regex_automata/util/look.rs
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
/*!
Types and routines for working with look-around assertions.
This module principally defines two types:
* [`Look`] enumerates all of the assertions supported by this crate.
* [`LookSet`] provides a way to efficiently store a set of [`Look`] values.
* [`LookMatcher`] provides routines for checking whether a `Look` or a
`LookSet` matches at a particular position in a haystack.
*/
// LAMENTATION: Sadly, a lot of the API of `Look` and `LookSet` were basically
// copied verbatim from the regex-syntax crate. I would have no problems using
// the regex-syntax types and defining the matching routines (only found
// in this crate) as free functions, except the `Look` and `LookSet` types
// are used in lots of places. Including in places we expect to work when
// regex-syntax is *not* enabled, such as in the definition of the NFA itself.
//
// Thankfully the code we copy is pretty simple and there isn't much of it.
// Otherwise, the rest of this module deals with *matching* the assertions,
// which is not something that regex-syntax handles.
use crate::util::{escape::DebugByte, utf8};
/// A look-around assertion.
///
/// An assertion matches at a position between characters in a haystack.
/// Namely, it does not actually "consume" any input as most parts of a regular
/// expression do. Assertions are a way of stating that some property must be
/// true at a particular point during matching.
///
/// For example, `(?m)^[a-z]+$` is a pattern that:
///
/// * Scans the haystack for a position at which `(?m:^)` is satisfied. That
/// occurs at either the beginning of the haystack, or immediately following
/// a `\n` character.
/// * Looks for one or more occurrences of `[a-z]`.
/// * Once `[a-z]+` has matched as much as it can, an overall match is only
/// reported when `[a-z]+` stops just before a `\n`.
///
/// So in this case, `abc` and `\nabc\n` match, but `\nabc1\n` does not.
///
/// Assertions are also called "look-around," "look-behind" and "look-ahead."
/// Specifically, some assertions are look-behind (like `^`), other assertions
/// are look-ahead (like `$`) and yet other assertions are both look-ahead and
/// look-behind (like `\b`).
///
/// # Assertions in an NFA
///
/// An assertion in a [`thompson::NFA`](crate::nfa::thompson::NFA) can be
/// thought of as a conditional epsilon transition. That is, a matching engine
/// like the [`PikeVM`](crate::nfa::thompson::pikevm::PikeVM) only permits
/// moving through conditional epsilon transitions when their condition
/// is satisfied at whatever position the `PikeVM` is currently at in the
/// haystack.
///
/// How assertions are handled in a `DFA` is trickier, since a DFA does not
/// have epsilon transitions at all. In this case, they are compiled into the
/// automaton itself, at the expense of more states than what would be required
/// without an assertion.
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
pub enum Look {
/// Match the beginning of text. Specifically, this matches at the starting
/// position of the input.
Start = 1 << 0,
/// Match the end of text. Specifically, this matches at the ending
/// position of the input.
End = 1 << 1,
/// Match the beginning of a line or the beginning of text. Specifically,
/// this matches at the starting position of the input, or at the position
/// immediately following a `\n` character.
StartLF = 1 << 2,
/// Match the end of a line or the end of text. Specifically, this matches
/// at the end position of the input, or at the position immediately
/// preceding a `\n` character.
EndLF = 1 << 3,
/// Match the beginning of a line or the beginning of text. Specifically,
/// this matches at the starting position of the input, or at the position
/// immediately following either a `\r` or `\n` character, but never after
/// a `\r` when a `\n` follows.
StartCRLF = 1 << 4,
/// Match the end of a line or the end of text. Specifically, this matches
/// at the end position of the input, or at the position immediately
/// preceding a `\r` or `\n` character, but never before a `\n` when a `\r`
/// precedes it.
EndCRLF = 1 << 5,
/// Match an ASCII-only word boundary. That is, this matches a position
/// where the left adjacent character and right adjacent character
/// correspond to a word and non-word or a non-word and word character.
WordAscii = 1 << 6,
/// Match an ASCII-only negation of a word boundary.
WordAsciiNegate = 1 << 7,
/// Match a Unicode-aware word boundary. That is, this matches a position
/// where the left adjacent character and right adjacent character
/// correspond to a word and non-word or a non-word and word character.
WordUnicode = 1 << 8,
/// Match a Unicode-aware negation of a word boundary.
WordUnicodeNegate = 1 << 9,
/// Match the start of an ASCII-only word boundary. That is, this matches a
/// position at either the beginning of the haystack or where the previous
/// character is not a word character and the following character is a word
/// character.
WordStartAscii = 1 << 10,
/// Match the end of an ASCII-only word boundary. That is, this matches
/// a position at either the end of the haystack or where the previous
/// character is a word character and the following character is not a word
/// character.
WordEndAscii = 1 << 11,
/// Match the start of a Unicode word boundary. That is, this matches a
/// position at either the beginning of the haystack or where the previous
/// character is not a word character and the following character is a word
/// character.
WordStartUnicode = 1 << 12,
/// Match the end of a Unicode word boundary. That is, this matches a
/// position at either the end of the haystack or where the previous
/// character is a word character and the following character is not a word
/// character.
WordEndUnicode = 1 << 13,
/// Match the start half of an ASCII-only word boundary. That is, this
/// matches a position at either the beginning of the haystack or where the
/// previous character is not a word character.
WordStartHalfAscii = 1 << 14,
/// Match the end half of an ASCII-only word boundary. That is, this
/// matches a position at either the end of the haystack or where the
/// following character is not a word character.
WordEndHalfAscii = 1 << 15,
/// Match the start half of a Unicode word boundary. That is, this matches
/// a position at either the beginning of the haystack or where the
/// previous character is not a word character.
WordStartHalfUnicode = 1 << 16,
/// Match the end half of a Unicode word boundary. That is, this matches
/// a position at either the end of the haystack or where the following
/// character is not a word character.
WordEndHalfUnicode = 1 << 17,
}
impl Look {
/// Flip the look-around assertion to its equivalent for reverse searches.
/// For example, `StartLF` gets translated to `EndLF`.
///
/// Some assertions, such as `WordUnicode`, remain the same since they
/// match the same positions regardless of the direction of the search.
#[inline]
pub const fn reversed(self) -> Look {
match self {
Look::Start => Look::End,
Look::End => Look::Start,
Look::StartLF => Look::EndLF,
Look::EndLF => Look::StartLF,
Look::StartCRLF => Look::EndCRLF,
Look::EndCRLF => Look::StartCRLF,
Look::WordAscii => Look::WordAscii,
Look::WordAsciiNegate => Look::WordAsciiNegate,
Look::WordUnicode => Look::WordUnicode,
Look::WordUnicodeNegate => Look::WordUnicodeNegate,
Look::WordStartAscii => Look::WordEndAscii,
Look::WordEndAscii => Look::WordStartAscii,
Look::WordStartUnicode => Look::WordEndUnicode,
Look::WordEndUnicode => Look::WordStartUnicode,
Look::WordStartHalfAscii => Look::WordEndHalfAscii,
Look::WordEndHalfAscii => Look::WordStartHalfAscii,
Look::WordStartHalfUnicode => Look::WordEndHalfUnicode,
Look::WordEndHalfUnicode => Look::WordStartHalfUnicode,
}
}
/// Return the underlying representation of this look-around enumeration
/// as an integer. Giving the return value to the [`Look::from_repr`]
/// constructor is guaranteed to return the same look-around variant that
/// one started with within a semver compatible release of this crate.
#[inline]
pub const fn as_repr(self) -> u32 {
// AFAIK, 'as' is the only way to zero-cost convert an int enum to an
// actual int.
self as u32
}
/// Given the underlying representation of a `Look` value, return the
/// corresponding `Look` value if the representation is valid. Otherwise
/// `None` is returned.
#[inline]
pub const fn from_repr(repr: u32) -> Option<Look> {
match repr {
0b00_0000_0000_0000_0001 => Some(Look::Start),
0b00_0000_0000_0000_0010 => Some(Look::End),
0b00_0000_0000_0000_0100 => Some(Look::StartLF),
0b00_0000_0000_0000_1000 => Some(Look::EndLF),
0b00_0000_0000_0001_0000 => Some(Look::StartCRLF),
0b00_0000_0000_0010_0000 => Some(Look::EndCRLF),
0b00_0000_0000_0100_0000 => Some(Look::WordAscii),
0b00_0000_0000_1000_0000 => Some(Look::WordAsciiNegate),
0b00_0000_0001_0000_0000 => Some(Look::WordUnicode),
0b00_0000_0010_0000_0000 => Some(Look::WordUnicodeNegate),
0b00_0000_0100_0000_0000 => Some(Look::WordStartAscii),
0b00_0000_1000_0000_0000 => Some(Look::WordEndAscii),
0b00_0001_0000_0000_0000 => Some(Look::WordStartUnicode),
0b00_0010_0000_0000_0000 => Some(Look::WordEndUnicode),
0b00_0100_0000_0000_0000 => Some(Look::WordStartHalfAscii),
0b00_1000_0000_0000_0000 => Some(Look::WordEndHalfAscii),
0b01_0000_0000_0000_0000 => Some(Look::WordStartHalfUnicode),
0b10_0000_0000_0000_0000 => Some(Look::WordEndHalfUnicode),
_ => None,
}
}
/// Returns a convenient single codepoint representation of this
/// look-around assertion. Each assertion is guaranteed to be represented
/// by a distinct character.
///
/// This is useful for succinctly representing a look-around assertion in
/// human friendly but succinct output intended for a programmer working on
/// regex internals.
#[inline]
pub const fn as_char(self) -> char {
match self {
Look::Start => 'A',
Look::End => 'z',
Look::StartLF => '^',
Look::EndLF => '$',
Look::StartCRLF => 'r',
Look::EndCRLF => 'R',
Look::WordAscii => 'b',
Look::WordAsciiNegate => 'B',
Look::WordUnicode => '𝛃',
Look::WordUnicodeNegate => '𝚩',
Look::WordStartAscii => '<',
Look::WordEndAscii => '>',
Look::WordStartUnicode => '〈',
Look::WordEndUnicode => '〉',
Look::WordStartHalfAscii => '◁',
Look::WordEndHalfAscii => '▷',
Look::WordStartHalfUnicode => '◀',
Look::WordEndHalfUnicode => '▶',
}
}
}
/// LookSet is a memory-efficient set of look-around assertions.
///
/// This is useful for efficiently tracking look-around assertions. For
/// example, a [`thompson::NFA`](crate::nfa::thompson::NFA) provides properties
/// that return `LookSet`s.
#[derive(Clone, Copy, Default, Eq, PartialEq)]
pub struct LookSet {
/// The underlying representation this set is exposed to make it possible
/// to store it somewhere efficiently. The representation is that
/// of a bitset, where each assertion occupies bit `i` where
/// `i = Look::as_repr()`.
///
/// Note that users of this internal representation must permit the full
/// range of `u16` values to be represented. For example, even if the
/// current implementation only makes use of the 10 least significant bits,
/// it may use more bits in a future semver compatible release.
pub bits: u32,
}
impl LookSet {
/// Create an empty set of look-around assertions.
#[inline]
pub fn empty() -> LookSet {
LookSet { bits: 0 }
}
/// Create a full set of look-around assertions.
///
/// This set contains all possible look-around assertions.
#[inline]
pub fn full() -> LookSet {
LookSet { bits: !0 }
}
/// Create a look-around set containing the look-around assertion given.
///
/// This is a convenience routine for creating an empty set and inserting
/// one look-around assertions.
#[inline]
pub fn singleton(look: Look) -> LookSet {
LookSet::empty().insert(look)
}
/// Returns the total number of look-around assertions in this set.
#[inline]
pub fn len(self) -> usize {
// OK because max value always fits in a u8, which in turn always
// fits in a usize, regardless of target.
usize::try_from(self.bits.count_ones()).unwrap()
}
/// Returns true if and only if this set is empty.
#[inline]
pub fn is_empty(self) -> bool {
self.len() == 0
}
/// Returns true if and only if the given look-around assertion is in this
/// set.
#[inline]
pub fn contains(self, look: Look) -> bool {
self.bits & look.as_repr() != 0
}
/// Returns true if and only if this set contains any anchor assertions.
/// This includes both "start/end of haystack" and "start/end of line."
#[inline]
pub fn contains_anchor(&self) -> bool {
self.contains_anchor_haystack() || self.contains_anchor_line()
}
/// Returns true if and only if this set contains any "start/end of
/// haystack" anchors. This doesn't include "start/end of line" anchors.
#[inline]
pub fn contains_anchor_haystack(&self) -> bool {
self.contains(Look::Start) || self.contains(Look::End)
}
/// Returns true if and only if this set contains any "start/end of line"
/// anchors. This doesn't include "start/end of haystack" anchors. This
/// includes both `\n` line anchors and CRLF (`\r\n`) aware line anchors.
#[inline]
pub fn contains_anchor_line(&self) -> bool {
self.contains(Look::StartLF)
|| self.contains(Look::EndLF)
|| self.contains(Look::StartCRLF)
|| self.contains(Look::EndCRLF)
}
/// Returns true if and only if this set contains any "start/end of line"
/// anchors that only treat `\n` as line terminators. This does not include
/// haystack anchors or CRLF aware line anchors.
#[inline]
pub fn contains_anchor_lf(&self) -> bool {
self.contains(Look::StartLF) || self.contains(Look::EndLF)
}
/// Returns true if and only if this set contains any "start/end of line"
/// anchors that are CRLF-aware. This doesn't include "start/end of
/// haystack" or "start/end of line-feed" anchors.
#[inline]
pub fn contains_anchor_crlf(&self) -> bool {
self.contains(Look::StartCRLF) || self.contains(Look::EndCRLF)
}
/// Returns true if and only if this set contains any word boundary or
/// negated word boundary assertions. This include both Unicode and ASCII
/// word boundaries.
#[inline]
pub fn contains_word(self) -> bool {
self.contains_word_unicode() || self.contains_word_ascii()
}
/// Returns true if and only if this set contains any Unicode word boundary
/// or negated Unicode word boundary assertions.
#[inline]
pub fn contains_word_unicode(self) -> bool {
self.contains(Look::WordUnicode)
|| self.contains(Look::WordUnicodeNegate)
|| self.contains(Look::WordStartUnicode)
|| self.contains(Look::WordEndUnicode)
|| self.contains(Look::WordStartHalfUnicode)
|| self.contains(Look::WordEndHalfUnicode)
}
/// Returns true if and only if this set contains any ASCII word boundary
/// or negated ASCII word boundary assertions.
#[inline]
pub fn contains_word_ascii(self) -> bool {
self.contains(Look::WordAscii)
|| self.contains(Look::WordAsciiNegate)
|| self.contains(Look::WordStartAscii)
|| self.contains(Look::WordEndAscii)
|| self.contains(Look::WordStartHalfAscii)
|| self.contains(Look::WordEndHalfAscii)
}
/// Returns an iterator over all of the look-around assertions in this set.
#[inline]
pub fn iter(self) -> LookSetIter {
LookSetIter { set: self }
}
/// Return a new set that is equivalent to the original, but with the given
/// assertion added to it. If the assertion is already in the set, then the
/// returned set is equivalent to the original.
#[inline]
pub fn insert(self, look: Look) -> LookSet {
LookSet { bits: self.bits | look.as_repr() }
}
/// Updates this set in place with the result of inserting the given
/// assertion into this set.
#[inline]
pub fn set_insert(&mut self, look: Look) {
*self = self.insert(look);
}
/// Return a new set that is equivalent to the original, but with the given
/// assertion removed from it. If the assertion is not in the set, then the
/// returned set is equivalent to the original.
#[inline]
pub fn remove(self, look: Look) -> LookSet {
LookSet { bits: self.bits & !look.as_repr() }
}
/// Updates this set in place with the result of removing the given
/// assertion from this set.
#[inline]
pub fn set_remove(&mut self, look: Look) {
*self = self.remove(look);
}
/// Returns a new set that is the result of subtracting the given set from
/// this set.
#[inline]
pub fn subtract(self, other: LookSet) -> LookSet {
LookSet { bits: self.bits & !other.bits }
}
/// Updates this set in place with the result of subtracting the given set
/// from this set.
#[inline]
pub fn set_subtract(&mut self, other: LookSet) {
*self = self.subtract(other);
}
/// Returns a new set that is the union of this and the one given.
#[inline]
pub fn union(self, other: LookSet) -> LookSet {
LookSet { bits: self.bits | other.bits }
}
/// Updates this set in place with the result of unioning it with the one
/// given.
#[inline]
pub fn set_union(&mut self, other: LookSet) {
*self = self.union(other);
}
/// Returns a new set that is the intersection of this and the one given.
#[inline]
pub fn intersect(self, other: LookSet) -> LookSet {
LookSet { bits: self.bits & other.bits }
}
/// Updates this set in place with the result of intersecting it with the
/// one given.
#[inline]
pub fn set_intersect(&mut self, other: LookSet) {
*self = self.intersect(other);
}
/// Return a `LookSet` from the slice given as a native endian 32-bit
/// integer.
///
/// # Panics
///
/// This panics if `slice.len() < 4`.
#[inline]
pub fn read_repr(slice: &[u8]) -> LookSet {
let bits = u32::from_ne_bytes(slice[..4].try_into().unwrap());
LookSet { bits }
}
/// Write a `LookSet` as a native endian 32-bit integer to the beginning
/// of the slice given.
///
/// # Panics
///
/// This panics if `slice.len() < 4`.
#[inline]
pub fn write_repr(self, slice: &mut [u8]) {
let raw = self.bits.to_ne_bytes();
slice[0] = raw[0];
slice[1] = raw[1];
slice[2] = raw[2];
slice[3] = raw[3];
}
/// Checks that all assertions in this set can be matched.
///
/// Some assertions, such as Unicode word boundaries, require optional (but
/// enabled by default) tables that may not be available. If there are
/// assertions in this set that require tables that are not available, then
/// this will return an error.
///
/// Specifically, this returns an error when the the
/// `unicode-word-boundary` feature is _not_ enabled _and_ this set
/// contains a Unicode word boundary assertion.
///
/// It can be useful to use this on the result of
/// [`NFA::look_set_any`](crate::nfa::thompson::NFA::look_set_any)
/// when building a matcher engine to ensure methods like
/// [`LookMatcher::matches_set`] do not panic at search time.
pub fn available(self) -> Result<(), UnicodeWordBoundaryError> {
if self.contains_word_unicode() {
UnicodeWordBoundaryError::check()?;
}
Ok(())
}
}
impl core::fmt::Debug for LookSet {
fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result {
if self.is_empty() {
return write!(f, "∅");
}
for look in self.iter() {
write!(f, "{}", look.as_char())?;
}
Ok(())
}
}
/// An iterator over all look-around assertions in a [`LookSet`].
///
/// This iterator is created by [`LookSet::iter`].
#[derive(Clone, Debug)]
pub struct LookSetIter {
set: LookSet,
}
impl Iterator for LookSetIter {
type Item = Look;
#[inline]
fn next(&mut self) -> Option<Look> {
if self.set.is_empty() {
return None;
}
// We'll never have more than u8::MAX distinct look-around assertions,
// so 'bit' will always fit into a u16.
let bit = u16::try_from(self.set.bits.trailing_zeros()).unwrap();
let look = Look::from_repr(1 << bit)?;
self.set = self.set.remove(look);
Some(look)
}
}
/// A matcher for look-around assertions.
///
/// This matcher permits configuring aspects of how look-around assertions are
/// matched.
///
/// # Example
///
/// A `LookMatcher` can change the line terminator used for matching multi-line
/// anchors such as `(?m:^)` and `(?m:$)`.
///
/// ```
/// use regex_automata::{
/// nfa::thompson::{self, pikevm::PikeVM},
/// util::look::LookMatcher,
/// Match, Input,
/// };
///
/// let mut lookm = LookMatcher::new();
/// lookm.set_line_terminator(b'\x00');
///
/// let re = PikeVM::builder()
/// .thompson(thompson::Config::new().look_matcher(lookm))
/// .build(r"(?m)^[a-z]+$")?;
/// let mut cache = re.create_cache();
///
/// // Multi-line assertions now use NUL as a terminator.
/// assert_eq!(
/// Some(Match::must(0, 1..4)),
/// re.find(&mut cache, b"\x00abc\x00"),
/// );
/// // ... and \n is no longer recognized as a terminator.
/// assert_eq!(
/// None,
/// re.find(&mut cache, b"\nabc\n"),
/// );
///
/// # Ok::<(), Box<dyn std::error::Error>>(())
/// ```
#[derive(Clone, Debug)]
pub struct LookMatcher {
lineterm: DebugByte,
}
impl LookMatcher {
/// Creates a new default matcher for look-around assertions.
pub fn new() -> LookMatcher {
LookMatcher { lineterm: DebugByte(b'\n') }
}
/// Sets the line terminator for use with `(?m:^)` and `(?m:$)`.
///
/// Namely, instead of `^` matching after `\n` and `$` matching immediately
/// before a `\n`, this will cause it to match after and before the byte
/// given.
///
/// It can occasionally be useful to use this to configure the line
/// terminator to the NUL byte when searching binary data.
///
/// Note that this does not apply to CRLF-aware line anchors such as
/// `(?Rm:^)` and `(?Rm:$)`. CRLF-aware line anchors are hard-coded to
/// use `\r` and `\n`.
pub fn set_line_terminator(&mut self, byte: u8) -> &mut LookMatcher {
self.lineterm.0 = byte;
self
}
/// Returns the line terminator that was configured for this matcher.
///
/// If no line terminator was configured, then this returns `\n`.
///
/// Note that the line terminator should only be used for matching `(?m:^)`
/// and `(?m:$)` assertions. It specifically should _not_ be used for
/// matching the CRLF aware assertions `(?Rm:^)` and `(?Rm:$)`.
pub fn get_line_terminator(&self) -> u8 {
self.lineterm.0
}
/// Returns true when the position `at` in `haystack` satisfies the given
/// look-around assertion.
///
/// # Panics
///
/// This panics when testing any Unicode word boundary assertion in this
/// set and when the Unicode word data is not available. Specifically, this
/// only occurs when the `unicode-word-boundary` feature is not enabled.
///
/// Since it's generally expected that this routine is called inside of
/// a matching engine, callers should check the error condition when
/// building the matching engine. If there is a Unicode word boundary
/// in the matcher and the data isn't available, then the matcher should
/// fail to build.
///
/// Callers can check the error condition with [`LookSet::available`].
///
/// This also may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn matches(&self, look: Look, haystack: &[u8], at: usize) -> bool {
self.matches_inline(look, haystack, at)
}
/// Like `matches`, but forcefully inlined.
///
/// # Panics
///
/// This panics when testing any Unicode word boundary assertion in this
/// set and when the Unicode word data is not available. Specifically, this
/// only occurs when the `unicode-word-boundary` feature is not enabled.
///
/// Since it's generally expected that this routine is called inside of
/// a matching engine, callers should check the error condition when
/// building the matching engine. If there is a Unicode word boundary
/// in the matcher and the data isn't available, then the matcher should
/// fail to build.
///
/// Callers can check the error condition with [`LookSet::available`].
///
/// This also may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(crate) fn matches_inline(
&self,
look: Look,
haystack: &[u8],
at: usize,
) -> bool {
match look {
Look::Start => self.is_start(haystack, at),
Look::End => self.is_end(haystack, at),
Look::StartLF => self.is_start_lf(haystack, at),
Look::EndLF => self.is_end_lf(haystack, at),
Look::StartCRLF => self.is_start_crlf(haystack, at),
Look::EndCRLF => self.is_end_crlf(haystack, at),
Look::WordAscii => self.is_word_ascii(haystack, at),
Look::WordAsciiNegate => self.is_word_ascii_negate(haystack, at),
Look::WordUnicode => self.is_word_unicode(haystack, at).unwrap(),
Look::WordUnicodeNegate => {
self.is_word_unicode_negate(haystack, at).unwrap()
}
Look::WordStartAscii => self.is_word_start_ascii(haystack, at),
Look::WordEndAscii => self.is_word_end_ascii(haystack, at),
Look::WordStartUnicode => {
self.is_word_start_unicode(haystack, at).unwrap()
}
Look::WordEndUnicode => {
self.is_word_end_unicode(haystack, at).unwrap()
}
Look::WordStartHalfAscii => {
self.is_word_start_half_ascii(haystack, at)
}
Look::WordEndHalfAscii => {
self.is_word_end_half_ascii(haystack, at)
}
Look::WordStartHalfUnicode => {
self.is_word_start_half_unicode(haystack, at).unwrap()
}
Look::WordEndHalfUnicode => {
self.is_word_end_half_unicode(haystack, at).unwrap()
}
}
}
/// Returns true when _all_ of the assertions in the given set match at the
/// given position in the haystack.
///
/// # Panics
///
/// This panics when testing any Unicode word boundary assertion in this
/// set and when the Unicode word data is not available. Specifically, this
/// only occurs when the `unicode-word-boundary` feature is not enabled.
///
/// Since it's generally expected that this routine is called inside of
/// a matching engine, callers should check the error condition when
/// building the matching engine. If there is a Unicode word boundary
/// in the matcher and the data isn't available, then the matcher should
/// fail to build.
///
/// Callers can check the error condition with [`LookSet::available`].
///
/// This also may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn matches_set(
&self,
set: LookSet,
haystack: &[u8],
at: usize,
) -> bool {
self.matches_set_inline(set, haystack, at)
}
/// Like `LookSet::matches`, but forcefully inlined for perf.
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(crate) fn matches_set_inline(
&self,
set: LookSet,
haystack: &[u8],
at: usize,
) -> bool {
// This used to luse LookSet::iter with Look::matches on each element,
// but that proved to be quite diastrous for perf. The manual "if
// the set has this assertion, check it" turns out to be quite a bit
// faster.
if set.contains(Look::Start) {
if !self.is_start(haystack, at) {
return false;
}
}
if set.contains(Look::End) {
if !self.is_end(haystack, at) {
return false;
}
}
if set.contains(Look::StartLF) {
if !self.is_start_lf(haystack, at) {
return false;
}
}
if set.contains(Look::EndLF) {
if !self.is_end_lf(haystack, at) {
return false;
}
}
if set.contains(Look::StartCRLF) {
if !self.is_start_crlf(haystack, at) {
return false;
}
}
if set.contains(Look::EndCRLF) {
if !self.is_end_crlf(haystack, at) {
return false;
}
}
if set.contains(Look::WordAscii) {
if !self.is_word_ascii(haystack, at) {
return false;
}
}
if set.contains(Look::WordAsciiNegate) {
if !self.is_word_ascii_negate(haystack, at) {
return false;
}
}
if set.contains(Look::WordUnicode) {
if !self.is_word_unicode(haystack, at).unwrap() {
return false;
}
}
if set.contains(Look::WordUnicodeNegate) {
if !self.is_word_unicode_negate(haystack, at).unwrap() {
return false;
}
}
if set.contains(Look::WordStartAscii) {
if !self.is_word_start_ascii(haystack, at) {
return false;
}
}
if set.contains(Look::WordEndAscii) {
if !self.is_word_end_ascii(haystack, at) {
return false;
}
}
if set.contains(Look::WordStartUnicode) {
if !self.is_word_start_unicode(haystack, at).unwrap() {
return false;
}
}
if set.contains(Look::WordEndUnicode) {
if !self.is_word_end_unicode(haystack, at).unwrap() {
return false;
}
}
if set.contains(Look::WordStartHalfAscii) {
if !self.is_word_start_half_ascii(haystack, at) {
return false;
}
}
if set.contains(Look::WordEndHalfAscii) {
if !self.is_word_end_half_ascii(haystack, at) {
return false;
}
}
if set.contains(Look::WordStartHalfUnicode) {
if !self.is_word_start_half_unicode(haystack, at).unwrap() {
return false;
}
}
if set.contains(Look::WordEndHalfUnicode) {
if !self.is_word_end_half_unicode(haystack, at).unwrap() {
return false;
}
}
true
}
/// Split up the given byte classes into equivalence classes in a way that
/// is consistent with this look-around assertion.
#[cfg(feature = "alloc")]
pub(crate) fn add_to_byteset(
&self,
look: Look,
set: &mut crate::util::alphabet::ByteClassSet,
) {
match look {
Look::Start | Look::End => {}
Look::StartLF | Look::EndLF => {
set.set_range(self.lineterm.0, self.lineterm.0);
}
Look::StartCRLF | Look::EndCRLF => {
set.set_range(b'\r', b'\r');
set.set_range(b'\n', b'\n');
}
Look::WordAscii
| Look::WordAsciiNegate
| Look::WordUnicode
| Look::WordUnicodeNegate
| Look::WordStartAscii
| Look::WordEndAscii
| Look::WordStartUnicode
| Look::WordEndUnicode
| Look::WordStartHalfAscii
| Look::WordEndHalfAscii
| Look::WordStartHalfUnicode
| Look::WordEndHalfUnicode => {
// We need to mark all ranges of bytes whose pairs result in
// evaluating \b differently. This isn't technically correct
// for Unicode word boundaries, but DFAs can't handle those
// anyway, and thus, the byte classes don't need to either
// since they are themselves only used in DFAs.
//
// FIXME: It seems like the calls to 'set_range' here are
// completely invariant, which means we could just hard-code
// them here without needing to write a loop. And we only need
// to do this dance at most once per regex.
//
// FIXME: Is this correct for \B?
let iswb = utf8::is_word_byte;
// This unwrap is OK because we guard every use of 'asu8' with
// a check that the input is <= 255.
let asu8 = |b: u16| u8::try_from(b).unwrap();
let mut b1: u16 = 0;
let mut b2: u16;
while b1 <= 255 {
b2 = b1 + 1;
while b2 <= 255 && iswb(asu8(b1)) == iswb(asu8(b2)) {
b2 += 1;
}
// The guards above guarantee that b2 can never get any
// bigger.
assert!(b2 <= 256);
// Subtracting 1 from b2 is always OK because it is always
// at least 1 greater than b1, and the assert above
// guarantees that the asu8 conversion will succeed.
set.set_range(asu8(b1), asu8(b2.checked_sub(1).unwrap()));
b1 = b2;
}
}
}
}
/// Returns true when [`Look::Start`] is satisfied `at` the given position
/// in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_start(&self, _haystack: &[u8], at: usize) -> bool {
at == 0
}
/// Returns true when [`Look::End`] is satisfied `at` the given position in
/// `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_end(&self, haystack: &[u8], at: usize) -> bool {
at == haystack.len()
}
/// Returns true when [`Look::StartLF`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_start_lf(&self, haystack: &[u8], at: usize) -> bool {
self.is_start(haystack, at) || haystack[at - 1] == self.lineterm.0
}
/// Returns true when [`Look::EndLF`] is satisfied `at` the given position
/// in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_end_lf(&self, haystack: &[u8], at: usize) -> bool {
self.is_end(haystack, at) || haystack[at] == self.lineterm.0
}
/// Returns true when [`Look::StartCRLF`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_start_crlf(&self, haystack: &[u8], at: usize) -> bool {
self.is_start(haystack, at)
|| haystack[at - 1] == b'\n'
|| (haystack[at - 1] == b'\r'
&& (at >= haystack.len() || haystack[at] != b'\n'))
}
/// Returns true when [`Look::EndCRLF`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_end_crlf(&self, haystack: &[u8], at: usize) -> bool {
self.is_end(haystack, at)
|| haystack[at] == b'\r'
|| (haystack[at] == b'\n'
&& (at == 0 || haystack[at - 1] != b'\r'))
}
/// Returns true when [`Look::WordAscii`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_word_ascii(&self, haystack: &[u8], at: usize) -> bool {
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]);
let word_after =
at < haystack.len() && utf8::is_word_byte(haystack[at]);
word_before != word_after
}
/// Returns true when [`Look::WordAsciiNegate`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_word_ascii_negate(&self, haystack: &[u8], at: usize) -> bool {
!self.is_word_ascii(haystack, at)
}
/// Returns true when [`Look::WordUnicode`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
///
/// # Errors
///
/// This returns an error when Unicode word boundary tables
/// are not available. Specifically, this only occurs when the
/// `unicode-word-boundary` feature is not enabled.
#[inline]
pub fn is_word_unicode(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, UnicodeWordBoundaryError> {
let word_before = is_word_char::rev(haystack, at)?;
let word_after = is_word_char::fwd(haystack, at)?;
Ok(word_before != word_after)
}
/// Returns true when [`Look::WordUnicodeNegate`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
///
/// # Errors
///
/// This returns an error when Unicode word boundary tables
/// are not available. Specifically, this only occurs when the
/// `unicode-word-boundary` feature is not enabled.
#[inline]
pub fn is_word_unicode_negate(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, UnicodeWordBoundaryError> {
// This is pretty subtle. Why do we need to do UTF-8 decoding here?
// Well... at time of writing, the is_word_char_{fwd,rev} routines will
// only return true if there is a valid UTF-8 encoding of a "word"
// codepoint, and false in every other case (including invalid UTF-8).
// This means that in regions of invalid UTF-8 (which might be a
// subset of valid UTF-8!), it would result in \B matching. While this
// would be questionable in the context of truly invalid UTF-8, it is
// *certainly* wrong to report match boundaries that split the encoding
// of a codepoint. So to work around this, we ensure that we can decode
// a codepoint on either side of `at`. If either direction fails, then
// we don't permit \B to match at all.
//
// Now, this isn't exactly optimal from a perf perspective. We could
// try and detect this in is_word_char::{fwd,rev}, but it's not clear
// if it's worth it. \B is, after all, rarely used. Even worse,
// is_word_char::{fwd,rev} could do its own UTF-8 decoding, and so this
// will wind up doing UTF-8 decoding twice. Owch. We could fix this
// with more code complexity, but it just doesn't feel worth it for \B.
//
// And in particular, we do *not* have to do this with \b, because \b
// *requires* that at least one side of `at` be a "word" codepoint,
// which in turn implies one side of `at` must be valid UTF-8. This in
// turn implies that \b can never split a valid UTF-8 encoding of a
// codepoint. In the case where one side of `at` is truly invalid UTF-8
// and the other side IS a word codepoint, then we want \b to match
// since it represents a valid UTF-8 boundary. It also makes sense. For
// example, you'd want \b\w+\b to match 'abc' in '\xFFabc\xFF'.
//
// Note also that this is not just '!is_word_unicode(..)' like it is
// for the ASCII case. For example, neither \b nor \B is satisfied
// within invalid UTF-8 sequences.
let word_before = at > 0
&& match utf8::decode_last(&haystack[..at]) {
None | Some(Err(_)) => return Ok(false),
Some(Ok(_)) => is_word_char::rev(haystack, at)?,
};
let word_after = at < haystack.len()
&& match utf8::decode(&haystack[at..]) {
None | Some(Err(_)) => return Ok(false),
Some(Ok(_)) => is_word_char::fwd(haystack, at)?,
};
Ok(word_before == word_after)
}
/// Returns true when [`Look::WordStartAscii`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_word_start_ascii(&self, haystack: &[u8], at: usize) -> bool {
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]);
let word_after =
at < haystack.len() && utf8::is_word_byte(haystack[at]);
!word_before && word_after
}
/// Returns true when [`Look::WordEndAscii`] is satisfied `at` the given
/// position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_word_end_ascii(&self, haystack: &[u8], at: usize) -> bool {
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]);
let word_after =
at < haystack.len() && utf8::is_word_byte(haystack[at]);
word_before && !word_after
}
/// Returns true when [`Look::WordStartUnicode`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
///
/// # Errors
///
/// This returns an error when Unicode word boundary tables
/// are not available. Specifically, this only occurs when the
/// `unicode-word-boundary` feature is not enabled.
#[inline]
pub fn is_word_start_unicode(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, UnicodeWordBoundaryError> {
let word_before = is_word_char::rev(haystack, at)?;
let word_after = is_word_char::fwd(haystack, at)?;
Ok(!word_before && word_after)
}
/// Returns true when [`Look::WordEndUnicode`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
///
/// # Errors
///
/// This returns an error when Unicode word boundary tables
/// are not available. Specifically, this only occurs when the
/// `unicode-word-boundary` feature is not enabled.
#[inline]
pub fn is_word_end_unicode(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, UnicodeWordBoundaryError> {
let word_before = is_word_char::rev(haystack, at)?;
let word_after = is_word_char::fwd(haystack, at)?;
Ok(word_before && !word_after)
}
/// Returns true when [`Look::WordStartHalfAscii`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_word_start_half_ascii(
&self,
haystack: &[u8],
at: usize,
) -> bool {
let word_before = at > 0 && utf8::is_word_byte(haystack[at - 1]);
!word_before
}
/// Returns true when [`Look::WordEndHalfAscii`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
#[inline]
pub fn is_word_end_half_ascii(&self, haystack: &[u8], at: usize) -> bool {
let word_after =
at < haystack.len() && utf8::is_word_byte(haystack[at]);
!word_after
}
/// Returns true when [`Look::WordStartHalfUnicode`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
///
/// # Errors
///
/// This returns an error when Unicode word boundary tables
/// are not available. Specifically, this only occurs when the
/// `unicode-word-boundary` feature is not enabled.
#[inline]
pub fn is_word_start_half_unicode(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, UnicodeWordBoundaryError> {
// See `is_word_unicode_negate` for why we need to do this. We don't
// need to do it for `is_word_start_unicode` because that guarantees
// that the position matched falls on a valid UTF-8 boundary given
// that the right side must be in \w.
let word_before = at > 0
&& match utf8::decode_last(&haystack[..at]) {
None | Some(Err(_)) => return Ok(false),
Some(Ok(_)) => is_word_char::rev(haystack, at)?,
};
Ok(!word_before)
}
/// Returns true when [`Look::WordEndHalfUnicode`] is satisfied `at` the
/// given position in `haystack`.
///
/// # Panics
///
/// This may panic when `at > haystack.len()`. Note that `at ==
/// haystack.len()` is legal and guaranteed not to panic.
///
/// # Errors
///
/// This returns an error when Unicode word boundary tables
/// are not available. Specifically, this only occurs when the
/// `unicode-word-boundary` feature is not enabled.
#[inline]
pub fn is_word_end_half_unicode(
&self,
haystack: &[u8],
at: usize,
) -> Result<bool, UnicodeWordBoundaryError> {
// See `is_word_unicode_negate` for why we need to do this. We don't
// need to do it for `is_word_end_unicode` because that guarantees
// that the position matched falls on a valid UTF-8 boundary given
// that the left side must be in \w.
let word_after = at < haystack.len()
&& match utf8::decode(&haystack[at..]) {
None | Some(Err(_)) => return Ok(false),
Some(Ok(_)) => is_word_char::fwd(haystack, at)?,
};
Ok(!word_after)
}
}
impl Default for LookMatcher {
fn default() -> LookMatcher {
LookMatcher::new()
}
}
/// An error that occurs when the Unicode-aware `\w` class is unavailable.
///
/// This error can occur when the data tables necessary for the Unicode aware
/// Perl character class `\w` are unavailable. The `\w` class is used to
/// determine whether a codepoint is considered a word character or not when
/// determining whether a Unicode aware `\b` (or `\B`) matches at a particular
/// position.
///
/// This error can only occur when the `unicode-word-boundary` feature is
/// disabled.
#[derive(Clone, Debug)]
pub struct UnicodeWordBoundaryError(());
impl UnicodeWordBoundaryError {
#[cfg(not(feature = "unicode-word-boundary"))]
pub(crate) fn new() -> UnicodeWordBoundaryError {
UnicodeWordBoundaryError(())
}
/// Returns an error if and only if Unicode word boundary data is
/// unavailable.
pub fn check() -> Result<(), UnicodeWordBoundaryError> {
is_word_char::check()
}
}
#[cfg(feature = "std")]
impl std::error::Error for UnicodeWordBoundaryError {}
impl core::fmt::Display for UnicodeWordBoundaryError {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
write!(
f,
"Unicode-aware \\b and \\B are unavailable because the \
requisite data tables are missing, please enable the \
unicode-word-boundary feature"
)
}
}
// Below are FOUR different ways for checking whether whether a "word"
// codepoint exists at a particular position in the haystack. The four
// different approaches are, in order of preference:
//
// 1. Parse '\w', convert to an NFA, convert to a fully compiled DFA on the
// first call, and then use that DFA for all subsequent calls.
// 2. Do UTF-8 decoding and use regex_syntax::is_word_character if available.
// 3. Do UTF-8 decoding and use our own 'perl_word' table.
// 4. Return an error.
//
// The reason for all of these approaches is a combination of perf and
// permitting one to build regex-automata without the Unicode data necessary
// for handling Unicode-aware word boundaries. (In which case, '(?-u:\b)' would
// still work.)
//
// The DFA approach is the fastest, but it requires the regex parser, the
// NFA compiler, the DFA builder and the DFA search runtime. That's a lot to
// bring in, but if it's available, it's (probably) the best we can do.
//
// Approaches (2) and (3) are effectively equivalent, but (2) reuses the
// data in regex-syntax and avoids duplicating it in regex-automata.
//
// Finally, (4) unconditionally returns an error since the requisite data isn't
// available anywhere.
//
// There are actually more approaches possible that we didn't implement. For
// example, if the DFA builder is available but the syntax parser is not, we
// could technically hand construct our own NFA from the 'perl_word' data
// table. But to avoid some pretty hairy code duplication, we would in turn
// need to pull the UTF-8 compiler out of the NFA compiler. Yikes.
//
// A possibly more sensible alternative is to use a lazy DFA when the full
// DFA builder isn't available...
//
// Yet another choice would be to build the full DFA and then embed it into the
// source. Then we'd only need to bring in the DFA search runtime, which is
// considerably smaller than the DFA builder code. The problem here is that the
// Debian people have spooked me[1] into avoiding cyclic dependencies. Namely,
// we'd need to build regex-cli, which depends on regex-automata in order to
// build some part of regex-automata. But to be honest, something like this has
// to be allowed somehow? I just don't know what the right process is.
//
// There are perhaps other choices as well. Why did I stop at these 4? Because
// I wanted to preserve my sanity. I suspect I'll wind up adding the lazy DFA
// approach eventually, as the benefits of the DFA approach are somewhat
// compelling. The 'boundary-words-holmes' benchmark tests this. (Note that
// the commands below no longer work. If necessary, we should re-capitulate
// the benchmark from whole cloth in rebar.)
//
// $ regex-cli bench measure -f boundary-words-holmes -e pikevm > dfa.csv
//
// Then I changed the code below so that the util/unicode_data/perl_word table
// was used and re-ran the benchmark:
//
// $ regex-cli bench measure -f boundary-words-holmes -e pikevm > table.csv
//
// And compared them:
//
// $ regex-cli bench diff dfa.csv table.csv
// benchmark engine dfa table
// --------- ------ --- -----
// internal/count/boundary-words-holmes regex/automata/pikevm 18.6 MB/s 12.9 MB/s
//
// Which is a nice improvement.
//
// UPDATE: It turns out that it takes approximately 22ms to build the reverse
// DFA for \w. (And about 3ms for the forward DFA.) It's probably not much in
// the grand scheme things, but that is a significant latency cost. So I'm not
// sure that's a good idea. I then tried using a lazy DFA instead, and that
// eliminated the overhead, but since the lazy DFA requires mutable working
// memory, that requires introducing a 'Cache' for every simultaneous call.
//
// I ended up deciding for now to just keep the "UTF-8 decode and check the
// table." The DFA and lazy DFA approaches are still below, but commented out.
//
// [1]: https://github.com/BurntSushi/ucd-generate/issues/11
/*
/// A module that looks for word codepoints using lazy DFAs.
#[cfg(all(
feature = "unicode-word-boundary",
feature = "syntax",
feature = "unicode-perl",
feature = "hybrid"
))]
mod is_word_char {
use alloc::vec::Vec;
use crate::{
hybrid::dfa::{Cache, DFA},
nfa::thompson::NFA,
util::{lazy::Lazy, pool::Pool, primitives::StateID},
Anchored, Input,
};
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> {
Ok(())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn fwd(
haystack: &[u8],
mut at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
static WORD: Lazy<DFA> = Lazy::new(|| DFA::new(r"\w").unwrap());
static CACHE: Lazy<Pool<Cache>> =
Lazy::new(|| Pool::new(|| WORD.create_cache()));
let dfa = Lazy::get(&WORD);
let mut cache = Lazy::get(&CACHE).get();
let mut sid = dfa
.start_state_forward(
&mut cache,
&Input::new("").anchored(Anchored::Yes),
)
.unwrap();
while at < haystack.len() {
let byte = haystack[at];
sid = dfa.next_state(&mut cache, sid, byte).unwrap();
at += 1;
if sid.is_tagged() {
if sid.is_match() {
return Ok(true);
} else if sid.is_dead() {
return Ok(false);
}
}
}
Ok(dfa.next_eoi_state(&mut cache, sid).unwrap().is_match())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn rev(
haystack: &[u8],
mut at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
static WORD: Lazy<DFA> = Lazy::new(|| {
DFA::builder()
.thompson(NFA::config().reverse(true))
.build(r"\w")
.unwrap()
});
static CACHE: Lazy<Pool<Cache>> =
Lazy::new(|| Pool::new(|| WORD.create_cache()));
let dfa = Lazy::get(&WORD);
let mut cache = Lazy::get(&CACHE).get();
let mut sid = dfa
.start_state_reverse(
&mut cache,
&Input::new("").anchored(Anchored::Yes),
)
.unwrap();
while at > 0 {
at -= 1;
let byte = haystack[at];
sid = dfa.next_state(&mut cache, sid, byte).unwrap();
if sid.is_tagged() {
if sid.is_match() {
return Ok(true);
} else if sid.is_dead() {
return Ok(false);
}
}
}
Ok(dfa.next_eoi_state(&mut cache, sid).unwrap().is_match())
}
}
*/
/*
/// A module that looks for word codepoints using fully compiled DFAs.
#[cfg(all(
feature = "unicode-word-boundary",
feature = "syntax",
feature = "unicode-perl",
feature = "dfa-build"
))]
mod is_word_char {
use alloc::vec::Vec;
use crate::{
dfa::{dense::DFA, Automaton, StartKind},
nfa::thompson::NFA,
util::{lazy::Lazy, primitives::StateID},
Anchored, Input,
};
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> {
Ok(())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn fwd(
haystack: &[u8],
mut at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
static WORD: Lazy<(DFA<Vec<u32>>, StateID)> = Lazy::new(|| {
let dfa = DFA::builder()
.configure(DFA::config().start_kind(StartKind::Anchored))
.build(r"\w")
.unwrap();
// OK because our regex has no look-around.
let start_id = dfa.universal_start_state(Anchored::Yes).unwrap();
(dfa, start_id)
});
let &(ref dfa, mut sid) = Lazy::get(&WORD);
while at < haystack.len() {
let byte = haystack[at];
sid = dfa.next_state(sid, byte);
at += 1;
if dfa.is_special_state(sid) {
if dfa.is_match_state(sid) {
return Ok(true);
} else if dfa.is_dead_state(sid) {
return Ok(false);
}
}
}
Ok(dfa.is_match_state(dfa.next_eoi_state(sid)))
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn rev(
haystack: &[u8],
mut at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
static WORD: Lazy<(DFA<Vec<u32>>, StateID)> = Lazy::new(|| {
let dfa = DFA::builder()
.configure(DFA::config().start_kind(StartKind::Anchored))
// From ad hoc measurements, it looks like setting
// shrink==false is slightly faster than shrink==true. I kind
// of feel like this indicates that shrinking is probably a
// failure, although it can help in some cases. Sigh.
.thompson(NFA::config().reverse(true).shrink(false))
.build(r"\w")
.unwrap();
// OK because our regex has no look-around.
let start_id = dfa.universal_start_state(Anchored::Yes).unwrap();
(dfa, start_id)
});
let &(ref dfa, mut sid) = Lazy::get(&WORD);
while at > 0 {
at -= 1;
let byte = haystack[at];
sid = dfa.next_state(sid, byte);
if dfa.is_special_state(sid) {
if dfa.is_match_state(sid) {
return Ok(true);
} else if dfa.is_dead_state(sid) {
return Ok(false);
}
}
}
Ok(dfa.is_match_state(dfa.next_eoi_state(sid)))
}
}
*/
/// A module that looks for word codepoints using regex-syntax's data tables.
#[cfg(all(
feature = "unicode-word-boundary",
feature = "syntax",
feature = "unicode-perl",
))]
mod is_word_char {
use regex_syntax::try_is_word_character;
use crate::util::utf8;
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> {
Ok(())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn fwd(
haystack: &[u8],
at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
Ok(match utf8::decode(&haystack[at..]) {
None | Some(Err(_)) => false,
Some(Ok(ch)) => try_is_word_character(ch).expect(
"since unicode-word-boundary, syntax and unicode-perl \
are all enabled, it is expected that \
try_is_word_character succeeds",
),
})
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn rev(
haystack: &[u8],
at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
Ok(match utf8::decode_last(&haystack[..at]) {
None | Some(Err(_)) => false,
Some(Ok(ch)) => try_is_word_character(ch).expect(
"since unicode-word-boundary, syntax and unicode-perl \
are all enabled, it is expected that \
try_is_word_character succeeds",
),
})
}
}
/// A module that looks for word codepoints using regex-automata's data tables
/// (which are only compiled when regex-syntax's tables aren't available).
///
/// Note that the cfg should match the one in src/util/unicode_data/mod.rs for
/// perl_word.
#[cfg(all(
feature = "unicode-word-boundary",
not(all(feature = "syntax", feature = "unicode-perl")),
))]
mod is_word_char {
use crate::util::utf8;
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> {
Ok(())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn fwd(
haystack: &[u8],
at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
Ok(match utf8::decode(&haystack[at..]) {
None | Some(Err(_)) => false,
Some(Ok(ch)) => is_word_character(ch),
})
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn rev(
haystack: &[u8],
at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
Ok(match utf8::decode_last(&haystack[..at]) {
None | Some(Err(_)) => false,
Some(Ok(ch)) => is_word_character(ch),
})
}
#[cfg_attr(feature = "perf-inline", inline(always))]
fn is_word_character(c: char) -> bool {
use crate::util::{unicode_data::perl_word::PERL_WORD, utf8};
if u8::try_from(c).map_or(false, utf8::is_word_byte) {
return true;
}
PERL_WORD
.binary_search_by(|&(start, end)| {
use core::cmp::Ordering;
if start <= c && c <= end {
Ordering::Equal
} else if start > c {
Ordering::Greater
} else {
Ordering::Less
}
})
.is_ok()
}
}
/// A module that always returns an error if Unicode word boundaries are
/// disabled. When this feature is disabled, then regex-automata will not
/// include its own data tables even if regex-syntax is disabled.
#[cfg(not(feature = "unicode-word-boundary"))]
mod is_word_char {
pub(super) fn check() -> Result<(), super::UnicodeWordBoundaryError> {
Err(super::UnicodeWordBoundaryError::new())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn fwd(
_bytes: &[u8],
_at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
Err(super::UnicodeWordBoundaryError::new())
}
#[cfg_attr(feature = "perf-inline", inline(always))]
pub(super) fn rev(
_bytes: &[u8],
_at: usize,
) -> Result<bool, super::UnicodeWordBoundaryError> {
Err(super::UnicodeWordBoundaryError::new())
}
}
#[cfg(test)]
mod tests {
use super::*;
macro_rules! testlook {
($look:expr, $haystack:expr, $at:expr) => {
LookMatcher::default().matches($look, $haystack.as_bytes(), $at)
};
}
#[test]
fn look_matches_start_line() {
let look = Look::StartLF;
assert!(testlook!(look, "", 0));
assert!(testlook!(look, "\n", 0));
assert!(testlook!(look, "\n", 1));
assert!(testlook!(look, "a", 0));
assert!(testlook!(look, "\na", 1));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a\na", 1));
}
#[test]
fn look_matches_end_line() {
let look = Look::EndLF;
assert!(testlook!(look, "", 0));
assert!(testlook!(look, "\n", 1));
assert!(testlook!(look, "\na", 0));
assert!(testlook!(look, "\na", 2));
assert!(testlook!(look, "a\na", 1));
assert!(!testlook!(look, "a", 0));
assert!(!testlook!(look, "\na", 1));
assert!(!testlook!(look, "a\na", 0));
assert!(!testlook!(look, "a\na", 2));
}
#[test]
fn look_matches_start_text() {
let look = Look::Start;
assert!(testlook!(look, "", 0));
assert!(testlook!(look, "\n", 0));
assert!(testlook!(look, "a", 0));
assert!(!testlook!(look, "\n", 1));
assert!(!testlook!(look, "\na", 1));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a\na", 1));
}
#[test]
fn look_matches_end_text() {
let look = Look::End;
assert!(testlook!(look, "", 0));
assert!(testlook!(look, "\n", 1));
assert!(testlook!(look, "\na", 2));
assert!(!testlook!(look, "\na", 0));
assert!(!testlook!(look, "a\na", 1));
assert!(!testlook!(look, "a", 0));
assert!(!testlook!(look, "\na", 1));
assert!(!testlook!(look, "a\na", 0));
assert!(!testlook!(look, "a\na", 2));
}
#[test]
#[cfg(all(not(miri), feature = "unicode-word-boundary"))]
fn look_matches_word_unicode() {
let look = Look::WordUnicode;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(testlook!(look, "a", 0));
assert!(testlook!(look, "a", 1));
assert!(testlook!(look, "a ", 1));
assert!(testlook!(look, " a ", 1));
assert!(testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃", 0));
assert!(testlook!(look, "𝛃", 4));
assert!(testlook!(look, "𝛃 ", 4));
assert!(testlook!(look, " 𝛃 ", 1));
assert!(testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints.
assert!(testlook!(look, "𝛃𐆀", 0));
assert!(testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(!testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(!testlook!(look, "a ", 2));
assert!(!testlook!(look, " a ", 0));
assert!(!testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "𝛃 ", 5));
assert!(!testlook!(look, " 𝛃 ", 0));
assert!(!testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(!testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_matches_word_ascii() {
let look = Look::WordAscii;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(testlook!(look, "a", 0));
assert!(testlook!(look, "a", 1));
assert!(testlook!(look, "a ", 1));
assert!(testlook!(look, " a ", 1));
assert!(testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint. Since this is
// an ASCII word boundary, none of these match.
assert!(!testlook!(look, "𝛃", 0));
assert!(!testlook!(look, "𝛃", 4));
assert!(!testlook!(look, "𝛃 ", 4));
assert!(!testlook!(look, " 𝛃 ", 1));
assert!(!testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints. Again, since
// this is an ASCII word boundary, none of these match.
assert!(!testlook!(look, "𝛃𐆀", 0));
assert!(!testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(!testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(!testlook!(look, "a ", 2));
assert!(!testlook!(look, " a ", 0));
assert!(!testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "𝛃 ", 5));
assert!(!testlook!(look, " 𝛃 ", 0));
assert!(!testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(!testlook!(look, "𝛃𐆀", 8));
}
#[test]
#[cfg(all(not(miri), feature = "unicode-word-boundary"))]
fn look_matches_word_unicode_negate() {
let look = Look::WordUnicodeNegate;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(!testlook!(look, "a", 0));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a ", 1));
assert!(!testlook!(look, " a ", 1));
assert!(!testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃", 0));
assert!(!testlook!(look, "𝛃", 4));
assert!(!testlook!(look, "𝛃 ", 4));
assert!(!testlook!(look, " 𝛃 ", 1));
assert!(!testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 0));
assert!(!testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(testlook!(look, "", 0));
assert!(testlook!(look, "ab", 1));
assert!(testlook!(look, "a ", 2));
assert!(testlook!(look, " a ", 0));
assert!(testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃b", 4));
assert!(testlook!(look, "𝛃 ", 5));
assert!(testlook!(look, " 𝛃 ", 0));
assert!(testlook!(look, " 𝛃 ", 6));
// These don't match because they could otherwise return an offset that
// splits the UTF-8 encoding of a codepoint.
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints. These also don't
// match because they could otherwise return an offset that splits the
// UTF-8 encoding of a codepoint.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
// But this one does, since 𐆀 isn't a word codepoint, and 8 is the end
// of the haystack. So the "end" of the haystack isn't a word and 𐆀
// isn't a word, thus, \B matches.
assert!(testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_matches_word_ascii_negate() {
let look = Look::WordAsciiNegate;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(!testlook!(look, "a", 0));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a ", 1));
assert!(!testlook!(look, " a ", 1));
assert!(!testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint. Since this is
// an ASCII word boundary, none of these match.
assert!(testlook!(look, "𝛃", 0));
assert!(testlook!(look, "𝛃", 4));
assert!(testlook!(look, "𝛃 ", 4));
assert!(testlook!(look, " 𝛃 ", 1));
assert!(testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints. Again, since
// this is an ASCII word boundary, none of these match.
assert!(testlook!(look, "𝛃𐆀", 0));
assert!(testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(testlook!(look, "", 0));
assert!(testlook!(look, "ab", 1));
assert!(testlook!(look, "a ", 2));
assert!(testlook!(look, " a ", 0));
assert!(testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(testlook!(look, "𝛃 ", 5));
assert!(testlook!(look, " 𝛃 ", 0));
assert!(testlook!(look, " 𝛃 ", 6));
assert!(testlook!(look, "𝛃", 1));
assert!(testlook!(look, "𝛃", 2));
assert!(testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(testlook!(look, "𝛃𐆀", 1));
assert!(testlook!(look, "𝛃𐆀", 2));
assert!(testlook!(look, "𝛃𐆀", 3));
assert!(testlook!(look, "𝛃𐆀", 5));
assert!(testlook!(look, "𝛃𐆀", 6));
assert!(testlook!(look, "𝛃𐆀", 7));
assert!(testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_matches_word_start_ascii() {
let look = Look::WordStartAscii;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(testlook!(look, "a", 0));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a ", 1));
assert!(testlook!(look, " a ", 1));
assert!(!testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint. Since this is
// an ASCII word boundary, none of these match.
assert!(!testlook!(look, "𝛃", 0));
assert!(!testlook!(look, "𝛃", 4));
assert!(!testlook!(look, "𝛃 ", 4));
assert!(!testlook!(look, " 𝛃 ", 1));
assert!(!testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints. Again, since
// this is an ASCII word boundary, none of these match.
assert!(!testlook!(look, "𝛃𐆀", 0));
assert!(!testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(!testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(!testlook!(look, "a ", 2));
assert!(!testlook!(look, " a ", 0));
assert!(!testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "b𝛃", 1));
assert!(!testlook!(look, "𝛃 ", 5));
assert!(!testlook!(look, " 𝛃 ", 0));
assert!(!testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(!testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_matches_word_end_ascii() {
let look = Look::WordEndAscii;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(!testlook!(look, "a", 0));
assert!(testlook!(look, "a", 1));
assert!(testlook!(look, "a ", 1));
assert!(!testlook!(look, " a ", 1));
assert!(testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint. Since this is
// an ASCII word boundary, none of these match.
assert!(!testlook!(look, "𝛃", 0));
assert!(!testlook!(look, "𝛃", 4));
assert!(!testlook!(look, "𝛃 ", 4));
assert!(!testlook!(look, " 𝛃 ", 1));
assert!(!testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints. Again, since
// this is an ASCII word boundary, none of these match.
assert!(!testlook!(look, "𝛃𐆀", 0));
assert!(!testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(!testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(!testlook!(look, "a ", 2));
assert!(!testlook!(look, " a ", 0));
assert!(!testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(testlook!(look, "b𝛃", 1));
assert!(!testlook!(look, "𝛃 ", 5));
assert!(!testlook!(look, " 𝛃 ", 0));
assert!(!testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(!testlook!(look, "𝛃𐆀", 8));
}
#[test]
#[cfg(all(not(miri), feature = "unicode-word-boundary"))]
fn look_matches_word_start_unicode() {
let look = Look::WordStartUnicode;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(testlook!(look, "a", 0));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a ", 1));
assert!(testlook!(look, " a ", 1));
assert!(!testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃", 0));
assert!(!testlook!(look, "𝛃", 4));
assert!(!testlook!(look, "𝛃 ", 4));
assert!(testlook!(look, " 𝛃 ", 1));
assert!(!testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints.
assert!(testlook!(look, "𝛃𐆀", 0));
assert!(!testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(!testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(!testlook!(look, "a ", 2));
assert!(!testlook!(look, " a ", 0));
assert!(!testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "b𝛃", 1));
assert!(!testlook!(look, "𝛃 ", 5));
assert!(!testlook!(look, " 𝛃 ", 0));
assert!(!testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(!testlook!(look, "𝛃𐆀", 8));
}
#[test]
#[cfg(all(not(miri), feature = "unicode-word-boundary"))]
fn look_matches_word_end_unicode() {
let look = Look::WordEndUnicode;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(!testlook!(look, "a", 0));
assert!(testlook!(look, "a", 1));
assert!(testlook!(look, "a ", 1));
assert!(!testlook!(look, " a ", 1));
assert!(testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃", 0));
assert!(testlook!(look, "𝛃", 4));
assert!(testlook!(look, "𝛃 ", 4));
assert!(!testlook!(look, " 𝛃 ", 1));
assert!(testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 0));
assert!(testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(!testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(!testlook!(look, "a ", 2));
assert!(!testlook!(look, " a ", 0));
assert!(!testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "b𝛃", 1));
assert!(!testlook!(look, "𝛃 ", 5));
assert!(!testlook!(look, " 𝛃 ", 0));
assert!(!testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(!testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_matches_word_start_half_ascii() {
let look = Look::WordStartHalfAscii;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(testlook!(look, "a", 0));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a ", 1));
assert!(testlook!(look, " a ", 1));
assert!(!testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint. Since this is
// an ASCII word boundary, none of these match.
assert!(testlook!(look, "𝛃", 0));
assert!(testlook!(look, "𝛃", 4));
assert!(testlook!(look, "𝛃 ", 4));
assert!(testlook!(look, " 𝛃 ", 1));
assert!(testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints. Again, since
// this is an ASCII word boundary, none of these match.
assert!(testlook!(look, "𝛃𐆀", 0));
assert!(testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(testlook!(look, "a ", 2));
assert!(testlook!(look, " a ", 0));
assert!(testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "b𝛃", 1));
assert!(testlook!(look, "𝛃 ", 5));
assert!(testlook!(look, " 𝛃 ", 0));
assert!(testlook!(look, " 𝛃 ", 6));
assert!(testlook!(look, "𝛃", 1));
assert!(testlook!(look, "𝛃", 2));
assert!(testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(testlook!(look, "𝛃𐆀", 1));
assert!(testlook!(look, "𝛃𐆀", 2));
assert!(testlook!(look, "𝛃𐆀", 3));
assert!(testlook!(look, "𝛃𐆀", 5));
assert!(testlook!(look, "𝛃𐆀", 6));
assert!(testlook!(look, "𝛃𐆀", 7));
assert!(testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_matches_word_end_half_ascii() {
let look = Look::WordEndHalfAscii;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(!testlook!(look, "a", 0));
assert!(testlook!(look, "a", 1));
assert!(testlook!(look, "a ", 1));
assert!(!testlook!(look, " a ", 1));
assert!(testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint. Since this is
// an ASCII word boundary, none of these match.
assert!(testlook!(look, "𝛃", 0));
assert!(testlook!(look, "𝛃", 4));
assert!(testlook!(look, "𝛃 ", 4));
assert!(testlook!(look, " 𝛃 ", 1));
assert!(testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints. Again, since
// this is an ASCII word boundary, none of these match.
assert!(testlook!(look, "𝛃𐆀", 0));
assert!(testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(testlook!(look, "a ", 2));
assert!(testlook!(look, " a ", 0));
assert!(testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(testlook!(look, "b𝛃", 1));
assert!(testlook!(look, "𝛃 ", 5));
assert!(testlook!(look, " 𝛃 ", 0));
assert!(testlook!(look, " 𝛃 ", 6));
assert!(testlook!(look, "𝛃", 1));
assert!(testlook!(look, "𝛃", 2));
assert!(testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(testlook!(look, "𝛃𐆀", 1));
assert!(testlook!(look, "𝛃𐆀", 2));
assert!(testlook!(look, "𝛃𐆀", 3));
assert!(testlook!(look, "𝛃𐆀", 5));
assert!(testlook!(look, "𝛃𐆀", 6));
assert!(testlook!(look, "𝛃𐆀", 7));
assert!(testlook!(look, "𝛃𐆀", 8));
}
#[test]
#[cfg(all(not(miri), feature = "unicode-word-boundary"))]
fn look_matches_word_start_half_unicode() {
let look = Look::WordStartHalfUnicode;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(testlook!(look, "a", 0));
assert!(!testlook!(look, "a", 1));
assert!(!testlook!(look, "a ", 1));
assert!(testlook!(look, " a ", 1));
assert!(!testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint.
assert!(testlook!(look, "𝛃", 0));
assert!(!testlook!(look, "𝛃", 4));
assert!(!testlook!(look, "𝛃 ", 4));
assert!(testlook!(look, " 𝛃 ", 1));
assert!(!testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints.
assert!(testlook!(look, "𝛃𐆀", 0));
assert!(!testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(testlook!(look, "a ", 2));
assert!(testlook!(look, " a ", 0));
assert!(testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "b𝛃", 1));
assert!(testlook!(look, "𝛃 ", 5));
assert!(testlook!(look, " 𝛃 ", 0));
assert!(testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(testlook!(look, "𝛃𐆀", 8));
}
#[test]
#[cfg(all(not(miri), feature = "unicode-word-boundary"))]
fn look_matches_word_end_half_unicode() {
let look = Look::WordEndHalfUnicode;
// \xF0\x9D\x9B\x83 = 𝛃 (in \w)
// \xF0\x90\x86\x80 = 𐆀 (not in \w)
// Simple ASCII word boundaries.
assert!(!testlook!(look, "a", 0));
assert!(testlook!(look, "a", 1));
assert!(testlook!(look, "a ", 1));
assert!(!testlook!(look, " a ", 1));
assert!(testlook!(look, " a ", 2));
// Unicode word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃", 0));
assert!(testlook!(look, "𝛃", 4));
assert!(testlook!(look, "𝛃 ", 4));
assert!(!testlook!(look, " 𝛃 ", 1));
assert!(testlook!(look, " 𝛃 ", 5));
// Unicode word boundaries between non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 0));
assert!(testlook!(look, "𝛃𐆀", 4));
// Non word boundaries for ASCII.
assert!(testlook!(look, "", 0));
assert!(!testlook!(look, "ab", 1));
assert!(testlook!(look, "a ", 2));
assert!(testlook!(look, " a ", 0));
assert!(testlook!(look, " a ", 3));
// Non word boundaries with a non-ASCII codepoint.
assert!(!testlook!(look, "𝛃b", 4));
assert!(!testlook!(look, "b𝛃", 1));
assert!(testlook!(look, "𝛃 ", 5));
assert!(testlook!(look, " 𝛃 ", 0));
assert!(testlook!(look, " 𝛃 ", 6));
assert!(!testlook!(look, "𝛃", 1));
assert!(!testlook!(look, "𝛃", 2));
assert!(!testlook!(look, "𝛃", 3));
// Non word boundaries with non-ASCII codepoints.
assert!(!testlook!(look, "𝛃𐆀", 1));
assert!(!testlook!(look, "𝛃𐆀", 2));
assert!(!testlook!(look, "𝛃𐆀", 3));
assert!(!testlook!(look, "𝛃𐆀", 5));
assert!(!testlook!(look, "𝛃𐆀", 6));
assert!(!testlook!(look, "𝛃𐆀", 7));
assert!(testlook!(look, "𝛃𐆀", 8));
}
#[test]
fn look_set() {
let mut f = LookSet::default();
assert!(!f.contains(Look::Start));
assert!(!f.contains(Look::End));
assert!(!f.contains(Look::StartLF));
assert!(!f.contains(Look::EndLF));
assert!(!f.contains(Look::WordUnicode));
assert!(!f.contains(Look::WordUnicodeNegate));
assert!(!f.contains(Look::WordAscii));
assert!(!f.contains(Look::WordAsciiNegate));
f = f.insert(Look::Start);
assert!(f.contains(Look::Start));
f = f.remove(Look::Start);
assert!(!f.contains(Look::Start));
f = f.insert(Look::End);
assert!(f.contains(Look::End));
f = f.remove(Look::End);
assert!(!f.contains(Look::End));
f = f.insert(Look::StartLF);
assert!(f.contains(Look::StartLF));
f = f.remove(Look::StartLF);
assert!(!f.contains(Look::StartLF));
f = f.insert(Look::EndLF);
assert!(f.contains(Look::EndLF));
f = f.remove(Look::EndLF);
assert!(!f.contains(Look::EndLF));
f = f.insert(Look::StartCRLF);
assert!(f.contains(Look::StartCRLF));
f = f.remove(Look::StartCRLF);
assert!(!f.contains(Look::StartCRLF));
f = f.insert(Look::EndCRLF);
assert!(f.contains(Look::EndCRLF));
f = f.remove(Look::EndCRLF);
assert!(!f.contains(Look::EndCRLF));
f = f.insert(Look::WordUnicode);
assert!(f.contains(Look::WordUnicode));
f = f.remove(Look::WordUnicode);
assert!(!f.contains(Look::WordUnicode));
f = f.insert(Look::WordUnicodeNegate);
assert!(f.contains(Look::WordUnicodeNegate));
f = f.remove(Look::WordUnicodeNegate);
assert!(!f.contains(Look::WordUnicodeNegate));
f = f.insert(Look::WordAscii);
assert!(f.contains(Look::WordAscii));
f = f.remove(Look::WordAscii);
assert!(!f.contains(Look::WordAscii));
f = f.insert(Look::WordAsciiNegate);
assert!(f.contains(Look::WordAsciiNegate));
f = f.remove(Look::WordAsciiNegate);
assert!(!f.contains(Look::WordAsciiNegate));
f = f.insert(Look::WordStartAscii);
assert!(f.contains(Look::WordStartAscii));
f = f.remove(Look::WordStartAscii);
assert!(!f.contains(Look::WordStartAscii));
f = f.insert(Look::WordEndAscii);
assert!(f.contains(Look::WordEndAscii));
f = f.remove(Look::WordEndAscii);
assert!(!f.contains(Look::WordEndAscii));
f = f.insert(Look::WordStartUnicode);
assert!(f.contains(Look::WordStartUnicode));
f = f.remove(Look::WordStartUnicode);
assert!(!f.contains(Look::WordStartUnicode));
f = f.insert(Look::WordEndUnicode);
assert!(f.contains(Look::WordEndUnicode));
f = f.remove(Look::WordEndUnicode);
assert!(!f.contains(Look::WordEndUnicode));
f = f.insert(Look::WordStartHalfAscii);
assert!(f.contains(Look::WordStartHalfAscii));
f = f.remove(Look::WordStartHalfAscii);
assert!(!f.contains(Look::WordStartHalfAscii));
f = f.insert(Look::WordEndHalfAscii);
assert!(f.contains(Look::WordEndHalfAscii));
f = f.remove(Look::WordEndHalfAscii);
assert!(!f.contains(Look::WordEndHalfAscii));
f = f.insert(Look::WordStartHalfUnicode);
assert!(f.contains(Look::WordStartHalfUnicode));
f = f.remove(Look::WordStartHalfUnicode);
assert!(!f.contains(Look::WordStartHalfUnicode));
f = f.insert(Look::WordEndHalfUnicode);
assert!(f.contains(Look::WordEndHalfUnicode));
f = f.remove(Look::WordEndHalfUnicode);
assert!(!f.contains(Look::WordEndHalfUnicode));
}
#[test]
fn look_set_iter() {
let set = LookSet::empty();
assert_eq!(0, set.iter().count());
let set = LookSet::full();
assert_eq!(18, set.iter().count());
let set =
LookSet::empty().insert(Look::StartLF).insert(Look::WordUnicode);
assert_eq!(2, set.iter().count());
let set = LookSet::empty().insert(Look::StartLF);
assert_eq!(1, set.iter().count());
let set = LookSet::empty().insert(Look::WordAsciiNegate);
assert_eq!(1, set.iter().count());
let set = LookSet::empty().insert(Look::WordEndHalfUnicode);
assert_eq!(1, set.iter().count());
}
#[test]
#[cfg(feature = "alloc")]
fn look_set_debug() {
let res = alloc::format!("{:?}", LookSet::empty());
assert_eq!("∅", res);
let res = alloc::format!("{:?}", LookSet::full());
assert_eq!("Az^$rRbB𝛃𝚩<>〈〉◁▷◀▶", res);
}
}