tree_sitter/lib.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 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
#![doc = include_str!("./README.md")]
#![cfg_attr(not(feature = "std"), no_std)]
pub mod ffi;
mod util;
#[cfg(not(feature = "std"))]
extern crate alloc;
#[cfg(not(feature = "std"))]
use alloc::{boxed::Box, format, string::String, string::ToString, vec::Vec};
use core::{
ffi::{c_char, c_void, CStr},
fmt::{self, Write},
hash, iter,
marker::PhantomData,
mem::MaybeUninit,
num::NonZeroU16,
ops::{self, Deref},
ptr::{self, NonNull},
slice, str,
sync::atomic::AtomicUsize,
};
#[cfg(feature = "std")]
use std::error;
#[cfg(all(feature = "std", any(unix, target_os = "wasi")))]
use std::os::fd::AsRawFd;
#[cfg(all(windows, feature = "std"))]
use std::os::windows::io::AsRawHandle;
use streaming_iterator::{StreamingIterator, StreamingIteratorMut};
use tree_sitter_language::LanguageFn;
#[cfg(feature = "wasm")]
mod wasm_language;
#[cfg(feature = "wasm")]
pub use wasm_language::*;
/// The latest ABI version that is supported by the current version of the
/// library.
///
/// When Languages are generated by the Tree-sitter CLI, they are
/// assigned an ABI version number that corresponds to the current CLI version.
/// The Tree-sitter library is generally backwards-compatible with languages
/// generated using older CLI versions, but is not forwards-compatible.
#[doc(alias = "TREE_SITTER_LANGUAGE_VERSION")]
pub const LANGUAGE_VERSION: usize = ffi::TREE_SITTER_LANGUAGE_VERSION as usize;
/// The earliest ABI version that is supported by the current version of the
/// library.
#[doc(alias = "TREE_SITTER_MIN_COMPATIBLE_LANGUAGE_VERSION")]
pub const MIN_COMPATIBLE_LANGUAGE_VERSION: usize =
ffi::TREE_SITTER_MIN_COMPATIBLE_LANGUAGE_VERSION as usize;
pub const PARSER_HEADER: &str = include_str!("../src/parser.h");
/// An opaque object that defines how to parse a particular language. The code
/// for each `Language` is generated by the Tree-sitter CLI.
#[doc(alias = "TSLanguage")]
#[derive(Debug, PartialEq, Eq, Hash)]
#[repr(transparent)]
pub struct Language(*const ffi::TSLanguage);
pub struct LanguageRef<'a>(*const ffi::TSLanguage, PhantomData<&'a ()>);
/// A tree that represents the syntactic structure of a source code file.
#[doc(alias = "TSTree")]
pub struct Tree(NonNull<ffi::TSTree>);
/// A position in a multi-line text document, in terms of rows and columns.
///
/// Rows and columns are zero-based.
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Hash, PartialOrd, Ord)]
pub struct Point {
pub row: usize,
pub column: usize,
}
/// A range of positions in a multi-line text document, both in terms of bytes
/// and of rows and columns.
#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash)]
pub struct Range {
pub start_byte: usize,
pub end_byte: usize,
pub start_point: Point,
pub end_point: Point,
}
/// A summary of a change to a text document.
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct InputEdit {
pub start_byte: usize,
pub old_end_byte: usize,
pub new_end_byte: usize,
pub start_position: Point,
pub old_end_position: Point,
pub new_end_position: Point,
}
/// A single node within a syntax [`Tree`].
#[doc(alias = "TSNode")]
#[derive(Clone, Copy)]
#[repr(transparent)]
pub struct Node<'tree>(ffi::TSNode, PhantomData<&'tree ()>);
/// A stateful object that this is used to produce a [`Tree`] based on some
/// source code.
#[doc(alias = "TSParser")]
pub struct Parser(NonNull<ffi::TSParser>);
/// A stateful object that is used to look up symbols valid in a specific parse
/// state
#[doc(alias = "TSLookaheadIterator")]
pub struct LookaheadIterator(NonNull<ffi::TSLookaheadIterator>);
struct LookaheadNamesIterator<'a>(&'a mut LookaheadIterator);
/// A type of log message.
#[derive(Debug, PartialEq, Eq)]
pub enum LogType {
Parse,
Lex,
}
type FieldId = NonZeroU16;
/// A callback that receives log messages during parser.
type Logger<'a> = Box<dyn FnMut(LogType, &str) + 'a>;
/// A stateful object for walking a syntax [`Tree`] efficiently.
#[doc(alias = "TSTreeCursor")]
pub struct TreeCursor<'cursor>(ffi::TSTreeCursor, PhantomData<&'cursor ()>);
/// A set of patterns that match nodes in a syntax tree.
#[doc(alias = "TSQuery")]
#[derive(Debug)]
#[allow(clippy::type_complexity)]
pub struct Query {
ptr: NonNull<ffi::TSQuery>,
capture_names: Box<[&'static str]>,
capture_quantifiers: Box<[Box<[CaptureQuantifier]>]>,
text_predicates: Box<[Box<[TextPredicateCapture]>]>,
property_settings: Box<[Box<[QueryProperty]>]>,
property_predicates: Box<[Box<[(QueryProperty, bool)]>]>,
general_predicates: Box<[Box<[QueryPredicate]>]>,
}
/// A quantifier for captures
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub enum CaptureQuantifier {
Zero,
ZeroOrOne,
ZeroOrMore,
One,
OneOrMore,
}
impl From<ffi::TSQuantifier> for CaptureQuantifier {
fn from(value: ffi::TSQuantifier) -> Self {
match value {
ffi::TSQuantifierZero => Self::Zero,
ffi::TSQuantifierZeroOrOne => Self::ZeroOrOne,
ffi::TSQuantifierZeroOrMore => Self::ZeroOrMore,
ffi::TSQuantifierOne => Self::One,
ffi::TSQuantifierOneOrMore => Self::OneOrMore,
_ => panic!("Unrecognized quantifier: {value}"),
}
}
}
/// A stateful object for executing a [`Query`] on a syntax [`Tree`].
#[doc(alias = "TSQueryCursor")]
pub struct QueryCursor {
ptr: NonNull<ffi::TSQueryCursor>,
}
/// A key-value pair associated with a particular pattern in a [`Query`].
#[derive(Debug, PartialEq, Eq)]
pub struct QueryProperty {
pub key: Box<str>,
pub value: Option<Box<str>>,
pub capture_id: Option<usize>,
}
#[derive(Debug, PartialEq, Eq)]
pub enum QueryPredicateArg {
Capture(u32),
String(Box<str>),
}
/// A key-value pair associated with a particular pattern in a [`Query`].
#[derive(Debug, PartialEq, Eq)]
pub struct QueryPredicate {
pub operator: Box<str>,
pub args: Box<[QueryPredicateArg]>,
}
/// A match of a [`Query`] to a particular set of [`Node`]s.
pub struct QueryMatch<'cursor, 'tree> {
pub pattern_index: usize,
pub captures: &'cursor [QueryCapture<'tree>],
id: u32,
cursor: *mut ffi::TSQueryCursor,
}
/// A sequence of [`QueryMatch`]es associated with a given [`QueryCursor`].
pub struct QueryMatches<'query, 'tree: 'query, T: TextProvider<I>, I: AsRef<[u8]>> {
ptr: *mut ffi::TSQueryCursor,
query: &'query Query,
text_provider: T,
buffer1: Vec<u8>,
buffer2: Vec<u8>,
current_match: Option<QueryMatch<'query, 'tree>>,
_phantom: PhantomData<(&'tree (), I)>,
}
/// A sequence of [`QueryCapture`]s associated with a given [`QueryCursor`].
pub struct QueryCaptures<'query, 'tree: 'query, T: TextProvider<I>, I: AsRef<[u8]>> {
ptr: *mut ffi::TSQueryCursor,
query: &'query Query,
text_provider: T,
buffer1: Vec<u8>,
buffer2: Vec<u8>,
current_match: Option<(QueryMatch<'query, 'tree>, usize)>,
_phantom: PhantomData<(&'tree (), I)>,
}
pub trait TextProvider<I>
where
I: AsRef<[u8]>,
{
type I: Iterator<Item = I>;
fn text(&mut self, node: Node) -> Self::I;
}
/// A particular [`Node`] that has been captured with a particular name within a
/// [`Query`].
#[derive(Clone, Copy, Debug)]
#[repr(C)]
pub struct QueryCapture<'tree> {
pub node: Node<'tree>,
pub index: u32,
}
/// An error that occurred when trying to assign an incompatible [`Language`] to
/// a [`Parser`].
#[derive(Debug, PartialEq, Eq)]
pub struct LanguageError {
version: usize,
}
/// An error that occurred in [`Parser::set_included_ranges`].
#[derive(Debug, PartialEq, Eq)]
pub struct IncludedRangesError(pub usize);
/// An error that occurred when trying to create a [`Query`].
#[derive(Debug, PartialEq, Eq)]
pub struct QueryError {
pub row: usize,
pub column: usize,
pub offset: usize,
pub message: String,
pub kind: QueryErrorKind,
}
#[derive(Debug, PartialEq, Eq)]
pub enum QueryErrorKind {
Syntax,
NodeType,
Field,
Capture,
Predicate,
Structure,
Language,
}
#[derive(Debug)]
/// The first item is the capture index
/// The next is capture specific, depending on what item is expected
/// The first bool is if the capture is positive
/// The last item is a bool signifying whether or not it's meant to match
/// any or all captures
enum TextPredicateCapture {
EqString(u32, Box<str>, bool, bool),
EqCapture(u32, u32, bool, bool),
MatchString(u32, regex::bytes::Regex, bool, bool),
AnyString(u32, Box<[Box<str>]>, bool),
}
// TODO: Remove this struct at at some point. If `core::str::lossy::Utf8Lossy`
// is ever stabilized.
pub struct LossyUtf8<'a> {
bytes: &'a [u8],
in_replacement: bool,
}
impl Language {
#[must_use]
pub fn new(builder: LanguageFn) -> Self {
Self(unsafe { builder.into_raw()().cast() })
}
/// Get the ABI version number that indicates which version of the
/// Tree-sitter CLI that was used to generate this [`Language`].
#[doc(alias = "ts_language_version")]
#[must_use]
pub fn version(&self) -> usize {
unsafe { ffi::ts_language_version(self.0) as usize }
}
/// Get the number of distinct node types in this language.
#[doc(alias = "ts_language_symbol_count")]
#[must_use]
pub fn node_kind_count(&self) -> usize {
unsafe { ffi::ts_language_symbol_count(self.0) as usize }
}
/// Get the number of valid states in this language.
#[doc(alias = "ts_language_state_count")]
#[must_use]
pub fn parse_state_count(&self) -> usize {
unsafe { ffi::ts_language_state_count(self.0) as usize }
}
/// Get the name of the node kind for the given numerical id.
#[doc(alias = "ts_language_symbol_name")]
#[must_use]
pub fn node_kind_for_id(&self, id: u16) -> Option<&'static str> {
let ptr = unsafe { ffi::ts_language_symbol_name(self.0, id) };
(!ptr.is_null()).then(|| unsafe { CStr::from_ptr(ptr) }.to_str().unwrap())
}
/// Get the numeric id for the given node kind.
#[doc(alias = "ts_language_symbol_for_name")]
#[must_use]
pub fn id_for_node_kind(&self, kind: &str, named: bool) -> u16 {
unsafe {
ffi::ts_language_symbol_for_name(
self.0,
kind.as_bytes().as_ptr().cast::<c_char>(),
kind.len() as u32,
named,
)
}
}
/// Check if the node type for the given numerical id is named (as opposed
/// to an anonymous node type).
#[must_use]
pub fn node_kind_is_named(&self, id: u16) -> bool {
unsafe { ffi::ts_language_symbol_type(self.0, id) == ffi::TSSymbolTypeRegular }
}
#[doc(alias = "ts_language_symbol_type")]
#[must_use]
pub fn node_kind_is_visible(&self, id: u16) -> bool {
unsafe { ffi::ts_language_symbol_type(self.0, id) <= ffi::TSSymbolTypeAnonymous }
}
/// Get the number of distinct field names in this language.
#[doc(alias = "ts_language_field_count")]
#[must_use]
pub fn field_count(&self) -> usize {
unsafe { ffi::ts_language_field_count(self.0) as usize }
}
/// Get the field names for the given numerical id.
#[doc(alias = "ts_language_field_name_for_id")]
#[must_use]
pub fn field_name_for_id(&self, field_id: u16) -> Option<&'static str> {
let ptr = unsafe { ffi::ts_language_field_name_for_id(self.0, field_id) };
(!ptr.is_null()).then(|| unsafe { CStr::from_ptr(ptr) }.to_str().unwrap())
}
/// Get the numerical id for the given field name.
#[doc(alias = "ts_language_field_id_for_name")]
#[must_use]
pub fn field_id_for_name(&self, field_name: impl AsRef<[u8]>) -> Option<FieldId> {
let field_name = field_name.as_ref();
let id = unsafe {
ffi::ts_language_field_id_for_name(
self.0,
field_name.as_ptr().cast::<c_char>(),
field_name.len() as u32,
)
};
FieldId::new(id)
}
/// Get the next parse state. Combine this with
/// [`lookahead_iterator`](Language::lookahead_iterator) to
/// generate completion suggestions or valid symbols in error nodes.
///
/// Example:
/// ```
/// let state = language.next_state(node.parse_state(), node.grammar_id());
/// ```
#[doc(alias = "ts_language_next_state")]
#[must_use]
pub fn next_state(&self, state: u16, id: u16) -> u16 {
unsafe { ffi::ts_language_next_state(self.0, state, id) }
}
/// Create a new lookahead iterator for this language and parse state.
///
/// This returns `None` if state is invalid for this language.
///
/// Iterating [`LookaheadIterator`] will yield valid symbols in the given
/// parse state. Newly created lookahead iterators will return the `ERROR`
/// symbol from [`LookaheadIterator::current_symbol`].
///
/// Lookahead iterators can be useful to generate suggestions and improve
/// syntax error diagnostics. To get symbols valid in an ERROR node, use the
/// lookahead iterator on its first leaf node state. For `MISSING` nodes, a
/// lookahead iterator created on the previous non-extra leaf node may be
/// appropriate.
#[doc(alias = "ts_lookahead_iterator_new")]
#[must_use]
pub fn lookahead_iterator(&self, state: u16) -> Option<LookaheadIterator> {
let ptr = unsafe { ffi::ts_lookahead_iterator_new(self.0, state) };
(!ptr.is_null()).then(|| unsafe { LookaheadIterator::from_raw(ptr) })
}
}
impl From<LanguageFn> for Language {
fn from(value: LanguageFn) -> Self {
Self::new(value)
}
}
impl Clone for Language {
fn clone(&self) -> Self {
unsafe { Self(ffi::ts_language_copy(self.0)) }
}
}
impl Drop for Language {
fn drop(&mut self) {
unsafe { ffi::ts_language_delete(self.0) }
}
}
impl<'a> Deref for LanguageRef<'a> {
type Target = Language;
fn deref(&self) -> &Self::Target {
unsafe { &*(core::ptr::addr_of!(self.0).cast::<Language>()) }
}
}
impl Default for Parser {
fn default() -> Self {
Self::new()
}
}
impl Parser {
/// Create a new parser.
#[doc(alias = "ts_parser_new")]
#[must_use]
pub fn new() -> Self {
unsafe {
let parser = ffi::ts_parser_new();
Self(NonNull::new_unchecked(parser))
}
}
/// Set the language that the parser should use for parsing.
///
/// Returns a Result indicating whether or not the language was successfully
/// assigned. True means assignment succeeded. False means there was a
/// version mismatch: the language was generated with an incompatible
/// version of the Tree-sitter CLI. Check the language's version using
/// [`Language::version`] and compare it to this library's
/// [`LANGUAGE_VERSION`](LANGUAGE_VERSION) and
/// [`MIN_COMPATIBLE_LANGUAGE_VERSION`](MIN_COMPATIBLE_LANGUAGE_VERSION)
/// constants.
#[doc(alias = "ts_parser_set_language")]
pub fn set_language(&mut self, language: &Language) -> Result<(), LanguageError> {
let version = language.version();
if (MIN_COMPATIBLE_LANGUAGE_VERSION..=LANGUAGE_VERSION).contains(&version) {
unsafe {
ffi::ts_parser_set_language(self.0.as_ptr(), language.0);
}
Ok(())
} else {
Err(LanguageError { version })
}
}
/// Get the parser's current language.
#[doc(alias = "ts_parser_language")]
#[must_use]
pub fn language(&self) -> Option<LanguageRef<'_>> {
let ptr = unsafe { ffi::ts_parser_language(self.0.as_ptr()) };
(!ptr.is_null()).then_some(LanguageRef(ptr, PhantomData))
}
/// Get the parser's current logger.
#[doc(alias = "ts_parser_logger")]
#[must_use]
pub fn logger(&self) -> Option<&Logger> {
let logger = unsafe { ffi::ts_parser_logger(self.0.as_ptr()) };
unsafe { logger.payload.cast::<Logger>().as_ref() }
}
/// Set the logging callback that a parser should use during parsing.
#[doc(alias = "ts_parser_set_logger")]
pub fn set_logger(&mut self, logger: Option<Logger>) {
let prev_logger = unsafe { ffi::ts_parser_logger(self.0.as_ptr()) };
if !prev_logger.payload.is_null() {
drop(unsafe { Box::from_raw(prev_logger.payload.cast::<Logger>()) });
}
let c_logger;
if let Some(logger) = logger {
let container = Box::new(logger);
unsafe extern "C" fn log(
payload: *mut c_void,
c_log_type: ffi::TSLogType,
c_message: *const c_char,
) {
let callback = payload.cast::<Logger>().as_mut().unwrap();
if let Ok(message) = CStr::from_ptr(c_message).to_str() {
let log_type = if c_log_type == ffi::TSLogTypeParse {
LogType::Parse
} else {
LogType::Lex
};
callback(log_type, message);
}
}
let raw_container = Box::into_raw(container);
c_logger = ffi::TSLogger {
payload: raw_container.cast::<c_void>(),
log: Some(log),
};
} else {
c_logger = ffi::TSLogger {
payload: ptr::null_mut(),
log: None,
};
}
unsafe { ffi::ts_parser_set_logger(self.0.as_ptr(), c_logger) };
}
/// Set the destination to which the parser should write debugging graphs
/// during parsing. The graphs are formatted in the DOT language. You may
/// want to pipe these graphs directly to a `dot(1)` process in order to
/// generate SVG output.
#[doc(alias = "ts_parser_print_dot_graphs")]
#[cfg(not(target_os = "wasi"))]
#[cfg(feature = "std")]
pub fn print_dot_graphs(
&mut self,
#[cfg(unix)] file: &impl AsRawFd,
#[cfg(windows)] file: &impl AsRawHandle,
) {
#[cfg(unix)]
{
let fd = file.as_raw_fd();
unsafe {
ffi::ts_parser_print_dot_graphs(self.0.as_ptr(), ffi::_ts_dup(fd));
}
}
#[cfg(windows)]
{
let handle = file.as_raw_handle();
unsafe {
ffi::ts_parser_print_dot_graphs(self.0.as_ptr(), ffi::_ts_dup(handle));
}
}
}
/// Stop the parser from printing debugging graphs while parsing.
#[doc(alias = "ts_parser_print_dot_graphs")]
pub fn stop_printing_dot_graphs(&mut self) {
unsafe { ffi::ts_parser_print_dot_graphs(self.0.as_ptr(), -1) }
}
/// Parse a slice of UTF8 text.
///
/// # Arguments:
/// * `text` The UTF8-encoded text to parse.
/// * `old_tree` A previous syntax tree parsed from the same document. If the text of the
/// document has changed since `old_tree` was created, then you must edit `old_tree` to match
/// the new text using [`Tree::edit`].
///
/// Returns a [`Tree`] if parsing succeeded, or `None` if:
/// * The parser has not yet had a language assigned with [`Parser::set_language`]
/// * The timeout set with [`Parser::set_timeout_micros`] expired
/// * The cancellation flag set with [`Parser::set_cancellation_flag`] was flipped
#[doc(alias = "ts_parser_parse")]
pub fn parse(&mut self, text: impl AsRef<[u8]>, old_tree: Option<&Tree>) -> Option<Tree> {
let bytes = text.as_ref();
let len = bytes.len();
self.parse_with(
&mut |i, _| (i < len).then(|| &bytes[i..]).unwrap_or_default(),
old_tree,
)
}
/// Parse a slice of UTF16 text.
///
/// # Arguments:
/// * `text` The UTF16-encoded text to parse.
/// * `old_tree` A previous syntax tree parsed from the same document. If the text of the
/// document has changed since `old_tree` was created, then you must edit `old_tree` to match
/// the new text using [`Tree::edit`].
pub fn parse_utf16(
&mut self,
input: impl AsRef<[u16]>,
old_tree: Option<&Tree>,
) -> Option<Tree> {
let code_points = input.as_ref();
let len = code_points.len();
self.parse_utf16_with(
&mut |i, _| (i < len).then(|| &code_points[i..]).unwrap_or_default(),
old_tree,
)
}
/// Parse UTF8 text provided in chunks by a callback.
///
/// # Arguments:
/// * `callback` A function that takes a byte offset and position and returns a slice of
/// UTF8-encoded text starting at that byte offset and position. The slices can be of any
/// length. If the given position is at the end of the text, the callback should return an
/// empty slice.
/// * `old_tree` A previous syntax tree parsed from the same document. If the text of the
/// document has changed since `old_tree` was created, then you must edit `old_tree` to match
/// the new text using [`Tree::edit`].
pub fn parse_with<T: AsRef<[u8]>, F: FnMut(usize, Point) -> T>(
&mut self,
callback: &mut F,
old_tree: Option<&Tree>,
) -> Option<Tree> {
// A pointer to this payload is passed on every call to the `read` C function.
// The payload contains two things:
// 1. A reference to the rust `callback`.
// 2. The text that was returned from the previous call to `callback`. This allows the
// callback to return owned values like vectors.
let mut payload: (&mut F, Option<T>) = (callback, None);
// This C function is passed to Tree-sitter as the input callback.
unsafe extern "C" fn read<T: AsRef<[u8]>, F: FnMut(usize, Point) -> T>(
payload: *mut c_void,
byte_offset: u32,
position: ffi::TSPoint,
bytes_read: *mut u32,
) -> *const c_char {
let (callback, text) = payload.cast::<(&mut F, Option<T>)>().as_mut().unwrap();
*text = Some(callback(byte_offset as usize, position.into()));
let slice = text.as_ref().unwrap().as_ref();
*bytes_read = slice.len() as u32;
slice.as_ptr().cast::<c_char>()
}
let c_input = ffi::TSInput {
payload: core::ptr::addr_of_mut!(payload).cast::<c_void>(),
read: Some(read::<T, F>),
encoding: ffi::TSInputEncodingUTF8,
};
let c_old_tree = old_tree.map_or(ptr::null_mut(), |t| t.0.as_ptr());
unsafe {
let c_new_tree = ffi::ts_parser_parse(self.0.as_ptr(), c_old_tree, c_input);
NonNull::new(c_new_tree).map(Tree)
}
}
/// Parse UTF16 text provided in chunks by a callback.
///
/// # Arguments:
/// * `callback` A function that takes a code point offset and position and returns a slice of
/// UTF16-encoded text starting at that byte offset and position. The slices can be of any
/// length. If the given position is at the end of the text, the callback should return an
/// empty slice.
/// * `old_tree` A previous syntax tree parsed from the same document. If the text of the
/// document has changed since `old_tree` was created, then you must edit `old_tree` to match
/// the new text using [`Tree::edit`].
pub fn parse_utf16_with<T: AsRef<[u16]>, F: FnMut(usize, Point) -> T>(
&mut self,
callback: &mut F,
old_tree: Option<&Tree>,
) -> Option<Tree> {
// A pointer to this payload is passed on every call to the `read` C function.
// The payload contains two things:
// 1. A reference to the rust `callback`.
// 2. The text that was returned from the previous call to `callback`. This allows the
// callback to return owned values like vectors.
let mut payload: (&mut F, Option<T>) = (callback, None);
// This C function is passed to Tree-sitter as the input callback.
unsafe extern "C" fn read<T: AsRef<[u16]>, F: FnMut(usize, Point) -> T>(
payload: *mut c_void,
byte_offset: u32,
position: ffi::TSPoint,
bytes_read: *mut u32,
) -> *const c_char {
let (callback, text) = payload.cast::<(&mut F, Option<T>)>().as_mut().unwrap();
*text = Some(callback(
(byte_offset / 2) as usize,
Point {
row: position.row as usize,
column: position.column as usize / 2,
},
));
let slice = text.as_ref().unwrap().as_ref();
*bytes_read = slice.len() as u32 * 2;
slice.as_ptr().cast::<c_char>()
}
let c_input = ffi::TSInput {
payload: core::ptr::addr_of_mut!(payload).cast::<c_void>(),
read: Some(read::<T, F>),
encoding: ffi::TSInputEncodingUTF16,
};
let c_old_tree = old_tree.map_or(ptr::null_mut(), |t| t.0.as_ptr());
unsafe {
let c_new_tree = ffi::ts_parser_parse(self.0.as_ptr(), c_old_tree, c_input);
NonNull::new(c_new_tree).map(Tree)
}
}
/// Instruct the parser to start the next parse from the beginning.
///
/// If the parser previously failed because of a timeout or a cancellation,
/// then by default, it will resume where it left off on the next call
/// to [`parse`](Parser::parse) or other parsing functions. If you don't
/// want to resume, and instead intend to use this parser to parse some
/// other document, you must call `reset` first.
#[doc(alias = "ts_parser_reset")]
pub fn reset(&mut self) {
unsafe { ffi::ts_parser_reset(self.0.as_ptr()) }
}
/// Get the duration in microseconds that parsing is allowed to take.
///
/// This is set via [`set_timeout_micros`](Parser::set_timeout_micros).
#[doc(alias = "ts_parser_timeout_micros")]
#[must_use]
pub fn timeout_micros(&self) -> u64 {
unsafe { ffi::ts_parser_timeout_micros(self.0.as_ptr()) }
}
/// Set the maximum duration in microseconds that parsing should be allowed
/// to take before halting.
///
/// If parsing takes longer than this, it will halt early, returning `None`.
/// See [`parse`](Parser::parse) for more information.
#[doc(alias = "ts_parser_set_timeout_micros")]
pub fn set_timeout_micros(&mut self, timeout_micros: u64) {
unsafe { ffi::ts_parser_set_timeout_micros(self.0.as_ptr(), timeout_micros) }
}
/// Set the ranges of text that the parser should include when parsing.
///
/// By default, the parser will always include entire documents. This
/// function allows you to parse only a *portion* of a document but
/// still return a syntax tree whose ranges match up with the document
/// as a whole. You can also pass multiple disjoint ranges.
///
/// If `ranges` is empty, then the entire document will be parsed.
/// Otherwise, the given ranges must be ordered from earliest to latest
/// in the document, and they must not overlap. That is, the following
/// must hold for all `i` < `length - 1`:
/// ```text
/// ranges[i].end_byte <= ranges[i + 1].start_byte
/// ```
/// If this requirement is not satisfied, method will return
/// [`IncludedRangesError`] error with an offset in the passed ranges
/// slice pointing to a first incorrect range.
#[doc(alias = "ts_parser_set_included_ranges")]
pub fn set_included_ranges(&mut self, ranges: &[Range]) -> Result<(), IncludedRangesError> {
let ts_ranges = ranges.iter().copied().map(Into::into).collect::<Vec<_>>();
let result = unsafe {
ffi::ts_parser_set_included_ranges(
self.0.as_ptr(),
ts_ranges.as_ptr(),
ts_ranges.len() as u32,
)
};
if result {
Ok(())
} else {
let mut prev_end_byte = 0;
for (i, range) in ranges.iter().enumerate() {
if range.start_byte < prev_end_byte || range.end_byte < range.start_byte {
return Err(IncludedRangesError(i));
}
prev_end_byte = range.end_byte;
}
Err(IncludedRangesError(0))
}
}
/// Get the ranges of text that the parser will include when parsing.
#[doc(alias = "ts_parser_included_ranges")]
#[must_use]
pub fn included_ranges(&self) -> Vec<Range> {
let mut count = 0u32;
unsafe {
let ptr =
ffi::ts_parser_included_ranges(self.0.as_ptr(), core::ptr::addr_of_mut!(count));
let ranges = slice::from_raw_parts(ptr, count as usize);
let result = ranges.iter().copied().map(Into::into).collect();
result
}
}
/// Get the parser's current cancellation flag pointer.
///
/// # Safety
///
/// It uses FFI
#[doc(alias = "ts_parser_cancellation_flag")]
#[must_use]
pub unsafe fn cancellation_flag(&self) -> Option<&AtomicUsize> {
ffi::ts_parser_cancellation_flag(self.0.as_ptr())
.cast::<AtomicUsize>()
.as_ref()
}
/// Set the parser's current cancellation flag pointer.
///
/// If a pointer is assigned, then the parser will periodically read from
/// this pointer during parsing. If it reads a non-zero value, it will halt
/// early, returning `None`. See [`parse`](Parser::parse) for more
/// information.
///
/// # Safety
///
/// It uses FFI
#[doc(alias = "ts_parser_set_cancellation_flag")]
pub unsafe fn set_cancellation_flag(&mut self, flag: Option<&AtomicUsize>) {
if let Some(flag) = flag {
ffi::ts_parser_set_cancellation_flag(
self.0.as_ptr(),
(flag as *const AtomicUsize).cast::<usize>(),
);
} else {
ffi::ts_parser_set_cancellation_flag(self.0.as_ptr(), ptr::null());
}
}
}
impl Drop for Parser {
fn drop(&mut self) {
self.stop_printing_dot_graphs();
self.set_logger(None);
unsafe { ffi::ts_parser_delete(self.0.as_ptr()) }
}
}
impl Tree {
/// Get the root node of the syntax tree.
#[doc(alias = "ts_tree_root_node")]
#[must_use]
pub fn root_node(&self) -> Node {
Node::new(unsafe { ffi::ts_tree_root_node(self.0.as_ptr()) }).unwrap()
}
/// Get the root node of the syntax tree, but with its position shifted
/// forward by the given offset.
#[doc(alias = "ts_tree_root_node_with_offset")]
#[must_use]
pub fn root_node_with_offset(&self, offset_bytes: usize, offset_extent: Point) -> Node {
Node::new(unsafe {
ffi::ts_tree_root_node_with_offset(
self.0.as_ptr(),
offset_bytes as u32,
offset_extent.into(),
)
})
.unwrap()
}
/// Get the language that was used to parse the syntax tree.
#[doc(alias = "ts_tree_language")]
#[must_use]
pub fn language(&self) -> LanguageRef {
LanguageRef(
unsafe { ffi::ts_tree_language(self.0.as_ptr()) },
PhantomData,
)
}
/// Edit the syntax tree to keep it in sync with source code that has been
/// edited.
///
/// You must describe the edit both in terms of byte offsets and in terms of
/// row/column coordinates.
#[doc(alias = "ts_tree_edit")]
pub fn edit(&mut self, edit: &InputEdit) {
let edit = edit.into();
unsafe { ffi::ts_tree_edit(self.0.as_ptr(), &edit) };
}
/// Create a new [`TreeCursor`] starting from the root of the tree.
#[must_use]
pub fn walk(&self) -> TreeCursor {
self.root_node().walk()
}
/// Compare this old edited syntax tree to a new syntax tree representing
/// the same document, returning a sequence of ranges whose syntactic
/// structure has changed.
///
/// For this to work correctly, this syntax tree must have been edited such
/// that its ranges match up to the new tree. Generally, you'll want to
/// call this method right after calling one of the [`Parser::parse`]
/// functions. Call it on the old tree that was passed to parse, and
/// pass the new tree that was returned from `parse`.
#[doc(alias = "ts_tree_get_changed_ranges")]
#[must_use]
pub fn changed_ranges(&self, other: &Self) -> impl ExactSizeIterator<Item = Range> {
let mut count = 0u32;
unsafe {
let ptr = ffi::ts_tree_get_changed_ranges(
self.0.as_ptr(),
other.0.as_ptr(),
core::ptr::addr_of_mut!(count),
);
util::CBufferIter::new(ptr, count as usize).map(Into::into)
}
}
/// Get the included ranges that were used to parse the syntax tree.
#[doc(alias = "ts_tree_included_ranges")]
#[must_use]
pub fn included_ranges(&self) -> Vec<Range> {
let mut count = 0u32;
unsafe {
let ptr = ffi::ts_tree_included_ranges(self.0.as_ptr(), core::ptr::addr_of_mut!(count));
let ranges = slice::from_raw_parts(ptr, count as usize);
let result = ranges.iter().copied().map(Into::into).collect();
(FREE_FN)(ptr.cast::<c_void>());
result
}
}
/// Print a graph of the tree to the given file descriptor.
/// The graph is formatted in the DOT language. You may want to pipe this
/// graph directly to a `dot(1)` process in order to generate SVG
/// output.
#[doc(alias = "ts_tree_print_dot_graph")]
#[cfg(not(target_os = "wasi"))]
#[cfg(feature = "std")]
pub fn print_dot_graph(
&self,
#[cfg(unix)] file: &impl AsRawFd,
#[cfg(windows)] file: &impl AsRawHandle,
) {
#[cfg(unix)]
{
let fd = file.as_raw_fd();
unsafe { ffi::ts_tree_print_dot_graph(self.0.as_ptr(), fd) }
}
#[cfg(windows)]
{
let handle = file.as_raw_handle();
unsafe { ffi::ts_tree_print_dot_graph(self.0.as_ptr(), handle as i32) }
}
}
}
impl fmt::Debug for Tree {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{{Tree {:?}}}", self.root_node())
}
}
impl Drop for Tree {
fn drop(&mut self) {
unsafe { ffi::ts_tree_delete(self.0.as_ptr()) }
}
}
impl Clone for Tree {
fn clone(&self) -> Self {
unsafe { Self(NonNull::new_unchecked(ffi::ts_tree_copy(self.0.as_ptr()))) }
}
}
impl<'tree> Node<'tree> {
fn new(node: ffi::TSNode) -> Option<Self> {
(!node.id.is_null()).then_some(Node(node, PhantomData))
}
/// Get a numeric id for this node that is unique.
///
/// Within a given syntax tree, no two nodes have the same id. However, if
/// a new tree is created based on an older tree, and a node from the old
/// tree is reused in the process, then that node will have the same id in
/// both trees.
#[must_use]
pub fn id(&self) -> usize {
self.0.id as usize
}
/// Get this node's type as a numerical id.
#[doc(alias = "ts_node_symbol")]
#[must_use]
pub fn kind_id(&self) -> u16 {
unsafe { ffi::ts_node_symbol(self.0) }
}
/// Get the node's type as a numerical id as it appears in the grammar
/// ignoring aliases.
#[doc(alias = "ts_node_grammar_symbol")]
#[must_use]
pub fn grammar_id(&self) -> u16 {
unsafe { ffi::ts_node_grammar_symbol(self.0) }
}
/// Get this node's type as a string.
#[doc(alias = "ts_node_type")]
#[must_use]
pub fn kind(&self) -> &'static str {
unsafe { CStr::from_ptr(ffi::ts_node_type(self.0)) }
.to_str()
.unwrap()
}
/// Get this node's symbol name as it appears in the grammar ignoring
/// aliases as a string.
#[doc(alias = "ts_node_grammar_type")]
#[must_use]
pub fn grammar_name(&self) -> &'static str {
unsafe { CStr::from_ptr(ffi::ts_node_grammar_type(self.0)) }
.to_str()
.unwrap()
}
/// Get the [`Language`] that was used to parse this node's syntax tree.
#[doc(alias = "ts_node_language")]
#[must_use]
pub fn language(&self) -> LanguageRef {
LanguageRef(unsafe { ffi::ts_node_language(self.0) }, PhantomData)
}
/// Check if this node is *named*.
///
/// Named nodes correspond to named rules in the grammar, whereas
/// *anonymous* nodes correspond to string literals in the grammar.
#[doc(alias = "ts_node_is_named")]
#[must_use]
pub fn is_named(&self) -> bool {
unsafe { ffi::ts_node_is_named(self.0) }
}
/// Check if this node is *extra*.
///
/// Extra nodes represent things like comments, which are not required the
/// grammar, but can appear anywhere.
#[doc(alias = "ts_node_is_extra")]
#[must_use]
pub fn is_extra(&self) -> bool {
unsafe { ffi::ts_node_is_extra(self.0) }
}
/// Check if this node has been edited.
#[doc(alias = "ts_node_has_changes")]
#[must_use]
pub fn has_changes(&self) -> bool {
unsafe { ffi::ts_node_has_changes(self.0) }
}
/// Check if this node represents a syntax error or contains any syntax
/// errors anywhere within it.
#[doc(alias = "ts_node_has_error")]
#[must_use]
pub fn has_error(&self) -> bool {
unsafe { ffi::ts_node_has_error(self.0) }
}
/// Check if this node represents a syntax error.
///
/// Syntax errors represent parts of the code that could not be incorporated
/// into a valid syntax tree.
#[doc(alias = "ts_node_is_error")]
#[must_use]
pub fn is_error(&self) -> bool {
unsafe { ffi::ts_node_is_error(self.0) }
}
/// Get this node's parse state.
#[doc(alias = "ts_node_parse_state")]
#[must_use]
pub fn parse_state(&self) -> u16 {
unsafe { ffi::ts_node_parse_state(self.0) }
}
/// Get the parse state after this node.
#[doc(alias = "ts_node_next_parse_state")]
#[must_use]
pub fn next_parse_state(&self) -> u16 {
unsafe { ffi::ts_node_next_parse_state(self.0) }
}
/// Check if this node is *missing*.
///
/// Missing nodes are inserted by the parser in order to recover from
/// certain kinds of syntax errors.
#[doc(alias = "ts_node_is_missing")]
#[must_use]
pub fn is_missing(&self) -> bool {
unsafe { ffi::ts_node_is_missing(self.0) }
}
/// Get the byte offsets where this node starts.
#[doc(alias = "ts_node_start_byte")]
#[must_use]
pub fn start_byte(&self) -> usize {
unsafe { ffi::ts_node_start_byte(self.0) as usize }
}
/// Get the byte offsets where this node end.
#[doc(alias = "ts_node_end_byte")]
#[must_use]
pub fn end_byte(&self) -> usize {
unsafe { ffi::ts_node_end_byte(self.0) as usize }
}
/// Get the byte range of source code that this node represents.
#[must_use]
pub fn byte_range(&self) -> core::ops::Range<usize> {
self.start_byte()..self.end_byte()
}
/// Get the range of source code that this node represents, both in terms of
/// raw bytes and of row/column coordinates.
#[must_use]
pub fn range(&self) -> Range {
Range {
start_byte: self.start_byte(),
end_byte: self.end_byte(),
start_point: self.start_position(),
end_point: self.end_position(),
}
}
/// Get this node's start position in terms of rows and columns.
#[doc(alias = "ts_node_start_point")]
#[must_use]
pub fn start_position(&self) -> Point {
let result = unsafe { ffi::ts_node_start_point(self.0) };
result.into()
}
/// Get this node's end position in terms of rows and columns.
#[doc(alias = "ts_node_end_point")]
#[must_use]
pub fn end_position(&self) -> Point {
let result = unsafe { ffi::ts_node_end_point(self.0) };
result.into()
}
/// Get the node's child at the given index, where zero represents the first
/// child.
///
/// This method is fairly fast, but its cost is technically log(i), so if
/// you might be iterating over a long list of children, you should use
/// [`Node::children`] instead.
#[doc(alias = "ts_node_child")]
#[must_use]
pub fn child(&self, i: usize) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_child(self.0, i as u32) })
}
/// Get this node's number of children.
#[doc(alias = "ts_node_child_count")]
#[must_use]
pub fn child_count(&self) -> usize {
unsafe { ffi::ts_node_child_count(self.0) as usize }
}
/// Get this node's *named* child at the given index.
///
/// See also [`Node::is_named`].
/// This method is fairly fast, but its cost is technically log(i), so if
/// you might be iterating over a long list of children, you should use
/// [`Node::named_children`] instead.
#[doc(alias = "ts_node_named_child")]
#[must_use]
pub fn named_child(&self, i: usize) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_named_child(self.0, i as u32) })
}
/// Get this node's number of *named* children.
///
/// See also [`Node::is_named`].
#[doc(alias = "ts_node_named_child_count")]
#[must_use]
pub fn named_child_count(&self) -> usize {
unsafe { ffi::ts_node_named_child_count(self.0) as usize }
}
/// Get the first child with the given field name.
///
/// If multiple children may have the same field name, access them using
/// [`children_by_field_name`](Node::children_by_field_name)
#[doc(alias = "ts_node_child_by_field_name")]
#[must_use]
pub fn child_by_field_name(&self, field_name: impl AsRef<[u8]>) -> Option<Self> {
let field_name = field_name.as_ref();
Self::new(unsafe {
ffi::ts_node_child_by_field_name(
self.0,
field_name.as_ptr().cast::<c_char>(),
field_name.len() as u32,
)
})
}
/// Get this node's child with the given numerical field id.
///
/// See also [`child_by_field_name`](Node::child_by_field_name). You can
/// convert a field name to an id using [`Language::field_id_for_name`].
#[doc(alias = "ts_node_child_by_field_id")]
#[must_use]
pub fn child_by_field_id(&self, field_id: u16) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_child_by_field_id(self.0, field_id) })
}
/// Get the field name of this node's child at the given index.
#[doc(alias = "ts_node_field_name_for_child")]
#[must_use]
pub fn field_name_for_child(&self, child_index: u32) -> Option<&'static str> {
unsafe {
let ptr = ffi::ts_node_field_name_for_child(self.0, child_index);
(!ptr.is_null()).then(|| CStr::from_ptr(ptr).to_str().unwrap())
}
}
/// Get the field name of this node's named child at the given index.
pub fn field_name_for_named_child(&self, named_child_index: u32) -> Option<&'static str> {
unsafe {
let ptr = ffi::ts_node_field_name_for_named_child(self.0, named_child_index);
(!ptr.is_null()).then(|| CStr::from_ptr(ptr).to_str().unwrap())
}
}
/// Iterate over this node's children.
///
/// A [`TreeCursor`] is used to retrieve the children efficiently. Obtain
/// a [`TreeCursor`] by calling [`Tree::walk`] or [`Node::walk`]. To avoid
/// unnecessary allocations, you should reuse the same cursor for
/// subsequent calls to this method.
///
/// If you're walking the tree recursively, you may want to use the
/// [`TreeCursor`] APIs directly instead.
pub fn children<'cursor>(
&self,
cursor: &'cursor mut TreeCursor<'tree>,
) -> impl ExactSizeIterator<Item = Node<'tree>> + 'cursor {
cursor.reset(*self);
cursor.goto_first_child();
(0..self.child_count()).map(move |_| {
let result = cursor.node();
cursor.goto_next_sibling();
result
})
}
/// Iterate over this node's named children.
///
/// See also [`Node::children`].
pub fn named_children<'cursor>(
&self,
cursor: &'cursor mut TreeCursor<'tree>,
) -> impl ExactSizeIterator<Item = Node<'tree>> + 'cursor {
cursor.reset(*self);
cursor.goto_first_child();
(0..self.named_child_count()).map(move |_| {
while !cursor.node().is_named() {
if !cursor.goto_next_sibling() {
break;
}
}
let result = cursor.node();
cursor.goto_next_sibling();
result
})
}
/// Iterate over this node's children with a given field name.
///
/// See also [`Node::children`].
pub fn children_by_field_name<'cursor>(
&self,
field_name: &str,
cursor: &'cursor mut TreeCursor<'tree>,
) -> impl Iterator<Item = Node<'tree>> + 'cursor {
let field_id = self.language().field_id_for_name(field_name);
let mut done = field_id.is_none();
if !done {
cursor.reset(*self);
cursor.goto_first_child();
}
iter::from_fn(move || {
if !done {
while cursor.field_id() != field_id {
if !cursor.goto_next_sibling() {
return None;
}
}
let result = cursor.node();
if !cursor.goto_next_sibling() {
done = true;
}
return Some(result);
}
None
})
}
/// Iterate over this node's children with a given field id.
///
/// See also [`Node::children_by_field_name`].
pub fn children_by_field_id<'cursor>(
&self,
field_id: FieldId,
cursor: &'cursor mut TreeCursor<'tree>,
) -> impl Iterator<Item = Node<'tree>> + 'cursor {
cursor.reset(*self);
cursor.goto_first_child();
let mut done = false;
iter::from_fn(move || {
if !done {
while cursor.field_id() != Some(field_id) {
if !cursor.goto_next_sibling() {
return None;
}
}
let result = cursor.node();
if !cursor.goto_next_sibling() {
done = true;
}
return Some(result);
}
None
})
}
/// Get this node's immediate parent.
/// Prefer [`child_containing_descendant`](Node::child_containing_descendant)
/// for iterating over this node's ancestors.
#[doc(alias = "ts_node_parent")]
#[must_use]
pub fn parent(&self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_parent(self.0) })
}
/// Get this node's child containing `descendant`. This will not return
/// the descendant if it is a direct child of `self`, for that use
/// [`Node::child_contains_descendant`].
#[doc(alias = "ts_node_child_containing_descendant")]
#[must_use]
#[deprecated(since = "0.24.0", note = "Prefer child_with_descendant instead")]
pub fn child_containing_descendant(&self, descendant: Self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_child_containing_descendant(self.0, descendant.0) })
}
/// Get the node that contains `descendant`.
///
/// Note that this can return `descendant` itself, unlike the deprecated function
/// [`Node::child_containing_descendant`].
#[doc(alias = "ts_node_child_with_descendant")]
#[must_use]
pub fn child_with_descendant(&self, descendant: Self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_child_with_descendant(self.0, descendant.0) })
}
/// Get this node's next sibling.
#[doc(alias = "ts_node_next_sibling")]
#[must_use]
pub fn next_sibling(&self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_next_sibling(self.0) })
}
/// Get this node's previous sibling.
#[doc(alias = "ts_node_prev_sibling")]
#[must_use]
pub fn prev_sibling(&self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_prev_sibling(self.0) })
}
/// Get this node's next named sibling.
#[doc(alias = "ts_node_next_named_sibling")]
#[must_use]
pub fn next_named_sibling(&self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_next_named_sibling(self.0) })
}
/// Get this node's previous named sibling.
#[doc(alias = "ts_node_prev_named_sibling")]
#[must_use]
pub fn prev_named_sibling(&self) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_prev_named_sibling(self.0) })
}
/// Get the node's first child that extends beyond the given byte offset.
#[doc(alias = "ts_node_first_child_for_byte")]
#[must_use]
pub fn first_child_for_byte(&self, byte: usize) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_first_child_for_byte(self.0, byte as u32) })
}
/// Get the node's first named child that extends beyond the given byte offset.
#[doc(alias = "ts_node_first_named_child_for_point")]
#[must_use]
pub fn first_named_child_for_byte(&self, byte: usize) -> Option<Self> {
Self::new(unsafe { ffi::ts_node_first_named_child_for_byte(self.0, byte as u32) })
}
/// Get the node's number of descendants, including one for the node itself.
#[doc(alias = "ts_node_descendant_count")]
#[must_use]
pub fn descendant_count(&self) -> usize {
unsafe { ffi::ts_node_descendant_count(self.0) as usize }
}
/// Get the smallest node within this node that spans the given range.
#[doc(alias = "ts_node_descendant_for_byte_range")]
#[must_use]
pub fn descendant_for_byte_range(&self, start: usize, end: usize) -> Option<Self> {
Self::new(unsafe {
ffi::ts_node_descendant_for_byte_range(self.0, start as u32, end as u32)
})
}
/// Get the smallest named node within this node that spans the given range.
#[doc(alias = "ts_node_named_descendant_for_byte_range")]
#[must_use]
pub fn named_descendant_for_byte_range(&self, start: usize, end: usize) -> Option<Self> {
Self::new(unsafe {
ffi::ts_node_named_descendant_for_byte_range(self.0, start as u32, end as u32)
})
}
/// Get the smallest node within this node that spans the given range.
#[doc(alias = "ts_node_descendant_for_point_range")]
#[must_use]
pub fn descendant_for_point_range(&self, start: Point, end: Point) -> Option<Self> {
Self::new(unsafe {
ffi::ts_node_descendant_for_point_range(self.0, start.into(), end.into())
})
}
/// Get the smallest named node within this node that spans the given range.
#[doc(alias = "ts_node_named_descendant_for_point_range")]
#[must_use]
pub fn named_descendant_for_point_range(&self, start: Point, end: Point) -> Option<Self> {
Self::new(unsafe {
ffi::ts_node_named_descendant_for_point_range(self.0, start.into(), end.into())
})
}
#[doc(alias = "ts_node_string")]
#[must_use]
pub fn to_sexp(&self) -> String {
let c_string = unsafe { ffi::ts_node_string(self.0) };
let result = unsafe { CStr::from_ptr(c_string) }
.to_str()
.unwrap()
.to_string();
unsafe { (FREE_FN)(c_string.cast::<c_void>()) };
result
}
pub fn utf8_text<'a>(&self, source: &'a [u8]) -> Result<&'a str, str::Utf8Error> {
str::from_utf8(&source[self.start_byte()..self.end_byte()])
}
#[must_use]
pub fn utf16_text<'a>(&self, source: &'a [u16]) -> &'a [u16] {
&source[self.start_byte()..self.end_byte()]
}
/// Create a new [`TreeCursor`] starting from this node.
#[doc(alias = "ts_tree_cursor_new")]
#[must_use]
pub fn walk(&self) -> TreeCursor<'tree> {
TreeCursor(unsafe { ffi::ts_tree_cursor_new(self.0) }, PhantomData)
}
/// Edit this node to keep it in-sync with source code that has been edited.
///
/// This function is only rarely needed. When you edit a syntax tree with
/// the [`Tree::edit`] method, all of the nodes that you retrieve from
/// the tree afterward will already reflect the edit. You only need to
/// use [`Node::edit`] when you have a specific [`Node`] instance that
/// you want to keep and continue to use after an edit.
#[doc(alias = "ts_node_edit")]
pub fn edit(&mut self, edit: &InputEdit) {
let edit = edit.into();
unsafe { ffi::ts_node_edit(core::ptr::addr_of_mut!(self.0), &edit) }
}
}
impl PartialEq for Node<'_> {
fn eq(&self, other: &Self) -> bool {
self.0.id == other.0.id
}
}
impl Eq for Node<'_> {}
impl hash::Hash for Node<'_> {
fn hash<H: hash::Hasher>(&self, state: &mut H) {
self.0.id.hash(state);
self.0.context[0].hash(state);
self.0.context[1].hash(state);
self.0.context[2].hash(state);
self.0.context[3].hash(state);
}
}
impl fmt::Debug for Node<'_> {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"{{Node {} {} - {}}}",
self.kind(),
self.start_position(),
self.end_position()
)
}
}
impl fmt::Display for Node<'_> {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let sexp = self.to_sexp();
if sexp.is_empty() {
write!(f, "")
} else if !f.alternate() {
write!(f, "{sexp}")
} else {
write!(f, "{}", format_sexp(&sexp, f.width().unwrap_or(0)))
}
}
}
impl<'cursor> TreeCursor<'cursor> {
/// Get the tree cursor's current [`Node`].
#[doc(alias = "ts_tree_cursor_current_node")]
#[must_use]
pub fn node(&self) -> Node<'cursor> {
Node(
unsafe { ffi::ts_tree_cursor_current_node(&self.0) },
PhantomData,
)
}
/// Get the numerical field id of this tree cursor's current node.
///
/// See also [`field_name`](TreeCursor::field_name).
#[doc(alias = "ts_tree_cursor_current_field_id")]
#[must_use]
pub fn field_id(&self) -> Option<FieldId> {
let id = unsafe { ffi::ts_tree_cursor_current_field_id(&self.0) };
FieldId::new(id)
}
/// Get the field name of this tree cursor's current node.
#[doc(alias = "ts_tree_cursor_current_field_name")]
#[must_use]
pub fn field_name(&self) -> Option<&'static str> {
unsafe {
let ptr = ffi::ts_tree_cursor_current_field_name(&self.0);
(!ptr.is_null()).then(|| CStr::from_ptr(ptr).to_str().unwrap())
}
}
/// Get the depth of the cursor's current node relative to the original
/// node that the cursor was constructed with.
#[doc(alias = "ts_tree_cursor_current_depth")]
#[must_use]
pub fn depth(&self) -> u32 {
unsafe { ffi::ts_tree_cursor_current_depth(&self.0) }
}
/// Get the index of the cursor's current node out of all of the
/// descendants of the original node that the cursor was constructed with
#[doc(alias = "ts_tree_cursor_current_descendant_index")]
#[must_use]
pub fn descendant_index(&self) -> usize {
unsafe { ffi::ts_tree_cursor_current_descendant_index(&self.0) as usize }
}
/// Move this cursor to the first child of its current node.
///
/// This returns `true` if the cursor successfully moved, and returns
/// `false` if there were no children.
#[doc(alias = "ts_tree_cursor_goto_first_child")]
pub fn goto_first_child(&mut self) -> bool {
unsafe { ffi::ts_tree_cursor_goto_first_child(&mut self.0) }
}
/// Move this cursor to the last child of its current node.
///
/// This returns `true` if the cursor successfully moved, and returns
/// `false` if there were no children.
///
/// Note that this function may be slower than
/// [`goto_first_child`](TreeCursor::goto_first_child) because it needs to
/// iterate through all the children to compute the child's position.
#[doc(alias = "ts_tree_cursor_goto_last_child")]
pub fn goto_last_child(&mut self) -> bool {
unsafe { ffi::ts_tree_cursor_goto_last_child(&mut self.0) }
}
/// Move this cursor to the parent of its current node.
///
/// This returns `true` if the cursor successfully moved, and returns
/// `false` if there was no parent node (the cursor was already on the
/// root node).
#[doc(alias = "ts_tree_cursor_goto_parent")]
pub fn goto_parent(&mut self) -> bool {
unsafe { ffi::ts_tree_cursor_goto_parent(&mut self.0) }
}
/// Move this cursor to the next sibling of its current node.
///
/// This returns `true` if the cursor successfully moved, and returns
/// `false` if there was no next sibling node.
#[doc(alias = "ts_tree_cursor_goto_next_sibling")]
pub fn goto_next_sibling(&mut self) -> bool {
unsafe { ffi::ts_tree_cursor_goto_next_sibling(&mut self.0) }
}
/// Move the cursor to the node that is the nth descendant of
/// the original node that the cursor was constructed with, where
/// zero represents the original node itself.
#[doc(alias = "ts_tree_cursor_goto_descendant")]
pub fn goto_descendant(&mut self, descendant_index: usize) {
unsafe { ffi::ts_tree_cursor_goto_descendant(&mut self.0, descendant_index as u32) }
}
/// Move this cursor to the previous sibling of its current node.
///
/// This returns `true` if the cursor successfully moved, and returns
/// `false` if there was no previous sibling node.
///
/// Note, that this function may be slower than
/// [`goto_next_sibling`](TreeCursor::goto_next_sibling) due to how node
/// positions are stored. In the worst case, this will need to iterate
/// through all the children upto the previous sibling node to recalculate
/// its position.
#[doc(alias = "ts_tree_cursor_goto_previous_sibling")]
pub fn goto_previous_sibling(&mut self) -> bool {
unsafe { ffi::ts_tree_cursor_goto_previous_sibling(&mut self.0) }
}
/// Move this cursor to the first child of its current node that extends
/// beyond the given byte offset.
///
/// This returns the index of the child node if one was found, and returns
/// `None` if no such child was found.
#[doc(alias = "ts_tree_cursor_goto_first_child_for_byte")]
pub fn goto_first_child_for_byte(&mut self, index: usize) -> Option<usize> {
let result =
unsafe { ffi::ts_tree_cursor_goto_first_child_for_byte(&mut self.0, index as u32) };
(result >= 0).then_some(result as usize)
}
/// Move this cursor to the first child of its current node that extends
/// beyond the given byte offset.
///
/// This returns the index of the child node if one was found, and returns
/// `None` if no such child was found.
#[doc(alias = "ts_tree_cursor_goto_first_child_for_point")]
pub fn goto_first_child_for_point(&mut self, point: Point) -> Option<usize> {
let result =
unsafe { ffi::ts_tree_cursor_goto_first_child_for_point(&mut self.0, point.into()) };
(result >= 0).then_some(result as usize)
}
/// Re-initialize this tree cursor to start at the original node that the
/// cursor was constructed with.
#[doc(alias = "ts_tree_cursor_reset")]
pub fn reset(&mut self, node: Node<'cursor>) {
unsafe { ffi::ts_tree_cursor_reset(&mut self.0, node.0) };
}
/// Re-initialize a tree cursor to the same position as another cursor.
///
/// Unlike [`reset`](TreeCursor::reset), this will not lose parent
/// information and allows reusing already created cursors.
#[doc(alias = "ts_tree_cursor_reset_to")]
pub fn reset_to(&mut self, cursor: &Self) {
unsafe { ffi::ts_tree_cursor_reset_to(&mut self.0, &cursor.0) };
}
}
impl Clone for TreeCursor<'_> {
fn clone(&self) -> Self {
TreeCursor(unsafe { ffi::ts_tree_cursor_copy(&self.0) }, PhantomData)
}
}
impl Drop for TreeCursor<'_> {
fn drop(&mut self) {
unsafe { ffi::ts_tree_cursor_delete(&mut self.0) }
}
}
impl LookaheadIterator {
/// Get the current language of the lookahead iterator.
#[doc(alias = "ts_lookahead_iterator_language")]
#[must_use]
pub fn language(&self) -> LanguageRef<'_> {
LanguageRef(
unsafe { ffi::ts_lookahead_iterator_language(self.0.as_ptr()) },
PhantomData,
)
}
/// Get the current symbol of the lookahead iterator.
#[doc(alias = "ts_lookahead_iterator_current_symbol")]
#[must_use]
pub fn current_symbol(&self) -> u16 {
unsafe { ffi::ts_lookahead_iterator_current_symbol(self.0.as_ptr()) }
}
/// Get the current symbol name of the lookahead iterator.
#[doc(alias = "ts_lookahead_iterator_current_symbol_name")]
#[must_use]
pub fn current_symbol_name(&self) -> &'static str {
unsafe {
CStr::from_ptr(ffi::ts_lookahead_iterator_current_symbol_name(
self.0.as_ptr(),
))
.to_str()
.unwrap()
}
}
/// Reset the lookahead iterator.
///
/// This returns `true` if the language was set successfully and `false`
/// otherwise.
#[doc(alias = "ts_lookahead_iterator_reset")]
pub fn reset(&mut self, language: &Language, state: u16) -> bool {
unsafe { ffi::ts_lookahead_iterator_reset(self.0.as_ptr(), language.0, state) }
}
/// Reset the lookahead iterator to another state.
///
/// This returns `true` if the iterator was reset to the given state and
/// `false` otherwise.
#[doc(alias = "ts_lookahead_iterator_reset_state")]
pub fn reset_state(&mut self, state: u16) -> bool {
unsafe { ffi::ts_lookahead_iterator_reset_state(self.0.as_ptr(), state) }
}
/// Iterate symbol names.
pub fn iter_names(&mut self) -> impl Iterator<Item = &'static str> + '_ {
LookaheadNamesIterator(self)
}
}
impl Iterator for LookaheadNamesIterator<'_> {
type Item = &'static str;
#[doc(alias = "ts_lookahead_iterator_next")]
fn next(&mut self) -> Option<Self::Item> {
unsafe { ffi::ts_lookahead_iterator_next(self.0 .0.as_ptr()) }
.then(|| self.0.current_symbol_name())
}
}
impl Iterator for LookaheadIterator {
type Item = u16;
#[doc(alias = "ts_lookahead_iterator_next")]
fn next(&mut self) -> Option<Self::Item> {
// the first symbol is always `0` so we can safely skip it
unsafe { ffi::ts_lookahead_iterator_next(self.0.as_ptr()) }.then(|| self.current_symbol())
}
}
impl Drop for LookaheadIterator {
#[doc(alias = "ts_lookahead_iterator_delete")]
fn drop(&mut self) {
unsafe { ffi::ts_lookahead_iterator_delete(self.0.as_ptr()) }
}
}
impl Query {
/// Create a new query from a string containing one or more S-expression
/// patterns.
///
/// The query is associated with a particular language, and can only be run
/// on syntax nodes parsed with that language. References to Queries can be
/// shared between multiple threads.
pub fn new(language: &Language, source: &str) -> Result<Self, QueryError> {
let mut error_offset = 0u32;
let mut error_type: ffi::TSQueryError = 0;
let bytes = source.as_bytes();
// Compile the query.
let ptr = unsafe {
ffi::ts_query_new(
language.0,
bytes.as_ptr().cast::<c_char>(),
bytes.len() as u32,
core::ptr::addr_of_mut!(error_offset),
core::ptr::addr_of_mut!(error_type),
)
};
// On failure, build an error based on the error code and offset.
if ptr.is_null() {
if error_type == ffi::TSQueryErrorLanguage {
return Err(QueryError {
row: 0,
column: 0,
offset: 0,
message: LanguageError {
version: language.version(),
}
.to_string(),
kind: QueryErrorKind::Language,
});
}
let offset = error_offset as usize;
let mut line_start = 0;
let mut row = 0;
let mut line_containing_error = None;
for line in source.lines() {
let line_end = line_start + line.len() + 1;
if line_end > offset {
line_containing_error = Some(line);
break;
}
line_start = line_end;
row += 1;
}
let column = offset - line_start;
let kind;
let message;
match error_type {
// Error types that report names
ffi::TSQueryErrorNodeType | ffi::TSQueryErrorField | ffi::TSQueryErrorCapture => {
let suffix = source.split_at(offset).1;
let in_quotes = source.as_bytes()[offset - 1] == b'"';
let mut end_offset = suffix.len();
if let Some(pos) = suffix
.char_indices()
.take_while(|(_, c)| *c != '\n')
.find_map(|(i, c)| match c {
'"' if in_quotes
&& i > 0
&& suffix.chars().nth(i - 1) != Some('\\') =>
{
Some(i)
}
c if !in_quotes
&& (c.is_whitespace() || c == '(' || c == ')' || c == ':') =>
{
Some(i)
}
_ => None,
})
{
end_offset = pos;
}
message = suffix.split_at(end_offset).0.to_string();
kind = match error_type {
ffi::TSQueryErrorNodeType => QueryErrorKind::NodeType,
ffi::TSQueryErrorField => QueryErrorKind::Field,
ffi::TSQueryErrorCapture => QueryErrorKind::Capture,
_ => unreachable!(),
};
}
// Error types that report positions
_ => {
message = line_containing_error.map_or_else(
|| "Unexpected EOF".to_string(),
|line| line.to_string() + "\n" + &" ".repeat(offset - line_start) + "^",
);
kind = match error_type {
ffi::TSQueryErrorStructure => QueryErrorKind::Structure,
_ => QueryErrorKind::Syntax,
};
}
};
return Err(QueryError {
row,
column,
offset,
message,
kind,
});
}
unsafe { Self::from_raw_parts(ptr, source) }
}
#[doc(hidden)]
unsafe fn from_raw_parts(ptr: *mut ffi::TSQuery, source: &str) -> Result<Self, QueryError> {
let ptr = {
struct TSQueryDrop(*mut ffi::TSQuery);
impl Drop for TSQueryDrop {
fn drop(&mut self) {
unsafe { ffi::ts_query_delete(self.0) }
}
}
TSQueryDrop(ptr)
};
let string_count = unsafe { ffi::ts_query_string_count(ptr.0) };
let capture_count = unsafe { ffi::ts_query_capture_count(ptr.0) };
let pattern_count = unsafe { ffi::ts_query_pattern_count(ptr.0) as usize };
let mut capture_names = Vec::with_capacity(capture_count as usize);
let mut capture_quantifiers_vec = Vec::with_capacity(pattern_count as usize);
let mut text_predicates_vec = Vec::with_capacity(pattern_count);
let mut property_predicates_vec = Vec::with_capacity(pattern_count);
let mut property_settings_vec = Vec::with_capacity(pattern_count);
let mut general_predicates_vec = Vec::with_capacity(pattern_count);
// Build a vector of strings to store the capture names.
for i in 0..capture_count {
unsafe {
let mut length = 0u32;
let name =
ffi::ts_query_capture_name_for_id(ptr.0, i, core::ptr::addr_of_mut!(length))
.cast::<u8>();
let name = slice::from_raw_parts(name, length as usize);
let name = str::from_utf8_unchecked(name);
capture_names.push(name);
}
}
// Build a vector to store capture qunatifiers.
for i in 0..pattern_count {
let mut capture_quantifiers = Vec::with_capacity(capture_count as usize);
for j in 0..capture_count {
unsafe {
let quantifier = ffi::ts_query_capture_quantifier_for_id(ptr.0, i as u32, j);
capture_quantifiers.push(quantifier.into());
}
}
capture_quantifiers_vec.push(capture_quantifiers.into());
}
// Build a vector of strings to represent literal values used in predicates.
let string_values = (0..string_count)
.map(|i| unsafe {
let mut length = 0u32;
let value =
ffi::ts_query_string_value_for_id(ptr.0, i, core::ptr::addr_of_mut!(length))
.cast::<u8>();
let value = slice::from_raw_parts(value, length as usize);
let value = str::from_utf8_unchecked(value);
value
})
.collect::<Vec<_>>();
// Build a vector of predicates for each pattern.
for i in 0..pattern_count {
let predicate_steps = unsafe {
let mut length = 0u32;
let raw_predicates = ffi::ts_query_predicates_for_pattern(
ptr.0,
i as u32,
core::ptr::addr_of_mut!(length),
);
(length > 0)
.then(|| slice::from_raw_parts(raw_predicates, length as usize))
.unwrap_or_default()
};
let byte_offset = unsafe { ffi::ts_query_start_byte_for_pattern(ptr.0, i as u32) };
let row = source
.char_indices()
.take_while(|(i, _)| *i < byte_offset as usize)
.filter(|(_, c)| *c == '\n')
.count();
use ffi::TSQueryPredicateStepType as T;
const TYPE_DONE: T = ffi::TSQueryPredicateStepTypeDone;
const TYPE_CAPTURE: T = ffi::TSQueryPredicateStepTypeCapture;
const TYPE_STRING: T = ffi::TSQueryPredicateStepTypeString;
let mut text_predicates = Vec::new();
let mut property_predicates = Vec::new();
let mut property_settings = Vec::new();
let mut general_predicates = Vec::new();
for p in predicate_steps.split(|s| s.type_ == TYPE_DONE) {
if p.is_empty() {
continue;
}
if p[0].type_ != TYPE_STRING {
return Err(predicate_error(
row,
format!(
"Expected predicate to start with a function name. Got @{}.",
capture_names[p[0].value_id as usize],
),
));
}
// Build a predicate for each of the known predicate function names.
let operator_name = string_values[p[0].value_id as usize];
match operator_name {
"eq?" | "not-eq?" | "any-eq?" | "any-not-eq?" => {
if p.len() != 3 {
return Err(predicate_error(
row,
format!(
"Wrong number of arguments to #eq? predicate. Expected 2, got {}.",
p.len() - 1
),
));
}
if p[1].type_ != TYPE_CAPTURE {
return Err(predicate_error(row, format!(
"First argument to #eq? predicate must be a capture name. Got literal \"{}\".",
string_values[p[1].value_id as usize],
)));
}
let is_positive = operator_name == "eq?" || operator_name == "any-eq?";
let match_all = match operator_name {
"eq?" | "not-eq?" => true,
"any-eq?" | "any-not-eq?" => false,
_ => unreachable!(),
};
text_predicates.push(if p[2].type_ == TYPE_CAPTURE {
TextPredicateCapture::EqCapture(
p[1].value_id,
p[2].value_id,
is_positive,
match_all,
)
} else {
TextPredicateCapture::EqString(
p[1].value_id,
string_values[p[2].value_id as usize].to_string().into(),
is_positive,
match_all,
)
});
}
"match?" | "not-match?" | "any-match?" | "any-not-match?" => {
if p.len() != 3 {
return Err(predicate_error(row, format!(
"Wrong number of arguments to #match? predicate. Expected 2, got {}.",
p.len() - 1
)));
}
if p[1].type_ != TYPE_CAPTURE {
return Err(predicate_error(row, format!(
"First argument to #match? predicate must be a capture name. Got literal \"{}\".",
string_values[p[1].value_id as usize],
)));
}
if p[2].type_ == TYPE_CAPTURE {
return Err(predicate_error(row, format!(
"Second argument to #match? predicate must be a literal. Got capture @{}.",
capture_names[p[2].value_id as usize],
)));
}
let is_positive =
operator_name == "match?" || operator_name == "any-match?";
let match_all = match operator_name {
"match?" | "not-match?" => true,
"any-match?" | "any-not-match?" => false,
_ => unreachable!(),
};
let regex = &string_values[p[2].value_id as usize];
text_predicates.push(TextPredicateCapture::MatchString(
p[1].value_id,
regex::bytes::Regex::new(regex).map_err(|_| {
predicate_error(row, format!("Invalid regex '{regex}'"))
})?,
is_positive,
match_all,
));
}
"set!" => property_settings.push(Self::parse_property(
row,
operator_name,
&capture_names,
&string_values,
&p[1..],
)?),
"is?" | "is-not?" => property_predicates.push((
Self::parse_property(
row,
operator_name,
&capture_names,
&string_values,
&p[1..],
)?,
operator_name == "is?",
)),
"any-of?" | "not-any-of?" => {
if p.len() < 2 {
return Err(predicate_error(row, format!(
"Wrong number of arguments to #any-of? predicate. Expected at least 1, got {}.",
p.len() - 1
)));
}
if p[1].type_ != TYPE_CAPTURE {
return Err(predicate_error(row, format!(
"First argument to #any-of? predicate must be a capture name. Got literal \"{}\".",
string_values[p[1].value_id as usize],
)));
}
let is_positive = operator_name == "any-of?";
let mut values = Vec::new();
for arg in &p[2..] {
if arg.type_ == TYPE_CAPTURE {
return Err(predicate_error(row, format!(
"Arguments to #any-of? predicate must be literals. Got capture @{}.",
capture_names[arg.value_id as usize],
)));
}
values.push(string_values[arg.value_id as usize]);
}
text_predicates.push(TextPredicateCapture::AnyString(
p[1].value_id,
values
.iter()
.map(|x| (*x).to_string().into())
.collect::<Vec<_>>()
.into(),
is_positive,
));
}
_ => general_predicates.push(QueryPredicate {
operator: operator_name.to_string().into(),
args: p[1..]
.iter()
.map(|a| {
if a.type_ == TYPE_CAPTURE {
QueryPredicateArg::Capture(a.value_id)
} else {
QueryPredicateArg::String(
string_values[a.value_id as usize].to_string().into(),
)
}
})
.collect(),
}),
}
}
text_predicates_vec.push(text_predicates.into());
property_predicates_vec.push(property_predicates.into());
property_settings_vec.push(property_settings.into());
general_predicates_vec.push(general_predicates.into());
}
let result = Self {
ptr: unsafe { NonNull::new_unchecked(ptr.0) },
capture_names: capture_names.into(),
capture_quantifiers: capture_quantifiers_vec.into(),
text_predicates: text_predicates_vec.into(),
property_predicates: property_predicates_vec.into(),
property_settings: property_settings_vec.into(),
general_predicates: general_predicates_vec.into(),
};
core::mem::forget(ptr);
Ok(result)
}
/// Get the byte offset where the given pattern starts in the query's
/// source.
#[doc(alias = "ts_query_start_byte_for_pattern")]
#[must_use]
pub fn start_byte_for_pattern(&self, pattern_index: usize) -> usize {
assert!(
pattern_index < self.text_predicates.len(),
"Pattern index is {pattern_index} but the pattern count is {}",
self.text_predicates.len(),
);
unsafe {
ffi::ts_query_start_byte_for_pattern(self.ptr.as_ptr(), pattern_index as u32) as usize
}
}
/// Get the byte offset where the given pattern ends in the query's
/// source.
#[doc(alias = "ts_query_end_byte_for_pattern")]
#[must_use]
pub fn end_byte_for_pattern(&self, pattern_index: usize) -> usize {
assert!(
pattern_index < self.text_predicates.len(),
"Pattern index is {pattern_index} but the pattern count is {}",
self.text_predicates.len(),
);
unsafe {
ffi::ts_query_end_byte_for_pattern(self.ptr.as_ptr(), pattern_index as u32) as usize
}
}
/// Get the number of patterns in the query.
#[doc(alias = "ts_query_pattern_count")]
#[must_use]
pub fn pattern_count(&self) -> usize {
unsafe { ffi::ts_query_pattern_count(self.ptr.as_ptr()) as usize }
}
/// Get the names of the captures used in the query.
#[must_use]
pub const fn capture_names(&self) -> &[&str] {
&self.capture_names
}
/// Get the quantifiers of the captures used in the query.
#[must_use]
pub const fn capture_quantifiers(&self, index: usize) -> &[CaptureQuantifier] {
&self.capture_quantifiers[index]
}
/// Get the index for a given capture name.
#[must_use]
pub fn capture_index_for_name(&self, name: &str) -> Option<u32> {
self.capture_names
.iter()
.position(|n| *n == name)
.map(|ix| ix as u32)
}
/// Get the properties that are checked for the given pattern index.
///
/// This includes predicates with the operators `is?` and `is-not?`.
#[must_use]
pub const fn property_predicates(&self, index: usize) -> &[(QueryProperty, bool)] {
&self.property_predicates[index]
}
/// Get the properties that are set for the given pattern index.
///
/// This includes predicates with the operator `set!`.
#[must_use]
pub const fn property_settings(&self, index: usize) -> &[QueryProperty] {
&self.property_settings[index]
}
/// Get the other user-defined predicates associated with the given index.
///
/// This includes predicate with operators other than:
/// * `match?`
/// * `eq?` and `not-eq?`
/// * `is?` and `is-not?`
/// * `set!`
#[must_use]
pub const fn general_predicates(&self, index: usize) -> &[QueryPredicate] {
&self.general_predicates[index]
}
/// Disable a certain capture within a query.
///
/// This prevents the capture from being returned in matches, and also
/// avoids any resource usage associated with recording the capture.
#[doc(alias = "ts_query_disable_capture")]
pub fn disable_capture(&mut self, name: &str) {
unsafe {
ffi::ts_query_disable_capture(
self.ptr.as_ptr(),
name.as_bytes().as_ptr().cast::<c_char>(),
name.len() as u32,
);
}
}
/// Disable a certain pattern within a query.
///
/// This prevents the pattern from matching, and also avoids any resource
/// usage associated with the pattern.
#[doc(alias = "ts_query_disable_pattern")]
pub fn disable_pattern(&mut self, index: usize) {
unsafe { ffi::ts_query_disable_pattern(self.ptr.as_ptr(), index as u32) }
}
/// Check if a given pattern within a query has a single root node.
#[doc(alias = "ts_query_is_pattern_rooted")]
#[must_use]
pub fn is_pattern_rooted(&self, index: usize) -> bool {
unsafe { ffi::ts_query_is_pattern_rooted(self.ptr.as_ptr(), index as u32) }
}
/// Check if a given pattern within a query has a single root node.
#[doc(alias = "ts_query_is_pattern_non_local")]
#[must_use]
pub fn is_pattern_non_local(&self, index: usize) -> bool {
unsafe { ffi::ts_query_is_pattern_non_local(self.ptr.as_ptr(), index as u32) }
}
/// Check if a given step in a query is 'definite'.
///
/// A query step is 'definite' if its parent pattern will be guaranteed to
/// match successfully once it reaches the step.
#[doc(alias = "ts_query_is_pattern_guaranteed_at_step")]
#[must_use]
pub fn is_pattern_guaranteed_at_step(&self, byte_offset: usize) -> bool {
unsafe {
ffi::ts_query_is_pattern_guaranteed_at_step(self.ptr.as_ptr(), byte_offset as u32)
}
}
fn parse_property(
row: usize,
function_name: &str,
capture_names: &[&str],
string_values: &[&str],
args: &[ffi::TSQueryPredicateStep],
) -> Result<QueryProperty, QueryError> {
if args.is_empty() || args.len() > 3 {
return Err(predicate_error(
row,
format!(
"Wrong number of arguments to {function_name} predicate. Expected 1 to 3, got {}.",
args.len(),
),
));
}
let mut capture_id = None;
let mut key = None;
let mut value = None;
for arg in args {
if arg.type_ == ffi::TSQueryPredicateStepTypeCapture {
if capture_id.is_some() {
return Err(predicate_error(
row,
format!(
"Invalid arguments to {function_name} predicate. Unexpected second capture name @{}",
capture_names[arg.value_id as usize]
),
));
}
capture_id = Some(arg.value_id as usize);
} else if key.is_none() {
key = Some(&string_values[arg.value_id as usize]);
} else if value.is_none() {
value = Some(string_values[arg.value_id as usize]);
} else {
return Err(predicate_error(
row,
format!(
"Invalid arguments to {function_name} predicate. Unexpected third argument @{}",
string_values[arg.value_id as usize]
),
));
}
}
if let Some(key) = key {
Ok(QueryProperty::new(key, value, capture_id))
} else {
Err(predicate_error(
row,
format!("Invalid arguments to {function_name} predicate. Missing key argument",),
))
}
}
}
impl Default for QueryCursor {
fn default() -> Self {
Self::new()
}
}
impl QueryCursor {
/// Create a new cursor for executing a given query.
///
/// The cursor stores the state that is needed to iteratively search for
/// matches.
#[doc(alias = "ts_query_cursor_new")]
#[must_use]
pub fn new() -> Self {
Self {
ptr: unsafe { NonNull::new_unchecked(ffi::ts_query_cursor_new()) },
}
}
/// Return the maximum number of in-progress matches for this cursor.
#[doc(alias = "ts_query_cursor_match_limit")]
#[must_use]
pub fn match_limit(&self) -> u32 {
unsafe { ffi::ts_query_cursor_match_limit(self.ptr.as_ptr()) }
}
/// Set the maximum number of in-progress matches for this cursor. The
/// limit must be > 0 and <= 65536.
#[doc(alias = "ts_query_cursor_set_match_limit")]
pub fn set_match_limit(&mut self, limit: u32) {
unsafe {
ffi::ts_query_cursor_set_match_limit(self.ptr.as_ptr(), limit);
}
}
/// Set the maximum duration in microseconds that query execution should be allowed to
/// take before halting.
///
/// If query execution takes longer than this, it will halt early, returning None.
#[doc(alias = "ts_query_cursor_set_timeout_micros")]
pub fn set_timeout_micros(&mut self, timeout: u64) {
unsafe {
ffi::ts_query_cursor_set_timeout_micros(self.ptr.as_ptr(), timeout);
}
}
/// Get the duration in microseconds that query execution is allowed to take.
///
/// This is set via [`set_timeout_micros`](QueryCursor::set_timeout_micros).
#[doc(alias = "ts_query_cursor_timeout_micros")]
#[must_use]
pub fn timeout_micros(&self) -> u64 {
unsafe { ffi::ts_query_cursor_timeout_micros(self.ptr.as_ptr()) }
}
/// Check if, on its last execution, this cursor exceeded its maximum number
/// of in-progress matches.
#[doc(alias = "ts_query_cursor_did_exceed_match_limit")]
#[must_use]
pub fn did_exceed_match_limit(&self) -> bool {
unsafe { ffi::ts_query_cursor_did_exceed_match_limit(self.ptr.as_ptr()) }
}
/// Iterate over all of the matches in the order that they were found.
///
/// Each match contains the index of the pattern that matched, and a list of
/// captures. Because multiple patterns can match the same set of nodes,
/// one match may contain captures that appear *before* some of the
/// captures from a previous match.
#[doc(alias = "ts_query_cursor_exec")]
pub fn matches<'query, 'cursor: 'query, 'tree, T: TextProvider<I>, I: AsRef<[u8]>>(
&'cursor mut self,
query: &'query Query,
node: Node<'tree>,
text_provider: T,
) -> QueryMatches<'query, 'tree, T, I> {
let ptr = self.ptr.as_ptr();
unsafe { ffi::ts_query_cursor_exec(ptr, query.ptr.as_ptr(), node.0) };
QueryMatches {
ptr,
query,
text_provider,
buffer1: Vec::default(),
buffer2: Vec::default(),
current_match: None,
_phantom: PhantomData,
}
}
/// Iterate over all of the individual captures in the order that they
/// appear.
///
/// This is useful if you don't care about which pattern matched, and just
/// want a single, ordered sequence of captures.
#[doc(alias = "ts_query_cursor_exec")]
pub fn captures<'query, 'cursor: 'query, 'tree, T: TextProvider<I>, I: AsRef<[u8]>>(
&'cursor mut self,
query: &'query Query,
node: Node<'tree>,
text_provider: T,
) -> QueryCaptures<'query, 'tree, T, I> {
let ptr = self.ptr.as_ptr();
unsafe { ffi::ts_query_cursor_exec(ptr, query.ptr.as_ptr(), node.0) };
QueryCaptures {
ptr,
query,
text_provider,
buffer1: Vec::default(),
buffer2: Vec::default(),
current_match: None,
_phantom: PhantomData,
}
}
/// Set the range in which the query will be executed, in terms of byte
/// offsets.
#[doc(alias = "ts_query_cursor_set_byte_range")]
pub fn set_byte_range(&mut self, range: ops::Range<usize>) -> &mut Self {
unsafe {
ffi::ts_query_cursor_set_byte_range(
self.ptr.as_ptr(),
range.start as u32,
range.end as u32,
);
}
self
}
/// Set the range in which the query will be executed, in terms of rows and
/// columns.
#[doc(alias = "ts_query_cursor_set_point_range")]
pub fn set_point_range(&mut self, range: ops::Range<Point>) -> &mut Self {
unsafe {
ffi::ts_query_cursor_set_point_range(
self.ptr.as_ptr(),
range.start.into(),
range.end.into(),
);
}
self
}
/// Set the maximum start depth for a query cursor.
///
/// This prevents cursors from exploring children nodes at a certain depth.
/// Note if a pattern includes many children, then they will still be
/// checked.
///
/// The zero max start depth value can be used as a special behavior and
/// it helps to destructure a subtree by staying on a node and using
/// captures for interested parts. Note that the zero max start depth
/// only limit a search depth for a pattern's root node but other nodes
/// that are parts of the pattern may be searched at any depth what
/// defined by the pattern structure.
///
/// Set to `None` to remove the maximum start depth.
#[doc(alias = "ts_query_cursor_set_max_start_depth")]
pub fn set_max_start_depth(&mut self, max_start_depth: Option<u32>) -> &mut Self {
unsafe {
ffi::ts_query_cursor_set_max_start_depth(
self.ptr.as_ptr(),
max_start_depth.unwrap_or(u32::MAX),
);
}
self
}
}
impl<'tree> QueryMatch<'_, 'tree> {
#[must_use]
pub const fn id(&self) -> u32 {
self.id
}
#[doc(alias = "ts_query_cursor_remove_match")]
pub fn remove(&self) {
unsafe { ffi::ts_query_cursor_remove_match(self.cursor, self.id) }
}
pub fn nodes_for_capture_index(
&self,
capture_ix: u32,
) -> impl Iterator<Item = Node<'tree>> + '_ {
self.captures
.iter()
.filter_map(move |capture| (capture.index == capture_ix).then_some(capture.node))
}
fn new(m: &ffi::TSQueryMatch, cursor: *mut ffi::TSQueryCursor) -> Self {
QueryMatch {
cursor,
id: m.id,
pattern_index: m.pattern_index as usize,
captures: (m.capture_count > 0)
.then(|| unsafe {
slice::from_raw_parts(
m.captures.cast::<QueryCapture<'tree>>(),
m.capture_count as usize,
)
})
.unwrap_or_default(),
}
}
pub fn satisfies_text_predicates<I: AsRef<[u8]>>(
&self,
query: &Query,
buffer1: &mut Vec<u8>,
buffer2: &mut Vec<u8>,
text_provider: &mut impl TextProvider<I>,
) -> bool {
struct NodeText<'a, T> {
buffer: &'a mut Vec<u8>,
first_chunk: Option<T>,
}
impl<'a, T: AsRef<[u8]>> NodeText<'a, T> {
fn new(buffer: &'a mut Vec<u8>) -> Self {
Self {
buffer,
first_chunk: None,
}
}
fn get_text(&mut self, chunks: &mut impl Iterator<Item = T>) -> &[u8] {
self.first_chunk = chunks.next();
if let Some(next_chunk) = chunks.next() {
self.buffer.clear();
self.buffer
.extend_from_slice(self.first_chunk.as_ref().unwrap().as_ref());
self.buffer.extend_from_slice(next_chunk.as_ref());
for chunk in chunks {
self.buffer.extend_from_slice(chunk.as_ref());
}
self.buffer.as_slice()
} else if let Some(ref first_chunk) = self.first_chunk {
first_chunk.as_ref()
} else {
&[]
}
}
}
let mut node_text1 = NodeText::new(buffer1);
let mut node_text2 = NodeText::new(buffer2);
query.text_predicates[self.pattern_index]
.iter()
.all(|predicate| match predicate {
TextPredicateCapture::EqCapture(i, j, is_positive, match_all_nodes) => {
let mut nodes_1 = self.nodes_for_capture_index(*i);
let mut nodes_2 = self.nodes_for_capture_index(*j);
while let (Some(node1), Some(node2)) = (nodes_1.next(), nodes_2.next()) {
let mut text1 = text_provider.text(node1);
let mut text2 = text_provider.text(node2);
let text1 = node_text1.get_text(&mut text1);
let text2 = node_text2.get_text(&mut text2);
let is_positive_match = text1 == text2;
if is_positive_match != *is_positive && *match_all_nodes {
return false;
}
if is_positive_match == *is_positive && !*match_all_nodes {
return true;
}
}
nodes_1.next().is_none() && nodes_2.next().is_none()
}
TextPredicateCapture::EqString(i, s, is_positive, match_all_nodes) => {
let nodes = self.nodes_for_capture_index(*i);
for node in nodes {
let mut text = text_provider.text(node);
let text = node_text1.get_text(&mut text);
let is_positive_match = text == s.as_bytes();
if is_positive_match != *is_positive && *match_all_nodes {
return false;
}
if is_positive_match == *is_positive && !*match_all_nodes {
return true;
}
}
true
}
TextPredicateCapture::MatchString(i, r, is_positive, match_all_nodes) => {
let nodes = self.nodes_for_capture_index(*i);
for node in nodes {
let mut text = text_provider.text(node);
let text = node_text1.get_text(&mut text);
let is_positive_match = r.is_match(text);
if is_positive_match != *is_positive && *match_all_nodes {
return false;
}
if is_positive_match == *is_positive && !*match_all_nodes {
return true;
}
}
true
}
TextPredicateCapture::AnyString(i, v, is_positive) => {
let nodes = self.nodes_for_capture_index(*i);
for node in nodes {
let mut text = text_provider.text(node);
let text = node_text1.get_text(&mut text);
if (v.iter().any(|s| text == s.as_bytes())) != *is_positive {
return false;
}
}
true
}
})
}
}
impl QueryProperty {
#[must_use]
pub fn new(key: &str, value: Option<&str>, capture_id: Option<usize>) -> Self {
Self {
capture_id,
key: key.to_string().into(),
value: value.map(|s| s.to_string().into()),
}
}
}
/// Provide StreamingIterator instead of traditional one as the underlying object in the C library
/// gets updated on each iteration. Created copies would have their internal state overwritten,
/// leading to Undefined Behavior
impl<'query, 'tree: 'query, T: TextProvider<I>, I: AsRef<[u8]>> StreamingIterator
for QueryMatches<'query, 'tree, T, I>
{
type Item = QueryMatch<'query, 'tree>;
fn advance(&mut self) {
self.current_match = unsafe {
loop {
let mut m = MaybeUninit::<ffi::TSQueryMatch>::uninit();
if ffi::ts_query_cursor_next_match(self.ptr, m.as_mut_ptr()) {
let result = QueryMatch::new(&m.assume_init(), self.ptr);
if result.satisfies_text_predicates(
self.query,
&mut self.buffer1,
&mut self.buffer2,
&mut self.text_provider,
) {
break Some(result);
}
} else {
break None;
}
}
};
}
fn get(&self) -> Option<&Self::Item> {
self.current_match.as_ref()
}
}
impl<'query, 'tree: 'query, T: TextProvider<I>, I: AsRef<[u8]>> StreamingIteratorMut
for QueryMatches<'query, 'tree, T, I>
{
fn get_mut(&mut self) -> Option<&mut Self::Item> {
self.current_match.as_mut()
}
}
impl<'query, 'tree: 'query, T: TextProvider<I>, I: AsRef<[u8]>> StreamingIterator
for QueryCaptures<'query, 'tree, T, I>
{
type Item = (QueryMatch<'query, 'tree>, usize);
fn advance(&mut self) {
self.current_match = unsafe {
loop {
let mut capture_index = 0u32;
let mut m = MaybeUninit::<ffi::TSQueryMatch>::uninit();
if ffi::ts_query_cursor_next_capture(
self.ptr,
m.as_mut_ptr(),
core::ptr::addr_of_mut!(capture_index),
) {
let result = QueryMatch::new(&m.assume_init(), self.ptr);
if result.satisfies_text_predicates(
self.query,
&mut self.buffer1,
&mut self.buffer2,
&mut self.text_provider,
) {
break Some((result, capture_index as usize));
}
result.remove();
} else {
break None;
}
}
}
}
fn get(&self) -> Option<&Self::Item> {
self.current_match.as_ref()
}
}
impl<'query, 'tree: 'query, T: TextProvider<I>, I: AsRef<[u8]>> StreamingIteratorMut
for QueryCaptures<'query, 'tree, T, I>
{
fn get_mut(&mut self) -> Option<&mut Self::Item> {
self.current_match.as_mut()
}
}
impl<T: TextProvider<I>, I: AsRef<[u8]>> QueryMatches<'_, '_, T, I> {
#[doc(alias = "ts_query_cursor_set_byte_range")]
pub fn set_byte_range(&mut self, range: ops::Range<usize>) {
unsafe {
ffi::ts_query_cursor_set_byte_range(self.ptr, range.start as u32, range.end as u32);
}
}
#[doc(alias = "ts_query_cursor_set_point_range")]
pub fn set_point_range(&mut self, range: ops::Range<Point>) {
unsafe {
ffi::ts_query_cursor_set_point_range(self.ptr, range.start.into(), range.end.into());
}
}
}
impl<T: TextProvider<I>, I: AsRef<[u8]>> QueryCaptures<'_, '_, T, I> {
#[doc(alias = "ts_query_cursor_set_byte_range")]
pub fn set_byte_range(&mut self, range: ops::Range<usize>) {
unsafe {
ffi::ts_query_cursor_set_byte_range(self.ptr, range.start as u32, range.end as u32);
}
}
#[doc(alias = "ts_query_cursor_set_point_range")]
pub fn set_point_range(&mut self, range: ops::Range<Point>) {
unsafe {
ffi::ts_query_cursor_set_point_range(self.ptr, range.start.into(), range.end.into());
}
}
}
impl fmt::Debug for QueryMatch<'_, '_> {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"QueryMatch {{ id: {}, pattern_index: {}, captures: {:?} }}",
self.id, self.pattern_index, self.captures
)
}
}
impl<F, R, I> TextProvider<I> for F
where
F: FnMut(Node) -> R,
R: Iterator<Item = I>,
I: AsRef<[u8]>,
{
type I = R;
fn text(&mut self, node: Node) -> Self::I {
(self)(node)
}
}
impl<'a> TextProvider<&'a [u8]> for &'a [u8] {
type I = iter::Once<&'a [u8]>;
fn text(&mut self, node: Node) -> Self::I {
iter::once(&self[node.byte_range()])
}
}
impl PartialEq for Query {
fn eq(&self, other: &Self) -> bool {
self.ptr == other.ptr
}
}
impl Drop for Query {
fn drop(&mut self) {
unsafe { ffi::ts_query_delete(self.ptr.as_ptr()) }
}
}
impl Drop for QueryCursor {
fn drop(&mut self) {
unsafe { ffi::ts_query_cursor_delete(self.ptr.as_ptr()) }
}
}
impl Point {
#[must_use]
pub const fn new(row: usize, column: usize) -> Self {
Self { row, column }
}
}
impl fmt::Display for Point {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "({}, {})", self.row, self.column)
}
}
impl From<Point> for ffi::TSPoint {
fn from(val: Point) -> Self {
Self {
row: val.row as u32,
column: val.column as u32,
}
}
}
impl From<ffi::TSPoint> for Point {
fn from(point: ffi::TSPoint) -> Self {
Self {
row: point.row as usize,
column: point.column as usize,
}
}
}
impl From<Range> for ffi::TSRange {
fn from(val: Range) -> Self {
Self {
start_byte: val.start_byte as u32,
end_byte: val.end_byte as u32,
start_point: val.start_point.into(),
end_point: val.end_point.into(),
}
}
}
impl From<ffi::TSRange> for Range {
fn from(range: ffi::TSRange) -> Self {
Self {
start_byte: range.start_byte as usize,
end_byte: range.end_byte as usize,
start_point: range.start_point.into(),
end_point: range.end_point.into(),
}
}
}
impl From<&'_ InputEdit> for ffi::TSInputEdit {
fn from(val: &'_ InputEdit) -> Self {
Self {
start_byte: val.start_byte as u32,
old_end_byte: val.old_end_byte as u32,
new_end_byte: val.new_end_byte as u32,
start_point: val.start_position.into(),
old_end_point: val.old_end_position.into(),
new_end_point: val.new_end_position.into(),
}
}
}
impl<'a> LossyUtf8<'a> {
#[must_use]
pub const fn new(bytes: &'a [u8]) -> Self {
LossyUtf8 {
bytes,
in_replacement: false,
}
}
}
impl<'a> Iterator for LossyUtf8<'a> {
type Item = &'a str;
fn next(&mut self) -> Option<&'a str> {
if self.bytes.is_empty() {
return None;
}
if self.in_replacement {
self.in_replacement = false;
return Some("\u{fffd}");
}
match core::str::from_utf8(self.bytes) {
Ok(valid) => {
self.bytes = &[];
Some(valid)
}
Err(error) => {
if let Some(error_len) = error.error_len() {
let error_start = error.valid_up_to();
if error_start > 0 {
let result =
unsafe { core::str::from_utf8_unchecked(&self.bytes[..error_start]) };
self.bytes = &self.bytes[(error_start + error_len)..];
self.in_replacement = true;
Some(result)
} else {
self.bytes = &self.bytes[error_len..];
Some("\u{fffd}")
}
} else {
None
}
}
}
}
}
#[must_use]
const fn predicate_error(row: usize, message: String) -> QueryError {
QueryError {
kind: QueryErrorKind::Predicate,
row,
column: 0,
offset: 0,
message,
}
}
impl fmt::Display for IncludedRangesError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "Incorrect range by index: {}", self.0)
}
}
impl fmt::Display for LanguageError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"Incompatible language version {}. Expected minimum {}, maximum {}",
self.version, MIN_COMPATIBLE_LANGUAGE_VERSION, LANGUAGE_VERSION,
)
}
}
impl fmt::Display for QueryError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let msg = match self.kind {
QueryErrorKind::Field => "Invalid field name ",
QueryErrorKind::NodeType => "Invalid node type ",
QueryErrorKind::Capture => "Invalid capture name ",
QueryErrorKind::Predicate => "Invalid predicate: ",
QueryErrorKind::Structure => "Impossible pattern:\n",
QueryErrorKind::Syntax => "Invalid syntax:\n",
QueryErrorKind::Language => "",
};
if msg.is_empty() {
write!(f, "{}", self.message)
} else {
write!(
f,
"Query error at {}:{}. {}{}",
self.row + 1,
self.column + 1,
msg,
self.message
)
}
}
}
#[doc(hidden)]
#[must_use]
pub fn format_sexp(sexp: &str, initial_indent_level: usize) -> String {
let mut indent_level = initial_indent_level;
let mut formatted = String::new();
let mut has_field = false;
let mut c_iter = sexp.chars().peekable();
let mut s = String::with_capacity(sexp.len());
let mut quote = '\0';
let mut saw_paren = false;
let mut did_last = false;
let mut fetch_next_str = |next: &mut String| {
next.clear();
while let Some(c) = c_iter.next() {
if c == '\'' || c == '"' {
quote = c;
} else if c == ' ' || (c == ')' && quote != '\0') {
if let Some(next_c) = c_iter.peek() {
if *next_c == quote {
next.push(c);
next.push(*next_c);
c_iter.next();
quote = '\0';
continue;
}
}
break;
}
if c == ')' {
saw_paren = true;
break;
}
next.push(c);
}
// at the end
if c_iter.peek().is_none() && next.is_empty() {
if saw_paren {
// but did we see a ) before ending?
saw_paren = false;
return Some(());
}
if !did_last {
// but did we account for the end empty string as if we're splitting?
did_last = true;
return Some(());
}
return None;
}
Some(())
};
while fetch_next_str(&mut s).is_some() {
if s.is_empty() && indent_level > 0 {
// ")"
indent_level -= 1;
write!(formatted, ")").unwrap();
} else if s.starts_with('(') {
if has_field {
has_field = false;
} else {
if indent_level > 0 {
writeln!(formatted).unwrap();
for _ in 0..indent_level {
write!(formatted, " ").unwrap();
}
}
indent_level += 1;
}
// "(node_name"
write!(formatted, "{s}").unwrap();
// "(MISSING node_name" or "(UNEXPECTED 'x'"
if s.starts_with("(MISSING") || s.starts_with("(UNEXPECTED") {
fetch_next_str(&mut s).unwrap();
if s.is_empty() {
while indent_level > 0 {
indent_level -= 1;
write!(formatted, ")").unwrap();
}
} else {
write!(formatted, " {s}").unwrap();
}
}
} else if s.ends_with(':') {
// "field:"
writeln!(formatted).unwrap();
for _ in 0..indent_level {
write!(formatted, " ").unwrap();
}
write!(formatted, "{s} ").unwrap();
has_field = true;
indent_level += 1;
}
}
formatted
}
pub fn wasm_stdlib_symbols() -> impl Iterator<Item = &'static str> {
const WASM_STDLIB_SYMBOLS: &str = include_str!(concat!(env!("OUT_DIR"), "/stdlib-symbols.txt"));
WASM_STDLIB_SYMBOLS
.lines()
.map(|s| s.trim_matches(|c| c == '"' || c == ','))
}
extern "C" {
fn free(ptr: *mut c_void);
}
static mut FREE_FN: unsafe extern "C" fn(ptr: *mut c_void) = free;
/// Sets the memory allocation functions that the core library should use.
///
/// # Safety
///
/// This function uses FFI and mutates a static global.
#[doc(alias = "ts_set_allocator")]
pub unsafe fn set_allocator(
new_malloc: Option<unsafe extern "C" fn(usize) -> *mut c_void>,
new_calloc: Option<unsafe extern "C" fn(usize, usize) -> *mut c_void>,
new_realloc: Option<unsafe extern "C" fn(*mut c_void, usize) -> *mut c_void>,
new_free: Option<unsafe extern "C" fn(*mut c_void)>,
) {
FREE_FN = new_free.unwrap_or(free);
ffi::ts_set_allocator(new_malloc, new_calloc, new_realloc, new_free);
}
#[cfg(feature = "std")]
impl error::Error for IncludedRangesError {}
#[cfg(feature = "std")]
impl error::Error for LanguageError {}
#[cfg(feature = "std")]
impl error::Error for QueryError {}
unsafe impl Send for Language {}
unsafe impl Sync for Language {}
unsafe impl Send for Node<'_> {}
unsafe impl Sync for Node<'_> {}
unsafe impl Send for LookaheadIterator {}
unsafe impl Sync for LookaheadIterator {}
unsafe impl Send for LookaheadNamesIterator<'_> {}
unsafe impl Sync for LookaheadNamesIterator<'_> {}
unsafe impl Send for Parser {}
unsafe impl Sync for Parser {}
unsafe impl Send for Query {}
unsafe impl Sync for Query {}
unsafe impl Send for QueryCursor {}
unsafe impl Sync for QueryCursor {}
unsafe impl Send for Tree {}
unsafe impl Sync for Tree {}
unsafe impl Send for TreeCursor<'_> {}
unsafe impl Sync for TreeCursor<'_> {}