Direct link to this page
JDK 1.6
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469
/* * @(#)Character.java 1.35 06/05/08 * * Copyright 2006 Sun Microsystems, Inc. All rights reserved. * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms. */ package java.lang; import java.util.Map; import java.util.HashMap; import java.util.Locale; /** * The <code>Character</code> class wraps a value of the primitive * type <code>char</code> in an object. An object of type * <code>Character</code> contains a single field whose type is * <code>char</code>. * <p> * In addition, this class provides several methods for determining * a character's category (lowercase letter, digit, etc.) and for converting * characters from uppercase to lowercase and vice versa. * <p> * Character information is based on the Unicode Standard, version 4.0. * <p> * The methods and data of class <code>Character</code> are defined by * the information in the <i>UnicodeData</i> file that is part of the * Unicode Character Database maintained by the Unicode * Consortium. This file specifies various properties including name * and general category for every defined Unicode code point or * character range. * <p> * The file and its description are available from the Unicode Consortium at: * <ul> * <li><a href="http://www.unicode.org">http://www.unicode.org</a> * </ul> * * <h4><a name="unicode">Unicode Character Representations</a></h4> * * <p>The <code>char</code> data type (and therefore the value that a * <code>Character</code> object encapsulates) are based on the * original Unicode specification, which defined characters as * fixed-width 16-bit entities. The Unicode standard has since been * changed to allow for characters whose representation requires more * than 16 bits. The range of legal <em>code point</em>s is now * U+0000 to U+10FFFF, known as <em>Unicode scalar value</em>. * (Refer to the <a * href="http://www.unicode.org/reports/tr27/#notation"><i> * definition</i></a> of the U+<i>n</i> notation in the Unicode * standard.) * * <p>The set of characters from U+0000 to U+FFFF is sometimes * referred to as the <em>Basic Multilingual Plane (BMP)</em>. <a * name="supplementary">Characters</a> whose code points are greater * than U+FFFF are called <em>supplementary character</em>s. The Java * 2 platform uses the UTF-16 representation in <code>char</code> * arrays and in the <code>String</code> and <code>StringBuffer</code> * classes. In this representation, supplementary characters are * represented as a pair of <code>char</code> values, the first from * the <em>high-surrogates</em> range, (\uD800-\uDBFF), the * second from the <em>low-surrogates</em> range * (\uDC00-\uDFFF). * * <p>A <code>char</code> value, therefore, represents Basic * Multilingual Plane (BMP) code points, including the surrogate * code points, or code units of the UTF-16 encoding. An * <code>int</code> value represents all Unicode code points, * including supplementary code points. The lower (least significant) * 21 bits of <code>int</code> are used to represent Unicode code * points and the upper (most significant) 11 bits must be zero. * Unless otherwise specified, the behavior with respect to * supplementary characters and surrogate <code>char</code> values is * as follows: * * <ul> * <li>The methods that only accept a <code>char</code> value cannot support * supplementary characters. They treat <code>char</code> values from the * surrogate ranges as undefined characters. For example, * <code>Character.isLetter('\uD840')</code> returns <code>false</code>, even though * this specific value if followed by any low-surrogate value in a string * would represent a letter. * * <li>The methods that accept an <code>int</code> value support all * Unicode characters, including supplementary characters. For * example, <code>Character.isLetter(0x2F81A)</code> returns * <code>true</code> because the code point value represents a letter * (a CJK ideograph). * </ul> * * <p>In the Java SE API documentation, <em>Unicode code point</em> is * used for character values in the range between U+0000 and U+10FFFF, * and <em>Unicode code unit</em> is used for 16-bit * <code>char</code> values that are code units of the <em>UTF-16</em> * encoding. For more information on Unicode terminology, refer to the * <a href="http://www.unicode.org/glossary/">Unicode Glossary</a>. * * @author Lee Boynton * @author Guy Steele * @author Akira Tanaka * @since 1.0 */ public final class Character extends Object implements java.io.Serializable, Comparable<Character> { /** * The minimum radix available for conversion to and from strings. * The constant value of this field is the smallest value permitted * for the radix argument in radix-conversion methods such as the * <code>digit</code> method, the <code>forDigit</code> * method, and the <code>toString</code> method of class * <code>Integer</code>. * * @see java.lang.Character#digit(char, int) * @see java.lang.Character#forDigit(int, int) * @see java.lang.Integer#toString(int, int) * @see java.lang.Integer#valueOf(java.lang.String) */ public static final int MIN_RADIX = 2; /** * The maximum radix available for conversion to and from strings. * The constant value of this field is the largest value permitted * for the radix argument in radix-conversion methods such as the * <code>digit</code> method, the <code>forDigit</code> * method, and the <code>toString</code> method of class * <code>Integer</code>. * * @see java.lang.Character#digit(char, int) * @see java.lang.Character#forDigit(int, int) * @see java.lang.Integer#toString(int, int) * @see java.lang.Integer#valueOf(java.lang.String) */ public static final int MAX_RADIX = 36; /** * The constant value of this field is the smallest value of type * <code>char</code>, <code>'\u0000'</code>. * * @since 1.0.2 */ public static final char MIN_VALUE = '\u0000'; /** * The constant value of this field is the largest value of type * <code>char</code>, <code>'\uFFFF'</code>. * * @since 1.0.2 */ public static final char MAX_VALUE = '\uffff'; /** * The <code>Class</code> instance representing the primitive type * <code>char</code>. * * @since 1.1 */ public static final Class<Character> TYPE = Class.getPrimitiveClass("char"); /* * Normative general types */ /* * General character types */ /** * General category "Cn" in the Unicode specification. * @since 1.1 */ public static final byte UNASSIGNED = 0; /** * General category "Lu" in the Unicode specification. * @since 1.1 */ public static final byte UPPERCASE_LETTER = 1; /** * General category "Ll" in the Unicode specification. * @since 1.1 */ public static final byte LOWERCASE_LETTER = 2; /** * General category "Lt" in the Unicode specification. * @since 1.1 */ public static final byte TITLECASE_LETTER = 3; /** * General category "Lm" in the Unicode specification. * @since 1.1 */ public static final byte MODIFIER_LETTER = 4; /** * General category "Lo" in the Unicode specification. * @since 1.1 */ public static final byte OTHER_LETTER = 5; /** * General category "Mn" in the Unicode specification. * @since 1.1 */ public static final byte NON_SPACING_MARK = 6; /** * General category "Me" in the Unicode specification. * @since 1.1 */ public static final byte ENCLOSING_MARK = 7; /** * General category "Mc" in the Unicode specification. * @since 1.1 */ public static final byte COMBINING_SPACING_MARK = 8; /** * General category "Nd" in the Unicode specification. * @since 1.1 */ public static final byte DECIMAL_DIGIT_NUMBER = 9; /** * General category "Nl" in the Unicode specification. * @since 1.1 */ public static final byte LETTER_NUMBER = 10; /** * General category "No" in the Unicode specification. * @since 1.1 */ public static final byte OTHER_NUMBER = 11; /** * General category "Zs" in the Unicode specification. * @since 1.1 */ public static final byte SPACE_SEPARATOR = 12; /** * General category "Zl" in the Unicode specification. * @since 1.1 */ public static final byte LINE_SEPARATOR = 13; /** * General category "Zp" in the Unicode specification. * @since 1.1 */ public static final byte PARAGRAPH_SEPARATOR = 14; /** * General category "Cc" in the Unicode specification. * @since 1.1 */ public static final byte CONTROL = 15; /** * General category "Cf" in the Unicode specification. * @since 1.1 */ public static final byte FORMAT = 16; /** * General category "Co" in the Unicode specification. * @since 1.1 */ public static final byte PRIVATE_USE = 18; /** * General category "Cs" in the Unicode specification. * @since 1.1 */ public static final byte SURROGATE = 19; /** * General category "Pd" in the Unicode specification. * @since 1.1 */ public static final byte DASH_PUNCTUATION = 20; /** * General category "Ps" in the Unicode specification. * @since 1.1 */ public static final byte START_PUNCTUATION = 21; /** * General category "Pe" in the Unicode specification. * @since 1.1 */ public static final byte END_PUNCTUATION = 22; /** * General category "Pc" in the Unicode specification. * @since 1.1 */ public static final byte CONNECTOR_PUNCTUATION = 23; /** * General category "Po" in the Unicode specification. * @since 1.1 */ public static final byte OTHER_PUNCTUATION = 24; /** * General category "Sm" in the Unicode specification. * @since 1.1 */ public static final byte MATH_SYMBOL = 25; /** * General category "Sc" in the Unicode specification. * @since 1.1 */ public static final byte CURRENCY_SYMBOL = 26; /** * General category "Sk" in the Unicode specification. * @since 1.1 */ public static final byte MODIFIER_SYMBOL = 27; /** * General category "So" in the Unicode specification. * @since 1.1 */ public static final byte OTHER_SYMBOL = 28; /** * General category "Pi" in the Unicode specification. * @since 1.4 */ public static final byte INITIAL_QUOTE_PUNCTUATION = 29; /** * General category "Pf" in the Unicode specification. * @since 1.4 */ public static final byte FINAL_QUOTE_PUNCTUATION = 30; /** * Error flag. Use int (code point) to avoid confusion with U+FFFF. */ static final int ERROR = 0xFFFFFFFF; /** * Undefined bidirectional character type. Undefined <code>char</code> * values have undefined directionality in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_UNDEFINED = -1; /** * Strong bidirectional character type "L" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_LEFT_TO_RIGHT = 0; /** * Strong bidirectional character type "R" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_RIGHT_TO_LEFT = 1; /** * Strong bidirectional character type "AL" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC = 2; /** * Weak bidirectional character type "EN" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_EUROPEAN_NUMBER = 3; /** * Weak bidirectional character type "ES" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR = 4; /** * Weak bidirectional character type "ET" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR = 5; /** * Weak bidirectional character type "AN" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_ARABIC_NUMBER = 6; /** * Weak bidirectional character type "CS" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_COMMON_NUMBER_SEPARATOR = 7; /** * Weak bidirectional character type "NSM" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_NONSPACING_MARK = 8; /** * Weak bidirectional character type "BN" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_BOUNDARY_NEUTRAL = 9; /** * Neutral bidirectional character type "B" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_PARAGRAPH_SEPARATOR = 10; /** * Neutral bidirectional character type "S" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_SEGMENT_SEPARATOR = 11; /** * Neutral bidirectional character type "WS" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_WHITESPACE = 12; /** * Neutral bidirectional character type "ON" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_OTHER_NEUTRALS = 13; /** * Strong bidirectional character type "LRE" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING = 14; /** * Strong bidirectional character type "LRO" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE = 15; /** * Strong bidirectional character type "RLE" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING = 16; /** * Strong bidirectional character type "RLO" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE = 17; /** * Weak bidirectional character type "PDF" in the Unicode specification. * @since 1.4 */ public static final byte DIRECTIONALITY_POP_DIRECTIONAL_FORMAT = 18; /** * The minimum value of a Unicode high-surrogate code unit in the * UTF-16 encoding. A high-surrogate is also known as a * <i>leading-surrogate</i>. * * @since 1.5 */ public static final char MIN_HIGH_SURROGATE = '\uD800'; /** * The maximum value of a Unicode high-surrogate code unit in the * UTF-16 encoding. A high-surrogate is also known as a * <i>leading-surrogate</i>. * * @since 1.5 */ public static final char MAX_HIGH_SURROGATE = '\uDBFF'; /** * The minimum value of a Unicode low-surrogate code unit in the * UTF-16 encoding. A low-surrogate is also known as a * <i>trailing-surrogate</i>. * * @since 1.5 */ public static final char MIN_LOW_SURROGATE = '\uDC00'; /** * The maximum value of a Unicode low-surrogate code unit in the * UTF-16 encoding. A low-surrogate is also known as a * <i>trailing-surrogate</i>. * * @since 1.5 */ public static final char MAX_LOW_SURROGATE = '\uDFFF'; /** * The minimum value of a Unicode surrogate code unit in the UTF-16 encoding. * * @since 1.5 */ public static final char MIN_SURROGATE = MIN_HIGH_SURROGATE; /** * The maximum value of a Unicode surrogate code unit in the UTF-16 encoding. * * @since 1.5 */ public static final char MAX_SURROGATE = MAX_LOW_SURROGATE; /** * The minimum value of a supplementary code point. * * @since 1.5 */ public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000; /** * The minimum value of a Unicode code point. * * @since 1.5 */ public static final int MIN_CODE_POINT = 0x000000; /** * The maximum value of a Unicode code point. * * @since 1.5 */ public static final int MAX_CODE_POINT = 0x10ffff; /** * Instances of this class represent particular subsets of the Unicode * character set. The only family of subsets defined in the * <code>Character</code> class is <code>{@link Character.UnicodeBlock * UnicodeBlock}</code>. Other portions of the Java API may define other * subsets for their own purposes. * * @since 1.2 */ public static class Subset { private String name; /** * Constructs a new <code>Subset</code> instance. * * @exception NullPointerException if name is <code>null</code> * @param name The name of this subset */ protected Subset(String name) { if (name == null) { throw new NullPointerException("name"); } this.name = name; } /** * Compares two <code>Subset</code> objects for equality. * This method returns <code>true</code> if and only if * <code>this</code> and the argument refer to the same * object; since this method is <code>final</code>, this * guarantee holds for all subclasses. */ public final boolean equals(Object obj) { return (this == obj); } /** * Returns the standard hash code as defined by the * <code>{@link Object#hashCode}</code> method. This method * is <code>final</code> in order to ensure that the * <code>equals</code> and <code>hashCode</code> methods will * be consistent in all subclasses. */ public final int hashCode() { return super.hashCode(); } /** * Returns the name of this subset. */ public final String toString() { return name; } } /** * A family of character subsets representing the character blocks in the * Unicode specification. Character blocks generally define characters * used for a specific script or purpose. A character is contained by * at most one Unicode block. * * @since 1.2 */ public static final class UnicodeBlock extends Subset { private static Map map = new HashMap(); /** * Create a UnicodeBlock with the given identifier name. * This name must be the same as the block identifier. */ private UnicodeBlock(String idName) { super(idName); map.put(idName.toUpperCase(Locale.US), this); } /** * Create a UnicodeBlock with the given identifier name and * alias name. */ private UnicodeBlock(String idName, String alias) { this(idName); map.put(alias.toUpperCase(Locale.US), this); } /** * Create a UnicodeBlock with the given identifier name and * alias names. */ private UnicodeBlock(String idName, String[] aliasName) { this(idName); if (aliasName != null) { for(int x=0; x<aliasName.length; ++x) { map.put(aliasName[x].toUpperCase(Locale.US), this); } } } /** * Constant for the "Basic Latin" Unicode character block. * @since 1.2 */ public static final UnicodeBlock BASIC_LATIN = new UnicodeBlock("BASIC_LATIN", new String[] {"Basic Latin", "BasicLatin" }); /** * Constant for the "Latin-1 Supplement" Unicode character block. * @since 1.2 */ public static final UnicodeBlock LATIN_1_SUPPLEMENT = new UnicodeBlock("LATIN_1_SUPPLEMENT", new String[]{ "Latin-1 Supplement", "Latin-1Supplement"}); /** * Constant for the "Latin Extended-A" Unicode character block. * @since 1.2 */ public static final UnicodeBlock LATIN_EXTENDED_A = new UnicodeBlock("LATIN_EXTENDED_A", new String[]{ "Latin Extended-A", "LatinExtended-A"}); /** * Constant for the "Latin Extended-B" Unicode character block. * @since 1.2 */ public static final UnicodeBlock LATIN_EXTENDED_B = new UnicodeBlock("LATIN_EXTENDED_B", new String[] {"Latin Extended-B", "LatinExtended-B"}); /** * Constant for the "IPA Extensions" Unicode character block. * @since 1.2 */ public static final UnicodeBlock IPA_EXTENSIONS = new UnicodeBlock("IPA_EXTENSIONS", new String[] {"IPA Extensions", "IPAExtensions"}); /** * Constant for the "Spacing Modifier Letters" Unicode character block. * @since 1.2 */ public static final UnicodeBlock SPACING_MODIFIER_LETTERS = new UnicodeBlock("SPACING_MODIFIER_LETTERS", new String[] { "Spacing Modifier Letters", "SpacingModifierLetters"}); /** * Constant for the "Combining Diacritical Marks" Unicode character block. * @since 1.2 */ public static final UnicodeBlock COMBINING_DIACRITICAL_MARKS = new UnicodeBlock("COMBINING_DIACRITICAL_MARKS", new String[] {"Combining Diacritical Marks", "CombiningDiacriticalMarks" }); /** * Constant for the "Greek and Coptic" Unicode character block. * <p> * This block was previously known as the "Greek" block. * * @since 1.2 */ public static final UnicodeBlock GREEK = new UnicodeBlock("GREEK", new String[] {"Greek and Coptic", "GreekandCoptic"}); /** * Constant for the "Cyrillic" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CYRILLIC = new UnicodeBlock("CYRILLIC"); /** * Constant for the "Armenian" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ARMENIAN = new UnicodeBlock("ARMENIAN"); /** * Constant for the "Hebrew" Unicode character block. * @since 1.2 */ public static final UnicodeBlock HEBREW = new UnicodeBlock("HEBREW"); /** * Constant for the "Arabic" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ARABIC = new UnicodeBlock("ARABIC"); /** * Constant for the "Devanagari" Unicode character block. * @since 1.2 */ public static final UnicodeBlock DEVANAGARI = new UnicodeBlock("DEVANAGARI"); /** * Constant for the "Bengali" Unicode character block. * @since 1.2 */ public static final UnicodeBlock BENGALI = new UnicodeBlock("BENGALI"); /** * Constant for the "Gurmukhi" Unicode character block. * @since 1.2 */ public static final UnicodeBlock GURMUKHI = new UnicodeBlock("GURMUKHI"); /** * Constant for the "Gujarati" Unicode character block. * @since 1.2 */ public static final UnicodeBlock GUJARATI = new UnicodeBlock("GUJARATI"); /** * Constant for the "Oriya" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ORIYA = new UnicodeBlock("ORIYA"); /** * Constant for the "Tamil" Unicode character block. * @since 1.2 */ public static final UnicodeBlock TAMIL = new UnicodeBlock("TAMIL"); /** * Constant for the "Telugu" Unicode character block. * @since 1.2 */ public static final UnicodeBlock TELUGU = new UnicodeBlock("TELUGU"); /** * Constant for the "Kannada" Unicode character block. * @since 1.2 */ public static final UnicodeBlock KANNADA = new UnicodeBlock("KANNADA"); /** * Constant for the "Malayalam" Unicode character block. * @since 1.2 */ public static final UnicodeBlock MALAYALAM = new UnicodeBlock("MALAYALAM"); /** * Constant for the "Thai" Unicode character block. * @since 1.2 */ public static final UnicodeBlock THAI = new UnicodeBlock("THAI"); /** * Constant for the "Lao" Unicode character block. * @since 1.2 */ public static final UnicodeBlock LAO = new UnicodeBlock("LAO"); /** * Constant for the "Tibetan" Unicode character block. * @since 1.2 */ public static final UnicodeBlock TIBETAN = new UnicodeBlock("TIBETAN"); /** * Constant for the "Georgian" Unicode character block. * @since 1.2 */ public static final UnicodeBlock GEORGIAN = new UnicodeBlock("GEORGIAN"); /** * Constant for the "Hangul Jamo" Unicode character block. * @since 1.2 */ public static final UnicodeBlock HANGUL_JAMO = new UnicodeBlock("HANGUL_JAMO", new String[] {"Hangul Jamo", "HangulJamo"}); /** * Constant for the "Latin Extended Additional" Unicode character block. * @since 1.2 */ public static final UnicodeBlock LATIN_EXTENDED_ADDITIONAL = new UnicodeBlock("LATIN_EXTENDED_ADDITIONAL", new String[] {"Latin Extended Additional", "LatinExtendedAdditional"}); /** * Constant for the "Greek Extended" Unicode character block. * @since 1.2 */ public static final UnicodeBlock GREEK_EXTENDED = new UnicodeBlock("GREEK_EXTENDED", new String[] {"Greek Extended", "GreekExtended"}); /** * Constant for the "General Punctuation" Unicode character block. * @since 1.2 */ public static final UnicodeBlock GENERAL_PUNCTUATION = new UnicodeBlock("GENERAL_PUNCTUATION", new String[] {"General Punctuation", "GeneralPunctuation"}); /** * Constant for the "Superscripts and Subscripts" Unicode character block. * @since 1.2 */ public static final UnicodeBlock SUPERSCRIPTS_AND_SUBSCRIPTS = new UnicodeBlock("SUPERSCRIPTS_AND_SUBSCRIPTS", new String[] {"Superscripts and Subscripts", "SuperscriptsandSubscripts" }); /** * Constant for the "Currency Symbols" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CURRENCY_SYMBOLS = new UnicodeBlock("CURRENCY_SYMBOLS", new String[] { "Currency Symbols", "CurrencySymbols"}); /** * Constant for the "Combining Diacritical Marks for Symbols" Unicode character block. * <p> * This block was previously known as "Combining Marks for Symbols". * @since 1.2 */ public static final UnicodeBlock COMBINING_MARKS_FOR_SYMBOLS = new UnicodeBlock("COMBINING_MARKS_FOR_SYMBOLS", new String[] {"Combining Diacritical Marks for Symbols", "CombiningDiacriticalMarksforSymbols", "Combining Marks for Symbols", "CombiningMarksforSymbols" }); /** * Constant for the "Letterlike Symbols" Unicode character block. * @since 1.2 */ public static final UnicodeBlock LETTERLIKE_SYMBOLS = new UnicodeBlock("LETTERLIKE_SYMBOLS", new String[] { "Letterlike Symbols", "LetterlikeSymbols"}); /** * Constant for the "Number Forms" Unicode character block. * @since 1.2 */ public static final UnicodeBlock NUMBER_FORMS = new UnicodeBlock("NUMBER_FORMS", new String[] {"Number Forms", "NumberForms"}); /** * Constant for the "Arrows" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ARROWS = new UnicodeBlock("ARROWS"); /** * Constant for the "Mathematical Operators" Unicode character block. * @since 1.2 */ public static final UnicodeBlock MATHEMATICAL_OPERATORS = new UnicodeBlock("MATHEMATICAL_OPERATORS", new String[] {"Mathematical Operators", "MathematicalOperators"}); /** * Constant for the "Miscellaneous Technical" Unicode character block. * @since 1.2 */ public static final UnicodeBlock MISCELLANEOUS_TECHNICAL = new UnicodeBlock("MISCELLANEOUS_TECHNICAL", new String[] {"Miscellaneous Technical", "MiscellaneousTechnical"}); /** * Constant for the "Control Pictures" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CONTROL_PICTURES = new UnicodeBlock("CONTROL_PICTURES", new String[] {"Control Pictures", "ControlPictures"}); /** * Constant for the "Optical Character Recognition" Unicode character block. * @since 1.2 */ public static final UnicodeBlock OPTICAL_CHARACTER_RECOGNITION = new UnicodeBlock("OPTICAL_CHARACTER_RECOGNITION", new String[] {"Optical Character Recognition", "OpticalCharacterRecognition"}); /** * Constant for the "Enclosed Alphanumerics" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ENCLOSED_ALPHANUMERICS = new UnicodeBlock("ENCLOSED_ALPHANUMERICS", new String[] {"Enclosed Alphanumerics", "EnclosedAlphanumerics"}); /** * Constant for the "Box Drawing" Unicode character block. * @since 1.2 */ public static final UnicodeBlock BOX_DRAWING = new UnicodeBlock("BOX_DRAWING", new String[] {"Box Drawing", "BoxDrawing"}); /** * Constant for the "Block Elements" Unicode character block. * @since 1.2 */ public static final UnicodeBlock BLOCK_ELEMENTS = new UnicodeBlock("BLOCK_ELEMENTS", new String[] {"Block Elements", "BlockElements"}); /** * Constant for the "Geometric Shapes" Unicode character block. * @since 1.2 */ public static final UnicodeBlock GEOMETRIC_SHAPES = new UnicodeBlock("GEOMETRIC_SHAPES", new String[] {"Geometric Shapes", "GeometricShapes"}); /** * Constant for the "Miscellaneous Symbols" Unicode character block. * @since 1.2 */ public static final UnicodeBlock MISCELLANEOUS_SYMBOLS = new UnicodeBlock("MISCELLANEOUS_SYMBOLS", new String[] {"Miscellaneous Symbols", "MiscellaneousSymbols"}); /** * Constant for the "Dingbats" Unicode character block. * @since 1.2 */ public static final UnicodeBlock DINGBATS = new UnicodeBlock("DINGBATS"); /** * Constant for the "CJK Symbols and Punctuation" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CJK_SYMBOLS_AND_PUNCTUATION = new UnicodeBlock("CJK_SYMBOLS_AND_PUNCTUATION", new String[] {"CJK Symbols and Punctuation", "CJKSymbolsandPunctuation"}); /** * Constant for the "Hiragana" Unicode character block. * @since 1.2 */ public static final UnicodeBlock HIRAGANA = new UnicodeBlock("HIRAGANA"); /** * Constant for the "Katakana" Unicode character block. * @since 1.2 */ public static final UnicodeBlock KATAKANA = new UnicodeBlock("KATAKANA"); /** * Constant for the "Bopomofo" Unicode character block. * @since 1.2 */ public static final UnicodeBlock BOPOMOFO = new UnicodeBlock("BOPOMOFO"); /** * Constant for the "Hangul Compatibility Jamo" Unicode character block. * @since 1.2 */ public static final UnicodeBlock HANGUL_COMPATIBILITY_JAMO = new UnicodeBlock("HANGUL_COMPATIBILITY_JAMO", new String[] {"Hangul Compatibility Jamo", "HangulCompatibilityJamo"}); /** * Constant for the "Kanbun" Unicode character block. * @since 1.2 */ public static final UnicodeBlock KANBUN = new UnicodeBlock("KANBUN"); /** * Constant for the "Enclosed CJK Letters and Months" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ENCLOSED_CJK_LETTERS_AND_MONTHS = new UnicodeBlock("ENCLOSED_CJK_LETTERS_AND_MONTHS", new String[] {"Enclosed CJK Letters and Months", "EnclosedCJKLettersandMonths"}); /** * Constant for the "CJK Compatibility" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CJK_COMPATIBILITY = new UnicodeBlock("CJK_COMPATIBILITY", new String[] {"CJK Compatibility", "CJKCompatibility"}); /** * Constant for the "CJK Unified Ideographs" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS = new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS", new String[] {"CJK Unified Ideographs", "CJKUnifiedIdeographs"}); /** * Constant for the "Hangul Syllables" Unicode character block. * @since 1.2 */ public static final UnicodeBlock HANGUL_SYLLABLES = new UnicodeBlock("HANGUL_SYLLABLES", new String[] {"Hangul Syllables", "HangulSyllables"}); /** * Constant for the "Private Use Area" Unicode character block. * @since 1.2 */ public static final UnicodeBlock PRIVATE_USE_AREA = new UnicodeBlock("PRIVATE_USE_AREA", new String[] {"Private Use Area", "PrivateUseArea"}); /** * Constant for the "CJK Compatibility Ideographs" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS = new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS", new String[] {"CJK Compatibility Ideographs", "CJKCompatibilityIdeographs"}); /** * Constant for the "Alphabetic Presentation Forms" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ALPHABETIC_PRESENTATION_FORMS = new UnicodeBlock("ALPHABETIC_PRESENTATION_FORMS", new String[] {"Alphabetic Presentation Forms", "AlphabeticPresentationForms"}); /** * Constant for the "Arabic Presentation Forms-A" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_A = new UnicodeBlock("ARABIC_PRESENTATION_FORMS_A", new String[] {"Arabic Presentation Forms-A", "ArabicPresentationForms-A"}); /** * Constant for the "Combining Half Marks" Unicode character block. * @since 1.2 */ public static final UnicodeBlock COMBINING_HALF_MARKS = new UnicodeBlock("COMBINING_HALF_MARKS", new String[] {"Combining Half Marks", "CombiningHalfMarks"}); /** * Constant for the "CJK Compatibility Forms" Unicode character block. * @since 1.2 */ public static final UnicodeBlock CJK_COMPATIBILITY_FORMS = new UnicodeBlock("CJK_COMPATIBILITY_FORMS", new String[] {"CJK Compatibility Forms", "CJKCompatibilityForms"}); /** * Constant for the "Small Form Variants" Unicode character block. * @since 1.2 */ public static final UnicodeBlock SMALL_FORM_VARIANTS = new UnicodeBlock("SMALL_FORM_VARIANTS", new String[] {"Small Form Variants", "SmallFormVariants"}); /** * Constant for the "Arabic Presentation Forms-B" Unicode character block. * @since 1.2 */ public static final UnicodeBlock ARABIC_PRESENTATION_FORMS_B = new UnicodeBlock("ARABIC_PRESENTATION_FORMS_B", new String[] {"Arabic Presentation Forms-B", "ArabicPresentationForms-B"}); /** * Constant for the "Halfwidth and Fullwidth Forms" Unicode character block. * @since 1.2 */ public static final UnicodeBlock HALFWIDTH_AND_FULLWIDTH_FORMS = new UnicodeBlock("HALFWIDTH_AND_FULLWIDTH_FORMS", new String[] {"Halfwidth and Fullwidth Forms", "HalfwidthandFullwidthForms"}); /** * Constant for the "Specials" Unicode character block. * @since 1.2 */ public static final UnicodeBlock SPECIALS = new UnicodeBlock("SPECIALS"); /** * @deprecated As of J2SE 5, use {@link #HIGH_SURROGATES}, * {@link #HIGH_PRIVATE_USE_SURROGATES}, and * {@link #LOW_SURROGATES}. These new constants match * the block definitions of the Unicode Standard. * The {@link #of(char)} and {@link #of(int)} methods * return the new constants, not SURROGATES_AREA. */ @Deprecated public static final UnicodeBlock SURROGATES_AREA = new UnicodeBlock("SURROGATES_AREA"); /** * Constant for the "Syriac" Unicode character block. * @since 1.4 */ public static final UnicodeBlock SYRIAC = new UnicodeBlock("SYRIAC"); /** * Constant for the "Thaana" Unicode character block. * @since 1.4 */ public static final UnicodeBlock THAANA = new UnicodeBlock("THAANA"); /** * Constant for the "Sinhala" Unicode character block. * @since 1.4 */ public static final UnicodeBlock SINHALA = new UnicodeBlock("SINHALA"); /** * Constant for the "Myanmar" Unicode character block. * @since 1.4 */ public static final UnicodeBlock MYANMAR = new UnicodeBlock("MYANMAR"); /** * Constant for the "Ethiopic" Unicode character block. * @since 1.4 */ public static final UnicodeBlock ETHIOPIC = new UnicodeBlock("ETHIOPIC"); /** * Constant for the "Cherokee" Unicode character block. * @since 1.4 */ public static final UnicodeBlock CHEROKEE = new UnicodeBlock("CHEROKEE"); /** * Constant for the "Unified Canadian Aboriginal Syllabics" Unicode character block. * @since 1.4 */ public static final UnicodeBlock UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = new UnicodeBlock("UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS", new String[] {"Unified Canadian Aboriginal Syllabics", "UnifiedCanadianAboriginalSyllabics"}); /** * Constant for the "Ogham" Unicode character block. * @since 1.4 */ public static final UnicodeBlock OGHAM = new UnicodeBlock("OGHAM"); /** * Constant for the "Runic" Unicode character block. * @since 1.4 */ public static final UnicodeBlock RUNIC = new UnicodeBlock("RUNIC"); /** * Constant for the "Khmer" Unicode character block. * @since 1.4 */ public static final UnicodeBlock KHMER = new UnicodeBlock("KHMER"); /** * Constant for the "Mongolian" Unicode character block. * @since 1.4 */ public static final UnicodeBlock MONGOLIAN = new UnicodeBlock("MONGOLIAN"); /** * Constant for the "Braille Patterns" Unicode character block. * @since 1.4 */ public static final UnicodeBlock BRAILLE_PATTERNS = new UnicodeBlock("BRAILLE_PATTERNS", new String[] {"Braille Patterns", "BraillePatterns"}); /** * Constant for the "CJK Radicals Supplement" Unicode character block. * @since 1.4 */ public static final UnicodeBlock CJK_RADICALS_SUPPLEMENT = new UnicodeBlock("CJK_RADICALS_SUPPLEMENT", new String[] {"CJK Radicals Supplement", "CJKRadicalsSupplement"}); /** * Constant for the "Kangxi Radicals" Unicode character block. * @since 1.4 */ public static final UnicodeBlock KANGXI_RADICALS = new UnicodeBlock("KANGXI_RADICALS", new String[] {"Kangxi Radicals", "KangxiRadicals"}); /** * Constant for the "Ideographic Description Characters" Unicode character block. * @since 1.4 */ public static final UnicodeBlock IDEOGRAPHIC_DESCRIPTION_CHARACTERS = new UnicodeBlock("IDEOGRAPHIC_DESCRIPTION_CHARACTERS", new String[] {"Ideographic Description Characters", "IdeographicDescriptionCharacters"}); /** * Constant for the "Bopomofo Extended" Unicode character block. * @since 1.4 */ public static final UnicodeBlock BOPOMOFO_EXTENDED = new UnicodeBlock("BOPOMOFO_EXTENDED", new String[] {"Bopomofo Extended", "BopomofoExtended"}); /** * Constant for the "CJK Unified Ideographs Extension A" Unicode character block. * @since 1.4 */ public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A", new String[] {"CJK Unified Ideographs Extension A", "CJKUnifiedIdeographsExtensionA"}); /** * Constant for the "Yi Syllables" Unicode character block. * @since 1.4 */ public static final UnicodeBlock YI_SYLLABLES = new UnicodeBlock("YI_SYLLABLES", new String[] {"Yi Syllables", "YiSyllables"}); /** * Constant for the "Yi Radicals" Unicode character block. * @since 1.4 */ public static final UnicodeBlock YI_RADICALS = new UnicodeBlock("YI_RADICALS", new String[] {"Yi Radicals", "YiRadicals"}); /** * Constant for the "Cyrillic Supplementary" Unicode character block. * @since 1.5 */ public static final UnicodeBlock CYRILLIC_SUPPLEMENTARY = new UnicodeBlock("CYRILLIC_SUPPLEMENTARY", new String[] {"Cyrillic Supplementary", "CyrillicSupplementary"}); /** * Constant for the "Tagalog" Unicode character block. * @since 1.5 */ public static final UnicodeBlock TAGALOG = new UnicodeBlock("TAGALOG"); /** * Constant for the "Hanunoo" Unicode character block. * @since 1.5 */ public static final UnicodeBlock HANUNOO = new UnicodeBlock("HANUNOO"); /** * Constant for the "Buhid" Unicode character block. * @since 1.5 */ public static final UnicodeBlock BUHID = new UnicodeBlock("BUHID"); /** * Constant for the "Tagbanwa" Unicode character block. * @since 1.5 */ public static final UnicodeBlock TAGBANWA = new UnicodeBlock("TAGBANWA"); /** * Constant for the "Limbu" Unicode character block. * @since 1.5 */ public static final UnicodeBlock LIMBU = new UnicodeBlock("LIMBU"); /** * Constant for the "Tai Le" Unicode character block. * @since 1.5 */ public static final UnicodeBlock TAI_LE = new UnicodeBlock("TAI_LE", new String[] {"Tai Le", "TaiLe"}); /** * Constant for the "Khmer Symbols" Unicode character block. * @since 1.5 */ public static final UnicodeBlock KHMER_SYMBOLS = new UnicodeBlock("KHMER_SYMBOLS", new String[] {"Khmer Symbols", "KhmerSymbols"}); /** * Constant for the "Phonetic Extensions" Unicode character block. * @since 1.5 */ public static final UnicodeBlock PHONETIC_EXTENSIONS = new UnicodeBlock("PHONETIC_EXTENSIONS", new String[] {"Phonetic Extensions", "PhoneticExtensions"}); /** * Constant for the "Miscellaneous Mathematical Symbols-A" Unicode character block. * @since 1.5 */ public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A", new String[]{"Miscellaneous Mathematical Symbols-A", "MiscellaneousMathematicalSymbols-A"}); /** * Constant for the "Supplemental Arrows-A" Unicode character block. * @since 1.5 */ public static final UnicodeBlock SUPPLEMENTAL_ARROWS_A = new UnicodeBlock("SUPPLEMENTAL_ARROWS_A", new String[] {"Supplemental Arrows-A", "SupplementalArrows-A"}); /** * Constant for the "Supplemental Arrows-B" Unicode character block. * @since 1.5 */ public static final UnicodeBlock SUPPLEMENTAL_ARROWS_B = new UnicodeBlock("SUPPLEMENTAL_ARROWS_B", new String[] {"Supplemental Arrows-B", "SupplementalArrows-B"}); /** * Constant for the "Miscellaneous Mathematical Symbols-B" Unicode character block. * @since 1.5 */ public static final UnicodeBlock MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = new UnicodeBlock("MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B", new String[] {"Miscellaneous Mathematical Symbols-B", "MiscellaneousMathematicalSymbols-B"}); /** * Constant for the "Supplemental Mathematical Operators" Unicode character block. * @since 1.5 */ public static final UnicodeBlock SUPPLEMENTAL_MATHEMATICAL_OPERATORS = new UnicodeBlock("SUPPLEMENTAL_MATHEMATICAL_OPERATORS", new String[]{"Supplemental Mathematical Operators", "SupplementalMathematicalOperators"} ); /** * Constant for the "Miscellaneous Symbols and Arrows" Unicode character block. * @since 1.5 */ public static final UnicodeBlock MISCELLANEOUS_SYMBOLS_AND_ARROWS = new UnicodeBlock("MISCELLANEOUS_SYMBOLS_AND_ARROWS", new String[] {"Miscellaneous Symbols and Arrows", "MiscellaneousSymbolsandArrows"}); /** * Constant for the "Katakana Phonetic Extensions" Unicode character block. * @since 1.5 */ public static final UnicodeBlock KATAKANA_PHONETIC_EXTENSIONS = new UnicodeBlock("KATAKANA_PHONETIC_EXTENSIONS", new String[] {"Katakana Phonetic Extensions", "KatakanaPhoneticExtensions"}); /** * Constant for the "Yijing Hexagram Symbols" Unicode character block. * @since 1.5 */ public static final UnicodeBlock YIJING_HEXAGRAM_SYMBOLS = new UnicodeBlock("YIJING_HEXAGRAM_SYMBOLS", new String[] {"Yijing Hexagram Symbols", "YijingHexagramSymbols"}); /** * Constant for the "Variation Selectors" Unicode character block. * @since 1.5 */ public static final UnicodeBlock VARIATION_SELECTORS = new UnicodeBlock("VARIATION_SELECTORS", new String[] {"Variation Selectors", "VariationSelectors"}); /** * Constant for the "Linear B Syllabary" Unicode character block. * @since 1.5 */ public static final UnicodeBlock LINEAR_B_SYLLABARY = new UnicodeBlock("LINEAR_B_SYLLABARY", new String[] {"Linear B Syllabary", "LinearBSyllabary"}); /** * Constant for the "Linear B Ideograms" Unicode character block. * @since 1.5 */ public static final UnicodeBlock LINEAR_B_IDEOGRAMS = new UnicodeBlock("LINEAR_B_IDEOGRAMS", new String[] {"Linear B Ideograms", "LinearBIdeograms"}); /** * Constant for the "Aegean Numbers" Unicode character block. * @since 1.5 */ public static final UnicodeBlock AEGEAN_NUMBERS = new UnicodeBlock("AEGEAN_NUMBERS", new String[] {"Aegean Numbers", "AegeanNumbers"}); /** * Constant for the "Old Italic" Unicode character block. * @since 1.5 */ public static final UnicodeBlock OLD_ITALIC = new UnicodeBlock("OLD_ITALIC", new String[] {"Old Italic", "OldItalic"}); /** * Constant for the "Gothic" Unicode character block. * @since 1.5 */ public static final UnicodeBlock GOTHIC = new UnicodeBlock("GOTHIC"); /** * Constant for the "Ugaritic" Unicode character block. * @since 1.5 */ public static final UnicodeBlock UGARITIC = new UnicodeBlock("UGARITIC"); /** * Constant for the "Deseret" Unicode character block. * @since 1.5 */ public static final UnicodeBlock DESERET = new UnicodeBlock("DESERET"); /** * Constant for the "Shavian" Unicode character block. * @since 1.5 */ public static final UnicodeBlock SHAVIAN = new UnicodeBlock("SHAVIAN"); /** * Constant for the "Osmanya" Unicode character block. * @since 1.5 */ public static final UnicodeBlock OSMANYA = new UnicodeBlock("OSMANYA"); /** * Constant for the "Cypriot Syllabary" Unicode character block. * @since 1.5 */ public static final UnicodeBlock CYPRIOT_SYLLABARY = new UnicodeBlock("CYPRIOT_SYLLABARY", new String[] {"Cypriot Syllabary", "CypriotSyllabary"}); /** * Constant for the "Byzantine Musical Symbols" Unicode character block. * @since 1.5 */ public static final UnicodeBlock BYZANTINE_MUSICAL_SYMBOLS = new UnicodeBlock("BYZANTINE_MUSICAL_SYMBOLS", new String[] {"Byzantine Musical Symbols", "ByzantineMusicalSymbols"}); /** * Constant for the "Musical Symbols" Unicode character block. * @since 1.5 */ public static final UnicodeBlock MUSICAL_SYMBOLS = new UnicodeBlock("MUSICAL_SYMBOLS", new String[] {"Musical Symbols", "MusicalSymbols"}); /** * Constant for the "Tai Xuan Jing Symbols" Unicode character block. * @since 1.5 */ public static final UnicodeBlock TAI_XUAN_JING_SYMBOLS = new UnicodeBlock("TAI_XUAN_JING_SYMBOLS", new String[] {"Tai Xuan Jing Symbols", "TaiXuanJingSymbols"}); /** * Constant for the "Mathematical Alphanumeric Symbols" Unicode character block. * @since 1.5 */ public static final UnicodeBlock MATHEMATICAL_ALPHANUMERIC_SYMBOLS = new UnicodeBlock("MATHEMATICAL_ALPHANUMERIC_SYMBOLS", new String[] {"Mathematical Alphanumeric Symbols", "MathematicalAlphanumericSymbols"}); /** * Constant for the "CJK Unified Ideographs Extension B" Unicode character block. * @since 1.5 */ public static final UnicodeBlock CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = new UnicodeBlock("CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B", new String[] {"CJK Unified Ideographs Extension B", "CJKUnifiedIdeographsExtensionB"}); /** * Constant for the "CJK Compatibility Ideographs Supplement" Unicode character block. * @since 1.5 */ public static final UnicodeBlock CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = new UnicodeBlock("CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT", new String[]{"CJK Compatibility Ideographs Supplement", "CJKCompatibilityIdeographsSupplement"}); /** * Constant for the "Tags" Unicode character block. * @since 1.5 */ public static final UnicodeBlock TAGS = new UnicodeBlock("TAGS"); /** * Constant for the "Variation Selectors Supplement" Unicode character block. * @since 1.5 */ public static final UnicodeBlock VARIATION_SELECTORS_SUPPLEMENT = new UnicodeBlock("VARIATION_SELECTORS_SUPPLEMENT", new String[] {"Variation Selectors Supplement", "VariationSelectorsSupplement"}); /** * Constant for the "Supplementary Private Use Area-A" Unicode character block. * @since 1.5 */ public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_A = new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_A", new String[] {"Supplementary Private Use Area-A", "SupplementaryPrivateUseArea-A"}); /** * Constant for the "Supplementary Private Use Area-B" Unicode character block. * @since 1.5 */ public static final UnicodeBlock SUPPLEMENTARY_PRIVATE_USE_AREA_B = new UnicodeBlock("SUPPLEMENTARY_PRIVATE_USE_AREA_B", new String[] {"Supplementary Private Use Area-B", "SupplementaryPrivateUseArea-B"}); /** * Constant for the "High Surrogates" Unicode character block. * This block represents codepoint values in the high surrogate * range: 0xD800 through 0xDB7F * * @since 1.5 */ public static final UnicodeBlock HIGH_SURROGATES = new UnicodeBlock("HIGH_SURROGATES", new String[] {"High Surrogates", "HighSurrogates"}); /** * Constant for the "High Private Use Surrogates" Unicode character block. * This block represents codepoint values in the high surrogate * range: 0xDB80 through 0xDBFF * * @since 1.5 */ public static final UnicodeBlock HIGH_PRIVATE_USE_SURROGATES = new UnicodeBlock("HIGH_PRIVATE_USE_SURROGATES", new String[] { "High Private Use Surrogates", "HighPrivateUseSurrogates"}); /** * Constant for the "Low Surrogates" Unicode character block. * This block represents codepoint values in the high surrogate * range: 0xDC00 through 0xDFFF * * @since 1.5 */ public static final UnicodeBlock LOW_SURROGATES = new UnicodeBlock("LOW_SURROGATES", new String[] {"Low Surrogates", "LowSurrogates"}); private static final int blockStarts[] = { 0x0000, // Basic Latin 0x0080, // Latin-1 Supplement 0x0100, // Latin Extended-A 0x0180, // Latin Extended-B 0x0250, // IPA Extensions 0x02B0, // Spacing Modifier Letters 0x0300, // Combining Diacritical Marks 0x0370, // Greek and Coptic 0x0400, // Cyrillic 0x0500, // Cyrillic Supplementary 0x0530, // Armenian 0x0590, // Hebrew 0x0600, // Arabic 0x0700, // Syriac 0x0750, // unassigned 0x0780, // Thaana 0x07C0, // unassigned 0x0900, // Devanagari 0x0980, // Bengali 0x0A00, // Gurmukhi 0x0A80, // Gujarati 0x0B00, // Oriya 0x0B80, // Tamil 0x0C00, // Telugu 0x0C80, // Kannada 0x0D00, // Malayalam 0x0D80, // Sinhala 0x0E00, // Thai 0x0E80, // Lao 0x0F00, // Tibetan 0x1000, // Myanmar 0x10A0, // Georgian 0x1100, // Hangul Jamo 0x1200, // Ethiopic 0x1380, // unassigned 0x13A0, // Cherokee 0x1400, // Unified Canadian Aboriginal Syllabics 0x1680, // Ogham 0x16A0, // Runic 0x1700, // Tagalog 0x1720, // Hanunoo 0x1740, // Buhid 0x1760, // Tagbanwa 0x1780, // Khmer 0x1800, // Mongolian 0x18B0, // unassigned 0x1900, // Limbu 0x1950, // Tai Le 0x1980, // unassigned 0x19E0, // Khmer Symbols 0x1A00, // unassigned 0x1D00, // Phonetic Extensions 0x1D80, // unassigned 0x1E00, // Latin Extended Additional 0x1F00, // Greek Extended 0x2000, // General Punctuation 0x2070, // Superscripts and Subscripts 0x20A0, // Currency Symbols 0x20D0, // Combining Diacritical Marks for Symbols 0x2100, // Letterlike Symbols 0x2150, // Number Forms 0x2190, // Arrows 0x2200, // Mathematical Operators 0x2300, // Miscellaneous Technical 0x2400, // Control Pictures 0x2440, // Optical Character Recognition 0x2460, // Enclosed Alphanumerics 0x2500, // Box Drawing 0x2580, // Block Elements 0x25A0, // Geometric Shapes 0x2600, // Miscellaneous Symbols 0x2700, // Dingbats 0x27C0, // Miscellaneous Mathematical Symbols-A 0x27F0, // Supplemental Arrows-A 0x2800, // Braille Patterns 0x2900, // Supplemental Arrows-B 0x2980, // Miscellaneous Mathematical Symbols-B 0x2A00, // Supplemental Mathematical Operators 0x2B00, // Miscellaneous Symbols and Arrows 0x2C00, // unassigned 0x2E80, // CJK Radicals Supplement 0x2F00, // Kangxi Radicals 0x2FE0, // unassigned 0x2FF0, // Ideographic Description Characters 0x3000, // CJK Symbols and Punctuation 0x3040, // Hiragana 0x30A0, // Katakana 0x3100, // Bopomofo 0x3130, // Hangul Compatibility Jamo 0x3190, // Kanbun 0x31A0, // Bopomofo Extended 0x31C0, // unassigned 0x31F0, // Katakana Phonetic Extensions 0x3200, // Enclosed CJK Letters and Months 0x3300, // CJK Compatibility 0x3400, // CJK Unified Ideographs Extension A 0x4DC0, // Yijing Hexagram Symbols 0x4E00, // CJK Unified Ideographs 0xA000, // Yi Syllables 0xA490, // Yi Radicals 0xA4D0, // unassigned 0xAC00, // Hangul Syllables 0xD7B0, // unassigned 0xD800, // High Surrogates 0xDB80, // High Private Use Surrogates 0xDC00, // Low Surrogates 0xE000, // Private Use 0xF900, // CJK Compatibility Ideographs 0xFB00, // Alphabetic Presentation Forms 0xFB50, // Arabic Presentation Forms-A 0xFE00, // Variation Selectors 0xFE10, // unassigned 0xFE20, // Combining Half Marks 0xFE30, // CJK Compatibility Forms 0xFE50, // Small Form Variants 0xFE70, // Arabic Presentation Forms-B 0xFF00, // Halfwidth and Fullwidth Forms 0xFFF0, // Specials 0x10000, // Linear B Syllabary 0x10080, // Linear B Ideograms 0x10100, // Aegean Numbers 0x10140, // unassigned 0x10300, // Old Italic 0x10330, // Gothic 0x10350, // unassigned 0x10380, // Ugaritic 0x103A0, // unassigned 0x10400, // Deseret 0x10450, // Shavian 0x10480, // Osmanya 0x104B0, // unassigned 0x10800, // Cypriot Syllabary 0x10840, // unassigned 0x1D000, // Byzantine Musical Symbols 0x1D100, // Musical Symbols 0x1D200, // unassigned 0x1D300, // Tai Xuan Jing Symbols 0x1D360, // unassigned 0x1D400, // Mathematical Alphanumeric Symbols 0x1D800, // unassigned 0x20000, // CJK Unified Ideographs Extension B 0x2A6E0, // unassigned 0x2F800, // CJK Compatibility Ideographs Supplement 0x2FA20, // unassigned 0xE0000, // Tags 0xE0080, // unassigned 0xE0100, // Variation Selectors Supplement 0xE01F0, // unassigned 0xF0000, // Supplementary Private Use Area-A 0x100000, // Supplementary Private Use Area-B }; private static final UnicodeBlock[] blocks = { BASIC_LATIN, LATIN_1_SUPPLEMENT, LATIN_EXTENDED_A, LATIN_EXTENDED_B, IPA_EXTENSIONS, SPACING_MODIFIER_LETTERS, COMBINING_DIACRITICAL_MARKS, GREEK, CYRILLIC, CYRILLIC_SUPPLEMENTARY, ARMENIAN, HEBREW, ARABIC, SYRIAC, null, THAANA, null, DEVANAGARI, BENGALI, GURMUKHI, GUJARATI, ORIYA, TAMIL, TELUGU, KANNADA, MALAYALAM, SINHALA, THAI, LAO, TIBETAN, MYANMAR, GEORGIAN, HANGUL_JAMO, ETHIOPIC, null, CHEROKEE, UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS, OGHAM, RUNIC, TAGALOG, HANUNOO, BUHID, TAGBANWA, KHMER, MONGOLIAN, null, LIMBU, TAI_LE, null, KHMER_SYMBOLS, null, PHONETIC_EXTENSIONS, null, LATIN_EXTENDED_ADDITIONAL, GREEK_EXTENDED, GENERAL_PUNCTUATION, SUPERSCRIPTS_AND_SUBSCRIPTS, CURRENCY_SYMBOLS, COMBINING_MARKS_FOR_SYMBOLS, LETTERLIKE_SYMBOLS, NUMBER_FORMS, ARROWS, MATHEMATICAL_OPERATORS, MISCELLANEOUS_TECHNICAL, CONTROL_PICTURES, OPTICAL_CHARACTER_RECOGNITION, ENCLOSED_ALPHANUMERICS, BOX_DRAWING, BLOCK_ELEMENTS, GEOMETRIC_SHAPES, MISCELLANEOUS_SYMBOLS, DINGBATS, MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A, SUPPLEMENTAL_ARROWS_A, BRAILLE_PATTERNS, SUPPLEMENTAL_ARROWS_B, MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B, SUPPLEMENTAL_MATHEMATICAL_OPERATORS, MISCELLANEOUS_SYMBOLS_AND_ARROWS, null, CJK_RADICALS_SUPPLEMENT, KANGXI_RADICALS, null, IDEOGRAPHIC_DESCRIPTION_CHARACTERS, CJK_SYMBOLS_AND_PUNCTUATION, HIRAGANA, KATAKANA, BOPOMOFO, HANGUL_COMPATIBILITY_JAMO, KANBUN, BOPOMOFO_EXTENDED, null, KATAKANA_PHONETIC_EXTENSIONS, ENCLOSED_CJK_LETTERS_AND_MONTHS, CJK_COMPATIBILITY, CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A, YIJING_HEXAGRAM_SYMBOLS, CJK_UNIFIED_IDEOGRAPHS, YI_SYLLABLES, YI_RADICALS, null, HANGUL_SYLLABLES, null, HIGH_SURROGATES, HIGH_PRIVATE_USE_SURROGATES, LOW_SURROGATES, PRIVATE_USE_AREA, CJK_COMPATIBILITY_IDEOGRAPHS, ALPHABETIC_PRESENTATION_FORMS, ARABIC_PRESENTATION_FORMS_A, VARIATION_SELECTORS, null, COMBINING_HALF_MARKS, CJK_COMPATIBILITY_FORMS, SMALL_FORM_VARIANTS, ARABIC_PRESENTATION_FORMS_B, HALFWIDTH_AND_FULLWIDTH_FORMS, SPECIALS, LINEAR_B_SYLLABARY, LINEAR_B_IDEOGRAMS, AEGEAN_NUMBERS, null, OLD_ITALIC, GOTHIC, null, UGARITIC, null, DESERET, SHAVIAN, OSMANYA, null, CYPRIOT_SYLLABARY, null, BYZANTINE_MUSICAL_SYMBOLS, MUSICAL_SYMBOLS, null, TAI_XUAN_JING_SYMBOLS, null, MATHEMATICAL_ALPHANUMERIC_SYMBOLS, null, CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B, null, CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT, null, TAGS, null, VARIATION_SELECTORS_SUPPLEMENT, null, SUPPLEMENTARY_PRIVATE_USE_AREA_A, SUPPLEMENTARY_PRIVATE_USE_AREA_B }; /** * Returns the object representing the Unicode block containing the * given character, or <code>null</code> if the character is not a * member of a defined block. * * <p><b>Note:</b> This method cannot handle <a * href="Character.html#supplementary"> supplementary * characters</a>. To support all Unicode characters, * including supplementary characters, use the {@link * #of(int)} method. * * @param c The character in question * @return The <code>UnicodeBlock</code> instance representing the * Unicode block of which this character is a member, or * <code>null</code> if the character is not a member of any * Unicode block */ public static UnicodeBlock of(char c) { return of((int)c); } /** * Returns the object representing the Unicode block * containing the given character (Unicode code point), or * <code>null</code> if the character is not a member of a * defined block. * * @param codePoint the character (Unicode code point) in question. * @return The <code>UnicodeBlock</code> instance representing the * Unicode block of which this character is a member, or * <code>null</code> if the character is not a member of any * Unicode block * @exception IllegalArgumentException if the specified * <code>codePoint</code> is an invalid Unicode code point. * @see Character#isValidCodePoint(int) * @since 1.5 */ public static UnicodeBlock of(int codePoint) { if (!isValidCodePoint(codePoint)) { throw new IllegalArgumentException(); } int top, bottom, current; bottom = 0; top = blockStarts.length; current = top/2; // invariant: top > current >= bottom && codePoint >= unicodeBlockStarts[bottom] while (top - bottom > 1) { if (codePoint >= blockStarts[current]) { bottom = current; } else { top = current; } current = (top + bottom) / 2; } return blocks[current]; } /** * Returns the UnicodeBlock with the given name. Block * names are determined by The Unicode Standard. The file * Blocks-<version>.txt defines blocks for a particular * version of the standard. The {@link Character} class specifies * the version of the standard that it supports. * <p> * This method accepts block names in the following forms: * <ol> * <li> Canonical block names as defined by the Unicode Standard. * For example, the standard defines a "Basic Latin" block. Therefore, this * method accepts "Basic Latin" as a valid block name. The documentation of * each UnicodeBlock provides the canonical name. * <li>Canonical block names with all spaces removed. For example, "BasicLatin" * is a valid block name for the "Basic Latin" block. * <li>The text representation of each constant UnicodeBlock identifier. * For example, this method will return the {@link #BASIC_LATIN} block if * provided with the "BASIC_LATIN" name. This form replaces all spaces and * hyphens in the canonical name with underscores. * </ol> * Finally, character case is ignored for all of the valid block name forms. * For example, "BASIC_LATIN" and "basic_latin" are both valid block names. * The en_US locale's case mapping rules are used to provide case-insensitive * string comparisons for block name validation. * <p> * If the Unicode Standard changes block names, both the previous and * current names will be accepted. * * @param blockName A <code>UnicodeBlock</code> name. * @return The <code>UnicodeBlock</code> instance identified * by <code>blockName</code> * @throws IllegalArgumentException if <code>blockName</code> is an * invalid name * @throws NullPointerException if <code>blockName</code> is null * @since 1.5 */ public static final UnicodeBlock forName(String blockName) { UnicodeBlock block = (UnicodeBlock)map.get(blockName.toUpperCase(Locale.US)); if (block == null) { throw new IllegalArgumentException(); } return block; } } /** * The value of the <code>Character</code>. * * @serial */ private final char value; /** use serialVersionUID from JDK 1.0.2 for interoperability */ private static final long serialVersionUID = 3786198910865385080L; /** * Constructs a newly allocated <code>Character</code> object that * represents the specified <code>char</code> value. * * @param value the value to be represented by the * <code>Character</code> object. */ public Character(char value) { this.value = value; } private static class CharacterCache { private CharacterCache(){} static final Character cache[] = new Character[127 + 1]; static { for(int i = 0; i < cache.length; i++) cache[i] = new Character((char)i); } } /** * Returns a <tt>Character</tt> instance representing the specified * <tt>char</tt> value. * If a new <tt>Character</tt> instance is not required, this method * should generally be used in preference to the constructor * {@link #Character(char)}, as this method is likely to yield * significantly better space and time performance by caching * frequently requested values. * * @param c a char value. * @return a <tt>Character</tt> instance representing <tt>c</tt>. * @since 1.5 */ public static Character valueOf(char c) { if(c <= 127) { // must cache return CharacterCache.cache[(int)c]; } return new Character(c); } /** * Returns the value of this <code>Character</code> object. * @return the primitive <code>char</code> value represented by * this object. */ public char charValue() { return value; } /** * Returns a hash code for this <code>Character</code>. * @return a hash code value for this object. */ public int hashCode() { return (int)value; } /** * Compares this object against the specified object. * The result is <code>true</code> if and only if the argument is not * <code>null</code> and is a <code>Character</code> object that * represents the same <code>char</code> value as this object. * * @param obj the object to compare with. * @return <code>true</code> if the objects are the same; * <code>false</code> otherwise. */ public boolean equals(Object obj) { if (obj instanceof Character) { return value == ((Character)obj).charValue(); } return false; } /** * Returns a <code>String</code> object representing this * <code>Character</code>'s value. The result is a string of * length 1 whose sole component is the primitive * <code>char</code> value represented by this * <code>Character</code> object. * * @return a string representation of this object. */ public String toString() { char buf[] = {value}; return String.valueOf(buf); } /** * Returns a <code>String</code> object representing the * specified <code>char</code>. The result is a string of length * 1 consisting solely of the specified <code>char</code>. * * @param c the <code>char</code> to be converted * @return the string representation of the specified <code>char</code> * @since 1.4 */ public static String toString(char c) { return String.valueOf(c); } // Maximum character handled by internal fast-path code which // avoids initializing large tables. // Note: performance of this "fast-path" code may be sub-optimal // in negative cases for some accessors due to complicated ranges. // Should revisit after optimization of table initialization. private static final int FAST_PATH_MAX = 255; /** * Provide the character plane to which this codepoint belongs. * * @param ch the codepoint * @return the plane of the codepoint argument * @since 1.5 */ private static int getPlane(int ch) { return (ch >>> 16); } /** * Determines whether the specified code point is a valid Unicode * code point value in the range of <code>0x0000</code> to * <code>0x10FFFF</code> inclusive. This method is equivalent to * the expression: * * <blockquote><pre> * codePoint >= 0x0000 && codePoint <= 0x10FFFF * </pre></blockquote> * * @param codePoint the Unicode code point to be tested * @return <code>true</code> if the specified code point value * is a valid code point value; * <code>false</code> otherwise. * @since 1.5 */ public static boolean isValidCodePoint(int codePoint) { return codePoint >= MIN_CODE_POINT && codePoint <= MAX_CODE_POINT; } /** * Determines whether the specified character (Unicode code point) * is in the supplementary character range. The method call is * equivalent to the expression: * <blockquote><pre> * codePoint >= 0x10000 && codePoint <= 0x10FFFF * </pre></blockquote> * * @param codePoint the character (Unicode code point) to be tested * @return <code>true</code> if the specified character is in the Unicode * supplementary character range; <code>false</code> otherwise. * @since 1.5 */ public static boolean isSupplementaryCodePoint(int codePoint) { return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT && codePoint <= MAX_CODE_POINT; } /** * Determines if the given <code>char</code> value is a * high-surrogate code unit (also known as <i>leading-surrogate * code unit</i>). Such values do not represent characters by * themselves, but are used in the representation of <a * href="#supplementary">supplementary characters</a> in the * UTF-16 encoding. * * <p>This method returns <code>true</code> if and only if * <blockquote><pre>ch >= '\uD800' && ch <= '\uDBFF' * </pre></blockquote> * is <code>true</code>. * * @param ch the <code>char</code> value to be tested. * @return <code>true</code> if the <code>char</code> value * is between '\uD800' and '\uDBFF' inclusive; * <code>false</code> otherwise. * @see java.lang.Character#isLowSurrogate(char) * @see Character.UnicodeBlock#of(int) * @since 1.5 */ public static boolean isHighSurrogate(char ch) { return ch >= MIN_HIGH_SURROGATE && ch <= MAX_HIGH_SURROGATE; } /** * Determines if the given <code>char</code> value is a * low-surrogate code unit (also known as <i>trailing-surrogate code * unit</i>). Such values do not represent characters by themselves, * but are used in the representation of <a * href="#supplementary">supplementary characters</a> in the UTF-16 encoding. * * <p> This method returns <code>true</code> if and only if * <blockquote><pre>ch >= '\uDC00' && ch <= '\uDFFF' * </pre></blockquote> is <code>true</code>. * * @param ch the <code>char</code> value to be tested. * @return <code>true</code> if the <code>char</code> value * is between '\uDC00' and '\uDFFF' inclusive; * <code>false</code> otherwise. * @see java.lang.Character#isHighSurrogate(char) * @since 1.5 */ public static boolean isLowSurrogate(char ch) { return ch >= MIN_LOW_SURROGATE && ch <= MAX_LOW_SURROGATE; } /** * Determines whether the specified pair of <code>char</code> * values is a valid surrogate pair. This method is equivalent to * the expression: * <blockquote><pre> * isHighSurrogate(high) && isLowSurrogate(low) * </pre></blockquote> * * @param high the high-surrogate code value to be tested * @param low the low-surrogate code value to be tested * @return <code>true</code> if the specified high and * low-surrogate code values represent a valid surrogate pair; * <code>false</code> otherwise. * @since 1.5 */ public static boolean isSurrogatePair(char high, char low) { return isHighSurrogate(high) && isLowSurrogate(low); } /** * Determines the number of <code>char</code> values needed to * represent the specified character (Unicode code point). If the * specified character is equal to or greater than 0x10000, then * the method returns 2. Otherwise, the method returns 1. * * <p>This method doesn't validate the specified character to be a * valid Unicode code point. The caller must validate the * character value using {@link #isValidCodePoint(int) isValidCodePoint} * if necessary. * * @param codePoint the character (Unicode code point) to be tested. * @return 2 if the character is a valid supplementary character; 1 otherwise. * @see #isSupplementaryCodePoint(int) * @since 1.5 */ public static int charCount(int codePoint) { return codePoint >= MIN_SUPPLEMENTARY_CODE_POINT? 2 : 1; } /** * Converts the specified surrogate pair to its supplementary code * point value. This method does not validate the specified * surrogate pair. The caller must validate it using {@link * #isSurrogatePair(char, char) isSurrogatePair} if necessary. * * @param high the high-surrogate code unit * @param low the low-surrogate code unit * @return the supplementary code point composed from the * specified surrogate pair. * @since 1.5 */ public static int toCodePoint(char high, char low) { return ((high - MIN_HIGH_SURROGATE) << 10) + (low - MIN_LOW_SURROGATE) + MIN_SUPPLEMENTARY_CODE_POINT; } /** * Returns the code point at the given index of the * <code>CharSequence</code>. If the <code>char</code> value at * the given index in the <code>CharSequence</code> is in the * high-surrogate range, the following index is less than the * length of the <code>CharSequence</code>, and the * <code>char</code> value at the following index is in the * low-surrogate range, then the supplementary code point * corresponding to this surrogate pair is returned. Otherwise, * the <code>char</code> value at the given index is returned. * * @param seq a sequence of <code>char</code> values (Unicode code * units) * @param index the index to the <code>char</code> values (Unicode * code units) in <code>seq</code> to be converted * @return the Unicode code point at the given index * @exception NullPointerException if <code>seq</code> is null. * @exception IndexOutOfBoundsException if the value * <code>index</code> is negative or not less than * {@link CharSequence#length() seq.length()}. * @since 1.5 */ public static int codePointAt(CharSequence seq, int index) { char c1 = seq.charAt(index++); if (isHighSurrogate(c1)) { if (index < seq.length()) { char c2 = seq.charAt(index); if (isLowSurrogate(c2)) { return toCodePoint(c1, c2); } } } return c1; } /** * Returns the code point at the given index of the * <code>char</code> array. If the <code>char</code> value at * the given index in the <code>char</code> array is in the * high-surrogate range, the following index is less than the * length of the <code>char</code> array, and the * <code>char</code> value at the following index is in the * low-surrogate range, then the supplementary code point * corresponding to this surrogate pair is returned. Otherwise, * the <code>char</code> value at the given index is returned. * * @param a the <code>char</code> array * @param index the index to the <code>char</code> values (Unicode * code units) in the <code>char</code> array to be converted * @return the Unicode code point at the given index * @exception NullPointerException if <code>a</code> is null. * @exception IndexOutOfBoundsException if the value * <code>index</code> is negative or not less than * the length of the <code>char</code> array. * @since 1.5 */ public static int codePointAt(char[] a, int index) { return codePointAtImpl(a, index, a.length); } /** * Returns the code point at the given index of the * <code>char</code> array, where only array elements with * <code>index</code> less than <code>limit</code> can be used. If * the <code>char</code> value at the given index in the * <code>char</code> array is in the high-surrogate range, the * following index is less than the <code>limit</code>, and the * <code>char</code> value at the following index is in the * low-surrogate range, then the supplementary code point * corresponding to this surrogate pair is returned. Otherwise, * the <code>char</code> value at the given index is returned. * * @param a the <code>char</code> array * @param index the index to the <code>char</code> values (Unicode * code units) in the <code>char</code> array to be converted * @param limit the index after the last array element that can be used in the * <code>char</code> array * @return the Unicode code point at the given index * @exception NullPointerException if <code>a</code> is null. * @exception IndexOutOfBoundsException if the <code>index</code> * argument is negative or not less than the <code>limit</code> * argument, or if the <code>limit</code> argument is negative or * greater than the length of the <code>char</code> array. * @since 1.5 */ public static int codePointAt(char[] a, int index, int limit) { if (index >= limit || limit < 0 || limit > a.length) { throw new IndexOutOfBoundsException(); } return codePointAtImpl(a, index, limit); } static int codePointAtImpl(char[] a, int index, int limit) { char c1 = a[index++]; if (isHighSurrogate(c1)) { if (index < limit) { char c2 = a[index]; if (isLowSurrogate(c2)) { return toCodePoint(c1, c2); } } } return c1; } /** * Returns the code point preceding the given index of the * <code>CharSequence</code>. If the <code>char</code> value at * <code>(index - 1)</code> in the <code>CharSequence</code> is in * the low-surrogate range, <code>(index - 2)</code> is not * negative, and the <code>char</code> value at <code>(index - * 2)</code> in the <code>CharSequence</code> is in the * high-surrogate range, then the supplementary code point * corresponding to this surrogate pair is returned. Otherwise, * the <code>char</code> value at <code>(index - 1)</code> is * returned. * * @param seq the <code>CharSequence</code> instance * @param index the index following the code point that should be returned * @return the Unicode code point value before the given index. * @exception NullPointerException if <code>seq</code> is null. * @exception IndexOutOfBoundsException if the <code>index</code> * argument is less than 1 or greater than {@link * CharSequence#length() seq.length()}. * @since 1.5 */ public static int codePointBefore(CharSequence seq, int index) { char c2 = seq.charAt(--index); if (isLowSurrogate(c2)) { if (index > 0) { char c1 = seq.charAt(--index); if (isHighSurrogate(c1)) { return toCodePoint(c1, c2); } } } return c2; } /** * Returns the code point preceding the given index of the * <code>char</code> array. If the <code>char</code> value at * <code>(index - 1)</code> in the <code>char</code> array is in * the low-surrogate range, <code>(index - 2)</code> is not * negative, and the <code>char</code> value at <code>(index - * 2)</code> in the <code>char</code> array is in the * high-surrogate range, then the supplementary code point * corresponding to this surrogate pair is returned. Otherwise, * the <code>char</code> value at <code>(index - 1)</code> is * returned. * * @param a the <code>char</code> array * @param index the index following the code point that should be returned * @return the Unicode code point value before the given index. * @exception NullPointerException if <code>a</code> is null. * @exception IndexOutOfBoundsException if the <code>index</code> * argument is less than 1 or greater than the length of the * <code>char</code> array * @since 1.5 */ public static int codePointBefore(char[] a, int index) { return codePointBeforeImpl(a, index, 0); } /** * Returns the code point preceding the given index of the * <code>char</code> array, where only array elements with * <code>index</code> greater than or equal to <code>start</code> * can be used. If the <code>char</code> value at <code>(index - * 1)</code> in the <code>char</code> array is in the * low-surrogate range, <code>(index - 2)</code> is not less than * <code>start</code>, and the <code>char</code> value at * <code>(index - 2)</code> in the <code>char</code> array is in * the high-surrogate range, then the supplementary code point * corresponding to this surrogate pair is returned. Otherwise, * the <code>char</code> value at <code>(index - 1)</code> is * returned. * * @param a the <code>char</code> array * @param index the index following the code point that should be returned * @param start the index of the first array element in the * <code>char</code> array * @return the Unicode code point value before the given index. * @exception NullPointerException if <code>a</code> is null. * @exception IndexOutOfBoundsException if the <code>index</code> * argument is not greater than the <code>start</code> argument or * is greater than the length of the <code>char</code> array, or * if the <code>start</code> argument is negative or not less than * the length of the <code>char</code> array. * @since 1.5 */ public static int codePointBefore(char[] a, int index, int start) { if (index <= start || start < 0 || start >= a.length) { throw new IndexOutOfBoundsException(); } return codePointBeforeImpl(a, index, start); } static int codePointBeforeImpl(char[] a, int index, int start) { char c2 = a[--index]; if (isLowSurrogate(c2)) { if (index > start) { char c1 = a[--index]; if (isHighSurrogate(c1)) { return toCodePoint(c1, c2); } } } return c2; } /** * Converts the specified character (Unicode code point) to its * UTF-16 representation. If the specified code point is a BMP * (Basic Multilingual Plane or Plane 0) value, the same value is * stored in <code>dst[dstIndex]</code>, and 1 is returned. If the * specified code point is a supplementary character, its * surrogate values are stored in <code>dst[dstIndex]</code> * (high-surrogate) and <code>dst[dstIndex+1]</code> * (low-surrogate), and 2 is returned. * * @param codePoint the character (Unicode code point) to be converted. * @param dst an array of <code>char</code> in which the * <code>codePoint</code>'s UTF-16 value is stored. * @param dstIndex the start index into the <code>dst</code> * array where the converted value is stored. * @return 1 if the code point is a BMP code point, 2 if the * code point is a supplementary code point. * @exception IllegalArgumentException if the specified * <code>codePoint</code> is not a valid Unicode code point. * @exception NullPointerException if the specified <code>dst</code> is null. * @exception IndexOutOfBoundsException if <code>dstIndex</code> * is negative or not less than <code>dst.length</code>, or if * <code>dst</code> at <code>dstIndex</code> doesn't have enough * array element(s) to store the resulting <code>char</code> * value(s). (If <code>dstIndex</code> is equal to * <code>dst.length-1</code> and the specified * <code>codePoint</code> is a supplementary character, the * high-surrogate value is not stored in * <code>dst[dstIndex]</code>.) * @since 1.5 */ public static int toChars(int codePoint, char[] dst, int dstIndex) { if (codePoint < 0 || codePoint > MAX_CODE_POINT) { throw new IllegalArgumentException(); } if (codePoint < MIN_SUPPLEMENTARY_CODE_POINT) { dst[dstIndex] = (char) codePoint; return 1; } toSurrogates(codePoint, dst, dstIndex); return 2; } /** * Converts the specified character (Unicode code point) to its * UTF-16 representation stored in a <code>char</code> array. If * the specified code point is a BMP (Basic Multilingual Plane or * Plane 0) value, the resulting <code>char</code> array has * the same value as <code>codePoint</code>. If the specified code * point is a supplementary code point, the resulting * <code>char</code> array has the corresponding surrogate pair. * * @param codePoint a Unicode code point * @return a <code>char</code> array having * <code>codePoint</code>'s UTF-16 representation. * @exception IllegalArgumentException if the specified * <code>codePoint</code> is not a valid Unicode code point. * @since 1.5 */ public static char[] toChars(int codePoint) { if (codePoint < 0 || codePoint > MAX_CODE_POINT) { throw new IllegalArgumentException(); } if (codePoint < MIN_SUPPLEMENTARY_CODE_POINT) { return new char[] { (char) codePoint }; } char[] result = new char[2]; toSurrogates(codePoint, result, 0); return result; } static void toSurrogates(int codePoint, char[] dst, int index) { int offset = codePoint - MIN_SUPPLEMENTARY_CODE_POINT; dst[index+1] = (char)((offset & 0x3ff) + MIN_LOW_SURROGATE); dst[index] = (char)((offset >>> 10) + MIN_HIGH_SURROGATE); } /** * Returns the number of Unicode code points in the text range of * the specified char sequence. The text range begins at the * specified <code>beginIndex</code> and extends to the * <code>char</code> at index <code>endIndex - 1</code>. Thus the * length (in <code>char</code>s) of the text range is * <code>endIndex-beginIndex</code>. Unpaired surrogates within * the text range count as one code point each. * * @param seq the char sequence * @param beginIndex the index to the first <code>char</code> of * the text range. * @param endIndex the index after the last <code>char</code> of * the text range. * @return the number of Unicode code points in the specified text * range * @exception NullPointerException if <code>seq</code> is null. * @exception IndexOutOfBoundsException if the * <code>beginIndex</code> is negative, or <code>endIndex</code> * is larger than the length of the given sequence, or * <code>beginIndex</code> is larger than <code>endIndex</code>. * @since 1.5 */ public static int codePointCount(CharSequence seq, int beginIndex, int endIndex) { int length = seq.length(); if (beginIndex < 0 || endIndex > length || beginIndex > endIndex) { throw new IndexOutOfBoundsException(); } int n = 0; for (int i = beginIndex; i < endIndex; ) { n++; if (isHighSurrogate(seq.charAt(i++))) { if (i < endIndex && isLowSurrogate(seq.charAt(i))) { i++; } } } return n; } /** * Returns the number of Unicode code points in a subarray of the * <code>char</code> array argument. The <code>offset</code> * argument is the index of the first <code>char</code> of the * subarray and the <code>count</code> argument specifies the * length of the subarray in <code>char</code>s. Unpaired * surrogates within the subarray count as one code point each. * * @param a the <code>char</code> array * @param offset the index of the first <code>char</code> in the * given <code>char</code> array * @param count the length of the subarray in <code>char</code>s * @return the number of Unicode code points in the specified subarray * @exception NullPointerException if <code>a</code> is null. * @exception IndexOutOfBoundsException if <code>offset</code> or * <code>count</code> is negative, or if <code>offset + * count</code> is larger than the length of the given array. * @since 1.5 */ public static int codePointCount(char[] a, int offset, int count) { if (count > a.length - offset || offset < 0 || count < 0) { throw new IndexOutOfBoundsException(); } return codePointCountImpl(a, offset, count); } static int codePointCountImpl(char[] a, int offset, int count) { int endIndex = offset + count; int n = 0; for (int i = offset; i < endIndex; ) { n++; if (isHighSurrogate(a[i++])) { if (i < endIndex && isLowSurrogate(a[i])) { i++; } } } return n; } /** * Returns the index within the given char sequence that is offset * from the given <code>index</code> by <code>codePointOffset</code> * code points. Unpaired surrogates within the text range given by * <code>index</code> and <code>codePointOffset</code> count as * one code point each. * * @param seq the char sequence * @param index the index to be offset * @param codePointOffset the offset in code points * @return the index within the char sequence * @exception NullPointerException if <code>seq</code> is null. * @exception IndexOutOfBoundsException if <code>index</code> * is negative or larger then the length of the char sequence, * or if <code>codePointOffset</code> is positive and the * subsequence starting with <code>index</code> has fewer than * <code>codePointOffset</code> code points, or if * <code>codePointOffset</code> is negative and the subsequence * before <code>index</code> has fewer than the absolute value * of <code>codePointOffset</code> code points. * @since 1.5 */ public static int offsetByCodePoints(CharSequence seq, int index, int codePointOffset) { int length = seq.length(); if (index < 0 || index > length) { throw new IndexOutOfBoundsException(); } int x = index; if (codePointOffset >= 0) { int i; for (i = 0; x < length && i < codePointOffset; i++) { if (isHighSurrogate(seq.charAt(x++))) { if (x < length && isLowSurrogate(seq.charAt(x))) { x++; } } } if (i < codePointOffset) { throw new IndexOutOfBoundsException(); } } else { int i; for (i = codePointOffset; x > 0 && i < 0; i++) { if (isLowSurrogate(seq.charAt(--x))) { if (x > 0 && isHighSurrogate(seq.charAt(x-1))) { x--; } } } if (i < 0) { throw new IndexOutOfBoundsException(); } } return x; } /** * Returns the index within the given <code>char</code> subarray * that is offset from the given <code>index</code> by * <code>codePointOffset</code> code points. The * <code>start</code> and <code>count</code> arguments specify a * subarray of the <code>char</code> array. Unpaired surrogates * within the text range given by <code>index</code> and * <code>codePointOffset</code> count as one code point each. * * @param a the <code>char</code> array * @param start the index of the first <code>char</code> of the * subarray * @param count the length of the subarray in <code>char</code>s * @param index the index to be offset * @param codePointOffset the offset in code points * @return the index within the subarray * @exception NullPointerException if <code>a</code> is null. * @exception IndexOutOfBoundsException * if <code>start</code> or <code>count</code> is negative, * or if <code>start + count</code> is larger than the length of * the given array, * or if <code>index</code> is less than <code>start</code> or * larger then <code>start + count</code>, * or if <code>codePointOffset</code> is positive and the text range * starting with <code>index</code> and ending with <code>start * + count - 1</code> has fewer than <code>codePointOffset</code> code * points, * or if <code>codePointOffset</code> is negative and the text range * starting with <code>start</code> and ending with <code>index * - 1</code> has fewer than the absolute value of * <code>codePointOffset</code> code points. * @since 1.5 */ public static int offsetByCodePoints(char[] a, int start, int count, int index, int codePointOffset) { if (count > a.length-start || start < 0 || count < 0 || index < start || index > start+count) { throw new IndexOutOfBoundsException(); } return offsetByCodePointsImpl(a, start, count, index, codePointOffset); } static int offsetByCodePointsImpl(char[]a, int start, int count, int index, int codePointOffset) { int x = index; if (codePointOffset >= 0) { int limit = start + count; int i; for (i = 0; x < limit && i < codePointOffset; i++) { if (isHighSurrogate(a[x++])) { if (x < limit && isLowSurrogate(a[x])) { x++; } } } if (i < codePointOffset) { throw new IndexOutOfBoundsException(); } } else { int i; for (i = codePointOffset; x > start && i < 0; i++) { if (isLowSurrogate(a[--x])) { if (x > start && isHighSurrogate(a[x-1])) { x--; } } } if (i < 0) { throw new IndexOutOfBoundsException(); } } return x; } /** * Determines if the specified character is a lowercase character. * <p> * A character is lowercase if its general category type, provided * by <code>Character.getType(ch)</code>, is * <code>LOWERCASE_LETTER</code>. * <p> * The following are examples of lowercase characters: * <p><blockquote><pre> * a b c d e f g h i j k l m n o p q r s t u v w x y z * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6' * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE' * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6' * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF' * </pre></blockquote> * <p> Many other Unicode characters are lowercase too. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isLowerCase(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is lowercase; * <code>false</code> otherwise. * @see java.lang.Character#isLowerCase(char) * @see java.lang.Character#isTitleCase(char) * @see java.lang.Character#toLowerCase(char) * @see java.lang.Character#getType(char) */ public static boolean isLowerCase(char ch) { return isLowerCase((int)ch); } /** * Determines if the specified character (Unicode code point) is a * lowercase character. * <p> * A character is lowercase if its general category type, provided * by {@link Character#getType getType(codePoint)}, is * <code>LOWERCASE_LETTER</code>. * <p> * The following are examples of lowercase characters: * <p><blockquote><pre> * a b c d e f g h i j k l m n o p q r s t u v w x y z * '\u00DF' '\u00E0' '\u00E1' '\u00E2' '\u00E3' '\u00E4' '\u00E5' '\u00E6' * '\u00E7' '\u00E8' '\u00E9' '\u00EA' '\u00EB' '\u00EC' '\u00ED' '\u00EE' * '\u00EF' '\u00F0' '\u00F1' '\u00F2' '\u00F3' '\u00F4' '\u00F5' '\u00F6' * '\u00F8' '\u00F9' '\u00FA' '\u00FB' '\u00FC' '\u00FD' '\u00FE' '\u00FF' * </pre></blockquote> * <p> Many other Unicode characters are lowercase too. * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is lowercase; * <code>false</code> otherwise. * @see java.lang.Character#isLowerCase(int) * @see java.lang.Character#isTitleCase(int) * @see java.lang.Character#toLowerCase(int) * @see java.lang.Character#getType(int) * @since 1.5 */ public static boolean isLowerCase(int codePoint) { boolean bLowerCase = false; // codePoint must be in the valid range of codepoints if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bLowerCase = CharacterDataLatin1.isLowerCase(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bLowerCase = CharacterData00.isLowerCase(codePoint); break; case(1): bLowerCase = CharacterData01.isLowerCase(codePoint); break; case(2): bLowerCase = CharacterData02.isLowerCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bLowerCase = CharacterDataUndefined.isLowerCase(codePoint); break; case(14): bLowerCase = CharacterData0E.isLowerCase(codePoint); break; case(15): // Private Use case(16): // Private Use bLowerCase = CharacterDataPrivateUse.isLowerCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bLowerCase remains false break; } } return bLowerCase; } /** * Determines if the specified character is an uppercase character. * <p> * A character is uppercase if its general category type, provided by * <code>Character.getType(ch)</code>, is <code>UPPERCASE_LETTER</code>. * <p> * The following are examples of uppercase characters: * <p><blockquote><pre> * A B C D E F G H I J K L M N O P Q R S T U V W X Y Z * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7' * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF' * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8' * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE' * </pre></blockquote> * <p> Many other Unicode characters are uppercase too.<p> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isUpperCase(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is uppercase; * <code>false</code> otherwise. * @see java.lang.Character#isLowerCase(char) * @see java.lang.Character#isTitleCase(char) * @see java.lang.Character#toUpperCase(char) * @see java.lang.Character#getType(char) * @since 1.0 */ public static boolean isUpperCase(char ch) { return isUpperCase((int)ch); } /** * Determines if the specified character (Unicode code point) is an uppercase character. * <p> * A character is uppercase if its general category type, provided by * {@link Character#getType(int) getType(codePoint)}, is <code>UPPERCASE_LETTER</code>. * <p> * The following are examples of uppercase characters: * <p><blockquote><pre> * A B C D E F G H I J K L M N O P Q R S T U V W X Y Z * '\u00C0' '\u00C1' '\u00C2' '\u00C3' '\u00C4' '\u00C5' '\u00C6' '\u00C7' * '\u00C8' '\u00C9' '\u00CA' '\u00CB' '\u00CC' '\u00CD' '\u00CE' '\u00CF' * '\u00D0' '\u00D1' '\u00D2' '\u00D3' '\u00D4' '\u00D5' '\u00D6' '\u00D8' * '\u00D9' '\u00DA' '\u00DB' '\u00DC' '\u00DD' '\u00DE' * </pre></blockquote> * <p> Many other Unicode characters are uppercase too.<p> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is uppercase; * <code>false</code> otherwise. * @see java.lang.Character#isLowerCase(int) * @see java.lang.Character#isTitleCase(int) * @see java.lang.Character#toUpperCase(int) * @see java.lang.Character#getType(int) * @since 1.5 */ public static boolean isUpperCase(int codePoint) { boolean bUpperCase = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bUpperCase = CharacterDataLatin1.isUpperCase(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bUpperCase = CharacterData00.isUpperCase(codePoint); break; case(1): bUpperCase = CharacterData01.isUpperCase(codePoint); break; case(2): bUpperCase = CharacterData02.isUpperCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bUpperCase = CharacterDataUndefined.isUpperCase(codePoint); break; case(14): bUpperCase = CharacterData0E.isUpperCase(codePoint); break; case(15): // Private Use case(16): // Private Use bUpperCase = CharacterDataPrivateUse.isUpperCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bUpperCase remains false; break; } } return bUpperCase; } /** * Determines if the specified character is a titlecase character. * <p> * A character is a titlecase character if its general * category type, provided by <code>Character.getType(ch)</code>, * is <code>TITLECASE_LETTER</code>. * <p> * Some characters look like pairs of Latin letters. For example, there * is an uppercase letter that looks like "LJ" and has a corresponding * lowercase letter that looks like "lj". A third form, which looks like "Lj", * is the appropriate form to use when rendering a word in lowercase * with initial capitals, as for a book title. * <p> * These are some of the Unicode characters for which this method returns * <code>true</code>: * <ul> * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON</code> * <li><code>LATIN CAPITAL LETTER L WITH SMALL LETTER J</code> * <li><code>LATIN CAPITAL LETTER N WITH SMALL LETTER J</code> * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z</code> * </ul> * <p> Many other Unicode characters are titlecase too.<p> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isTitleCase(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is titlecase; * <code>false</code> otherwise. * @see java.lang.Character#isLowerCase(char) * @see java.lang.Character#isUpperCase(char) * @see java.lang.Character#toTitleCase(char) * @see java.lang.Character#getType(char) * @since 1.0.2 */ public static boolean isTitleCase(char ch) { return isTitleCase((int)ch); } /** * Determines if the specified character (Unicode code point) is a titlecase character. * <p> * A character is a titlecase character if its general * category type, provided by {@link Character#getType(int) getType(codePoint)}, * is <code>TITLECASE_LETTER</code>. * <p> * Some characters look like pairs of Latin letters. For example, there * is an uppercase letter that looks like "LJ" and has a corresponding * lowercase letter that looks like "lj". A third form, which looks like "Lj", * is the appropriate form to use when rendering a word in lowercase * with initial capitals, as for a book title. * <p> * These are some of the Unicode characters for which this method returns * <code>true</code>: * <ul> * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON</code> * <li><code>LATIN CAPITAL LETTER L WITH SMALL LETTER J</code> * <li><code>LATIN CAPITAL LETTER N WITH SMALL LETTER J</code> * <li><code>LATIN CAPITAL LETTER D WITH SMALL LETTER Z</code> * </ul> * <p> Many other Unicode characters are titlecase too.<p> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is titlecase; * <code>false</code> otherwise. * @see java.lang.Character#isLowerCase(int) * @see java.lang.Character#isUpperCase(int) * @see java.lang.Character#toTitleCase(int) * @see java.lang.Character#getType(int) * @since 1.5 */ public static boolean isTitleCase(int codePoint) { boolean bTitleCase = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bTitleCase = CharacterDataLatin1.isTitleCase(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bTitleCase = CharacterData00.isTitleCase(codePoint); break; case(1): bTitleCase = CharacterData01.isTitleCase(codePoint); break; case(2): bTitleCase = CharacterData02.isTitleCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bTitleCase = CharacterDataUndefined.isTitleCase(codePoint); break; case(14): bTitleCase = CharacterData0E.isTitleCase(codePoint); break; case(15): // Private Use case(16): // Private Use bTitleCase = CharacterDataPrivateUse.isTitleCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bTitleCase remains false; break; } } return bTitleCase; } /** * Determines if the specified character is a digit. * <p> * A character is a digit if its general category type, provided * by <code>Character.getType(ch)</code>, is * <code>DECIMAL_DIGIT_NUMBER</code>. * <p> * Some Unicode character ranges that contain digits: * <ul> * <li><code>'\u0030'</code> through <code>'\u0039'</code>, * ISO-LATIN-1 digits (<code>'0'</code> through <code>'9'</code>) * <li><code>'\u0660'</code> through <code>'\u0669'</code>, * Arabic-Indic digits * <li><code>'\u06F0'</code> through <code>'\u06F9'</code>, * Extended Arabic-Indic digits * <li><code>'\u0966'</code> through <code>'\u096F'</code>, * Devanagari digits * <li><code>'\uFF10'</code> through <code>'\uFF19'</code>, * Fullwidth digits * </ul> * * Many other character ranges contain digits as well. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isDigit(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is a digit; * <code>false</code> otherwise. * @see java.lang.Character#digit(char, int) * @see java.lang.Character#forDigit(int, int) * @see java.lang.Character#getType(char) */ public static boolean isDigit(char ch) { return isDigit((int)ch); } /** * Determines if the specified character (Unicode code point) is a digit. * <p> * A character is a digit if its general category type, provided * by {@link Character#getType(int) getType(codePoint)}, is * <code>DECIMAL_DIGIT_NUMBER</code>. * <p> * Some Unicode character ranges that contain digits: * <ul> * <li><code>'\u0030'</code> through <code>'\u0039'</code>, * ISO-LATIN-1 digits (<code>'0'</code> through <code>'9'</code>) * <li><code>'\u0660'</code> through <code>'\u0669'</code>, * Arabic-Indic digits * <li><code>'\u06F0'</code> through <code>'\u06F9'</code>, * Extended Arabic-Indic digits * <li><code>'\u0966'</code> through <code>'\u096F'</code>, * Devanagari digits * <li><code>'\uFF10'</code> through <code>'\uFF19'</code>, * Fullwidth digits * </ul> * * Many other character ranges contain digits as well. * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is a digit; * <code>false</code> otherwise. * @see java.lang.Character#forDigit(int, int) * @see java.lang.Character#getType(int) * @since 1.5 */ public static boolean isDigit(int codePoint) { boolean bDigit = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bDigit = CharacterDataLatin1.isDigit(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bDigit = CharacterData00.isDigit(codePoint); break; case(1): bDigit = CharacterData01.isDigit(codePoint); break; case(2): bDigit = CharacterData02.isDigit(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bDigit = CharacterDataUndefined.isDigit(codePoint); break; case(14): bDigit = CharacterData0E.isDigit(codePoint); break; case(15): // Private Use case(16): // Private Use bDigit = CharacterDataPrivateUse.isDigit(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bDigit remains false; break; } } return bDigit; } /** * Determines if a character is defined in Unicode. * <p> * A character is defined if at least one of the following is true: * <ul> * <li>It has an entry in the UnicodeData file. * <li>It has a value in a range defined by the UnicodeData file. * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isDefined(int)} method. * * @param ch the character to be tested * @return <code>true</code> if the character has a defined meaning * in Unicode; <code>false</code> otherwise. * @see java.lang.Character#isDigit(char) * @see java.lang.Character#isLetter(char) * @see java.lang.Character#isLetterOrDigit(char) * @see java.lang.Character#isLowerCase(char) * @see java.lang.Character#isTitleCase(char) * @see java.lang.Character#isUpperCase(char) * @since 1.0.2 */ public static boolean isDefined(char ch) { return isDefined((int)ch); } /** * Determines if a character (Unicode code point) is defined in Unicode. * <p> * A character is defined if at least one of the following is true: * <ul> * <li>It has an entry in the UnicodeData file. * <li>It has a value in a range defined by the UnicodeData file. * </ul> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character has a defined meaning * in Unicode; <code>false</code> otherwise. * @see java.lang.Character#isDigit(int) * @see java.lang.Character#isLetter(int) * @see java.lang.Character#isLetterOrDigit(int) * @see java.lang.Character#isLowerCase(int) * @see java.lang.Character#isTitleCase(int) * @see java.lang.Character#isUpperCase(int) * @since 1.5 */ public static boolean isDefined(int codePoint) { boolean bDefined = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bDefined = CharacterDataLatin1.isDefined(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bDefined = CharacterData00.isDefined(codePoint); break; case(1): bDefined = CharacterData01.isDefined(codePoint); break; case(2): bDefined = CharacterData02.isDefined(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bDefined = CharacterDataUndefined.isDefined(codePoint); break; case(14): bDefined = CharacterData0E.isDefined(codePoint); break; case(15): // Private Use case(16): // Private Use bDefined = CharacterDataPrivateUse.isDefined(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bDefined remains false; break; } } return bDefined; } /** * Determines if the specified character is a letter. * <p> * A character is considered to be a letter if its general * category type, provided by <code>Character.getType(ch)</code>, * is any of the following: * <ul> * <li> <code>UPPERCASE_LETTER</code> * <li> <code>LOWERCASE_LETTER</code> * <li> <code>TITLECASE_LETTER</code> * <li> <code>MODIFIER_LETTER</code> * <li> <code>OTHER_LETTER</code> * </ul> * * Not all letters have case. Many characters are * letters but are neither uppercase nor lowercase nor titlecase. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isLetter(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is a letter; * <code>false</code> otherwise. * @see java.lang.Character#isDigit(char) * @see java.lang.Character#isJavaIdentifierStart(char) * @see java.lang.Character#isJavaLetter(char) * @see java.lang.Character#isJavaLetterOrDigit(char) * @see java.lang.Character#isLetterOrDigit(char) * @see java.lang.Character#isLowerCase(char) * @see java.lang.Character#isTitleCase(char) * @see java.lang.Character#isUnicodeIdentifierStart(char) * @see java.lang.Character#isUpperCase(char) */ public static boolean isLetter(char ch) { return isLetter((int)ch); } /** * Determines if the specified character (Unicode code point) is a letter. * <p> * A character is considered to be a letter if its general * category type, provided by {@link Character#getType(int) getType(codePoint)}, * is any of the following: * <ul> * <li> <code>UPPERCASE_LETTER</code> * <li> <code>LOWERCASE_LETTER</code> * <li> <code>TITLECASE_LETTER</code> * <li> <code>MODIFIER_LETTER</code> * <li> <code>OTHER_LETTER</code> * </ul> * * Not all letters have case. Many characters are * letters but are neither uppercase nor lowercase nor titlecase. * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is a letter; * <code>false</code> otherwise. * @see java.lang.Character#isDigit(int) * @see java.lang.Character#isJavaIdentifierStart(int) * @see java.lang.Character#isLetterOrDigit(int) * @see java.lang.Character#isLowerCase(int) * @see java.lang.Character#isTitleCase(int) * @see java.lang.Character#isUnicodeIdentifierStart(int) * @see java.lang.Character#isUpperCase(int) * @since 1.5 */ public static boolean isLetter(int codePoint) { boolean bLetter = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bLetter = CharacterDataLatin1.isLetter(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bLetter = CharacterData00.isLetter(codePoint); break; case(1): bLetter = CharacterData01.isLetter(codePoint); break; case(2): bLetter = CharacterData02.isLetter(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bLetter = CharacterDataUndefined.isLetter(codePoint); break; case(14): bLetter = CharacterData0E.isLetter(codePoint); break; case(15): // Private Use case(16): // Private Use bLetter = CharacterDataPrivateUse.isLetter(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bLetter remains false; break; } } return bLetter; } /** * Determines if the specified character is a letter or digit. * <p> * A character is considered to be a letter or digit if either * <code>Character.isLetter(char ch)</code> or * <code>Character.isDigit(char ch)</code> returns * <code>true</code> for the character. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isLetterOrDigit(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is a letter or digit; * <code>false</code> otherwise. * @see java.lang.Character#isDigit(char) * @see java.lang.Character#isJavaIdentifierPart(char) * @see java.lang.Character#isJavaLetter(char) * @see java.lang.Character#isJavaLetterOrDigit(char) * @see java.lang.Character#isLetter(char) * @see java.lang.Character#isUnicodeIdentifierPart(char) * @since 1.0.2 */ public static boolean isLetterOrDigit(char ch) { return isLetterOrDigit((int)ch); } /** * Determines if the specified character (Unicode code point) is a letter or digit. * <p> * A character is considered to be a letter or digit if either * {@link #isLetter(int) isLetter(codePoint)} or * {@link #isDigit(int) isDigit(codePoint)} returns * <code>true</code> for the character. * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is a letter or digit; * <code>false</code> otherwise. * @see java.lang.Character#isDigit(int) * @see java.lang.Character#isJavaIdentifierPart(int) * @see java.lang.Character#isLetter(int) * @see java.lang.Character#isUnicodeIdentifierPart(int) * @since 1.5 */ public static boolean isLetterOrDigit(int codePoint) { boolean bLetterOrDigit = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bLetterOrDigit = CharacterDataLatin1.isLetterOrDigit(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bLetterOrDigit = CharacterData00.isLetterOrDigit(codePoint); break; case(1): bLetterOrDigit = CharacterData01.isLetterOrDigit(codePoint); break; case(2): bLetterOrDigit = CharacterData02.isLetterOrDigit(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bLetterOrDigit = CharacterDataUndefined.isLetterOrDigit(codePoint); break; case(14): // Undefined bLetterOrDigit = CharacterData0E.isLetterOrDigit(codePoint); break; case(15): // Private Use case(16): // Private Use bLetterOrDigit = CharacterDataPrivateUse.isLetterOrDigit(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bLetterOrDigit remains false; break; } } return bLetterOrDigit; } /** * Determines if the specified character is permissible as the first * character in a Java identifier. * <p> * A character may start a Java identifier if and only if * one of the following is true: * <ul> * <li> {@link #isLetter(char) isLetter(ch)} returns <code>true</code> * <li> {@link #getType(char) getType(ch)} returns <code>LETTER_NUMBER</code> * <li> ch is a currency symbol (such as "$") * <li> ch is a connecting punctuation character (such as "_"). * </ul> * * @param ch the character to be tested. * @return <code>true</code> if the character may start a Java * identifier; <code>false</code> otherwise. * @see java.lang.Character#isJavaLetterOrDigit(char) * @see java.lang.Character#isJavaIdentifierStart(char) * @see java.lang.Character#isJavaIdentifierPart(char) * @see java.lang.Character#isLetter(char) * @see java.lang.Character#isLetterOrDigit(char) * @see java.lang.Character#isUnicodeIdentifierStart(char) * @since 1.02 * @deprecated Replaced by isJavaIdentifierStart(char). */ @Deprecated public static boolean isJavaLetter(char ch) { return isJavaIdentifierStart(ch); } /** * Determines if the specified character may be part of a Java * identifier as other than the first character. * <p> * A character may be part of a Java identifier if and only if any * of the following are true: * <ul> * <li> it is a letter * <li> it is a currency symbol (such as <code>'$'</code>) * <li> it is a connecting punctuation character (such as <code>'_'</code>) * <li> it is a digit * <li> it is a numeric letter (such as a Roman numeral character) * <li> it is a combining mark * <li> it is a non-spacing mark * <li> <code>isIdentifierIgnorable</code> returns * <code>true</code> for the character. * </ul> * * @param ch the character to be tested. * @return <code>true</code> if the character may be part of a * Java identifier; <code>false</code> otherwise. * @see java.lang.Character#isJavaLetter(char) * @see java.lang.Character#isJavaIdentifierStart(char) * @see java.lang.Character#isJavaIdentifierPart(char) * @see java.lang.Character#isLetter(char) * @see java.lang.Character#isLetterOrDigit(char) * @see java.lang.Character#isUnicodeIdentifierPart(char) * @see java.lang.Character#isIdentifierIgnorable(char) * @since 1.02 * @deprecated Replaced by isJavaIdentifierPart(char). */ @Deprecated public static boolean isJavaLetterOrDigit(char ch) { return isJavaIdentifierPart(ch); } /** * Determines if the specified character is * permissible as the first character in a Java identifier. * <p> * A character may start a Java identifier if and only if * one of the following conditions is true: * <ul> * <li> {@link #isLetter(char) isLetter(ch)} returns <code>true</code> * <li> {@link #getType(char) getType(ch)} returns <code>LETTER_NUMBER</code> * <li> ch is a currency symbol (such as "$") * <li> ch is a connecting punctuation character (such as "_"). * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isJavaIdentifierStart(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character may start a Java identifier; * <code>false</code> otherwise. * @see java.lang.Character#isJavaIdentifierPart(char) * @see java.lang.Character#isLetter(char) * @see java.lang.Character#isUnicodeIdentifierStart(char) * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) * @since 1.1 */ public static boolean isJavaIdentifierStart(char ch) { return isJavaIdentifierStart((int)ch); } /** * Determines if the character (Unicode code point) is * permissible as the first character in a Java identifier. * <p> * A character may start a Java identifier if and only if * one of the following conditions is true: * <ul> * <li> {@link #isLetter(int) isLetter(codePoint)} * returns <code>true</code> * <li> {@link #getType(int) getType(codePoint)} * returns <code>LETTER_NUMBER</code> * <li> the referenced character is a currency symbol (such as "$") * <li> the referenced character is a connecting punctuation character * (such as "_"). * </ul> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character may start a Java identifier; * <code>false</code> otherwise. * @see java.lang.Character#isJavaIdentifierPart(int) * @see java.lang.Character#isLetter(int) * @see java.lang.Character#isUnicodeIdentifierStart(int) * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) * @since 1.5 */ public static boolean isJavaIdentifierStart(int codePoint) { boolean bJavaStart = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bJavaStart = CharacterDataLatin1.isJavaIdentifierStart(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bJavaStart = CharacterData00.isJavaIdentifierStart(codePoint); break; case(1): bJavaStart = CharacterData01.isJavaIdentifierStart(codePoint); break; case(2): bJavaStart = CharacterData02.isJavaIdentifierStart(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bJavaStart = CharacterDataUndefined.isJavaIdentifierStart(codePoint); break; case(14): bJavaStart = CharacterData0E.isJavaIdentifierStart(codePoint); break; case(15): // Private Use case(16): // Private Use bJavaStart = CharacterDataPrivateUse.isJavaIdentifierStart(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bJavaStart remains false; break; } } return bJavaStart; } /** * Determines if the specified character may be part of a Java * identifier as other than the first character. * <p> * A character may be part of a Java identifier if any of the following * are true: * <ul> * <li> it is a letter * <li> it is a currency symbol (such as <code>'$'</code>) * <li> it is a connecting punctuation character (such as <code>'_'</code>) * <li> it is a digit * <li> it is a numeric letter (such as a Roman numeral character) * <li> it is a combining mark * <li> it is a non-spacing mark * <li> <code>isIdentifierIgnorable</code> returns * <code>true</code> for the character * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isJavaIdentifierPart(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character may be part of a * Java identifier; <code>false</code> otherwise. * @see java.lang.Character#isIdentifierIgnorable(char) * @see java.lang.Character#isJavaIdentifierStart(char) * @see java.lang.Character#isLetterOrDigit(char) * @see java.lang.Character#isUnicodeIdentifierPart(char) * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) * @since 1.1 */ public static boolean isJavaIdentifierPart(char ch) { return isJavaIdentifierPart((int)ch); } /** * Determines if the character (Unicode code point) may be part of a Java * identifier as other than the first character. * <p> * A character may be part of a Java identifier if any of the following * are true: * <ul> * <li> it is a letter * <li> it is a currency symbol (such as <code>'$'</code>) * <li> it is a connecting punctuation character (such as <code>'_'</code>) * <li> it is a digit * <li> it is a numeric letter (such as a Roman numeral character) * <li> it is a combining mark * <li> it is a non-spacing mark * <li> {@link #isIdentifierIgnorable(int) * isIdentifierIgnorable(codePoint)} returns <code>true</code> for * the character * </ul> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character may be part of a * Java identifier; <code>false</code> otherwise. * @see java.lang.Character#isIdentifierIgnorable(int) * @see java.lang.Character#isJavaIdentifierStart(int) * @see java.lang.Character#isLetterOrDigit(int) * @see java.lang.Character#isUnicodeIdentifierPart(int) * @see javax.lang.model.SourceVersion#isIdentifier(CharSequence) * @since 1.5 */ public static boolean isJavaIdentifierPart(int codePoint) { boolean bJavaPart = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bJavaPart = CharacterDataLatin1.isJavaIdentifierPart(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bJavaPart = CharacterData00.isJavaIdentifierPart(codePoint); break; case(1): bJavaPart = CharacterData01.isJavaIdentifierPart(codePoint); break; case(2): bJavaPart = CharacterData02.isJavaIdentifierPart(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bJavaPart = CharacterDataUndefined.isJavaIdentifierPart(codePoint); break; case(14): bJavaPart = CharacterData0E.isJavaIdentifierPart(codePoint); break; case(15): // Private Use case(16): // Private Use bJavaPart = CharacterDataPrivateUse.isJavaIdentifierPart(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bJavaPart remains false; break; } } return bJavaPart; } /** * Determines if the specified character is permissible as the * first character in a Unicode identifier. * <p> * A character may start a Unicode identifier if and only if * one of the following conditions is true: * <ul> * <li> {@link #isLetter(char) isLetter(ch)} returns <code>true</code> * <li> {@link #getType(char) getType(ch)} returns * <code>LETTER_NUMBER</code>. * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isUnicodeIdentifierStart(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character may start a Unicode * identifier; <code>false</code> otherwise. * @see java.lang.Character#isJavaIdentifierStart(char) * @see java.lang.Character#isLetter(char) * @see java.lang.Character#isUnicodeIdentifierPart(char) * @since 1.1 */ public static boolean isUnicodeIdentifierStart(char ch) { return isUnicodeIdentifierStart((int)ch); } /** * Determines if the specified character (Unicode code point) is permissible as the * first character in a Unicode identifier. * <p> * A character may start a Unicode identifier if and only if * one of the following conditions is true: * <ul> * <li> {@link #isLetter(int) isLetter(codePoint)} * returns <code>true</code> * <li> {@link #getType(int) getType(codePoint)} * returns <code>LETTER_NUMBER</code>. * </ul> * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character may start a Unicode * identifier; <code>false</code> otherwise. * @see java.lang.Character#isJavaIdentifierStart(int) * @see java.lang.Character#isLetter(int) * @see java.lang.Character#isUnicodeIdentifierPart(int) * @since 1.5 */ public static boolean isUnicodeIdentifierStart(int codePoint) { boolean bUnicodeStart = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bUnicodeStart = CharacterDataLatin1.isUnicodeIdentifierStart(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bUnicodeStart = CharacterData00.isUnicodeIdentifierStart(codePoint); break; case(1): bUnicodeStart = CharacterData01.isUnicodeIdentifierStart(codePoint); break; case(2): bUnicodeStart = CharacterData02.isUnicodeIdentifierStart(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bUnicodeStart = CharacterDataUndefined.isUnicodeIdentifierStart(codePoint); break; case(14): bUnicodeStart = CharacterData0E.isUnicodeIdentifierStart(codePoint); break; case(15): // Private Use case(16): // Private Use bUnicodeStart = CharacterDataPrivateUse.isUnicodeIdentifierStart(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bUnicodeStart remains false; break; } } return bUnicodeStart; } /** * Determines if the specified character may be part of a Unicode * identifier as other than the first character. * <p> * A character may be part of a Unicode identifier if and only if * one of the following statements is true: * <ul> * <li> it is a letter * <li> it is a connecting punctuation character (such as <code>'_'</code>) * <li> it is a digit * <li> it is a numeric letter (such as a Roman numeral character) * <li> it is a combining mark * <li> it is a non-spacing mark * <li> <code>isIdentifierIgnorable</code> returns * <code>true</code> for this character. * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isUnicodeIdentifierPart(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character may be part of a * Unicode identifier; <code>false</code> otherwise. * @see java.lang.Character#isIdentifierIgnorable(char) * @see java.lang.Character#isJavaIdentifierPart(char) * @see java.lang.Character#isLetterOrDigit(char) * @see java.lang.Character#isUnicodeIdentifierStart(char) * @since 1.1 */ public static boolean isUnicodeIdentifierPart(char ch) { return isUnicodeIdentifierPart((int)ch); } /** * Determines if the specified character (Unicode code point) may be part of a Unicode * identifier as other than the first character. * <p> * A character may be part of a Unicode identifier if and only if * one of the following statements is true: * <ul> * <li> it is a letter * <li> it is a connecting punctuation character (such as <code>'_'</code>) * <li> it is a digit * <li> it is a numeric letter (such as a Roman numeral character) * <li> it is a combining mark * <li> it is a non-spacing mark * <li> <code>isIdentifierIgnorable</code> returns * <code>true</code> for this character. * </ul> * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character may be part of a * Unicode identifier; <code>false</code> otherwise. * @see java.lang.Character#isIdentifierIgnorable(int) * @see java.lang.Character#isJavaIdentifierPart(int) * @see java.lang.Character#isLetterOrDigit(int) * @see java.lang.Character#isUnicodeIdentifierStart(int) * @since 1.5 */ public static boolean isUnicodeIdentifierPart(int codePoint) { boolean bUnicodePart = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bUnicodePart = CharacterDataLatin1.isUnicodeIdentifierPart(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bUnicodePart = CharacterData00.isUnicodeIdentifierPart(codePoint); break; case(1): bUnicodePart = CharacterData01.isUnicodeIdentifierPart(codePoint); break; case(2): bUnicodePart = CharacterData02.isUnicodeIdentifierPart(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bUnicodePart = CharacterDataUndefined.isUnicodeIdentifierPart(codePoint); break; case(14): bUnicodePart = CharacterData0E.isUnicodeIdentifierPart(codePoint); break; case(15): // Private Use case(16): // Private Use bUnicodePart = CharacterDataPrivateUse.isUnicodeIdentifierPart(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint //bUnicodePart remains false; break; } } return bUnicodePart; } /** * Determines if the specified character should be regarded as * an ignorable character in a Java identifier or a Unicode identifier. * <p> * The following Unicode characters are ignorable in a Java identifier * or a Unicode identifier: * <ul> * <li>ISO control characters that are not whitespace * <ul> * <li><code>'\u0000'</code> through <code>'\u0008'</code> * <li><code>'\u000E'</code> through <code>'\u001B'</code> * <li><code>'\u007F'</code> through <code>'\u009F'</code> * </ul> * * <li>all characters that have the <code>FORMAT</code> general * category value * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isIdentifierIgnorable(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is an ignorable control * character that may be part of a Java or Unicode identifier; * <code>false</code> otherwise. * @see java.lang.Character#isJavaIdentifierPart(char) * @see java.lang.Character#isUnicodeIdentifierPart(char) * @since 1.1 */ public static boolean isIdentifierIgnorable(char ch) { return isIdentifierIgnorable((int)ch); } /** * Determines if the specified character (Unicode code point) should be regarded as * an ignorable character in a Java identifier or a Unicode identifier. * <p> * The following Unicode characters are ignorable in a Java identifier * or a Unicode identifier: * <ul> * <li>ISO control characters that are not whitespace * <ul> * <li><code>'\u0000'</code> through <code>'\u0008'</code> * <li><code>'\u000E'</code> through <code>'\u001B'</code> * <li><code>'\u007F'</code> through <code>'\u009F'</code> * </ul> * * <li>all characters that have the <code>FORMAT</code> general * category value * </ul> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is an ignorable control * character that may be part of a Java or Unicode identifier; * <code>false</code> otherwise. * @see java.lang.Character#isJavaIdentifierPart(int) * @see java.lang.Character#isUnicodeIdentifierPart(int) * @since 1.5 */ public static boolean isIdentifierIgnorable(int codePoint) { boolean bIdentifierIgnorable = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bIdentifierIgnorable = CharacterDataLatin1.isIdentifierIgnorable(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bIdentifierIgnorable = CharacterData00.isIdentifierIgnorable(codePoint); break; case(1): bIdentifierIgnorable = CharacterData01.isIdentifierIgnorable(codePoint); break; case(2): bIdentifierIgnorable = CharacterData02.isIdentifierIgnorable(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bIdentifierIgnorable = CharacterDataUndefined.isIdentifierIgnorable(codePoint); break; case(14): bIdentifierIgnorable = CharacterData0E.isIdentifierIgnorable(codePoint); break; case(15): // Private Use case(16): // Private Use bIdentifierIgnorable = CharacterDataPrivateUse.isIdentifierIgnorable(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bIdentifierIgnorable remains false; break; } } return bIdentifierIgnorable; } /** * Converts the character argument to lowercase using case * mapping information from the UnicodeData file. * <p> * Note that * <code>Character.isLowerCase(Character.toLowerCase(ch))</code> * does not always return <code>true</code> for some ranges of * characters, particularly those that are symbols or ideographs. * * <p>In general, {@link java.lang.String#toLowerCase()} should be used to map * characters to lowercase. <code>String</code> case mapping methods * have several benefits over <code>Character</code> case mapping methods. * <code>String</code> case mapping methods can perform locale-sensitive * mappings, context-sensitive mappings, and 1:M character mappings, whereas * the <code>Character</code> case mapping methods cannot. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #toLowerCase(int)} method. * * @param ch the character to be converted. * @return the lowercase equivalent of the character, if any; * otherwise, the character itself. * @see java.lang.Character#isLowerCase(char) * @see java.lang.String#toLowerCase() */ public static char toLowerCase(char ch) { return (char)toLowerCase((int)ch); } /** * Converts the character (Unicode code point) argument to * lowercase using case mapping information from the UnicodeData * file. * * <p> Note that * <code>Character.isLowerCase(Character.toLowerCase(codePoint))</code> * does not always return <code>true</code> for some ranges of * characters, particularly those that are symbols or ideographs. * * <p>In general, {@link java.lang.String#toLowerCase()} should be used to map * characters to lowercase. <code>String</code> case mapping methods * have several benefits over <code>Character</code> case mapping methods. * <code>String</code> case mapping methods can perform locale-sensitive * mappings, context-sensitive mappings, and 1:M character mappings, whereas * the <code>Character</code> case mapping methods cannot. * * @param codePoint the character (Unicode code point) to be converted. * @return the lowercase equivalent of the character (Unicode code * point), if any; otherwise, the character itself. * @see java.lang.Character#isLowerCase(int) * @see java.lang.String#toLowerCase() * * @since 1.5 */ public static int toLowerCase(int codePoint) { int lowerCase = codePoint; int plane = 0; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { lowerCase = CharacterDataLatin1.toLowerCase(codePoint); } else { plane = getPlane(codePoint); switch(plane) { case(0): lowerCase = CharacterData00.toLowerCase(codePoint); break; case(1): lowerCase = CharacterData01.toLowerCase(codePoint); break; case(2): lowerCase = CharacterData02.toLowerCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined lowerCase = CharacterDataUndefined.toLowerCase(codePoint); break; case(14): lowerCase = CharacterData0E.toLowerCase(codePoint); break; case(15): // Private Use case(16): // Private Use lowerCase = CharacterDataPrivateUse.toLowerCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // lowerCase remains codePoint; break; } } return lowerCase; } /** * Converts the character argument to uppercase using case mapping * information from the UnicodeData file. * <p> * Note that * <code>Character.isUpperCase(Character.toUpperCase(ch))</code> * does not always return <code>true</code> for some ranges of * characters, particularly those that are symbols or ideographs. * * <p>In general, {@link java.lang.String#toUpperCase()} should be used to map * characters to uppercase. <code>String</code> case mapping methods * have several benefits over <code>Character</code> case mapping methods. * <code>String</code> case mapping methods can perform locale-sensitive * mappings, context-sensitive mappings, and 1:M character mappings, whereas * the <code>Character</code> case mapping methods cannot. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #toUpperCase(int)} method. * * @param ch the character to be converted. * @return the uppercase equivalent of the character, if any; * otherwise, the character itself. * @see java.lang.Character#isUpperCase(char) * @see java.lang.String#toUpperCase() */ public static char toUpperCase(char ch) { return (char)toUpperCase((int)ch); } /** * Converts the character (Unicode code point) argument to * uppercase using case mapping information from the UnicodeData * file. * * <p>Note that * <code>Character.isUpperCase(Character.toUpperCase(codePoint))</code> * does not always return <code>true</code> for some ranges of * characters, particularly those that are symbols or ideographs. * * <p>In general, {@link java.lang.String#toUpperCase()} should be used to map * characters to uppercase. <code>String</code> case mapping methods * have several benefits over <code>Character</code> case mapping methods. * <code>String</code> case mapping methods can perform locale-sensitive * mappings, context-sensitive mappings, and 1:M character mappings, whereas * the <code>Character</code> case mapping methods cannot. * * @param codePoint the character (Unicode code point) to be converted. * @return the uppercase equivalent of the character, if any; * otherwise, the character itself. * @see java.lang.Character#isUpperCase(int) * @see java.lang.String#toUpperCase() * * @since 1.5 */ public static int toUpperCase(int codePoint) { int upperCase = codePoint; int plane = 0; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { upperCase = CharacterDataLatin1.toUpperCase(codePoint); } else { plane = getPlane(codePoint); switch(plane) { case(0): upperCase = CharacterData00.toUpperCase(codePoint); break; case(1): upperCase = CharacterData01.toUpperCase(codePoint); break; case(2): upperCase = CharacterData02.toUpperCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined upperCase = CharacterDataUndefined.toUpperCase(codePoint); break; case(14): upperCase = CharacterData0E.toUpperCase(codePoint); break; case(15): // Private Use case(16): // Private Use upperCase = CharacterDataPrivateUse.toUpperCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // upperCase remains codePoint; break; } } return upperCase; } /** * Converts the character argument to titlecase using case mapping * information from the UnicodeData file. If a character has no * explicit titlecase mapping and is not itself a titlecase char * according to UnicodeData, then the uppercase mapping is * returned as an equivalent titlecase mapping. If the * <code>char</code> argument is already a titlecase * <code>char</code>, the same <code>char</code> value will be * returned. * <p> * Note that * <code>Character.isTitleCase(Character.toTitleCase(ch))</code> * does not always return <code>true</code> for some ranges of * characters. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #toTitleCase(int)} method. * * @param ch the character to be converted. * @return the titlecase equivalent of the character, if any; * otherwise, the character itself. * @see java.lang.Character#isTitleCase(char) * @see java.lang.Character#toLowerCase(char) * @see java.lang.Character#toUpperCase(char) * @since 1.0.2 */ public static char toTitleCase(char ch) { return (char)toTitleCase((int)ch); } /** * Converts the character (Unicode code point) argument to titlecase using case mapping * information from the UnicodeData file. If a character has no * explicit titlecase mapping and is not itself a titlecase char * according to UnicodeData, then the uppercase mapping is * returned as an equivalent titlecase mapping. If the * character argument is already a titlecase * character, the same character value will be * returned. * * <p>Note that * <code>Character.isTitleCase(Character.toTitleCase(codePoint))</code> * does not always return <code>true</code> for some ranges of * characters. * * @param codePoint the character (Unicode code point) to be converted. * @return the titlecase equivalent of the character, if any; * otherwise, the character itself. * @see java.lang.Character#isTitleCase(int) * @see java.lang.Character#toLowerCase(int) * @see java.lang.Character#toUpperCase(int) * @since 1.5 */ public static int toTitleCase(int codePoint) { int titleCase = codePoint; int plane = 0; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { titleCase = CharacterDataLatin1.toTitleCase(codePoint); } else { plane = getPlane(codePoint); switch(plane) { case(0): titleCase = CharacterData00.toTitleCase(codePoint); break; case(1): titleCase = CharacterData01.toTitleCase(codePoint); break; case(2): titleCase = CharacterData02.toTitleCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined titleCase = CharacterDataUndefined.toTitleCase(codePoint); break; case(14): titleCase = CharacterData0E.toTitleCase(codePoint); break; case(15): // Private Use case(16): // Private Use titleCase = CharacterDataPrivateUse.toTitleCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // titleCase remains codePoint; break; } } return titleCase; } /** * Returns the numeric value of the character <code>ch</code> in the * specified radix. * <p> * If the radix is not in the range <code>MIN_RADIX</code> <= * <code>radix</code> <= <code>MAX_RADIX</code> or if the * value of <code>ch</code> is not a valid digit in the specified * radix, <code>-1</code> is returned. A character is a valid digit * if at least one of the following is true: * <ul> * <li>The method <code>isDigit</code> is <code>true</code> of the character * and the Unicode decimal digit value of the character (or its * single-character decomposition) is less than the specified radix. * In this case the decimal digit value is returned. * <li>The character is one of the uppercase Latin letters * <code>'A'</code> through <code>'Z'</code> and its code is less than * <code>radix + 'A' - 10</code>. * In this case, <code>ch - 'A' + 10</code> * is returned. * <li>The character is one of the lowercase Latin letters * <code>'a'</code> through <code>'z'</code> and its code is less than * <code>radix + 'a' - 10</code>. * In this case, <code>ch - 'a' + 10</code> * is returned. * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #digit(int, int)} method. * * @param ch the character to be converted. * @param radix the radix. * @return the numeric value represented by the character in the * specified radix. * @see java.lang.Character#forDigit(int, int) * @see java.lang.Character#isDigit(char) */ public static int digit(char ch, int radix) { return digit((int)ch, radix); } /** * Returns the numeric value of the specified character (Unicode * code point) in the specified radix. * * <p>If the radix is not in the range <code>MIN_RADIX</code> <= * <code>radix</code> <= <code>MAX_RADIX</code> or if the * character is not a valid digit in the specified * radix, <code>-1</code> is returned. A character is a valid digit * if at least one of the following is true: * <ul> * <li>The method {@link #isDigit(int) isDigit(codePoint)} is <code>true</code> of the character * and the Unicode decimal digit value of the character (or its * single-character decomposition) is less than the specified radix. * In this case the decimal digit value is returned. * <li>The character is one of the uppercase Latin letters * <code>'A'</code> through <code>'Z'</code> and its code is less than * <code>radix + 'A' - 10</code>. * In this case, <code>ch - 'A' + 10</code> * is returned. * <li>The character is one of the lowercase Latin letters * <code>'a'</code> through <code>'z'</code> and its code is less than * <code>radix + 'a' - 10</code>. * In this case, <code>ch - 'a' + 10</code> * is returned. * </ul> * * @param codePoint the character (Unicode code point) to be converted. * @param radix the radix. * @return the numeric value represented by the character in the * specified radix. * @see java.lang.Character#forDigit(int, int) * @see java.lang.Character#isDigit(int) * @since 1.5 */ public static int digit(int codePoint, int radix) { int digit = -1; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { digit = CharacterDataLatin1.digit(codePoint, radix); } else { int plane = getPlane(codePoint); switch(plane) { case(0): digit = CharacterData00.digit(codePoint, radix); break; case(1): digit = CharacterData01.digit(codePoint, radix); break; case(2): digit = CharacterData02.digit(codePoint, radix); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined digit = CharacterDataUndefined.digit(codePoint, radix); break; case(14): digit = CharacterData0E.digit(codePoint, radix); break; case(15): // Private Use case(16): // Private Use digit = CharacterDataPrivateUse.digit(codePoint, radix); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // digit remains -1; break; } } return digit; } /** * Returns the <code>int</code> value that the specified Unicode * character represents. For example, the character * <code>'\u216C'</code> (the roman numeral fifty) will return * an int with a value of 50. * <p> * The letters A-Z in their uppercase (<code>'\u0041'</code> through * <code>'\u005A'</code>), lowercase * (<code>'\u0061'</code> through <code>'\u007A'</code>), and * full width variant (<code>'\uFF21'</code> through * <code>'\uFF3A'</code> and <code>'\uFF41'</code> through * <code>'\uFF5A'</code>) forms have numeric values from 10 * through 35. This is independent of the Unicode specification, * which does not assign numeric values to these <code>char</code> * values. * <p> * If the character does not have a numeric value, then -1 is returned. * If the character has a numeric value that cannot be represented as a * nonnegative integer (for example, a fractional value), then -2 * is returned. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #getNumericValue(int)} method. * * @param ch the character to be converted. * @return the numeric value of the character, as a nonnegative <code>int</code> * value; -2 if the character has a numeric value that is not a * nonnegative integer; -1 if the character has no numeric value. * @see java.lang.Character#forDigit(int, int) * @see java.lang.Character#isDigit(char) * @since 1.1 */ public static int getNumericValue(char ch) { return getNumericValue((int)ch); } /** * Returns the <code>int</code> value that the specified * character (Unicode code point) represents. For example, the character * <code>'\u216C'</code> (the Roman numeral fifty) will return * an <code>int</code> with a value of 50. * <p> * The letters A-Z in their uppercase (<code>'\u0041'</code> through * <code>'\u005A'</code>), lowercase * (<code>'\u0061'</code> through <code>'\u007A'</code>), and * full width variant (<code>'\uFF21'</code> through * <code>'\uFF3A'</code> and <code>'\uFF41'</code> through * <code>'\uFF5A'</code>) forms have numeric values from 10 * through 35. This is independent of the Unicode specification, * which does not assign numeric values to these <code>char</code> * values. * <p> * If the character does not have a numeric value, then -1 is returned. * If the character has a numeric value that cannot be represented as a * nonnegative integer (for example, a fractional value), then -2 * is returned. * * @param codePoint the character (Unicode code point) to be converted. * @return the numeric value of the character, as a nonnegative <code>int</code> * value; -2 if the character has a numeric value that is not a * nonnegative integer; -1 if the character has no numeric value. * @see java.lang.Character#forDigit(int, int) * @see java.lang.Character#isDigit(int) * @since 1.5 */ public static int getNumericValue(int codePoint) { int numericValue = -1; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { numericValue = CharacterDataLatin1.getNumericValue(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): numericValue = CharacterData00.getNumericValue(codePoint); break; case(1): numericValue = CharacterData01.getNumericValue(codePoint); break; case(2): numericValue = CharacterData02.getNumericValue(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined numericValue = CharacterDataUndefined.getNumericValue(codePoint); break; case(14): numericValue = CharacterData0E.getNumericValue(codePoint); break; case(15): // Private Use case(16): // Private Use numericValue = CharacterDataPrivateUse.getNumericValue(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // numericValue remains -1 break; } } return numericValue; } /** * Determines if the specified character is ISO-LATIN-1 white space. * This method returns <code>true</code> for the following five * characters only: * <table> * <tr><td><code>'\t'</code></td> <td><code>'\u0009'</code></td> * <td><code>HORIZONTAL TABULATION</code></td></tr> * <tr><td><code>'\n'</code></td> <td><code>'\u000A'</code></td> * <td><code>NEW LINE</code></td></tr> * <tr><td><code>'\f'</code></td> <td><code>'\u000C'</code></td> * <td><code>FORM FEED</code></td></tr> * <tr><td><code>'\r'</code></td> <td><code>'\u000D'</code></td> * <td><code>CARRIAGE RETURN</code></td></tr> * <tr><td><code>' '</code></td> <td><code>'\u0020'</code></td> * <td><code>SPACE</code></td></tr> * </table> * * @param ch the character to be tested. * @return <code>true</code> if the character is ISO-LATIN-1 white * space; <code>false</code> otherwise. * @see java.lang.Character#isSpaceChar(char) * @see java.lang.Character#isWhitespace(char) * @deprecated Replaced by isWhitespace(char). */ @Deprecated public static boolean isSpace(char ch) { return (ch <= 0x0020) && (((((1L << 0x0009) | (1L << 0x000A) | (1L << 0x000C) | (1L << 0x000D) | (1L << 0x0020)) >> ch) & 1L) != 0); } /** * Determines if the specified character is a Unicode space character. * A character is considered to be a space character if and only if * it is specified to be a space character by the Unicode standard. This * method returns true if the character's general category type is any of * the following: * <ul> * <li> <code>SPACE_SEPARATOR</code> * <li> <code>LINE_SEPARATOR</code> * <li> <code>PARAGRAPH_SEPARATOR</code> * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isSpaceChar(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is a space character; * <code>false</code> otherwise. * @see java.lang.Character#isWhitespace(char) * @since 1.1 */ public static boolean isSpaceChar(char ch) { return isSpaceChar((int)ch); } /** * Determines if the specified character (Unicode code point) is a * Unicode space character. A character is considered to be a * space character if and only if it is specified to be a space * character by the Unicode standard. This method returns true if * the character's general category type is any of the following: * * <ul> * <li> {@link #SPACE_SEPARATOR} * <li> {@link #LINE_SEPARATOR} * <li> {@link #PARAGRAPH_SEPARATOR} * </ul> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is a space character; * <code>false</code> otherwise. * @see java.lang.Character#isWhitespace(int) * @since 1.5 */ public static boolean isSpaceChar(int codePoint) { boolean bSpaceChar = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bSpaceChar = CharacterDataLatin1.isSpaceChar(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bSpaceChar = CharacterData00.isSpaceChar(codePoint); break; case(1): bSpaceChar = CharacterData01.isSpaceChar(codePoint); break; case(2): bSpaceChar = CharacterData02.isSpaceChar(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bSpaceChar = CharacterDataUndefined.isSpaceChar(codePoint); break; case(14): bSpaceChar = CharacterData0E.isSpaceChar(codePoint); break; case(15): // Private Use case(16): // Private Use bSpaceChar = CharacterDataPrivateUse.isSpaceChar(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bSpaceChar remains false break; } } return bSpaceChar; } /** * Determines if the specified character is white space according to Java. * A character is a Java whitespace character if and only if it satisfies * one of the following criteria: * <ul> * <li> It is a Unicode space character (<code>SPACE_SEPARATOR</code>, * <code>LINE_SEPARATOR</code>, or <code>PARAGRAPH_SEPARATOR</code>) * but is not also a non-breaking space (<code>'\u00A0'</code>, * <code>'\u2007'</code>, <code>'\u202F'</code>). * <li> It is <code>'\u0009'</code>, HORIZONTAL TABULATION. * <li> It is <code>'\u000A'</code>, LINE FEED. * <li> It is <code>'\u000B'</code>, VERTICAL TABULATION. * <li> It is <code>'\u000C'</code>, FORM FEED. * <li> It is <code>'\u000D'</code>, CARRIAGE RETURN. * <li> It is <code>'\u001C'</code>, FILE SEPARATOR. * <li> It is <code>'\u001D'</code>, GROUP SEPARATOR. * <li> It is <code>'\u001E'</code>, RECORD SEPARATOR. * <li> It is <code>'\u001F'</code>, UNIT SEPARATOR. * </ul> * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isWhitespace(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is a Java whitespace * character; <code>false</code> otherwise. * @see java.lang.Character#isSpaceChar(char) * @since 1.1 */ public static boolean isWhitespace(char ch) { return isWhitespace((int)ch); } /** * Determines if the specified character (Unicode code point) is * white space according to Java. A character is a Java * whitespace character if and only if it satisfies one of the * following criteria: * <ul> * <li> It is a Unicode space character ({@link #SPACE_SEPARATOR}, * {@link #LINE_SEPARATOR}, or {@link #PARAGRAPH_SEPARATOR}) * but is not also a non-breaking space (<code>'\u00A0'</code>, * <code>'\u2007'</code>, <code>'\u202F'</code>). * <li> It is <code>'\u0009'</code>, HORIZONTAL TABULATION. * <li> It is <code>'\u000A'</code>, LINE FEED. * <li> It is <code>'\u000B'</code>, VERTICAL TABULATION. * <li> It is <code>'\u000C'</code>, FORM FEED. * <li> It is <code>'\u000D'</code>, CARRIAGE RETURN. * <li> It is <code>'\u001C'</code>, FILE SEPARATOR. * <li> It is <code>'\u001D'</code>, GROUP SEPARATOR. * <li> It is <code>'\u001E'</code>, RECORD SEPARATOR. * <li> It is <code>'\u001F'</code>, UNIT SEPARATOR. * </ul> * <p> * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is a Java whitespace * character; <code>false</code> otherwise. * @see java.lang.Character#isSpaceChar(int) * @since 1.5 */ public static boolean isWhitespace(int codePoint) { boolean bWhiteSpace = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bWhiteSpace = CharacterDataLatin1.isWhitespace(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bWhiteSpace = CharacterData00.isWhitespace(codePoint); break; case(1): bWhiteSpace = CharacterData01.isWhitespace(codePoint); break; case(2): bWhiteSpace = CharacterData02.isWhitespace(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bWhiteSpace = CharacterDataUndefined.isWhitespace(codePoint); break; case(14): bWhiteSpace = CharacterData0E.isWhitespace(codePoint); break; case(15): // Private Use case(16): // Private Use bWhiteSpace = CharacterDataPrivateUse.isWhitespace(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bWhiteSpace remains false break; } } return bWhiteSpace; } /** * Determines if the specified character is an ISO control * character. A character is considered to be an ISO control * character if its code is in the range <code>'\u0000'</code> * through <code>'\u001F'</code> or in the range * <code>'\u007F'</code> through <code>'\u009F'</code>. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isISOControl(int)} method. * * @param ch the character to be tested. * @return <code>true</code> if the character is an ISO control character; * <code>false</code> otherwise. * * @see java.lang.Character#isSpaceChar(char) * @see java.lang.Character#isWhitespace(char) * @since 1.1 */ public static boolean isISOControl(char ch) { return isISOControl((int)ch); } /** * Determines if the referenced character (Unicode code point) is an ISO control * character. A character is considered to be an ISO control * character if its code is in the range <code>'\u0000'</code> * through <code>'\u001F'</code> or in the range * <code>'\u007F'</code> through <code>'\u009F'</code>. * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is an ISO control character; * <code>false</code> otherwise. * @see java.lang.Character#isSpaceChar(int) * @see java.lang.Character#isWhitespace(int) * @since 1.5 */ public static boolean isISOControl(int codePoint) { return (codePoint >= 0x0000 && codePoint <= 0x001F) || (codePoint >= 0x007F && codePoint <= 0x009F); } /** * Returns a value indicating a character's general category. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #getType(int)} method. * * @param ch the character to be tested. * @return a value of type <code>int</code> representing the * character's general category. * @see java.lang.Character#COMBINING_SPACING_MARK * @see java.lang.Character#CONNECTOR_PUNCTUATION * @see java.lang.Character#CONTROL * @see java.lang.Character#CURRENCY_SYMBOL * @see java.lang.Character#DASH_PUNCTUATION * @see java.lang.Character#DECIMAL_DIGIT_NUMBER * @see java.lang.Character#ENCLOSING_MARK * @see java.lang.Character#END_PUNCTUATION * @see java.lang.Character#FINAL_QUOTE_PUNCTUATION * @see java.lang.Character#FORMAT * @see java.lang.Character#INITIAL_QUOTE_PUNCTUATION * @see java.lang.Character#LETTER_NUMBER * @see java.lang.Character#LINE_SEPARATOR * @see java.lang.Character#LOWERCASE_LETTER * @see java.lang.Character#MATH_SYMBOL * @see java.lang.Character#MODIFIER_LETTER * @see java.lang.Character#MODIFIER_SYMBOL * @see java.lang.Character#NON_SPACING_MARK * @see java.lang.Character#OTHER_LETTER * @see java.lang.Character#OTHER_NUMBER * @see java.lang.Character#OTHER_PUNCTUATION * @see java.lang.Character#OTHER_SYMBOL * @see java.lang.Character#PARAGRAPH_SEPARATOR * @see java.lang.Character#PRIVATE_USE * @see java.lang.Character#SPACE_SEPARATOR * @see java.lang.Character#START_PUNCTUATION * @see java.lang.Character#SURROGATE * @see java.lang.Character#TITLECASE_LETTER * @see java.lang.Character#UNASSIGNED * @see java.lang.Character#UPPERCASE_LETTER * @since 1.1 */ public static int getType(char ch) { return getType((int)ch); } /** * Returns a value indicating a character's general category. * * @param codePoint the character (Unicode code point) to be tested. * @return a value of type <code>int</code> representing the * character's general category. * @see Character#COMBINING_SPACING_MARK COMBINING_SPACING_MARK * @see Character#CONNECTOR_PUNCTUATION CONNECTOR_PUNCTUATION * @see Character#CONTROL CONTROL * @see Character#CURRENCY_SYMBOL CURRENCY_SYMBOL * @see Character#DASH_PUNCTUATION DASH_PUNCTUATION * @see Character#DECIMAL_DIGIT_NUMBER DECIMAL_DIGIT_NUMBER * @see Character#ENCLOSING_MARK ENCLOSING_MARK * @see Character#END_PUNCTUATION END_PUNCTUATION * @see Character#FINAL_QUOTE_PUNCTUATION FINAL_QUOTE_PUNCTUATION * @see Character#FORMAT FORMAT * @see Character#INITIAL_QUOTE_PUNCTUATION INITIAL_QUOTE_PUNCTUATION * @see Character#LETTER_NUMBER LETTER_NUMBER * @see Character#LINE_SEPARATOR LINE_SEPARATOR * @see Character#LOWERCASE_LETTER LOWERCASE_LETTER * @see Character#MATH_SYMBOL MATH_SYMBOL * @see Character#MODIFIER_LETTER MODIFIER_LETTER * @see Character#MODIFIER_SYMBOL MODIFIER_SYMBOL * @see Character#NON_SPACING_MARK NON_SPACING_MARK * @see Character#OTHER_LETTER OTHER_LETTER * @see Character#OTHER_NUMBER OTHER_NUMBER * @see Character#OTHER_PUNCTUATION OTHER_PUNCTUATION * @see Character#OTHER_SYMBOL OTHER_SYMBOL * @see Character#PARAGRAPH_SEPARATOR PARAGRAPH_SEPARATOR * @see Character#PRIVATE_USE PRIVATE_USE * @see Character#SPACE_SEPARATOR SPACE_SEPARATOR * @see Character#START_PUNCTUATION START_PUNCTUATION * @see Character#SURROGATE SURROGATE * @see Character#TITLECASE_LETTER TITLECASE_LETTER * @see Character#UNASSIGNED UNASSIGNED * @see Character#UPPERCASE_LETTER UPPERCASE_LETTER * @since 1.5 */ public static int getType(int codePoint) { int type = Character.UNASSIGNED; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { type = CharacterDataLatin1.getType(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): type = CharacterData00.getType(codePoint); break; case(1): type = CharacterData01.getType(codePoint); break; case(2): type = CharacterData02.getType(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined type = CharacterDataUndefined.getType(codePoint); break; case(14): type = CharacterData0E.getType(codePoint); break; case(15): // Private Use case(16): // Private Use type = CharacterDataPrivateUse.getType(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // type remains UNASSIGNED break; } } return type; } /** * Determines the character representation for a specific digit in * the specified radix. If the value of <code>radix</code> is not a * valid radix, or the value of <code>digit</code> is not a valid * digit in the specified radix, the null character * (<code>'\u0000'</code>) is returned. * <p> * The <code>radix</code> argument is valid if it is greater than or * equal to <code>MIN_RADIX</code> and less than or equal to * <code>MAX_RADIX</code>. The <code>digit</code> argument is valid if * <code>0 <=digit < radix</code>. * <p> * If the digit is less than 10, then * <code>'0' + digit</code> is returned. Otherwise, the value * <code>'a' + digit - 10</code> is returned. * * @param digit the number to convert to a character. * @param radix the radix. * @return the <code>char</code> representation of the specified digit * in the specified radix. * @see java.lang.Character#MIN_RADIX * @see java.lang.Character#MAX_RADIX * @see java.lang.Character#digit(char, int) */ public static char forDigit(int digit, int radix) { if ((digit >= radix) || (digit < 0)) { return '\0'; } if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) { return '\0'; } if (digit < 10) { return (char)('0' + digit); } return (char)('a' - 10 + digit); } /** * Returns the Unicode directionality property for the given * character. Character directionality is used to calculate the * visual ordering of text. The directionality value of undefined * <code>char</code> values is <code>DIRECTIONALITY_UNDEFINED</code>. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #getDirectionality(int)} method. * * @param ch <code>char</code> for which the directionality property * is requested. * @return the directionality property of the <code>char</code> value. * * @see Character#DIRECTIONALITY_UNDEFINED * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR * @see Character#DIRECTIONALITY_ARABIC_NUMBER * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR * @see Character#DIRECTIONALITY_NONSPACING_MARK * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR * @see Character#DIRECTIONALITY_WHITESPACE * @see Character#DIRECTIONALITY_OTHER_NEUTRALS * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT * @since 1.4 */ public static byte getDirectionality(char ch) { return getDirectionality((int)ch); } /** * Returns the Unicode directionality property for the given * character (Unicode code point). Character directionality is * used to calculate the visual ordering of text. The * directionality value of undefined character is {@link * #DIRECTIONALITY_UNDEFINED}. * * @param codePoint the character (Unicode code point) for which * the directionality property is requested. * @return the directionality property of the character. * * @see Character#DIRECTIONALITY_UNDEFINED DIRECTIONALITY_UNDEFINED * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT DIRECTIONALITY_LEFT_TO_RIGHT * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT DIRECTIONALITY_RIGHT_TO_LEFT * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC DIRECTIONALITY_RIGHT_TO_LEFT_ARABIC * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER DIRECTIONALITY_EUROPEAN_NUMBER * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR DIRECTIONALITY_EUROPEAN_NUMBER_SEPARATOR * @see Character#DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR DIRECTIONALITY_EUROPEAN_NUMBER_TERMINATOR * @see Character#DIRECTIONALITY_ARABIC_NUMBER DIRECTIONALITY_ARABIC_NUMBER * @see Character#DIRECTIONALITY_COMMON_NUMBER_SEPARATOR DIRECTIONALITY_COMMON_NUMBER_SEPARATOR * @see Character#DIRECTIONALITY_NONSPACING_MARK DIRECTIONALITY_NONSPACING_MARK * @see Character#DIRECTIONALITY_BOUNDARY_NEUTRAL DIRECTIONALITY_BOUNDARY_NEUTRAL * @see Character#DIRECTIONALITY_PARAGRAPH_SEPARATOR DIRECTIONALITY_PARAGRAPH_SEPARATOR * @see Character#DIRECTIONALITY_SEGMENT_SEPARATOR DIRECTIONALITY_SEGMENT_SEPARATOR * @see Character#DIRECTIONALITY_WHITESPACE DIRECTIONALITY_WHITESPACE * @see Character#DIRECTIONALITY_OTHER_NEUTRALS DIRECTIONALITY_OTHER_NEUTRALS * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING DIRECTIONALITY_LEFT_TO_RIGHT_EMBEDDING * @see Character#DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE DIRECTIONALITY_LEFT_TO_RIGHT_OVERRIDE * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING DIRECTIONALITY_RIGHT_TO_LEFT_EMBEDDING * @see Character#DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE DIRECTIONALITY_RIGHT_TO_LEFT_OVERRIDE * @see Character#DIRECTIONALITY_POP_DIRECTIONAL_FORMAT DIRECTIONALITY_POP_DIRECTIONAL_FORMAT * @since 1.5 */ public static byte getDirectionality(int codePoint) { byte directionality = Character.DIRECTIONALITY_UNDEFINED; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { directionality = CharacterDataLatin1.getDirectionality(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): directionality = CharacterData00.getDirectionality(codePoint); break; case(1): directionality = CharacterData01.getDirectionality(codePoint); break; case(2): directionality = CharacterData02.getDirectionality(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined directionality = CharacterDataUndefined.getDirectionality(codePoint); break; case(14): directionality = CharacterData0E.getDirectionality(codePoint); break; case(15): // Private Use case(16): // Private Use directionality = CharacterDataPrivateUse.getDirectionality(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // directionality remains DIRECTIONALITY_UNDEFINED break; } } return directionality; } /** * Determines whether the character is mirrored according to the * Unicode specification. Mirrored characters should have their * glyphs horizontally mirrored when displayed in text that is * right-to-left. For example, <code>'\u0028'</code> LEFT * PARENTHESIS is semantically defined to be an <i>opening * parenthesis</i>. This will appear as a "(" in text that is * left-to-right but as a ")" in text that is right-to-left. * * <p><b>Note:</b> This method cannot handle <a * href="#supplementary"> supplementary characters</a>. To support * all Unicode characters, including supplementary characters, use * the {@link #isMirrored(int)} method. * * @param ch <code>char</code> for which the mirrored property is requested * @return <code>true</code> if the char is mirrored, <code>false</code> * if the <code>char</code> is not mirrored or is not defined. * @since 1.4 */ public static boolean isMirrored(char ch) { return isMirrored((int)ch); } /** * Determines whether the specified character (Unicode code point) * is mirrored according to the Unicode specification. Mirrored * characters should have their glyphs horizontally mirrored when * displayed in text that is right-to-left. For example, * <code>'\u0028'</code> LEFT PARENTHESIS is semantically * defined to be an <i>opening parenthesis</i>. This will appear * as a "(" in text that is left-to-right but as a ")" in text * that is right-to-left. * * @param codePoint the character (Unicode code point) to be tested. * @return <code>true</code> if the character is mirrored, <code>false</code> * if the character is not mirrored or is not defined. * @since 1.5 */ public static boolean isMirrored(int codePoint) { boolean bMirrored = false; if (codePoint >= MIN_CODE_POINT && codePoint <= FAST_PATH_MAX) { bMirrored = CharacterDataLatin1.isMirrored(codePoint); } else { int plane = getPlane(codePoint); switch(plane) { case(0): bMirrored = CharacterData00.isMirrored(codePoint); break; case(1): bMirrored = CharacterData01.isMirrored(codePoint); break; case(2): bMirrored = CharacterData02.isMirrored(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined bMirrored = CharacterDataUndefined.isMirrored(codePoint); break; case(14): bMirrored = CharacterData0E.isMirrored(codePoint); break; case(15): // Private Use case(16): // Private Use bMirrored = CharacterDataPrivateUse.isMirrored(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // bMirrored remains false break; } } return bMirrored; } /** * Compares two <code>Character</code> objects numerically. * * @param anotherCharacter the <code>Character</code> to be compared. * @return the value <code>0</code> if the argument <code>Character</code> * is equal to this <code>Character</code>; a value less than * <code>0</code> if this <code>Character</code> is numerically less * than the <code>Character</code> argument; and a value greater than * <code>0</code> if this <code>Character</code> is numerically greater * than the <code>Character</code> argument (unsigned comparison). * Note that this is strictly a numerical comparison; it is not * locale-dependent. * @since 1.2 */ public int compareTo(Character anotherCharacter) { return this.value - anotherCharacter.value; } /** * Converts the character (Unicode code point) argument to uppercase using * information from the UnicodeData file. * <p> * * @param codePoint the character (Unicode code point) to be converted. * @return either the uppercase equivalent of the character, if * any, or an error flag (<code>Character.ERROR</code>) * that indicates that a 1:M <code>char</code> mapping exists. * @see java.lang.Character#isLowerCase(char) * @see java.lang.Character#isUpperCase(char) * @see java.lang.Character#toLowerCase(char) * @see java.lang.Character#toTitleCase(char) * @since 1.4 */ static int toUpperCaseEx(int codePoint) { int upperCase = codePoint; int plane = 0; assert isValidCodePoint(codePoint); if (codePoint <= FAST_PATH_MAX) { upperCase = CharacterDataLatin1.toUpperCaseEx(codePoint); } else { plane = getPlane(codePoint); switch(plane) { case(0): upperCase = CharacterData00.toUpperCaseEx(codePoint); break; case(1): upperCase = CharacterData01.toUpperCase(codePoint); break; case(2): upperCase = CharacterData02.toUpperCase(codePoint); break; case(3): // Undefined case(4): // Undefined case(5): // Undefined case(6): // Undefined case(7): // Undefined case(8): // Undefined case(9): // Undefined case(10): // Undefined case(11): // Undefined case(12): // Undefined case(13): // Undefined upperCase = CharacterDataUndefined.toUpperCase(codePoint); break; case(14): upperCase = CharacterData0E.toUpperCase(codePoint); break; case(15): // Private Use case(16): // Private Use upperCase = CharacterDataPrivateUse.toUpperCase(codePoint); break; default: // the argument's plane is invalid, and thus is an invalid codepoint // upperCase remains codePoint; break; } } return upperCase; } /** * Converts the character (Unicode code point) argument to uppercase using case * mapping information from the SpecialCasing file in the Unicode * specification. If a character has no explicit uppercase * mapping, then the <code>char</code> itself is returned in the * <code>char[]</code>. * * @param codePoint the character (Unicode code point) to be converted. * @return a <code>char[]</code> with the uppercased character. * @since 1.4 */ static char[] toUpperCaseCharArray(int codePoint) { char[] upperCase = null; // As of Unicode 4.0, 1:M uppercasings only happen in the BMP. assert isValidCodePoint(codePoint) && !isSupplementaryCodePoint(codePoint); if (codePoint <= FAST_PATH_MAX) { upperCase = CharacterDataLatin1.toUpperCaseCharArray(codePoint); } else { upperCase = CharacterData00.toUpperCaseCharArray(codePoint); } return upperCase; } /** * The number of bits used to represent a <tt>char</tt> value in unsigned * binary form. * * @since 1.5 */ public static final int SIZE = 16; /** * Returns the value obtained by reversing the order of the bytes in the * specified <tt>char</tt> value. * * @return the value obtained by reversing (or, equivalently, swapping) * the bytes in the specified <tt>char</tt> value. * @since 1.5 */ public static char reverseBytes(char ch) { return (char) (((ch & 0xFF00) >> 8) | (ch << 8)); } }
