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
/* * @(#)Pattern.java 1.124 07/03/15 * * Copyright 2006 Sun Microsystems, Inc. All rights reserved. * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms. */ package java.util.regex; import java.security.AccessController; import java.security.PrivilegedAction; import java.text.CharacterIterator; import java.text.Normalizer; import java.util.ArrayList; import java.util.HashMap; import java.util.Arrays; /** * A compiled representation of a regular expression. * * <p> A regular expression, specified as a string, must first be compiled into * an instance of this class. The resulting pattern can then be used to create * a {@link Matcher} object that can match arbitrary {@link * java.lang.CharSequence </code>character sequences<code>} against the regular * expression. All of the state involved in performing a match resides in the * matcher, so many matchers can share the same pattern. * * <p> A typical invocation sequence is thus * * <blockquote><pre> * Pattern p = Pattern.{@link #compile compile}("a*b"); * Matcher m = p.{@link #matcher matcher}("aaaaab"); * boolean b = m.{@link Matcher#matches matches}();</pre></blockquote> * * <p> A {@link #matches matches} method is defined by this class as a * convenience for when a regular expression is used just once. This method * compiles an expression and matches an input sequence against it in a single * invocation. The statement * * <blockquote><pre> * boolean b = Pattern.matches("a*b", "aaaaab");</pre></blockquote> * * is equivalent to the three statements above, though for repeated matches it * is less efficient since it does not allow the compiled pattern to be reused. * * <p> Instances of this class are immutable and are safe for use by multiple * concurrent threads. Instances of the {@link Matcher} class are not safe for * such use. * * * <a name="sum"> * <h4> Summary of regular-expression constructs </h4> * * <table border="0" cellpadding="1" cellspacing="0" * summary="Regular expression constructs, and what they match"> * * <tr align="left"> * <th bgcolor="#CCCCFF" align="left" id="construct">Construct</th> * <th bgcolor="#CCCCFF" align="left" id="matches">Matches</th> * </tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="characters">Characters</th></tr> * * <tr><td valign="top" headers="construct characters"><i>x</i></td> * <td headers="matches">The character <i>x</i></td></tr> * <tr><td valign="top" headers="construct characters"><tt>\\</tt></td> * <td headers="matches">The backslash character</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\0</tt><i>n</i></td> * <td headers="matches">The character with octal value <tt>0</tt><i>n</i> * (0 <tt><=</tt> <i>n</i> <tt><=</tt> 7)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\0</tt><i>nn</i></td> * <td headers="matches">The character with octal value <tt>0</tt><i>nn</i> * (0 <tt><=</tt> <i>n</i> <tt><=</tt> 7)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\0</tt><i>mnn</i></td> * <td headers="matches">The character with octal value <tt>0</tt><i>mnn</i> * (0 <tt><=</tt> <i>m</i> <tt><=</tt> 3, * 0 <tt><=</tt> <i>n</i> <tt><=</tt> 7)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\x</tt><i>hh</i></td> * <td headers="matches">The character with hexadecimal value <tt>0x</tt><i>hh</i></td></tr> * <tr><td valign="top" headers="construct characters"><tt>\u</tt><i>hhhh</i></td> * <td headers="matches">The character with hexadecimal value <tt>0x</tt><i>hhhh</i></td></tr> * <tr><td valign="top" headers="matches"><tt>\t</tt></td> * <td headers="matches">The tab character (<tt>'\u0009'</tt>)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\n</tt></td> * <td headers="matches">The newline (line feed) character (<tt>'\u000A'</tt>)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\r</tt></td> * <td headers="matches">The carriage-return character (<tt>'\u000D'</tt>)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\f</tt></td> * <td headers="matches">The form-feed character (<tt>'\u000C'</tt>)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\a</tt></td> * <td headers="matches">The alert (bell) character (<tt>'\u0007'</tt>)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\e</tt></td> * <td headers="matches">The escape character (<tt>'\u001B'</tt>)</td></tr> * <tr><td valign="top" headers="construct characters"><tt>\c</tt><i>x</i></td> * <td headers="matches">The control character corresponding to <i>x</i></td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="classes">Character classes</th></tr> * * <tr><td valign="top" headers="construct classes"><tt>[abc]</tt></td> * <td headers="matches"><tt>a</tt>, <tt>b</tt>, or <tt>c</tt> (simple class)</td></tr> * <tr><td valign="top" headers="construct classes"><tt>[^abc]</tt></td> * <td headers="matches">Any character except <tt>a</tt>, <tt>b</tt>, or <tt>c</tt> (negation)</td></tr> * <tr><td valign="top" headers="construct classes"><tt>[a-zA-Z]</tt></td> * <td headers="matches"><tt>a</tt> through <tt>z</tt> * or <tt>A</tt> through <tt>Z</tt>, inclusive (range)</td></tr> * <tr><td valign="top" headers="construct classes"><tt>[a-d[m-p]]</tt></td> * <td headers="matches"><tt>a</tt> through <tt>d</tt>, * or <tt>m</tt> through <tt>p</tt>: <tt>[a-dm-p]</tt> (union)</td></tr> * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[def]]</tt></td> * <td headers="matches"><tt>d</tt>, <tt>e</tt>, or <tt>f</tt> (intersection)</tr> * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[^bc]]</tt></td> * <td headers="matches"><tt>a</tt> through <tt>z</tt>, * except for <tt>b</tt> and <tt>c</tt>: <tt>[ad-z]</tt> (subtraction)</td></tr> * <tr><td valign="top" headers="construct classes"><tt>[a-z&&[^m-p]]</tt></td> * <td headers="matches"><tt>a</tt> through <tt>z</tt>, * and not <tt>m</tt> through <tt>p</tt>: <tt>[a-lq-z]</tt>(subtraction)</td></tr> * <tr><th> </th></tr> * * <tr align="left"><th colspan="2" id="predef">Predefined character classes</th></tr> * * <tr><td valign="top" headers="construct predef"><tt>.</tt></td> * <td headers="matches">Any character (may or may not match <a href="#lt">line terminators</a>)</td></tr> * <tr><td valign="top" headers="construct predef"><tt>\d</tt></td> * <td headers="matches">A digit: <tt>[0-9]</tt></td></tr> * <tr><td valign="top" headers="construct predef"><tt>\D</tt></td> * <td headers="matches">A non-digit: <tt>[^0-9]</tt></td></tr> * <tr><td valign="top" headers="construct predef"><tt>\s</tt></td> * <td headers="matches">A whitespace character: <tt>[ \t\n\x0B\f\r]</tt></td></tr> * <tr><td valign="top" headers="construct predef"><tt>\S</tt></td> * <td headers="matches">A non-whitespace character: <tt>[^\s]</tt></td></tr> * <tr><td valign="top" headers="construct predef"><tt>\w</tt></td> * <td headers="matches">A word character: <tt>[a-zA-Z_0-9]</tt></td></tr> * <tr><td valign="top" headers="construct predef"><tt>\W</tt></td> * <td headers="matches">A non-word character: <tt>[^\w]</tt></td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="posix">POSIX character classes</b> (US-ASCII only)<b></th></tr> * * <tr><td valign="top" headers="construct posix"><tt>\p{Lower}</tt></td> * <td headers="matches">A lower-case alphabetic character: <tt>[a-z]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Upper}</tt></td> * <td headers="matches">An upper-case alphabetic character:<tt>[A-Z]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{ASCII}</tt></td> * <td headers="matches">All ASCII:<tt>[\x00-\x7F]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Alpha}</tt></td> * <td headers="matches">An alphabetic character:<tt>[\p{Lower}\p{Upper}]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Digit}</tt></td> * <td headers="matches">A decimal digit: <tt>[0-9]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Alnum}</tt></td> * <td headers="matches">An alphanumeric character:<tt>[\p{Alpha}\p{Digit}]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Punct}</tt></td> * <td headers="matches">Punctuation: One of <tt>!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~</tt></td></tr> * <!-- <tt>[\!"#\$%&'\(\)\*\+,\-\./:;\<=\>\?@\[\\\]\^_`\{\|\}~]</tt> * <tt>[\X21-\X2F\X31-\X40\X5B-\X60\X7B-\X7E]</tt> --> * <tr><td valign="top" headers="construct posix"><tt>\p{Graph}</tt></td> * <td headers="matches">A visible character: <tt>[\p{Alnum}\p{Punct}]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Print}</tt></td> * <td headers="matches">A printable character: <tt>[\p{Graph}\x20]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Blank}</tt></td> * <td headers="matches">A space or a tab: <tt>[ \t]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Cntrl}</tt></td> * <td headers="matches">A control character: <tt>[\x00-\x1F\x7F]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{XDigit}</tt></td> * <td headers="matches">A hexadecimal digit: <tt>[0-9a-fA-F]</tt></td></tr> * <tr><td valign="top" headers="construct posix"><tt>\p{Space}</tt></td> * <td headers="matches">A whitespace character: <tt>[ \t\n\x0B\f\r]</tt></td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2">java.lang.Character classes (simple <a href="#jcc">java character type</a>)</th></tr> * * <tr><td valign="top"><tt>\p{javaLowerCase}</tt></td> * <td>Equivalent to java.lang.Character.isLowerCase()</td></tr> * <tr><td valign="top"><tt>\p{javaUpperCase}</tt></td> * <td>Equivalent to java.lang.Character.isUpperCase()</td></tr> * <tr><td valign="top"><tt>\p{javaWhitespace}</tt></td> * <td>Equivalent to java.lang.Character.isWhitespace()</td></tr> * <tr><td valign="top"><tt>\p{javaMirrored}</tt></td> * <td>Equivalent to java.lang.Character.isMirrored()</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="unicode">Classes for Unicode blocks and categories</th></tr> * * <tr><td valign="top" headers="construct unicode"><tt>\p{InGreek}</tt></td> * <td headers="matches">A character in the Greek block (simple <a href="#ubc">block</a>)</td></tr> * <tr><td valign="top" headers="construct unicode"><tt>\p{Lu}</tt></td> * <td headers="matches">An uppercase letter (simple <a href="#ubc">category</a>)</td></tr> * <tr><td valign="top" headers="construct unicode"><tt>\p{Sc}</tt></td> * <td headers="matches">A currency symbol</td></tr> * <tr><td valign="top" headers="construct unicode"><tt>\P{InGreek}</tt></td> * <td headers="matches">Any character except one in the Greek block (negation)</td></tr> * <tr><td valign="top" headers="construct unicode"><tt>[\p{L}&&[^\p{Lu}]] </tt></td> * <td headers="matches">Any letter except an uppercase letter (subtraction)</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="bounds">Boundary matchers</th></tr> * * <tr><td valign="top" headers="construct bounds"><tt>^</tt></td> * <td headers="matches">The beginning of a line</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>$</tt></td> * <td headers="matches">The end of a line</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>\b</tt></td> * <td headers="matches">A word boundary</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>\B</tt></td> * <td headers="matches">A non-word boundary</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>\A</tt></td> * <td headers="matches">The beginning of the input</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>\G</tt></td> * <td headers="matches">The end of the previous match</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>\Z</tt></td> * <td headers="matches">The end of the input but for the final * <a href="#lt">terminator</a>, if any</td></tr> * <tr><td valign="top" headers="construct bounds"><tt>\z</tt></td> * <td headers="matches">The end of the input</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="greedy">Greedy quantifiers</th></tr> * * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>?</tt></td> * <td headers="matches"><i>X</i>, once or not at all</td></tr> * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>*</tt></td> * <td headers="matches"><i>X</i>, zero or more times</td></tr> * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>+</tt></td> * <td headers="matches"><i>X</i>, one or more times</td></tr> * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>{</tt><i>n</i><tt>}</tt></td> * <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr> * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>{</tt><i>n</i><tt>,}</tt></td> * <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr> * <tr><td valign="top" headers="construct greedy"><i>X</i><tt>{</tt><i>n</i><tt>,</tt><i>m</i><tt>}</tt></td> * <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="reluc">Reluctant quantifiers</th></tr> * * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>??</tt></td> * <td headers="matches"><i>X</i>, once or not at all</td></tr> * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>*?</tt></td> * <td headers="matches"><i>X</i>, zero or more times</td></tr> * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>+?</tt></td> * <td headers="matches"><i>X</i>, one or more times</td></tr> * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>{</tt><i>n</i><tt>}?</tt></td> * <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr> * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>{</tt><i>n</i><tt>,}?</tt></td> * <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr> * <tr><td valign="top" headers="construct reluc"><i>X</i><tt>{</tt><i>n</i><tt>,</tt><i>m</i><tt>}?</tt></td> * <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="poss">Possessive quantifiers</th></tr> * * <tr><td valign="top" headers="construct poss"><i>X</i><tt>?+</tt></td> * <td headers="matches"><i>X</i>, once or not at all</td></tr> * <tr><td valign="top" headers="construct poss"><i>X</i><tt>*+</tt></td> * <td headers="matches"><i>X</i>, zero or more times</td></tr> * <tr><td valign="top" headers="construct poss"><i>X</i><tt>++</tt></td> * <td headers="matches"><i>X</i>, one or more times</td></tr> * <tr><td valign="top" headers="construct poss"><i>X</i><tt>{</tt><i>n</i><tt>}+</tt></td> * <td headers="matches"><i>X</i>, exactly <i>n</i> times</td></tr> * <tr><td valign="top" headers="construct poss"><i>X</i><tt>{</tt><i>n</i><tt>,}+</tt></td> * <td headers="matches"><i>X</i>, at least <i>n</i> times</td></tr> * <tr><td valign="top" headers="construct poss"><i>X</i><tt>{</tt><i>n</i><tt>,</tt><i>m</i><tt>}+</tt></td> * <td headers="matches"><i>X</i>, at least <i>n</i> but not more than <i>m</i> times</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="logical">Logical operators</th></tr> * * <tr><td valign="top" headers="construct logical"><i>XY</i></td> * <td headers="matches"><i>X</i> followed by <i>Y</i></td></tr> * <tr><td valign="top" headers="construct logical"><i>X</i><tt>|</tt><i>Y</i></td> * <td headers="matches">Either <i>X</i> or <i>Y</i></td></tr> * <tr><td valign="top" headers="construct logical"><tt>(</tt><i>X</i><tt>)</tt></td> * <td headers="matches">X, as a <a href="#cg">capturing group</a></td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="backref">Back references</th></tr> * * <tr><td valign="bottom" headers="construct backref"><tt>\</tt><i>n</i></td> * <td valign="bottom" headers="matches">Whatever the <i>n</i><sup>th</sup> * <a href="#cg">capturing group</a> matched</td></tr> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="quot">Quotation</th></tr> * * <tr><td valign="top" headers="construct quot"><tt>\</tt></td> * <td headers="matches">Nothing, but quotes the following character</td></tr> * <tr><td valign="top" headers="construct quot"><tt>\Q</tt></td> * <td headers="matches">Nothing, but quotes all characters until <tt>\E</tt></td></tr> * <tr><td valign="top" headers="construct quot"><tt>\E</tt></td> * <td headers="matches">Nothing, but ends quoting started by <tt>\Q</tt></td></tr> * <!-- Metachars: !$()*+.<>?[\]^{|} --> * * <tr><th> </th></tr> * <tr align="left"><th colspan="2" id="special">Special constructs (non-capturing)</th></tr> * * <tr><td valign="top" headers="construct special"><tt>(?:</tt><i>X</i><tt>)</tt></td> * <td headers="matches"><i>X</i>, as a non-capturing group</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?idmsux-idmsux) </tt></td> * <td headers="matches">Nothing, but turns match flags <a href="#CASE_INSENSITIVE">i</a> * <a href="#UNIX_LINES">d</a> <a href="#MULTILINE">m</a> <a href="#DOTALL">s</a> * <a href="#UNICODE_CASE">u</a> <a href="#COMMENTS">x</a> on - off</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?idmsux-idmsux:</tt><i>X</i><tt>)</tt> </td> * <td headers="matches"><i>X</i>, as a <a href="#cg">non-capturing group</a> with the * given flags <a href="#CASE_INSENSITIVE">i</a> <a href="#UNIX_LINES">d</a> * <a href="#MULTILINE">m</a> <a href="#DOTALL">s</a> <a href="#UNICODE_CASE">u</a > * <a href="#COMMENTS">x</a> on - off</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?=</tt><i>X</i><tt>)</tt></td> * <td headers="matches"><i>X</i>, via zero-width positive lookahead</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?!</tt><i>X</i><tt>)</tt></td> * <td headers="matches"><i>X</i>, via zero-width negative lookahead</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?<=</tt><i>X</i><tt>)</tt></td> * <td headers="matches"><i>X</i>, via zero-width positive lookbehind</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?<!</tt><i>X</i><tt>)</tt></td> * <td headers="matches"><i>X</i>, via zero-width negative lookbehind</td></tr> * <tr><td valign="top" headers="construct special"><tt>(?></tt><i>X</i><tt>)</tt></td> * <td headers="matches"><i>X</i>, as an independent, non-capturing group</td></tr> * * </table> * * <hr> * * * <a name="bs"> * <h4> Backslashes, escapes, and quoting </h4> * * <p> The backslash character (<tt>'\'</tt>) serves to introduce escaped * constructs, as defined in the table above, as well as to quote characters * that otherwise would be interpreted as unescaped constructs. Thus the * expression <tt>\\</tt> matches a single backslash and <tt>\{</tt> matches a * left brace. * * <p> It is an error to use a backslash prior to any alphabetic character that * does not denote an escaped construct; these are reserved for future * extensions to the regular-expression language. A backslash may be used * prior to a non-alphabetic character regardless of whether that character is * part of an unescaped construct. * * <p> Backslashes within string literals in Java source code are interpreted * as required by the <a * href="http://java.sun.com/docs/books/jls">Java Language * Specification</a> as either <a * href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#100850">Unicode * escapes</a> or other <a * href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#101089">character * escapes</a>. It is therefore necessary to double backslashes in string * literals that represent regular expressions to protect them from * interpretation by the Java bytecode compiler. The string literal * <tt>"\b"</tt>, for example, matches a single backspace character when * interpreted as a regular expression, while <tt>"\\b"</tt> matches a * word boundary. The string literal <tt>"\(hello\)"</tt> is illegal * and leads to a compile-time error; in order to match the string * <tt>(hello)</tt> the string literal <tt>"\\(hello\\)"</tt> * must be used. * * <a name="cc"> * <h4> Character Classes </h4> * * <p> Character classes may appear within other character classes, and * may be composed by the union operator (implicit) and the intersection * operator (<tt>&&</tt>). * The union operator denotes a class that contains every character that is * in at least one of its operand classes. The intersection operator * denotes a class that contains every character that is in both of its * operand classes. * * <p> The precedence of character-class operators is as follows, from * highest to lowest: * * <blockquote><table border="0" cellpadding="1" cellspacing="0" * summary="Precedence of character class operators."> * <tr><th>1 </th> * <td>Literal escape </td> * <td><tt>\x</tt></td></tr> * <tr><th>2 </th> * <td>Grouping</td> * <td><tt>[...]</tt></td></tr> * <tr><th>3 </th> * <td>Range</td> * <td><tt>a-z</tt></td></tr> * <tr><th>4 </th> * <td>Union</td> * <td><tt>[a-e][i-u]</tt></td></tr> * <tr><th>5 </th> * <td>Intersection</td> * <td><tt>[a-z&&[aeiou]]</tt></td></tr> * </table></blockquote> * * <p> Note that a different set of metacharacters are in effect inside * a character class than outside a character class. For instance, the * regular expression <tt>.</tt> loses its special meaning inside a * character class, while the expression <tt>-</tt> becomes a range * forming metacharacter. * * <a name="lt"> * <h4> Line terminators </h4> * * <p> A <i>line terminator</i> is a one- or two-character sequence that marks * the end of a line of the input character sequence. The following are * recognized as line terminators: * * <ul> * * <li> A newline (line feed) character (<tt>'\n'</tt>), * * <li> A carriage-return character followed immediately by a newline * character (<tt>"\r\n"</tt>), * * <li> A standalone carriage-return character (<tt>'\r'</tt>), * * <li> A next-line character (<tt>'\u0085'</tt>), * * <li> A line-separator character (<tt>'\u2028'</tt>), or * * <li> A paragraph-separator character (<tt>'\u2029</tt>). * * </ul> * <p>If {@link #UNIX_LINES} mode is activated, then the only line terminators * recognized are newline characters. * * <p> The regular expression <tt>.</tt> matches any character except a line * terminator unless the {@link #DOTALL} flag is specified. * * <p> By default, the regular expressions <tt>^</tt> and <tt>$</tt> ignore * line terminators and only match at the beginning and the end, respectively, * of the entire input sequence. If {@link #MULTILINE} mode is activated then * <tt>^</tt> matches at the beginning of input and after any line terminator * except at the end of input. When in {@link #MULTILINE} mode <tt>$</tt> * matches just before a line terminator or the end of the input sequence. * * <a name="cg"> * <h4> Groups and capturing </h4> * * <p> Capturing groups are numbered by counting their opening parentheses from * left to right. In the expression <tt>((A)(B(C)))</tt>, for example, there * are four such groups: </p> * * <blockquote><table cellpadding=1 cellspacing=0 summary="Capturing group numberings"> * <tr><th>1 </th> * <td><tt>((A)(B(C)))</tt></td></tr> * <tr><th>2 </th> * <td><tt>(A)</tt></td></tr> * <tr><th>3 </th> * <td><tt>(B(C))</tt></td></tr> * <tr><th>4 </th> * <td><tt>(C)</tt></td></tr> * </table></blockquote> * * <p> Group zero always stands for the entire expression. * * <p> Capturing groups are so named because, during a match, each subsequence * of the input sequence that matches such a group is saved. The captured * subsequence may be used later in the expression, via a back reference, and * may also be retrieved from the matcher once the match operation is complete. * * <p> The captured input associated with a group is always the subsequence * that the group most recently matched. If a group is evaluated a second time * because of quantification then its previously-captured value, if any, will * be retained if the second evaluation fails. Matching the string * <tt>"aba"</tt> against the expression <tt>(a(b)?)+</tt>, for example, leaves * group two set to <tt>"b"</tt>. All captured input is discarded at the * beginning of each match. * * <p> Groups beginning with <tt>(?</tt> are pure, <i>non-capturing</i> groups * that do not capture text and do not count towards the group total. * * * <h4> Unicode support </h4> * * <p> This class is in conformance with Level 1 of <a * href="http://www.unicode.org/reports/tr18/"><i>Unicode Technical * Standard #18: Unicode Regular Expression Guidelines</i></a>, plus RL2.1 * Canonical Equivalents. * * <p> Unicode escape sequences such as <tt>\u2014</tt> in Java source code * are processed as described in <a * href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#100850">\u00A73.3</a> * of the Java Language Specification. Such escape sequences are also * implemented directly by the regular-expression parser so that Unicode * escapes can be used in expressions that are read from files or from the * keyboard. Thus the strings <tt>"\u2014"</tt> and <tt>"\\u2014"</tt>, * while not equal, compile into the same pattern, which matches the character * with hexadecimal value <tt>0x2014</tt>. * * <a name="ubc"> <p>Unicode blocks and categories are written with the * <tt>\p</tt> and <tt>\P</tt> constructs as in * Perl. <tt>\p{</tt><i>prop</i><tt>}</tt> matches if the input has the * property <i>prop</i>, while <tt>\P{</tt><i>prop</i><tt>}</tt> does not match if * the input has that property. Blocks are specified with the prefix * <tt>In</tt>, as in <tt>InMongolian</tt>. Categories may be specified with * the optional prefix <tt>Is</tt>: Both <tt>\p{L}</tt> and <tt>\p{IsL}</tt> * denote the category of Unicode letters. Blocks and categories can be used * both inside and outside of a character class. * * <p> The supported categories are those of * <a href="http://www.unicode.org/unicode/standard/standard.html"> * <i>The Unicode Standard</i></a> in the version specified by the * {@link java.lang.Character Character} class. The category names are those * defined in the Standard, both normative and informative. * The block names supported by <code>Pattern</code> are the valid block names * accepted and defined by * {@link java.lang.Character.UnicodeBlock#forName(String) UnicodeBlock.forName}. * * <a name="jcc"> <p>Categories that behave like the java.lang.Character * boolean is<i>methodname</i> methods (except for the deprecated ones) are * available through the same <tt>\p{</tt><i>prop</i><tt>}</tt> syntax where * the specified property has the name <tt>java<i>methodname</i></tt>. * * <h4> Comparison to Perl 5 </h4> * * <p>The <code>Pattern</code> engine performs traditional NFA-based matching * with ordered alternation as occurs in Perl 5. * * <p> Perl constructs not supported by this class: </p> * * <ul> * * <li><p> The conditional constructs <tt>(?{</tt><i>X</i><tt>})</tt> and * <tt>(?(</tt><i>condition</i><tt>)</tt><i>X</i><tt>|</tt><i>Y</i><tt>)</tt>, * </p></li> * * <li><p> The embedded code constructs <tt>(?{</tt><i>code</i><tt>})</tt> * and <tt>(??{</tt><i>code</i><tt>})</tt>,</p></li> * * <li><p> The embedded comment syntax <tt>(?#comment)</tt>, and </p></li> * * <li><p> The preprocessing operations <tt>\l</tt> <tt>\u</tt>, * <tt>\L</tt>, and <tt>\U</tt>. </p></li> * * </ul> * * <p> Constructs supported by this class but not by Perl: </p> * * <ul> * * <li><p> Possessive quantifiers, which greedily match as much as they can * and do not back off, even when doing so would allow the overall match to * succeed. </p></li> * * <li><p> Character-class union and intersection as described * <a href="#cc">above</a>.</p></li> * * </ul> * * <p> Notable differences from Perl: </p> * * <ul> * * <li><p> In Perl, <tt>\1</tt> through <tt>\9</tt> are always interpreted * as back references; a backslash-escaped number greater than <tt>9</tt> is * treated as a back reference if at least that many subexpressions exist, * otherwise it is interpreted, if possible, as an octal escape. In this * class octal escapes must always begin with a zero. In this class, * <tt>\1</tt> through <tt>\9</tt> are always interpreted as back * references, and a larger number is accepted as a back reference if at * least that many subexpressions exist at that point in the regular * expression, otherwise the parser will drop digits until the number is * smaller or equal to the existing number of groups or it is one digit. * </p></li> * * <li><p> Perl uses the <tt>g</tt> flag to request a match that resumes * where the last match left off. This functionality is provided implicitly * by the {@link Matcher} class: Repeated invocations of the {@link * Matcher#find find} method will resume where the last match left off, * unless the matcher is reset. </p></li> * * <li><p> In Perl, embedded flags at the top level of an expression affect * the whole expression. In this class, embedded flags always take effect * at the point at which they appear, whether they are at the top level or * within a group; in the latter case, flags are restored at the end of the * group just as in Perl. </p></li> * * <li><p> Perl is forgiving about malformed matching constructs, as in the * expression <tt>*a</tt>, as well as dangling brackets, as in the * expression <tt>abc]</tt>, and treats them as literals. This * class also accepts dangling brackets but is strict about dangling * metacharacters like +, ? and *, and will throw a * {@link PatternSyntaxException} if it encounters them. </p></li> * * </ul> * * * <p> For a more precise description of the behavior of regular expression * constructs, please see <a href="http://www.oreilly.com/catalog/regex3/"> * <i>Mastering Regular Expressions, 3nd Edition</i>, Jeffrey E. F. Friedl, * O'Reilly and Associates, 2006.</a> * </p> * * @see java.lang.String#split(String, int) * @see java.lang.String#split(String) * * @author Mike McCloskey * @author Mark Reinhold * @author JSR-51 Expert Group * @version 1.124, 07/03/15 * @since 1.4 * @spec JSR-51 */ public final class Pattern implements java.io.Serializable { /** * Regular expression modifier values. Instead of being passed as * arguments, they can also be passed as inline modifiers. * For example, the following statements have the same effect. * <pre> * RegExp r1 = RegExp.compile("abc", Pattern.I|Pattern.M); * RegExp r2 = RegExp.compile("(?im)abc", 0); * </pre> * * The flags are duplicated so that the familiar Perl match flag * names are available. */ /** * Enables Unix lines mode. * * <p> In this mode, only the <tt>'\n'</tt> line terminator is recognized * in the behavior of <tt>.</tt>, <tt>^</tt>, and <tt>$</tt>. * * <p> Unix lines mode can also be enabled via the embedded flag * expression <tt>(?d)</tt>. */ public static final int UNIX_LINES = 0x01; /** * Enables case-insensitive matching. * * <p> By default, case-insensitive matching assumes that only characters * in the US-ASCII charset are being matched. Unicode-aware * case-insensitive matching can be enabled by specifying the {@link * #UNICODE_CASE} flag in conjunction with this flag. * * <p> Case-insensitive matching can also be enabled via the embedded flag * expression <tt>(?i)</tt>. * * <p> Specifying this flag may impose a slight performance penalty. </p> */ public static final int CASE_INSENSITIVE = 0x02; /** * Permits whitespace and comments in pattern. * * <p> In this mode, whitespace is ignored, and embedded comments starting * with <tt>#</tt> are ignored until the end of a line. * * <p> Comments mode can also be enabled via the embedded flag * expression <tt>(?x)</tt>. */ public static final int COMMENTS = 0x04; /** * Enables multiline mode. * * <p> In multiline mode the expressions <tt>^</tt> and <tt>$</tt> match * just after or just before, respectively, a line terminator or the end of * the input sequence. By default these expressions only match at the * beginning and the end of the entire input sequence. * * <p> Multiline mode can also be enabled via the embedded flag * expression <tt>(?m)</tt>. </p> */ public static final int MULTILINE = 0x08; /** * Enables literal parsing of the pattern. * * <p> When this flag is specified then the input string that specifies * the pattern is treated as a sequence of literal characters. * Metacharacters or escape sequences in the input sequence will be * given no special meaning. * * <p>The flags CASE_INSENSITIVE and UNICODE_CASE retain their impact on * matching when used in conjunction with this flag. The other flags * become superfluous. * * <p> There is no embedded flag character for enabling literal parsing. * @since 1.5 */ public static final int LITERAL = 0x10; /** * Enables dotall mode. * * <p> In dotall mode, the expression <tt>.</tt> matches any character, * including a line terminator. By default this expression does not match * line terminators. * * <p> Dotall mode can also be enabled via the embedded flag * expression <tt>(?s)</tt>. (The <tt>s</tt> is a mnemonic for * "single-line" mode, which is what this is called in Perl.) </p> */ public static final int DOTALL = 0x20; /** * Enables Unicode-aware case folding. * * <p> When this flag is specified then case-insensitive matching, when * enabled by the {@link #CASE_INSENSITIVE} flag, is done in a manner * consistent with the Unicode Standard. By default, case-insensitive * matching assumes that only characters in the US-ASCII charset are being * matched. * * <p> Unicode-aware case folding can also be enabled via the embedded flag * expression <tt>(?u)</tt>. * * <p> Specifying this flag may impose a performance penalty. </p> */ public static final int UNICODE_CASE = 0x40; /** * Enables canonical equivalence. * * <p> When this flag is specified then two characters will be considered * to match if, and only if, their full canonical decompositions match. * The expression <tt>"a\u030A"</tt>, for example, will match the * string <tt>"\u00E5"</tt> when this flag is specified. By default, * matching does not take canonical equivalence into account. * * <p> There is no embedded flag character for enabling canonical * equivalence. * * <p> Specifying this flag may impose a performance penalty. </p> */ public static final int CANON_EQ = 0x80; /* Pattern has only two serialized components: The pattern string * and the flags, which are all that is needed to recompile the pattern * when it is deserialized. */ /** use serialVersionUID from Merlin b59 for interoperability */ private static final long serialVersionUID = 5073258162644648461L; /** * The original regular-expression pattern string. * * @serial */ private String pattern; /** * The original pattern flags. * * @serial */ private int flags; /** * Boolean indicating this Pattern is compiled; this is necessary in order * to lazily compile deserialized Patterns. */ private transient volatile boolean compiled = false; /** * The normalized pattern string. */ private transient String normalizedPattern; /** * The starting point of state machine for the find operation. This allows * a match to start anywhere in the input. */ transient Node root; /** * The root of object tree for a match operation. The pattern is matched * at the beginning. This may include a find that uses BnM or a First * node. */ transient Node matchRoot; /** * Temporary storage used by parsing pattern slice. */ transient int[] buffer; /** * Temporary storage used while parsing group references. */ transient GroupHead[] groupNodes; /** * Temporary null terminated code point array used by pattern compiling. */ private transient int[] temp; /** * The number of capturing groups in this Pattern. Used by matchers to * allocate storage needed to perform a match. */ transient int capturingGroupCount; /** * The local variable count used by parsing tree. Used by matchers to * allocate storage needed to perform a match. */ transient int localCount; /** * Index into the pattern string that keeps track of how much has been * parsed. */ private transient int cursor; /** * Holds the length of the pattern string. */ private transient int patternLength; /** * Compiles the given regular expression into a pattern. </p> * * @param regex * The expression to be compiled * * @throws PatternSyntaxException * If the expression's syntax is invalid */ public static Pattern compile(String regex) { return new Pattern(regex, 0); } /** * Compiles the given regular expression into a pattern with the given * flags. </p> * * @param regex * The expression to be compiled * * @param flags * Match flags, a bit mask that may include * {@link #CASE_INSENSITIVE}, {@link #MULTILINE}, {@link #DOTALL}, * {@link #UNICODE_CASE}, {@link #CANON_EQ}, {@link #UNIX_LINES}, * {@link #LITERAL} and {@link #COMMENTS} * * @throws IllegalArgumentException * If bit values other than those corresponding to the defined * match flags are set in <tt>flags</tt> * * @throws PatternSyntaxException * If the expression's syntax is invalid */ public static Pattern compile(String regex, int flags) { return new Pattern(regex, flags); } /** * Returns the regular expression from which this pattern was compiled. * </p> * * @return The source of this pattern */ public String pattern() { return pattern; } /** * <p>Returns the string representation of this pattern. This * is the regular expression from which this pattern was * compiled.</p> * * @return The string representation of this pattern * @since 1.5 */ public String toString() { return pattern; } /** * Creates a matcher that will match the given input against this pattern. * </p> * * @param input * The character sequence to be matched * * @return A new matcher for this pattern */ public Matcher matcher(CharSequence input) { if (!compiled) { synchronized(this) { if (!compiled) compile(); } } Matcher m = new Matcher(this, input); return m; } /** * Returns this pattern's match flags. </p> * * @return The match flags specified when this pattern was compiled */ public int flags() { return flags; } /** * Compiles the given regular expression and attempts to match the given * input against it. * * <p> An invocation of this convenience method of the form * * <blockquote><pre> * Pattern.matches(regex, input);</pre></blockquote> * * behaves in exactly the same way as the expression * * <blockquote><pre> * Pattern.compile(regex).matcher(input).matches()</pre></blockquote> * * <p> If a pattern is to be used multiple times, compiling it once and reusing * it will be more efficient than invoking this method each time. </p> * * @param regex * The expression to be compiled * * @param input * The character sequence to be matched * * @throws PatternSyntaxException * If the expression's syntax is invalid */ public static boolean matches(String regex, CharSequence input) { Pattern p = Pattern.compile(regex); Matcher m = p.matcher(input); return m.matches(); } /** * Splits the given input sequence around matches of this pattern. * * <p> The array returned by this method contains each substring of the * input sequence that is terminated by another subsequence that matches * this pattern or is terminated by the end of the input sequence. The * substrings in the array are in the order in which they occur in the * input. If this pattern does not match any subsequence of the input then * the resulting array has just one element, namely the input sequence in * string form. * * <p> The <tt>limit</tt> parameter controls the number of times the * pattern is applied and therefore affects the length of the resulting * array. If the limit <i>n</i> is greater than zero then the pattern * will be applied at most <i>n</i> - 1 times, the array's * length will be no greater than <i>n</i>, and the array's last entry * will contain all input beyond the last matched delimiter. If <i>n</i> * is non-positive then the pattern will be applied as many times as * possible and the array can have any length. If <i>n</i> is zero then * the pattern will be applied as many times as possible, the array can * have any length, and trailing empty strings will be discarded. * * <p> The input <tt>"boo:and:foo"</tt>, for example, yields the following * results with these parameters: * * <blockquote><table cellpadding=1 cellspacing=0 * summary="Split examples showing regex, limit, and result"> * <tr><th><P align="left"><i>Regex </i></th> * <th><P align="left"><i>Limit </i></th> * <th><P align="left"><i>Result </i></th></tr> * <tr><td align=center>:</td> * <td align=center>2</td> * <td><tt>{ "boo", "and:foo" }</tt></td></tr> * <tr><td align=center>:</td> * <td align=center>5</td> * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> * <tr><td align=center>:</td> * <td align=center>-2</td> * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> * <tr><td align=center>o</td> * <td align=center>5</td> * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> * <tr><td align=center>o</td> * <td align=center>-2</td> * <td><tt>{ "b", "", ":and:f", "", "" }</tt></td></tr> * <tr><td align=center>o</td> * <td align=center>0</td> * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> * </table></blockquote> * * * @param input * The character sequence to be split * * @param limit * The result threshold, as described above * * @return The array of strings computed by splitting the input * around matches of this pattern */ public String[] split(CharSequence input, int limit) { int index = 0; boolean matchLimited = limit > 0; ArrayList<String> matchList = new ArrayList<String>(); Matcher m = matcher(input); // Add segments before each match found while(m.find()) { if (!matchLimited || matchList.size() < limit - 1) { String match = input.subSequence(index, m.start()).toString(); matchList.add(match); index = m.end(); } else if (matchList.size() == limit - 1) { // last one String match = input.subSequence(index, input.length()).toString(); matchList.add(match); index = m.end(); } } // If no match was found, return this if (index == 0) return new String[] {input.toString()}; // Add remaining segment if (!matchLimited || matchList.size() < limit) matchList.add(input.subSequence(index, input.length()).toString()); // Construct result int resultSize = matchList.size(); if (limit == 0) while (resultSize > 0 && matchList.get(resultSize-1).equals("")) resultSize--; String[] result = new String[resultSize]; return matchList.subList(0, resultSize).toArray(result); } /** * Splits the given input sequence around matches of this pattern. * * <p> This method works as if by invoking the two-argument {@link * #split(java.lang.CharSequence, int) split} method with the given input * sequence and a limit argument of zero. Trailing empty strings are * therefore not included in the resulting array. </p> * * <p> The input <tt>"boo:and:foo"</tt>, for example, yields the following * results with these expressions: * * <blockquote><table cellpadding=1 cellspacing=0 * summary="Split examples showing regex and result"> * <tr><th><P align="left"><i>Regex </i></th> * <th><P align="left"><i>Result</i></th></tr> * <tr><td align=center>:</td> * <td><tt>{ "boo", "and", "foo" }</tt></td></tr> * <tr><td align=center>o</td> * <td><tt>{ "b", "", ":and:f" }</tt></td></tr> * </table></blockquote> * * * @param input * The character sequence to be split * * @return The array of strings computed by splitting the input * around matches of this pattern */ public String[] split(CharSequence input) { return split(input, 0); } /** * Returns a literal pattern <code>String</code> for the specified * <code>String</code>. * * <p>This method produces a <code>String</code> that can be used to * create a <code>Pattern</code> that would match the string * <code>s</code> as if it were a literal pattern.</p> Metacharacters * or escape sequences in the input sequence will be given no special * meaning. * * @param s The string to be literalized * @return A literal string replacement * @since 1.5 */ public static String quote(String s) { int slashEIndex = s.indexOf("\\E"); if (slashEIndex == -1) return "\\Q" + s + "\\E"; StringBuilder sb = new StringBuilder(s.length() * 2); sb.append("\\Q"); slashEIndex = 0; int current = 0; while ((slashEIndex = s.indexOf("\\E", current)) != -1) { sb.append(s.substring(current, slashEIndex)); current = slashEIndex + 2; sb.append("\\E\\\\E\\Q"); } sb.append(s.substring(current, s.length())); sb.append("\\E"); return sb.toString(); } /** * Recompile the Pattern instance from a stream. The original pattern * string is read in and the object tree is recompiled from it. */ private void readObject(java.io.ObjectInputStream s) throws java.io.IOException, ClassNotFoundException { // Read in all fields s.defaultReadObject(); // Initialize counts capturingGroupCount = 1; localCount = 0; // if length > 0, the Pattern is lazily compiled compiled = false; if (pattern.length() == 0) { root = new Start(lastAccept); matchRoot = lastAccept; compiled = true; } } /** * This private constructor is used to create all Patterns. The pattern * string and match flags are all that is needed to completely describe * a Pattern. An empty pattern string results in an object tree with * only a Start node and a LastNode node. */ private Pattern(String p, int f) { pattern = p; flags = f; // Reset group index count capturingGroupCount = 1; localCount = 0; if (pattern.length() > 0) { compile(); } else { root = new Start(lastAccept); matchRoot = lastAccept; } } /** * The pattern is converted to normalizedD form and then a pure group * is constructed to match canonical equivalences of the characters. */ private void normalize() { boolean inCharClass = false; int lastCodePoint = -1; // Convert pattern into normalizedD form normalizedPattern = Normalizer.normalize(pattern, Normalizer.Form.NFD); patternLength = normalizedPattern.length(); // Modify pattern to match canonical equivalences StringBuilder newPattern = new StringBuilder(patternLength); for(int i=0; i<patternLength; ) { int c = normalizedPattern.codePointAt(i); StringBuilder sequenceBuffer; if ((Character.getType(c) == Character.NON_SPACING_MARK) && (lastCodePoint != -1)) { sequenceBuffer = new StringBuilder(); sequenceBuffer.appendCodePoint(lastCodePoint); sequenceBuffer.appendCodePoint(c); while(Character.getType(c) == Character.NON_SPACING_MARK) { i += Character.charCount(c); if (i >= patternLength) break; c = normalizedPattern.codePointAt(i); sequenceBuffer.appendCodePoint(c); } String ea = produceEquivalentAlternation( sequenceBuffer.toString()); newPattern.setLength(newPattern.length()-Character.charCount(lastCodePoint)); newPattern.append("(?:").append(ea).append(")"); } else if (c == '[' && lastCodePoint != '\\') { i = normalizeCharClass(newPattern, i); } else { newPattern.appendCodePoint(c); } lastCodePoint = c; i += Character.charCount(c); } normalizedPattern = newPattern.toString(); } /** * Complete the character class being parsed and add a set * of alternations to it that will match the canonical equivalences * of the characters within the class. */ private int normalizeCharClass(StringBuilder newPattern, int i) { StringBuilder charClass = new StringBuilder(); StringBuilder eq = null; int lastCodePoint = -1; String result; i++; charClass.append("["); while(true) { int c = normalizedPattern.codePointAt(i); StringBuilder sequenceBuffer; if (c == ']' && lastCodePoint != '\\') { charClass.append((char)c); break; } else if (Character.getType(c) == Character.NON_SPACING_MARK) { sequenceBuffer = new StringBuilder(); sequenceBuffer.appendCodePoint(lastCodePoint); while(Character.getType(c) == Character.NON_SPACING_MARK) { sequenceBuffer.appendCodePoint(c); i += Character.charCount(c); if (i >= normalizedPattern.length()) break; c = normalizedPattern.codePointAt(i); } String ea = produceEquivalentAlternation( sequenceBuffer.toString()); charClass.setLength(charClass.length()-Character.charCount(lastCodePoint)); if (eq == null) eq = new StringBuilder(); eq.append('|'); eq.append(ea); } else { charClass.appendCodePoint(c); i++; } if (i == normalizedPattern.length()) throw error("Unclosed character class"); lastCodePoint = c; } if (eq != null) { result = "(?:"+charClass.toString()+eq.toString()+")"; } else { result = charClass.toString(); } newPattern.append(result); return i; } /** * Given a specific sequence composed of a regular character and * combining marks that follow it, produce the alternation that will * match all canonical equivalences of that sequence. */ private String produceEquivalentAlternation(String source) { int len = countChars(source, 0, 1); if (source.length() == len) // source has one character. return source; String base = source.substring(0,len); String combiningMarks = source.substring(len); String[] perms = producePermutations(combiningMarks); StringBuilder result = new StringBuilder(source); // Add combined permutations for(int x=0; x<perms.length; x++) { String next = base + perms[x]; if (x>0) result.append("|"+next); next = composeOneStep(next); if (next != null) result.append("|"+produceEquivalentAlternation(next)); } return result.toString(); } /** * Returns an array of strings that have all the possible * permutations of the characters in the input string. * This is used to get a list of all possible orderings * of a set of combining marks. Note that some of the permutations * are invalid because of combining class collisions, and these * possibilities must be removed because they are not canonically * equivalent. */ private String[] producePermutations(String input) { if (input.length() == countChars(input, 0, 1)) return new String[] {input}; if (input.length() == countChars(input, 0, 2)) { int c0 = Character.codePointAt(input, 0); int c1 = Character.codePointAt(input, Character.charCount(c0)); if (getClass(c1) == getClass(c0)) { return new String[] {input}; } String[] result = new String[2]; result[0] = input; StringBuilder sb = new StringBuilder(2); sb.appendCodePoint(c1); sb.appendCodePoint(c0); result[1] = sb.toString(); return result; } int length = 1; int nCodePoints = countCodePoints(input); for(int x=1; x<nCodePoints; x++) length = length * (x+1); String[] temp = new String[length]; int combClass[] = new int[nCodePoints]; for(int x=0, i=0; x<nCodePoints; x++) { int c = Character.codePointAt(input, i); combClass[x] = getClass(c); i += Character.charCount(c); } // For each char, take it out and add the permutations // of the remaining chars int index = 0; int len; // offset maintains the index in code units. loop: for(int x=0, offset=0; x<nCodePoints; x++, offset+=len) { len = countChars(input, offset, 1); boolean skip = false; for(int y=x-1; y>=0; y--) { if (combClass[y] == combClass[x]) { continue loop; } } StringBuilder sb = new StringBuilder(input); String otherChars = sb.delete(offset, offset+len).toString(); String[] subResult = producePermutations(otherChars); String prefix = input.substring(offset, offset+len); for(int y=0; y<subResult.length; y++) temp[index++] = prefix + subResult[y]; } String[] result = new String[index]; for (int x=0; x<index; x++) result[x] = temp[x]; return result; } private int getClass(int c) { return sun.text.Normalizer.getCombiningClass(c); } /** * Attempts to compose input by combining the first character * with the first combining mark following it. Returns a String * that is the composition of the leading character with its first * combining mark followed by the remaining combining marks. Returns * null if the first two characters cannot be further composed. */ private String composeOneStep(String input) { int len = countChars(input, 0, 2); String firstTwoCharacters = input.substring(0, len); String result = Normalizer.normalize(firstTwoCharacters, Normalizer.Form.NFC); if (result.equals(firstTwoCharacters)) return null; else { String remainder = input.substring(len); return result + remainder; } } /** * Preprocess any \Q...\E sequences in `temp', meta-quoting them. * See the description of `quotemeta' in perlfunc(1). */ private void RemoveQEQuoting() { final int pLen = patternLength; int i = 0; while (i < pLen-1) { if (temp[i] != '\\') i += 1; else if (temp[i + 1] != 'Q') i += 2; else break; } if (i >= pLen - 1) // No \Q sequence found return; int j = i; i += 2; int[] newtemp = new int[j + 2*(pLen-i) + 2]; System.arraycopy(temp, 0, newtemp, 0, j); boolean inQuote = true; while (i < pLen) { int c = temp[i++]; if (! ASCII.isAscii(c) || ASCII.isAlnum(c)) { newtemp[j++] = c; } else if (c != '\\') { if (inQuote) newtemp[j++] = '\\'; newtemp[j++] = c; } else if (inQuote) { if (temp[i] == 'E') { i++; inQuote = false; } else { newtemp[j++] = '\\'; newtemp[j++] = '\\'; } } else { if (temp[i] == 'Q') { i++; inQuote = true; } else { newtemp[j++] = c; if (i != pLen) newtemp[j++] = temp[i++]; } } } patternLength = j; temp = Arrays.copyOf(newtemp, j + 2); // double zero termination } /** * Copies regular expression to an int array and invokes the parsing * of the expression which will create the object tree. */ private void compile() { // Handle canonical equivalences if (has(CANON_EQ) && !has(LITERAL)) { normalize(); } else { normalizedPattern = pattern; } patternLength = normalizedPattern.length(); // Copy pattern to int array for convenience // Use double zero to terminate pattern temp = new int[patternLength + 2]; boolean hasSupplementary = false; int c, count = 0; // Convert all chars into code points for (int x = 0; x < patternLength; x += Character.charCount(c)) { c = normalizedPattern.codePointAt(x); if (isSupplementary(c)) { hasSupplementary = true; } temp[count++] = c; } patternLength = count; // patternLength now in code points if (! has(LITERAL)) RemoveQEQuoting(); // Allocate all temporary objects here. buffer = new int[32]; groupNodes = new GroupHead[10]; if (has(LITERAL)) { // Literal pattern handling matchRoot = newSlice(temp, patternLength, hasSupplementary); matchRoot.next = lastAccept; } else { // Start recursive descent parsing matchRoot = expr(lastAccept); // Check extra pattern characters if (patternLength != cursor) { if (peek() == ')') { throw error("Unmatched closing ')'"); } else { throw error("Unexpected internal error"); } } } // Peephole optimization if (matchRoot instanceof Slice) { root = BnM.optimize(matchRoot); if (root == matchRoot) { root = hasSupplementary ? new StartS(matchRoot) : new Start(matchRoot); } } else if (matchRoot instanceof Begin || matchRoot instanceof First) { root = matchRoot; } else { root = hasSupplementary ? new StartS(matchRoot) : new Start(matchRoot); } // Release temporary storage temp = null; buffer = null; groupNodes = null; patternLength = 0; compiled = true; } /** * Used to print out a subtree of the Pattern to help with debugging. */ private static void printObjectTree(Node node) { while(node != null) { if (node instanceof Prolog) { System.out.println(node); printObjectTree(((Prolog)node).loop); System.out.println("**** end contents prolog loop"); } else if (node instanceof Loop) { System.out.println(node); printObjectTree(((Loop)node).body); System.out.println("**** end contents Loop body"); } else if (node instanceof Curly) { System.out.println(node); printObjectTree(((Curly)node).atom); System.out.println("**** end contents Curly body"); } else if (node instanceof GroupCurly) { System.out.println(node); printObjectTree(((GroupCurly)node).atom); System.out.println("**** end contents GroupCurly body"); } else if (node instanceof GroupTail) { System.out.println(node); System.out.println("Tail next is "+node.next); return; } else { System.out.println(node); } node = node.next; if (node != null) System.out.println("->next:"); if (node == Pattern.accept) { System.out.println("Accept Node"); node = null; } } } /** * Used to accumulate information about a subtree of the object graph * so that optimizations can be applied to the subtree. */ static final class TreeInfo { int minLength; int maxLength; boolean maxValid; boolean deterministic; TreeInfo() { reset(); } void reset() { minLength = 0; maxLength = 0; maxValid = true; deterministic = true; } } /* * The following private methods are mainly used to improve the * readability of the code. In order to let the Java compiler easily * inline them, we should not put many assertions or error checks in them. */ /** * Indicates whether a particular flag is set or not. */ private boolean has(int f) { return (flags & f) != 0; } /** * Match next character, signal error if failed. */ private void accept(int ch, String s) { int testChar = temp[cursor++]; if (has(COMMENTS)) testChar = parsePastWhitespace(testChar); if (ch != testChar) { throw error(s); } } /** * Mark the end of pattern with a specific character. */ private void mark(int c) { temp[patternLength] = c; } /** * Peek the next character, and do not advance the cursor. */ private int peek() { int ch = temp[cursor]; if (has(COMMENTS)) ch = peekPastWhitespace(ch); return ch; } /** * Read the next character, and advance the cursor by one. */ private int read() { int ch = temp[cursor++]; if (has(COMMENTS)) ch = parsePastWhitespace(ch); return ch; } /** * Read the next character, and advance the cursor by one, * ignoring the COMMENTS setting */ private int readEscaped() { int ch = temp[cursor++]; return ch; } /** * Advance the cursor by one, and peek the next character. */ private int next() { int ch = temp[++cursor]; if (has(COMMENTS)) ch = peekPastWhitespace(ch); return ch; } /** * Advance the cursor by one, and peek the next character, * ignoring the COMMENTS setting */ private int nextEscaped() { int ch = temp[++cursor]; return ch; } /** * If in xmode peek past whitespace and comments. */ private int peekPastWhitespace(int ch) { while (ASCII.isSpace(ch) || ch == '#') { while (ASCII.isSpace(ch)) ch = temp[++cursor]; if (ch == '#') { ch = peekPastLine(); } } return ch; } /** * If in xmode parse past whitespace and comments. */ private int parsePastWhitespace(int ch) { while (ASCII.isSpace(ch) || ch == '#') { while (ASCII.isSpace(ch)) ch = temp[cursor++]; if (ch == '#') ch = parsePastLine(); } return ch; } /** * xmode parse past comment to end of line. */ private int parsePastLine() { int ch = temp[cursor++]; while (ch != 0 && !isLineSeparator(ch)) ch = temp[cursor++]; return ch; } /** * xmode peek past comment to end of line. */ private int peekPastLine() { int ch = temp[++cursor]; while (ch != 0 && !isLineSeparator(ch)) ch = temp[++cursor]; return ch; } /** * Determines if character is a line separator in the current mode */ private boolean isLineSeparator(int ch) { if (has(UNIX_LINES)) { return ch == '\n'; } else { return (ch == '\n' || ch == '\r' || (ch|1) == '\u2029' || ch == '\u0085'); } } /** * Read the character after the next one, and advance the cursor by two. */ private int skip() { int i = cursor; int ch = temp[i+1]; cursor = i + 2; return ch; } /** * Unread one next character, and retreat cursor by one. */ private void unread() { cursor--; } /** * Internal method used for handling all syntax errors. The pattern is * displayed with a pointer to aid in locating the syntax error. */ private PatternSyntaxException error(String s) { return new PatternSyntaxException(s, normalizedPattern, cursor - 1); } /** * Determines if there is any supplementary character or unpaired * surrogate in the specified range. */ private boolean findSupplementary(int start, int end) { for (int i = start; i < end; i++) { if (isSupplementary(temp[i])) return true; } return false; } /** * Determines if the specified code point is a supplementary * character or unpaired surrogate. */ private static final boolean isSupplementary(int ch) { return ch >= Character.MIN_SUPPLEMENTARY_CODE_POINT || isSurrogate(ch); } /** * The following methods handle the main parsing. They are sorted * according to their precedence order, the lowest one first. */ /** * The expression is parsed with branch nodes added for alternations. * This may be called recursively to parse sub expressions that may * contain alternations. */ private Node expr(Node end) { Node prev = null; Node firstTail = null; Node branchConn = null; for (;;) { Node node = sequence(end); Node nodeTail = root; //double return if (prev == null) { prev = node; firstTail = nodeTail; } else { // Branch if (branchConn == null) { branchConn = new BranchConn(); branchConn.next = end; } if (node == end) { // if the node returned from sequence() is "end" // we have an empty expr, set a null atom into // the branch to indicate to go "next" directly. node = null; } else { // the "tail.next" of each atom goes to branchConn nodeTail.next = branchConn; } if (prev instanceof Branch) { ((Branch)prev).add(node); } else { if (prev == end) { prev = null; } else { // replace the "end" with "branchConn" at its tail.next // when put the "prev" into the branch as the first atom. firstTail.next = branchConn; } prev = new Branch(prev, node, branchConn); } } if (peek() != '|') { return prev; } next(); } } /** * Parsing of sequences between alternations. */ private Node sequence(Node end) { Node head = null; Node tail = null; Node node = null; LOOP: for (;;) { int ch = peek(); switch (ch) { case '(': // Because group handles its own closure, // we need to treat it differently node = group0(); // Check for comment or flag group if (node == null) continue; if (head == null) head = node; else tail.next = node; // Double return: Tail was returned in root tail = root; continue; case '[': node = clazz(true); break; case '\\': ch = nextEscaped(); if (ch == 'p' || ch == 'P') { boolean oneLetter = true; boolean comp = (ch == 'P'); ch = next(); // Consume { if present if (ch != '{') { unread(); } else { oneLetter = false; } node = family(oneLetter).maybeComplement(comp); } else { unread(); node = atom(); } break; case '^': next(); if (has(MULTILINE)) { if (has(UNIX_LINES)) node = new UnixCaret(); else node = new Caret(); } else { node = new Begin(); } break; case '$': next(); if (has(UNIX_LINES)) node = new UnixDollar(has(MULTILINE)); else node = new Dollar(has(MULTILINE)); break; case '.': next(); if (has(DOTALL)) { node = new All(); } else { if (has(UNIX_LINES)) node = new UnixDot(); else { node = new Dot(); } } break; case '|': case ')': break LOOP; case ']': // Now interpreting dangling ] and } as literals case '}': node = atom(); break; case '?': case '*': case '+': next(); throw error("Dangling meta character '" + ((char)ch) + "'"); case 0: if (cursor >= patternLength) { break LOOP; } // Fall through default: node = atom(); break; } node = closure(node); if (head == null) { head = tail = node; } else { tail.next = node; tail = node; } } if (head == null) { return end; } tail.next = end; root = tail; //double return return head; } /** * Parse and add a new Single or Slice. */ private Node atom() { int first = 0; int prev = -1; boolean hasSupplementary = false; int ch = peek(); for (;;) { switch (ch) { case '*': case '+': case '?': case '{': if (first > 1) { cursor = prev; // Unwind one character first--; } break; case '$': case '.': case '^': case '(': case '[': case '|': case ')': break; case '\\': ch = nextEscaped(); if (ch == 'p' || ch == 'P') { // Property if (first > 0) { // Slice is waiting; handle it first unread(); break; } else { // No slice; just return the family node boolean comp = (ch == 'P'); boolean oneLetter = true; ch = next(); // Consume { if present if (ch != '{') unread(); else oneLetter = false; return family(oneLetter).maybeComplement(comp); } } unread(); prev = cursor; ch = escape(false, first == 0); if (ch >= 0) { append(ch, first); first++; if (isSupplementary(ch)) { hasSupplementary = true; } ch = peek(); continue; } else if (first == 0) { return root; } // Unwind meta escape sequence cursor = prev; break; case 0: if (cursor >= patternLength) { break; } // Fall through default: prev = cursor; append(ch, first); first++; if (isSupplementary(ch)) { hasSupplementary = true; } ch = next(); continue; } break; } if (first == 1) { return newSingle(buffer[0]); } else { return newSlice(buffer, first, hasSupplementary); } } private void append(int ch, int len) { if (len >= buffer.length) { int[] tmp = new int[len+len]; System.arraycopy(buffer, 0, tmp, 0, len); buffer = tmp; } buffer[len] = ch; } /** * Parses a backref greedily, taking as many numbers as it * can. The first digit is always treated as a backref, but * multi digit numbers are only treated as a backref if at * least that many backrefs exist at this point in the regex. */ private Node ref(int refNum) { boolean done = false; while(!done) { int ch = peek(); switch(ch) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': int newRefNum = (refNum * 10) + (ch - '0'); // Add another number if it doesn't make a group // that doesn't exist if (capturingGroupCount - 1 < newRefNum) { done = true; break; } refNum = newRefNum; read(); break; default: done = true; break; } } if (has(CASE_INSENSITIVE)) return new CIBackRef(refNum, has(UNICODE_CASE)); else return new BackRef(refNum); } /** * Parses an escape sequence to determine the actual value that needs * to be matched. * If -1 is returned and create was true a new object was added to the tree * to handle the escape sequence. * If the returned value is greater than zero, it is the value that * matches the escape sequence. */ private int escape(boolean inclass, boolean create) { int ch = skip(); switch (ch) { case '0': return o(); case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': if (inclass) break; if (create) { root = ref((ch - '0')); } return -1; case 'A': if (inclass) break; if (create) root = new Begin(); return -1; case 'B': if (inclass) break; if (create) root = new Bound(Bound.NONE); return -1; case 'C': break; case 'D': if (create) root = new Ctype(ASCII.DIGIT).complement(); return -1; case 'E': case 'F': break; case 'G': if (inclass) break; if (create) root = new LastMatch(); return -1; case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': break; case 'S': if (create) root = new Ctype(ASCII.SPACE).complement(); return -1; case 'T': case 'U': case 'V': break; case 'W': if (create) root = new Ctype(ASCII.WORD).complement(); return -1; case 'X': case 'Y': break; case 'Z': if (inclass) break; if (create) { if (has(UNIX_LINES)) root = new UnixDollar(false); else root = new Dollar(false); } return -1; case 'a': return '\007'; case 'b': if (inclass) break; if (create) root = new Bound(Bound.BOTH); return -1; case 'c': return c(); case 'd': if (create) root = new Ctype(ASCII.DIGIT); return -1; case 'e': return '\033'; case 'f': return '\f'; case 'g': case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': break; case 'n': return '\n'; case 'o': case 'p': case 'q': break; case 'r': return '\r'; case 's': if (create) root = new Ctype(ASCII.SPACE); return -1; case 't': return '\t'; case 'u': return u(); case 'v': return '\013'; case 'w': if (create) root = new Ctype(ASCII.WORD); return -1; case 'x': return x(); case 'y': break; case 'z': if (inclass) break; if (create) root = new End(); return -1; default: return ch; } throw error("Illegal/unsupported escape sequence"); } /** * Parse a character class, and return the node that matches it. * * Consumes a ] on the way out if consume is true. Usually consume * is true except for the case of [abc&&def] where def is a separate * right hand node with "understood" brackets. */ private CharProperty clazz(boolean consume) { CharProperty prev = null; CharProperty node = null; BitClass bits = new BitClass(); boolean include = true; boolean firstInClass = true; int ch = next(); for (;;) { switch (ch) { case '^': // Negates if first char in a class, otherwise literal if (firstInClass) { if (temp[cursor-1] != '[') break; ch = next(); include = !include; continue; } else { // ^ not first in class, treat as literal break; } case '[': firstInClass = false; node = clazz(true); if (prev == null) prev = node; else prev = union(prev, node); ch = peek(); continue; case '&': firstInClass = false; ch = next(); if (ch == '&') { ch = next(); CharProperty rightNode = null; while (ch != ']' && ch != '&') { if (ch == '[') { if (rightNode == null) rightNode = clazz(true); else rightNode = union(rightNode, clazz(true)); } else { // abc&&def unread(); rightNode = clazz(false); } ch = peek(); } if (rightNode != null) node = rightNode; if (prev == null) { if (rightNode == null) throw error("Bad class syntax"); else prev = rightNode; } else { prev = intersection(prev, node); } } else { // treat as a literal & unread(); break; } continue; case 0: firstInClass = false; if (cursor >= patternLength) throw error("Unclosed character class"); break; case ']': firstInClass = false; if (prev != null) { if (consume) next(); return prev; } break; default: firstInClass = false; break; } node = range(bits); if (include) { if (prev == null) { prev = node; } else { if (prev != node) prev = union(prev, node); } } else { if (prev == null) { prev = node.complement(); } else { if (prev != node) prev = setDifference(prev, node); } } ch = peek(); } } private CharProperty bitsOrSingle(BitClass bits, int ch) { /* Bits can only handle codepoints in [u+0000-u+00ff] range. Use "single" node instead of bits when dealing with unicode case folding for codepoints listed below. (1)Uppercase out of range: u+00ff, u+00b5 toUpperCase(u+00ff) -> u+0178 toUpperCase(u+00b5) -> u+039c (2)LatinSmallLetterLongS u+17f toUpperCase(u+017f) -> u+0053 (3)LatinSmallLetterDotlessI u+131 toUpperCase(u+0131) -> u+0049 (4)LatinCapitalLetterIWithDotAbove u+0130 toLowerCase(u+0130) -> u+0069 (5)KelvinSign u+212a toLowerCase(u+212a) ==> u+006B (6)AngstromSign u+212b toLowerCase(u+212b) ==> u+00e5 */ int d; if (ch < 256 && !(has(CASE_INSENSITIVE) && has(UNICODE_CASE) && (ch == 0xff || ch == 0xb5 || ch == 0x49 || ch == 0x69 || //I and i ch == 0x53 || ch == 0x73 || //S and s ch == 0x4b || ch == 0x6b || //K and k ch == 0xc5 || ch == 0xe5))) //A+ring return bits.add(ch, flags()); return newSingle(ch); } /** * Parse a single character or a character range in a character class * and return its representative node. */ private CharProperty range(BitClass bits) { int ch = peek(); if (ch == '\\') { ch = nextEscaped(); if (ch == 'p' || ch == 'P') { // A property boolean comp = (ch == 'P'); boolean oneLetter = true; // Consume { if present ch = next(); if (ch != '{') unread(); else oneLetter = false; return family(oneLetter).maybeComplement(comp); } else { // ordinary escape unread(); ch = escape(true, true); if (ch == -1) return (CharProperty) root; } } else { ch = single(); } if (ch >= 0) { if (peek() == '-') { int endRange = temp[cursor+1]; if (endRange == '[') { return bitsOrSingle(bits, ch); } if (endRange != ']') { next(); int m = single(); if (m < ch) throw error("Illegal character range"); if (has(CASE_INSENSITIVE)) return caseInsensitiveRangeFor(ch, m); else return rangeFor(ch, m); } } return bitsOrSingle(bits, ch); } throw error("Unexpected character '"+((char)ch)+"'"); } private int single() { int ch = peek(); switch (ch) { case '\\': return escape(true, false); default: next(); return ch; } } /** * Parses a Unicode character family and returns its representative node. */ private CharProperty family(boolean singleLetter) { next(); String name; if (singleLetter) { int c = temp[cursor]; if (!Character.isSupplementaryCodePoint(c)) { name = String.valueOf((char)c); } else { name = new String(temp, cursor, 1); } read(); } else { int i = cursor; mark('}'); while(read() != '}') { } mark('\000'); int j = cursor; if (j > patternLength) throw error("Unclosed character family"); if (i + 1 >= j) throw error("Empty character family"); name = new String(temp, i, j-i-1); } if (name.startsWith("In")) { return unicodeBlockPropertyFor(name.substring(2)); } else { if (name.startsWith("Is")) name = name.substring(2); return charPropertyNodeFor(name); } } /** * Returns a CharProperty matching all characters in a UnicodeBlock. */ private CharProperty unicodeBlockPropertyFor(String name) { final Character.UnicodeBlock block; try { block = Character.UnicodeBlock.forName(name); } catch (IllegalArgumentException iae) { throw error("Unknown character block name {" + name + "}"); } return new CharProperty() { boolean isSatisfiedBy(int ch) { return block == Character.UnicodeBlock.of(ch);}}; } /** * Returns a CharProperty matching all characters in a named property. */ private CharProperty charPropertyNodeFor(String name) { CharProperty p = CharPropertyNames.charPropertyFor(name); if (p == null) throw error("Unknown character property name {" + name + "}"); return p; } /** * Parses a group and returns the head node of a set of nodes that process * the group. Sometimes a double return system is used where the tail is * returned in root. */ private Node group0() { boolean capturingGroup = false; Node head = null; Node tail = null; int save = flags; root = null; int ch = next(); if (ch == '?') { ch = skip(); switch (ch) { case ':': // (?:xxx) pure group head = createGroup(true); tail = root; head.next = expr(tail); break; case '=': // (?=xxx) and (?!xxx) lookahead case '!': head = createGroup(true); tail = root; head.next = expr(tail); if (ch == '=') { head = tail = new Pos(head); } else { head = tail = new Neg(head); } break; case '>': // (?>xxx) independent group head = createGroup(true); tail = root; head.next = expr(tail); head = tail = new Ques(head, INDEPENDENT); break; case '<': // (?<xxx) look behind ch = read(); int start = cursor; head = createGroup(true); tail = root; head.next = expr(tail); tail.next = lookbehindEnd; TreeInfo info = new TreeInfo(); head.study(info); if (info.maxValid == false) { throw error("Look-behind group does not have " + "an obvious maximum length"); } boolean hasSupplementary = findSupplementary(start, patternLength); if (ch == '=') { head = tail = (hasSupplementary ? new BehindS(head, info.maxLength, info.minLength) : new Behind(head, info.maxLength, info.minLength)); } else if (ch == '!') { head = tail = (hasSupplementary ? new NotBehindS(head, info.maxLength, info.minLength) : new NotBehind(head, info.maxLength, info.minLength)); } else { throw error("Unknown look-behind group"); } break; case '$': case '@': throw error("Unknown group type"); default: // (?xxx:) inlined match flags unread(); addFlag(); ch = read(); if (ch == ')') { return null; // Inline modifier only } if (ch != ':') { throw error("Unknown inline modifier"); } head = createGroup(true); tail = root; head.next = expr(tail); break; } } else { // (xxx) a regular group capturingGroup = true; head = createGroup(false); tail = root; head.next = expr(tail); } accept(')', "Unclosed group"); flags = save; // Check for quantifiers Node node = closure(head); if (node == head) { // No closure root = tail; return node; // Dual return } if (head == tail) { // Zero length assertion root = node; return node; // Dual return } if (node instanceof Ques) { Ques ques = (Ques) node; if (ques.type == POSSESSIVE) { root = node; return node; } tail.next = new BranchConn(); tail = tail.next; if (ques.type == GREEDY) { head = new Branch(head, null, tail); } else { // Reluctant quantifier head = new Branch(null, head, tail); } root = tail; return head; } else if (node instanceof Curly) { Curly curly = (Curly) node; if (curly.type == POSSESSIVE) { root = node; return node; } // Discover if the group is deterministic TreeInfo info = new TreeInfo(); if (head.study(info)) { // Deterministic GroupTail temp = (GroupTail) tail; head = root = new GroupCurly(head.next, curly.cmin, curly.cmax, curly.type, ((GroupTail)tail).localIndex, ((GroupTail)tail).groupIndex, capturingGroup); return head; } else { // Non-deterministic int temp = ((GroupHead) head).localIndex; Loop loop; if (curly.type == GREEDY) loop = new Loop(this.localCount, temp); else // Reluctant Curly loop = new LazyLoop(this.localCount, temp); Prolog prolog = new Prolog(loop); this.localCount += 1; loop.cmin = curly.cmin; loop.cmax = curly.cmax; loop.body = head; tail.next = loop; root = loop; return prolog; // Dual return } } throw error("Internal logic error"); } /** * Create group head and tail nodes using double return. If the group is * created with anonymous true then it is a pure group and should not * affect group counting. */ private Node createGroup(boolean anonymous) { int localIndex = localCount++; int groupIndex = 0; if (!anonymous) groupIndex = capturingGroupCount++; GroupHead head = new GroupHead(localIndex); root = new GroupTail(localIndex, groupIndex); if (!anonymous && groupIndex < 10) groupNodes[groupIndex] = head; return head; } /** * Parses inlined match flags and set them appropriately. */ private void addFlag() { int ch = peek(); for (;;) { switch (ch) { case 'i': flags |= CASE_INSENSITIVE; break; case 'm': flags |= MULTILINE; break; case 's': flags |= DOTALL; break; case 'd': flags |= UNIX_LINES; break; case 'u': flags |= UNICODE_CASE; break; case 'c': flags |= CANON_EQ; break; case 'x': flags |= COMMENTS; break; case '-': // subFlag then fall through ch = next(); subFlag(); default: return; } ch = next(); } } /** * Parses the second part of inlined match flags and turns off * flags appropriately. */ private void subFlag() { int ch = peek(); for (;;) { switch (ch) { case 'i': flags &= ~CASE_INSENSITIVE; break; case 'm': flags &= ~MULTILINE; break; case 's': flags &= ~DOTALL; break; case 'd': flags &= ~UNIX_LINES; break; case 'u': flags &= ~UNICODE_CASE; break; case 'c': flags &= ~CANON_EQ; break; case 'x': flags &= ~COMMENTS; break; default: return; } ch = next(); } } static final int MAX_REPS = 0x7FFFFFFF; static final int GREEDY = 0; static final int LAZY = 1; static final int POSSESSIVE = 2; static final int INDEPENDENT = 3; /** * Processes repetition. If the next character peeked is a quantifier * then new nodes must be appended to handle the repetition. * Prev could be a single or a group, so it could be a chain of nodes. */ private Node closure(Node prev) { Node atom; int ch = peek(); switch (ch) { case '?': ch = next(); if (ch == '?') { next(); return new Ques(prev, LAZY); } else if (ch == '+') { next(); return new Ques(prev, POSSESSIVE); } return new Ques(prev, GREEDY); case '*': ch = next(); if (ch == '?') { next(); return new Curly(prev, 0, MAX_REPS, LAZY); } else if (ch == '+') { next(); return new Curly(prev, 0, MAX_REPS, POSSESSIVE); } return new Curly(prev, 0, MAX_REPS, GREEDY); case '+': ch = next(); if (ch == '?') { next(); return new Curly(prev, 1, MAX_REPS, LAZY); } else if (ch == '+') { next(); return new Curly(prev, 1, MAX_REPS, POSSESSIVE); } return new Curly(prev, 1, MAX_REPS, GREEDY); case '{': ch = temp[cursor+1]; if (ASCII.isDigit(ch)) { skip(); int cmin = 0; do { cmin = cmin * 10 + (ch - '0'); } while (ASCII.isDigit(ch = read())); int cmax = cmin; if (ch == ',') { ch = read(); cmax = MAX_REPS; if (ch != '}') { cmax = 0; while (ASCII.isDigit(ch)) { cmax = cmax * 10 + (ch - '0'); ch = read(); } } } if (ch != '}') throw error("Unclosed counted closure"); if (((cmin) | (cmax) | (cmax - cmin)) < 0) throw error("Illegal repetition range"); Curly curly; ch = peek(); if (ch == '?') { next(); curly = new Curly(prev, cmin, cmax, LAZY); } else if (ch == '+') { next(); curly = new Curly(prev, cmin, cmax, POSSESSIVE); } else { curly = new Curly(prev, cmin, cmax, GREEDY); } return curly; } else { throw error("Illegal repetition"); } default: return prev; } } /** * Utility method for parsing control escape sequences. */ private int c() { if (cursor < patternLength) { return read() ^ 64; } throw error("Illegal control escape sequence"); } /** * Utility method for parsing octal escape sequences. */ private int o() { int n = read(); if (((n-'0')|('7'-n)) >= 0) { int m = read(); if (((m-'0')|('7'-m)) >= 0) { int o = read(); if ((((o-'0')|('7'-o)) >= 0) && (((n-'0')|('3'-n)) >= 0)) { return (n - '0') * 64 + (m - '0') * 8 + (o - '0'); } unread(); return (n - '0') * 8 + (m - '0'); } unread(); return (n - '0'); } throw error("Illegal octal escape sequence"); } /** * Utility method for parsing hexadecimal escape sequences. */ private int x() { int n = read(); if (ASCII.isHexDigit(n)) { int m = read(); if (ASCII.isHexDigit(m)) { return ASCII.toDigit(n) * 16 + ASCII.toDigit(m); } } throw error("Illegal hexadecimal escape sequence"); } /** * Utility method for parsing unicode escape sequences. */ private int u() { int n = 0; for (int i = 0; i < 4; i++) { int ch = read(); if (!ASCII.isHexDigit(ch)) { throw error("Illegal Unicode escape sequence"); } n = n * 16 + ASCII.toDigit(ch); } return n; } // // Utility methods for code point support // /** * Tests a surrogate value. */ private static final boolean isSurrogate(int c) { return c >= Character.MIN_HIGH_SURROGATE && c <= Character.MAX_LOW_SURROGATE; } private static final int countChars(CharSequence seq, int index, int lengthInCodePoints) { // optimization if (lengthInCodePoints == 1 && !Character.isHighSurrogate(seq.charAt(index))) { assert (index >= 0 && index < seq.length()); return 1; } int length = seq.length(); int x = index; if (lengthInCodePoints >= 0) { assert (index >= 0 && index < length); for (int i = 0; x < length && i < lengthInCodePoints; i++) { if (Character.isHighSurrogate(seq.charAt(x++))) { if (x < length && Character.isLowSurrogate(seq.charAt(x))) { x++; } } } return x - index; } assert (index >= 0 && index <= length); if (index == 0) { return 0; } int len = -lengthInCodePoints; for (int i = 0; x > 0 && i < len; i++) { if (Character.isLowSurrogate(seq.charAt(--x))) { if (x > 0 && Character.isHighSurrogate(seq.charAt(x-1))) { x--; } } } return index - x; } private static final int countCodePoints(CharSequence seq) { int length = seq.length(); int n = 0; for (int i = 0; i < length; ) { n++; if (Character.isHighSurrogate(seq.charAt(i++))) { if (i < length && Character.isLowSurrogate(seq.charAt(i))) { i++; } } } return n; } /** * Creates a bit vector for matching Latin-1 values. A normal BitClass * never matches values above Latin-1, and a complemented BitClass always * matches values above Latin-1. */ private static final class BitClass extends BmpCharProperty { final boolean[] bits; BitClass() { bits = new boolean[256]; } private BitClass(boolean[] bits) { this.bits = bits; } BitClass add(int c, int flags) { assert c >= 0 && c <= 255; if ((flags & CASE_INSENSITIVE) != 0) { if (ASCII.isAscii(c)) { bits[ASCII.toUpper(c)] = true; bits[ASCII.toLower(c)] = true; } else if ((flags & UNICODE_CASE) != 0) { bits[Character.toLowerCase(c)] = true; bits[Character.toUpperCase(c)] = true; } } bits[c] = true; return this; } boolean isSatisfiedBy(int ch) { return ch < 256 && bits[ch]; } } /** * Returns a suitably optimized, single character matcher. */ private CharProperty newSingle(final int ch) { if (has(CASE_INSENSITIVE)) { int lower, upper; if (has(UNICODE_CASE)) { upper = Character.toUpperCase(ch); lower = Character.toLowerCase(upper); if (upper != lower) return new SingleU(lower); } else if (ASCII.isAscii(ch)) { lower = ASCII.toLower(ch); upper = ASCII.toUpper(ch); if (lower != upper) return new SingleI(lower, upper); } } if (isSupplementary(ch)) return new SingleS(ch); // Match a given Unicode character return new Single(ch); // Match a given BMP character } /** * Utility method for creating a string slice matcher. */ private Node newSlice(int[] buf, int count, boolean hasSupplementary) { int[] tmp = new int[count]; if (has(CASE_INSENSITIVE)) { if (has(UNICODE_CASE)) { for (int i = 0; i < count; i++) { tmp[i] = Character.toLowerCase( Character.toUpperCase(buf[i])); } return hasSupplementary? new SliceUS(tmp) : new SliceU(tmp); } for (int i = 0; i < count; i++) { tmp[i] = ASCII.toLower(buf[i]); } return hasSupplementary? new SliceIS(tmp) : new SliceI(tmp); } for (int i = 0; i < count; i++) { tmp[i] = buf[i]; } return hasSupplementary ? new SliceS(tmp) : new Slice(tmp); } /** * The following classes are the building components of the object * tree that represents a compiled regular expression. The object tree * is made of individual elements that handle constructs in the Pattern. * Each type of object knows how to match its equivalent construct with * the match() method. */ /** * Base class for all node classes. Subclasses should override the match() * method as appropriate. This class is an accepting node, so its match() * always returns true. */ static class Node extends Object { Node next; Node() { next = Pattern.accept; } /** * This method implements the classic accept node. */ boolean match(Matcher matcher, int i, CharSequence seq) { matcher.last = i; matcher.groups[0] = matcher.first; matcher.groups[1] = matcher.last; return true; } /** * This method is good for all zero length assertions. */ boolean study(TreeInfo info) { if (next != null) { return next.study(info); } else { return info.deterministic; } } } static class LastNode extends Node { /** * This method implements the classic accept node with * the addition of a check to see if the match occurred * using all of the input. */ boolean match(Matcher matcher, int i, CharSequence seq) { if (matcher.acceptMode == Matcher.ENDANCHOR && i != matcher.to) return false; matcher.last = i; matcher.groups[0] = matcher.first; matcher.groups[1] = matcher.last; return true; } } /** * Used for REs that can start anywhere within the input string. * This basically tries to match repeatedly at each spot in the * input string, moving forward after each try. An anchored search * or a BnM will bypass this node completely. */ static class Start extends Node { int minLength; Start(Node node) { this.next = node; TreeInfo info = new TreeInfo(); next.study(info); minLength = info.minLength; } boolean match(Matcher matcher, int i, CharSequence seq) { if (i > matcher.to - minLength) { matcher.hitEnd = true; return false; } boolean ret = false; int guard = matcher.to - minLength; for (; i <= guard; i++) { if (ret = next.match(matcher, i, seq)) break; if (i == guard) matcher.hitEnd = true; } if (ret) { matcher.first = i; matcher.groups[0] = matcher.first; matcher.groups[1] = matcher.last; } return ret; } boolean study(TreeInfo info) { next.study(info); info.maxValid = false; info.deterministic = false; return false; } } /* * StartS supports supplementary characters, including unpaired surrogates. */ static final class StartS extends Start { StartS(Node node) { super(node); } boolean match(Matcher matcher, int i, CharSequence seq) { if (i > matcher.to - minLength) { matcher.hitEnd = true; return false; } boolean ret = false; int guard = matcher.to - minLength; while (i <= guard) { if ((ret = next.match(matcher, i, seq)) || i == guard) break; // Optimization to move to the next character. This is // faster than countChars(seq, i, 1). if (Character.isHighSurrogate(seq.charAt(i++))) { if (i < seq.length() && Character.isLowSurrogate(seq.charAt(i))) { i++; } } if (i == guard) matcher.hitEnd = true; } if (ret) { matcher.first = i; matcher.groups[0] = matcher.first; matcher.groups[1] = matcher.last; } return ret; } } /** * Node to anchor at the beginning of input. This object implements the * match for a \A sequence, and the caret anchor will use this if not in * multiline mode. */ static final class Begin extends Node { boolean match(Matcher matcher, int i, CharSequence seq) { int fromIndex = (matcher.anchoringBounds) ? matcher.from : 0; if (i == fromIndex && next.match(matcher, i, seq)) { matcher.first = i; matcher.groups[0] = i; matcher.groups[1] = matcher.last; return true; } else { return false; } } } /** * Node to anchor at the end of input. This is the absolute end, so this * should not match at the last newline before the end as $ will. */ static final class End extends Node { boolean match(Matcher matcher, int i, CharSequence seq) { int endIndex = (matcher.anchoringBounds) ? matcher.to : matcher.getTextLength(); if (i == endIndex) { matcher.hitEnd = true; return next.match(matcher, i, seq); } return false; } } /** * Node to anchor at the beginning of a line. This is essentially the * object to match for the multiline ^. */ static final class Caret extends Node { boolean match(Matcher matcher, int i, CharSequence seq) { int startIndex = matcher.from; int endIndex = matcher.to; if (!matcher.anchoringBounds) { startIndex = 0; endIndex = matcher.getTextLength(); } // Perl does not match ^ at end of input even after newline if (i == endIndex) { matcher.hitEnd = true; return false; } if (i > startIndex) { char ch = seq.charAt(i-1); if (ch != '\n' && ch != '\r' && (ch|1) != '\u2029' && ch != '\u0085' ) { return false; } // Should treat /r/n as one newline if (ch == '\r' && seq.charAt(i) == '\n') return false; } return next.match(matcher, i, seq); } } /** * Node to anchor at the beginning of a line when in unixdot mode. */ static final class UnixCaret extends Node { boolean match(Matcher matcher, int i, CharSequence seq) { int startIndex = matcher.from; int endIndex = matcher.to; if (!matcher.anchoringBounds) { startIndex = 0; endIndex = matcher.getTextLength(); } // Perl does not match ^ at end of input even after newline if (i == endIndex) { matcher.hitEnd = true; return false; } if (i > startIndex) { char ch = seq.charAt(i-1); if (ch != '\n') { return false; } } return next.match(matcher, i, seq); } } /** * Node to match the location where the last match ended. * This is used for the \G construct. */ static final class LastMatch extends Node { boolean match(Matcher matcher, int i, CharSequence seq) { if (i != matcher.oldLast) return false; return next.match(matcher, i, seq); } } /** * Node to anchor at the end of a line or the end of input based on the * multiline mode. * * When not in multiline mode, the $ can only match at the very end * of the input, unless the input ends in a line terminator in which * it matches right before the last line terminator. * * Note that \r\n is considered an atomic line terminator. * * Like ^ the $ operator matches at a position, it does not match the * line terminators themselves. */ static final class Dollar extends Node { boolean multiline; Dollar(boolean mul) { multiline = mul; } boolean match(Matcher matcher, int i, CharSequence seq) { int endIndex = (matcher.anchoringBounds) ? matcher.to : matcher.getTextLength(); if (!multiline) { if (i < endIndex - 2) return false; if (i == endIndex - 2) { char ch = seq.charAt(i); if (ch != '\r') return false; ch = seq.charAt(i + 1); if (ch != '\n') return false; } } // Matches before any line terminator; also matches at the // end of input // Before line terminator: // If multiline, we match here no matter what // If not multiline, fall through so that the end // is marked as hit; this must be a /r/n or a /n // at the very end so the end was hit; more input // could make this not match here if (i < endIndex) { char ch = seq.charAt(i); if (ch == '\n') { // No match between \r\n if (i > 0 && seq.charAt(i-1) == '\r') return false; if (multiline) return next.match(matcher, i, seq); } else if (ch == '\r' || ch == '\u0085' || (ch|1) == '\u2029') { if (multiline) return next.match(matcher, i, seq); } else { // No line terminator, no match return false; } } // Matched at current end so hit end matcher.hitEnd = true; // If a $ matches because of end of input, then more input // could cause it to fail! matcher.requireEnd = true; return next.match(matcher, i, seq); } boolean study(TreeInfo info) { next.study(info); return info.deterministic; } } /** * Node to anchor at the end of a line or the end of input based on the * multiline mode when in unix lines mode. */ static final class UnixDollar extends Node { boolean multiline; UnixDollar(boolean mul) { multiline = mul; } boolean match(Matcher matcher, int i, CharSequence seq) { int endIndex = (matcher.anchoringBounds) ? matcher.to : matcher.getTextLength(); if (i < endIndex) { char ch = seq.charAt(i); if (ch == '\n') { // If not multiline, then only possible to // match at very end or one before end if (multiline == false && i != endIndex - 1) return false; // If multiline return next.match without setting // matcher.hitEnd if (multiline) return next.match(matcher, i, seq); } else { return false; } } // Matching because at the end or 1 before the end; // more input could change this so set hitEnd matcher.hitEnd = true; // If a $ matches because of end of input, then more input // could cause it to fail! matcher.requireEnd = true; return next.match(matcher, i, seq); } boolean study(TreeInfo info) { next.study(info); return info.deterministic; } } /** * Abstract node class to match one character satisfying some * boolean property. */ private static abstract class CharProperty extends Node { abstract boolean isSatisfiedBy(int ch); CharProperty complement() { return new CharProperty() { boolean isSatisfiedBy(int ch) { return ! CharProperty.this.isSatisfiedBy(ch);}}; } CharProperty maybeComplement(boolean complement) { return complement ? complement() : this; } boolean match(Matcher matcher, int i, CharSequence seq) { if (i < matcher.to) { int ch = Character.codePointAt(seq, i); return isSatisfiedBy(ch) && next.match(matcher, i+Character.charCount(ch), seq); } else { matcher.hitEnd = true; return false; } } boolean study(TreeInfo info) { info.minLength++; info.maxLength++; return next.study(info); } } /** * Optimized version of CharProperty that works only for * properties never satisfied by Supplementary characters. */ private static abstract class BmpCharProperty extends CharProperty { boolean match(Matcher matcher, int i, CharSequence seq) { if (i < matcher.to) { return isSatisfiedBy(seq.charAt(i)) && next.match(matcher, i+1, seq); } else { matcher.hitEnd = true; return false; } } } /** * Node class that matches a Supplementary Unicode character */ static final class SingleS extends CharProperty { final int c; SingleS(int c) { this.c = c; } boolean isSatisfiedBy(int ch) { return ch == c; } } /** * Optimization -- matches a given BMP character */ static final class Single extends BmpCharProperty { final int c; Single(int c) { this.c = c; } boolean isSatisfiedBy(int ch) { return ch == c; } } /** * Case insensitive matches a given BMP character */ static final class SingleI extends BmpCharProperty { final int lower; final int upper; SingleI(int lower, int upper) { this.lower = lower; this.upper = upper; } boolean isSatisfiedBy(int ch) { return ch == lower || ch == upper; } } /** * Unicode case insensitive matches a given Unicode character */ static final class SingleU extends CharProperty { final int lower; SingleU(int lower) { this.lower = lower; } boolean isSatisfiedBy(int ch) { return lower == ch || lower == Character.toLowerCase(Character.toUpperCase(ch)); } } /** * Node class that matches a Unicode category. */ static final class Category extends CharProperty { final int typeMask; Category(int typeMask) { this.typeMask = typeMask; } boolean isSatisfiedBy(int ch) { return (typeMask & (1 << Character.getType(ch))) != 0; } } /** * Node class that matches a POSIX type. */ static final class Ctype extends BmpCharProperty { final int ctype; Ctype(int ctype) { this.ctype = ctype; } boolean isSatisfiedBy(int ch) { return ch < 128 && ASCII.isType(ch, ctype); } } /** * Base class for all Slice nodes */ static class SliceNode extends Node { int[] buffer; SliceNode(int[] buf) { buffer = buf; } boolean study(TreeInfo info) { info.minLength += buffer.length; info.maxLength += buffer.length; return next.study(info); } } /** * Node class for a case sensitive/BMP-only sequence of literal * characters. */ static final class Slice extends SliceNode { Slice(int[] buf) { super(buf); } boolean match(Matcher matcher, int i, CharSequence seq) { int[] buf = buffer; int len = buf.length; for (int j=0; j<len; j++) { if ((i+j) >= matcher.to) { matcher.hitEnd = true; return false; } if (buf[j] != seq.charAt(i+j)) return false; } return next.match(matcher, i+len, seq); } } /** * Node class for a case_insensitive/BMP-only sequence of literal * characters. */ static class SliceI extends SliceNode { SliceI(int[] buf) { super(buf); } boolean match(Matcher matcher, int i, CharSequence seq) { int[] buf = buffer; int len = buf.length; for (int j=0; j<len; j++) { if ((i+j) >= matcher.to) { matcher.hitEnd = true; return false; } int c = seq.charAt(i+j); if (buf[j] != c && buf[j] != ASCII.toLower(c)) return false; } return next.match(matcher, i+len, seq); } } /** * Node class for a unicode_case_insensitive/BMP-only sequence of * literal characters. Uses unicode case folding. */ static final class SliceU extends SliceNode { SliceU(int[] buf) { super(buf); } boolean match(Matcher matcher, int i, CharSequence seq) { int[] buf = buffer; int len = buf.length; for (int j=0; j<len; j++) { if ((i+j) >= matcher.to) { matcher.hitEnd = true; return false; } int c = seq.charAt(i+j); if (buf[j] != c && buf[j] != Character.toLowerCase(Character.toUpperCase(c))) return false; } return next.match(matcher, i+len, seq); } } /** * Node class for a case sensitive sequence of literal characters * including supplementary characters. */ static final class SliceS extends SliceNode { SliceS(int[] buf) { super(buf); } boolean match(Matcher matcher, int i, CharSequence seq) { int[] buf = buffer; int x = i; for (int j = 0; j < buf.length; j++) { if (x >= matcher.to) { matcher.hitEnd = true; return false; } int c = Character.codePointAt(seq, x); if (buf[j] != c) return false; x += Character.charCount(c); if (x > matcher.to) { matcher.hitEnd = true; return false; } } return next.match(matcher, x, seq); } } /** * Node class for a case insensitive sequence of literal characters * including supplementary characters. */ static class SliceIS extends SliceNode { SliceIS(int[] buf) { super(buf); } int toLower(int c) { return ASCII.toLower(c); } boolean match(Matcher matcher, int i, CharSequence seq) { int[] buf = buffer; int x = i; for (int j = 0; j < buf.length; j++) { if (x >= matcher.to) { matcher.hitEnd = true; return false; } int c = Character.codePointAt(seq, x); if (buf[j] != c && buf[j] != toLower(c)) return false; x += Character.charCount(c); if (x > matcher.to) { matcher.hitEnd = true; return false; } } return next.match(matcher, x, seq); } } /** * Node class for a case insensitive sequence of literal characters. * Uses unicode case folding. */ static final class SliceUS extends SliceIS { SliceUS(int[] buf) { super(buf); } int toLower(int c) { return Character.toLowerCase(Character.toUpperCase(c)); } } private static boolean inRange(int lower, int ch, int upper) { return lower <= ch && ch <= upper; } /** * Returns node for matching characters within an explicit value range. */ private static CharProperty rangeFor(final int lower, final int upper) { return new CharProperty() { boolean isSatisfiedBy(int ch) { return inRange(lower, ch, upper);}}; } /** * Returns node for matching characters within an explicit value * range in a case insensitive manner. */ private CharProperty caseInsensitiveRangeFor(final int lower, final int upper) { if (has(UNICODE_CASE)) return new CharProperty() { boolean isSatisfiedBy(int ch) { if (inRange(lower, ch, upper)) return true; int up = Character.toUpperCase(ch); return inRange(lower, up, upper) || inRange(lower, Character.toLowerCase(up), upper);}}; return new CharProperty() { boolean isSatisfiedBy(int ch) { return inRange(lower, ch, upper) || ASCII.isAscii(ch) && (inRange(lower, ASCII.toUpper(ch), upper) || inRange(lower, ASCII.toLower(ch), upper)); }}; } /** * Implements the Unicode category ALL and the dot metacharacter when * in dotall mode. */ static final class All extends CharProperty { boolean isSatisfiedBy(int ch) { return true; } } /** * Node class for the dot metacharacter when dotall is not enabled. */ static final class Dot extends CharProperty { boolean isSatisfiedBy(int ch) { return (ch != '\n' && ch != '\r' && (ch|1) != '\u2029' && ch != '\u0085'); } } /** * Node class for the dot metacharacter when dotall is not enabled * but UNIX_LINES is enabled. */ static final class UnixDot extends CharProperty { boolean isSatisfiedBy(int ch) { return ch != '\n'; } } /** * The 0 or 1 quantifier. This one class implements all three types. */ static final class Ques extends Node { Node atom; int type; Ques(Node node, int type) { this.atom = node; this.type = type; } boolean match(Matcher matcher, int i, CharSequence seq) { switch (type) { case GREEDY: return (atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq)) || next.match(matcher, i, seq); case LAZY: return next.match(matcher, i, seq) || (atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq)); case POSSESSIVE: if (atom.match(matcher, i, seq)) i = matcher.last; return next.match(matcher, i, seq); default: return atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq); } } boolean study(TreeInfo info) { if (type != INDEPENDENT) { int minL = info.minLength; atom.study(info); info.minLength = minL; info.deterministic = false; return next.study(info); } else { atom.study(info); return next.study(info); } } } /** * Handles the curly-brace style repetition with a specified minimum and * maximum occurrences. The * quantifier is handled as a special case. * This class handles the three types. */ static final class Curly extends Node { Node atom; int type; int cmin; int cmax; Curly(Node node, int cmin, int cmax, int type) { this.atom = node; this.type = type; this.cmin = cmin; this.cmax = cmax; } boolean match(Matcher matcher, int i, CharSequence seq) { int j; for (j = 0; j < cmin; j++) { if (atom.match(matcher, i, seq)) { i = matcher.last; continue; } return false; } if (type == GREEDY) return match0(matcher, i, j, seq); else if (type == LAZY) return match1(matcher, i, j, seq); else return match2(matcher, i, j, seq); } // Greedy match. // i is the index to start matching at // j is the number of atoms that have matched boolean match0(Matcher matcher, int i, int j, CharSequence seq) { if (j >= cmax) { // We have matched the maximum... continue with the rest of // the regular expression return next.match(matcher, i, seq); } int backLimit = j; while (atom.match(matcher, i, seq)) { // k is the length of this match int k = matcher.last - i; if (k == 0) // Zero length match break; // Move up index and number matched i = matcher.last; j++; // We are greedy so match as many as we can while (j < cmax) { if (!atom.match(matcher, i, seq)) break; if (i + k != matcher.last) { if (match0(matcher, matcher.last, j+1, seq)) return true; break; } i += k; j++; } // Handle backing off if match fails while (j >= backLimit) { if (next.match(matcher, i, seq)) return true; i -= k; j--; } return false; } return next.match(matcher, i, seq); } // Reluctant match. At this point, the minimum has been satisfied. // i is the index to start matching at // j is the number of atoms that have matched boolean match1(Matcher matcher, int i, int j, CharSequence seq) { for (;;) { // Try finishing match without consuming any more if (next.match(matcher, i, seq)) return true; // At the maximum, no match found if (j >= cmax) return false; // Okay, must try one more atom if (!atom.match(matcher, i, seq)) return false; // If we haven't moved forward then must break out if (i == matcher.last) return false; // Move up index and number matched i = matcher.last; j++; } } boolean match2(Matcher matcher, int i, int j, CharSequence seq) { for (; j < cmax; j++) { if (!atom.match(matcher, i, seq)) break; if (i == matcher.last) break; i = matcher.last; } return next.match(matcher, i, seq); } boolean study(TreeInfo info) { // Save original info int minL = info.minLength; int maxL = info.maxLength; boolean maxV = info.maxValid; boolean detm = info.deterministic; info.reset(); atom.study(info); int temp = info.minLength * cmin + minL; if (temp < minL) { temp = 0xFFFFFFF; // arbitrary large number } info.minLength = temp; if (maxV & info.maxValid) { temp = info.maxLength * cmax + maxL; info.maxLength = temp; if (temp < maxL) { info.maxValid = false; } } else { info.maxValid = false; } if (info.deterministic && cmin == cmax) info.deterministic = detm; else info.deterministic = false; return next.study(info); } } /** * Handles the curly-brace style repetition with a specified minimum and * maximum occurrences in deterministic cases. This is an iterative * optimization over the Prolog and Loop system which would handle this * in a recursive way. The * quantifier is handled as a special case. * If capture is true then this class saves group settings and ensures * that groups are unset when backing off of a group match. */ static final class GroupCurly extends Node { Node atom; int type; int cmin; int cmax; int localIndex; int groupIndex; boolean capture; GroupCurly(Node node, int cmin, int cmax, int type, int local, int group, boolean capture) { this.atom = node; this.type = type; this.cmin = cmin; this.cmax = cmax; this.localIndex = local; this.groupIndex = group; this.capture = capture; } boolean match(Matcher matcher, int i, CharSequence seq) { int[] groups = matcher.groups; int[] locals = matcher.locals; int save0 = locals[localIndex]; int save1 = 0; int save2 = 0; if (capture) { save1 = groups[groupIndex]; save2 = groups[groupIndex+1]; } // Notify GroupTail there is no need to setup group info // because it will be set here locals[localIndex] = -1; boolean ret = true; for (int j = 0; j < cmin; j++) { if (atom.match(matcher, i, seq)) { if (capture) { groups[groupIndex] = i; groups[groupIndex+1] = matcher.last; } i = matcher.last; } else { ret = false; break; } } if (ret) { if (type == GREEDY) { ret = match0(matcher, i, cmin, seq); } else if (type == LAZY) { ret = match1(matcher, i, cmin, seq); } else { ret = match2(matcher, i, cmin, seq); } } if (!ret) { locals[localIndex] = save0; if (capture) { groups[groupIndex] = save1; groups[groupIndex+1] = save2; } } return ret; } // Aggressive group match boolean match0(Matcher matcher, int i, int j, CharSequence seq) { int[] groups = matcher.groups; int save0 = 0; int save1 = 0; if (capture) { save0 = groups[groupIndex]; save1 = groups[groupIndex+1]; } for (;;) { if (j >= cmax) break; if (!atom.match(matcher, i, seq)) break; int k = matcher.last - i; if (k <= 0) { if (capture) { groups[groupIndex] = i; groups[groupIndex+1] = i + k; } i = i + k; break; } for (;;) { if (capture) { groups[groupIndex] = i; groups[groupIndex+1] = i + k; } i = i + k; if (++j >= cmax) break; if (!atom.match(matcher, i, seq)) break; if (i + k != matcher.last) { if (match0(matcher, i, j, seq)) return true; break; } } while (j > cmin) { if (next.match(matcher, i, seq)) { if (capture) { groups[groupIndex+1] = i; groups[groupIndex] = i - k; } i = i - k; return true; } // backing off if (capture) { groups[groupIndex+1] = i; groups[groupIndex] = i - k; } i = i - k; j--; } break; } if (capture) { groups[groupIndex] = save0; groups[groupIndex+1] = save1; } return next.match(matcher, i, seq); } // Reluctant matching boolean match1(Matcher matcher, int i, int j, CharSequence seq) { for (;;) { if (next.match(matcher, i, seq)) return true; if (j >= cmax) return false; if (!atom.match(matcher, i, seq)) return false; if (i == matcher.last) return false; if (capture) { matcher.groups[groupIndex] = i; matcher.groups[groupIndex+1] = matcher.last; } i = matcher.last; j++; } } // Possessive matching boolean match2(Matcher matcher, int i, int j, CharSequence seq) { for (; j < cmax; j++) { if (!atom.match(matcher, i, seq)) { break; } if (capture) { matcher.groups[groupIndex] = i; matcher.groups[groupIndex+1] = matcher.last; } if (i == matcher.last) { break; } i = matcher.last; } return next.match(matcher, i, seq); } boolean study(TreeInfo info) { // Save original info int minL = info.minLength; int maxL = info.maxLength; boolean maxV = info.maxValid; boolean detm = info.deterministic; info.reset(); atom.study(info); int temp = info.minLength * cmin + minL; if (temp < minL) { temp = 0xFFFFFFF; // Arbitrary large number } info.minLength = temp; if (maxV & info.maxValid) { temp = info.maxLength * cmax + maxL; info.maxLength = temp; if (temp < maxL) { info.maxValid = false; } } else { info.maxValid = false; } if (info.deterministic && cmin == cmax) { info.deterministic = detm; } else { info.deterministic = false; } return next.study(info); } } /** * A Guard node at the end of each atom node in a Branch. It * serves the purpose of chaining the "match" operation to * "next" but not the "study", so we can collect the TreeInfo * of each atom node without including the TreeInfo of the * "next". */ static final class BranchConn extends Node { BranchConn() {}; boolean match(Matcher matcher, int i, CharSequence seq) { return next.match(matcher, i, seq); } boolean study(TreeInfo info) { return info.deterministic; } } /** * Handles the branching of alternations. Note this is also used for * the ? quantifier to branch between the case where it matches once * and where it does not occur. */ static final class Branch extends Node { Node[] atoms = new Node[2]; int size = 2; Node conn; Branch(Node first, Node second, Node branchConn) { conn = branchConn; atoms[0] = first; atoms[1] = second; } void add(Node node) { if (size >= atoms.length) { Node[] tmp = new Node[atoms.length*2]; System.arraycopy(atoms, 0, tmp, 0, atoms.length); atoms = tmp; } atoms[size++] = node; } boolean match(Matcher matcher, int i, CharSequence seq) { for (int n = 0; n < size; n++) { if (atoms[n] == null) { if (conn.next.match(matcher, i, seq)) return true; } else if (atoms[n].match(matcher, i, seq)) { return true; } } return false; } boolean study(TreeInfo info) { int minL = info.minLength; int maxL = info.maxLength; boolean maxV = info.maxValid; int minL2 = Integer.MAX_VALUE; //arbitrary large enough num int maxL2 = -1; for (int n = 0; n < size; n++) { info.reset(); if (atoms[n] != null) atoms[n].study(info); minL2 = Math.min(minL2, info.minLength); maxL2 = Math.max(maxL2, info.maxLength); maxV = (maxV & info.maxValid); } minL += minL2; maxL += maxL2; info.reset(); conn.next.study(info); info.minLength += minL; info.maxLength += maxL; info.maxValid &= maxV; info.deterministic = false; return false; } } /** * The GroupHead saves the location where the group begins in the locals * and restores them when the match is done. * * The matchRef is used when a reference to this group is accessed later * in the expression. The locals will have a negative value in them to * indicate that we do not want to unset the group if the reference * doesn't match. */ static final class GroupHead extends Node { int localIndex; GroupHead(int localCount) { localIndex = localCount; } boolean match(Matcher matcher, int i, CharSequence seq) { int save = matcher.locals[localIndex]; matcher.locals[localIndex] = i; boolean ret = next.match(matcher, i, seq); matcher.locals[localIndex] = save; return ret; } boolean matchRef(Matcher matcher, int i, CharSequence seq) { int save = matcher.locals[localIndex]; matcher.locals[localIndex] = ~i; // HACK boolean ret = next.match(matcher, i, seq); matcher.locals[localIndex] = save; return ret; } } /** * Recursive reference to a group in the regular expression. It calls * matchRef because if the reference fails to match we would not unset * the group. */ static final class GroupRef extends Node { GroupHead head; GroupRef(GroupHead head) { this.head = head; } boolean match(Matcher matcher, int i, CharSequence seq) { return head.matchRef(matcher, i, seq) && next.match(matcher, matcher.last, seq); } boolean study(TreeInfo info) { info.maxValid = false; info.deterministic = false; return next.study(info); } } /** * The GroupTail handles the setting of group beginning and ending * locations when groups are successfully matched. It must also be able to * unset groups that have to be backed off of. * * The GroupTail node is also used when a previous group is referenced, * and in that case no group information needs to be set. */ static final class GroupTail extends Node { int localIndex; int groupIndex; GroupTail(int localCount, int groupCount) { localIndex = localCount; groupIndex = groupCount + groupCount; } boolean match(Matcher matcher, int i, CharSequence seq) { int tmp = matcher.locals[localIndex]; if (tmp >= 0) { // This is the normal group case. // Save the group so we can unset it if it // backs off of a match. int groupStart = matcher.groups[groupIndex]; int groupEnd = matcher.groups[groupIndex+1]; matcher.groups[groupIndex] = tmp; matcher.groups[groupIndex+1] = i; if (next.match(matcher, i, seq)) { return true; } matcher.groups[groupIndex] = groupStart; matcher.groups[groupIndex+1] = groupEnd; return false; } else { // This is a group reference case. We don't need to save any // group info because it isn't really a group. matcher.last = i; return true; } } } /** * This sets up a loop to handle a recursive quantifier structure. */ static final class Prolog extends Node { Loop loop; Prolog(Loop loop) { this.loop = loop; } boolean match(Matcher matcher, int i, CharSequence seq) { return loop.matchInit(matcher, i, seq); } boolean study(TreeInfo info) { return loop.study(info); } } /** * Handles the repetition count for a greedy Curly. The matchInit * is called from the Prolog to save the index of where the group * beginning is stored. A zero length group check occurs in the * normal match but is skipped in the matchInit. */ static class Loop extends Node { Node body; int countIndex; // local count index in matcher locals int beginIndex; // group beginning index int cmin, cmax; Loop(int countIndex, int beginIndex) { this.countIndex = countIndex; this.beginIndex = beginIndex; } boolean match(Matcher matcher, int i, CharSequence seq) { // Avoid infinite loop in zero-length case. if (i > matcher.locals[beginIndex]) { int count = matcher.locals[countIndex]; // This block is for before we reach the minimum // iterations required for the loop to match if (count < cmin) { matcher.locals[countIndex] = count + 1; boolean b = body.match(matcher, i, seq); // If match failed we must backtrack, so // the loop count should NOT be incremented if (!b) matcher.locals[countIndex] = count; // Return success or failure since we are under // minimum return b; } // This block is for after we have the minimum // iterations required for the loop to match if (count < cmax) { matcher.locals[countIndex] = count + 1; boolean b = body.match(matcher, i, seq); // If match failed we must backtrack, so // the loop count should NOT be incremented if (!b) matcher.locals[countIndex] = count; else return true; } } return next.match(matcher, i, seq); } boolean matchInit(Matcher matcher, int i, CharSequence seq) { int save = matcher.locals[countIndex]; boolean ret = false; if (0 < cmin) { matcher.locals[countIndex] = 1; ret = body.match(matcher, i, seq); } else if (0 < cmax) { matcher.locals[countIndex] = 1; ret = body.match(matcher, i, seq); if (ret == false) ret = next.match(matcher, i, seq); } else { ret = next.match(matcher, i, seq); } matcher.locals[countIndex] = save; return ret; } boolean study(TreeInfo info) { info.maxValid = false; info.deterministic = false; return false; } } /** * Handles the repetition count for a reluctant Curly. The matchInit * is called from the Prolog to save the index of where the group * beginning is stored. A zero length group check occurs in the * normal match but is skipped in the matchInit. */ static final class LazyLoop extends Loop { LazyLoop(int countIndex, int beginIndex) { super(countIndex, beginIndex); } boolean match(Matcher matcher, int i, CharSequence seq) { // Check for zero length group if (i > matcher.locals[beginIndex]) { int count = matcher.locals[countIndex]; if (count < cmin) { matcher.locals[countIndex] = count + 1; boolean result = body.match(matcher, i, seq); // If match failed we must backtrack, so // the loop count should NOT be incremented if (!result) matcher.locals[countIndex] = count; return result; } if (next.match(matcher, i, seq)) return true; if (count < cmax) { matcher.locals[countIndex] = count + 1; boolean result = body.match(matcher, i, seq); // If match failed we must backtrack, so // the loop count should NOT be incremented if (!result) matcher.locals[countIndex] = count; return result; } return false; } return next.match(matcher, i, seq); } boolean matchInit(Matcher matcher, int i, CharSequence seq) { int save = matcher.locals[countIndex]; boolean ret = false; if (0 < cmin) { matcher.locals[countIndex] = 1; ret = body.match(matcher, i, seq); } else if (next.match(matcher, i, seq)) { ret = true; } else if (0 < cmax) { matcher.locals[countIndex] = 1; ret = body.match(matcher, i, seq); } matcher.locals[countIndex] = save; return ret; } boolean study(TreeInfo info) { info.maxValid = false; info.deterministic = false; return false; } } /** * Refers to a group in the regular expression. Attempts to match * whatever the group referred to last matched. */ static class BackRef extends Node { int groupIndex; BackRef(int groupCount) { super(); groupIndex = groupCount + groupCount; } boolean match(Matcher matcher, int i, CharSequence seq) { int j = matcher.groups[groupIndex]; int k = matcher.groups[groupIndex+1]; int groupSize = k - j; // If the referenced group didn't match, neither can this if (j < 0) return false; // If there isn't enough input left no match if (i + groupSize > matcher.to) { matcher.hitEnd = true; return false; } // Check each new char to make sure it matches what the group // referenced matched last time around for (int index=0; index<groupSize; index++) if (seq.charAt(i+index) != seq.charAt(j+index)) return false; return next.match(matcher, i+groupSize, seq); } boolean study(TreeInfo info) { info.maxValid = false; return next.study(info); } } static class CIBackRef extends Node { int groupIndex; boolean doUnicodeCase; CIBackRef(int groupCount, boolean doUnicodeCase) { super(); groupIndex = groupCount + groupCount; this.doUnicodeCase = doUnicodeCase; } boolean match(Matcher matcher, int i, CharSequence seq) { int j = matcher.groups[groupIndex]; int k = matcher.groups[groupIndex+1]; int groupSize = k - j; // If the referenced group didn't match, neither can this if (j < 0) return false; // If there isn't enough input left no match if (i + groupSize > matcher.to) { matcher.hitEnd = true; return false; } // Check each new char to make sure it matches what the group // referenced matched last time around int x = i; for (int index=0; index<groupSize; index++) { int c1 = Character.codePointAt(seq, x); int c2 = Character.codePointAt(seq, j); if (c1 != c2) { if (doUnicodeCase) { int cc1 = Character.toUpperCase(c1); int cc2 = Character.toUpperCase(c2); if (cc1 != cc2 && Character.toLowerCase(cc1) != Character.toLowerCase(cc2)) return false; } else { if (ASCII.toLower(c1) != ASCII.toLower(c2)) return false; } } x += Character.charCount(c1); j += Character.charCount(c2); } return next.match(matcher, i+groupSize, seq); } boolean study(TreeInfo info) { info.maxValid = false; return next.study(info); } } /** * Searches until the next instance of its atom. This is useful for * finding the atom efficiently without passing an instance of it * (greedy problem) and without a lot of wasted search time (reluctant * problem). */ static final class First extends Node { Node atom; First(Node node) { this.atom = BnM.optimize(node); } boolean match(Matcher matcher, int i, CharSequence seq) { if (atom instanceof BnM) { return atom.match(matcher, i, seq) && next.match(matcher, matcher.last, seq); } for (;;) { if (i > matcher.to) { matcher.hitEnd = true; return false; } if (atom.match(matcher, i, seq)) { return next.match(matcher, matcher.last, seq); } i += countChars(seq, i, 1); matcher.first++; } } boolean study(TreeInfo info) { atom.study(info); info.maxValid = false; info.deterministic = false; return next.study(info); } } static final class Conditional extends Node { Node cond, yes, not; Conditional(Node cond, Node yes, Node not) { this.cond = cond; this.yes = yes; this.not = not; } boolean match(Matcher matcher, int i, CharSequence seq) { if (cond.match(matcher, i, seq)) { return yes.match(matcher, i, seq); } else { return not.match(matcher, i, seq); } } boolean study(TreeInfo info) { int minL = info.minLength; int maxL = info.maxLength; boolean maxV = info.maxValid; info.reset(); yes.study(info); int minL2 = info.minLength; int maxL2 = info.maxLength; boolean maxV2 = info.maxValid; info.reset(); not.study(info); info.minLength = minL + Math.min(minL2, info.minLength); info.maxLength = maxL + Math.max(maxL2, info.maxLength); info.maxValid = (maxV & maxV2 & info.maxValid); info.deterministic = false; return next.study(info); } } /** * Zero width positive lookahead. */ static final class Pos extends Node { Node cond; Pos(Node cond) { this.cond = cond; } boolean match(Matcher matcher, int i, CharSequence seq) { int savedTo = matcher.to; boolean conditionMatched = false; // Relax transparent region boundaries for lookahead if (matcher.transparentBounds) matcher.to = matcher.getTextLength(); try { conditionMatched = cond.match(matcher, i, seq); } finally { // Reinstate region boundaries matcher.to = savedTo; } return conditionMatched && next.match(matcher, i, seq); } } /** * Zero width negative lookahead. */ static final class Neg extends Node { Node cond; Neg(Node cond) { this.cond = cond; } boolean match(Matcher matcher, int i, CharSequence seq) { int savedTo = matcher.to; boolean conditionMatched = false; // Relax transparent region boundaries for lookahead if (matcher.transparentBounds) matcher.to = matcher.getTextLength(); try { if (i < matcher.to) { conditionMatched = !cond.match(matcher, i, seq); } else { // If a negative lookahead succeeds then more input // could cause it to fail! matcher.requireEnd = true; conditionMatched = !cond.match(matcher, i, seq); } } finally { // Reinstate region boundaries matcher.to = savedTo; } return conditionMatched && next.match(matcher, i, seq); } } /** * For use with lookbehinds; matches the position where the lookbehind * was encountered. */ static Node lookbehindEnd = new Node() { boolean match(Matcher matcher, int i, CharSequence seq) { return i == matcher.lookbehindTo; } }; /** * Zero width positive lookbehind. */ static class Behind extends Node { Node cond; int rmax, rmin; Behind(Node cond, int rmax, int rmin) { this.cond = cond; this.rmax = rmax; this.rmin = rmin; } boolean match(Matcher matcher, int i, CharSequence seq) { int savedFrom = matcher.from; boolean conditionMatched = false; int startIndex = (!matcher.transparentBounds) ? matcher.from : 0; int from = Math.max(i - rmax, startIndex); // Set end boundary int savedLBT = matcher.lookbehindTo; matcher.lookbehindTo = i; // Relax transparent region boundaries for lookbehind if (matcher.transparentBounds) matcher.from = 0; for (int j = i - rmin; !conditionMatched && j >= from; j--) { conditionMatched = cond.match(matcher, j, seq); } matcher.from = savedFrom; matcher.lookbehindTo = savedLBT; return conditionMatched && next.match(matcher, i, seq); } } /** * Zero width positive lookbehind, including supplementary * characters or unpaired surrogates. */ static final class BehindS extends Behind { BehindS(Node cond, int rmax, int rmin) { super(cond, rmax, rmin); } boolean match(Matcher matcher, int i, CharSequence seq) { int rmaxChars = countChars(seq, i, -rmax); int rminChars = countChars(seq, i, -rmin); int savedFrom = matcher.from; int startIndex = (!matcher.transparentBounds) ? matcher.from : 0; boolean conditionMatched = false; int from = Math.max(i - rmaxChars, startIndex); // Set end boundary int savedLBT = matcher.lookbehindTo; matcher.lookbehindTo = i; // Relax transparent region boundaries for lookbehind if (matcher.transparentBounds) matcher.from = 0; for (int j = i - rminChars; !conditionMatched && j >= from; j -= j>from ? countChars(seq, j, -1) : 1) { conditionMatched = cond.match(matcher, j, seq); } matcher.from = savedFrom; matcher.lookbehindTo = savedLBT; return conditionMatched && next.match(matcher, i, seq); } } /** * Zero width negative lookbehind. */ static class NotBehind extends Node { Node cond; int rmax, rmin; NotBehind(Node cond, int rmax, int rmin) { this.cond = cond; this.rmax = rmax; this.rmin = rmin; } boolean match(Matcher matcher, int i, CharSequence seq) { int savedLBT = matcher.lookbehindTo; int savedFrom = matcher.from; boolean conditionMatched = false; int startIndex = (!matcher.transparentBounds) ? matcher.from : 0; int from = Math.max(i - rmax, startIndex); matcher.lookbehindTo = i; // Relax transparent region boundaries for lookbehind if (matcher.transparentBounds) matcher.from = 0; for (int j = i - rmin; !conditionMatched && j >= from; j--) { conditionMatched = cond.match(matcher, j, seq); } // Reinstate region boundaries matcher.from = savedFrom; matcher.lookbehindTo = savedLBT; return !conditionMatched && next.match(matcher, i, seq); } } /** * Zero width negative lookbehind, including supplementary * characters or unpaired surrogates. */ static final class NotBehindS extends NotBehind { NotBehindS(Node cond, int rmax, int rmin) { super(cond, rmax, rmin); } boolean match(Matcher matcher, int i, CharSequence seq) { int rmaxChars = countChars(seq, i, -rmax); int rminChars = countChars(seq, i, -rmin); int savedFrom = matcher.from; int savedLBT = matcher.lookbehindTo; boolean conditionMatched = false; int startIndex = (!matcher.transparentBounds) ? matcher.from : 0; int from = Math.max(i - rmaxChars, startIndex); matcher.lookbehindTo = i; // Relax transparent region boundaries for lookbehind if (matcher.transparentBounds) matcher.from = 0; for (int j = i - rminChars; !conditionMatched && j >= from; j -= j>from ? countChars(seq, j, -1) : 1) { conditionMatched = cond.match(matcher, j, seq); } //Reinstate region boundaries matcher.from = savedFrom; matcher.lookbehindTo = savedLBT; return !conditionMatched && next.match(matcher, i, seq); } } /** * Returns the set union of two CharProperty nodes. */ private static CharProperty union(final CharProperty lhs, final CharProperty rhs) { return new CharProperty() { boolean isSatisfiedBy(int ch) { return lhs.isSatisfiedBy(ch) || rhs.isSatisfiedBy(ch);}}; } /** * Returns the set intersection of two CharProperty nodes. */ private static CharProperty intersection(final CharProperty lhs, final CharProperty rhs) { return new CharProperty() { boolean isSatisfiedBy(int ch) { return lhs.isSatisfiedBy(ch) && rhs.isSatisfiedBy(ch);}}; } /** * Returns the set difference of two CharProperty nodes. */ private static CharProperty setDifference(final CharProperty lhs, final CharProperty rhs) { return new CharProperty() { boolean isSatisfiedBy(int ch) { return ! rhs.isSatisfiedBy(ch) && lhs.isSatisfiedBy(ch);}}; } /** * Handles word boundaries. Includes a field to allow this one class to * deal with the different types of word boundaries we can match. The word * characters include underscores, letters, and digits. Non spacing marks * can are also part of a word if they have a base character, otherwise * they are ignored for purposes of finding word boundaries. */ static final class Bound extends Node { static int LEFT = 0x1; static int RIGHT= 0x2; static int BOTH = 0x3; static int NONE = 0x4; int type; Bound(int n) { type = n; } int check(Matcher matcher, int i, CharSequence seq) { int ch; boolean left = false; int startIndex = matcher.from; int endIndex = matcher.to; if (matcher.transparentBounds) { startIndex = 0; endIndex = matcher.getTextLength(); } if (i > startIndex) { ch = Character.codePointBefore(seq, i); left = (ch == '_' || Character.isLetterOrDigit(ch) || ((Character.getType(ch) == Character.NON_SPACING_MARK) && hasBaseCharacter(matcher, i-1, seq))); } boolean right = false; if (i < endIndex) { ch = Character.codePointAt(seq, i); right = (ch == '_' || Character.isLetterOrDigit(ch) || ((Character.getType(ch) == Character.NON_SPACING_MARK) && hasBaseCharacter(matcher, i, seq))); } else { // Tried to access char past the end matcher.hitEnd = true; // The addition of another char could wreck a boundary matcher.requireEnd = true; } return ((left ^ right) ? (right ? LEFT : RIGHT) : NONE); } boolean match(Matcher matcher, int i, CharSequence seq) { return (check(matcher, i, seq) & type) > 0 && next.match(matcher, i, seq); } } /** * Non spacing marks only count as word characters in bounds calculations * if they have a base character. */ private static boolean hasBaseCharacter(Matcher matcher, int i, CharSequence seq) { int start = (!matcher.transparentBounds) ? matcher.from : 0; for (int x=i; x >= start; x--) { int ch = Character.codePointAt(seq, x); if (Character.isLetterOrDigit(ch)) return true; if (Character.getType(ch) == Character.NON_SPACING_MARK) continue; return false; } return false; } /** * Attempts to match a slice in the input using the Boyer-Moore string * matching algorithm. The algorithm is based on the idea that the * pattern can be shifted farther ahead in the search text if it is * matched right to left. * <p> * The pattern is compared to the input one character at a time, from * the rightmost character in the pattern to the left. If the characters * all match the pattern has been found. If a character does not match, * the pattern is shifted right a distance that is the maximum of two * functions, the bad character shift and the good suffix shift. This * shift moves the attempted match position through the input more * quickly than a naive one position at a time check. * <p> * The bad character shift is based on the character from the text that * did not match. If the character does not appear in the pattern, the * pattern can be shifted completely beyond the bad character. If the * character does occur in the pattern, the pattern can be shifted to * line the pattern up with the next occurrence of that character. * <p> * The good suffix shift is based on the idea that some subset on the right * side of the pattern has matched. When a bad character is found, the * pattern can be shifted right by the pattern length if the subset does * not occur again in pattern, or by the amount of distance to the * next occurrence of the subset in the pattern. * * Boyer-Moore search methods adapted from code by Amy Yu. */ static class BnM extends Node { int[] buffer; int[] lastOcc; int[] optoSft; /** * Pre calculates arrays needed to generate the bad character * shift and the good suffix shift. Only the last seven bits * are used to see if chars match; This keeps the tables small * and covers the heavily used ASCII range, but occasionally * results in an aliased match for the bad character shift. */ static Node optimize(Node node) { if (!(node instanceof Slice)) { return node; } int[] src = ((Slice) node).buffer; int patternLength = src.length; // The BM algorithm requires a bit of overhead; // If the pattern is short don't use it, since // a shift larger than the pattern length cannot // be used anyway. if (patternLength < 4) { return node; } int i, j, k; int[] lastOcc = new int[128]; int[] optoSft = new int[patternLength]; // Precalculate part of the bad character shift // It is a table for where in the pattern each // lower 7-bit value occurs for (i = 0; i < patternLength; i++) { lastOcc[src[i]&0x7F] = i + 1; } // Precalculate the good suffix shift // i is the shift amount being considered NEXT: for (i = patternLength; i > 0; i--) { // j is the beginning index of suffix being considered for (j = patternLength - 1; j >= i; j--) { // Testing for good suffix if (src[j] == src[j-i]) { // src[j..len] is a good suffix optoSft[j-1] = i; } else { // No match. The array has already been // filled up with correct values before. continue NEXT; } } // This fills up the remaining of optoSft // any suffix can not have larger shift amount // then its sub-suffix. Why??? while (j > 0) { optoSft[--j] = i; } } // Set the guard value because of unicode compression optoSft[patternLength-1] = 1; if (node instanceof SliceS) return new BnMS(src, lastOcc, optoSft, node.next); return new BnM(src, lastOcc, optoSft, node.next); } BnM(int[] src, int[] lastOcc, int[] optoSft, Node next) { this.buffer = src; this.lastOcc = lastOcc; this.optoSft = optoSft; this.next = next; } boolean match(Matcher matcher, int i, CharSequence seq) { int[] src = buffer; int patternLength = src.length; int last = matcher.to - patternLength; // Loop over all possible match positions in text NEXT: while (i <= last) { // Loop over pattern from right to left for (int j = patternLength - 1; j >= 0; j--) { int ch = seq.charAt(i+j); if (ch != src[j]) { // Shift search to the right by the maximum of the // bad character shift and the good suffix shift i += Math.max(j + 1 - lastOcc[ch&0x7F], optoSft[j]); continue NEXT; } } // Entire pattern matched starting at i matcher.first = i; boolean ret = next.match(matcher, i + patternLength, seq); if (ret) { matcher.first = i; matcher.groups[0] = matcher.first; matcher.groups[1] = matcher.last; return true; } i++; } // BnM is only used as the leading node in the unanchored case, // and it replaced its Start() which always searches to the end // if it doesn't find what it's looking for, so hitEnd is true. matcher.hitEnd = true; return false; } boolean study(TreeInfo info) { info.minLength += buffer.length; info.maxValid = false; return next.study(info); } } /** * Supplementary support version of BnM(). Unpaired surrogates are * also handled by this class. */ static final class BnMS extends BnM { int lengthInChars; BnMS(int[] src, int[] lastOcc, int[] optoSft, Node next) { super(src, lastOcc, optoSft, next); for (int x = 0; x < buffer.length; x++) { lengthInChars += Character.charCount(buffer[x]); } } boolean match(Matcher matcher, int i, CharSequence seq) { int[] src = buffer; int patternLength = src.length; int last = matcher.to - lengthInChars; // Loop over all possible match positions in text NEXT: while (i <= last) { // Loop over pattern from right to left int ch; for (int j = countChars(seq, i, patternLength), x = patternLength - 1; j > 0; j -= Character.charCount(ch), x--) { ch = Character.codePointBefore(seq, i+j); if (ch != src[x]) { // Shift search to the right by the maximum of the // bad character shift and the good suffix shift int n = Math.max(x + 1 - lastOcc[ch&0x7F], optoSft[x]); i += countChars(seq, i, n); continue NEXT; } } // Entire pattern matched starting at i matcher.first = i; boolean ret = next.match(matcher, i + lengthInChars, seq); if (ret) { matcher.first = i; matcher.groups[0] = matcher.first; matcher.groups[1] = matcher.last; return true; } i += countChars(seq, i, 1); } matcher.hitEnd = true; return false; } } /////////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////////// /** * This must be the very first initializer. */ static Node accept = new Node(); static Node lastAccept = new LastNode(); private static class CharPropertyNames { static CharProperty charPropertyFor(String name) { CharPropertyFactory m = map.get(name); return m == null ? null : m.make(); } private static abstract class CharPropertyFactory { abstract CharProperty make(); } private static void defCategory(String name, final int typeMask) { map.put(name, new CharPropertyFactory() { CharProperty make() { return new Category(typeMask);}}); } private static void defRange(String name, final int lower, final int upper) { map.put(name, new CharPropertyFactory() { CharProperty make() { return rangeFor(lower, upper);}}); } private static void defCtype(String name, final int ctype) { map.put(name, new CharPropertyFactory() { CharProperty make() { return new Ctype(ctype);}}); } private static abstract class CloneableProperty extends CharProperty implements Cloneable { public CloneableProperty clone() { try { return (CloneableProperty) super.clone(); } catch (CloneNotSupportedException e) { throw new AssertionError(e); } } } private static void defClone(String name, final CloneableProperty p) { map.put(name, new CharPropertyFactory() { CharProperty make() { return p.clone();}}); } private static final HashMap<String, CharPropertyFactory> map = new HashMap<String, CharPropertyFactory>(); static { // Unicode character property aliases, defined in // http://www.unicode.org/Public/UNIDATA/PropertyValueAliases.txt defCategory("Cn", 1<<Character.UNASSIGNED); defCategory("Lu", 1<<Character.UPPERCASE_LETTER); defCategory("Ll", 1<<Character.LOWERCASE_LETTER); defCategory("Lt", 1<<Character.TITLECASE_LETTER); defCategory("Lm", 1<<Character.MODIFIER_LETTER); defCategory("Lo", 1<<Character.OTHER_LETTER); defCategory("Mn", 1<<Character.NON_SPACING_MARK); defCategory("Me", 1<<Character.ENCLOSING_MARK); defCategory("Mc", 1<<Character.COMBINING_SPACING_MARK); defCategory("Nd", 1<<Character.DECIMAL_DIGIT_NUMBER); defCategory("Nl", 1<<Character.LETTER_NUMBER); defCategory("No", 1<<Character.OTHER_NUMBER); defCategory("Zs", 1<<Character.SPACE_SEPARATOR); defCategory("Zl", 1<<Character.LINE_SEPARATOR); defCategory("Zp", 1<<Character.PARAGRAPH_SEPARATOR); defCategory("Cc", 1<<Character.CONTROL); defCategory("Cf", 1<<Character.FORMAT); defCategory("Co", 1<<Character.PRIVATE_USE); defCategory("Cs", 1<<Character.SURROGATE); defCategory("Pd", 1<<Character.DASH_PUNCTUATION); defCategory("Ps", 1<<Character.START_PUNCTUATION); defCategory("Pe", 1<<Character.END_PUNCTUATION); defCategory("Pc", 1<<Character.CONNECTOR_PUNCTUATION); defCategory("Po", 1<<Character.OTHER_PUNCTUATION); defCategory("Sm", 1<<Character.MATH_SYMBOL); defCategory("Sc", 1<<Character.CURRENCY_SYMBOL); defCategory("Sk", 1<<Character.MODIFIER_SYMBOL); defCategory("So", 1<<Character.OTHER_SYMBOL); defCategory("Pi", 1<<Character.INITIAL_QUOTE_PUNCTUATION); defCategory("Pf", 1<<Character.FINAL_QUOTE_PUNCTUATION); defCategory("L", ((1<<Character.UPPERCASE_LETTER) | (1<<Character.LOWERCASE_LETTER) | (1<<Character.TITLECASE_LETTER) | (1<<Character.MODIFIER_LETTER) | (1<<Character.OTHER_LETTER))); defCategory("M", ((1<<Character.NON_SPACING_MARK) | (1<<Character.ENCLOSING_MARK) | (1<<Character.COMBINING_SPACING_MARK))); defCategory("N", ((1<<Character.DECIMAL_DIGIT_NUMBER) | (1<<Character.LETTER_NUMBER) | (1<<Character.OTHER_NUMBER))); defCategory("Z", ((1<<Character.SPACE_SEPARATOR) | (1<<Character.LINE_SEPARATOR) | (1<<Character.PARAGRAPH_SEPARATOR))); defCategory("C", ((1<<Character.CONTROL) | (1<<Character.FORMAT) | (1<<Character.PRIVATE_USE) | (1<<Character.SURROGATE))); // Other defCategory("P", ((1<<Character.DASH_PUNCTUATION) | (1<<Character.START_PUNCTUATION) | (1<<Character.END_PUNCTUATION) | (1<<Character.CONNECTOR_PUNCTUATION) | (1<<Character.OTHER_PUNCTUATION) | (1<<Character.INITIAL_QUOTE_PUNCTUATION) | (1<<Character.FINAL_QUOTE_PUNCTUATION))); defCategory("S", ((1<<Character.MATH_SYMBOL) | (1<<Character.CURRENCY_SYMBOL) | (1<<Character.MODIFIER_SYMBOL) | (1<<Character.OTHER_SYMBOL))); defCategory("LC", ((1<<Character.UPPERCASE_LETTER) | (1<<Character.LOWERCASE_LETTER) | (1<<Character.TITLECASE_LETTER))); defCategory("LD", ((1<<Character.UPPERCASE_LETTER) | (1<<Character.LOWERCASE_LETTER) | (1<<Character.TITLECASE_LETTER) | (1<<Character.MODIFIER_LETTER) | (1<<Character.OTHER_LETTER) | (1<<Character.DECIMAL_DIGIT_NUMBER))); defRange("L1", 0x00, 0xFF); // Latin-1 map.put(__JOT_PIECE_503__, new CharPropertyFactory() { CharProperty make() { return new All(); }}); // Posix regular expression character classes, defined in // http://www.unix.org/onlinepubs/009695399/basedefs/xbd_chap09.html defRange("ASCII", 0x00, 0x7F); // ASCII defCtype("Alnum", ASCII.ALNUM); // Alphanumeric characters defCtype("Alpha", ASCII.ALPHA); // Alphabetic characters defCtype("Blank", ASCII.BLANK); // Space and tab characters defCtype("Cntrl", ASCII.CNTRL); // Control characters defRange("Digit", '0', '9'); // Numeric characters defCtype("Graph", ASCII.GRAPH); // printable and visible defRange("Lower", 'a', 'z'); // Lower-case alphabetic defRange("Print", 0x20, 0x7E); // Printable characters defCtype("Punct", ASCII.PUNCT); // Punctuation characters defCtype("Space", ASCII.SPACE); // Space characters defRange("Upper", 'A', 'Z'); // Upper-case alphabetic defCtype("XDigit",ASCII.XDIGIT); // hexadecimal digits // Java character properties, defined by methods in Character.java defClone(__JOT_PIECE_517__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isLowerCase(ch);}}); defClone(__JOT_PIECE_518__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isUpperCase(ch);}}); defClone(__JOT_PIECE_519__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isTitleCase(ch);}}); defClone(__JOT_PIECE_520__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isDigit(ch);}}); defClone(__JOT_PIECE_521__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isDefined(ch);}}); defClone(__JOT_PIECE_522__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isLetter(ch);}}); defClone(__JOT_PIECE_523__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isLetterOrDigit(ch);}}); defClone(__JOT_PIECE_524__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isJavaIdentifierStart(ch);}}); defClone(__JOT_PIECE_525__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isJavaIdentifierPart(ch);}}); defClone(__JOT_PIECE_526__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isUnicodeIdentifierStart(ch);}}); defClone(__JOT_PIECE_527__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isUnicodeIdentifierPart(ch);}}); defClone(__JOT_PIECE_528__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isIdentifierIgnorable(ch);}}); defClone(__JOT_PIECE_529__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isSpaceChar(ch);}}); defClone(__JOT_PIECE_530__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isWhitespace(ch);}}); defClone(__JOT_PIECE_531__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isISOControl(ch);}}); defClone(__JOT_PIECE_532__, new CloneableProperty() { boolean isSatisfiedBy(int ch) { return Character.isMirrored(ch);}}); } } }
