ё тағир дода мешаванд, он бояд барқарор карда шавад. Функсияҳои highlight_dump ва modified_dump дар Module:debug барои чопи натиҷа аз Module:User:Erutuon/script recognition истифода шуданд.
Барои фаҳмонидани формат, калидҳои аввал гурӯҳҳои 4096 кодҳо мебошанд (0x1000 дар заминаи шонздаҳӣ). Калиди 0 барои гурӯҳи якуми 4096 нуқтаҳои рамзӣ аз U+000 то U+FFF мебошад. Дар дохили ҷадвалҳо барои ҳар як блоки кодҳо, синтаксиси { 0x41, 0x5A, "Latn" } нишон медиҳад, ки ҳамаи аломатҳо аз рамзи 0x41 (U+0041 ё аломати A) то рамзи 0x5A (U+005A ё аломати Z) ба хати лотинӣ. Ҷадвали 0x5A ҳамаи нуқтаҳои рамзии инфиродиро дар бар мегирад, ки ба скрипт тааллуқ доранд, вале дар дохили диапазон пайдо намешаванд.
Эҳтиёт бошед: сарфи назар аз он ки аз ҷониби Module:Unicode data додаҳо истифода мешавад, он аз синфҳои скрипти Wiktionary тавлид шудааст.
Ихтилофҳо байни маҷмӯи аломатҳои скриптҳои гуногун
вироишИн модул назар ба Модул:scripts/data камтар скриптҳоро дар бар мегирад, зеро баъзе скриптҳо умуман аломат надоранд ва маҷмӯи аломатҳои баъзе скриптҳо бо ҳамдигар мухолифанд. Инҳоянд роҳҳои ҳалли низоъҳо.
Скриптҳо хориҷ карда мешаванд, агар онҳо дорои аломатҳои якхела бо скрипти дигари асосӣ бошанд ё аз ду ё зиёда скриптҳои дигар иборат бошанд. Масалан, fa-Arab хориҷ карда шудааст, зеро он дорои ҳамон аломатҳо бо Arab ва Jpan партофта шудааст, зеро он аз Hani иборат аст. , Hira ва Kana.
Агар скрипт аз аломатҳои скрипти дигар ва бо иловаи баъзе аломатҳои беназир иборат бошад, танҳо аломатҳои нодир ба скрипт тааллуқ доранд. Масалан, polytonic аз аломатҳои Grek иборат аст, ки дар имлои монотонии Юнонии муосир истифода мешаванд, инчунин аломатҳои барои Юнони Қадим; дар ин модул танҳо аломатҳои юнонии қадим ҳамчун polytonic ҳисоб карда мешаванд. Бо Cyrs ва Cyrl, Latinx ва Latn низ ҳамин тавр аст.
return {
[0x00] = {
{ 0x00041, 0x0005A, "Latn"},
{ 0x00061, 0x0007A, "Latn"},
{ 0x000C0, 0x000D6, "Latn"},
{ 0x000D8, 0x000F6, "Latn"},
{ 0x000F8, 0x0024F, "Latn"},
{ 0x00370, 0x003E1, "Grek", "Polyt" },
{ 0x003E2, 0x003EF, "Copt" },
{ 0x003F0, 0x003FF, "Grek", "Polyt" },
{ 0x00400, 0x0045F, "Cyrl" },
{ 0x00460, 0x00469, "Cyrs" },
{ 0x0046A, 0x0046D, "Cyrl" },
{ 0x0046E, 0x00471, "Cyrs" },
{ 0x00472, 0x00475, "Cyrl" },
{ 0x00476, 0x00489, "Cyrs" },
{ 0x0048A, 0x00527, "Cyrl" },
{ 0x00531, 0x0058F, "Armn" },
{ 0x00590, 0x005FF, "Hebr" },
{ 0x00600, 0x006FF, "Arab" },
{ 0x00700, 0x0074F, "Syrc" },
{ 0x00750, 0x0077F, "Arab" },
{ 0x00780, 0x007B1, "Thaa" },
{ 0x007C0, 0x007FF, "Nkoo" },
{ 0x00800, 0x0083E, "Samr" },
{ 0x00840, 0x0085E, "Mand" },
{ 0x00860, 0x0086A, "Syrc" },
{ 0x008A0, 0x008FF, "Arab" },
{ 0x00900, 0x0097F, "Deva" },
{ 0x00980, 0x00983, "Beng" },
{ 0x00985, 0x0098C, "Beng" },
{ 0x00993, 0x009A8, "Beng" },
{ 0x009AA, 0x009B0, "Beng" },
{ 0x009B6, 0x009B9, "Beng" },
{ 0x009BC, 0x009C4, "Beng" },
{ 0x009CB, 0x009CE, "Beng" },
{ 0x009E0, 0x009E3, "Beng" },
{ 0x009E6, 0x009EF, "Beng" },
{ 0x009F0, 0x009F1, "as-Beng" },
{ 0x00A01, 0x00A76, "Guru" },
{ 0x00A81, 0x00AF1, "Gujr" },
{ 0x00B01, 0x00B77, "Orya" },
{ 0x00B82, 0x00BFA, "Taml" },
{ 0x00C00, 0x00C7F, "Telu" },
{ 0x00C80, 0x00CF2, "Knda" },
{ 0x00D02, 0x00D7F, "Mlym" },
{ 0x00D82, 0x00DF4, "Sinh" },
{ 0x00E01, 0x00E5B, "Thai" },
{ 0x00E81, 0x00EDF, "Laoo" },
{ 0x00F00, 0x00FDA, "Tibt" },
length = 48,
},
[0x01] = {
{ 0x01000, 0x0109F, "Mymr" },
{ 0x010A0, 0x010CD, "Geok" },
{ 0x010D0, 0x010FF, "Geor" },
{ 0x01100, 0x011FF, "Hang" },
{ 0x01200, 0x01399, "Ethi" },
{ 0x013A0, 0x013F4, "Cher" },
{ 0x01400, 0x0167F, "Cans" },
{ 0x01680, 0x0169C, "Ogam" },
{ 0x016A0, 0x016F0, "Runr" },
{ 0x01700, 0x01714, "Tglg" },
{ 0x01720, 0x01734, "Hano" },
{ 0x01740, 0x01753, "Buhd" },
{ 0x01760, 0x01773, "Tagb" },
{ 0x01780, 0x017F9, "Khmr" },
{ 0x01800, 0x018AA, "Mong" },
{ 0x01900, 0x0194F, "Limb" },
{ 0x01950, 0x01974, "Tale" },
{ 0x01980, 0x019DF, "Talu" },
{ 0x019E0, 0x019FF, "Khmr" },
{ 0x01A00, 0x01A1F, "Bugi" },
{ 0x01A20, 0x01AAD, "Lana" },
{ 0x01B00, 0x01B7C, "Bali" },
{ 0x01B80, 0x01BBF, "Sund" },
{ 0x01BC0, 0x01BFF, "Batk" },
{ 0x01C00, 0x01C4F, "Lepc" },
{ 0x01C50, 0x01C7F, "Olck" },
{ 0x01C90, 0x01CBF, "Geor" },
{ 0x01E00, 0x01EFF, "Latn" },
{ 0x01F00, 0x01FFE, "Polyt" },
length = 29,
},
[0x02] = {
{ 0x02190, 0x021FF, "Zsym" },
{ 0x02200, 0x022FF, "Zmth" },
{ 0x02300, 0x023FF, "Zsym" },
{ 0x02500, 0x027BF, "Zsym" },
{ 0x027C0, 0x027EF, "Zmth" },
{ 0x02800, 0x028FF, "Brai" },
{ 0x02980, 0x02AFF, "Zmth" },
{ 0x02B00, 0x02BFE, "Zsym" },
{ 0x02C00, 0x02C5E, "Glag" },
{ 0x02C60, 0x02C7F, "Latn" },
{ 0x02C80, 0x02CFF, "Copt" },
{ 0x02D00, 0x02D2D, "Geok" },
{ 0x02D30, 0x02D7F, "Tfng" },
{ 0x02D80, 0x02DDE, "Ethi" },
{ 0x02E80, 0x02FDF, "Hani" },
length = 15,
},
[0x03] = {
{ 0x03001, 0x03002, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" },
{ 0x03003, 0x03007, "Hani" },
{ 0x03008, 0x03011, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" },
{ 0x03012, 0x03013, "Hani" },
{ 0x03014, 0x0301B, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" },
{ 0x0301C, 0x0301F, "Hani", "Bopo", "Hang", "Hira", "Kana" },
{ 0x03020, 0x0303F, "Hani" },
{ 0x03041, 0x0309F, "Hira" },
{ 0x030A0, 0x030FF, "Kana" },
{ 0x03105, 0x0312F, "Bopo" },
{ 0x03131, 0x0318E, "Hang" },
{ 0x031A0, 0x031BA, "Bopo" },
{ 0x031C0, 0x031E3, "Hani" },
{ 0x031F0, 0x031FF, "Kana" },
{ 0x03220, 0x03247, "Hani" },
{ 0x03280, 0x032B0, "Hani" },
{ 0x032C0, 0x032CB, "Hani" },
{ 0x03300, 0x03357, "Kana" },
{ 0x03358, 0x03370, "Hani" },
{ 0x0337B, 0x0337F, "Hani" },
{ 0x033E0, 0x033FE, "Hani" },
{ 0x03400, 0x03FFF, "Hani" },
length = 22,
},
[0x04] = {
{ 0x04000, 0x04DB5, "Hani" },
{ 0x04E00, 0x04FFF, "Hani" },
length = 2,
},
[0x05] = {
{ 0x05000, 0x05FFF, "Hani" },
length = 1,
},
[0x06] = {
{ 0x06000, 0x06FFF, "Hani" },
length = 1,
},
[0x07] = {
{ 0x07000, 0x07FFF, "Hani" },
length = 1,
},
[0x08] = {
{ 0x08000, 0x08FFF, "Hani" },
length = 1,
},
[0x09] = {
{ 0x09000, 0x09FFF, "Hani" },
length = 1,
},
[0x0A] = {
{ 0x0A000, 0x0A4C6, "Yiii" },
{ 0x0A4D0, 0x0A4FF, "Lisu" },
{ 0x0A500, 0x0A62B, "Vaii" },
{ 0x0A640, 0x0A67F, "Cyrs" },
{ 0x0A680, 0x0A697, "Cyrl" },
{ 0x0A6A0, 0x0A6F7, "Bamu" },
{ 0x0A720, 0x0A7FF, "Latn" },
{ 0x0A800, 0x0A82B, "Sylo" },
{ 0x0A830, 0x0A832, "Deva", "Dogr", "Gujr", "Guru", "Khoj", "Knda", "Kthi", "Mahj", "Modi", "Nand", "Sind", "Takr", "Tirh"},
{ 0x0A833, 0x0A835, "Deva", "Dogr", "Gujr", "Guru", "Khoj", "Knda", "Kthi", "Mahj", "Mlym", "Modi", "Nand", "Sind", "Takr", "Tirh"},
{ 0x0A836, 0x0A839, "Deva", "Dogr", "Gujr", "Guru", "Khoj", "Kthi", "Mahj", "Modi", "Sind", "Takr", "Tirh"},
{ 0x0A840, 0x0A877, "Phag" },
{ 0x0A880, 0x0A8D9, "Saur" },
{ 0x0A8E0, 0x0A8FF, "Deva" },
{ 0x0A900, 0x0A92F, "Kali" },
{ 0x0A930, 0x0A95F, "Rjng" },
{ 0x0A980, 0x0A9DF, "Java" },
{ 0x0A9E0, 0x0A9FE, "Mymr" },
{ 0x0AA00, 0x0AA5F, "Cham" },
{ 0x0AA60, 0x0AA7F, "Mymr" },
{ 0x0AA80, 0x0AADF, "Tavt" },
{ 0x0AAE0, 0x0AAFF, "Mtei" },
{ 0x0AB01, 0x0AB2E, "Ethi" },
{ 0x0AB30, 0x0AB65, "Latn" },
{ 0x0AB70, 0x0ABBF, "Cher" },
{ 0x0ABC0, 0x0ABFF, "Mtei" },
{ 0x0AC00, 0x0AFFF, "Hang" },
length = 27,
},
[0x0B] = {
{ 0x0B000, 0x0BFFF, "Hang" },
length = 1,
},
[0x0C] = {
{ 0x0C000, 0x0CFFF, "Hang" },
length = 1,
},
[0x0D] = {
{ 0x0D000, 0x0D7A3, "Hang" },
length = 1,
},
[0x0F] = {
{ 0x0FA27, 0x0FA29, "Hani" },
{ 0x0FB13, 0x0FB17, "Armn" },
{ 0x0FB1D, 0x0FB4F, "Hebr" },
{ 0x0FB50, 0x0FDFD, "Arab" },
{ 0x0FE45, 0x0FE46, "Hani", "Bopo", "Hang", "Hira", "Kana" },
{ 0x0FE70, 0x0FEFC, "Arab" },
{ 0x0FF61, 0x0FF65, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" },
length = 7,
},
[0x10] = {
{ 0x10000, 0x100FA, "Linb" },
{ 0x10280, 0x1029C, "Lyci" },
{ 0x102A0, 0x102D0, "Cari" },
{ 0x102E1, 0x102FB, "Copt" },
{ 0x10300, 0x10323, "Ital" },
{ 0x10330, 0x1034A, "Goth" },
{ 0x10350, 0x1037A, "Perm" },
{ 0x10380, 0x1039F, "Ugar" },
{ 0x103A0, 0x103D5, "Xpeo" },
{ 0x10400, 0x1044F, "Dsrt" },
{ 0x10450, 0x1047F, "Shaw" },
{ 0x10480, 0x104A9, "Osma" },
{ 0x104B0, 0x104FB, "Osge" },
{ 0x10500, 0x10527, "Elba" },
{ 0x10530, 0x10563, "Aghb" },
{ 0x10600, 0x10767, "Lina" },
{ 0x10800, 0x1083F, "Cprt" },
{ 0x10840, 0x1085F, "Armi" },
{ 0x10860, 0x1087F, "Palm" },
{ 0x10880, 0x108AF, "Nbat" },
{ 0x108E0, 0x108FF, "Hatr" },
{ 0x10900, 0x1091F, "Phnx" },
{ 0x10920, 0x1093F, "Lydi" },
{ 0x10980, 0x1099F, "Mero" },
{ 0x109A0, 0x109BF, "Merc" },
{ 0x10A00, 0x10A58, "Khar" },
{ 0x10A60, 0x10A7F, "Sarb" },
{ 0x10A80, 0x10A9F, "Narb" },
{ 0x10AC0, 0x10AF6, "Mani" },
{ 0x10B00, 0x10B3F, "Avst" },
{ 0x10B40, 0x10B5F, "Prti" },
{ 0x10B60, 0x10B7F, "Phli" },
{ 0x10B80, 0x10BAF, "Phlp" },
{ 0x10C00, 0x10C48, "Orkh" },
{ 0x10C80, 0x10CB2, "Hung" },
{ 0x10D00, 0x10D39, "Rohg" },
{ 0x10E60, 0x10E7E, "Rumin" },
{ 0x10F00, 0x10F27, "Sogo" },
{ 0x10F30, 0x10F59, "Sogd" },
{ 0x10F70, 0x10FAF, "Ougr" },
{ 0x10FE0, 0x10FFF, "Elym" },
length = 41,
},
[0x11] = {
{ 0x11000, 0x1107F, "Brah" },
{ 0x11080, 0x110CD, "Kthi" },
{ 0x110D0, 0x110F9, "Sora" },
{ 0x11100, 0x11146, "Cakm" },
{ 0x11150, 0x11176, "Mahj" },
{ 0x11180, 0x111D9, "Shrd" },
{ 0x11200, 0x1123D, "Khoj" },
{ 0x11280, 0x112A9, "Mult" },
{ 0x112B0, 0x112F9, "Sind" },
{ 0x11301, 0x11374, "Gran" },
{ 0x11400, 0x1145E, "Newa" },
{ 0x11480, 0x114D9, "Tirh" },
{ 0x11580, 0x115DD, "Sidd" },
{ 0x11600, 0x11659, "Modi" },
{ 0x11680, 0x116C9, "Takr" },
{ 0x11700, 0x1173F, "Ahom" },
{ 0x11800, 0x1183B, "Dogr" },
{ 0x118A0, 0x118FF, "Wara" },
{ 0x119A0, 0x119FF, "Nand" },
{ 0x11A00, 0x11A47, "Zanb" },
{ 0x11A50, 0x11AA2, "Soyo" },
{ 0x11AC0, 0x11AF8, "Pauc" },
{ 0x11C00, 0x11C6C, "Bhks" },
{ 0x11C70, 0x11CB6, "Marc" },
{ 0x11D00, 0x11D59, "Gonm" },
{ 0x11D60, 0x11DA9, "Gong" },
{ 0x11EE0, 0x11EF8, "Maka" },
length = 27,
},
[0x12] = {
{ 0x12000, 0x1236E, "Xsux" },
{ 0x12400, 0x12473, "Xsux" },
{ 0x12F90, 0x12FFF, "Cpmn" },
length = 3,
},
[0x13] = {
{ 0x13000, 0x1342E, "Egyp" },
length = 1,
},
[0x14] = {
{ 0x14400, 0x14646, "Hluw" },
length = 1,
},
[0x16] = {
{ 0x16800, 0x16A38, "Bamu" },
{ 0x16A40, 0x16A6F, "Mroo" },
{ 0x16AD0, 0x16AF5, "Bass" },
{ 0x16B00, 0x16B8F, "Hmng" },
{ 0x16E40, 0x16E9A, "Medf" },
{ 0x16F00, 0x16F9F, "Plrd" },
length = 6,
},
[0x17] = {
{ 0x17000, 0x17FFF, "Tang" },
length = 1,
},
[0x18] = {
{ 0x18000, 0x18AF2, "Tang" },
length = 1,
},
[0x1B] = {
{ 0x1B001, 0x1B11E, "Hira" },
{ 0x1B170, 0x1B2FB, "Nshu" },
{ 0x1BC00, 0x1BC9F, "Dupl" },
length = 3,
},
[0x1D] = {
{ 0x1D100, 0x1D1DD, "Music" },
{ 0x1D2E0, 0x1D2F3, "Maya" },
{ 0x1D400, 0x1D7FF, "Zmth" },
{ 0x1D800, 0x1DAAF, "Sgnw" },
length = 4,
},
[0x1E] = {
{ 0x1E000, 0x1E02A, "Glag" },
{ 0x1E800, 0x1E8D6, "Mend" },
{ 0x1E900, 0x1E95F, "Adlm" },
length = 3,
},
[0x1F] = {
{ 0x1F000, 0x1F0F5, "Zsym" },
{ 0x1F300, 0x1FA6D, "Zsym" },
length = 2,
},
[0x20] = {
{ 0x20000, 0x20FFF, "Hani" },
length = 1,
},
[0x21] = {
{ 0x21000, 0x21FFF, "Hani" },
length = 1,
},
[0x22] = {
{ 0x22000, 0x22FFF, "Hani" },
length = 1,
},
[0x23] = {
{ 0x23000, 0x23FFF, "Hani" },
length = 1,
},
[0x24] = {
{ 0x24000, 0x24FFF, "Hani" },
length = 1,
},
[0x25] = {
{ 0x25000, 0x25FFF, "Hani" },
length = 1,
},
[0x26] = {
{ 0x26000, 0x26FFF, "Hani" },
length = 1,
},
[0x27] = {
{ 0x27000, 0x27FFF, "Hani" },
length = 1,
},
[0x28] = {
{ 0x28000, 0x28FFF, "Hani" },
length = 1,
},
[0x29] = {
{ 0x29000, 0x29FFF, "Hani" },
length = 1,
},
[0x2A] = {
{ 0x2A000, 0x2AFFF, "Hani" },
length = 1,
},
[0x2B] = {
{ 0x2B000, 0x2BFFF, "Hani" },
length = 1,
},
[0x2C] = {
{ 0x2C000, 0x2CFFF, "Hani" },
length = 1,
},
[0x2D] = {
{ 0x2D000, 0x2DFFF, "Hani" },
length = 1,
},
[0x2E] = {
{ 0x2E000, 0x2EBE0, "Hani" },
length = 1,
},
individual = {
[0x00462] = "Cyrl",
[0x00463] = "Cyrl",
[0x0060C] = "Arab, Nkoo, Rohg, Syrc, Thaa, Yezi",
[0x0061B] = "Arab, Nkoo, Rohg, Syrc, Thaa, Yezi",
[0x0061F] = "Arab, Adlm, Nkoo, Rohg, Syrc, Thaa, Yezi",
[0x00640] = "Arab, Adlm, Mand, Mani, Ougr, Phlp, Rohg, Sogd, Syrc",
[0x00951] = "Deva, Beng, Gran, Gujr, Guru, Knda, Latn, Mlym, Orya, Shrd, Taml, Telu, Tirh",
[0x00952] = "Deva, Beng, Gran, Gujr, Guru, Knda, Latn, Mlym, Orya, Taml, Telu, Tirh",
[0x00964] = "Deva, Beng, Dogr, Gong, Gonm, Gran, Gujr, Guru, Knda, Mahj, Mlym, Nand, Orya, Sind, Sinh, Sylo, Takr, Taml, Telu, Tirh",
[0x00965] = "Deva, Beng, Dogr, Gong, Gonm, Gran, Gujr, Guru, Knda, Limb, Mahj, Mlym, Nand, Orya, Sind, Sinh, Sylo, Takr, Taml, Telu, Tirh",
[0x0098F] = "Beng",
[0x00990] = "Beng",
[0x009A1] = "Beng",
[0x009A2] = "Beng",
[0x009AF] = "Beng",
[0x009B2] = "Beng",
[0x009BC] = "Beng",
[0x009C7] = "Beng",
[0x009C8] = "Beng",
[0x009D7] = "Beng",
[0x01CDA] = "Deva, Knda, Mlym, Orya, Taml, Telu",
[0x01CF2] = "Deva, Beng, Gran, Knda, Nand, Orya, Telu, Tirh",
[0x02135] = "Zmth",
[0x03000] = "Hani",
[0x03003] = "Hani, Bopo, Hang, Hira, Kana",
[0x03013] = "Hani, Bopo, Hang, Hira, Kana",
[0x03030] = "Hani, Bopo, Hang, Hira, Kana",
[0x03037] = "Hani, Bopo, Hang, Hira, Kana",
[0x030FB] = "Kana, Hani, Bopo, Hang, Hira, Yiii",
[0x032FF] = "Hani",
[0x0FA0E] = "Hani",
[0x0FA0F] = "Hani",
[0x0FA11] = "Hani",
[0x0FA13] = "Hani",
[0x0FA14] = "Hani",
[0x0FA1F] = "Hani",
[0x0FA21] = "Hani",
[0x0FA23] = "Hani",
[0x0FA24] = "Hani",
[0x1056F] = "Aghb",
[0x16FE0] = "Tang",
[0x16FE1] = "Nshu",
[0x1B000] = "Kana",
},
blocks = {
{ 0x04, 0x09, "Hani" },
{ 0x0B, 0x0D, "Hang" },
{ 0x17, 0x18, "Tang" },
{ 0x20, 0x2E, "Hani" },
},
}