ru_ru_Latn_BGN.txt (11350B)
1 # © 2016 and later: Unicode, Inc. and others. 2 # License & terms of use: http://www.unicode.org/copyright.html 3 # Generated using tools/cldr/cldr-to-icu/ 4 # 5 # File: ru_ru_Latn_BGN.txt 6 # Generated from CLDR 7 # 8 9 # BGN/PCGN 1947 System 10 # 11 # The BGN/PCGN system for Russian was adopted by the BGN in 1944 and 12 # by the PCGN in 1947 for use in romanizing names written in the 13 # Russian Cyrillic alphabet. 14 # 15 # The Russian Alphabet as defined by the BGN (Page 93): 16 # АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ 17 # абвгдеёжзийклмнопрстуфхцчшщъыьэюя 18 # 19 # Originally prepared by Michael Everson everson@evertype.com 20 # Fixed by Frank Yung-Fong Tang ftang@google.com 21 # 22 # Test Data from http://en.wikipedia.org/wiki/BGN/PCGN_romanization_of_Russian 23 ######################################################################## 24 # MINIMAL FILTER: Russian-Latin 25 ::[АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюя]; 26 ::NFC; 27 ######################################################################## 28 # Define All Transformation Variables 29 ######################################################################## 30 $prime = ʹ ; 31 $doublePrime = ʺ ; 32 $wordBoundary = [^[:L:][:M:][:N:]] ; 33 $upperVowels = [АЕЁЭИОУЫЮЯ] ; 34 $lowerVowels = [аеёэиоуыюя] ; 35 $vowels = [$upperVowels $lowerVowels] ; 36 $upperConsonants = [[:Uppercase:]-$vowels] ; 37 $lowerConsonants = [[:Lowercase:]-$vowels] ; 38 $consonants = [$upperConsonants $lowerConsonants] ; 39 $upper = [:Uppercase:]; 40 $lower = [:Lowercase:]; 41 ######################################################################## 42 # Rules moved to front to avoid masking 43 ######################################################################## 44 $lowerVowels { ы → ·y ; 45 $upperVowels { [Ыы] } $lower → ·y ; 46 $upperVowels { [Ыы] } → ·Y ; 47 [$consonants - [Йй]]{Э → ·E ; 48 [$consonants - [Йй]]{э → ·e ; 49 [$upperVowels [ЙЪЬ]] { Е } $upper → YE ; # CYRILLIC CAPITAL LETTER IE 50 [$upperVowels [ЙЪЬ]] { Е → Ye ; # CYRILLIC CAPITAL LETTER IE 51 [$upperVowels $lowerVowels [ЙйЪъЬь]] { е → ye ; # CYRILLIC SMALL LETTER IE 52 [$upperVowels [ЙЪЬ]] { Ё } $upper → YË ; # CYRILLIC CAPITAL LETTER IO 53 [$upperVowels [ЙЪЬ]] { Ё → Yë ; # CYRILLIC CAPITAL LETTER IO 54 [$upperVowels $lowerVowels [ЙйЪъЬь]] { ё → yë ; # CYRILLIC SMALL LETTER IO 55 # Since in the above rule we look at the Cyrillic context before the E/Ё/ё, 56 # we have to transform these in a separate pass before we change the vowels. 57 # The ::Null forces a separate pass. 58 ::Null; 59 ######################################################################## 60 # Start of Alphabetic Transformations 61 ######################################################################## 62 А → A ; # CYRILLIC CAPITAL LETTER A 63 а → a ; # CYRILLIC SMALL LETTER A 64 Б → B ; # CYRILLIC CAPITAL LETTER BE 65 б → b ; # CYRILLIC SMALL LETTER BE 66 В → V ; # CYRILLIC CAPITAL LETTER VE 67 в → v ; # CYRILLIC SMALL LETTER VE 68 Г → G ; # CYRILLIC CAPITAL LETTER GHE 69 г → g ; # CYRILLIC SMALL LETTER GHE 70 Д → D ; # CYRILLIC CAPITAL LETTER DE 71 д → d ; # CYRILLIC SMALL LETTER DE 72 ######################################################################## 73 # BGN Page 94 Rule 1: 74 # # The character e should be romanized ye 75 # initially, after the vowel # characters a, e, ё, и, о, у, ы, э, ю, 76 # and я, and after й, ъ, and ь. 77 # In all other instances, it should 78 # be romanized e. 79 ######################################################################## 80 # BUG(ftang)- the following two lines said BEFORE the vowels, instead of AFTER 81 # Е}[$upperVowels [ЙЪЬ]] → YE ; # CYRILLIC CAPITAL LETTER IE 82 # Е}[$lowerVowels [йъь]] → Ye ; # CYRILLIC CAPITAL LETTER IE 83 $wordBoundary{Е} $upper → YE ; # CYRILLIC CAPITAL LETTER IE 84 $wordBoundary{Е → Ye ; # CYRILLIC CAPITAL LETTER IE 85 Е → E ; # CYRILLIC CAPITAL LETTER IE 86 # 87 # BUG(ftang)- the following line said BEFORE the vowels, instead of AFTER 88 # е}[$upperVowels $lowerVowels [ЙйЪъЬь]] → ye ; # CYRILLIC SMALL LETTER IE 89 $wordBoundary{е → ye ; # CYRILLIC SMALL LETTER IE 90 е → e ; # CYRILLIC SMALL LETTER IE 91 ######################################################################## 92 # End of Rule 1 93 ######################################################################## 94 ######################################################################## 95 # BGN Page 94 Rule 2: 96 # 97 # The character ё is not considered a separate character of the 98 # Russian alphabet and the dieresis is generally not shown. When the 99 # dieresis is shown, the character should be romanized yë initially, 100 # after the vowel characters a, e, ё, и, о, у, ы, э, ю, and я, and 101 # after й, ъ, and ь, In all other instances, it should be romanized 102 # ё. When the dieresis is not shown, the character may still be 103 # romanized in the preceding manner or, alternatively, in accordance 104 # with note 1. 105 ######################################################################## 106 # BUG(ftang)- the following two lines said BEFORE the vowels, instead of AFTER 107 # Ё}[$upperVowels [ЙЪЬ]] → YË ; # CYRILLIC CAPITAL LETTER IO 108 # Ё}[$lowerVowels [йъь]] → Yë ; # CYRILLIC CAPITAL LETTER IO 109 $wordBoundary {Ё} [·]? $upper → YË ; # CYRILLIC CAPITAL LETTER IO 110 $wordBoundary {Ё} [·]? $lower → Yë ; # CYRILLIC CAPITAL LETTER IO 111 Ё → Ë ; # CYRILLIC CAPITAL LETTER IO 112 # BUG(ftang)- the following line said BEFORE the vowels, instead of AFTER 113 # ё}[$upperVowels $lowerVowels [ЙйЪъЬь]] → yë ; # CYRILLIC SMALL LETTER IO 114 $wordBoundary{ё → yë ; # CYRILLIC SMALL LETTER IO 115 ё → ë ; # CYRILLIC SMALL LETTER IO 116 ######################################################################## 117 # End of Rule 2 118 ######################################################################## 119 Ж} $lower → Zh ; # CYRILLIC CAPITAL LETTER ZHE 120 Ж → ZH ; # CYRILLIC CAPITAL LETTER ZHE 121 ж → zh ; # CYRILLIC SMALL LETTER ZHE 122 ######################################################################## 123 # BGN Page 94 Rule 3.4 124 # э after any consonant character except 125 # й becomes ·е 126 ######################################################################## 127 З → Z ; # CYRILLIC CAPITAL LETTER ZE 128 з → z ; # CYRILLIC SMALL LETTER ZE 129 # BUG(ftang) The following two lines said those consonant becomes ·е 130 # [$consonants - [Йй]]}Э → ·Е ; 131 # [$consonants - [Йй]]}э → ·е ; 132 ######################################################################## 133 # End of Rule 3.4 134 ######################################################################## 135 И → I ; # CYRILLIC CAPITAL LETTER I 136 и → i ; # CYRILLIC SMALL LETTER I 137 ######################################################################## 138 # BGN Page 94 Rule 3: 139 # 140 # Unusual Russian character sequences occurring primarily in 141 # non-Russian-language names may be romanized as shown below in order 142 # to provide differentiation from regularly-occurring digraphs and 143 # character sequences. 144 # 145 # BGN Page 94 Rule 3.1 146 # й before а, у, ы, or э becomes у· 147 ######################################################################## 148 Й}[АаУуЫыЭэ] → Y· ; # CYRILLIC CAPITAL LETTER I 149 й}[АаУуЫыЭэ] → y· ; # CYRILLIC SMALL LETTER I 150 Й → Y ; # CYRILLIC CAPITAL LETTER I 151 й → y ; # CYRILLIC SMALL LETTER I 152 ######################################################################## 153 # End Rule 3.1 154 ######################################################################## 155 К → K ; # CYRILLIC CAPITAL LETTER KA 156 к → k ; # CYRILLIC SMALL LETTER KA 157 Л → L ; # CYRILLIC CAPITAL LETTER EL 158 л → l ; # CYRILLIC SMALL LETTER EL 159 М → M ; # CYRILLIC CAPITAL LETTER EM 160 м → m ; # CYRILLIC SMALL LETTER EM 161 Н → N ; # CYRILLIC CAPITAL LETTER EN 162 н → n ; # CYRILLIC SMALL LETTER EN 163 О → O ; # CYRILLIC CAPITAL LETTER O 164 о → o ; # CYRILLIC SMALL LETTER O 165 П → P ; # CYRILLIC CAPITAL LETTER PE 166 п → p ; # CYRILLIC SMALL LETTER PE 167 Р → R ; # CYRILLIC CAPITAL LETTER ER 168 р → r ; # CYRILLIC SMALL LETTER ER 169 С → S ; # CYRILLIC CAPITAL LETTER ES 170 с → s ; # CYRILLIC SMALL LETTER ES 171 ######################################################################## 172 # BGN Page 94 Rule 3.5 173 # тс becomes t·s 174 ######################################################################## 175 ТС → T·S ; # CYRILLIC CAPITAL LETTER TE 176 Тс → T·s ; # CYRILLIC CAPITAL LETTER TE 177 тс → t·s ; # CYRILLIC SMALL LETTER TE 178 Т → T ; # CYRILLIC CAPITAL LETTER TE 179 т → t ; # CYRILLIC SMALL LETTER TE 180 ######################################################################## 181 # End Rule 3.5 182 ######################################################################## 183 У → U ; # CYRILLIC CAPITAL LETTER U 184 у → u ; # CYRILLIC SMALL LETTER U 185 Ф → F ; # CYRILLIC CAPITAL LETTER EF 186 ф → f ; # CYRILLIC SMALL LETTER EF 187 Х} $lower → Kh ; # CYRILLIC CAPITAL LETTER HA 188 Х → KH ; # CYRILLIC CAPITAL LETTER HA 189 х → kh ; # CYRILLIC SMALL LETTER HA 190 Ц} $lower → Ts ; # CYRILLIC CAPITAL LETTER TSE 191 Ц → TS ; # CYRILLIC CAPITAL LETTER TSE 192 ц → ts ; # CYRILLIC SMALL LETTER TSE 193 Ч} $lower → Ch ; # CYRILLIC CAPITAL LETTER CHE 194 Ч → CH ; # CYRILLIC CAPITAL LETTER CHE 195 ч → ch ; # CYRILLIC SMALL LETTER CHE 196 ######################################################################## 197 # BGN Page 94 Rule 3.6 198 # шч becomes sh·ch 199 ######################################################################## 200 ШЧ → SH·CH ; # CYRILLIC CAPITAL LETTER SHA 201 Шч → Sh·ch ; # CYRILLIC CAPITAL LETTER SHA 202 шч → sh·ch ; # CYRILLIC SMALL LETTER SHA 203 Ш} $lower → Sh ; # CYRILLIC CAPITAL LETTER SHA 204 Ш → SH ; # CYRILLIC CAPITAL LETTER SHA 205 ш → sh ; # CYRILLIC SMALL LETTER SHA 206 Щ} $lower → Shch ; # CYRILLIC CAPITAL LETTER SHCHA 207 Щ → SHCH ; # CYRILLIC CAPITAL LETTER SHCHA 208 щ → shch ; # CYRILLIC SMALL LETTER SHCHA 209 ######################################################################## 210 # End Rule 3.6 211 ######################################################################## 212 Ъ → $doublePrime ; # CYRILLIC CAPITAL LETTER HARD SIGN 213 ъ → $doublePrime ; # CYRILLIC SMALL LETTER HARD SIGN 214 ######################################################################## 215 # BGN Page 94 Rule 3.2 216 # ы before а, у, ы, or э becomes у· 217 # 218 # BGN Page 94 Rule 3.3 219 # ы after any vowel character becomes ·у 220 ######################################################################## 221 # 222 # BUG(ftang) the following line said the vowels will change 223 # $vowels}Ы → ·Y ; # CYRILLIC CAPITAL LETTER I 224 # $vowels}ы → ·y ; # CYRILLIC CAPITAL LETTER I 225 Ы}[АаУуЫыЭэ] → Y· ; # CYRILLIC CAPITAL LETTER YERU 226 ы}[ауыэ] → y· ; # CYRILLIC SMALL LETTER YERU 227 Ы → Y ; # CYRILLIC CAPITAL LETTER YERU 228 ы → y ; # CYRILLIC SMALL LETTER YERU 229 ######################################################################## 230 # End Rule 3.2 and 3.3 231 ######################################################################## 232 Ь → $prime ; # CYRILLIC CAPITAL LETTER SOFT SIGN 233 ь → $prime ; # CYRILLIC SMALL LETTER SOFT SIGN 234 Э → E ; # CYRILLIC CAPITAL LETTER E 235 э → e ; # CYRILLIC SMALL LETTER E 236 Ю} $lower → Yu ; # CYRILLIC CAPITAL LETTER YU 237 Ю → YU ; # CYRILLIC CAPITAL LETTER YU 238 ю → yu ; # CYRILLIC SMALL LETTER YU 239 Я} $lower → Ya ; # CYRILLIC CAPITAL LETTER YA 240 Я → YA ; # CYRILLIC CAPITAL LETTER YA 241 я → ya ; # CYRILLIC SMALL LETTER YA