unicode.cc.svn-base

Google浏览器V8内核代码

unsigned CharacterStream::Length() {
  unsigned result = 0;
  while (has_more()) {
    result++;
    GetNext();
  }
  Rewind();
  return result;
}

void CharacterStream::Seek(unsigned position) {
  Rewind();
  for (unsigned i = 0; i < position; i++) {
    GetNext();
  }
}

// Uppercase:            point.category == 'Lu'

static const uint16_t kUppercaseTable0Size = 509;
static const uint16_t kUppercaseTable0[509] = { 32833, 90, 32960, 214, 32984, 222, 256, 258, 260, 262, 264, 266, 268, 270, 272, 274, 276, 278, 280, 282, 284, 286, 288, 290, 292, 294, 296, 298, 300, 302, 304, 306, 308, 310, 313, 315, 317, 319, 321, 323, 325, 327, 330, 332, 334, 336, 338, 340, 342, 344, 346, 348, 350, 352, 354, 356, 358, 360, 362, 364, 366, 368, 370, 372, 374, 33144, 377, 379, 381, 33153, 386, 388, 33158, 391, 33161, 395, 33166, 401, 33171, 404, 33174, 408, 33180, 413, 33183, 416, 418, 420, 33190, 423, 425, 428, 33198, 431, 33201, 435, 437, 33207, 440, 444, 452, 455, 458, 461, 463, 465, 467, 469, 471, 473, 475, 478, 480, 482, 484, 486, 488, 490, 492, 494, 497, 500, 33270, 504, 506, 508, 510, 512, 514, 516, 518, 520, 522, 524, 526, 528, 530, 532, 534, 536, 538, 540, 542, 544, 546, 548, 550, 552, 554, 556, 558, 560, 562, 33338, 571, 33341, 574, 577, 33347, 582, 584, 586, 588, 590, 902, 33672, 906, 908, 33678, 911, 33681, 929, 33699, 939, 33746, 980, 984, 986, 988, 990, 992, 994, 996, 998, 1000, 1002, 1004, 1006, 1012, 1015, 33785, 1018, 33789, 1071, 1120, 1122, 1124, 1126, 1128, 1130, 1132, 1134, 1136, 1138, 1140, 1142, 1144, 1146, 1148, 1150, 1152, 1162, 1164, 1166, 1168, 1170, 1172, 1174, 1176, 1178, 1180, 1182, 1184, 1186, 1188, 1190, 1192, 1194, 1196, 1198, 1200, 1202, 1204, 1206, 1208, 1210, 1212, 1214, 33984, 1217, 1219, 1221, 1223, 1225, 1227, 1229, 1232, 1234, 1236, 1238, 1240, 1242, 1244, 1246, 1248, 1250, 1252, 1254, 1256, 1258, 1260, 1262, 1264, 1266, 1268, 1270, 1272, 1274, 1276, 1278, 1280, 1282, 1284, 1286, 1288, 1290, 1292, 1294, 1296, 1298, 34097, 1366, 37024, 4293, 7680, 7682, 7684, 7686, 7688, 7690, 7692, 7694, 7696, 7698, 7700, 7702, 7704, 7706, 7708, 7710, 7712, 7714, 7716, 7718, 7720, 7722, 7724, 7726, 7728, 7730, 7732, 7734, 7736, 7738, 7740, 7742, 7744, 7746, 7748, 7750, 7752, 7754, 7756, 7758, 7760, 7762, 7764, 7766, 7768, 7770, 7772, 7774, 7776, 7778, 7780, 7782, 7784, 7786, 7788, 7790, 7792, 7794, 7796, 7798, 7800, 7802, 7804, 7806, 7808, 7810, 7812, 7814, 7816, 7818, 7820, 7822, 7824, 7826, 7828, 7840, 7842, 7844, 7846, 7848, 7850, 7852, 7854, 7856, 7858, 7860, 7862, 7864, 7866, 7868, 7870, 7872, 7874, 7876, 7878, 7880, 7882, 7884, 7886, 7888, 7890, 7892, 7894, 7896, 7898, 7900, 7902, 7904, 7906, 7908, 7910, 7912, 7914, 7916, 7918, 7920, 7922, 7924, 7926, 7928, 40712, 7951, 40728, 7965, 40744, 7983, 40760, 7999, 40776, 8013, 8025, 8027, 8029, 8031, 40808, 8047, 40888, 8123, 40904, 8139, 40920, 8155, 40936, 8172, 40952, 8187, 8450, 8455, 41227, 8461, 41232, 8466, 8469, 41241, 8477, 8484, 8486, 8488, 41258, 8493, 41264, 8499, 41278, 8511, 8517, 8579, 44032, 11310, 11360, 44130, 11364, 11367, 11369, 11371, 11381, 11392, 11394, 11396, 11398, 11400, 11402, 11404, 11406, 11408, 11410, 11412, 11414, 11416, 11418, 11420, 11422, 11424, 11426, 11428, 11430, 11432, 11434, 11436, 11438, 11440, 11442, 11444, 11446, 11448, 11450, 11452, 11454, 11456, 11458, 11460, 11462, 11464, 11466, 11468, 11470, 11472, 11474, 11476, 11478, 11480, 11482, 11484, 11486, 11488, 11490 }; // NOLINT
static const uint16_t kUppercaseTable1Size = 2;
static const uint16_t kUppercaseTable1[2] = { 65313, 32570 }; // NOLINT
static const uint16_t kUppercaseTable2Size = 2;
static const uint16_t kUppercaseTable2[2] = { 33792, 1063 }; // NOLINT
static const uint16_t kUppercaseTable3Size = 58;
static const uint16_t kUppercaseTable3[58] = { 54272, 21529, 54324, 21581, 54376, 21633, 21660, 54430, 21663, 21666, 54437, 21670, 54441, 21676, 54446, 21685, 54480, 21737, 54532, 21765, 54535, 21770, 54541, 21780, 54550, 21788, 54584, 21817, 54587, 21822, 54592, 21828, 21830, 54602, 21840, 54636, 21893, 54688, 21945, 54740, 21997, 54792, 22049, 54844, 22101, 54896, 22153, 54952, 22208, 55010, 22266, 55068, 22324, 55126, 22382, 55184, 22440, 22474 }; // NOLINT
bool Uppercase::Is(uchar c) {
  int chunk_index = c >> 15;
  switch (chunk_index) {
    case 0: return LookupPredicate(kUppercaseTable0,
                                       kUppercaseTable0Size,
                                       c);
    case 1: return LookupPredicate(kUppercaseTable1,
                                       kUppercaseTable1Size,
                                       c);
    case 2: return LookupPredicate(kUppercaseTable2,
                                       kUppercaseTable2Size,
                                       c);
    case 3: return LookupPredicate(kUppercaseTable3,
                                       kUppercaseTable3Size,
                                       c);
    default: return false;
  }
}

// Lowercase:            point.category == 'Ll'

static const uint16_t kLowercaseTable0Size = 528;
static const uint16_t kLowercaseTable0[528] = { 32865, 122, 170, 181, 186, 32991, 246, 33016, 255, 257, 259, 261, 263, 265, 267, 269, 271, 273, 275, 277, 279, 281, 283, 285, 287, 289, 291, 293, 295, 297, 299, 301, 303, 305, 307, 309, 33079, 312, 314, 316, 318, 320, 322, 324, 326, 33096, 329, 331, 333, 335, 337, 339, 341, 343, 345, 347, 349, 351, 353, 355, 357, 359, 361, 363, 365, 367, 369, 371, 373, 375, 378, 380, 33150, 384, 387, 389, 392, 33164, 397, 402, 405, 33177, 411, 414, 417, 419, 421, 424, 33194, 427, 429, 432, 436, 438, 33209, 442, 33213, 447, 454, 457, 460, 462, 464, 466, 468, 470, 472, 474, 33244, 477, 479, 481, 483, 485, 487, 489, 491, 493, 33263, 496, 499, 501, 505, 507, 509, 511, 513, 515, 517, 519, 521, 523, 525, 527, 529, 531, 533, 535, 537, 539, 541, 543, 545, 547, 549, 551, 553, 555, 557, 559, 561, 33331, 569, 572, 33343, 576, 578, 583, 585, 587, 589, 33359, 659, 33429, 687, 33659, 893, 912, 33708, 974, 33744, 977, 33749, 983, 985, 987, 989, 991, 993, 995, 997, 999, 1001, 1003, 1005, 33775, 1011, 1013, 1016, 33787, 1020, 33840, 1119, 1121, 1123, 1125, 1127, 1129, 1131, 1133, 1135, 1137, 1139, 1141, 1143, 1145, 1147, 1149, 1151, 1153, 1163, 1165, 1167, 1169, 1171, 1173, 1175, 1177, 1179, 1181, 1183, 1185, 1187, 1189, 1191, 1193, 1195, 1197, 1199, 1201, 1203, 1205, 1207, 1209, 1211, 1213, 1215, 1218, 1220, 1222, 1224, 1226, 1228, 33998, 1231, 1233, 1235, 1237, 1239, 1241, 1243, 1245, 1247, 1249, 1251, 1253, 1255, 1257, 1259, 1261, 1263, 1265, 1267, 1269, 1271, 1273, 1275, 1277, 1279, 1281, 1283, 1285, 1287, 1289, 1291, 1293, 1295, 1297, 1299, 34145, 1415, 40192, 7467, 40290, 7543, 40313, 7578, 7681, 7683, 7685, 7687, 7689, 7691, 7693, 7695, 7697, 7699, 7701, 7703, 7705, 7707, 7709, 7711, 7713, 7715, 7717, 7719, 7721, 7723, 7725, 7727, 7729, 7731, 7733, 7735, 7737, 7739, 7741, 7743, 7745, 7747, 7749, 7751, 7753, 7755, 7757, 7759, 7761, 7763, 7765, 7767, 7769, 7771, 7773, 7775, 7777, 7779, 7781, 7783, 7785, 7787, 7789, 7791, 7793, 7795, 7797, 7799, 7801, 7803, 7805, 7807, 7809, 7811, 7813, 7815, 7817, 7819, 7821, 7823, 7825, 7827, 40597, 7835, 7841, 7843, 7845, 7847, 7849, 7851, 7853, 7855, 7857, 7859, 7861, 7863, 7865, 7867, 7869, 7871, 7873, 7875, 7877, 7879, 7881, 7883, 7885, 7887, 7889, 7891, 7893, 7895, 7897, 7899, 7901, 7903, 7905, 7907, 7909, 7911, 7913, 7915, 7917, 7919, 7921, 7923, 7925, 7927, 7929, 40704, 7943, 40720, 7957, 40736, 7975, 40752, 7991, 40768, 8005, 40784, 8023, 40800, 8039, 40816, 8061, 40832, 8071, 40848, 8087, 40864, 8103, 40880, 8116, 40886, 8119, 8126, 40898, 8132, 40902, 8135, 40912, 8147, 40918, 8151, 40928, 8167, 40946, 8180, 40950, 8183, 8305, 8319, 8458, 41230, 8463, 8467, 8495, 8500, 8505, 41276, 8509, 41286, 8521, 8526, 8580, 44080, 11358, 11361, 44133, 11366, 11368, 11370, 11372, 11380, 44150, 11383, 11393, 11395, 11397, 11399, 11401, 11403, 11405, 11407, 11409, 11411, 11413, 11415, 11417, 11419, 11421, 11423, 11425, 11427, 11429, 11431, 11433, 11435, 11437, 11439, 11441, 11443, 11445, 11447, 11449, 11451, 11453, 11455, 11457, 11459, 11461, 11463, 11465, 11467, 11469, 11471, 11473, 11475, 11477, 11479, 11481, 11483, 11485, 11487, 11489, 44259, 11492, 44288, 11557 }; // NOLINT
static const uint16_t kLowercaseTable1Size = 6;
static const uint16_t kLowercaseTable1[6] = { 64256, 31494, 64275, 31511, 65345, 32602 }; // NOLINT
static const uint16_t kLowercaseTable2Size = 2;
static const uint16_t kLowercaseTable2[2] = { 33832, 1103 }; // NOLINT
static const uint16_t kLowercaseTable3Size = 54;
static const uint16_t kLowercaseTable3[54] = { 54298, 21555, 54350, 21588, 54358, 21607, 54402, 21659, 54454, 21689, 21691, 54461, 21699, 54469, 21711, 54506, 21763, 54558, 21815, 54610, 21867, 54662, 21919, 54714, 21971, 54766, 22023, 54818, 22075, 54870, 22127, 54922, 22181, 54978, 22234, 55004, 22241, 55036, 22292, 55062, 22299, 55094, 22350, 55120, 22357, 55152, 22408, 55178, 22415, 55210, 22466, 55236, 22473, 22475 }; // NOLINT
bool Lowercase::Is(uchar c) {
  int chunk_index = c >> 15;
  switch (chunk_index) {
    case 0: return LookupPredicate(kLowercaseTable0,
                                       kLowercaseTable0Size,
                                       c);
    case 1: return LookupPredicate(kLowercaseTable1,
                                       kLowercaseTable1Size,
                                       c);
    case 2: return LookupPredicate(kLowercaseTable2,
                                       kLowercaseTable2Size,
                                       c);
    case 3: return LookupPredicate(kLowercaseTable3,
                                       kLowercaseTable3Size,
                                       c);
    default: return false;
  }
}

// Letter:               point.category in ['Lu', 'Ll', 'Lt', 'Lm', 'Lo' ]

static const uint16_t kLetterTable0Size = 476;
static const uint16_t kLetterTable0[476] = { 32833, 90, 32865, 122, 170, 181, 186, 32960, 214, 32984, 246, 33016, 705, 33478, 721, 33504, 740, 750, 33658, 893, 902, 33672, 906, 908, 33678, 929, 33699, 974, 33744, 1013, 33783, 1153, 33930, 1299, 34097, 1366, 1369, 34145, 1415, 34256, 1514, 34288, 1522, 34337, 1594, 34368, 1610, 34414, 1647, 34417, 1747, 1749, 34533, 1766, 34542, 1775, 34554, 1788, 1791, 1808, 34578, 1839, 34637, 1901, 34688, 1957, 1969, 34762, 2026, 34804, 2037, 2042, 35076, 2361, 2365, 2384, 35160, 2401, 35195, 2431, 35205, 2444, 35215, 2448, 35219, 2472, 35242, 2480, 2482, 35254, 2489, 2493, 2510, 35292, 2525, 35295, 2529, 35312, 2545, 35333, 2570, 35343, 2576, 35347, 2600, 35370, 2608, 35378, 2611, 35381, 2614, 35384, 2617, 35417, 2652, 2654, 35442, 2676, 35461, 2701, 35471, 2705, 35475, 2728, 35498, 2736, 35506, 2739, 35509, 2745, 2749, 2768, 35552, 2785, 35589, 2828, 35599, 2832, 35603, 2856, 35626, 2864, 35634, 2867, 35637, 2873, 2877, 35676, 2909, 35679, 2913, 2929, 2947, 35717, 2954, 35726, 2960, 35730, 2965, 35737, 2970, 2972, 35742, 2975, 35747, 2980, 35752, 2986, 35758, 3001, 35845, 3084, 35854, 3088, 35858, 3112, 35882, 3123, 35893, 3129, 35936, 3169, 35973, 3212, 35982, 3216, 35986, 3240, 36010, 3251, 36021, 3257, 3261, 3294, 36064, 3297, 36101, 3340, 36110, 3344, 36114, 3368, 36138, 3385, 36192, 3425, 36229, 3478, 36250, 3505, 36275, 3515, 3517, 36288, 3526, 36353, 3632, 36402, 3635, 36416, 3654, 36481, 3714, 3716, 36487, 3720, 3722, 3725, 36500, 3735, 36505, 3743, 36513, 3747, 3749, 3751, 36522, 3755, 36525, 3760, 36530, 3763, 3773, 36544, 3780, 3782, 36572, 3805, 3840, 36672, 3911, 36681, 3946, 36744, 3979, 36864, 4129, 36899, 4135, 36905, 4138, 36944, 4181, 37024, 4293, 37072, 4346, 4348, 37120, 4441, 37215, 4514, 37288, 4601, 37376, 4680, 37450, 4685, 37456, 4694, 4696, 37466, 4701, 37472, 4744, 37514, 4749, 37520, 4784, 37554, 4789, 37560, 4798, 4800, 37570, 4805, 37576, 4822, 37592, 4880, 37650, 4885, 37656, 4954, 37760, 5007, 37792, 5108, 37889, 5740, 38511, 5750, 38529, 5786, 38560, 5866, 38656, 5900, 38670, 5905, 38688, 5937, 38720, 5969, 38752, 5996, 38766, 6000, 38784, 6067, 6103, 6108, 38944, 6263, 39040, 6312, 39168, 6428, 39248, 6509, 39280, 6516, 39296, 6569, 39361, 6599, 39424, 6678, 39685, 6963, 39749, 6987, 40192, 7615, 40448, 7835, 40608, 7929, 40704, 7957, 40728, 7965, 40736, 8005, 40776, 8013, 40784, 8023, 8025, 8027, 8029, 40799, 8061, 40832, 8116, 40886, 8124, 8126, 40898, 8132, 40902, 8140, 40912, 8147, 40918, 8155, 40928, 8172, 40946, 8180, 40950, 8188, 8305, 8319, 41104, 8340, 8450, 8455, 41226, 8467, 8469, 41241, 8477, 8484, 8486, 8488, 41258, 8493, 41263, 8505, 41276, 8511, 41285, 8521, 8526, 41347, 8580, 44032, 11310, 44080, 11358, 44128, 11372, 44148, 11383, 44160, 11492, 44288, 11557, 44336, 11621, 11631, 44416, 11670, 44448, 11686, 44456, 11694, 44464, 11702, 44472, 11710, 44480, 11718, 44488, 11726, 44496, 11734, 44504, 11742, 45061, 12294, 45105, 12341, 45115, 12348, 45121, 12438, 45213, 12447, 45217, 12538, 45308, 12543, 45317, 12588, 45361, 12686, 45472, 12727, 45552, 12799, 46080, 19893, 52736, 32767 }; // NOLINT
static const uint16_t kLetterTable1Size = 68;
static const uint16_t kLetterTable1[68] = { 32768, 8123, 40960, 9356, 42775, 10010, 43008, 10241, 43011, 10245, 43015, 10250, 43020, 10274, 43072, 10355, 44032, 22435, 63744, 31277, 64048, 31338, 64112, 31449, 64256, 31494, 64275, 31511, 31517, 64287, 31528, 64298, 31542, 64312, 31548, 31550, 64320, 31553, 64323, 31556, 64326, 31665, 64467, 32061, 64848, 32143, 64914, 32199, 65008, 32251, 65136, 32372, 65142, 32508, 65313, 32570, 65345, 32602, 65382, 32702, 65474, 32711, 65482, 32719, 65490, 32727, 65498, 32732 }; // NOLINT
static const uint16_t kLetterTable2Size = 48;
static const uint16_t kLetterTable2[48] = { 32768, 11, 32781, 38, 32808, 58, 32828, 61, 32831, 77, 32848, 93, 32896, 250, 33536, 798, 33584, 832, 33602, 841, 33664, 925, 33696, 963, 33736, 975, 33792, 1181, 34816, 2053, 2056, 34826, 2101, 34871, 2104, 2108, 2111, 35072, 2325, 2560, 35344, 2579, 35349, 2583, 35353, 2611, 40960, 9070 }; // NOLINT
static const uint16_t kLetterTable3Size = 57;
static const uint16_t kLetterTable3[57] = { 54272, 21588, 54358, 21660, 54430, 21663, 21666, 54437, 21670, 54441, 21676, 54446, 21689, 21691, 54461, 21699, 54469, 21765, 54535, 21770, 54541, 21780, 54550, 21788, 54558, 21817, 54587, 21822, 54592, 21828, 21830, 54602, 21840, 54610, 22181, 54952, 22208, 54978, 22234, 55004, 22266, 55036, 22292, 55062, 22324, 55094, 22350, 55120, 22382, 55152, 22408, 55178, 22440, 55210, 22466, 55236, 22475 }; // NOLINT
static const uint16_t kLetterTable4Size = 2;
static const uint16_t kLetterTable4[2] = { 32768, 32767 }; // NOLINT
static const uint16_t kLetterTable5Size = 4;
static const uint16_t kLetterTable5[4] = { 32768, 9942, 63488, 31261 }; // NOLINT
bool Letter::Is(uchar c) {
  int chunk_index = c >> 15;
  switch (chunk_index) {
    case 0: return LookupPredicate(kLetterTable0,
                                       kLetterTable0Size,
                                       c);
    case 1: return LookupPredicate(kLetterTable1,
                                       kLetterTable1Size,
                                       c);
    case 2: return LookupPredicate(kLetterTable2,
                                       kLetterTable2Size,
                                       c);
    case 3: return LookupPredicate(kLetterTable3,
                                       kLetterTable3Size,
                                       c);
    case 4: return LookupPredicate(kLetterTable4,
                                       kLetterTable4Size,
                                       c);
    case 5: return LookupPredicate(kLetterTable5,
                                       kLetterTable5Size,
                                       c);
    default: return false;
  }
}

// Space:                point.category == 'Zs'

static const uint16_t kSpaceTable0Size = 9;
static const uint16_t kSpaceTable0[9] = { 32, 160, 5760, 6158, 40960, 8202, 8239, 8287, 12288 }; // NOLINT
bool Space::Is(uchar c) {
  int chunk_index = c >> 15;
  switch (chunk_index) {
    case 0: return LookupPredicate(kSpaceTable0,
                                       kSpaceTable0Size,
                                       c);
    default: return false;
  }
}

// Titlecase:            point.category == 'Lt'

static const uint16_t kTitlecaseTable0Size = 13;
static const uint16_t kTitlecaseTable0[13] = { 453, 456, 459, 498, 40840, 8079, 40856, 8095, 40872, 8111, 8124, 8140, 8188 }; // NOLINT
bool Titlecase::Is(uchar c) {
  int chunk_index = c >> 15;
  switch (chunk_index) {
    case 0: return LookupPredicate(kTitlecaseTable0,
                                       kTitlecaseTable0Size,
                                       c);
    default: return false;
  }
}

// Number:               point.category in ['Nd', 'Nl', 'No' ]

static const uint16_t kNumberTable0Size = 86;
static const uint16_t kNumberTable0[86] = { 32816, 57, 32946, 179, 185, 32956, 190, 34400, 1641, 34544, 1785, 34752, 1993, 35174, 2415, 35302, 2543, 35316, 2553, 35430, 2671, 35558, 2799, 35686, 2927, 35814, 3058, 35942, 3183, 36070, 3311, 36198, 3439, 36432, 3673, 36560, 3801, 36640, 3891, 36928, 4169, 37737, 4988, 38638, 5872, 38880, 6121, 38896, 6137, 38928, 6169, 39238, 6479, 39376, 6617, 39760, 7001, 8304, 41076, 8313, 41088, 8329, 41299, 8578, 42080, 9371, 42218, 9471, 42870, 10131, 11517, 12295, 45089, 12329, 45112, 12346, 45458, 12693, 45600, 12841, 45649, 12895, 45696, 12937, 45745, 12991 }; // NOLINT
static const uint16_t kNumberTable1Size = 2;
static const uint16_t kNumberTable1[2] = { 65296, 32537 }; // NOLINT
static const uint16_t kNumberTable2Size = 19;
static const uint16_t kNumberTable2[19] = { 33031, 307, 33088, 376, 394, 33568, 803, 833, 842, 33745, 981, 33952, 1193, 35094, 2329, 35392, 2631, 41984, 9314 }; // NOLINT
static const uint16_t kNumberTable3Size = 4;