icuSources/data/translit/it_ja.txt

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