1 /************************************************************** 2 * 3 * Licensed to the Apache Software Foundation (ASF) under one 4 * or more contributor license agreements. See the NOTICE file 5 * distributed with this work for additional information 6 * regarding copyright ownership. The ASF licenses this file 7 * to you under the Apache License, Version 2.0 (the 8 * "License"); you may not use this file except in compliance 9 * with the License. You may obtain a copy of the License at 10 * 11 * http://www.apache.org/licenses/LICENSE-2.0 12 * 13 * Unless required by applicable law or agreed to in writing, 14 * software distributed under the License is distributed on an 15 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY 16 * KIND, either express or implied. See the License for the 17 * specific language governing permissions and limitations 18 * under the License. 19 * 20 *************************************************************/ 21 22 23 24 // MARKER(update_precomp.py): autogen include statement, do not remove 25 #include "precompiled_i18npool.hxx" 26 27 // prevent internal compiler error with MSVC6SP3 28 #include <utility> 29 30 #define TRANSLITERATION_ProlongedSoundMark_ja_JP 31 #include <transliteration_Ignore.hxx> 32 33 using namespace com::sun::star::uno; 34 using namespace com::sun::star::lang; 35 using namespace rtl; 36 37 namespace com { namespace sun { namespace star { namespace i18n { 38 39 static sal_Unicode table_normalwidth[] = { 40 // 0x0000, // 0x3040 41 0x3041, // 0x3041 HIRAGANA LETTER SMALL A 42 0x3042, // 0x3042 HIRAGANA LETTER A 43 0x3043, // 0x3043 HIRAGANA LETTER SMALL I 44 0x3044, // 0x3044 HIRAGANA LETTER I 45 0x3045, // 0x3045 HIRAGANA LETTER SMALL U 46 0x3046, // 0x3046 HIRAGANA LETTER U 47 0x3047, // 0x3047 HIRAGANA LETTER SMALL E 48 0x3048, // 0x3048 HIRAGANA LETTER E 49 0x3049, // 0x3049 HIRAGANA LETTER SMALL O 50 0x304a, // 0x304a HIRAGANA LETTER O 51 0x3042, // 0x304b HIRAGANA LETTER KA 52 0x3042, // 0x304c HIRAGANA LETTER GA 53 0x3044, // 0x304d HIRAGANA LETTER KI 54 0x3044, // 0x304e HIRAGANA LETTER GI 55 0x3046, // 0x304f HIRAGANA LETTER KU 56 0x3046, // 0x3050 HIRAGANA LETTER GU 57 0x3048, // 0x3051 HIRAGANA LETTER KE 58 0x3048, // 0x3052 HIRAGANA LETTER GE 59 0x304a, // 0x3053 HIRAGANA LETTER KO 60 0x304a, // 0x3054 HIRAGANA LETTER GO 61 0x3042, // 0x3055 HIRAGANA LETTER SA 62 0x3042, // 0x3056 HIRAGANA LETTER ZA 63 0x3044, // 0x3057 HIRAGANA LETTER SI 64 0x3044, // 0x3058 HIRAGANA LETTER ZI 65 0x3046, // 0x3059 HIRAGANA LETTER SU 66 0x3046, // 0x305a HIRAGANA LETTER ZU 67 0x3048, // 0x305b HIRAGANA LETTER SE 68 0x3048, // 0x305c HIRAGANA LETTER ZE 69 0x304a, // 0x305d HIRAGANA LETTER SO 70 0x304a, // 0x305e HIRAGANA LETTER ZO 71 0x3042, // 0x305f HIRAGANA LETTER TA 72 0x3042, // 0x3060 HIRAGANA LETTER DA 73 0x3044, // 0x3061 HIRAGANA LETTER TI 74 0x3044, // 0x3062 HIRAGANA LETTER DI 75 0x3045, // 0x3063 HIRAGANA LETTER SMALL TU 76 0x3046, // 0x3064 HIRAGANA LETTER TU 77 0x3046, // 0x3065 HIRAGANA LETTER DU 78 0x3048, // 0x3066 HIRAGANA LETTER TE 79 0x3048, // 0x3067 HIRAGANA LETTER DE 80 0x304a, // 0x3068 HIRAGANA LETTER TO 81 0x304a, // 0x3069 HIRAGANA LETTER DO 82 0x3042, // 0x306a HIRAGANA LETTER NA 83 0x3044, // 0x306b HIRAGANA LETTER NI 84 0x3046, // 0x306c HIRAGANA LETTER NU 85 0x3048, // 0x306d HIRAGANA LETTER NE 86 0x304a, // 0x306e HIRAGANA LETTER NO 87 0x3042, // 0x306f HIRAGANA LETTER HA 88 0x3042, // 0x3070 HIRAGANA LETTER BA 89 0x3042, // 0x3071 HIRAGANA LETTER PA 90 0x3044, // 0x3072 HIRAGANA LETTER HI 91 0x3044, // 0x3073 HIRAGANA LETTER BI 92 0x3044, // 0x3074 HIRAGANA LETTER PI 93 0x3046, // 0x3075 HIRAGANA LETTER HU 94 0x3046, // 0x3076 HIRAGANA LETTER BU 95 0x3046, // 0x3077 HIRAGANA LETTER PU 96 0x3048, // 0x3078 HIRAGANA LETTER HE 97 0x3048, // 0x3079 HIRAGANA LETTER BE 98 0x3048, // 0x307a HIRAGANA LETTER PE 99 0x304a, // 0x307b HIRAGANA LETTER HO 100 0x304a, // 0x307c HIRAGANA LETTER BO 101 0x304a, // 0x307d HIRAGANA LETTER PO 102 0x3042, // 0x307e HIRAGANA LETTER MA 103 0x3044, // 0x307f HIRAGANA LETTER MI 104 0x3046, // 0x3080 HIRAGANA LETTER MU 105 0x3048, // 0x3081 HIRAGANA LETTER ME 106 0x304a, // 0x3082 HIRAGANA LETTER MO 107 0x3041, // 0x3083 HIRAGANA LETTER SMALL YA 108 0x3042, // 0x3084 HIRAGANA LETTER YA 109 0x3045, // 0x3085 HIRAGANA LETTER SMALL YU 110 0x3046, // 0x3086 HIRAGANA LETTER YU 111 0x3049, // 0x3087 HIRAGANA LETTER SMALL YO 112 0x304a, // 0x3088 HIRAGANA LETTER YO 113 0x3042, // 0x3089 HIRAGANA LETTER RA 114 0x3044, // 0x308a HIRAGANA LETTER RI 115 0x3046, // 0x308b HIRAGANA LETTER RU 116 0x3048, // 0x308c HIRAGANA LETTER RE 117 0x304a, // 0x308d HIRAGANA LETTER RO 118 0x3041, // 0x308e HIRAGANA LETTER SMALL WA 119 0x3042, // 0x308f HIRAGANA LETTER WA 120 0x3044, // 0x3090 HIRAGANA LETTER WI 121 0x3048, // 0x3091 HIRAGANA LETTER WE 122 0x304a, // 0x3092 HIRAGANA LETTER WO 123 0x0000, // 0x3093 HIRAGANA LETTER N 124 0x3046, // 0x3094 HIRAGANA LETTER VU 125 0x0000, // 0x3095 126 0x0000, // 0x3096 127 0x0000, // 0x3097 128 0x0000, // 0x3098 129 0x0000, // 0x3099 COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK 130 0x0000, // 0x309a COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK 131 0x0000, // 0x309b KATAKANA-HIRAGANA VOICED SOUND MARK 132 0x0000, // 0x309c KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK 133 0x0000, // 0x309d HIRAGANA ITERATION MARK 134 0x0000, // 0x309e HIRAGANA VOICED ITERATION MARK 135 0x0000, // 0x309f 136 0x0000, // 0x30a0 137 0x30a1, // 0x30a1 KATAKANA LETTER SMALL A 138 0x30a2, // 0x30a2 KATAKANA LETTER A 139 0x30a3, // 0x30a3 KATAKANA LETTER SMALL I 140 0x30a4, // 0x30a4 KATAKANA LETTER I 141 0x30a5, // 0x30a5 KATAKANA LETTER SMALL U 142 0x30a6, // 0x30a6 KATAKANA LETTER U 143 0x30a7, // 0x30a7 KATAKANA LETTER SMALL E 144 0x30a8, // 0x30a8 KATAKANA LETTER E 145 0x30a9, // 0x30a9 KATAKANA LETTER SMALL O 146 0x30aa, // 0x30aa KATAKANA LETTER O 147 0x30a2, // 0x30ab KATAKANA LETTER KA 148 0x30a2, // 0x30ac KATAKANA LETTER GA 149 0x30a4, // 0x30ad KATAKANA LETTER KI 150 0x30a4, // 0x30ae KATAKANA LETTER GI 151 0x30a6, // 0x30af KATAKANA LETTER KU 152 0x30a6, // 0x30b0 KATAKANA LETTER GU 153 0x30a8, // 0x30b1 KATAKANA LETTER KE 154 0x30a8, // 0x30b2 KATAKANA LETTER GE 155 0x30aa, // 0x30b3 KATAKANA LETTER KO 156 0x30aa, // 0x30b4 KATAKANA LETTER GO 157 0x30a2, // 0x30b5 KATAKANA LETTER SA 158 0x30a2, // 0x30b6 KATAKANA LETTER ZA 159 0x30a4, // 0x30b7 KATAKANA LETTER SI 160 0x30a4, // 0x30b8 KATAKANA LETTER ZI 161 0x30a6, // 0x30b9 KATAKANA LETTER SU 162 0x30a6, // 0x30ba KATAKANA LETTER ZU 163 0x30a8, // 0x30bb KATAKANA LETTER SE 164 0x30a8, // 0x30bc KATAKANA LETTER ZE 165 0x30aa, // 0x30bd KATAKANA LETTER SO 166 0x30aa, // 0x30be KATAKANA LETTER ZO 167 0x30a2, // 0x30bf KATAKANA LETTER TA 168 0x30a2, // 0x30c0 KATAKANA LETTER DA 169 0x30a4, // 0x30c1 KATAKANA LETTER TI 170 0x30a4, // 0x30c2 KATAKANA LETTER DI 171 0x30a5, // 0x30c3 KATAKANA LETTER SMALL TU 172 0x30a6, // 0x30c4 KATAKANA LETTER TU 173 0x30a6, // 0x30c5 KATAKANA LETTER DU 174 0x30a8, // 0x30c6 KATAKANA LETTER TE 175 0x30a8, // 0x30c7 KATAKANA LETTER DE 176 0x30aa, // 0x30c8 KATAKANA LETTER TO 177 0x30aa, // 0x30c9 KATAKANA LETTER DO 178 0x30a2, // 0x30ca KATAKANA LETTER NA 179 0x30a4, // 0x30cb KATAKANA LETTER NI 180 0x30a6, // 0x30cc KATAKANA LETTER NU 181 0x30a8, // 0x30cd KATAKANA LETTER NE 182 0x30aa, // 0x30ce KATAKANA LETTER NO 183 0x30a2, // 0x30cf KATAKANA LETTER HA 184 0x30a2, // 0x30d0 KATAKANA LETTER BA 185 0x30a2, // 0x30d1 KATAKANA LETTER PA 186 0x30a4, // 0x30d2 KATAKANA LETTER HI 187 0x30a4, // 0x30d3 KATAKANA LETTER BI 188 0x30a4, // 0x30d4 KATAKANA LETTER PI 189 0x30a6, // 0x30d5 KATAKANA LETTER HU 190 0x30a6, // 0x30d6 KATAKANA LETTER BU 191 0x30a6, // 0x30d7 KATAKANA LETTER PU 192 0x30a8, // 0x30d8 KATAKANA LETTER HE 193 0x30a8, // 0x30d9 KATAKANA LETTER BE 194 0x30a8, // 0x30da KATAKANA LETTER PE 195 0x30aa, // 0x30db KATAKANA LETTER HO 196 0x30aa, // 0x30dc KATAKANA LETTER BO 197 0x30aa, // 0x30dd KATAKANA LETTER PO 198 0x30a2, // 0x30de KATAKANA LETTER MA 199 0x30a4, // 0x30df KATAKANA LETTER MI 200 0x30a6, // 0x30e0 KATAKANA LETTER MU 201 0x30a8, // 0x30e1 KATAKANA LETTER ME 202 0x30aa, // 0x30e2 KATAKANA LETTER MO 203 0x30a1, // 0x30e3 KATAKANA LETTER SMALL YA 204 0x30a2, // 0x30e4 KATAKANA LETTER YA 205 0x30a5, // 0x30e5 KATAKANA LETTER SMALL YU 206 0x30a6, // 0x30e6 KATAKANA LETTER YU 207 0x30a9, // 0x30e7 KATAKANA LETTER SMALL YO 208 0x30aa, // 0x30e8 KATAKANA LETTER YO 209 0x30a2, // 0x30e9 KATAKANA LETTER RA 210 0x30a4, // 0x30ea KATAKANA LETTER RI 211 0x30a6, // 0x30eb KATAKANA LETTER RU 212 0x30a8, // 0x30ec KATAKANA LETTER RE 213 0x30aa, // 0x30ed KATAKANA LETTER RO 214 0x30a1, // 0x30ee KATAKANA LETTER SMALL WA 215 0x30a2, // 0x30ef KATAKANA LETTER WA 216 0x30a4, // 0x30f0 KATAKANA LETTER WI 217 0x30a8, // 0x30f1 KATAKANA LETTER WE 218 0x30aa, // 0x30f2 KATAKANA LETTER WO 219 0x0000, // 0x30f3 KATAKANA LETTER N 220 0x30a6, // 0x30f4 KATAKANA LETTER VU 221 0x30a1, // 0x30f5 KATAKANA LETTER SMALL KA 222 0x30a7, // 0x30f6 KATAKANA LETTER SMALL KE 223 0x30a2, // 0x30f7 KATAKANA LETTER VA 224 0x30a4, // 0x30f8 KATAKANA LETTER VI 225 0x30a8, // 0x30f9 KATAKANA LETTER VE 226 0x30aa // 0x30fa KATAKANA LETTER VO 227 // 0x0000, // 0x30fb KATAKANA MIDDLE DOT 228 // 0x0000, // 0x30fc KATAKANA-HIRAGANA PROLONGED SOUND MARK 229 // 0x0000, // 0x30fd KATAKANA ITERATION MARK 230 // 0x0000, // 0x30fe KATAKANA VOICED ITERATION MARK 231 // 0x0000 // 0x30ff 232 }; 233 234 static sal_Unicode table_halfwidth[] = { 235 // 0x0000, // 0xff61 HALFWIDTH IDEOGRAPHIC FULL STOP 236 // 0x0000, // 0xff62 HALFWIDTH LEFT CORNER BRACKET 237 // 0x0000, // 0xff63 HALFWIDTH RIGHT CORNER BRACKET 238 // 0x0000, // 0xff64 HALFWIDTH IDEOGRAPHIC COMMA 239 // 0x0000, // 0xff65 HALFWIDTH KATAKANA MIDDLE DOT 240 0xff75, // 0xff66 HALFWIDTH KATAKANA LETTER WO 241 0xff67, // 0xff67 HALFWIDTH KATAKANA LETTER SMALL A 242 0xff68, // 0xff68 HALFWIDTH KATAKANA LETTER SMALL I 243 0xff69, // 0xff69 HALFWIDTH KATAKANA LETTER SMALL U 244 0xff6a, // 0xff6a HALFWIDTH KATAKANA LETTER SMALL E 245 0xff6b, // 0xff6b HALFWIDTH KATAKANA LETTER SMALL O 246 0xff67, // 0xff6c HALFWIDTH KATAKANA LETTER SMALL YA 247 0xff69, // 0xff6d HALFWIDTH KATAKANA LETTER SMALL YU 248 0xff6b, // 0xff6e HALFWIDTH KATAKANA LETTER SMALL YO 249 0xff69, // 0xff6f HALFWIDTH KATAKANA LETTER SMALL TU 250 0x0000, // 0xff70 HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 251 0xff71, // 0xff71 HALFWIDTH KATAKANA LETTER A 252 0xff72, // 0xff72 HALFWIDTH KATAKANA LETTER I 253 0xff73, // 0xff73 HALFWIDTH KATAKANA LETTER U 254 0xff74, // 0xff74 HALFWIDTH KATAKANA LETTER E 255 0xff75, // 0xff75 HALFWIDTH KATAKANA LETTER O 256 0xff71, // 0xff76 HALFWIDTH KATAKANA LETTER KA 257 0xff72, // 0xff77 HALFWIDTH KATAKANA LETTER KI 258 0xff73, // 0xff78 HALFWIDTH KATAKANA LETTER KU 259 0xff74, // 0xff79 HALFWIDTH KATAKANA LETTER KE 260 0xff75, // 0xff7a HALFWIDTH KATAKANA LETTER KO 261 0xff71, // 0xff7b HALFWIDTH KATAKANA LETTER SA 262 0xff72, // 0xff7c HALFWIDTH KATAKANA LETTER SI 263 0xff73, // 0xff7d HALFWIDTH KATAKANA LETTER SU 264 0xff74, // 0xff7e HALFWIDTH KATAKANA LETTER SE 265 0xff75, // 0xff7f HALFWIDTH KATAKANA LETTER SO 266 0xff71, // 0xff80 HALFWIDTH KATAKANA LETTER TA 267 0xff72, // 0xff81 HALFWIDTH KATAKANA LETTER TI 268 0xff73, // 0xff82 HALFWIDTH KATAKANA LETTER TU 269 0xff74, // 0xff83 HALFWIDTH KATAKANA LETTER TE 270 0xff75, // 0xff84 HALFWIDTH KATAKANA LETTER TO 271 0xff71, // 0xff85 HALFWIDTH KATAKANA LETTER NA 272 0xff72, // 0xff86 HALFWIDTH KATAKANA LETTER NI 273 0xff73, // 0xff87 HALFWIDTH KATAKANA LETTER NU 274 0xff74, // 0xff88 HALFWIDTH KATAKANA LETTER NE 275 0xff75, // 0xff89 HALFWIDTH KATAKANA LETTER NO 276 0xff71, // 0xff8a HALFWIDTH KATAKANA LETTER HA 277 0xff72, // 0xff8b HALFWIDTH KATAKANA LETTER HI 278 0xff73, // 0xff8c HALFWIDTH KATAKANA LETTER HU 279 0xff74, // 0xff8d HALFWIDTH KATAKANA LETTER HE 280 0xff75, // 0xff8e HALFWIDTH KATAKANA LETTER HO 281 0xff71, // 0xff8f HALFWIDTH KATAKANA LETTER MA 282 0xff72, // 0xff90 HALFWIDTH KATAKANA LETTER MI 283 0xff73, // 0xff91 HALFWIDTH KATAKANA LETTER MU 284 0xff74, // 0xff92 HALFWIDTH KATAKANA LETTER ME 285 0xff75, // 0xff93 HALFWIDTH KATAKANA LETTER MO 286 0xff71, // 0xff94 HALFWIDTH KATAKANA LETTER YA 287 0xff73, // 0xff95 HALFWIDTH KATAKANA LETTER YU 288 0xff75, // 0xff96 HALFWIDTH KATAKANA LETTER YO 289 0xff71, // 0xff97 HALFWIDTH KATAKANA LETTER RA 290 0xff72, // 0xff98 HALFWIDTH KATAKANA LETTER RI 291 0xff73, // 0xff99 HALFWIDTH KATAKANA LETTER RU 292 0xff74, // 0xff9a HALFWIDTH KATAKANA LETTER RE 293 0xff75, // 0xff9b HALFWIDTH KATAKANA LETTER RO 294 0xff71 // 0xff9c HALFWIDTH KATAKANA LETTER WA 295 // 0x0000, // 0xff9d HALFWIDTH KATAKANA LETTER N 296 // 0x0000, // 0xff9e HALFWIDTH KATAKANA VOICED SOUND MARK 297 // 0x0000 // 0xff9f HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK 298 }; 299 300 301 OUString SAL_CALL 302 ignoreProlongedSoundMark_ja_JP::folding( const OUString& inStr, sal_Int32 startPos, sal_Int32 nCount, Sequence< sal_Int32 >& offset ) 303 throw(RuntimeException) 304 { 305 // Create a string buffer which can hold nCount + 1 characters. 306 // The reference count is 0 now. 307 rtl_uString * newStr = x_rtl_uString_new_WithLength( nCount ); // defined in x_rtl_ustring.h 308 sal_Unicode * dst = newStr->buffer; 309 const sal_Unicode * src = inStr.getStr() + startPos; 310 311 sal_Int32 *p = 0; 312 sal_Int32 position = 0; 313 314 if (useOffset) { 315 // Allocate nCount length to offset argument. 316 offset.realloc( nCount ); 317 p = offset.getArray(); 318 position = startPos; 319 } 320 321 // 322 sal_Unicode previousChar = *src ++; 323 sal_Unicode currentChar; 324 325 // Conversion 326 while (-- nCount > 0) { 327 currentChar = *src ++; 328 329 if (currentChar == 0x30fc || // KATAKANA-HIRAGANA PROLONGED SOUND MARK 330 currentChar == 0xff70) { // HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK 331 332 if (0x3041 <= previousChar && previousChar <= 0x30fa) { 333 currentChar = table_normalwidth[ previousChar - 0x3041 ]; 334 } 335 else if (0xff66 <= previousChar && previousChar <= 0xff9c) { 336 currentChar = table_halfwidth[ previousChar - 0xff66 ]; 337 } 338 } 339 340 if (useOffset) 341 *p ++ = position ++; 342 *dst ++ = previousChar; 343 previousChar = currentChar; 344 } 345 346 if (nCount == 0) { 347 if (useOffset) 348 *p = position; 349 *dst ++ = previousChar; 350 } 351 352 *dst = (sal_Unicode) 0; 353 354 newStr->length = sal_Int32(dst - newStr->buffer); 355 if (useOffset) 356 offset.realloc(newStr->length); 357 return OUString( newStr ); // defined in rtl/usrting. The reference count is increased from 0 to 1. 358 359 } 360 361 } } } } 362