1 <?xml version="1.0" encoding="UTF-8" ?> 2 <!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd"> 3 <!-- 4 Copyright 1991-2013 Unicode, Inc. 5 CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/) 6 For terms of use, see http://www.unicode.org/copyright.html 7 --> 8 <supplementalData> 9 <version number="$Revision: 12263 $"/> 10 <transforms> 11 <transform source="zh_Latn_PINYIN" target="ru" direction="forward" alias="ru-t-zh-latn-pinyin"> 12 <tRule><![CDATA[ 13 # Cyrillization of Mandarin Chinese from Pinyin into Russian (Palladius system). 14 # 15 # References: 16 # http://ru.wikipedia.org/wiki/__ 17 # http://www.omniglot.com/writing/mandarin_pts.htm 18 # http://www.pinyin.info/romanization/russian/index.html 19 # These differ in the treatment of some syllables (e.g. <jue>) from the rules 20 # below. 21 # 22 # Further commentary: 23 # http://languagelog.ldc.upenn.edu/nll/?p=604 24 # 25 # Remove tone marks. 26 27 :: NFD (NFC); 28 [\u0304\u0301\u030C\u0300\u0306] ; 29 :: NFC (NFD); 30 # 31 # 32 # Syllabify. Add apostrophes to disambiguate whether <n> and <g> belong to the 33 # coda or onset of a syllable. 34 35 :: Null (); 36 ng } [aeou] n\'g; 37 ng ng\'; 38 n } [aeiou] \'n; 39 n n\'; 40 # 41 # 42 # Main pass. 43 44 :: Null (); 45 # 46 # 47 48 Ai ; 49 A ; 50 B ; 51 Ch ; 52 Ci ; 53 C ; 54 D ; 55 E ; 56 F ; 57 G ; 58 H ; 59 Ju | ; 60 J ; 61 K ; 62 L ; 63 M ; 64 N ; 65 O ; 66 P ; 67 Qu | ; 68 Q ; 69 R ; 70 Sh ; 71 Si ; 72 S ; 73 T ; 74 Wu ; 75 W ; 76 Xu | ; 77 X ; 78 Yai ; 79 Ya ; 80 Ye ; 81 Yi ; 82 You ; 83 Yo } ng ; 84 Yo ; 85 Yu | v; 86 Zh ; 87 Zi ; 88 Z ; 89 # 90 # 91 92 [$] { n ; 93 \'n ; 94 \' ; 95 # 96 # 97 98 ai ; 99 a ; 100 b ; 101 ch ; 102 ci ; 103 c ; 104 d ; 105 ei ; 106 e ; 107 f ; 108 g ; 109 h ; 110 ia ; 111 ie ; 112 io } ng ; 113 iu ; 114 i ; 115 ju | ; 116 j ; 117 k ; 118 l ; 119 m ; 120 ng ; 121 n ; 122 o } ng ; 123 o ; 124 p ; 125 qu | ; 126 q ; 127 r } [^aeiou] ; 128 r ; 129 sh ; 130 si ; 131 s ; 132 t ; 133 [] { ui ; # special exception 134 ui ; 135 uo ; 136 u ; 137 | v; 138 # 139 # We use the dummy symbol <v> to signal that an <> or equivalent character has 140 # just been processed. 141 142 ve ; 143 # 144 #alternative: ve ; 145 146 v } [an] ; 147 v ; 148 wu ; 149 w ; 150 xu | ; 151 x ; 152 yai ; 153 ya ; 154 ye ; 155 yi ; 156 you ; 157 yo } ng ; 158 yo ; 159 yu | v; 160 zh ; 161 zi ; 162 z ; 163 # 164 # 165 # Final pass: Make sure that the output consists entirely of Cyrillic letters. 166 167 :: NFC (); 168 ]]></tRule> 169 </transform> 170 </transforms> 171 </supplementalData> 172