icuSources/data/translit/it_ja.txt

   1 # ***************************************************************************
   2 # *
   3 # *  Copyright (C) 2004-2016, International Business Machines
   4 # *  Corporation; Unicode, Inc.; and others.  All Rights Reserved.
   5 # *
   6 # ***************************************************************************
   7 # File: it_ja.txt
   8 # Generated from CLDR
   9 #
  10
  11 # Italian to Katakana Transliteration Table for ICU
  12 # Based on:
  13 #   "現代イタリア語入門" (大学書林, 1974. ISBN:978-4475017176)
  14 #   http://ja.wikipedia.org/wiki/%E3%82%A4%E3%82%BF%E3%83%AA%E3%82%A2%E8%AA%9E
  15 ::NFD(NFC);
  16 ::Lower();
  17 ::[:Latin:] fullwidth-halfwidth();
  18 #
  19 #
  20 # Variables.
  21 $vowel = [aeiou];
  22 $consonant = [bcdfghjklmnpqrstvwxyz];
  23 #
  24 #
  25 # Ignore apostrophe.
  26 ($consonant) \' → | $1;
  27 \' → ;
  28 #
  29 #
  30 cqu → ック;
  31 cc → ッ | c;
  32 ca → カ;
  33 ッ { cia → チャ;
  34 cio → チョ;
  35 ci → チ;
  36 cu → ク;
  37 ce → チェ;
  38 co → コ;
  39 #
  40 #
  41 cha → シャ;
  42 chi → キ;
  43 chu → チュ;
  44 che → ケ;
  45 cho → チョ;
  46 #
  47 #
  48 gg → ッ | g;
  49 ghi → ギ;
  50 ghe → ゲ;
  51 ghu → グ;
  52 gli → | li;
  53 gna → ニャ;
  54 gni → ニ;
  55 gnu → ヌ;
  56 gne → ニェ;
  57 gno → ニョ;
  58 #
  59 #
  60 ga → ガ;
  61 gia → ジャ;
  62 giu → ジュ;
  63 gio → ジョ;
  64 gi → ジ;
  65 gu → グ;
  66 ge → ジェ;
  67 go → ゴ;
  68 #
  69 #
  70 rr → ッ | r;
  71 ra → ラ;
  72 ri → リ;
  73 ru → ル;
  74 re → レ;
  75 ro → ロ;
  76 #
  77 #
  78 ll → ッ | l;
  79 la → ラ;
  80 li → リ;
  81 lu → ル;
  82 le → レ;
  83 lo → ロ;
  84 #
  85 #
  86 tt → ッ | t;
  87 ta → タ;
  88 ti → ティ;
  89 thi → ティ;
  90 tu → トゥ;
  91 thu → トゥ;
  92 te → テ;
  93 the → テ;
  94 to → ト;
  95 tho → ト;
  96 tzu → | ッツ;
  97 tz → | zz;
  98 #
  99 #
 100 dd → ッ | d;
 101 da → ダ;
 102 di → ディ;
 103 du → ドゥ;
 104 de → デ;
 105 do → ド;
 106 #
 107 #
 108 ma → マ;
 109 mi → ミ;
 110 mu → ム;
 111 me → メ;
 112 mo → モ;
 113 m } $consonant → ン;
 114 #
 115 #
 116 na → ナ;
 117 ni → ニ;
 118 nu → ヌ;
 119 ne → ネ;
 120 no → ノ;
 121 #
 122 #
 123 ff → ッ | f;
 124 fa → ファ;
 125 fi → フィ;
 126 fu → フ;
 127 fe → フェ;
 128 fo → フォ;
 129 #
 130 #
 131 bb → ッ | b;
 132 ba → バ;
 133 bi → ビ;
 134 bu → ブ;
 135 be → ベ;
 136 bo → ボ;
 137 #
 138 #
 139 pp → ッ | p;
 140 pa → パ;
 141 pi → ピ;
 142 pu → プ;
 143 pe → ペ;
 144 po → ポ;
 145 #
 146 #
 147 vv → ッ | v;
 148 va → ヴァ;
 149 vi → ヴィ;
 150 vu → ヴ;
 151 ve → ヴェ;
 152 vo → ヴォ;
 153 #
 154 #
 155 sa } nt[ao] → サ;
 156 ss → ッ | \~s;
 157 #
 158 #
 159 # 's' is voiced before [bdglmnrv].
 160 sb → ズ | b;
 161 sd → ズ | d;
 162 sg → ズ | g;
 163 sl → ズ | l;
 164 sm → ズ | m;
 165 sn → ズ | n;
 166 sr → ズ | r;
 167 sv → ズ | v;
 168 #
 169 #
 170 # Force 's' after a consonat to be unvoiced.
 171 ($consonant) s } $vowel → | $1 \~ s;
 172 \~sa → サ;
 173 \~si → シ;
 174 \~su → ス;
 175 \~se → セ;
 176 \~so → ソ;
 177 #
 178 #
 179 # 's' at the beginning is usually unvoiced.
 180 [:^Letter:] { sa → サ;
 181 [:^Letter:] { si → シ;
 182 [:^Letter:] { su → ス;
 183 [:^Letter:] { se → セ;
 184 [:^Letter:] { so → ソ;
 185 #
 186 #
 187 # Otherwise voiced 's' are common.
 188 sa → ザ;
 189 si → ジ;
 190 su → ズ;
 191 se → ゼ;
 192 so → ゾ;
 193 #
 194 #
 195 scia → シャ;
 196 sci → シ;
 197 sce → シェ;
 198 #
 199 #
 200 zz → ッ | \~z;
 201 #
 202 # Force 'z' after a consonat to be unvoiced.
 203 ($consonant) z → | $1 \~z;
 204 \~za → ツァ;
 205 \~zi → ツィ;
 206 \~zu → ツ;
 207 \~ze → ツェ;
 208 \~zo → ツォ;
 209 #
 210 #
 211 # Otherwise voiced 'z' are common except for 'zi'.
 212 za → ザ;
 213 [:^Letter:] { zi → ジ;
 214 zi → ツィ;
 215 zu → ズ;
 216 ze → ゼ;
 217 zo → ゾ;
 218 #
 219 #
 220 ja → ヤ;
 221 je → イェ;
 222 j → | i;
 223 #
 224 #
 225 # Standalone vowels and consonants.
 226 a → ア;
 227 i → イ;
 228 u → ウ;
 229 e → エ;
 230 o → オ;
 231 #
 232 #
 233 b → ブ;
 234 c → ク;
 235 d → ド;
 236 f → フ;
 237 g → グ;
 238 h → ;
 239 k → | c;
 240 l → ル;
 241 m → ム;
 242 n → ン;
 243 p → プ;
 244 q → | c;
 245 r → ル;
 246 s → ス;
 247 t → ト;
 248 v → ヴ;
 249 x → | cs;
 250 y → | i;
 251 z → ツ;
 252 #
 253 #
 254 # word delimiter of transliterated foreign phrase is '・'.
 255 ' ' → ・;
 256 #
 257 #
 258 # Latin hyphen should be transliterated to U+30A0 (KATAKANA-HIRAGANA
 259 # DOUBLE HYPHEN), ideally. But since the character isn't supported by
 260 # many fonts or softwares, we use U+FF1D (FULLWIDTH EQUALS SIGN),
 261 # which is widely used as "double hyphen".
 262 #
 263 \- → ＝;
 264 #
 265 #
 266 [:nonspacing mark:] → ;
 267 ::NFC(NFD);
 268