icuSources/data/translit/zh_Latn_PINYIN_ru.txt

   1 # © 2016 and later: Unicode, Inc. and others.
   2 # License & terms of use: http://www.unicode.org/copyright.html#License
   3 #
   4 # File: zh_Latn_PINYIN_ru.txt
   5 # Generated from CLDR
   6 #
   7
   8 # Cyrillization of Mandarin Chinese from Pinyin into Russian (Palladius system).
   9 #
  10 # References:
  11 #   http://ru.wikipedia.org/wiki/Транскрипционная_система_Палладия
  12 #   http://www.omniglot.com/writing/mandarin_pts.htm
  13 #   http://www.pinyin.info/romanization/russian/index.html
  14 # These differ in the treatment of some syllables (e.g. <jue>) from the rules
  15 # below.
  16 #
  17 # Further commentary:
  18 #   http://languagelog.ldc.upenn.edu/nll/?p=604
  19 #
  20 # Remove tone marks.
  21 :: NFD (NFC);
  22 [\u0304\u0301\u030C\u0300\u0306] → ;
  23 :: NFC (NFD);
  24 #
  25 #
  26 # Syllabify. Add apostrophes to disambiguate whether <n> and <g> belong to the
  27 # coda or onset of a syllable.
  28 :: Null ();
  29 ng } [aeou] → n\'g;
  30 ng → ng\';
  31 n } [aeiouü] → \'n;
  32 n → n\';
  33 #
  34 #
  35 # Main pass.
  36 :: Null ();
  37 #
  38 #
  39 Ai → Ай;
  40 A  → А;
  41 B  → Б;
  42 Ch → Ч;
  43 Ci → Цы;
  44 C  → Ц;
  45 D  → Д;
  46 E  → Э;
  47 F  → Ф;
  48 G  → Г;
  49 H  → Х;
  50 Ju → Цз | ü;
  51 J  → Цз;
  52 K  → К;
  53 L  → Л;
  54 M  → М;
  55 N  → Н;
  56 O  → О;
  57 P  → П;
  58 Qu → Ц | ü;
  59 Q  → Ц;
  60 R  → Ж;
  61 Sh → Ш;
  62 Si → Сы;
  63 S  → С;
  64 T  → Т;
  65 Wu → У;
  66 W  → В;
  67 Xu → С | ü;
  68 X  → С;
  69 Yai → Яй;
  70 Ya → Я;
  71 Ye → Е;
  72 Yi → И;
  73 You → Ю;
  74 Yo } ng → Ю;
  75 Yo → Ё;
  76 Yu → Ю | v;
  77 Zh → Чж;
  78 Zi → Цзы;
  79 Z  → Цз;
  80 #
  81 #
  82 [$] { n → н;
  83 \'n → н;
  84 \'  → ;
  85 #
  86 #
  87 ai → ай;
  88 a  → а;
  89 b  → б;
  90 ch → ч;
  91 ci → цы;
  92 c  → ц;
  93 d  → д;
  94 ei → эй;
  95 e  → э;
  96 f  → ф;
  97 g  → г;
  98 h  → х;
  99 ia → я;
 100 ie → е;
 101 io } ng → ю;
 102 iu → ю;
 103 i  → и;
 104 ju → цз | ü;
 105 j  → цз;
 106 k  → к;
 107 l  → л;
 108 m  → м;
 109 ng → н;
 110 n  → нь;
 111 o } ng → у;
 112 o  → о;
 113 p  → п;
 114 qu → ц | ü;
 115 q  → ц;
 116 r } [^aeiou] → р;
 117 r  → ж;
 118 sh → ш;
 119 si → сы;
 120 s  → с;
 121 t  → т;
 122 [Хх] { ui → уэй;  # special exception
 123 ui → уй;
 124 uo → о;
 125 u  → у;
 126 ü  → ю | v;
 127 #
 128 # We use the dummy symbol <v> to signal that an <ü> or equivalent character has
 129 # just been processed.
 130 ve → э;
 131 #
 132 #alternative: ve → е;
 133 v } [an] → ;
 134 v  → й;
 135 wu → у;
 136 w  → в;
 137 xu → с | ü;
 138 x  → с;
 139 yai → яй;
 140 ya → я;
 141 ye → е;
 142 yi → и;
 143 you → ю;
 144 yo } ng → ю;
 145 yo → ё;
 146 yu → ю | v;
 147 zh → чж;
 148 zi → цзы;
 149 z  → цз;
 150 #
 151 #
 152 # Final pass: Make sure that the output consists entirely of Cyrillic letters.
 153 :: NFC ();
 154