1<?xml version="1.0" encoding="UTF-8" ?> 2<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd"> 3<!-- 4Copyright © 1991-2013 Unicode, Inc. 5CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/) 6For terms of use, see http://www.unicode.org/copyright.html 7--> 8<supplementalData> 9 <version number="$Revision: 12263 $"/> 10 <transforms> 11 <transform source="Cyrl" target="Latn" direction="both" alias="Cyrillic-Latin und-Latn-t-und-cyrl" backwardAlias="Latin-Cyrillic und-Cyrl-t-und-latn"> 12 <tRule> 13# TODO: add remaining characters 14# Should add variants for Russian-English, Russian-German 15# Those can use this as a base, and then remap cases 16# like a $hat to ya or ja. 17# :: [\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:]] ; 18### WARNING, ̈ must be added to the generated filters, in both directions ### 19# MINIMAL FILTER 20:: [Ққ̈Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ̆Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ; 21:: NFD (NFC) ; 22$modprime = ʹ; 23$modprime2 = ʺ; 24$grave = ̀; 25$acute = ́; 26$hat = ̂; 27$breve = ̆ ; 28$dot = ̇ ; 29$caron = ̌ ; 30$comma = ̦ ; 31$under = ̱ ; 32$descender = ˌ; 33# move up so not masked 34я ↔ a $hat ; # CYRILLIC SMALL LETTER YA 35Я ↔ A $hat ; # CYRILLIC CAPITAL LETTER YA 36ч ↔ c $caron ; # CYRILLIC SMALL LETTER CHE 37Ч ↔ C $caron; # CYRILLIC CAPITAL LETTER CHE 38# ҷ ↔ XXX ; # CYRILLIC SMALL LETTER CHE WITH DESCENDER 39# Ҷ ↔ XXX ; # CYRILLIC CAPITAL LETTER CHE WITH DESCENDER 40# ӌ ↔ XXX ; # CYRILLIC SMALL LETTER KHAKASSIAN CHE 41# Ӌ ↔ XXX ; # CYRILLIC CAPITAL LETTER KHAKASSIAN CHE 42# ҹ ↔ XXX ; # CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE 43# Ҹ ↔ XXX ; # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE 44э ↔ e $acute; # CYRILLIC SMALL LETTER E 45Э ↔ E $acute; # CYRILLIC CAPITAL LETTER E 46є ↔ e $hat; # CYRILLIC SMALL LETTER UKRAINIAN IE 47Є ↔ E $hat; # CYRILLIC CAPITAL LETTER UKRAINIAN IE 48ш ↔ s $caron ; # CYRILLIC SMALL LETTER SHA 49Ш ↔ S $caron ; # CYRILLIC CAPITAL LETTER SHA 50щ ↔ s $hat ; # CYRILLIC SMALL LETTER SHCHA 51Щ ↔ S $hat; # CYRILLIC CAPITAL LETTER SHCHA 52ѕ ↔ z $hat ; # CYRILLIC SMALL LETTER DZE 53Ѕ ↔ Z $hat; # CYRILLIC CAPITAL LETTER DZE 54# ӡ ↔ XXX ; # CYRILLIC SMALL LETTER ABKHASIAN DZE 55# Ӡ ↔ XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN DZE 56ю ↔ u $hat ; # CYRILLIC SMALL LETTER YU 57Ю ↔ U $hat ; # CYRILLIC CAPITAL LETTER YU 58і ↔ i $acute; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 59І ↔ I $acute; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I 60ј ↔ j $caron; # CYRILLIC SMALL LETTER JE 61Ј ↔ J $caron; # CYRILLIC CAPITAL LETTER JE 62љ ↔ l $hat ; # CYRILLIC SMALL LETTER LJE 63Љ ↔ L $hat ; # CYRILLIC CAPITAL LETTER LJE 64њ ↔ n $hat ; # CYRILLIC SMALL LETTER NJE 65Њ ↔ N $hat ; # CYRILLIC CAPITAL LETTER NJE 66ћ ↔ c $acute ; # CYRILLIC SMALL LETTER TSHE 67Ћ ↔ C $acute ; # CYRILLIC CAPITAL LETTER TSHE 68џ ↔ d $hat ; # CYRILLIC SMALL LETTER DZHE 69Џ ↔ D $hat ; # CYRILLIC CAPITAL LETTER DZHE 70# Normal order 71а ↔ a ; # CYRILLIC SMALL LETTER A 72А ↔ A ; # CYRILLIC CAPITAL LETTER A 73ә ↔ ə ; # CYRILLIC SMALL LETTER SCHWA 74Ә ↔ Ə ; # CYRILLIC CAPITAL LETTER SCHWA 75ӕ ↔ æ ; # CYRILLIC SMALL LIGATURE A IE 76Ӕ ↔ Æ ; # CYRILLIC CAPITAL LIGATURE A IE 77б ↔ b ; # CYRILLIC SMALL LETTER BE 78Б ↔ B ; # CYRILLIC CAPITAL LETTER BE 79в ↔ v ; # CYRILLIC SMALL LETTER VE 80В ↔ V ; # CYRILLIC CAPITAL LETTER VE 81ґ ↔ g $grave ; # CYRILLIC SMALL LETTER GHE WITH UPTURN 82Ґ ↔ G $grave ; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN 83ғ ↔ g $dot ; # CYRILLIC SMALL LETTER GHE WITH STROKE 84Ғ ↔ G $dot; # CYRILLIC CAPITAL LETTER GHE WITH STROKE 85ҕ ↔ g $breve; # CYRILLIC SMALL LETTER GHE WITH MIDDLE HOOK 86Ҕ ↔ G $breve; # CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK 87г ↔ g ; # CYRILLIC SMALL LETTER GHE 88Г ↔ G ; # CYRILLIC CAPITAL LETTER GHE 89д ↔ d; # CYRILLIC SMALL LETTER DE 90Д ↔ D; # CYRILLIC CAPITAL LETTER DE 91ђ ↔ đ ; # CYRILLIC SMALL LETTER DJE 92Ђ ↔ Đ ; # CYRILLIC CAPITAL LETTER DJE 93ҙ ↔ z $comma ; # CYRILLIC SMALL LETTER ZE WITH DESCENDER 94Ҙ ↔ Z $comma ; # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER 95е ↔ e ; # CYRILLIC SMALL LETTER IE 96Е ↔ E; # CYRILLIC CAPITAL LETTER IE 97ж ↔ z $caron; # CYRILLIC SMALL LETTER ZHE 98Ж ↔ Z $caron; # CYRILLIC CAPITAL LETTER ZHE 99# җ ↔ XXX ; # CYRILLIC SMALL LETTER ZHE WITH DESCENDER 100# Җ ↔ XXX ; # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER 101з ↔ z ; # CYRILLIC SMALL LETTER ZE 102З ↔ Z; # CYRILLIC CAPITAL LETTER ZE 103й ↔ j ; # CYRILLIC SMALL LETTER I 104Й ↔ J ; # CYRILLIC CAPITAL LETTER I 105и ↔ i ; # CYRILLIC SMALL LETTER I 106И ↔ I ; # CYRILLIC CAPITAL LETTER I 107қ ↔ k $descender ; # CYRILLIC SMALL LETTER KA WITH DESCENDER 108Қ ↔ K $descender ; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER 109к ↔ k ; # CYRILLIC SMALL LETTER KA 110К ↔ K; # CYRILLIC CAPITAL LETTER KA 111# ӄ ↔ XXX ; # CYRILLIC SMALL LETTER KA WITH HOOK 112# Ӄ ↔ XXX ; # CYRILLIC CAPITAL LETTER KA WITH HOOK 113# ҡ ↔ XXX ; # CYRILLIC SMALL LETTER BASHKIR KA 114# Ҡ ↔ XXX ; # CYRILLIC CAPITAL LETTER BASHKIR KA 115# ҟ ↔ XXX ; # CYRILLIC SMALL LETTER KA WITH STROKE 116# Ҟ ↔ XXX ; # CYRILLIC CAPITAL LETTER KA WITH STROKE 117# ҝ ↔ XXX ; # CYRILLIC SMALL LETTER KA WITH VERTICAL STROKE 118# Ҝ ↔ XXX ; # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE 119л ↔ l ; # CYRILLIC SMALL LETTER EL 120Л ↔ L; # CYRILLIC CAPITAL LETTER EL 121м ↔ m ; # CYRILLIC SMALL LETTER EM 122М ↔ M ; # CYRILLIC CAPITAL LETTER EM 123н ↔ n ; # CYRILLIC SMALL LETTER EN 124Н ↔ N; # CYRILLIC CAPITAL LETTER EN 125# ң ↔ XXX ; # CYRILLIC SMALL LETTER EN WITH DESCENDER 126# Ң ↔ XXX ; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER 127# ӈ ↔ XXX ; # CYRILLIC SMALL LETTER EN WITH HOOK 128# Ӈ ↔ XXX ; # CYRILLIC CAPITAL LETTER EN WITH HOOK 129# ҥ ↔ XXX ; # CYRILLIC SMALL LIGATURE EN GHE 130# Ҥ ↔ XXX ; # CYRILLIC CAPITAL LIGATURE EN GHE 131о ↔ o ; # CYRILLIC SMALL LETTER O 132О ↔ O ; # CYRILLIC CAPITAL LETTER O 133# ө ↔ XXX ; # CYRILLIC SMALL LETTER BARRED O 134# Ө ↔ XXX ; # CYRILLIC CAPITAL LETTER BARRED O 135п ↔ p ; # CYRILLIC SMALL LETTER PE 136П ↔ P ; # CYRILLIC CAPITAL LETTER PE 137# ҧ ↔ XXX ; # CYRILLIC SMALL LETTER PE WITH MIDDLE HOOK 138# Ҧ ↔ XXX ; # CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK 139# ҁ ↔ XXX ; # CYRILLIC SMALL LETTER KOPPA 140# Ҁ ↔ XXX ; # CYRILLIC CAPITAL LETTER KOPPA 141р ↔ r ; # CYRILLIC SMALL LETTER ER 142Р ↔ R ; # CYRILLIC CAPITAL LETTER ER 143# ҏ ↔ XXX ; # CYRILLIC SMALL LETTER ER WITH TICK 144# Ҏ ↔ XXX ; # CYRILLIC CAPITAL LETTER ER WITH TICK 145с ↔ s ; # CYRILLIC SMALL LETTER ES 146С ↔ S ; # CYRILLIC CAPITAL LETTER ES 147# ҫ ↔ XXX ; # CYRILLIC SMALL LETTER ES WITH DESCENDER 148# Ҫ ↔ XXX ; # CYRILLIC CAPITAL LETTER ES WITH DESCENDER 149т ↔ t ; # CYRILLIC SMALL LETTER TE 150Т ↔ T ; # CYRILLIC CAPITAL LETTER TE 151# ҭ ↔ XXX ; # CYRILLIC SMALL LETTER TE WITH DESCENDER 152# Ҭ ↔ XXX ; # CYRILLIC CAPITAL LETTER TE WITH DESCENDER 153у ↔ u ; # CYRILLIC SMALL LETTER U 154У ↔ U ; # CYRILLIC CAPITAL LETTER U 155# ү ↔ XXX ; # CYRILLIC SMALL LETTER STRAIGHT U 156# Ү ↔ XXX ; # CYRILLIC CAPITAL LETTER STRAIGHT U 157# ұ ↔ XXX ; # CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE 158# Ұ ↔ XXX ; # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE 159# ѹ ↔ XXX ; # CYRILLIC SMALL LETTER UK 160# Ѹ ↔ XXX ; # CYRILLIC CAPITAL LETTER UK 161ф ↔ f ; # CYRILLIC SMALL LETTER EF 162Ф ↔ F ; # CYRILLIC CAPITAL LETTER EF 163х ↔ h ; # CYRILLIC SMALL LETTER HA 164Х ↔ H; # CYRILLIC CAPITAL LETTER HA 165# ҳ ↔ XXX ; # CYRILLIC SMALL LETTER HA WITH DESCENDER 166# Ҳ ↔ XXX ; # CYRILLIC CAPITAL LETTER HA WITH DESCENDER 167# һ ↔ XXX ; # CYRILLIC SMALL LETTER SHHA 168# Һ ↔ XXX ; # CYRILLIC CAPITAL LETTER SHHA 169# ѡ ↔ XXX ; # CYRILLIC SMALL LETTER OMEGA 170# Ѡ ↔ XXX ; # CYRILLIC CAPITAL LETTER OMEGA 171# ѿ ↔ XXX ; # CYRILLIC SMALL LETTER OT 172# Ѿ ↔ XXX ; # CYRILLIC CAPITAL LETTER OT 173# ѽ ↔ XXX ; # CYRILLIC SMALL LETTER OMEGA WITH TITLO 174# Ѽ ↔ XXX ; # CYRILLIC CAPITAL LETTER OMEGA WITH TITLO 175# ѻ ↔ XXX ; # CYRILLIC SMALL LETTER ROUND OMEGA 176# Ѻ ↔ XXX ; # CYRILLIC CAPITAL LETTER ROUND OMEGA 177ц ↔ c ; # CYRILLIC SMALL LETTER TSE 178Ц ↔ C; # CYRILLIC CAPITAL LETTER TSE 179# ҵ ↔ XXX ; # CYRILLIC SMALL LIGATURE TE TSE 180# Ҵ ↔ XXX ; # CYRILLIC CAPITAL LIGATURE TE TSE 181# ҽ ↔ XXX ; # CYRILLIC SMALL LETTER ABKHASIAN CHE 182# Ҽ ↔ XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE 183# ҿ ↔ XXX ; # CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER 184# Ҿ ↔ XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER 185Ъ ↔ $modprime2 $under ; # CYRILLIC CAPITAL LETTER HARD SIGN 186ъ ↔ $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN 187Ь ↔ $modprime $under ; # CYRILLIC CAPITAL LETTER SOFT SIGN 188ь ↔ $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN 189ы ↔ y ; # CYRILLIC SMALL LETTER YERU 190Ы ↔ Y ; # CYRILLIC CAPITAL LETTER YERU 191# ҍ ↔ XXX ; # CYRILLIC SMALL LETTER SEMISOFT SIGN 192# Ҍ ↔ XXX ; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN 193# ѣ ↔ XXX ; # CYRILLIC SMALL LETTER YAT 194# Ѣ ↔ XXX ; # CYRILLIC CAPITAL LETTER YAT 195# ѥ ↔ XXX ; # CYRILLIC SMALL LETTER IOTIFIED E 196# Ѥ ↔ XXX ; # CYRILLIC CAPITAL LETTER IOTIFIED E 197# ѧ ↔ XXX ; # CYRILLIC SMALL LETTER LITTLE YUS 198# Ѧ ↔ XXX ; # CYRILLIC CAPITAL LETTER LITTLE YUS 199# ѫ ↔ XXX ; # CYRILLIC SMALL LETTER BIG YUS 200# Ѫ ↔ XXX ; # CYRILLIC CAPITAL LETTER BIG YUS 201# ѩ ↔ XXX ; # CYRILLIC SMALL LETTER IOTIFIED LITTLE YUS 202# Ѩ ↔ XXX ; # CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS 203# ѭ ↔ XXX ; # CYRILLIC SMALL LETTER IOTIFIED BIG YUS 204# Ѭ ↔ XXX ; # CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS 205# ѯ ↔ XXX ; # CYRILLIC SMALL LETTER KSI 206# Ѯ ↔ XXX ; # CYRILLIC CAPITAL LETTER KSI 207# ѱ ↔ XXX ; # CYRILLIC SMALL LETTER PSI 208# Ѱ ↔ XXX ; # CYRILLIC CAPITAL LETTER PSI 209# ѳ ↔ XXX ; # CYRILLIC SMALL LETTER FITA 210# Ѳ ↔ XXX ; # CYRILLIC CAPITAL LETTER FITA 211# ѵ ↔ XXX ; # CYRILLIC SMALL LETTER IZHITSA 212# Ѵ ↔ XXX ; # CYRILLIC CAPITAL LETTER IZHITSA 213# ҩ ↔ XXX ; # CYRILLIC SMALL LETTER ABKHASIAN HA 214# Ҩ ↔ XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN HA 215# Ӏ ↔ XXX ; # CYRILLIC LETTER PALOCHKA 216### ӑ ↔ XXX ; # CYRILLIC SMALL LETTER A 217### Ӑ ↔ XXX ; # CYRILLIC CAPITAL LETTER A 218### ӓ ↔ XXX ; # CYRILLIC SMALL LETTER A 219### Ӓ ↔ XXX ; # CYRILLIC CAPITAL LETTER A 220### ӛ ↔ XXX ; # CYRILLIC SMALL LETTER SCHWA 221### Ӛ ↔ XXX ; # CYRILLIC CAPITAL LETTER SCHWA 222### ѓ ↔ XXX ; # CYRILLIC SMALL LETTER GHE 223### Ѓ ↔ XXX ; # CYRILLIC CAPITAL LETTER GHE 224### ѐ ↔ XXX ; # CYRILLIC SMALL LETTER IE 225### Ѐ ↔ XXX ; # CYRILLIC CAPITAL LETTER IE 226### ё ↔ XXX ; # CYRILLIC SMALL LETTER IE 227### Ё ↔ XXX ; # CYRILLIC CAPITAL LETTER IE 228### ӗ ↔ XXX ; # CYRILLIC SMALL LETTER IE 229### Ӗ ↔ XXX ; # CYRILLIC CAPITAL LETTER IE 230### ӂ ↔ XXX ; # CYRILLIC SMALL LETTER ZHE 231### Ӂ ↔ XXX ; # CYRILLIC CAPITAL LETTER ZHE 232### ӝ ↔ XXX ; # CYRILLIC SMALL LETTER ZHE 233### Ӝ ↔ XXX ; # CYRILLIC CAPITAL LETTER ZHE 234### ӟ ↔ XXX ; # CYRILLIC SMALL LETTER ZE 235### Ӟ ↔ XXX ; # CYRILLIC CAPITAL LETTER ZE 236### ѝ ↔ XXX ; # CYRILLIC SMALL LETTER I 237### Ѝ ↔ XXX ; # CYRILLIC CAPITAL LETTER I 238### ӣ ↔ XXX ; # CYRILLIC SMALL LETTER I 239### Ӣ ↔ XXX ; # CYRILLIC CAPITAL LETTER I 240### ӥ ↔ XXX ; # CYRILLIC SMALL LETTER I 241### Ӥ ↔ XXX ; # CYRILLIC CAPITAL LETTER I 242### ї ↔ XXX ; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 243### Ї ↔ XXX ; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I 244### ӧ ↔ XXX ; # CYRILLIC SMALL LETTER O 245### Ӧ ↔ XXX ; # CYRILLIC CAPITAL LETTER O 246### ӫ ↔ XXX ; # CYRILLIC SMALL LETTER BARRED O 247### Ӫ ↔ XXX ; # CYRILLIC CAPITAL LETTER BARRED O 248### ќ ↔ XXX ; # CYRILLIC SMALL LETTER KA 249### Ќ ↔ XXX ; # CYRILLIC CAPITAL LETTER KA 250### ӯ ↔ XXX ; # CYRILLIC SMALL LETTER U 251### Ӯ ↔ XXX ; # CYRILLIC CAPITAL LETTER U 252### ў ↔ XXX ; # CYRILLIC SMALL LETTER U 253### Ў ↔ XXX ; # CYRILLIC CAPITAL LETTER U 254### ӱ ↔ XXX ; # CYRILLIC SMALL LETTER U 255### Ӱ ↔ XXX ; # CYRILLIC CAPITAL LETTER U 256### ӳ ↔ XXX ; # CYRILLIC SMALL LETTER U 257### Ӳ ↔ XXX ; # CYRILLIC CAPITAL LETTER U 258### ӵ ↔ XXX ; # CYRILLIC SMALL LETTER CHE 259### Ӵ ↔ XXX ; # CYRILLIC CAPITAL LETTER CHE 260### ӹ ↔ XXX ; # CYRILLIC SMALL LETTER YERU 261### Ӹ ↔ XXX ; # CYRILLIC CAPITAL LETTER YERU 262### ӭ ↔ XXX ; # CYRILLIC SMALL LETTER E 263### Ӭ ↔ XXX ; # CYRILLIC CAPITAL LETTER E 264### ѷ ↔ XXX ; # CYRILLIC SMALL LETTER IZHITSA 265### Ѷ ↔ XXX ; # CYRILLIC CAPITAL LETTER IZHITSA 266# Completeness 267$ignore = [[:Mark:]''] * ; 268| k ← q ; 269| K ← Q ; 270| u ← w ; 271| U ← W ; 272| KS ← X } $ignore [:UppercaseLetter:] ; 273| KS ← [:UppercaseLetter:] $ignore { X ; 274| Ks ← X ; 275| ks ← x ; 276:: NFC (NFD) ; 277# note: a global filter is more efficient, but MUST include all source chars!! 278# :: ([\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:]]); 279# MINIMAL FILTER: Latin-Cyrillic 280:: ( [ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ; 281 </tRule> 282 </transform> 283 </transforms> 284</supplementalData> 285