1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649
use core::{
borrow::Borrow,
panic::{RefUnwindSafe, UnwindSafe},
};
use alloc::{boxed::Box, sync::Arc, vec, vec::Vec};
use regex_syntax::{
ast,
hir::{self, Hir},
};
use crate::{
meta::{
error::BuildError,
strategy::{self, Strategy},
wrappers,
},
nfa::thompson::WhichCaptures,
util::{
captures::{Captures, GroupInfo},
iter,
pool::{Pool, PoolGuard},
prefilter::Prefilter,
primitives::{NonMaxUsize, PatternID},
search::{HalfMatch, Input, Match, MatchKind, PatternSet, Span},
},
};
/// A type alias for our pool of meta::Cache that fixes the type parameters to
/// what we use for the meta regex below.
type CachePool = Pool<Cache, CachePoolFn>;
/// Same as above, but for the guard returned by a pool.
type CachePoolGuard<'a> = PoolGuard<'a, Cache, CachePoolFn>;
/// The type of the closure we use to create new caches. We need to spell out
/// all of the marker traits or else we risk leaking !MARKER impls.
type CachePoolFn =
Box<dyn Fn() -> Cache + Send + Sync + UnwindSafe + RefUnwindSafe>;
/// A regex matcher that works by composing several other regex matchers
/// automatically.
///
/// In effect, a meta regex papers over a lot of the quirks or performance
/// problems in each of the regex engines in this crate. Its goal is to provide
/// an infallible and simple API that "just does the right thing" in the common
/// case.
///
/// A meta regex is the implementation of a `Regex` in the `regex` crate.
/// Indeed, the `regex` crate API is essentially just a light wrapper over
/// this type. This includes the `regex` crate's `RegexSet` API!
///
/// # Composition
///
/// This is called a "meta" matcher precisely because it uses other regex
/// matchers to provide a convenient high level regex API. Here are some
/// examples of how other regex matchers are composed:
///
/// * When calling [`Regex::captures`], instead of immediately
/// running a slower but more capable regex engine like the
/// [`PikeVM`](crate::nfa::thompson::pikevm::PikeVM), the meta regex engine
/// will usually first look for the bounds of a match with a higher throughput
/// regex engine like a [lazy DFA](crate::hybrid). Only when a match is found
/// is a slower engine like `PikeVM` used to find the matching span for each
/// capture group.
/// * While higher throughout engines like the lazy DFA cannot handle
/// Unicode word boundaries in general, they can still be used on pure ASCII
/// haystacks by pretending that Unicode word boundaries are just plain ASCII
/// word boundaries. However, if a haystack is not ASCII, the meta regex engine
/// will automatically switch to a (possibly slower) regex engine that supports
/// Unicode word boundaries in general.
/// * In some cases where a regex pattern is just a simple literal or a small
/// set of literals, an actual regex engine won't be used at all. Instead,
/// substring or multi-substring search algorithms will be employed.
///
/// There are many other forms of composition happening too, but the above
/// should give a general idea. In particular, it may perhaps be surprising
/// that *multiple* regex engines might get executed for a single search. That
/// is, the decision of what regex engine to use is not _just_ based on the
/// pattern, but also based on the dynamic execution of the search itself.
///
/// The primary reason for this composition is performance. The fundamental
/// tension is that the faster engines tend to be less capable, and the more
/// capable engines tend to be slower.
///
/// Note that the forms of composition that are allowed are determined by
/// compile time crate features and configuration. For example, if the `hybrid`
/// feature isn't enabled, or if [`Config::hybrid`] has been disabled, then the
/// meta regex engine will never use a lazy DFA.
///
/// # Synchronization and cloning
///
/// Most of the regex engines in this crate require some kind of mutable
/// "scratch" space to read and write from while performing a search. Since
/// a meta regex composes these regex engines, a meta regex also requires
/// mutable scratch space. This scratch space is called a [`Cache`].
///
/// Most regex engines _also_ usually have a read-only component, typically
/// a [Thompson `NFA`](crate::nfa::thompson::NFA).
///
/// In order to make the `Regex` API convenient, most of the routines hide
/// the fact that a `Cache` is needed at all. To achieve this, a [memory
/// pool](crate::util::pool::Pool) is used internally to retrieve `Cache`
/// values in a thread safe way that also permits reuse. This in turn implies
/// that every such search call requires some form of synchronization. Usually
/// this synchronization is fast enough to not notice, but in some cases, it
/// can be a bottleneck. This typically occurs when all of the following are
/// true:
///
/// * The same `Regex` is shared across multiple threads simultaneously,
/// usually via a [`util::lazy::Lazy`](crate::util::lazy::Lazy) or something
/// similar from the `once_cell` or `lazy_static` crates.
/// * The primary unit of work in each thread is a regex search.
/// * Searches are run on very short haystacks.
///
/// This particular case can lead to high contention on the pool used by a
/// `Regex` internally, which can in turn increase latency to a noticeable
/// effect. This cost can be mitigated in one of the following ways:
///
/// * Use a distinct copy of a `Regex` in each thread, usually by cloning it.
/// Cloning a `Regex` _does not_ do a deep copy of its read-only component.
/// But it does lead to each `Regex` having its own memory pool, which in
/// turn eliminates the problem of contention. In general, this technique should
/// not result in any additional memory usage when compared to sharing the same
/// `Regex` across multiple threads simultaneously.
/// * Use lower level APIs, like [`Regex::search_with`], which permit passing
/// a `Cache` explicitly. In this case, it is up to you to determine how best
/// to provide a `Cache`. For example, you might put a `Cache` in thread-local
/// storage if your use case allows for it.
///
/// Overall, this is an issue that happens rarely in practice, but it can
/// happen.
///
/// # Warning: spin-locks may be used in alloc-only mode
///
/// When this crate is built without the `std` feature and the high level APIs
/// on a `Regex` are used, then a spin-lock will be used to synchronize access
/// to an internal pool of `Cache` values. This may be undesirable because
/// a spin-lock is [effectively impossible to implement correctly in user
/// space][spinlocks-are-bad]. That is, more concretely, the spin-lock could
/// result in a deadlock.
///
/// [spinlocks-are-bad]: https://matklad.github.io/2020/01/02/spinlocks-considered-harmful.html
///
/// If one wants to avoid the use of spin-locks when the `std` feature is
/// disabled, then you must use APIs that accept a `Cache` value explicitly.
/// For example, [`Regex::search_with`].
///
/// # Example
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"^[0-9]{4}-[0-9]{2}-[0-9]{2}$")?;
/// assert!(re.is_match("2010-03-14"));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: anchored search
///
/// This example shows how to use [`Input::anchored`] to run an anchored
/// search, even when the regex pattern itself isn't anchored. An anchored
/// search guarantees that if a match is found, then the start offset of the
/// match corresponds to the offset at which the search was started.
///
/// ```
/// use regex_automata::{meta::Regex, Anchored, Input, Match};
///
/// let re = Regex::new(r"\bfoo\b")?;
/// let input = Input::new("xx foo xx").range(3..).anchored(Anchored::Yes);
/// // The offsets are in terms of the original haystack.
/// assert_eq!(Some(Match::must(0, 3..6)), re.find(input));
///
/// // Notice that no match occurs here, because \b still takes the
/// // surrounding context into account, even if it means looking back
/// // before the start of your search.
/// let hay = "xxfoo xx";
/// let input = Input::new(hay).range(2..).anchored(Anchored::Yes);
/// assert_eq!(None, re.find(input));
/// // Indeed, you cannot achieve the above by simply slicing the
/// // haystack itself, since the regex engine can't see the
/// // surrounding context. This is why 'Input' permits setting
/// // the bounds of a search!
/// let input = Input::new(&hay[2..]).anchored(Anchored::Yes);
/// // WRONG!
/// assert_eq!(Some(Match::must(0, 0..3)), re.find(input));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: earliest search
///
/// This example shows how to use [`Input::earliest`] to run a search that
/// might stop before finding the typical leftmost match.
///
/// ```
/// use regex_automata::{meta::Regex, Anchored, Input, Match};
///
/// let re = Regex::new(r"[a-z]{3}|b")?;
/// let input = Input::new("abc").earliest(true);
/// assert_eq!(Some(Match::must(0, 1..2)), re.find(input));
///
/// // Note that "earliest" isn't really a match semantic unto itself.
/// // Instead, it is merely an instruction to whatever regex engine
/// // gets used internally to quit as soon as it can. For example,
/// // this regex uses a different search technique, and winds up
/// // producing a different (but valid) match!
/// let re = Regex::new(r"abc|b")?;
/// let input = Input::new("abc").earliest(true);
/// assert_eq!(Some(Match::must(0, 0..3)), re.find(input));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: change the line terminator
///
/// This example shows how to enable multi-line mode by default and change
/// the line terminator to the NUL byte:
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .syntax(syntax::Config::new().multi_line(true))
/// .configure(Regex::config().line_terminator(b'\x00'))
/// .build(r"^foo$")?;
/// let hay = "\x00foo\x00";
/// assert_eq!(Some(Match::must(0, 1..4)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[derive(Debug)]
pub struct Regex {
/// The actual regex implementation.
imp: Arc<RegexI>,
/// A thread safe pool of caches.
///
/// For the higher level search APIs, a `Cache` is automatically plucked
/// from this pool before running a search. The lower level `with` methods
/// permit the caller to provide their own cache, thereby bypassing
/// accesses to this pool.
///
/// Note that we put this outside the `Arc` so that cloning a `Regex`
/// results in creating a fresh `CachePool`. This in turn permits callers
/// to clone regexes into separate threads where each such regex gets
/// the pool's "thread owner" optimization. Otherwise, if one shares the
/// `Regex` directly, then the pool will go through a slower mutex path for
/// all threads except for the "owner."
pool: CachePool,
}
/// The internal implementation of `Regex`, split out so that it can be wrapped
/// in an `Arc`.
#[derive(Debug)]
struct RegexI {
/// The core matching engine.
///
/// Why is this reference counted when RegexI is already wrapped in an Arc?
/// Well, we need to capture this in a closure to our `Pool` below in order
/// to create new `Cache` values when needed. So since it needs to be in
/// two places, we make it reference counted.
///
/// We make `RegexI` itself reference counted too so that `Regex` itself
/// stays extremely small and very cheap to clone.
strat: Arc<dyn Strategy>,
/// Metadata about the regexes driving the strategy. The metadata is also
/// usually stored inside the strategy too, but we put it here as well
/// so that we can get quick access to it (without virtual calls) before
/// executing the regex engine. For example, we use this metadata to
/// detect a subset of cases where we know a match is impossible, and can
/// thus avoid calling into the strategy at all.
///
/// Since `RegexInfo` is stored in multiple places, it is also reference
/// counted.
info: RegexInfo,
}
/// Convenience constructors for a `Regex` using the default configuration.
impl Regex {
/// Builds a `Regex` from a single pattern string using the default
/// configuration.
///
/// If there was a problem parsing the pattern or a problem turning it into
/// a regex matcher, then an error is returned.
///
/// If you want to change the configuration of a `Regex`, use a [`Builder`]
/// with a [`Config`].
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::new(r"(?Rm)^foo$")?;
/// let hay = "\r\nfoo\r\n";
/// assert_eq!(Some(Match::must(0, 2..5)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn new(pattern: &str) -> Result<Regex, BuildError> {
Regex::builder().build(pattern)
}
/// Builds a `Regex` from many pattern strings using the default
/// configuration.
///
/// If there was a problem parsing any of the patterns or a problem turning
/// them into a regex matcher, then an error is returned.
///
/// If you want to change the configuration of a `Regex`, use a [`Builder`]
/// with a [`Config`].
///
/// # Example: simple lexer
///
/// This simplistic example leverages the multi-pattern support to build a
/// simple little lexer. The pattern ID in the match tells you which regex
/// matched, which in turn might be used to map back to the "type" of the
/// token returned by the lexer.
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::new_many(&[
/// r"[[:space:]]",
/// r"[A-Za-z0-9][A-Za-z0-9_]+",
/// r"->",
/// r".",
/// ])?;
/// let haystack = "fn is_boss(bruce: i32, springsteen: String) -> bool;";
/// let matches: Vec<Match> = re.find_iter(haystack).collect();
/// assert_eq!(matches, vec![
/// Match::must(1, 0..2), // 'fn'
/// Match::must(0, 2..3), // ' '
/// Match::must(1, 3..10), // 'is_boss'
/// Match::must(3, 10..11), // '('
/// Match::must(1, 11..16), // 'bruce'
/// Match::must(3, 16..17), // ':'
/// Match::must(0, 17..18), // ' '
/// Match::must(1, 18..21), // 'i32'
/// Match::must(3, 21..22), // ','
/// Match::must(0, 22..23), // ' '
/// Match::must(1, 23..34), // 'springsteen'
/// Match::must(3, 34..35), // ':'
/// Match::must(0, 35..36), // ' '
/// Match::must(1, 36..42), // 'String'
/// Match::must(3, 42..43), // ')'
/// Match::must(0, 43..44), // ' '
/// Match::must(2, 44..46), // '->'
/// Match::must(0, 46..47), // ' '
/// Match::must(1, 47..51), // 'bool'
/// Match::must(3, 51..52), // ';'
/// ]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// One can write a lexer like the above using a regex like
/// `(?P<space>[[:space:]])|(?P<ident>[A-Za-z0-9][A-Za-z0-9_]+)|...`,
/// but then you need to ask whether capture group matched to determine
/// which branch in the regex matched, and thus, which token the match
/// corresponds to. In contrast, the above example includes the pattern ID
/// in the match. There's no need to use capture groups at all.
///
/// # Example: finding the pattern that caused an error
///
/// When a syntax error occurs, it is possible to ask which pattern
/// caused the syntax error.
///
/// ```
/// use regex_automata::{meta::Regex, PatternID};
///
/// let err = Regex::new_many(&["a", "b", r"\p{Foo}", "c"]).unwrap_err();
/// assert_eq!(Some(PatternID::must(2)), err.pattern());
/// ```
///
/// # Example: zero patterns is valid
///
/// Building a regex with zero patterns results in a regex that never
/// matches anything. Because this routine is generic, passing an empty
/// slice usually requires a turbo-fish (or something else to help type
/// inference).
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::new_many::<&str>(&[])?;
/// assert_eq!(None, re.find(""));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn new_many<P: AsRef<str>>(
patterns: &[P],
) -> Result<Regex, BuildError> {
Regex::builder().build_many(patterns)
}
/// Return a default configuration for a `Regex`.
///
/// This is a convenience routine to avoid needing to import the [`Config`]
/// type when customizing the construction of a `Regex`.
///
/// # Example: lower the NFA size limit
///
/// In some cases, the default size limit might be too big. The size limit
/// can be lowered, which will prevent large regex patterns from compiling.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// .configure(Regex::config().nfa_size_limit(Some(20 * (1<<10))))
/// // Not even 20KB is enough to build a single large Unicode class!
/// .build(r"\pL");
/// assert!(result.is_err());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn config() -> Config {
Config::new()
}
/// Return a builder for configuring the construction of a `Regex`.
///
/// This is a convenience routine to avoid needing to import the
/// [`Builder`] type in common cases.
///
/// # Example: change the line terminator
///
/// This example shows how to enable multi-line mode by default and change
/// the line terminator to the NUL byte:
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .syntax(syntax::Config::new().multi_line(true))
/// .configure(Regex::config().line_terminator(b'\x00'))
/// .build(r"^foo$")?;
/// let hay = "\x00foo\x00";
/// assert_eq!(Some(Match::must(0, 1..4)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn builder() -> Builder {
Builder::new()
}
}
/// High level convenience routines for using a regex to search a haystack.
impl Regex {
/// Returns true if and only if this regex matches the given haystack.
///
/// This routine may short circuit if it knows that scanning future input
/// will never lead to a different result. (Consider how this might make
/// a difference given the regex `a+` on the haystack `aaaaaaaaaaaaaaa`.
/// This routine _may_ stop after it sees the first `a`, but routines like
/// `find` need to continue searching because `+` is greedy by default.)
///
/// # Example
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new("foo[0-9]+bar")?;
///
/// assert!(re.is_match("foo12345bar"));
/// assert!(!re.is_match("foobar"));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: consistency with search APIs
///
/// `is_match` is guaranteed to return `true` whenever `find` returns a
/// match. This includes searches that are executed entirely within a
/// codepoint:
///
/// ```
/// use regex_automata::{meta::Regex, Input};
///
/// let re = Regex::new("a*")?;
///
/// // This doesn't match because the default configuration bans empty
/// // matches from splitting a codepoint.
/// assert!(!re.is_match(Input::new("☃").span(1..2)));
/// assert_eq!(None, re.find(Input::new("☃").span(1..2)));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// Notice that when UTF-8 mode is disabled, then the above reports a
/// match because the restriction against zero-width matches that split a
/// codepoint has been lifted:
///
/// ```
/// use regex_automata::{meta::Regex, Input, Match};
///
/// let re = Regex::builder()
/// .configure(Regex::config().utf8_empty(false))
/// .build("a*")?;
///
/// assert!(re.is_match(Input::new("☃").span(1..2)));
/// assert_eq!(
/// Some(Match::must(0, 1..1)),
/// re.find(Input::new("☃").span(1..2)),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// A similar idea applies when using line anchors with CRLF mode enabled,
/// which prevents them from matching between a `\r` and a `\n`.
///
/// ```
/// use regex_automata::{meta::Regex, Input, Match};
///
/// let re = Regex::new(r"(?Rm:$)")?;
/// assert!(!re.is_match(Input::new("\r\n").span(1..1)));
/// // A regular line anchor, which only considers \n as a
/// // line terminator, will match.
/// let re = Regex::new(r"(?m:$)")?;
/// assert!(re.is_match(Input::new("\r\n").span(1..1)));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn is_match<'h, I: Into<Input<'h>>>(&self, input: I) -> bool {
let input = input.into().earliest(true);
if self.imp.info.is_impossible(&input) {
return false;
}
let mut guard = self.pool.get();
let result = self.imp.strat.is_match(&mut guard, &input);
// See 'Regex::search' for why we put the guard back explicitly.
PoolGuard::put(guard);
result
}
/// Executes a leftmost search and returns the first match that is found,
/// if one exists.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::new("foo[0-9]+")?;
/// assert_eq!(Some(Match::must(0, 0..8)), re.find("foo12345"));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn find<'h, I: Into<Input<'h>>>(&self, input: I) -> Option<Match> {
self.search(&input.into())
}
/// Executes a leftmost forward search and writes the spans of capturing
/// groups that participated in a match into the provided [`Captures`]
/// value. If no match was found, then [`Captures::is_match`] is guaranteed
/// to return `false`.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Span};
///
/// let re = Regex::new(r"^([0-9]{4})-([0-9]{2})-([0-9]{2})$")?;
/// let mut caps = re.create_captures();
///
/// re.captures("2010-03-14", &mut caps);
/// assert!(caps.is_match());
/// assert_eq!(Some(Span::from(0..4)), caps.get_group(1));
/// assert_eq!(Some(Span::from(5..7)), caps.get_group(2));
/// assert_eq!(Some(Span::from(8..10)), caps.get_group(3));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn captures<'h, I: Into<Input<'h>>>(
&self,
input: I,
caps: &mut Captures,
) {
self.search_captures(&input.into(), caps)
}
/// Returns an iterator over all non-overlapping leftmost matches in
/// the given haystack. If no match exists, then the iterator yields no
/// elements.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::new("foo[0-9]+")?;
/// let haystack = "foo1 foo12 foo123";
/// let matches: Vec<Match> = re.find_iter(haystack).collect();
/// assert_eq!(matches, vec![
/// Match::must(0, 0..4),
/// Match::must(0, 5..10),
/// Match::must(0, 11..17),
/// ]);
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn find_iter<'r, 'h, I: Into<Input<'h>>>(
&'r self,
input: I,
) -> FindMatches<'r, 'h> {
let cache = self.pool.get();
let it = iter::Searcher::new(input.into());
FindMatches { re: self, cache, it }
}
/// Returns an iterator over all non-overlapping `Captures` values. If no
/// match exists, then the iterator yields no elements.
///
/// This yields the same matches as [`Regex::find_iter`], but it includes
/// the spans of all capturing groups that participate in each match.
///
/// **Tip:** See [`util::iter::Searcher`](crate::util::iter::Searcher) for
/// how to correctly iterate over all matches in a haystack while avoiding
/// the creation of a new `Captures` value for every match. (Which you are
/// forced to do with an `Iterator`.)
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Span};
///
/// let re = Regex::new("foo(?P<numbers>[0-9]+)")?;
///
/// let haystack = "foo1 foo12 foo123";
/// let matches: Vec<Span> = re
/// .captures_iter(haystack)
/// // The unwrap is OK since 'numbers' matches if the pattern matches.
/// .map(|caps| caps.get_group_by_name("numbers").unwrap())
/// .collect();
/// assert_eq!(matches, vec![
/// Span::from(3..4),
/// Span::from(8..10),
/// Span::from(14..17),
/// ]);
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn captures_iter<'r, 'h, I: Into<Input<'h>>>(
&'r self,
input: I,
) -> CapturesMatches<'r, 'h> {
let cache = self.pool.get();
let caps = self.create_captures();
let it = iter::Searcher::new(input.into());
CapturesMatches { re: self, cache, caps, it }
}
/// Returns an iterator of spans of the haystack given, delimited by a
/// match of the regex. Namely, each element of the iterator corresponds to
/// a part of the haystack that *isn't* matched by the regular expression.
///
/// # Example
///
/// To split a string delimited by arbitrary amounts of spaces or tabs:
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"[ \t]+")?;
/// let hay = "a b \t c\td e";
/// let fields: Vec<&str> = re.split(hay).map(|span| &hay[span]).collect();
/// assert_eq!(fields, vec!["a", "b", "c", "d", "e"]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: more cases
///
/// Basic usage:
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r" ")?;
/// let hay = "Mary had a little lamb";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["Mary", "had", "a", "little", "lamb"]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec![""]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "lionXXtigerXleopard";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["lion", "", "tiger", "leopard"]);
///
/// let re = Regex::new(r"::")?;
/// let hay = "lion::tiger::leopard";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["lion", "tiger", "leopard"]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// If a haystack contains multiple contiguous matches, you will end up
/// with empty spans yielded by the iterator:
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"X")?;
/// let hay = "XXXXaXXbXc";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["", "", "", "", "a", "", "b", "c"]);
///
/// let re = Regex::new(r"/")?;
/// let hay = "(///)";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["(", "", "", ")"]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// Separators at the start or end of a haystack are neighbored by empty
/// spans.
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"0")?;
/// let hay = "010";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["", "1", ""]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// When the empty string is used as a regex, it splits at every valid
/// UTF-8 boundary by default (which includes the beginning and end of the
/// haystack):
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"")?;
/// let hay = "rust";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["", "r", "u", "s", "t", ""]);
///
/// // Splitting by an empty string is UTF-8 aware by default!
/// let re = Regex::new(r"")?;
/// let hay = "☃";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["", "☃", ""]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// But note that UTF-8 mode for empty strings can be disabled, which will
/// then result in a match at every byte offset in the haystack,
/// including between every UTF-8 code unit.
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::builder()
/// .configure(Regex::config().utf8_empty(false))
/// .build(r"")?;
/// let hay = "☃".as_bytes();
/// let got: Vec<&[u8]> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec![
/// // Writing byte string slices is just brutal. The problem is that
/// // b"foo" has type &[u8; 3] instead of &[u8].
/// &[][..], &[b'\xE2'][..], &[b'\x98'][..], &[b'\x83'][..], &[][..],
/// ]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// Contiguous separators (commonly shows up with whitespace), can lead to
/// possibly surprising behavior. For example, this code is correct:
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r" ")?;
/// let hay = " a b c";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["", "", "", "", "a", "", "b", "c"]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// It does *not* give you `["a", "b", "c"]`. For that behavior, you'd want
/// to match contiguous space characters:
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r" +")?;
/// let hay = " a b c";
/// let got: Vec<&str> = re.split(hay).map(|sp| &hay[sp]).collect();
/// // N.B. This does still include a leading empty span because ' +'
/// // matches at the beginning of the haystack.
/// assert_eq!(got, vec!["", "a", "b", "c"]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn split<'r, 'h, I: Into<Input<'h>>>(
&'r self,
input: I,
) -> Split<'r, 'h> {
Split { finder: self.find_iter(input), last: 0 }
}
/// Returns an iterator of at most `limit` spans of the haystack given,
/// delimited by a match of the regex. (A `limit` of `0` will return no
/// spans.) Namely, each element of the iterator corresponds to a part
/// of the haystack that *isn't* matched by the regular expression. The
/// remainder of the haystack that is not split will be the last element in
/// the iterator.
///
/// # Example
///
/// Get the first two words in some haystack:
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"\W+").unwrap();
/// let hay = "Hey! How are you?";
/// let fields: Vec<&str> =
/// re.splitn(hay, 3).map(|span| &hay[span]).collect();
/// assert_eq!(fields, vec!["Hey", "How", "are you?"]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Examples: more cases
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r" ")?;
/// let hay = "Mary had a little lamb";
/// let got: Vec<&str> = re.splitn(hay, 3).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["Mary", "had", "a little lamb"]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "";
/// let got: Vec<&str> = re.splitn(hay, 3).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec![""]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "lionXXtigerXleopard";
/// let got: Vec<&str> = re.splitn(hay, 3).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["lion", "", "tigerXleopard"]);
///
/// let re = Regex::new(r"::")?;
/// let hay = "lion::tiger::leopard";
/// let got: Vec<&str> = re.splitn(hay, 2).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["lion", "tiger::leopard"]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "abcXdef";
/// let got: Vec<&str> = re.splitn(hay, 1).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["abcXdef"]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "abcdef";
/// let got: Vec<&str> = re.splitn(hay, 2).map(|sp| &hay[sp]).collect();
/// assert_eq!(got, vec!["abcdef"]);
///
/// let re = Regex::new(r"X")?;
/// let hay = "abcXdef";
/// let got: Vec<&str> = re.splitn(hay, 0).map(|sp| &hay[sp]).collect();
/// assert!(got.is_empty());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn splitn<'r, 'h, I: Into<Input<'h>>>(
&'r self,
input: I,
limit: usize,
) -> SplitN<'r, 'h> {
SplitN { splits: self.split(input), limit }
}
}
/// Lower level search routines that give more control.
impl Regex {
/// Returns the start and end offset of the leftmost match. If no match
/// exists, then `None` is returned.
///
/// This is like [`Regex::find`] but, but it accepts a concrete `&Input`
/// instead of an `Into<Input>`.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Input, Match};
///
/// let re = Regex::new(r"Samwise|Sam")?;
/// let input = Input::new(
/// "one of the chief characters, Samwise the Brave",
/// );
/// assert_eq!(Some(Match::must(0, 29..36)), re.search(&input));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search(&self, input: &Input<'_>) -> Option<Match> {
if self.imp.info.is_impossible(input) {
return None;
}
let mut guard = self.pool.get();
let result = self.imp.strat.search(&mut guard, input);
// We do this dance with the guard and explicitly put it back in the
// pool because it seems to result in better codegen. If we let the
// guard's Drop impl put it back in the pool, then functions like
// ptr::drop_in_place get called and they *don't* get inlined. This
// isn't usually a big deal, but in latency sensitive benchmarks the
// extra function call can matter.
//
// I used `rebar measure -f '^grep/every-line$' -e meta` to measure
// the effects here.
//
// Note that this doesn't eliminate the latency effects of using the
// pool. There is still some (minor) cost for the "thread owner" of the
// pool. (i.e., The thread that first calls a regex search routine.)
// However, for other threads using the regex, the pool access can be
// quite expensive as it goes through a mutex. Callers can avoid this
// by either cloning the Regex (which creates a distinct copy of the
// pool), or callers can use the lower level APIs that accept a 'Cache'
// directly and do their own handling.
PoolGuard::put(guard);
result
}
/// Returns the end offset of the leftmost match. If no match exists, then
/// `None` is returned.
///
/// This is distinct from [`Regex::search`] in that it only returns the end
/// of a match and not the start of the match. Depending on a variety of
/// implementation details, this _may_ permit the regex engine to do less
/// overall work. For example, if a DFA is being used to execute a search,
/// then the start of a match usually requires running a separate DFA in
/// reverse to the find the start of a match. If one only needs the end of
/// a match, then the separate reverse scan to find the start of a match
/// can be skipped. (Note that the reverse scan is avoided even when using
/// `Regex::search` when possible, for example, in the case of an anchored
/// search.)
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Input, HalfMatch};
///
/// let re = Regex::new(r"Samwise|Sam")?;
/// let input = Input::new(
/// "one of the chief characters, Samwise the Brave",
/// );
/// assert_eq!(Some(HalfMatch::must(0, 36)), re.search_half(&input));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_half(&self, input: &Input<'_>) -> Option<HalfMatch> {
if self.imp.info.is_impossible(input) {
return None;
}
let mut guard = self.pool.get();
let result = self.imp.strat.search_half(&mut guard, input);
// See 'Regex::search' for why we put the guard back explicitly.
PoolGuard::put(guard);
result
}
/// Executes a leftmost forward search and writes the spans of capturing
/// groups that participated in a match into the provided [`Captures`]
/// value. If no match was found, then [`Captures::is_match`] is guaranteed
/// to return `false`.
///
/// This is like [`Regex::captures`], but it accepts a concrete `&Input`
/// instead of an `Into<Input>`.
///
/// # Example: specific pattern search
///
/// This example shows how to build a multi-pattern `Regex` that permits
/// searching for specific patterns.
///
/// ```
/// use regex_automata::{
/// meta::Regex,
/// Anchored, Match, PatternID, Input,
/// };
///
/// let re = Regex::new_many(&["[a-z0-9]{6}", "[a-z][a-z0-9]{5}"])?;
/// let mut caps = re.create_captures();
/// let haystack = "foo123";
///
/// // Since we are using the default leftmost-first match and both
/// // patterns match at the same starting position, only the first pattern
/// // will be returned in this case when doing a search for any of the
/// // patterns.
/// let expected = Some(Match::must(0, 0..6));
/// re.search_captures(&Input::new(haystack), &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// // But if we want to check whether some other pattern matches, then we
/// // can provide its pattern ID.
/// let expected = Some(Match::must(1, 0..6));
/// let input = Input::new(haystack)
/// .anchored(Anchored::Pattern(PatternID::must(1)));
/// re.search_captures(&input, &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: specifying the bounds of a search
///
/// This example shows how providing the bounds of a search can produce
/// different results than simply sub-slicing the haystack.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, Match, Input};
///
/// let re = Regex::new(r"\b[0-9]{3}\b")?;
/// let mut caps = re.create_captures();
/// let haystack = "foo123bar";
///
/// // Since we sub-slice the haystack, the search doesn't know about
/// // the larger context and assumes that `123` is surrounded by word
/// // boundaries. And of course, the match position is reported relative
/// // to the sub-slice as well, which means we get `0..3` instead of
/// // `3..6`.
/// let expected = Some(Match::must(0, 0..3));
/// let input = Input::new(&haystack[3..6]);
/// re.search_captures(&input, &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// // But if we provide the bounds of the search within the context of the
/// // entire haystack, then the search can take the surrounding context
/// // into account. (And if we did find a match, it would be reported
/// // as a valid offset into `haystack` instead of its sub-slice.)
/// let expected = None;
/// let input = Input::new(haystack).range(3..6);
/// re.search_captures(&input, &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_captures(&self, input: &Input<'_>, caps: &mut Captures) {
caps.set_pattern(None);
let pid = self.search_slots(input, caps.slots_mut());
caps.set_pattern(pid);
}
/// Executes a leftmost forward search and writes the spans of capturing
/// groups that participated in a match into the provided `slots`, and
/// returns the matching pattern ID. The contents of the slots for patterns
/// other than the matching pattern are unspecified. If no match was found,
/// then `None` is returned and the contents of `slots` is unspecified.
///
/// This is like [`Regex::search`], but it accepts a raw slots slice
/// instead of a `Captures` value. This is useful in contexts where you
/// don't want or need to allocate a `Captures`.
///
/// It is legal to pass _any_ number of slots to this routine. If the regex
/// engine would otherwise write a slot offset that doesn't fit in the
/// provided slice, then it is simply skipped. In general though, there are
/// usually three slice lengths you might want to use:
///
/// * An empty slice, if you only care about which pattern matched.
/// * A slice with [`pattern_len() * 2`](Regex::pattern_len) slots, if you
/// only care about the overall match spans for each matching pattern.
/// * A slice with
/// [`slot_len()`](crate::util::captures::GroupInfo::slot_len) slots, which
/// permits recording match offsets for every capturing group in every
/// pattern.
///
/// # Example
///
/// This example shows how to find the overall match offsets in a
/// multi-pattern search without allocating a `Captures` value. Indeed, we
/// can put our slots right on the stack.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, PatternID, Input};
///
/// let re = Regex::new_many(&[
/// r"\pL+",
/// r"\d+",
/// ])?;
/// let input = Input::new("!@#123");
///
/// // We only care about the overall match offsets here, so we just
/// // allocate two slots for each pattern. Each slot records the start
/// // and end of the match.
/// let mut slots = [None; 4];
/// let pid = re.search_slots(&input, &mut slots);
/// assert_eq!(Some(PatternID::must(1)), pid);
///
/// // The overall match offsets are always at 'pid * 2' and 'pid * 2 + 1'.
/// // See 'GroupInfo' for more details on the mapping between groups and
/// // slot indices.
/// let slot_start = pid.unwrap().as_usize() * 2;
/// let slot_end = slot_start + 1;
/// assert_eq!(Some(3), slots[slot_start].map(|s| s.get()));
/// assert_eq!(Some(6), slots[slot_end].map(|s| s.get()));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_slots(
&self,
input: &Input<'_>,
slots: &mut [Option<NonMaxUsize>],
) -> Option<PatternID> {
if self.imp.info.is_impossible(input) {
return None;
}
let mut guard = self.pool.get();
let result = self.imp.strat.search_slots(&mut guard, input, slots);
// See 'Regex::search' for why we put the guard back explicitly.
PoolGuard::put(guard);
result
}
/// Writes the set of patterns that match anywhere in the given search
/// configuration to `patset`. If multiple patterns match at the same
/// position and this `Regex` was configured with [`MatchKind::All`]
/// semantics, then all matching patterns are written to the given set.
///
/// Unless all of the patterns in this `Regex` are anchored, then generally
/// speaking, this will scan the entire haystack.
///
/// This search routine *does not* clear the pattern set. This gives some
/// flexibility to the caller (e.g., running multiple searches with the
/// same pattern set), but does make the API bug-prone if you're reusing
/// the same pattern set for multiple searches but intended them to be
/// independent.
///
/// If a pattern ID matched but the given `PatternSet` does not have
/// sufficient capacity to store it, then it is not inserted and silently
/// dropped.
///
/// # Example
///
/// This example shows how to find all matching patterns in a haystack,
/// even when some patterns match at the same position as other patterns.
/// It is important that we configure the `Regex` with [`MatchKind::All`]
/// semantics here, or else overlapping matches will not be reported.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, Input, MatchKind, PatternSet};
///
/// let patterns = &[
/// r"\w+", r"\d+", r"\pL+", r"foo", r"bar", r"barfoo", r"foobar",
/// ];
/// let re = Regex::builder()
/// .configure(Regex::config().match_kind(MatchKind::All))
/// .build_many(patterns)?;
///
/// let input = Input::new("foobar");
/// let mut patset = PatternSet::new(re.pattern_len());
/// re.which_overlapping_matches(&input, &mut patset);
/// let expected = vec![0, 2, 3, 4, 6];
/// let got: Vec<usize> = patset.iter().map(|p| p.as_usize()).collect();
/// assert_eq!(expected, got);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn which_overlapping_matches(
&self,
input: &Input<'_>,
patset: &mut PatternSet,
) {
if self.imp.info.is_impossible(input) {
return;
}
let mut guard = self.pool.get();
let result = self
.imp
.strat
.which_overlapping_matches(&mut guard, input, patset);
// See 'Regex::search' for why we put the guard back explicitly.
PoolGuard::put(guard);
result
}
}
/// Lower level search routines that give more control, and require the caller
/// to provide an explicit [`Cache`] parameter.
impl Regex {
/// This is like [`Regex::search`], but requires the caller to
/// explicitly pass a [`Cache`].
///
/// # Why pass a `Cache` explicitly?
///
/// Passing a `Cache` explicitly will bypass the use of an internal memory
/// pool used by `Regex` to get a `Cache` for a search. The use of this
/// pool can be slower in some cases when a `Regex` is used from multiple
/// threads simultaneously. Typically, performance only becomes an issue
/// when there is heavy contention, which in turn usually only occurs
/// when each thread's primary unit of work is a regex search on a small
/// haystack.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Input, Match};
///
/// let re = Regex::new(r"Samwise|Sam")?;
/// let mut cache = re.create_cache();
/// let input = Input::new(
/// "one of the chief characters, Samwise the Brave",
/// );
/// assert_eq!(
/// Some(Match::must(0, 29..36)),
/// re.search_with(&mut cache, &input),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_with(
&self,
cache: &mut Cache,
input: &Input<'_>,
) -> Option<Match> {
if self.imp.info.is_impossible(input) {
return None;
}
self.imp.strat.search(cache, input)
}
/// This is like [`Regex::search_half`], but requires the caller to
/// explicitly pass a [`Cache`].
///
/// # Why pass a `Cache` explicitly?
///
/// Passing a `Cache` explicitly will bypass the use of an internal memory
/// pool used by `Regex` to get a `Cache` for a search. The use of this
/// pool can be slower in some cases when a `Regex` is used from multiple
/// threads simultaneously. Typically, performance only becomes an issue
/// when there is heavy contention, which in turn usually only occurs
/// when each thread's primary unit of work is a regex search on a small
/// haystack.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Input, HalfMatch};
///
/// let re = Regex::new(r"Samwise|Sam")?;
/// let mut cache = re.create_cache();
/// let input = Input::new(
/// "one of the chief characters, Samwise the Brave",
/// );
/// assert_eq!(
/// Some(HalfMatch::must(0, 36)),
/// re.search_half_with(&mut cache, &input),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_half_with(
&self,
cache: &mut Cache,
input: &Input<'_>,
) -> Option<HalfMatch> {
if self.imp.info.is_impossible(input) {
return None;
}
self.imp.strat.search_half(cache, input)
}
/// This is like [`Regex::search_captures`], but requires the caller to
/// explicitly pass a [`Cache`].
///
/// # Why pass a `Cache` explicitly?
///
/// Passing a `Cache` explicitly will bypass the use of an internal memory
/// pool used by `Regex` to get a `Cache` for a search. The use of this
/// pool can be slower in some cases when a `Regex` is used from multiple
/// threads simultaneously. Typically, performance only becomes an issue
/// when there is heavy contention, which in turn usually only occurs
/// when each thread's primary unit of work is a regex search on a small
/// haystack.
///
/// # Example: specific pattern search
///
/// This example shows how to build a multi-pattern `Regex` that permits
/// searching for specific patterns.
///
/// ```
/// use regex_automata::{
/// meta::Regex,
/// Anchored, Match, PatternID, Input,
/// };
///
/// let re = Regex::new_many(&["[a-z0-9]{6}", "[a-z][a-z0-9]{5}"])?;
/// let (mut cache, mut caps) = (re.create_cache(), re.create_captures());
/// let haystack = "foo123";
///
/// // Since we are using the default leftmost-first match and both
/// // patterns match at the same starting position, only the first pattern
/// // will be returned in this case when doing a search for any of the
/// // patterns.
/// let expected = Some(Match::must(0, 0..6));
/// re.search_captures_with(&mut cache, &Input::new(haystack), &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// // But if we want to check whether some other pattern matches, then we
/// // can provide its pattern ID.
/// let expected = Some(Match::must(1, 0..6));
/// let input = Input::new(haystack)
/// .anchored(Anchored::Pattern(PatternID::must(1)));
/// re.search_captures_with(&mut cache, &input, &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: specifying the bounds of a search
///
/// This example shows how providing the bounds of a search can produce
/// different results than simply sub-slicing the haystack.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, Match, Input};
///
/// let re = Regex::new(r"\b[0-9]{3}\b")?;
/// let (mut cache, mut caps) = (re.create_cache(), re.create_captures());
/// let haystack = "foo123bar";
///
/// // Since we sub-slice the haystack, the search doesn't know about
/// // the larger context and assumes that `123` is surrounded by word
/// // boundaries. And of course, the match position is reported relative
/// // to the sub-slice as well, which means we get `0..3` instead of
/// // `3..6`.
/// let expected = Some(Match::must(0, 0..3));
/// let input = Input::new(&haystack[3..6]);
/// re.search_captures_with(&mut cache, &input, &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// // But if we provide the bounds of the search within the context of the
/// // entire haystack, then the search can take the surrounding context
/// // into account. (And if we did find a match, it would be reported
/// // as a valid offset into `haystack` instead of its sub-slice.)
/// let expected = None;
/// let input = Input::new(haystack).range(3..6);
/// re.search_captures_with(&mut cache, &input, &mut caps);
/// assert_eq!(expected, caps.get_match());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_captures_with(
&self,
cache: &mut Cache,
input: &Input<'_>,
caps: &mut Captures,
) {
caps.set_pattern(None);
let pid = self.search_slots_with(cache, input, caps.slots_mut());
caps.set_pattern(pid);
}
/// This is like [`Regex::search_slots`], but requires the caller to
/// explicitly pass a [`Cache`].
///
/// # Why pass a `Cache` explicitly?
///
/// Passing a `Cache` explicitly will bypass the use of an internal memory
/// pool used by `Regex` to get a `Cache` for a search. The use of this
/// pool can be slower in some cases when a `Regex` is used from multiple
/// threads simultaneously. Typically, performance only becomes an issue
/// when there is heavy contention, which in turn usually only occurs
/// when each thread's primary unit of work is a regex search on a small
/// haystack.
///
/// # Example
///
/// This example shows how to find the overall match offsets in a
/// multi-pattern search without allocating a `Captures` value. Indeed, we
/// can put our slots right on the stack.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, PatternID, Input};
///
/// let re = Regex::new_many(&[
/// r"\pL+",
/// r"\d+",
/// ])?;
/// let mut cache = re.create_cache();
/// let input = Input::new("!@#123");
///
/// // We only care about the overall match offsets here, so we just
/// // allocate two slots for each pattern. Each slot records the start
/// // and end of the match.
/// let mut slots = [None; 4];
/// let pid = re.search_slots_with(&mut cache, &input, &mut slots);
/// assert_eq!(Some(PatternID::must(1)), pid);
///
/// // The overall match offsets are always at 'pid * 2' and 'pid * 2 + 1'.
/// // See 'GroupInfo' for more details on the mapping between groups and
/// // slot indices.
/// let slot_start = pid.unwrap().as_usize() * 2;
/// let slot_end = slot_start + 1;
/// assert_eq!(Some(3), slots[slot_start].map(|s| s.get()));
/// assert_eq!(Some(6), slots[slot_end].map(|s| s.get()));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn search_slots_with(
&self,
cache: &mut Cache,
input: &Input<'_>,
slots: &mut [Option<NonMaxUsize>],
) -> Option<PatternID> {
if self.imp.info.is_impossible(input) {
return None;
}
self.imp.strat.search_slots(cache, input, slots)
}
/// This is like [`Regex::which_overlapping_matches`], but requires the
/// caller to explicitly pass a [`Cache`].
///
/// Passing a `Cache` explicitly will bypass the use of an internal memory
/// pool used by `Regex` to get a `Cache` for a search. The use of this
/// pool can be slower in some cases when a `Regex` is used from multiple
/// threads simultaneously. Typically, performance only becomes an issue
/// when there is heavy contention, which in turn usually only occurs
/// when each thread's primary unit of work is a regex search on a small
/// haystack.
///
/// # Why pass a `Cache` explicitly?
///
/// # Example
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, Input, MatchKind, PatternSet};
///
/// let patterns = &[
/// r"\w+", r"\d+", r"\pL+", r"foo", r"bar", r"barfoo", r"foobar",
/// ];
/// let re = Regex::builder()
/// .configure(Regex::config().match_kind(MatchKind::All))
/// .build_many(patterns)?;
/// let mut cache = re.create_cache();
///
/// let input = Input::new("foobar");
/// let mut patset = PatternSet::new(re.pattern_len());
/// re.which_overlapping_matches_with(&mut cache, &input, &mut patset);
/// let expected = vec![0, 2, 3, 4, 6];
/// let got: Vec<usize> = patset.iter().map(|p| p.as_usize()).collect();
/// assert_eq!(expected, got);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn which_overlapping_matches_with(
&self,
cache: &mut Cache,
input: &Input<'_>,
patset: &mut PatternSet,
) {
if self.imp.info.is_impossible(input) {
return;
}
self.imp.strat.which_overlapping_matches(cache, input, patset)
}
}
/// Various non-search routines for querying properties of a `Regex` and
/// convenience routines for creating [`Captures`] and [`Cache`] values.
impl Regex {
/// Creates a new object for recording capture group offsets. This is used
/// in search APIs like [`Regex::captures`] and [`Regex::search_captures`].
///
/// This is a convenience routine for
/// `Captures::all(re.group_info().clone())`. Callers may build other types
/// of `Captures` values that record less information (and thus require
/// less work from the regex engine) using [`Captures::matches`] and
/// [`Captures::empty`].
///
/// # Example
///
/// This shows some alternatives to [`Regex::create_captures`]:
///
/// ```
/// use regex_automata::{
/// meta::Regex,
/// util::captures::Captures,
/// Match, PatternID, Span,
/// };
///
/// let re = Regex::new(r"(?<first>[A-Z][a-z]+) (?<last>[A-Z][a-z]+)")?;
///
/// // This is equivalent to Regex::create_captures. It stores matching
/// // offsets for all groups in the regex.
/// let mut all = Captures::all(re.group_info().clone());
/// re.captures("Bruce Springsteen", &mut all);
/// assert_eq!(Some(Match::must(0, 0..17)), all.get_match());
/// assert_eq!(Some(Span::from(0..5)), all.get_group_by_name("first"));
/// assert_eq!(Some(Span::from(6..17)), all.get_group_by_name("last"));
///
/// // In this version, we only care about the implicit groups, which
/// // means offsets for the explicit groups will be unavailable. It can
/// // sometimes be faster to ask for fewer groups, since the underlying
/// // regex engine needs to do less work to keep track of them.
/// let mut matches = Captures::matches(re.group_info().clone());
/// re.captures("Bruce Springsteen", &mut matches);
/// // We still get the overall match info.
/// assert_eq!(Some(Match::must(0, 0..17)), matches.get_match());
/// // But now the explicit groups are unavailable.
/// assert_eq!(None, matches.get_group_by_name("first"));
/// assert_eq!(None, matches.get_group_by_name("last"));
///
/// // Finally, in this version, we don't ask to keep track of offsets for
/// // *any* groups. All we get back is whether a match occurred, and if
/// // so, the ID of the pattern that matched.
/// let mut empty = Captures::empty(re.group_info().clone());
/// re.captures("Bruce Springsteen", &mut empty);
/// // it's a match!
/// assert!(empty.is_match());
/// // for pattern ID 0
/// assert_eq!(Some(PatternID::ZERO), empty.pattern());
/// // Match offsets are unavailable.
/// assert_eq!(None, empty.get_match());
/// // And of course, explicit groups are unavailable too.
/// assert_eq!(None, empty.get_group_by_name("first"));
/// assert_eq!(None, empty.get_group_by_name("last"));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn create_captures(&self) -> Captures {
Captures::all(self.group_info().clone())
}
/// Creates a new cache for use with lower level search APIs like
/// [`Regex::search_with`].
///
/// The cache returned should only be used for searches for this `Regex`.
/// If you want to reuse the cache for another `Regex`, then you must call
/// [`Cache::reset`] with that `Regex`.
///
/// This is a convenience routine for [`Cache::new`].
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Input, Match};
///
/// let re = Regex::new(r"(?-u)m\w+\s+m\w+")?;
/// let mut cache = re.create_cache();
/// let input = Input::new("crazy janey and her mission man");
/// assert_eq!(
/// Some(Match::must(0, 20..31)),
/// re.search_with(&mut cache, &input),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn create_cache(&self) -> Cache {
self.imp.strat.create_cache()
}
/// Returns the total number of patterns in this regex.
///
/// The standard [`Regex::new`] constructor always results in a `Regex`
/// with a single pattern, but [`Regex::new_many`] permits building a
/// multi-pattern regex.
///
/// A `Regex` guarantees that the maximum possible `PatternID` returned in
/// any match is `Regex::pattern_len() - 1`. In the case where the number
/// of patterns is `0`, a match is impossible.
///
/// # Example
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let re = Regex::new(r"(?m)^[a-z]$")?;
/// assert_eq!(1, re.pattern_len());
///
/// let re = Regex::new_many::<&str>(&[])?;
/// assert_eq!(0, re.pattern_len());
///
/// let re = Regex::new_many(&["a", "b", "c"])?;
/// assert_eq!(3, re.pattern_len());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn pattern_len(&self) -> usize {
self.imp.info.pattern_len()
}
/// Returns the total number of capturing groups.
///
/// This includes the implicit capturing group corresponding to the
/// entire match. Therefore, the minimum value returned is `1`.
///
/// # Example
///
/// This shows a few patterns and how many capture groups they have.
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let len = |pattern| {
/// Regex::new(pattern).map(|re| re.captures_len())
/// };
///
/// assert_eq!(1, len("a")?);
/// assert_eq!(2, len("(a)")?);
/// assert_eq!(3, len("(a)|(b)")?);
/// assert_eq!(5, len("(a)(b)|(c)(d)")?);
/// assert_eq!(2, len("(a)|b")?);
/// assert_eq!(2, len("a|(b)")?);
/// assert_eq!(2, len("(b)*")?);
/// assert_eq!(2, len("(b)+")?);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: multiple patterns
///
/// This routine also works for multiple patterns. The total number is
/// the sum of the capture groups of each pattern.
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let len = |patterns| {
/// Regex::new_many(patterns).map(|re| re.captures_len())
/// };
///
/// assert_eq!(2, len(&["a", "b"])?);
/// assert_eq!(4, len(&["(a)", "(b)"])?);
/// assert_eq!(6, len(&["(a)|(b)", "(c)|(d)"])?);
/// assert_eq!(8, len(&["(a)(b)|(c)(d)", "(x)(y)"])?);
/// assert_eq!(3, len(&["(a)", "b"])?);
/// assert_eq!(3, len(&["a", "(b)"])?);
/// assert_eq!(4, len(&["(a)", "(b)*"])?);
/// assert_eq!(4, len(&["(a)+", "(b)+"])?);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn captures_len(&self) -> usize {
self.imp
.info
.props_union()
.explicit_captures_len()
.saturating_add(self.pattern_len())
}
/// Returns the total number of capturing groups that appear in every
/// possible match.
///
/// If the number of capture groups can vary depending on the match, then
/// this returns `None`. That is, a value is only returned when the number
/// of matching groups is invariant or "static."
///
/// Note that like [`Regex::captures_len`], this **does** include the
/// implicit capturing group corresponding to the entire match. Therefore,
/// when a non-None value is returned, it is guaranteed to be at least `1`.
/// Stated differently, a return value of `Some(0)` is impossible.
///
/// # Example
///
/// This shows a few cases where a static number of capture groups is
/// available and a few cases where it is not.
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let len = |pattern| {
/// Regex::new(pattern).map(|re| re.static_captures_len())
/// };
///
/// assert_eq!(Some(1), len("a")?);
/// assert_eq!(Some(2), len("(a)")?);
/// assert_eq!(Some(2), len("(a)|(b)")?);
/// assert_eq!(Some(3), len("(a)(b)|(c)(d)")?);
/// assert_eq!(None, len("(a)|b")?);
/// assert_eq!(None, len("a|(b)")?);
/// assert_eq!(None, len("(b)*")?);
/// assert_eq!(Some(2), len("(b)+")?);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: multiple patterns
///
/// This property extends to regexes with multiple patterns as well. In
/// order for their to be a static number of capture groups in this case,
/// every pattern must have the same static number.
///
/// ```
/// use regex_automata::meta::Regex;
///
/// let len = |patterns| {
/// Regex::new_many(patterns).map(|re| re.static_captures_len())
/// };
///
/// assert_eq!(Some(1), len(&["a", "b"])?);
/// assert_eq!(Some(2), len(&["(a)", "(b)"])?);
/// assert_eq!(Some(2), len(&["(a)|(b)", "(c)|(d)"])?);
/// assert_eq!(Some(3), len(&["(a)(b)|(c)(d)", "(x)(y)"])?);
/// assert_eq!(None, len(&["(a)", "b"])?);
/// assert_eq!(None, len(&["a", "(b)"])?);
/// assert_eq!(None, len(&["(a)", "(b)*"])?);
/// assert_eq!(Some(2), len(&["(a)+", "(b)+"])?);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn static_captures_len(&self) -> Option<usize> {
self.imp
.info
.props_union()
.static_explicit_captures_len()
.map(|len| len.saturating_add(1))
}
/// Return information about the capture groups in this `Regex`.
///
/// A `GroupInfo` is an immutable object that can be cheaply cloned. It
/// is responsible for maintaining a mapping between the capture groups
/// in the concrete syntax of zero or more regex patterns and their
/// internal representation used by some of the regex matchers. It is also
/// responsible for maintaining a mapping between the name of each group
/// (if one exists) and its corresponding group index.
///
/// A `GroupInfo` is ultimately what is used to build a [`Captures`] value,
/// which is some mutable space where group offsets are stored as a result
/// of a search.
///
/// # Example
///
/// This shows some alternatives to [`Regex::create_captures`]:
///
/// ```
/// use regex_automata::{
/// meta::Regex,
/// util::captures::Captures,
/// Match, PatternID, Span,
/// };
///
/// let re = Regex::new(r"(?<first>[A-Z][a-z]+) (?<last>[A-Z][a-z]+)")?;
///
/// // This is equivalent to Regex::create_captures. It stores matching
/// // offsets for all groups in the regex.
/// let mut all = Captures::all(re.group_info().clone());
/// re.captures("Bruce Springsteen", &mut all);
/// assert_eq!(Some(Match::must(0, 0..17)), all.get_match());
/// assert_eq!(Some(Span::from(0..5)), all.get_group_by_name("first"));
/// assert_eq!(Some(Span::from(6..17)), all.get_group_by_name("last"));
///
/// // In this version, we only care about the implicit groups, which
/// // means offsets for the explicit groups will be unavailable. It can
/// // sometimes be faster to ask for fewer groups, since the underlying
/// // regex engine needs to do less work to keep track of them.
/// let mut matches = Captures::matches(re.group_info().clone());
/// re.captures("Bruce Springsteen", &mut matches);
/// // We still get the overall match info.
/// assert_eq!(Some(Match::must(0, 0..17)), matches.get_match());
/// // But now the explicit groups are unavailable.
/// assert_eq!(None, matches.get_group_by_name("first"));
/// assert_eq!(None, matches.get_group_by_name("last"));
///
/// // Finally, in this version, we don't ask to keep track of offsets for
/// // *any* groups. All we get back is whether a match occurred, and if
/// // so, the ID of the pattern that matched.
/// let mut empty = Captures::empty(re.group_info().clone());
/// re.captures("Bruce Springsteen", &mut empty);
/// // it's a match!
/// assert!(empty.is_match());
/// // for pattern ID 0
/// assert_eq!(Some(PatternID::ZERO), empty.pattern());
/// // Match offsets are unavailable.
/// assert_eq!(None, empty.get_match());
/// // And of course, explicit groups are unavailable too.
/// assert_eq!(None, empty.get_group_by_name("first"));
/// assert_eq!(None, empty.get_group_by_name("last"));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn group_info(&self) -> &GroupInfo {
self.imp.strat.group_info()
}
/// Returns the configuration object used to build this `Regex`.
///
/// If no configuration object was explicitly passed, then the
/// configuration returned represents the default.
#[inline]
pub fn get_config(&self) -> &Config {
self.imp.info.config()
}
/// Returns true if this regex has a high chance of being "accelerated."
///
/// The precise meaning of "accelerated" is specifically left unspecified,
/// but the general meaning is that the search is a high likelihood of
/// running faster than a character-at-a-time loop inside a standard
/// regex engine.
///
/// When a regex is accelerated, it is only a *probabilistic* claim. That
/// is, just because the regex is believed to be accelerated, that doesn't
/// mean it will definitely execute searches very fast. Similarly, if a
/// regex is *not* accelerated, that is also a probabilistic claim. That
/// is, a regex for which `is_accelerated` returns `false` could still run
/// searches more quickly than a regex for which `is_accelerated` returns
/// `true`.
///
/// Whether a regex is marked as accelerated or not is dependent on
/// implementations details that may change in a semver compatible release.
/// That is, a regex that is accelerated in a `x.y.1` release might not be
/// accelerated in a `x.y.2` release.
///
/// Basically, the value of acceleration boils down to a hedge: a hodge
/// podge of internal heuristics combine to make a probabilistic guess
/// that this regex search may run "fast." The value in knowing this from
/// a caller's perspective is that it may act as a signal that no further
/// work should be done to accelerate a search. For example, a grep-like
/// tool might try to do some extra work extracting literals from a regex
/// to create its own heuristic acceleration strategies. But it might
/// choose to defer to this crate's acceleration strategy if one exists.
/// This routine permits querying whether such a strategy is active for a
/// particular regex.
///
/// # Example
///
/// ```
/// use regex_automata::meta::Regex;
///
/// // A simple literal is very likely to be accelerated.
/// let re = Regex::new(r"foo")?;
/// assert!(re.is_accelerated());
///
/// // A regex with no literals is likely to not be accelerated.
/// let re = Regex::new(r"\w")?;
/// assert!(!re.is_accelerated());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[inline]
pub fn is_accelerated(&self) -> bool {
self.imp.strat.is_accelerated()
}
/// Return the total approximate heap memory, in bytes, used by this `Regex`.
///
/// Note that currently, there is no high level configuration for setting
/// a limit on the specific value returned by this routine. Instead, the
/// following routines can be used to control heap memory at a bit of a
/// lower level:
///
/// * [`Config::nfa_size_limit`] controls how big _any_ of the NFAs are
/// allowed to be.
/// * [`Config::onepass_size_limit`] controls how big the one-pass DFA is
/// allowed to be.
/// * [`Config::hybrid_cache_capacity`] controls how much memory the lazy
/// DFA is permitted to allocate to store its transition table.
/// * [`Config::dfa_size_limit`] controls how big a fully compiled DFA is
/// allowed to be.
/// * [`Config::dfa_state_limit`] controls the conditions under which the
/// meta regex engine will even attempt to build a fully compiled DFA.
#[inline]
pub fn memory_usage(&self) -> usize {
self.imp.strat.memory_usage()
}
}
impl Clone for Regex {
fn clone(&self) -> Regex {
let imp = Arc::clone(&self.imp);
let pool = {
let strat = Arc::clone(&imp.strat);
let create: CachePoolFn = Box::new(move || strat.create_cache());
Pool::new(create)
};
Regex { imp, pool }
}
}
#[derive(Clone, Debug)]
pub(crate) struct RegexInfo(Arc<RegexInfoI>);
#[derive(Clone, Debug)]
struct RegexInfoI {
config: Config,
props: Vec<hir::Properties>,
props_union: hir::Properties,
}
impl RegexInfo {
fn new(config: Config, hirs: &[&Hir]) -> RegexInfo {
// Collect all of the properties from each of the HIRs, and also
// union them into one big set of properties representing all HIRs
// as if they were in one big alternation.
let mut props = vec![];
for hir in hirs.iter() {
props.push(hir.properties().clone());
}
let props_union = hir::Properties::union(&props);
RegexInfo(Arc::new(RegexInfoI { config, props, props_union }))
}
pub(crate) fn config(&self) -> &Config {
&self.0.config
}
pub(crate) fn props(&self) -> &[hir::Properties] {
&self.0.props
}
pub(crate) fn props_union(&self) -> &hir::Properties {
&self.0.props_union
}
pub(crate) fn pattern_len(&self) -> usize {
self.props().len()
}
pub(crate) fn memory_usage(&self) -> usize {
self.props().iter().map(|p| p.memory_usage()).sum::<usize>()
+ self.props_union().memory_usage()
}
/// Returns true when the search is guaranteed to be anchored. That is,
/// when a match is reported, its offset is guaranteed to correspond to
/// the start of the search.
///
/// This includes returning true when `input` _isn't_ anchored but the
/// underlying regex is.
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(crate) fn is_anchored_start(&self, input: &Input<'_>) -> bool {
input.get_anchored().is_anchored() || self.is_always_anchored_start()
}
/// Returns true when this regex is always anchored to the start of a
/// search. And in particular, that regardless of an `Input` configuration,
/// if any match is reported it must start at `0`.
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(crate) fn is_always_anchored_start(&self) -> bool {
use regex_syntax::hir::Look;
self.props_union().look_set_prefix().contains(Look::Start)
}
/// Returns true when this regex is always anchored to the end of a
/// search. And in particular, that regardless of an `Input` configuration,
/// if any match is reported it must end at the end of the haystack.
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(crate) fn is_always_anchored_end(&self) -> bool {
use regex_syntax::hir::Look;
self.props_union().look_set_suffix().contains(Look::End)
}
/// Returns true if and only if it is known that a match is impossible
/// for the given input. This is useful for short-circuiting and avoiding
/// running the regex engine if it's known no match can be reported.
///
/// Note that this doesn't necessarily detect every possible case. For
/// example, when `pattern_len() == 0`, a match is impossible, but that
/// case is so rare that it's fine to be handled by the regex engine
/// itself. That is, it's not worth the cost of adding it here in order to
/// make it a little faster. The reason is that this is called for every
/// search. so there is some cost to adding checks here. Arguably, some of
/// the checks that are here already probably shouldn't be here...
#[cfg_attr(feature = "perf-inline", inline(always))]
fn is_impossible(&self, input: &Input<'_>) -> bool {
// The underlying regex is anchored, so if we don't start the search
// at position 0, a match is impossible, because the anchor can only
// match at position 0.
if input.start() > 0 && self.is_always_anchored_start() {
return true;
}
// Same idea, but for the end anchor.
if input.end() < input.haystack().len()
&& self.is_always_anchored_end()
{
return true;
}
// If the haystack is smaller than the minimum length required, then
// we know there can be no match.
let minlen = match self.props_union().minimum_len() {
None => return false,
Some(minlen) => minlen,
};
if input.get_span().len() < minlen {
return true;
}
// Same idea as minimum, but for maximum. This is trickier. We can
// only apply the maximum when we know the entire span that we're
// searching *has* to match according to the regex (and possibly the
// input configuration). If we know there is too much for the regex
// to match, we can bail early.
//
// I don't think we can apply the maximum otherwise unfortunately.
if self.is_anchored_start(input) && self.is_always_anchored_end() {
let maxlen = match self.props_union().maximum_len() {
None => return false,
Some(maxlen) => maxlen,
};
if input.get_span().len() > maxlen {
return true;
}
}
false
}
}
/// An iterator over all non-overlapping matches.
///
/// The iterator yields a [`Match`] value until no more matches could be found.
///
/// The lifetime parameters are as follows:
///
/// * `'r` represents the lifetime of the `Regex` that produced this iterator.
/// * `'h` represents the lifetime of the haystack being searched.
///
/// This iterator can be created with the [`Regex::find_iter`] method.
#[derive(Debug)]
pub struct FindMatches<'r, 'h> {
re: &'r Regex,
cache: CachePoolGuard<'r>,
it: iter::Searcher<'h>,
}
impl<'r, 'h> FindMatches<'r, 'h> {
/// Returns the `Regex` value that created this iterator.
#[inline]
pub fn regex(&self) -> &'r Regex {
self.re
}
/// Returns the current `Input` associated with this iterator.
///
/// The `start` position on the given `Input` may change during iteration,
/// but all other values are guaranteed to remain invariant.
#[inline]
pub fn input<'s>(&'s self) -> &'s Input<'h> {
self.it.input()
}
}
impl<'r, 'h> Iterator for FindMatches<'r, 'h> {
type Item = Match;
#[inline]
fn next(&mut self) -> Option<Match> {
let FindMatches { re, ref mut cache, ref mut it } = *self;
it.advance(|input| Ok(re.search_with(cache, input)))
}
#[inline]
fn count(self) -> usize {
// If all we care about is a count of matches, then we only need to
// find the end position of each match. This can give us a 2x perf
// boost in some cases, because it avoids needing to do a reverse scan
// to find the start of a match.
let FindMatches { re, mut cache, it } = self;
// This does the deref for PoolGuard once instead of every iter.
let cache = &mut *cache;
it.into_half_matches_iter(
|input| Ok(re.search_half_with(cache, input)),
)
.count()
}
}
impl<'r, 'h> core::iter::FusedIterator for FindMatches<'r, 'h> {}
/// An iterator over all non-overlapping leftmost matches with their capturing
/// groups.
///
/// The iterator yields a [`Captures`] value until no more matches could be
/// found.
///
/// The lifetime parameters are as follows:
///
/// * `'r` represents the lifetime of the `Regex` that produced this iterator.
/// * `'h` represents the lifetime of the haystack being searched.
///
/// This iterator can be created with the [`Regex::captures_iter`] method.
#[derive(Debug)]
pub struct CapturesMatches<'r, 'h> {
re: &'r Regex,
cache: CachePoolGuard<'r>,
caps: Captures,
it: iter::Searcher<'h>,
}
impl<'r, 'h> CapturesMatches<'r, 'h> {
/// Returns the `Regex` value that created this iterator.
#[inline]
pub fn regex(&self) -> &'r Regex {
self.re
}
/// Returns the current `Input` associated with this iterator.
///
/// The `start` position on the given `Input` may change during iteration,
/// but all other values are guaranteed to remain invariant.
#[inline]
pub fn input<'s>(&'s self) -> &'s Input<'h> {
self.it.input()
}
}
impl<'r, 'h> Iterator for CapturesMatches<'r, 'h> {
type Item = Captures;
#[inline]
fn next(&mut self) -> Option<Captures> {
// Splitting 'self' apart seems necessary to appease borrowck.
let CapturesMatches { re, ref mut cache, ref mut caps, ref mut it } =
*self;
let _ = it.advance(|input| {
re.search_captures_with(cache, input, caps);
Ok(caps.get_match())
});
if caps.is_match() {
Some(caps.clone())
} else {
None
}
}
#[inline]
fn count(self) -> usize {
let CapturesMatches { re, mut cache, it, .. } = self;
// This does the deref for PoolGuard once instead of every iter.
let cache = &mut *cache;
it.into_half_matches_iter(
|input| Ok(re.search_half_with(cache, input)),
)
.count()
}
}
impl<'r, 'h> core::iter::FusedIterator for CapturesMatches<'r, 'h> {}
/// Yields all substrings delimited by a regular expression match.
///
/// The spans correspond to the offsets between matches.
///
/// The lifetime parameters are as follows:
///
/// * `'r` represents the lifetime of the `Regex` that produced this iterator.
/// * `'h` represents the lifetime of the haystack being searched.
///
/// This iterator can be created with the [`Regex::split`] method.
#[derive(Debug)]
pub struct Split<'r, 'h> {
finder: FindMatches<'r, 'h>,
last: usize,
}
impl<'r, 'h> Split<'r, 'h> {
/// Returns the current `Input` associated with this iterator.
///
/// The `start` position on the given `Input` may change during iteration,
/// but all other values are guaranteed to remain invariant.
#[inline]
pub fn input<'s>(&'s self) -> &'s Input<'h> {
self.finder.input()
}
}
impl<'r, 'h> Iterator for Split<'r, 'h> {
type Item = Span;
fn next(&mut self) -> Option<Span> {
match self.finder.next() {
None => {
let len = self.finder.it.input().haystack().len();
if self.last > len {
None
} else {
let span = Span::from(self.last..len);
self.last = len + 1; // Next call will return None
Some(span)
}
}
Some(m) => {
let span = Span::from(self.last..m.start());
self.last = m.end();
Some(span)
}
}
}
}
impl<'r, 'h> core::iter::FusedIterator for Split<'r, 'h> {}
/// Yields at most `N` spans delimited by a regular expression match.
///
/// The spans correspond to the offsets between matches. The last span will be
/// whatever remains after splitting.
///
/// The lifetime parameters are as follows:
///
/// * `'r` represents the lifetime of the `Regex` that produced this iterator.
/// * `'h` represents the lifetime of the haystack being searched.
///
/// This iterator can be created with the [`Regex::splitn`] method.
#[derive(Debug)]
pub struct SplitN<'r, 'h> {
splits: Split<'r, 'h>,
limit: usize,
}
impl<'r, 'h> SplitN<'r, 'h> {
/// Returns the current `Input` associated with this iterator.
///
/// The `start` position on the given `Input` may change during iteration,
/// but all other values are guaranteed to remain invariant.
#[inline]
pub fn input<'s>(&'s self) -> &'s Input<'h> {
self.splits.input()
}
}
impl<'r, 'h> Iterator for SplitN<'r, 'h> {
type Item = Span;
fn next(&mut self) -> Option<Span> {
if self.limit == 0 {
return None;
}
self.limit -= 1;
if self.limit > 0 {
return self.splits.next();
}
let len = self.splits.finder.it.input().haystack().len();
if self.splits.last > len {
// We've already returned all substrings.
None
} else {
// self.n == 0, so future calls will return None immediately
Some(Span::from(self.splits.last..len))
}
}
fn size_hint(&self) -> (usize, Option<usize>) {
(0, Some(self.limit))
}
}
impl<'r, 'h> core::iter::FusedIterator for SplitN<'r, 'h> {}
/// Represents mutable scratch space used by regex engines during a search.
///
/// Most of the regex engines in this crate require some kind of
/// mutable state in order to execute a search. This mutable state is
/// explicitly separated from the core regex object (such as a
/// [`thompson::NFA`](crate::nfa::thompson::NFA)) so that the read-only regex
/// object can be shared across multiple threads simultaneously without any
/// synchronization. Conversely, a `Cache` must either be duplicated if using
/// the same `Regex` from multiple threads, or else there must be some kind of
/// synchronization that guarantees exclusive access while it's in use by one
/// thread.
///
/// A `Regex` attempts to do this synchronization for you by using a thread
/// pool internally. Its size scales roughly with the number of simultaneous
/// regex searches.
///
/// For cases where one does not want to rely on a `Regex`'s internal thread
/// pool, lower level routines such as [`Regex::search_with`] are provided
/// that permit callers to pass a `Cache` into the search routine explicitly.
///
/// General advice is that the thread pool is often more than good enough.
/// However, it may be possible to observe the effects of its latency,
/// especially when searching many small haystacks from many threads
/// simultaneously.
///
/// Caches can be created from their corresponding `Regex` via
/// [`Regex::create_cache`]. A cache can only be used with either the `Regex`
/// that created it, or the `Regex` that was most recently used to reset it
/// with [`Cache::reset`]. Using a cache with any other `Regex` may result in
/// panics or incorrect results.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Input, Match};
///
/// let re = Regex::new(r"(?-u)m\w+\s+m\w+")?;
/// let mut cache = re.create_cache();
/// let input = Input::new("crazy janey and her mission man");
/// assert_eq!(
/// Some(Match::must(0, 20..31)),
/// re.search_with(&mut cache, &input),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[derive(Debug, Clone)]
pub struct Cache {
pub(crate) capmatches: Captures,
pub(crate) pikevm: wrappers::PikeVMCache,
pub(crate) backtrack: wrappers::BoundedBacktrackerCache,
pub(crate) onepass: wrappers::OnePassCache,
pub(crate) hybrid: wrappers::HybridCache,
pub(crate) revhybrid: wrappers::ReverseHybridCache,
}
impl Cache {
/// Creates a new `Cache` for use with this regex.
///
/// The cache returned should only be used for searches for the given
/// `Regex`. If you want to reuse the cache for another `Regex`, then you
/// must call [`Cache::reset`] with that `Regex`.
pub fn new(re: &Regex) -> Cache {
re.create_cache()
}
/// Reset this cache such that it can be used for searching with the given
/// `Regex` (and only that `Regex`).
///
/// A cache reset permits potentially reusing memory already allocated in
/// this cache with a different `Regex`.
///
/// # Example
///
/// This shows how to re-purpose a cache for use with a different `Regex`.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, Match, Input};
///
/// let re1 = Regex::new(r"\w")?;
/// let re2 = Regex::new(r"\W")?;
///
/// let mut cache = re1.create_cache();
/// assert_eq!(
/// Some(Match::must(0, 0..2)),
/// re1.search_with(&mut cache, &Input::new("Δ")),
/// );
///
/// // Using 'cache' with re2 is not allowed. It may result in panics or
/// // incorrect results. In order to re-purpose the cache, we must reset
/// // it with the Regex we'd like to use it with.
/// //
/// // Similarly, after this reset, using the cache with 're1' is also not
/// // allowed.
/// cache.reset(&re2);
/// assert_eq!(
/// Some(Match::must(0, 0..3)),
/// re2.search_with(&mut cache, &Input::new("☃")),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn reset(&mut self, re: &Regex) {
re.imp.strat.reset_cache(self)
}
/// Returns the heap memory usage, in bytes, of this cache.
///
/// This does **not** include the stack size used up by this cache. To
/// compute that, use `std::mem::size_of::<Cache>()`.
pub fn memory_usage(&self) -> usize {
let mut bytes = 0;
bytes += self.pikevm.memory_usage();
bytes += self.backtrack.memory_usage();
bytes += self.onepass.memory_usage();
bytes += self.hybrid.memory_usage();
bytes += self.revhybrid.memory_usage();
bytes
}
}
/// An object describing the configuration of a `Regex`.
///
/// This configuration only includes options for the
/// non-syntax behavior of a `Regex`, and can be applied via the
/// [`Builder::configure`] method. For configuring the syntax options, see
/// [`util::syntax::Config`](crate::util::syntax::Config).
///
/// # Example: lower the NFA size limit
///
/// In some cases, the default size limit might be too big. The size limit can
/// be lowered, which will prevent large regex patterns from compiling.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// .configure(Regex::config().nfa_size_limit(Some(20 * (1<<10))))
/// // Not even 20KB is enough to build a single large Unicode class!
/// .build(r"\pL");
/// assert!(result.is_err());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[derive(Clone, Debug, Default)]
pub struct Config {
// As with other configuration types in this crate, we put all our knobs
// in options so that we can distinguish between "default" and "not set."
// This makes it possible to easily combine multiple configurations
// without default values overwriting explicitly specified values. See the
// 'overwrite' method.
//
// For docs on the fields below, see the corresponding method setters.
match_kind: Option<MatchKind>,
utf8_empty: Option<bool>,
autopre: Option<bool>,
pre: Option<Option<Prefilter>>,
which_captures: Option<WhichCaptures>,
nfa_size_limit: Option<Option<usize>>,
onepass_size_limit: Option<Option<usize>>,
hybrid_cache_capacity: Option<usize>,
hybrid: Option<bool>,
dfa: Option<bool>,
dfa_size_limit: Option<Option<usize>>,
dfa_state_limit: Option<Option<usize>>,
onepass: Option<bool>,
backtrack: Option<bool>,
byte_classes: Option<bool>,
line_terminator: Option<u8>,
}
impl Config {
/// Create a new configuration object for a `Regex`.
pub fn new() -> Config {
Config::default()
}
/// Set the match semantics for a `Regex`.
///
/// The default value is [`MatchKind::LeftmostFirst`].
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Match, MatchKind};
///
/// // By default, leftmost-first semantics are used, which
/// // disambiguates matches at the same position by selecting
/// // the one that corresponds earlier in the pattern.
/// let re = Regex::new("sam|samwise")?;
/// assert_eq!(Some(Match::must(0, 0..3)), re.find("samwise"));
///
/// // But with 'all' semantics, match priority is ignored
/// // and all match states are included. When coupled with
/// // a leftmost search, the search will report the last
/// // possible match.
/// let re = Regex::builder()
/// .configure(Regex::config().match_kind(MatchKind::All))
/// .build("sam|samwise")?;
/// assert_eq!(Some(Match::must(0, 0..7)), re.find("samwise"));
/// // Beware that this can lead to skipping matches!
/// // Usually 'all' is used for anchored reverse searches
/// // only, or for overlapping searches.
/// assert_eq!(Some(Match::must(0, 4..11)), re.find("sam samwise"));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn match_kind(self, kind: MatchKind) -> Config {
Config { match_kind: Some(kind), ..self }
}
/// Toggles whether empty matches are permitted to occur between the code
/// units of a UTF-8 encoded codepoint.
///
/// This should generally be enabled when search a `&str` or anything that
/// you otherwise know is valid UTF-8. It should be disabled in all other
/// cases. Namely, if the haystack is not valid UTF-8 and this is enabled,
/// then behavior is unspecified.
///
/// By default, this is enabled.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::new("")?;
/// let got: Vec<Match> = re.find_iter("☃").collect();
/// // Matches only occur at the beginning and end of the snowman.
/// assert_eq!(got, vec![
/// Match::must(0, 0..0),
/// Match::must(0, 3..3),
/// ]);
///
/// let re = Regex::builder()
/// .configure(Regex::config().utf8_empty(false))
/// .build("")?;
/// let got: Vec<Match> = re.find_iter("☃").collect();
/// // Matches now occur at every position!
/// assert_eq!(got, vec![
/// Match::must(0, 0..0),
/// Match::must(0, 1..1),
/// Match::must(0, 2..2),
/// Match::must(0, 3..3),
/// ]);
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn utf8_empty(self, yes: bool) -> Config {
Config { utf8_empty: Some(yes), ..self }
}
/// Toggles whether automatic prefilter support is enabled.
///
/// If this is disabled and [`Config::prefilter`] is not set, then the
/// meta regex engine will not use any prefilters. This can sometimes
/// be beneficial in cases where you know (or have measured) that the
/// prefilter leads to overall worse search performance.
///
/// By default, this is enabled.
///
/// # Example
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::builder()
/// .configure(Regex::config().auto_prefilter(false))
/// .build(r"Bruce \w+")?;
/// let hay = "Hello Bruce Springsteen!";
/// assert_eq!(Some(Match::must(0, 6..23)), re.find(hay));
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn auto_prefilter(self, yes: bool) -> Config {
Config { autopre: Some(yes), ..self }
}
/// Overrides and sets the prefilter to use inside a `Regex`.
///
/// This permits one to forcefully set a prefilter in cases where the
/// caller knows better than whatever the automatic prefilter logic is
/// capable of.
///
/// By default, this is set to `None` and an automatic prefilter will be
/// used if one could be built. (Assuming [`Config::auto_prefilter`] is
/// enabled, which it is by default.)
///
/// # Example
///
/// This example shows how to set your own prefilter. In the case of a
/// pattern like `Bruce \w+`, the automatic prefilter is likely to be
/// constructed in a way that it will look for occurrences of `Bruce `.
/// In most cases, this is the best choice. But in some cases, it may be
/// the case that running `memchr` on `B` is the best choice. One can
/// achieve that behavior by overriding the automatic prefilter logic
/// and providing a prefilter that just matches `B`.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{
/// meta::Regex,
/// util::prefilter::Prefilter,
/// Match, MatchKind,
/// };
///
/// let pre = Prefilter::new(MatchKind::LeftmostFirst, &["B"])
/// .expect("a prefilter");
/// let re = Regex::builder()
/// .configure(Regex::config().prefilter(Some(pre)))
/// .build(r"Bruce \w+")?;
/// let hay = "Hello Bruce Springsteen!";
/// assert_eq!(Some(Match::must(0, 6..23)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: incorrect prefilters can lead to incorrect results!
///
/// Be warned that setting an incorrect prefilter can lead to missed
/// matches. So if you use this option, ensure your prefilter can _never_
/// report false negatives. (A false positive is, on the other hand, quite
/// okay and generally unavoidable.)
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::{
/// meta::Regex,
/// util::prefilter::Prefilter,
/// Match, MatchKind,
/// };
///
/// let pre = Prefilter::new(MatchKind::LeftmostFirst, &["Z"])
/// .expect("a prefilter");
/// let re = Regex::builder()
/// .configure(Regex::config().prefilter(Some(pre)))
/// .build(r"Bruce \w+")?;
/// let hay = "Hello Bruce Springsteen!";
/// // Oops! No match found, but there should be one!
/// assert_eq!(None, re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn prefilter(self, pre: Option<Prefilter>) -> Config {
Config { pre: Some(pre), ..self }
}
/// Configures what kinds of groups are compiled as "capturing" in the
/// underlying regex engine.
///
/// This is set to [`WhichCaptures::All`] by default. Callers may wish to
/// use [`WhichCaptures::Implicit`] in cases where one wants avoid the
/// overhead of capture states for explicit groups.
///
/// Note that another approach to avoiding the overhead of capture groups
/// is by using non-capturing groups in the regex pattern. That is,
/// `(?:a)` instead of `(a)`. This option is useful when you can't control
/// the concrete syntax but know that you don't need the underlying capture
/// states. For example, using `WhichCaptures::Implicit` will behave as if
/// all explicit capturing groups in the pattern were non-capturing.
///
/// Setting this to `WhichCaptures::None` is usually not the right thing to
/// do. When no capture states are compiled, some regex engines (such as
/// the `PikeVM`) won't be able to report match offsets. This will manifest
/// as no match being found.
///
/// # Example
///
/// This example demonstrates how the results of capture groups can change
/// based on this option. First we show the default (all capture groups in
/// the pattern are capturing):
///
/// ```
/// use regex_automata::{meta::Regex, Match, Span};
///
/// let re = Regex::new(r"foo([0-9]+)bar")?;
/// let hay = "foo123bar";
///
/// let mut caps = re.create_captures();
/// re.captures(hay, &mut caps);
/// assert_eq!(Some(Span::from(0..9)), caps.get_group(0));
/// assert_eq!(Some(Span::from(3..6)), caps.get_group(1));
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// And now we show the behavior when we only include implicit capture
/// groups. In this case, we can only find the overall match span, but the
/// spans of any other explicit group don't exist because they are treated
/// as non-capturing. (In effect, when `WhichCaptures::Implicit` is used,
/// there is no real point in using [`Regex::captures`] since it will never
/// be able to report more information than [`Regex::find`].)
///
/// ```
/// use regex_automata::{
/// meta::Regex,
/// nfa::thompson::WhichCaptures,
/// Match,
/// Span,
/// };
///
/// let re = Regex::builder()
/// .configure(Regex::config().which_captures(WhichCaptures::Implicit))
/// .build(r"foo([0-9]+)bar")?;
/// let hay = "foo123bar";
///
/// let mut caps = re.create_captures();
/// re.captures(hay, &mut caps);
/// assert_eq!(Some(Span::from(0..9)), caps.get_group(0));
/// assert_eq!(None, caps.get_group(1));
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn which_captures(mut self, which_captures: WhichCaptures) -> Config {
self.which_captures = Some(which_captures);
self
}
/// Sets the size limit, in bytes, to enforce on the construction of every
/// NFA build by the meta regex engine.
///
/// Setting it to `None` disables the limit. This is not recommended if
/// you're compiling untrusted patterns.
///
/// Note that this limit is applied to _each_ NFA built, and if any of
/// them exceed the limit, then construction will fail. This limit does
/// _not_ correspond to the total memory used by all NFAs in the meta regex
/// engine.
///
/// This defaults to some reasonable number that permits most reasonable
/// patterns.
///
/// # Example
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// .configure(Regex::config().nfa_size_limit(Some(20 * (1<<10))))
/// // Not even 20KB is enough to build a single large Unicode class!
/// .build(r"\pL");
/// assert!(result.is_err());
///
/// // But notice that building such a regex with the exact same limit
/// // can succeed depending on other aspects of the configuration. For
/// // example, a single *forward* NFA will (at time of writing) fit into
/// // the 20KB limit, but a *reverse* NFA of the same pattern will not.
/// // So if one configures a meta regex such that a reverse NFA is never
/// // needed and thus never built, then the 20KB limit will be enough for
/// // a pattern like \pL!
/// let result = Regex::builder()
/// .configure(Regex::config()
/// .nfa_size_limit(Some(20 * (1<<10)))
/// // The DFAs are the only thing that (currently) need a reverse
/// // NFA. So if both are disabled, the meta regex engine will
/// // skip building the reverse NFA. Note that this isn't an API
/// // guarantee. A future semver compatible version may introduce
/// // new use cases for a reverse NFA.
/// .hybrid(false)
/// .dfa(false)
/// )
/// // Not even 20KB is enough to build a single large Unicode class!
/// .build(r"\pL");
/// assert!(result.is_ok());
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn nfa_size_limit(self, limit: Option<usize>) -> Config {
Config { nfa_size_limit: Some(limit), ..self }
}
/// Sets the size limit, in bytes, for the one-pass DFA.
///
/// Setting it to `None` disables the limit. Disabling the limit is
/// strongly discouraged when compiling untrusted patterns. Even if the
/// patterns are trusted, it still may not be a good idea, since a one-pass
/// DFA can use a lot of memory. With that said, as the size of a regex
/// increases, the likelihood of it being one-pass likely decreases.
///
/// This defaults to some reasonable number that permits most reasonable
/// one-pass patterns.
///
/// # Example
///
/// This shows how to set the one-pass DFA size limit. Note that since
/// a one-pass DFA is an optional component of the meta regex engine,
/// this size limit only impacts what is built internally and will never
/// determine whether a `Regex` itself fails to build.
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// .configure(Regex::config().onepass_size_limit(Some(2 * (1<<20))))
/// .build(r"\pL{5}");
/// assert!(result.is_ok());
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn onepass_size_limit(self, limit: Option<usize>) -> Config {
Config { onepass_size_limit: Some(limit), ..self }
}
/// Set the cache capacity, in bytes, for the lazy DFA.
///
/// The cache capacity of the lazy DFA determines approximately how much
/// heap memory it is allowed to use to store its state transitions. The
/// state transitions are computed at search time, and if the cache fills
/// up it, it is cleared. At this point, any previously generated state
/// transitions are lost and are re-generated if they're needed again.
///
/// This sort of cache filling and clearing works quite well _so long as
/// cache clearing happens infrequently_. If it happens too often, then the
/// meta regex engine will stop using the lazy DFA and switch over to a
/// different regex engine.
///
/// In cases where the cache is cleared too often, it may be possible to
/// give the cache more space and reduce (or eliminate) how often it is
/// cleared. Similarly, sometimes a regex is so big that the lazy DFA isn't
/// used at all if its cache capacity isn't big enough.
///
/// The capacity set here is a _limit_ on how much memory is used. The
/// actual memory used is only allocated as it's needed.
///
/// Determining the right value for this is a little tricky and will likely
/// required some profiling. Enabling the `logging` feature and setting the
/// log level to `trace` will also tell you how often the cache is being
/// cleared.
///
/// # Example
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// .configure(Regex::config().hybrid_cache_capacity(20 * (1<<20)))
/// .build(r"\pL{5}");
/// assert!(result.is_ok());
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn hybrid_cache_capacity(self, limit: usize) -> Config {
Config { hybrid_cache_capacity: Some(limit), ..self }
}
/// Sets the size limit, in bytes, for heap memory used for a fully
/// compiled DFA.
///
/// **NOTE:** If you increase this, you'll likely also need to increase
/// [`Config::dfa_state_limit`].
///
/// In contrast to the lazy DFA, building a full DFA requires computing
/// all of its state transitions up front. This can be a very expensive
/// process, and runs in worst case `2^n` time and space (where `n` is
/// proportional to the size of the regex). However, a full DFA unlocks
/// some additional optimization opportunities.
///
/// Because full DFAs can be so expensive, the default limits for them are
/// incredibly small. Generally speaking, if your regex is moderately big
/// or if you're using Unicode features (`\w` is Unicode-aware by default
/// for example), then you can expect that the meta regex engine won't even
/// attempt to build a DFA for it.
///
/// If this and [`Config::dfa_state_limit`] are set to `None`, then the
/// meta regex will not use any sort of limits when deciding whether to
/// build a DFA. This in turn makes construction of a `Regex` take
/// worst case exponential time and space. Even short patterns can result
/// in huge space blow ups. So it is strongly recommended to keep some kind
/// of limit set!
///
/// The default is set to a small number that permits some simple regexes
/// to get compiled into DFAs in reasonable time.
///
/// # Example
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// // 100MB is much bigger than the default.
/// .configure(Regex::config()
/// .dfa_size_limit(Some(100 * (1<<20)))
/// // We don't care about size too much here, so just
/// // remove the NFA state limit altogether.
/// .dfa_state_limit(None))
/// .build(r"\pL{5}");
/// assert!(result.is_ok());
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn dfa_size_limit(self, limit: Option<usize>) -> Config {
Config { dfa_size_limit: Some(limit), ..self }
}
/// Sets a limit on the total number of NFA states, beyond which, a full
/// DFA is not attempted to be compiled.
///
/// This limit works in concert with [`Config::dfa_size_limit`]. Namely,
/// where as `Config::dfa_size_limit` is applied by attempting to construct
/// a DFA, this limit is used to avoid the attempt in the first place. This
/// is useful to avoid hefty initialization costs associated with building
/// a DFA for cases where it is obvious the DFA will ultimately be too big.
///
/// By default, this is set to a very small number.
///
/// # Example
///
/// ```
/// # if cfg!(miri) { return Ok(()); } // miri takes too long
/// use regex_automata::meta::Regex;
///
/// let result = Regex::builder()
/// .configure(Regex::config()
/// // Sometimes the default state limit rejects DFAs even
/// // if they would fit in the size limit. Here, we disable
/// // the check on the number of NFA states and just rely on
/// // the size limit.
/// .dfa_state_limit(None))
/// .build(r"(?-u)\w{30}");
/// assert!(result.is_ok());
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn dfa_state_limit(self, limit: Option<usize>) -> Config {
Config { dfa_state_limit: Some(limit), ..self }
}
/// Whether to attempt to shrink the size of the alphabet for the regex
/// pattern or not. When enabled, the alphabet is shrunk into a set of
/// equivalence classes, where every byte in the same equivalence class
/// cannot discriminate between a match or non-match.
///
/// **WARNING:** This is only useful for debugging DFAs. Disabling this
/// does not yield any speed advantages. Indeed, disabling it can result
/// in much higher memory usage. Disabling byte classes is useful for
/// debugging the actual generated transitions because it lets one see the
/// transitions defined on actual bytes instead of the equivalence classes.
///
/// This option is enabled by default and should never be disabled unless
/// one is debugging the meta regex engine's internals.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::builder()
/// .configure(Regex::config().byte_classes(false))
/// .build(r"[a-z]+")?;
/// let hay = "!!quux!!";
/// assert_eq!(Some(Match::must(0, 2..6)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn byte_classes(self, yes: bool) -> Config {
Config { byte_classes: Some(yes), ..self }
}
/// Set the line terminator to be used by the `^` and `$` anchors in
/// multi-line mode.
///
/// This option has no effect when CRLF mode is enabled. That is,
/// regardless of this setting, `(?Rm:^)` and `(?Rm:$)` will always treat
/// `\r` and `\n` as line terminators (and will never match between a `\r`
/// and a `\n`).
///
/// By default, `\n` is the line terminator.
///
/// **Warning**: This does not change the behavior of `.`. To do that,
/// you'll need to configure the syntax option
/// [`syntax::Config::line_terminator`](crate::util::syntax::Config::line_terminator)
/// in addition to this. Otherwise, `.` will continue to match any
/// character other than `\n`.
///
/// # Example
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .syntax(syntax::Config::new().multi_line(true))
/// .configure(Regex::config().line_terminator(b'\x00'))
/// .build(r"^foo$")?;
/// let hay = "\x00foo\x00";
/// assert_eq!(Some(Match::must(0, 1..4)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn line_terminator(self, byte: u8) -> Config {
Config { line_terminator: Some(byte), ..self }
}
/// Toggle whether the hybrid NFA/DFA (also known as the "lazy DFA") should
/// be available for use by the meta regex engine.
///
/// Enabling this does not necessarily mean that the lazy DFA will
/// definitely be used. It just means that it will be _available_ for use
/// if the meta regex engine thinks it will be useful.
///
/// When the `hybrid` crate feature is enabled, then this is enabled by
/// default. Otherwise, if the crate feature is disabled, then this is
/// always disabled, regardless of its setting by the caller.
pub fn hybrid(self, yes: bool) -> Config {
Config { hybrid: Some(yes), ..self }
}
/// Toggle whether a fully compiled DFA should be available for use by the
/// meta regex engine.
///
/// Enabling this does not necessarily mean that a DFA will definitely be
/// used. It just means that it will be _available_ for use if the meta
/// regex engine thinks it will be useful.
///
/// When the `dfa-build` crate feature is enabled, then this is enabled by
/// default. Otherwise, if the crate feature is disabled, then this is
/// always disabled, regardless of its setting by the caller.
pub fn dfa(self, yes: bool) -> Config {
Config { dfa: Some(yes), ..self }
}
/// Toggle whether a one-pass DFA should be available for use by the meta
/// regex engine.
///
/// Enabling this does not necessarily mean that a one-pass DFA will
/// definitely be used. It just means that it will be _available_ for
/// use if the meta regex engine thinks it will be useful. (Indeed, a
/// one-pass DFA can only be used when the regex is one-pass. See the
/// [`dfa::onepass`](crate::dfa::onepass) module for more details.)
///
/// When the `dfa-onepass` crate feature is enabled, then this is enabled
/// by default. Otherwise, if the crate feature is disabled, then this is
/// always disabled, regardless of its setting by the caller.
pub fn onepass(self, yes: bool) -> Config {
Config { onepass: Some(yes), ..self }
}
/// Toggle whether a bounded backtracking regex engine should be available
/// for use by the meta regex engine.
///
/// Enabling this does not necessarily mean that a bounded backtracker will
/// definitely be used. It just means that it will be _available_ for use
/// if the meta regex engine thinks it will be useful.
///
/// When the `nfa-backtrack` crate feature is enabled, then this is enabled
/// by default. Otherwise, if the crate feature is disabled, then this is
/// always disabled, regardless of its setting by the caller.
pub fn backtrack(self, yes: bool) -> Config {
Config { backtrack: Some(yes), ..self }
}
/// Returns the match kind on this configuration, as set by
/// [`Config::match_kind`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_match_kind(&self) -> MatchKind {
self.match_kind.unwrap_or(MatchKind::LeftmostFirst)
}
/// Returns whether empty matches must fall on valid UTF-8 boundaries, as
/// set by [`Config::utf8_empty`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_utf8_empty(&self) -> bool {
self.utf8_empty.unwrap_or(true)
}
/// Returns whether automatic prefilters are enabled, as set by
/// [`Config::auto_prefilter`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_auto_prefilter(&self) -> bool {
self.autopre.unwrap_or(true)
}
/// Returns a manually set prefilter, if one was set by
/// [`Config::prefilter`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_prefilter(&self) -> Option<&Prefilter> {
self.pre.as_ref().unwrap_or(&None).as_ref()
}
/// Returns the capture configuration, as set by
/// [`Config::which_captures`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_which_captures(&self) -> WhichCaptures {
self.which_captures.unwrap_or(WhichCaptures::All)
}
/// Returns NFA size limit, as set by [`Config::nfa_size_limit`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_nfa_size_limit(&self) -> Option<usize> {
self.nfa_size_limit.unwrap_or(Some(10 * (1 << 20)))
}
/// Returns one-pass DFA size limit, as set by
/// [`Config::onepass_size_limit`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_onepass_size_limit(&self) -> Option<usize> {
self.onepass_size_limit.unwrap_or(Some(1 * (1 << 20)))
}
/// Returns hybrid NFA/DFA cache capacity, as set by
/// [`Config::hybrid_cache_capacity`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_hybrid_cache_capacity(&self) -> usize {
self.hybrid_cache_capacity.unwrap_or(2 * (1 << 20))
}
/// Returns DFA size limit, as set by [`Config::dfa_size_limit`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_dfa_size_limit(&self) -> Option<usize> {
// The default for this is VERY small because building a full DFA is
// ridiculously costly. But for regexes that are very small, it can be
// beneficial to use a full DFA. In particular, a full DFA can enable
// additional optimizations via something called "accelerated" states.
// Namely, when there's a state with only a few outgoing transitions,
// we can temporary suspend walking the transition table and use memchr
// for just those outgoing transitions to skip ahead very quickly.
//
// Generally speaking, if Unicode is enabled in your regex and you're
// using some kind of Unicode feature, then it's going to blow this
// size limit. Moreover, Unicode tends to defeat the "accelerated"
// state optimization too, so it's a double whammy.
//
// We also use a limit on the number of NFA states to avoid even
// starting the DFA construction process. Namely, DFA construction
// itself could make lots of initial allocs proportional to the size
// of the NFA, and if the NFA is large, it doesn't make sense to pay
// that cost if we know it's likely to be blown by a large margin.
self.dfa_size_limit.unwrap_or(Some(40 * (1 << 10)))
}
/// Returns DFA size limit in terms of the number of states in the NFA, as
/// set by [`Config::dfa_state_limit`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_dfa_state_limit(&self) -> Option<usize> {
// Again, as with the size limit, we keep this very small.
self.dfa_state_limit.unwrap_or(Some(30))
}
/// Returns whether byte classes are enabled, as set by
/// [`Config::byte_classes`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_byte_classes(&self) -> bool {
self.byte_classes.unwrap_or(true)
}
/// Returns the line terminator for this configuration, as set by
/// [`Config::line_terminator`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_line_terminator(&self) -> u8 {
self.line_terminator.unwrap_or(b'\n')
}
/// Returns whether the hybrid NFA/DFA regex engine may be used, as set by
/// [`Config::hybrid`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_hybrid(&self) -> bool {
#[cfg(feature = "hybrid")]
{
self.hybrid.unwrap_or(true)
}
#[cfg(not(feature = "hybrid"))]
{
false
}
}
/// Returns whether the DFA regex engine may be used, as set by
/// [`Config::dfa`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_dfa(&self) -> bool {
#[cfg(feature = "dfa-build")]
{
self.dfa.unwrap_or(true)
}
#[cfg(not(feature = "dfa-build"))]
{
false
}
}
/// Returns whether the one-pass DFA regex engine may be used, as set by
/// [`Config::onepass`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_onepass(&self) -> bool {
#[cfg(feature = "dfa-onepass")]
{
self.onepass.unwrap_or(true)
}
#[cfg(not(feature = "dfa-onepass"))]
{
false
}
}
/// Returns whether the bounded backtracking regex engine may be used, as
/// set by [`Config::backtrack`].
///
/// If it was not explicitly set, then a default value is returned.
pub fn get_backtrack(&self) -> bool {
#[cfg(feature = "nfa-backtrack")]
{
self.backtrack.unwrap_or(true)
}
#[cfg(not(feature = "nfa-backtrack"))]
{
false
}
}
/// Overwrite the default configuration such that the options in `o` are
/// always used. If an option in `o` is not set, then the corresponding
/// option in `self` is used. If it's not set in `self` either, then it
/// remains not set.
pub(crate) fn overwrite(&self, o: Config) -> Config {
Config {
match_kind: o.match_kind.or(self.match_kind),
utf8_empty: o.utf8_empty.or(self.utf8_empty),
autopre: o.autopre.or(self.autopre),
pre: o.pre.or_else(|| self.pre.clone()),
which_captures: o.which_captures.or(self.which_captures),
nfa_size_limit: o.nfa_size_limit.or(self.nfa_size_limit),
onepass_size_limit: o
.onepass_size_limit
.or(self.onepass_size_limit),
hybrid_cache_capacity: o
.hybrid_cache_capacity
.or(self.hybrid_cache_capacity),
hybrid: o.hybrid.or(self.hybrid),
dfa: o.dfa.or(self.dfa),
dfa_size_limit: o.dfa_size_limit.or(self.dfa_size_limit),
dfa_state_limit: o.dfa_state_limit.or(self.dfa_state_limit),
onepass: o.onepass.or(self.onepass),
backtrack: o.backtrack.or(self.backtrack),
byte_classes: o.byte_classes.or(self.byte_classes),
line_terminator: o.line_terminator.or(self.line_terminator),
}
}
}
/// A builder for configuring and constructing a `Regex`.
///
/// The builder permits configuring two different aspects of a `Regex`:
///
/// * [`Builder::configure`] will set high-level configuration options as
/// described by a [`Config`].
/// * [`Builder::syntax`] will set the syntax level configuration options
/// as described by a [`util::syntax::Config`](crate::util::syntax::Config).
/// This only applies when building a `Regex` from pattern strings.
///
/// Once configured, the builder can then be used to construct a `Regex` from
/// one of 4 different inputs:
///
/// * [`Builder::build`] creates a regex from a single pattern string.
/// * [`Builder::build_many`] creates a regex from many pattern strings.
/// * [`Builder::build_from_hir`] creates a regex from a
/// [`regex-syntax::Hir`](Hir) expression.
/// * [`Builder::build_many_from_hir`] creates a regex from many
/// [`regex-syntax::Hir`](Hir) expressions.
///
/// The latter two methods in particular provide a way to construct a fully
/// feature regular expression matcher directly from an `Hir` expression
/// without having to first convert it to a string. (This is in contrast to the
/// top-level `regex` crate which intentionally provides no such API in order
/// to avoid making `regex-syntax` a public dependency.)
///
/// As a convenience, this builder may be created via [`Regex::builder`], which
/// may help avoid an extra import.
///
/// # Example: change the line terminator
///
/// This example shows how to enable multi-line mode by default and change the
/// line terminator to the NUL byte:
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .syntax(syntax::Config::new().multi_line(true))
/// .configure(Regex::config().line_terminator(b'\x00'))
/// .build(r"^foo$")?;
/// let hay = "\x00foo\x00";
/// assert_eq!(Some(Match::must(0, 1..4)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
///
/// # Example: disable UTF-8 requirement
///
/// By default, regex patterns are required to match UTF-8. This includes
/// regex patterns that can produce matches of length zero. In the case of an
/// empty match, by default, matches will not appear between the code units of
/// a UTF-8 encoded codepoint.
///
/// However, it can be useful to disable this requirement, particularly if
/// you're searching things like `&[u8]` that are not known to be valid UTF-8.
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let mut builder = Regex::builder();
/// // Disables the requirement that non-empty matches match UTF-8.
/// builder.syntax(syntax::Config::new().utf8(false));
/// // Disables the requirement that empty matches match UTF-8 boundaries.
/// builder.configure(Regex::config().utf8_empty(false));
///
/// // We can match raw bytes via \xZZ syntax, but we need to disable
/// // Unicode mode to do that. We could disable it everywhere, or just
/// // selectively, as shown here.
/// let re = builder.build(r"(?-u:\xFF)foo(?-u:\xFF)")?;
/// let hay = b"\xFFfoo\xFF";
/// assert_eq!(Some(Match::must(0, 0..5)), re.find(hay));
///
/// // We can also match between code units.
/// let re = builder.build(r"")?;
/// let hay = "☃";
/// assert_eq!(re.find_iter(hay).collect::<Vec<Match>>(), vec![
/// Match::must(0, 0..0),
/// Match::must(0, 1..1),
/// Match::must(0, 2..2),
/// Match::must(0, 3..3),
/// ]);
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[derive(Clone, Debug)]
pub struct Builder {
config: Config,
ast: ast::parse::ParserBuilder,
hir: hir::translate::TranslatorBuilder,
}
impl Builder {
/// Creates a new builder for configuring and constructing a [`Regex`].
pub fn new() -> Builder {
Builder {
config: Config::default(),
ast: ast::parse::ParserBuilder::new(),
hir: hir::translate::TranslatorBuilder::new(),
}
}
/// Builds a `Regex` from a single pattern string.
///
/// If there was a problem parsing the pattern or a problem turning it into
/// a regex matcher, then an error is returned.
///
/// # Example
///
/// This example shows how to configure syntax options.
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .syntax(syntax::Config::new().crlf(true).multi_line(true))
/// .build(r"^foo$")?;
/// let hay = "\r\nfoo\r\n";
/// assert_eq!(Some(Match::must(0, 2..5)), re.find(hay));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn build(&self, pattern: &str) -> Result<Regex, BuildError> {
self.build_many(&[pattern])
}
/// Builds a `Regex` from many pattern strings.
///
/// If there was a problem parsing any of the patterns or a problem turning
/// them into a regex matcher, then an error is returned.
///
/// # Example: finding the pattern that caused an error
///
/// When a syntax error occurs, it is possible to ask which pattern
/// caused the syntax error.
///
/// ```
/// use regex_automata::{meta::Regex, PatternID};
///
/// let err = Regex::builder()
/// .build_many(&["a", "b", r"\p{Foo}", "c"])
/// .unwrap_err();
/// assert_eq!(Some(PatternID::must(2)), err.pattern());
/// ```
///
/// # Example: zero patterns is valid
///
/// Building a regex with zero patterns results in a regex that never
/// matches anything. Because this routine is generic, passing an empty
/// slice usually requires a turbo-fish (or something else to help type
/// inference).
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .build_many::<&str>(&[])?;
/// assert_eq!(None, re.find(""));
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn build_many<P: AsRef<str>>(
&self,
patterns: &[P],
) -> Result<Regex, BuildError> {
use crate::util::primitives::IteratorIndexExt;
log! {
debug!("building meta regex with {} patterns:", patterns.len());
for (pid, p) in patterns.iter().with_pattern_ids() {
let p = p.as_ref();
// We might split a grapheme with this truncation logic, but
// that's fine. We at least avoid splitting a codepoint.
let maxoff = p
.char_indices()
.map(|(i, ch)| i + ch.len_utf8())
.take(1000)
.last()
.unwrap_or(0);
if maxoff < p.len() {
debug!("{:?}: {}[... snip ...]", pid, &p[..maxoff]);
} else {
debug!("{:?}: {}", pid, p);
}
}
}
let (mut asts, mut hirs) = (vec![], vec![]);
for (pid, p) in patterns.iter().with_pattern_ids() {
let ast = self
.ast
.build()
.parse(p.as_ref())
.map_err(|err| BuildError::ast(pid, err))?;
asts.push(ast);
}
for ((pid, p), ast) in
patterns.iter().with_pattern_ids().zip(asts.iter())
{
let hir = self
.hir
.build()
.translate(p.as_ref(), ast)
.map_err(|err| BuildError::hir(pid, err))?;
hirs.push(hir);
}
self.build_many_from_hir(&hirs)
}
/// Builds a `Regex` directly from an `Hir` expression.
///
/// This is useful if you needed to parse a pattern string into an `Hir`
/// for other reasons (such as analysis or transformations). This routine
/// permits building a `Regex` directly from the `Hir` expression instead
/// of first converting the `Hir` back to a pattern string.
///
/// When using this method, any options set via [`Builder::syntax`] are
/// ignored. Namely, the syntax options only apply when parsing a pattern
/// string, which isn't relevant here.
///
/// If there was a problem building the underlying regex matcher for the
/// given `Hir`, then an error is returned.
///
/// # Example
///
/// This example shows how one can hand-construct an `Hir` expression and
/// build a regex from it without doing any parsing at all.
///
/// ```
/// use {
/// regex_automata::{meta::Regex, Match},
/// regex_syntax::hir::{Hir, Look},
/// };
///
/// // (?Rm)^foo$
/// let hir = Hir::concat(vec![
/// Hir::look(Look::StartCRLF),
/// Hir::literal("foo".as_bytes()),
/// Hir::look(Look::EndCRLF),
/// ]);
/// let re = Regex::builder()
/// .build_from_hir(&hir)?;
/// let hay = "\r\nfoo\r\n";
/// assert_eq!(Some(Match::must(0, 2..5)), re.find(hay));
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn build_from_hir(&self, hir: &Hir) -> Result<Regex, BuildError> {
self.build_many_from_hir(&[hir])
}
/// Builds a `Regex` directly from many `Hir` expressions.
///
/// This is useful if you needed to parse pattern strings into `Hir`
/// expressions for other reasons (such as analysis or transformations).
/// This routine permits building a `Regex` directly from the `Hir`
/// expressions instead of first converting the `Hir` expressions back to
/// pattern strings.
///
/// When using this method, any options set via [`Builder::syntax`] are
/// ignored. Namely, the syntax options only apply when parsing a pattern
/// string, which isn't relevant here.
///
/// If there was a problem building the underlying regex matcher for the
/// given `Hir` expressions, then an error is returned.
///
/// Note that unlike [`Builder::build_many`], this can only fail as a
/// result of building the underlying matcher. In that case, there is
/// no single `Hir` expression that can be isolated as a reason for the
/// failure. So if this routine fails, it's not possible to determine which
/// `Hir` expression caused the failure.
///
/// # Example
///
/// This example shows how one can hand-construct multiple `Hir`
/// expressions and build a single regex from them without doing any
/// parsing at all.
///
/// ```
/// use {
/// regex_automata::{meta::Regex, Match},
/// regex_syntax::hir::{Hir, Look},
/// };
///
/// // (?Rm)^foo$
/// let hir1 = Hir::concat(vec![
/// Hir::look(Look::StartCRLF),
/// Hir::literal("foo".as_bytes()),
/// Hir::look(Look::EndCRLF),
/// ]);
/// // (?Rm)^bar$
/// let hir2 = Hir::concat(vec![
/// Hir::look(Look::StartCRLF),
/// Hir::literal("bar".as_bytes()),
/// Hir::look(Look::EndCRLF),
/// ]);
/// let re = Regex::builder()
/// .build_many_from_hir(&[&hir1, &hir2])?;
/// let hay = "\r\nfoo\r\nbar";
/// let got: Vec<Match> = re.find_iter(hay).collect();
/// let expected = vec![
/// Match::must(0, 2..5),
/// Match::must(1, 7..10),
/// ];
/// assert_eq!(expected, got);
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn build_many_from_hir<H: Borrow<Hir>>(
&self,
hirs: &[H],
) -> Result<Regex, BuildError> {
let config = self.config.clone();
// We collect the HIRs into a vec so we can write internal routines
// with '&[&Hir]'. i.e., Don't use generics everywhere to keep code
// bloat down..
let hirs: Vec<&Hir> = hirs.iter().map(|hir| hir.borrow()).collect();
let info = RegexInfo::new(config, &hirs);
let strat = strategy::new(&info, &hirs)?;
let pool = {
let strat = Arc::clone(&strat);
let create: CachePoolFn = Box::new(move || strat.create_cache());
Pool::new(create)
};
Ok(Regex { imp: Arc::new(RegexI { strat, info }), pool })
}
/// Configure the behavior of a `Regex`.
///
/// This configuration controls non-syntax options related to the behavior
/// of a `Regex`. This includes things like whether empty matches can split
/// a codepoint, prefilters, line terminators and a long list of options
/// for configuring which regex engines the meta regex engine will be able
/// to use internally.
///
/// # Example
///
/// This example shows how to disable UTF-8 empty mode. This will permit
/// empty matches to occur between the UTF-8 encoding of a codepoint.
///
/// ```
/// use regex_automata::{meta::Regex, Match};
///
/// let re = Regex::new("")?;
/// let got: Vec<Match> = re.find_iter("☃").collect();
/// // Matches only occur at the beginning and end of the snowman.
/// assert_eq!(got, vec![
/// Match::must(0, 0..0),
/// Match::must(0, 3..3),
/// ]);
///
/// let re = Regex::builder()
/// .configure(Regex::config().utf8_empty(false))
/// .build("")?;
/// let got: Vec<Match> = re.find_iter("☃").collect();
/// // Matches now occur at every position!
/// assert_eq!(got, vec![
/// Match::must(0, 0..0),
/// Match::must(0, 1..1),
/// Match::must(0, 2..2),
/// Match::must(0, 3..3),
/// ]);
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn configure(&mut self, config: Config) -> &mut Builder {
self.config = self.config.overwrite(config);
self
}
/// Configure the syntax options when parsing a pattern string while
/// building a `Regex`.
///
/// These options _only_ apply when [`Builder::build`] or [`Builder::build_many`]
/// are used. The other build methods accept `Hir` values, which have
/// already been parsed.
///
/// # Example
///
/// This example shows how to enable case insensitive mode.
///
/// ```
/// use regex_automata::{meta::Regex, util::syntax, Match};
///
/// let re = Regex::builder()
/// .syntax(syntax::Config::new().case_insensitive(true))
/// .build(r"δ")?;
/// assert_eq!(Some(Match::must(0, 0..2)), re.find(r"Δ"));
///
/// Ok::<(), Box<dyn std::error::Error>>(())
/// ```
pub fn syntax(
&mut self,
config: crate::util::syntax::Config,
) -> &mut Builder {
config.apply_ast(&mut self.ast);
config.apply_hir(&mut self.hir);
self
}
}
#[cfg(test)]
mod tests {
use super::*;
// I found this in the course of building out the benchmark suite for
// rebar.
#[test]
fn regression_suffix_literal_count() {
let _ = env_logger::try_init();
let re = Regex::new(r"[a-zA-Z]+ing").unwrap();
assert_eq!(1, re.find_iter("tingling").count());
}
}