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
/* * @(#)Scanner.java 1.27 06/06/28 * * Copyright 2006 Sun Microsystems, Inc. All rights reserved. * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms. */ package java.util; import java.util.regex.*; import java.io.*; import java.math.*; import java.nio.*; import java.nio.channels.*; import java.nio.charset.*; import java.text.*; import java.util.Locale; import sun.misc.LRUCache; /** * A simple text scanner which can parse primitive types and strings using * regular expressions. * * <p>A <code>Scanner</code> breaks its input into tokens using a * delimiter pattern, which by default matches whitespace. The resulting * tokens may then be converted into values of different types using the * various <tt>next</tt> methods. * * <p>For example, this code allows a user to read a number from * <tt>System.in</tt>: * <blockquote><pre> * Scanner sc = new Scanner(System.in); * int i = sc.nextInt(); * </pre></blockquote> * * <p>As another example, this code allows <code>long</code> types to be * assigned from entries in a file <code>myNumbers</code>: * <blockquote><pre> * Scanner sc = new Scanner(new File("myNumbers")); * while (sc.hasNextLong()) { * long aLong = sc.nextLong(); * }</pre></blockquote> * * <p>The scanner can also use delimiters other than whitespace. This * example reads several items in from a string: *<blockquote><pre> * String input = "1 fish 2 fish red fish blue fish"; * Scanner s = new Scanner(input).useDelimiter("\\s*fish\\s*"); * System.out.println(s.nextInt()); * System.out.println(s.nextInt()); * System.out.println(s.next()); * System.out.println(s.next()); * s.close(); </pre></blockquote> * <p> * prints the following output: * <blockquote><pre> * 1 * 2 * red * blue </pre></blockquote> * * <p>The same output can be generated with this code, which uses a regular * expression to parse all four tokens at once: *<blockquote><pre> * String input = "1 fish 2 fish red fish blue fish"; * Scanner s = new Scanner(input); * s.findInLine("(\\d+) fish (\\d+) fish (\\w+) fish (\\w+)"); * MatchResult result = s.match(); * for (int i=1; i<=result.groupCount(); i++) * System.out.println(result.group(i)); * s.close(); </pre></blockquote> * * <p>The <a name="default-delimiter">default whitespace delimiter</a> used * by a scanner is as recognized by {@link java.lang.Character}.{@link * java.lang.Character#isWhitespace(char) isWhitespace}. The {@link #reset} * method will reset the value of the scanner's delimiter to the default * whitespace delimiter regardless of whether it was previously changed. * * <p>A scanning operation may block waiting for input. * * <p>The {@link #next} and {@link #hasNext} methods and their * primitive-type companion methods (such as {@link #nextInt} and * {@link #hasNextInt}) first skip any input that matches the delimiter * pattern, and then attempt to return the next token. Both <tt>hasNext</tt> * and <tt>next</tt> methods may block waiting for further input. Whether a * <tt>hasNext</tt> method blocks has no connection to whether or not its * associated <tt>next</tt> method will block. * * <p> The {@link #findInLine}, {@link #findWithinHorizon}, and {@link #skip} * methods operate independently of the delimiter pattern. These methods will * attempt to match the specified pattern with no regard to delimiters in the * input and thus can be used in special circumstances where delimiters are * not relevant. These methods may block waiting for more input. * * <p>When a scanner throws an {@link InputMismatchException}, the scanner * will not pass the token that caused the exception, so that it may be * retrieved or skipped via some other method. * * <p>Depending upon the type of delimiting pattern, empty tokens may be * returned. For example, the pattern <tt>"\\s+"</tt> will return no empty * tokens since it matches multiple instances of the delimiter. The delimiting * pattern <tt>"\\s"</tt> could return empty tokens since it only passes one * space at a time. * * <p> A scanner can read text from any object which implements the {@link * java.lang.Readable} interface. If an invocation of the underlying * readable's {@link java.lang.Readable#read} method throws an {@link * java.io.IOException} then the scanner assumes that the end of the input * has been reached. The most recent <tt>IOException</tt> thrown by the * underlying readable can be retrieved via the {@link #ioException} method. * * <p>When a <code>Scanner</code> is closed, it will close its input source * if the source implements the {@link java.io.Closeable} interface. * * <p>A <code>Scanner</code> is not safe for multithreaded use without * external synchronization. * * <p>Unless otherwise mentioned, passing a <code>null</code> parameter into * any method of a <code>Scanner</code> will cause a * <code>NullPointerException</code> to be thrown. * * <p>A scanner will default to interpreting numbers as decimal unless a * different radix has been set by using the {@link #useRadix} method. The * {@link #reset} method will reset the value of the scanner's radix to * <code>10</code> regardless of whether it was previously changed. * * <a name="localized-numbers"> * <h4> Localized numbers </h4> * * <p> An instance of this class is capable of scanning numbers in the standard * formats as well as in the formats of the scanner's locale. A scanner's * <a name="initial-locale">initial locale </a>is the value returned by the {@link * java.util.Locale#getDefault} method; it may be changed via the {@link * #useLocale} method. The {@link #reset} method will reset the value of the * scanner's locale to the initial locale regardless of whether it was * previously changed. * * <p>The localized formats are defined in terms of the following parameters, * which for a particular locale are taken from that locale's {@link * java.text.DecimalFormat DecimalFormat} object, <tt>df</tt>, and its and * {@link java.text.DecimalFormatSymbols DecimalFormatSymbols} object, * <tt>dfs</tt>. * * <blockquote><table> * <tr><td valign="top"><i>LocalGroupSeparator </i></td> * <td valign="top">The character used to separate thousands groups, * <i>i.e.,</i> <tt>dfs.</tt>{@link * java.text.DecimalFormatSymbols#getGroupingSeparator * getGroupingSeparator()}</td></tr> * <tr><td valign="top"><i>LocalDecimalSeparator </i></td> * <td valign="top">The character used for the decimal point, * <i>i.e.,</i> <tt>dfs.</tt>{@link * java.text.DecimalFormatSymbols#getDecimalSeparator * getDecimalSeparator()}</td></tr> * <tr><td valign="top"><i>LocalPositivePrefix </i></td> * <td valign="top">The string that appears before a positive number (may * be empty), <i>i.e.,</i> <tt>df.</tt>{@link * java.text.DecimalFormat#getPositivePrefix * getPositivePrefix()}</td></tr> * <tr><td valign="top"><i>LocalPositiveSuffix </i></td> * <td valign="top">The string that appears after a positive number (may be * empty), <i>i.e.,</i> <tt>df.</tt>{@link * java.text.DecimalFormat#getPositiveSuffix * getPositiveSuffix()}</td></tr> * <tr><td valign="top"><i>LocalNegativePrefix </i></td> * <td valign="top">The string that appears before a negative number (may * be empty), <i>i.e.,</i> <tt>df.</tt>{@link * java.text.DecimalFormat#getNegativePrefix * getNegativePrefix()}</td></tr> * <tr><td valign="top"><i>LocalNegativeSuffix </i></td> * <td valign="top">The string that appears after a negative number (may be * empty), <i>i.e.,</i> <tt>df.</tt>{@link * java.text.DecimalFormat#getNegativeSuffix * getNegativeSuffix()}</td></tr> * <tr><td valign="top"><i>LocalNaN </i></td> * <td valign="top">The string that represents not-a-number for * floating-point values, * <i>i.e.,</i> <tt>dfs.</tt>{@link * java.text.DecimalFormatSymbols#getNaN * getNaN()}</td></tr> * <tr><td valign="top"><i>LocalInfinity </i></td> * <td valign="top">The string that represents infinity for floating-point * values, <i>i.e.,</i> <tt>dfs.</tt>{@link * java.text.DecimalFormatSymbols#getInfinity * getInfinity()}</td></tr> * </table></blockquote> * * <a name="number-syntax"> * <h4> Number syntax </h4> * * <p> The strings that can be parsed as numbers by an instance of this class * are specified in terms of the following regular-expression grammar, where * Rmax is the highest digit in the radix being used (for example, Rmax is 9 * in base 10). * * <p> * <table cellspacing=0 cellpadding=0 align=center> * * <tr><td valign=top align=right><i>NonASCIIDigit</i> ::</td> * <td valign=top>= A non-ASCII character c for which * {@link java.lang.Character#isDigit Character.isDigit}<tt>(c)</tt> * returns true</td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>Non0Digit</i> ::</td> * <td><tt>= [1-</tt><i>Rmax</i><tt>] | </tt><i>NonASCIIDigit</i></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>Digit</i> ::</td> * <td><tt>= [0-</tt><i>Rmax</i><tt>] | </tt><i>NonASCIIDigit</i></td></tr> * * <tr><td> </td></tr> * * <tr><td valign=top align=right><i>GroupedNumeral</i> ::</td> * <td valign=top> * <table cellpadding=0 cellspacing=0> * <tr><td><tt>= ( </tt></td> * <td><i>Non0Digit</i><tt> * </tt><i>Digit</i><tt>? * </tt><i>Digit</i><tt>?</tt></td></tr> * <tr><td></td> * <td><tt>( </tt><i>LocalGroupSeparator</i><tt> * </tt><i>Digit</i><tt> * </tt><i>Digit</i><tt> * </tt><i>Digit</i><tt> )+ )</tt></td></tr> * </table></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>Numeral</i> ::</td> * <td><tt>= ( ( </tt><i>Digit</i><tt>+ ) * | </tt><i>GroupedNumeral</i><tt> )</tt></td></tr> * * <tr><td> </td></tr> * * <tr><td valign=top align=right> * <a name="Integer-regex"><i>Integer</i> ::</td> * <td valign=top><tt>= ( [-+]? ( </tt><i>Numeral</i><tt> * ) )</tt></td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> </tt><i>Numeral</i><tt> * </tt><i>LocalPositiveSuffix</i></td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> </tt><i>Numeral</i><tt> * </tt><i>LocalNegativeSuffix</i></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>DecimalNumeral</i> ::</td> * <td><tt>= </tt><i>Numeral</i></td></tr> * <tr><td></td> * <td><tt>| </tt><i>Numeral</i><tt> * </tt><i>LocalDecimalSeparator</i><tt> * </tt><i>Digit</i><tt>*</tt></td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalDecimalSeparator</i><tt> * </tt><i>Digit</i><tt>+</tt></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>Exponent</i> ::</td> * <td><tt>= ( [eE] [+-]? </tt><i>Digit</i><tt>+ )</tt></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right> * <a name="Decimal-regex"><i>Decimal</i> ::</td> * <td><tt>= ( [-+]? </tt><i>DecimalNumeral</i><tt> * </tt><i>Exponent</i><tt>? )</tt></td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> * </tt><i>DecimalNumeral</i><tt> * </tt><i>LocalPositiveSuffix</i> * </tt><i>Exponent</i><tt>?</td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> * </tt><i>DecimalNumeral</i><tt> * </tt><i>LocalNegativeSuffix</i> * </tt><i>Exponent</i><tt>?</td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>HexFloat</i> ::</td> * <td><tt>= [-+]? 0[xX][0-9a-fA-F]*\.[0-9a-fA-F]+ * ([pP][-+]?[0-9]+)?</tt></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>NonNumber</i> ::</td> * <td valign=top><tt>= NaN * | </tt><i>LocalNan</i><tt> * | Infinity * | </tt><i>LocalInfinity</i></td></tr> * * <tr><td> </td></tr> * * <tr><td align=right><i>SignedNonNumber</i> ::</td> * <td><tt>= ( [-+]? </tt><i>NonNumber</i><tt> )</tt></td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalPositivePrefix</i><tt> * </tt><i>NonNumber</i><tt> * </tt><i>LocalPositiveSuffix</i></td></tr> * <tr><td></td> * <td><tt>| </tt><i>LocalNegativePrefix</i><tt> * </tt><i>NonNumber</i><tt> * </tt><i>LocalNegativeSuffix</i></td></tr> * * <tr><td> </td></tr> * * <tr><td valign=top align=right> * <a name="Float-regex"><i>Float</i> ::</td> * <td valign=top><tt>= </tt><i>Decimal</i><tt></td></tr> * <tr><td></td> * <td><tt>| </tt><i>HexFloat</i><tt></td></tr> * <tr><td></td> * <td><tt>| </tt><i>SignedNonNumber</i><tt></td></tr> * * </table> * </center> * * <p> Whitespace is not significant in the above regular expressions. * * @version 1.27, 06/28/06 * @since 1.5 */ public final class Scanner implements Iterator<String> { // Internal buffer used to hold input private CharBuffer buf; // Size of internal character buffer private static final int BUFFER_SIZE = 1024; // change to 1024; // The index into the buffer currently held by the Scanner private int position; // Internal matcher used for finding delimiters private Matcher matcher; // Pattern used to delimit tokens private Pattern delimPattern; // Pattern found in last hasNext operation private Pattern hasNextPattern; // Position after last hasNext operation private int hasNextPosition; // Result after last hasNext operation private String hasNextResult; // The input source private Readable source; // Boolean is true if source is done private boolean sourceClosed = false; // Boolean indicating more input is required private boolean needInput = false; // Boolean indicating if a delim has been skipped this operation private boolean skipped = false; // A store of a position that the scanner may fall back to private int savedScannerPosition = -1; // A cache of the last primitive type scanned private Object typeCache = null; // Boolean indicating if a match result is available private boolean matchValid = false; // Boolean indicating if this scanner has been closed private boolean closed = false; // The current radix used by this scanner private int radix = 10; // The default radix for this scanner private int defaultRadix = 10; // The locale used by this scanner private Locale locale = null; // A cache of the last few recently used Patterns private LRUCache<String,Pattern> patternCache = new LRUCache<String,Pattern>(7) { protected Pattern create(String s) { return Pattern.compile(s); } protected boolean hasName(Pattern p, String s) { return p.pattern().equals(s); } }; // A holder of the last IOException encountered private IOException lastException; // A pattern for java whitespace private static Pattern WHITESPACE_PATTERN = Pattern.compile( "\\p{javaWhitespace}+"); // A pattern for any token private static Pattern FIND_ANY_PATTERN = Pattern.compile("(?s).*"); // A pattern for non-ASCII digits private static Pattern NON_ASCII_DIGIT = Pattern.compile( "[\\p{javaDigit}&&[^0-9]]"); // Fields and methods to support scanning primitive types /** * Locale dependent values used to scan numbers */ private String groupSeparator = "\\,"; private String decimalSeparator = "\\."; private String nanString = "NaN"; private String infinityString = "Infinity"; private String positivePrefix = ""; private String negativePrefix = "\\-"; private String positiveSuffix = ""; private String negativeSuffix = ""; /** * Fields and an accessor method to match booleans */ private static volatile Pattern boolPattern; private static final String BOOLEAN_PATTERN = "true|false"; private static Pattern boolPattern() { Pattern bp = boolPattern; if (bp == null) boolPattern = bp = Pattern.compile(BOOLEAN_PATTERN, Pattern.CASE_INSENSITIVE); return bp; } /** * Fields and methods to match bytes, shorts, ints, and longs */ private Pattern integerPattern; private String digits = "0123456789abcdefghijklmnopqrstuvwxyz"; private String non0Digit = "[\\p{javaDigit}&&[^0]]"; private int SIMPLE_GROUP_INDEX = 5; private String buildIntegerPatternString() { String radixDigits = digits.substring(0, radix); // \\p{javaDigit} is not guaranteed to be appropriate // here but what can we do? The final authority will be // whatever parse method is invoked, so ultimately the // Scanner will do the right thing String digit = "((?i)["+radixDigits+"]|\\p{javaDigit})"; String groupedNumeral = "("+non0Digit+digit+"?"+digit+"?("+ groupSeparator+digit+digit+digit+")+)"; // digit++ is the possessive form which is necessary for reducing // backtracking that would otherwise cause unacceptable performance String numeral = "(("+ digit+"++)|"+groupedNumeral+")"; String javaStyleInteger = "([-+]?(" + numeral + "))"; String negativeInteger = negativePrefix + numeral + negativeSuffix; String positiveInteger = positivePrefix + numeral + positiveSuffix; return "("+ javaStyleInteger + ")|(" + positiveInteger + ")|(" + negativeInteger + ")"; } private Pattern integerPattern() { if (integerPattern == null) { integerPattern = patternCache.forName(buildIntegerPatternString()); } return integerPattern; } /** * Fields and an accessor method to match line separators */ private static volatile Pattern separatorPattern; private static volatile Pattern linePattern; private static final String LINE_SEPARATOR_PATTERN = "\r\n|[\n\r\u2028\u2029\u0085]"; private static final String LINE_PATTERN = ".*("+LINE_SEPARATOR_PATTERN+")|.+$"; private static Pattern separatorPattern() { Pattern sp = separatorPattern; if (sp == null) separatorPattern = sp = Pattern.compile(LINE_SEPARATOR_PATTERN); return sp; } private static Pattern linePattern() { Pattern lp = linePattern; if (lp == null) linePattern = lp = Pattern.compile(LINE_PATTERN); return lp; } /** * Fields and methods to match floats and doubles */ private Pattern floatPattern; private Pattern decimalPattern; private void buildFloatAndDecimalPattern() { // \\p{javaDigit} may not be perfect, see above String digit = "([0-9]|(\\p{javaDigit}))"; String exponent = "([eE][+-]?"+digit+"+)?"; String groupedNumeral = "("+non0Digit+digit+"?"+digit+"?("+ groupSeparator+digit+digit+digit+")+)"; // Once again digit++ is used for performance, as above String numeral = "(("+digit+"++)|"+groupedNumeral+")"; String decimalNumeral = "("+numeral+"|"+numeral + decimalSeparator + digit + "*+|"+ decimalSeparator + digit + "++)"; String nonNumber = "(NaN|"+nanString+"|Infinity|"+ infinityString+")"; String positiveFloat = "(" + positivePrefix + decimalNumeral + positiveSuffix + exponent + ")"; String negativeFloat = "(" + negativePrefix + decimalNumeral + negativeSuffix + exponent + ")"; String decimal = "(([-+]?" + decimalNumeral + exponent + ")|"+ positiveFloat + "|" + negativeFloat + ")"; String hexFloat = "[-+]?0[xX][0-9a-fA-F]*\\.[0-9a-fA-F]+([pP][-+]?[0-9]+)?"; String positiveNonNumber = "(" + positivePrefix + nonNumber + positiveSuffix + ")"; String negativeNonNumber = "(" + negativePrefix + nonNumber + negativeSuffix + ")"; String signedNonNumber = "(([-+]?"+nonNumber+")|" + positiveNonNumber + "|" + negativeNonNumber + ")"; floatPattern = Pattern.compile(decimal + "|" + hexFloat + "|" + signedNonNumber); decimalPattern = Pattern.compile(decimal); } private Pattern floatPattern() { if (floatPattern == null) { buildFloatAndDecimalPattern(); } return floatPattern; } private Pattern decimalPattern() { if (decimalPattern == null) { buildFloatAndDecimalPattern(); } return decimalPattern; } // Constructors /** * Constructs a <code>Scanner</code> that returns values scanned * from the specified source delimited by the specified pattern. * * @param source A character source implementing the Readable interface * @param pattern A delimiting pattern * @return A scanner with the specified source and pattern */ private Scanner(Readable source, Pattern pattern) { if (source == null) throw new NullPointerException("source"); if (pattern == null) throw new NullPointerException("pattern"); this.source = source; delimPattern = pattern; buf = CharBuffer.allocate(BUFFER_SIZE); buf.limit(0); matcher = delimPattern.matcher(buf); matcher.useTransparentBounds(true); matcher.useAnchoringBounds(false); useLocale(Locale.getDefault()); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified source. * * @param source A character source implementing the {@link Readable} * interface */ public Scanner(Readable source) { this(source, WHITESPACE_PATTERN); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified input stream. Bytes from the stream are converted * into characters using the underlying platform's * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}. * * @param source An input stream to be scanned */ public Scanner(InputStream source) { this(new InputStreamReader(source), WHITESPACE_PATTERN); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified input stream. Bytes from the stream are converted * into characters using the specified charset. * * @param source An input stream to be scanned * @param charsetName The encoding type used to convert bytes from the * stream into characters to be scanned * @throws IllegalArgumentException if the specified character set * does not exist */ public Scanner(InputStream source, String charsetName) { this(makeReadable(source, charsetName), WHITESPACE_PATTERN); } private static Readable makeReadable(InputStream source, String charsetName) { if (source == null) throw new NullPointerException("source"); InputStreamReader isr = null; try { isr = new InputStreamReader(source, charsetName); } catch (UnsupportedEncodingException uee) { IllegalArgumentException iae = new IllegalArgumentException(); iae.initCause(uee); throw iae; } return isr; } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified file. Bytes from the file are converted into * characters using the underlying platform's * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}. * * @param source A file to be scanned * @throws FileNotFoundException if source is not found */ public Scanner(File source) throws FileNotFoundException { this((ReadableByteChannel)(new FileInputStream(source).getChannel())); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified file. Bytes from the file are converted into * characters using the specified charset. * * @param source A file to be scanned * @param charsetName The encoding type used to convert bytes from the file * into characters to be scanned * @throws FileNotFoundException if source is not found * @throws IllegalArgumentException if the specified encoding is * not found */ public Scanner(File source, String charsetName) throws FileNotFoundException { this((ReadableByteChannel)(new FileInputStream(source).getChannel()), charsetName); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified string. * * @param source A string to scan */ public Scanner(String source) { this(new StringReader(source), WHITESPACE_PATTERN); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified channel. Bytes from the source are converted into * characters using the underlying platform's * {@linkplain java.nio.charset.Charset#defaultCharset() default charset}. * * @param source A channel to scan */ public Scanner(ReadableByteChannel source) { this(makeReadable(source), WHITESPACE_PATTERN); } private static Readable makeReadable(ReadableByteChannel source) { if (source == null) throw new NullPointerException("source"); String defaultCharsetName = java.nio.charset.Charset.defaultCharset().name(); return Channels.newReader(source, java.nio.charset.Charset.defaultCharset().name()); } /** * Constructs a new <code>Scanner</code> that produces values scanned * from the specified channel. Bytes from the source are converted into * characters using the specified charset. * * @param source A channel to scan * @param charsetName The encoding type used to convert bytes from the * channel into characters to be scanned * @throws IllegalArgumentException if the specified character set * does not exist */ public Scanner(ReadableByteChannel source, String charsetName) { this(makeReadable(source, charsetName), WHITESPACE_PATTERN); } private static Readable makeReadable(ReadableByteChannel source, String charsetName) { if (source == null) throw new NullPointerException("source"); if (!Charset.isSupported(charsetName)) throw new IllegalArgumentException(charsetName); return Channels.newReader(source, charsetName); } // Private primitives used to support scanning private void saveState() { savedScannerPosition = position; } private void revertState() { this.position = savedScannerPosition; savedScannerPosition = -1; skipped = false; } private boolean revertState(boolean b) { this.position = savedScannerPosition; savedScannerPosition = -1; skipped = false; return b; } private void cacheResult() { hasNextResult = matcher.group(); hasNextPosition = matcher.end(); hasNextPattern = matcher.pattern(); } private void cacheResult(String result) { hasNextResult = result; hasNextPosition = matcher.end(); hasNextPattern = matcher.pattern(); } // Clears both regular cache and type cache private void clearCaches() { hasNextPattern = null; typeCache = null; } // Also clears the both the regular cache and the type cache private String getCachedResult() { position = hasNextPosition; hasNextPattern = null; typeCache = null; return hasNextResult; } // Also clears the both the regular cache and the type cache private void useTypeCache() { if (closed) throw new IllegalStateException("Scanner closed"); position = hasNextPosition; hasNextPattern = null; typeCache = null; } // Tries to read more input. May block. private void readInput() { if (buf.limit() == buf.capacity()) makeSpace(); // Prepare to receive data int p = buf.position(); buf.position(buf.limit()); buf.limit(buf.capacity()); int n = 0; try { n = source.read(buf); } catch (IOException ioe) { lastException = ioe; n = -1; } if (n == -1) { sourceClosed = true; needInput = false; } if (n > 0) needInput = false; // Restore current position and limit for reading buf.limit(buf.position()); buf.position(p); } // After this method is called there will either be an exception // or else there will be space in the buffer private boolean makeSpace() { clearCaches(); int offset = savedScannerPosition == -1 ? position : savedScannerPosition; buf.position(offset); // Gain space by compacting buffer if (offset > 0) { buf.compact(); translateSavedIndexes(offset); position -= offset; buf.flip(); return true; } // Gain space by growing buffer int newSize = buf.capacity() * 2; CharBuffer newBuf = CharBuffer.allocate(newSize); newBuf.put(buf); newBuf.flip(); translateSavedIndexes(offset); position -= offset; buf = newBuf; matcher.reset(buf); return true; } // When a buffer compaction/reallocation occurs the saved indexes must // be modified appropriately private void translateSavedIndexes(int offset) { if (savedScannerPosition != -1) savedScannerPosition -= offset; } // If we are at the end of input then NoSuchElement; // If there is still input left then InputMismatch private void throwFor() { skipped = false; if ((sourceClosed) && (position == buf.limit())) throw new NoSuchElementException(); else throw new InputMismatchException(); } // Returns true if a complete token or partial token is in the buffer. // It is not necessary to find a complete token since a partial token // means that there will be another token with or without more input. private boolean hasTokenInBuffer() { matchValid = false; matcher.usePattern(delimPattern); matcher.region(position, buf.limit()); // Skip delims first if (matcher.lookingAt()) position = matcher.end(); // If we are sitting at the end, no more tokens in buffer if (position == buf.limit()) return false; return true; } /* * Returns a "complete token" that matches the specified pattern * * A token is complete if surrounded by delims; a partial token * is prefixed by delims but not postfixed by them * * The position is advanced to the end of that complete token * * Pattern == null means accept any token at all * * Triple return: * 1. valid string means it was found * 2. null with needInput=false means we won't ever find it * 3. null with needInput=true means try again after readInput */ private String getCompleteTokenInBuffer(Pattern pattern) { matchValid = false; // Skip delims first matcher.usePattern(delimPattern); if (!skipped) { // Enforcing only one skip of leading delims matcher.region(position, buf.limit()); if (matcher.lookingAt()) { // If more input could extend the delimiters then we must wait // for more input if (matcher.hitEnd() && !sourceClosed) { needInput = true; return null; } // The delims were whole and the matcher should skip them skipped = true; position = matcher.end(); } } // If we are sitting at the end, no more tokens in buffer if (position == buf.limit()) { if (sourceClosed) return null; needInput = true; return null; } // Must look for next delims. Simply attempting to match the // pattern at this point may find a match but it might not be // the first longest match because of missing input, or it might // match a partial token instead of the whole thing. // Then look for next delims matcher.region(position, buf.limit()); boolean foundNextDelim = matcher.find(); if (foundNextDelim && (matcher.end() == position)) { // Zero length delimiter match; we should find the next one // using the automatic advance past a zero length match; // Otherwise we have just found the same one we just skipped foundNextDelim = matcher.find(); } if (foundNextDelim) { // In the rare case that more input could cause the match // to be lost and there is more input coming we must wait // for more input. Note that hitting the end is okay as long // as the match cannot go away. It is the beginning of the // next delims we want to be sure about, we don't care if // they potentially extend further. if (matcher.requireEnd() && !sourceClosed) { needInput = true; return null; } int tokenEnd = matcher.start(); // There is a complete token. if (pattern == null) { // Must continue with match to provide valid MatchResult pattern = FIND_ANY_PATTERN; } // Attempt to match against the desired pattern matcher.usePattern(pattern); matcher.region(position, tokenEnd); if (matcher.matches()) { String s = matcher.group(); position = matcher.end(); return s; } else { // Complete token but it does not match return null; } } // If we can't find the next delims but no more input is coming, // then we can treat the remainder as a whole token if (sourceClosed) { if (pattern == null) { // Must continue with match to provide valid MatchResult pattern = FIND_ANY_PATTERN; } // Last token; Match the pattern here or throw matcher.usePattern(pattern); matcher.region(position, buf.limit()); if (matcher.matches()) { String s = matcher.group(); position = matcher.end(); return s; } // Last piece does not match return null; } // There is a partial token in the buffer; must read more // to complete it needInput = true; return null; } // Finds the specified pattern in the buffer up to horizon. // Returns a match for the specified input pattern. private String findPatternInBuffer(Pattern pattern, int horizon) { matchValid = false; matcher.usePattern(pattern); int bufferLimit = buf.limit(); int horizonLimit = -1; int searchLimit = bufferLimit; if (horizon > 0) { horizonLimit = position + horizon; if (horizonLimit < bufferLimit) searchLimit = horizonLimit; } matcher.region(position, searchLimit); if (matcher.find()) { if (matcher.hitEnd() && (!sourceClosed)) { // The match may be longer if didn't hit horizon or real end if (searchLimit != horizonLimit) { // Hit an artificial end; try to extend the match needInput = true; return null; } // The match could go away depending on what is next if ((searchLimit == horizonLimit) && matcher.requireEnd()) { // Rare case: we hit the end of input and it happens // that it is at the horizon and the end of input is // required for the match. needInput = true; return null; } } // Did not hit end, or hit real end, or hit horizon position = matcher.end(); return matcher.group(); } if (sourceClosed) return null; // If there is no specified horizon, or if we have not searched // to the specified horizon yet, get more input if ((horizon == 0) || (searchLimit != horizonLimit)) needInput = true; return null; } // Returns a match for the specified input pattern anchored at // the current position private String matchPatternInBuffer(Pattern pattern) { matchValid = false; matcher.usePattern(pattern); matcher.region(position, buf.limit()); if (matcher.lookingAt()) { if (matcher.hitEnd() && (!sourceClosed)) { // Get more input and try again needInput = true; return null; } position = matcher.end(); return matcher.group(); } if (sourceClosed) return null; // Read more to find pattern needInput = true; return null; } // Throws if the scanner is closed private void ensureOpen() { if (closed) throw new IllegalStateException("Scanner closed"); } // Public methods /** * Closes this scanner. * * <p> If this scanner has not yet been closed then if its underlying * {@linkplain java.lang.Readable readable} also implements the {@link * java.io.Closeable} interface then the readable's <tt>close</tt> method * will be invoked. If this scanner is already closed then invoking this * method will have no effect. * * <p>Attempting to perform search operations after a scanner has * been closed will result in an {@link IllegalStateException}. * */ public void close() { if (closed) return; if (source instanceof Closeable) { try { ((Closeable)source).close(); } catch (IOException ioe) { lastException = ioe; } } sourceClosed = true; source = null; closed = true; } /** * Returns the <code>IOException</code> last thrown by this * <code>Scanner</code>'s underlying <code>Readable</code>. This method * returns <code>null</code> if no such exception exists. * * @return the last exception thrown by this scanner's readable */ public IOException ioException() { return lastException; } /** * Returns the <code>Pattern</code> this <code>Scanner</code> is currently * using to match delimiters. * * @return this scanner's delimiting pattern. */ public Pattern delimiter() { return delimPattern; } /** * Sets this scanner's delimiting pattern to the specified pattern. * * @param pattern A delimiting pattern * @return this scanner */ public Scanner useDelimiter(Pattern pattern) { delimPattern = pattern; return this; } /** * Sets this scanner's delimiting pattern to a pattern constructed from * the specified <code>String</code>. * * <p> An invocation of this method of the form * <tt>useDelimiter(pattern)</tt> behaves in exactly the same way as the * invocation <tt>useDelimiter(Pattern.compile(pattern))</tt>. * * <p> Invoking the {@link #reset} method will set the scanner's delimiter * to the <a href= "#default-delimiter">default</a>. * * @param pattern A string specifying a delimiting pattern * @return this scanner */ public Scanner useDelimiter(String pattern) { delimPattern = patternCache.forName(pattern); return this; } /** * Returns this scanner's locale. * * <p>A scanner's locale affects many elements of its default * primitive matching regular expressions; see * <a href= "#localized-numbers">localized numbers</a> above. * * @return this scanner's locale */ public Locale locale() { return this.locale; } /** * Sets this scanner's locale to the specified locale. * * <p>A scanner's locale affects many elements of its default * primitive matching regular expressions; see * <a href= "#localized-numbers">localized numbers</a> above. * * <p>Invoking the {@link #reset} method will set the scanner's locale to * the <a href= "#initial-locale">initial locale</a>. * * @param locale A string specifying the locale to use * @return this scanner */ public Scanner useLocale(Locale locale) { if (locale.equals(this.locale)) return this; this.locale = locale; DecimalFormat df = (DecimalFormat)NumberFormat.getNumberInstance(locale); DecimalFormatSymbols dfs = DecimalFormatSymbols.getInstance(locale); // These must be literalized to avoid collision with regex // metacharacters such as dot or parenthesis groupSeparator = "\\" + dfs.getGroupingSeparator(); decimalSeparator = "\\" + dfs.getDecimalSeparator(); // Quoting the nonzero length locale-specific things // to avoid potential conflict with metacharacters nanString = "\\Q" + dfs.getNaN() + "\\E"; infinityString = "\\Q" + dfs.getInfinity() + "\\E"; positivePrefix = df.getPositivePrefix(); if (positivePrefix.length() > 0) positivePrefix = "\\Q" + positivePrefix + "\\E"; negativePrefix = df.getNegativePrefix(); if (negativePrefix.length() > 0) negativePrefix = "\\Q" + negativePrefix + "\\E"; positiveSuffix = df.getPositiveSuffix(); if (positiveSuffix.length() > 0) positiveSuffix = "\\Q" + positiveSuffix + "\\E"; negativeSuffix = df.getNegativeSuffix(); if (negativeSuffix.length() > 0) negativeSuffix = "\\Q" + negativeSuffix + "\\E"; // Force rebuilding and recompilation of locale dependent // primitive patterns integerPattern = null; floatPattern = null; return this; } /** * Returns this scanner's default radix. * * <p>A scanner's radix affects elements of its default * number matching regular expressions; see * <a href= "#localized-numbers">localized numbers</a> above. * * @return the default radix of this scanner */ public int radix() { return this.defaultRadix; } /** * Sets this scanner's default radix to the specified radix. * * <p>A scanner's radix affects elements of its default * number matching regular expressions; see * <a href= "#localized-numbers">localized numbers</a> above. * * <p>If the radix is less than <code>Character.MIN_RADIX</code> * or greater than <code>Character.MAX_RADIX</code>, then an * <code>IllegalArgumentException</code> is thrown. * * <p>Invoking the {@link #reset} method will set the scanner's radix to * <code>10</code>. * * @param radix The radix to use when scanning numbers * @return this scanner * @throws IllegalArgumentException if radix is out of range */ public Scanner useRadix(int radix) { if ((radix < Character.MIN_RADIX) || (radix > Character.MAX_RADIX)) throw new IllegalArgumentException("radix:"+radix); if (this.defaultRadix == radix) return this; this.defaultRadix = radix; // Force rebuilding and recompilation of radix dependent patterns integerPattern = null; return this; } // The next operation should occur in the specified radix but // the default is left untouched. private void setRadix(int radix) { if (this.radix != radix) { // Force rebuilding and recompilation of radix dependent patterns integerPattern = null; this.radix = radix; } } /** * Returns the match result of the last scanning operation performed * by this scanner. This method throws <code>IllegalStateException</code> * if no match has been performed, or if the last match was * not successful. * * <p>The various <code>next</code>methods of <code>Scanner</code> * make a match result available if they complete without throwing an * exception. For instance, after an invocation of the {@link #nextInt} * method that returned an int, this method returns a * <code>MatchResult</code> for the search of the * <a href="#Integer-regex"><i>Integer</i></a> regular expression * defined above. Similarly the {@link #findInLine}, * {@link #findWithinHorizon}, and {@link #skip} methods will make a * match available if they succeed. * * @return a match result for the last match operation * @throws IllegalStateException If no match result is available */ public MatchResult match() { if (!matchValid) throw new IllegalStateException("No match result available"); return matcher.toMatchResult(); } /** * <p>Returns the string representation of this <code>Scanner</code>. The * string representation of a <code>Scanner</code> contains information * that may be useful for debugging. The exact format is unspecified. * * @return The string representation of this scanner */ public String toString() { StringBuilder sb = new StringBuilder(); sb.append("java.util.Scanner"); sb.append("[delimiters=" + delimPattern + "]"); sb.append("[position=" + position + "]"); sb.append("[match valid=" + matchValid + "]"); sb.append("[need input=" + needInput + "]"); sb.append("[source closed=" + sourceClosed + "]"); sb.append("[skipped=" + skipped + "]"); sb.append("[group separator=" + groupSeparator + "]"); sb.append("[decimal separator=" + decimalSeparator + "]"); sb.append("[positive prefix=" + positivePrefix + "]"); sb.append("[negative prefix=" + negativePrefix + "]"); sb.append("[positive suffix=" + positiveSuffix + "]"); sb.append("[negative suffix=" + negativeSuffix + "]"); sb.append("[NaN string=" + nanString + "]"); sb.append("[infinity string=" + infinityString + "]"); return sb.toString(); } /** * Returns true if this scanner has another token in its input. * This method may block while waiting for input to scan. * The scanner does not advance past any input. * * @return true if and only if this scanner has another token * @throws IllegalStateException if this scanner is closed * @see java.util.Iterator */ public boolean hasNext() { ensureOpen(); saveState(); while (!sourceClosed) { if (hasTokenInBuffer()) return revertState(true); readInput(); } boolean result = hasTokenInBuffer(); return revertState(result); } /** * Finds and returns the next complete token from this scanner. * A complete token is preceded and followed by input that matches * the delimiter pattern. This method may block while waiting for input * to scan, even if a previous invocation of {@link #hasNext} returned * <code>true</code>. * * @return the next token * @throws NoSuchElementException if no more tokens are available * @throws IllegalStateException if this scanner is closed * @see java.util.Iterator */ public String next() { ensureOpen(); clearCaches(); while (true) { String token = getCompleteTokenInBuffer(null); if (token != null) { matchValid = true; skipped = false; return token; } if (needInput) readInput(); else throwFor(); } } /** * The remove operation is not supported by this implementation of * <code>Iterator</code>. * * @throws UnsupportedOperationException if this method is invoked. * @see java.util.Iterator */ public void remove() { throw new UnsupportedOperationException(); } /** * Returns true if the next token matches the pattern constructed from the * specified string. The scanner does not advance past any input. * * <p> An invocation of this method of the form <tt>hasNext(pattern)</tt> * behaves in exactly the same way as the invocation * <tt>hasNext(Pattern.compile(pattern))</tt>. * * @param pattern a string specifying the pattern to scan * @return true if and only if this scanner has another token matching * the specified pattern * @throws IllegalStateException if this scanner is closed */ public boolean hasNext(String pattern) { return hasNext(patternCache.forName(pattern)); } /** * Returns the next token if it matches the pattern constructed from the * specified string. If the match is successful, the scanner advances * past the input that matched the pattern. * * <p> An invocation of this method of the form <tt>next(pattern)</tt> * behaves in exactly the same way as the invocation * <tt>next(Pattern.compile(pattern))</tt>. * * @param pattern a string specifying the pattern to scan * @return the next token * @throws NoSuchElementException if no such tokens are available * @throws IllegalStateException if this scanner is closed */ public String next(String pattern) { return next(patternCache.forName(pattern)); } /** * Returns true if the next complete token matches the specified pattern. * A complete token is prefixed and postfixed by input that matches * the delimiter pattern. This method may block while waiting for input. * The scanner does not advance past any input. * * @param pattern the pattern to scan for * @return true if and only if this scanner has another token matching * the specified pattern * @throws IllegalStateException if this scanner is closed */ public boolean hasNext(Pattern pattern) { ensureOpen(); if (pattern == null) throw new NullPointerException(); hasNextPattern = null; saveState(); while (true) { if (getCompleteTokenInBuffer(pattern) != null) { matchValid = true; cacheResult(); return revertState(true); } if (needInput) readInput(); else return revertState(false); } } /** * Returns the next token if it matches the specified pattern. This * method may block while waiting for input to scan, even if a previous * invocation of {@link #hasNext(Pattern)} returned <code>true</code>. * If the match is successful, the scanner advances past the input that * matched the pattern. * * @param pattern the pattern to scan for * @return the next token * @throws NoSuchElementException if no more tokens are available * @throws IllegalStateException if this scanner is closed */ public String next(Pattern pattern) { ensureOpen(); if (pattern == null) throw new NullPointerException(); // Did we already find this pattern? if (hasNextPattern == pattern) return getCachedResult(); clearCaches(); // Search for the pattern while (true) { String token = getCompleteTokenInBuffer(pattern); if (token != null) { matchValid = true; skipped = false; return token; } if (needInput) readInput(); else throwFor(); } } /** * Returns true if there is another line in the input of this scanner. * This method may block while waiting for input. The scanner does not * advance past any input. * * @return true if and only if this scanner has another line of input * @throws IllegalStateException if this scanner is closed */ public boolean hasNextLine() { saveState(); String result = findWithinHorizon(linePattern(), 0); if (result != null) { MatchResult mr = this.match(); String lineSep = mr.group(1); if (lineSep != null) { result = result.substring(0, result.length() - lineSep.length()); cacheResult(result); } else { cacheResult(); } } revertState(); return (result != null); } /** * Advances this scanner past the current line and returns the input * that was skipped. * * This method returns the rest of the current line, excluding any line * separator at the end. The position is set to the beginning of the next * line. * * <p>Since this method continues to search through the input looking * for a line separator, it may buffer all of the input searching for * the line to skip if no line separators are present. * * @return the line that was skipped * @throws NoSuchElementException if no line was found * @throws IllegalStateException if this scanner is closed */ public String nextLine() { if (hasNextPattern == linePattern()) return getCachedResult(); clearCaches(); String result = findWithinHorizon(linePattern, 0); if (result == null) throw new NoSuchElementException("No line found"); MatchResult mr = this.match(); String lineSep = mr.group(1); if (lineSep != null) result = result.substring(0, result.length() - lineSep.length()); if (result == null) throw new NoSuchElementException(); else return result; } // Public methods that ignore delimiters /** * Attempts to find the next occurrence of a pattern constructed from the * specified string, ignoring delimiters. * * <p>An invocation of this method of the form <tt>findInLine(pattern)</tt> * behaves in exactly the same way as the invocation * <tt>findInLine(Pattern.compile(pattern))</tt>. * * @param pattern a string specifying the pattern to search for * @return the text that matched the specified pattern * @throws IllegalStateException if this scanner is closed */ public String findInLine(String pattern) { return findInLine(patternCache.forName(pattern)); } /** * Attempts to find the next occurrence of the specified pattern ignoring * delimiters. If the pattern is found before the next line separator, the * scanner advances past the input that matched and returns the string that * matched the pattern. * If no such pattern is detected in the input up to the next line * separator, then <code>null</code> is returned and the scanner's * position is unchanged. This method may block waiting for input that * matches the pattern. * * <p>Since this method continues to search through the input looking * for the specified pattern, it may buffer all of the input searching for * the desired token if no line separators are present. * * @param pattern the pattern to scan for * @return the text that matched the specified pattern * @throws IllegalStateException if this scanner is closed */ public String findInLine(Pattern pattern) { ensureOpen(); if (pattern == null) throw new NullPointerException(); clearCaches(); // Expand buffer to include the next newline or end of input int endPosition = 0; saveState(); while (true) { String token = findPatternInBuffer(separatorPattern(), 0); if (token != null) { endPosition = matcher.start(); break; // up to next newline } if (needInput) { readInput(); } else { endPosition = buf.limit(); break; // up to end of input } } revertState(); int horizonForLine = endPosition - position; // If there is nothing between the current pos and the next // newline simply return null, invoking findWithinHorizon // with "horizon=0" will scan beyond the line bound. if (horizonForLine == 0) return null; // Search for the pattern return findWithinHorizon(pattern, horizonForLine); } /** * Attempts to find the next occurrence of a pattern constructed from the * specified string, ignoring delimiters. * * <p>An invocation of this method of the form * <tt>findWithinHorizon(pattern)</tt> behaves in exactly the same way as * the invocation * <tt>findWithinHorizon(Pattern.compile(pattern, horizon))</tt>. * * @param pattern a string specifying the pattern to search for * @return the text that matched the specified pattern * @throws IllegalStateException if this scanner is closed * @throws IllegalArgumentException if horizon is negative */ public String findWithinHorizon(String pattern, int horizon) { return findWithinHorizon(patternCache.forName(pattern), horizon); } /** * Attempts to find the next occurrence of the specified pattern. * * <p>This method searches through the input up to the specified * search horizon, ignoring delimiters. If the pattern is found the * scanner advances past the input that matched and returns the string * that matched the pattern. If no such pattern is detected then the * null is returned and the scanner's position remains unchanged. This * method may block waiting for input that matches the pattern. * * <p>A scanner will never search more than <code>horizon</code> code * points beyond its current position. Note that a match may be clipped * by the horizon; that is, an arbitrary match result may have been * different if the horizon had been larger. The scanner treats the * horizon as a transparent, non-anchoring bound (see {@link * Matcher#useTransparentBounds} and {@link Matcher#useAnchoringBounds}). * * <p>If horizon is <code>0</code>, then the horizon is ignored and * this method continues to search through the input looking for the * specified pattern without bound. In this case it may buffer all of * the input searching for the pattern. * * <p>If horizon is negative, then an IllegalArgumentException is * thrown. * * @param pattern the pattern to scan for * @return the text that matched the specified pattern * @throws IllegalStateException if this scanner is closed * @throws IllegalArgumentException if horizon is negative */ public String findWithinHorizon(Pattern pattern, int horizon) { ensureOpen(); if (pattern == null) throw new NullPointerException(); if (horizon < 0) throw new IllegalArgumentException("horizon < 0"); clearCaches(); // Search for the pattern while (true) { String token = findPatternInBuffer(pattern, horizon); if (token != null) { matchValid = true; return token; } if (needInput) readInput(); else break; // up to end of input } return null; } /** * Skips input that matches the specified pattern, ignoring delimiters. * This method will skip input if an anchored match of the specified * pattern succeeds. * * <p>If a match to the specified pattern is not found at the * current position, then no input is skipped and a * <tt>NoSuchElementException</tt> is thrown. * * <p>Since this method seeks to match the specified pattern starting at * the scanner's current position, patterns that can match a lot of * input (".*", for example) may cause the scanner to buffer a large * amount of input. * * <p>Note that it is possible to skip something without risking a * <code>NoSuchElementException</code> by using a pattern that can * match nothing, e.g., <code>sc.skip("[ \t]*")</code>. * * @param pattern a string specifying the pattern to skip over * @return this scanner * @throws NoSuchElementException if the specified pattern is not found * @throws IllegalStateException if this scanner is closed */ public Scanner skip(Pattern pattern) { ensureOpen(); if (pattern == null) throw new NullPointerException(); clearCaches(); // Search for the pattern while (true) { String token = matchPatternInBuffer(pattern); if (token != null) { matchValid = true; position = matcher.end(); return this; } if (needInput) readInput(); else throw new NoSuchElementException(); } } /** * Skips input that matches a pattern constructed from the specified * string. * * <p> An invocation of this method of the form <tt>skip(pattern)</tt> * behaves in exactly the same way as the invocation * <tt>skip(Pattern.compile(pattern))</tt>. * * @param pattern a string specifying the pattern to skip over * @return this scanner * @throws IllegalStateException if this scanner is closed */ public Scanner skip(String pattern) { return skip(patternCache.forName(pattern)); } // Convenience methods for scanning primitives /** * Returns true if the next token in this scanner's input can be * interpreted as a boolean value using a case insensitive pattern * created from the string "true|false". The scanner does not * advance past the input that matched. * * @return true if and only if this scanner's next token is a valid * boolean value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextBoolean() { return hasNext(boolPattern()); } /** * Scans the next token of the input into a boolean value and returns * that value. This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid boolean value. * If the match is successful, the scanner advances past the input that * matched. * * @return the boolean scanned from the input * @throws InputMismatchException if the next token is not a valid boolean * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public boolean nextBoolean() { clearCaches(); return Boolean.parseBoolean(next(boolPattern())); } /** * Returns true if the next token in this scanner's input can be * interpreted as a byte value in the default radix using the * {@link #nextByte} method. The scanner does not advance past any input. * * @return true if and only if this scanner's next token is a valid * byte value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextByte() { return hasNextByte(defaultRadix); } /** * Returns true if the next token in this scanner's input can be * interpreted as a byte value in the specified radix using the * {@link #nextByte} method. The scanner does not advance past any input. * * @param radix the radix used to interpret the token as a byte value * @return true if and only if this scanner's next token is a valid * byte value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextByte(int radix) { setRadix(radix); boolean result = hasNext(integerPattern()); if (result) { // Cache it try { String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? processIntegerToken(hasNextResult) : hasNextResult; typeCache = Byte.parseByte(s, radix); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a <tt>byte</tt>. * * <p> An invocation of this method of the form * <tt>nextByte()</tt> behaves in exactly the same way as the * invocation <tt>nextByte(radix)</tt>, where <code>radix</code> * is the default radix of this scanner. * * @return the <tt>byte</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public byte nextByte() { return nextByte(defaultRadix); } /** * Scans the next token of the input as a <tt>byte</tt>. * This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid byte value as * described below. If the translation is successful, the scanner advances * past the input that matched. * * <p> If the next token matches the <a * href="#Integer-regex"><i>Integer</i></a> regular expression defined * above then the token is converted into a <tt>byte</tt> value as if by * removing all locale specific prefixes, group separators, and locale * specific suffixes, then mapping non-ASCII digits into ASCII * digits via {@link Character#digit Character.digit}, prepending a * negative sign (-) if the locale specific negative prefixes and suffixes * were present, and passing the resulting string to * {@link Byte#parseByte(String, int) Byte.parseByte} with the * specified radix. * * @param radix the radix used to interpret the token as a byte value * @return the <tt>byte</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public byte nextByte(int radix) { // Check cached result if ((typeCache != null) && (typeCache instanceof Byte) && this.radix == radix) { byte val = ((Byte)typeCache).byteValue(); useTypeCache(); return val; } setRadix(radix); clearCaches(); // Search for next byte try { String s = next(integerPattern()); if (matcher.group(SIMPLE_GROUP_INDEX) == null) s = processIntegerToken(s); return Byte.parseByte(s, radix); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * Returns true if the next token in this scanner's input can be * interpreted as a short value in the default radix using the * {@link #nextShort} method. The scanner does not advance past any input. * * @return true if and only if this scanner's next token is a valid * short value in the default radix * @throws IllegalStateException if this scanner is closed */ public boolean hasNextShort() { return hasNextShort(defaultRadix); } /** * Returns true if the next token in this scanner's input can be * interpreted as a short value in the specified radix using the * {@link #nextShort} method. The scanner does not advance past any input. * * @param radix the radix used to interpret the token as a short value * @return true if and only if this scanner's next token is a valid * short value in the specified radix * @throws IllegalStateException if this scanner is closed */ public boolean hasNextShort(int radix) { setRadix(radix); boolean result = hasNext(integerPattern()); if (result) { // Cache it try { String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? processIntegerToken(hasNextResult) : hasNextResult; typeCache = Short.parseShort(s, radix); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a <tt>short</tt>. * * <p> An invocation of this method of the form * <tt>nextShort()</tt> behaves in exactly the same way as the * invocation <tt>nextShort(radix)</tt>, where <code>radix</code> * is the default radix of this scanner. * * @return the <tt>short</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public short nextShort() { return nextShort(defaultRadix); } /** * Scans the next token of the input as a <tt>short</tt>. * This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid short value as * described below. If the translation is successful, the scanner advances * past the input that matched. * * <p> If the next token matches the <a * href="#Integer-regex"><i>Integer</i></a> regular expression defined * above then the token is converted into a <tt>short</tt> value as if by * removing all locale specific prefixes, group separators, and locale * specific suffixes, then mapping non-ASCII digits into ASCII * digits via {@link Character#digit Character.digit}, prepending a * negative sign (-) if the locale specific negative prefixes and suffixes * were present, and passing the resulting string to * {@link Short#parseShort(String, int) Short.parseShort} with the * specified radix. * * @param radix the radix used to interpret the token as a short value * @return the <tt>short</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public short nextShort(int radix) { // Check cached result if ((typeCache != null) && (typeCache instanceof Short) && this.radix == radix) { short val = ((Short)typeCache).shortValue(); useTypeCache(); return val; } setRadix(radix); clearCaches(); // Search for next short try { String s = next(integerPattern()); if (matcher.group(SIMPLE_GROUP_INDEX) == null) s = processIntegerToken(s); return Short.parseShort(s, radix); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * Returns true if the next token in this scanner's input can be * interpreted as an int value in the default radix using the * {@link #nextInt} method. The scanner does not advance past any input. * * @return true if and only if this scanner's next token is a valid * int value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextInt() { return hasNextInt(defaultRadix); } /** * Returns true if the next token in this scanner's input can be * interpreted as an int value in the specified radix using the * {@link #nextInt} method. The scanner does not advance past any input. * * @param radix the radix used to interpret the token as an int value * @return true if and only if this scanner's next token is a valid * int value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextInt(int radix) { setRadix(radix); boolean result = hasNext(integerPattern()); if (result) { // Cache it try { String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? processIntegerToken(hasNextResult) : hasNextResult; typeCache = Integer.parseInt(s, radix); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * The integer token must be stripped of prefixes, group separators, * and suffixes, non ascii digits must be converted into ascii digits * before parse will accept it. */ private String processIntegerToken(String token) { String result = token.replaceAll(""+groupSeparator, ""); boolean isNegative = false; int preLen = negativePrefix.length(); if ((preLen > 0) && result.startsWith(negativePrefix)) { isNegative = true; result = result.substring(preLen); } int sufLen = negativeSuffix.length(); if ((sufLen > 0) && result.endsWith(negativeSuffix)) { isNegative = true; result = result.substring(result.length() - sufLen, result.length()); } if (isNegative) result = "-" + result; return result; } /** * Scans the next token of the input as an <tt>int</tt>. * * <p> An invocation of this method of the form * <tt>nextInt()</tt> behaves in exactly the same way as the * invocation <tt>nextInt(radix)</tt>, where <code>radix</code> * is the default radix of this scanner. * * @return the <tt>int</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public int nextInt() { return nextInt(defaultRadix); } /** * Scans the next token of the input as an <tt>int</tt>. * This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid int value as * described below. If the translation is successful, the scanner advances * past the input that matched. * * <p> If the next token matches the <a * href="#Integer-regex"><i>Integer</i></a> regular expression defined * above then the token is converted into an <tt>int</tt> value as if by * removing all locale specific prefixes, group separators, and locale * specific suffixes, then mapping non-ASCII digits into ASCII * digits via {@link Character#digit Character.digit}, prepending a * negative sign (-) if the locale specific negative prefixes and suffixes * were present, and passing the resulting string to * {@link Integer#parseInt(String, int) Integer.parseInt} with the * specified radix. * * @param radix the radix used to interpret the token as an int value * @return the <tt>int</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public int nextInt(int radix) { // Check cached result if ((typeCache != null) && (typeCache instanceof Integer) && this.radix == radix) { int val = ((Integer)typeCache).intValue(); useTypeCache(); return val; } setRadix(radix); clearCaches(); // Search for next int try { String s = next(integerPattern()); if (matcher.group(SIMPLE_GROUP_INDEX) == null) s = processIntegerToken(s); return Integer.parseInt(s, radix); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * Returns true if the next token in this scanner's input can be * interpreted as a long value in the default radix using the * {@link #nextLong} method. The scanner does not advance past any input. * * @return true if and only if this scanner's next token is a valid * long value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextLong() { return hasNextLong(defaultRadix); } /** * Returns true if the next token in this scanner's input can be * interpreted as a long value in the specified radix using the * {@link #nextLong} method. The scanner does not advance past any input. * * @param radix the radix used to interpret the token as a long value * @return true if and only if this scanner's next token is a valid * long value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextLong(int radix) { setRadix(radix); boolean result = hasNext(integerPattern()); if (result) { // Cache it try { String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? processIntegerToken(hasNextResult) : hasNextResult; typeCache = Long.parseLong(s, radix); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a <tt>long</tt>. * * <p> An invocation of this method of the form * <tt>nextLong()</tt> behaves in exactly the same way as the * invocation <tt>nextLong(radix)</tt>, where <code>radix</code> * is the default radix of this scanner. * * @return the <tt>long</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public long nextLong() { return nextLong(defaultRadix); } /** * Scans the next token of the input as a <tt>long</tt>. * This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid long value as * described below. If the translation is successful, the scanner advances * past the input that matched. * * <p> If the next token matches the <a * href="#Integer-regex"><i>Integer</i></a> regular expression defined * above then the token is converted into a <tt>long</tt> value as if by * removing all locale specific prefixes, group separators, and locale * specific suffixes, then mapping non-ASCII digits into ASCII * digits via {@link Character#digit Character.digit}, prepending a * negative sign (-) if the locale specific negative prefixes and suffixes * were present, and passing the resulting string to * {@link Long#parseLong(String, int) Long.parseLong} with the * specified radix. * * @param radix the radix used to interpret the token as an int value * @return the <tt>long</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public long nextLong(int radix) { // Check cached result if ((typeCache != null) && (typeCache instanceof Long) && this.radix == radix) { long val = ((Long)typeCache).longValue(); useTypeCache(); return val; } setRadix(radix); clearCaches(); try { String s = next(integerPattern()); if (matcher.group(SIMPLE_GROUP_INDEX) == null) s = processIntegerToken(s); return Long.parseLong(s, radix); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * The float token must be stripped of prefixes, group separators, * and suffixes, non ascii digits must be converted into ascii digits * before parseFloat will accept it. * * If there are non-ascii digits in the token these digits must * be processed before the token is passed to parseFloat. */ private String processFloatToken(String token) { String result = token.replaceAll(groupSeparator, ""); if (!decimalSeparator.equals("\\.")) result = result.replaceAll(decimalSeparator, "."); boolean isNegative = false; int preLen = negativePrefix.length(); if ((preLen > 0) && result.startsWith(negativePrefix)) { isNegative = true; result = result.substring(preLen); } int sufLen = negativeSuffix.length(); if ((sufLen > 0) && result.endsWith(negativeSuffix)) { isNegative = true; result = result.substring(result.length() - sufLen, result.length()); } if (result.equals(nanString)) result = "NaN"; if (result.equals(infinityString)) result = "Infinity"; if (isNegative) result = "-" + result; // Translate non-ASCII digits Matcher m = NON_ASCII_DIGIT.matcher(result); if (m.find()) { StringBuilder inASCII = new StringBuilder(); for (int i=0; i<result.length(); i++) { char nextChar = result.charAt(i); if (Character.isDigit(nextChar)) { int d = Character.digit(nextChar, 10); if (d != -1) inASCII.append(d); else inASCII.append(nextChar); } else { inASCII.append(nextChar); } } result = inASCII.toString(); } return result; } /** * Returns true if the next token in this scanner's input can be * interpreted as a float value using the {@link #nextFloat} * method. The scanner does not advance past any input. * * @return true if and only if this scanner's next token is a valid * float value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextFloat() { setRadix(10); boolean result = hasNext(floatPattern()); if (result) { // Cache it try { String s = processFloatToken(hasNextResult); typeCache = Float.valueOf(Float.parseFloat(s)); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a <tt>float</tt>. * This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid float value as * described below. If the translation is successful, the scanner advances * past the input that matched. * * <p> If the next token matches the <a * href="#Float-regex"><i>Float</i></a> regular expression defined above * then the token is converted into a <tt>float</tt> value as if by * removing all locale specific prefixes, group separators, and locale * specific suffixes, then mapping non-ASCII digits into ASCII * digits via {@link Character#digit Character.digit}, prepending a * negative sign (-) if the locale specific negative prefixes and suffixes * were present, and passing the resulting string to * {@link Float#parseFloat Float.parseFloat}. If the token matches * the localized NaN or infinity strings, then either "Nan" or "Infinity" * is passed to {@link Float#parseFloat(String) Float.parseFloat} as * appropriate. * * @return the <tt>float</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Float</i> * regular expression, or is out of range * @throws NoSuchElementException if input is exhausted * @throws IllegalStateException if this scanner is closed */ public float nextFloat() { // Check cached result if ((typeCache != null) && (typeCache instanceof Float)) { float val = ((Float)typeCache).floatValue(); useTypeCache(); return val; } setRadix(10); clearCaches(); try { return Float.parseFloat(processFloatToken(next(floatPattern()))); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * Returns true if the next token in this scanner's input can be * interpreted as a double value using the {@link #nextDouble} * method. The scanner does not advance past any input. * * @return true if and only if this scanner's next token is a valid * double value * @throws IllegalStateException if this scanner is closed */ public boolean hasNextDouble() { setRadix(10); boolean result = hasNext(floatPattern()); if (result) { // Cache it try { String s = processFloatToken(hasNextResult); typeCache = Double.valueOf(Double.parseDouble(s)); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a <tt>double</tt>. * This method will throw <code>InputMismatchException</code> * if the next token cannot be translated into a valid double value. * If the translation is successful, the scanner advances past the input * that matched. * * <p> If the next token matches the <a * href="#Float-regex"><i>Float</i></a> regular expression defined above * then the token is converted into a <tt>double</tt> value as if by * removing all locale specific prefixes, group separators, and locale * specific suffixes, then mapping non-ASCII digits into ASCII * digits via {@link Character#digit Character.digit}, prepending a * negative sign (-) if the locale specific negative prefixes and suffixes * were present, and passing the resulting string to * {@link Double#parseDouble Double.parseDouble}. If the token matches * the localized NaN or infinity strings, then either "Nan" or "Infinity" * is passed to {@link Double#parseDouble(String) Double.parseDouble} as * appropriate. * * @return the <tt>double</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Float</i> * regular expression, or is out of range * @throws NoSuchElementException if the input is exhausted * @throws IllegalStateException if this scanner is closed */ public double nextDouble() { // Check cached result if ((typeCache != null) && (typeCache instanceof Double)) { double val = ((Double)typeCache).doubleValue(); useTypeCache(); return val; } setRadix(10); clearCaches(); // Search for next float try { return Double.parseDouble(processFloatToken(next(floatPattern()))); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } // Convenience methods for scanning multi precision numbers /** * Returns true if the next token in this scanner's input can be * interpreted as a <code>BigInteger</code> in the default radix using the * {@link #nextBigInteger} method. The scanner does not advance past any * input. * * @return true if and only if this scanner's next token is a valid * <code>BigInteger</code> * @throws IllegalStateException if this scanner is closed */ public boolean hasNextBigInteger() { return hasNextBigInteger(defaultRadix); } /** * Returns true if the next token in this scanner's input can be * interpreted as a <code>BigInteger</code> in the specified radix using * the {@link #nextBigInteger} method. The scanner does not advance past * any input. * * @param radix the radix used to interpret the token as an integer * @return true if and only if this scanner's next token is a valid * <code>BigInteger</code> * @throws IllegalStateException if this scanner is closed */ public boolean hasNextBigInteger(int radix) { setRadix(radix); boolean result = hasNext(integerPattern()); if (result) { // Cache it try { String s = (matcher.group(SIMPLE_GROUP_INDEX) == null) ? processIntegerToken(hasNextResult) : hasNextResult; typeCache = new BigInteger(s, radix); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a {@link java.math.BigInteger * BigInteger}. * * <p> An invocation of this method of the form * <tt>nextBigInteger()</tt> behaves in exactly the same way as the * invocation <tt>nextBigInteger(radix)</tt>, where <code>radix</code> * is the default radix of this scanner. * * @return the <tt>BigInteger</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if the input is exhausted * @throws IllegalStateException if this scanner is closed */ public BigInteger nextBigInteger() { return nextBigInteger(defaultRadix); } /** * Scans the next token of the input as a {@link java.math.BigInteger * BigInteger}. * * <p> If the next token matches the <a * href="#Integer-regex"><i>Integer</i></a> regular expression defined * above then the token is converted into a <tt>BigInteger</tt> value as if * by removing all group separators, mapping non-ASCII digits into ASCII * digits via the {@link Character#digit Character.digit}, and passing the * resulting string to the {@link * java.math.BigInteger#BigInteger(java.lang.String) * BigInteger(String, int)} constructor with the specified radix. * * @param radix the radix used to interpret the token * @return the <tt>BigInteger</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Integer</i> * regular expression, or is out of range * @throws NoSuchElementException if the input is exhausted * @throws IllegalStateException if this scanner is closed */ public BigInteger nextBigInteger(int radix) { // Check cached result if ((typeCache != null) && (typeCache instanceof BigInteger) && this.radix == radix) { BigInteger val = (BigInteger)typeCache; useTypeCache(); return val; } setRadix(radix); clearCaches(); // Search for next int try { String s = next(integerPattern()); if (matcher.group(SIMPLE_GROUP_INDEX) == null) s = processIntegerToken(s); return new BigInteger(s, radix); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * Returns true if the next token in this scanner's input can be * interpreted as a <code>BigDecimal</code> using the * {@link #nextBigDecimal} method. The scanner does not advance past any * input. * * @return true if and only if this scanner's next token is a valid * <code>BigDecimal</code> * @throws IllegalStateException if this scanner is closed */ public boolean hasNextBigDecimal() { setRadix(10); boolean result = hasNext(decimalPattern()); if (result) { // Cache it try { String s = processFloatToken(hasNextResult); typeCache = new BigDecimal(s); } catch (NumberFormatException nfe) { result = false; } } return result; } /** * Scans the next token of the input as a {@link java.math.BigDecimal * BigDecimal}. * * <p> If the next token matches the <a * href="#Decimal-regex"><i>Decimal</i></a> regular expression defined * above then the token is converted into a <tt>BigDecimal</tt> value as if * by removing all group separators, mapping non-ASCII digits into ASCII * digits via the {@link Character#digit Character.digit}, and passing the * resulting string to the {@link * java.math.BigDecimal#BigDecimal(java.lang.String) BigDecimal(String)} * constructor. * * @return the <tt>BigDecimal</tt> scanned from the input * @throws InputMismatchException * if the next token does not match the <i>Decimal</i> * regular expression, or is out of range * @throws NoSuchElementException if the input is exhausted * @throws IllegalStateException if this scanner is closed */ public BigDecimal nextBigDecimal() { // Check cached result if ((typeCache != null) && (typeCache instanceof BigDecimal)) { BigDecimal val = (BigDecimal)typeCache; useTypeCache(); return val; } setRadix(10); clearCaches(); // Search for next float try { String s = processFloatToken(next(decimalPattern())); return new BigDecimal(s); } catch (NumberFormatException nfe) { position = matcher.start(); // don't skip bad token throw new InputMismatchException(nfe.getMessage()); } } /** * Resets this scanner. * * <p> Resetting a scanner discards all of its explicit state * information which may have been changed by invocations of {@link * #useDelimiter}, {@link #useLocale}, or {@link #useRadix}. * * <p> An invocation of this method of the form * <tt>scanner.reset()</tt> behaves in exactly the same way as the * invocation * * <blockquote><pre> * scanner.useDelimiter("\\p{javaWhitespace}+") * .useLocale(Locale.getDefault()) * .useRadix(10); * </pre></blockquote> * * @return this scanner * * @since 1.6 */ public Scanner reset() { delimPattern = WHITESPACE_PATTERN; useLocale(Locale.getDefault()); useRadix(10); clearCaches(); return this; } }
