/usr/lib/python2.7/dist-packages/pyparsing.py is in python-pyparsing 2.1.10+dfsg1-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 | # module pyparsing.py
#
# Copyright (c) 2003-2016 Paul T. McGuire
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#
__doc__ = \
"""
pyparsing module - Classes and methods to define and execute parsing grammars
The pyparsing module is an alternative approach to creating and executing simple grammars,
vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you
don't need to learn a new syntax for defining grammars or matching expressions - the parsing module
provides a library of classes that you use to construct the grammar directly in Python.
Here is a program to parse "Hello, World!" (or any greeting of the form
C{"<salutation>, <addressee>!"}), built up using L{Word}, L{Literal}, and L{And} elements
(L{'+'<ParserElement.__add__>} operator gives L{And} expressions, strings are auto-converted to
L{Literal} expressions)::
from pyparsing import Word, alphas
# define grammar of a greeting
greet = Word(alphas) + "," + Word(alphas) + "!"
hello = "Hello, World!"
print (hello, "->", greet.parseString(hello))
The program outputs the following::
Hello, World! -> ['Hello', ',', 'World', '!']
The Python representation of the grammar is quite readable, owing to the self-explanatory
class names, and the use of '+', '|' and '^' operators.
The L{ParseResults} object returned from L{ParserElement.parseString<ParserElement.parseString>} can be accessed as a nested list, a dictionary, or an
object with named attributes.
The pyparsing module handles some of the problems that are typically vexing when writing text parsers:
- extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.)
- quoted strings
- embedded comments
"""
__version__ = "2.1.10"
__versionTime__ = "07 Oct 2016 01:31 UTC"
__author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"
import string
from weakref import ref as wkref
import copy
import sys
import warnings
import re
import sre_constants
import collections
import pprint
import traceback
import types
from datetime import datetime
try:
from _thread import RLock
except ImportError:
from threading import RLock
try:
from collections import OrderedDict as _OrderedDict
except ImportError:
try:
from ordereddict import OrderedDict as _OrderedDict
except ImportError:
_OrderedDict = None
#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )
__all__ = [
'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty',
'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal',
'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or',
'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException',
'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException',
'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter',
'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore',
'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col',
'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString',
'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums',
'htmlComment', 'javaStyleComment', 'line', 'lineEnd', 'lineStart', 'lineno',
'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral',
'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables',
'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity',
'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd',
'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute',
'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation','locatedExpr', 'withClass',
'CloseMatch', 'tokenMap', 'pyparsing_common',
]
system_version = tuple(sys.version_info)[:3]
PY_3 = system_version[0] == 3
if PY_3:
_MAX_INT = sys.maxsize
basestring = str
unichr = chr
_ustr = str
# build list of single arg builtins, that can be used as parse actions
singleArgBuiltins = [sum, len, sorted, reversed, list, tuple, set, any, all, min, max]
else:
_MAX_INT = sys.maxint
range = xrange
def _ustr(obj):
"""Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries
str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It
then < returns the unicode object | encodes it with the default encoding | ... >.
"""
if isinstance(obj,unicode):
return obj
try:
# If this works, then _ustr(obj) has the same behaviour as str(obj), so
# it won't break any existing code.
return str(obj)
except UnicodeEncodeError:
# Else encode it
ret = unicode(obj).encode(sys.getdefaultencoding(), 'xmlcharrefreplace')
xmlcharref = Regex('&#\d+;')
xmlcharref.setParseAction(lambda t: '\\u' + hex(int(t[0][2:-1]))[2:])
return xmlcharref.transformString(ret)
# build list of single arg builtins, tolerant of Python version, that can be used as parse actions
singleArgBuiltins = []
import __builtin__
for fname in "sum len sorted reversed list tuple set any all min max".split():
try:
singleArgBuiltins.append(getattr(__builtin__,fname))
except AttributeError:
continue
_generatorType = type((y for y in range(1)))
def _xml_escape(data):
"""Escape &, <, >, ", ', etc. in a string of data."""
# ampersand must be replaced first
from_symbols = '&><"\''
to_symbols = ('&'+s+';' for s in "amp gt lt quot apos".split())
for from_,to_ in zip(from_symbols, to_symbols):
data = data.replace(from_, to_)
return data
class _Constants(object):
pass
alphas = string.ascii_uppercase + string.ascii_lowercase
nums = "0123456789"
hexnums = nums + "ABCDEFabcdef"
alphanums = alphas + nums
_bslash = chr(92)
printables = "".join(c for c in string.printable if c not in string.whitespace)
class ParseBaseException(Exception):
"""base exception class for all parsing runtime exceptions"""
# Performance tuning: we construct a *lot* of these, so keep this
# constructor as small and fast as possible
def __init__( self, pstr, loc=0, msg=None, elem=None ):
self.loc = loc
if msg is None:
self.msg = pstr
self.pstr = ""
else:
self.msg = msg
self.pstr = pstr
self.parserElement = elem
self.args = (pstr, loc, msg)
@classmethod
def _from_exception(cls, pe):
"""
internal factory method to simplify creating one type of ParseException
from another - avoids having __init__ signature conflicts among subclasses
"""
return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement)
def __getattr__( self, aname ):
"""supported attributes by name are:
- lineno - returns the line number of the exception text
- col - returns the column number of the exception text
- line - returns the line containing the exception text
"""
if( aname == "lineno" ):
return lineno( self.loc, self.pstr )
elif( aname in ("col", "column") ):
return col( self.loc, self.pstr )
elif( aname == "line" ):
return line( self.loc, self.pstr )
else:
raise AttributeError(aname)
def __str__( self ):
return "%s (at char %d), (line:%d, col:%d)" % \
( self.msg, self.loc, self.lineno, self.column )
def __repr__( self ):
return _ustr(self)
def markInputline( self, markerString = ">!<" ):
"""Extracts the exception line from the input string, and marks
the location of the exception with a special symbol.
"""
line_str = self.line
line_column = self.column - 1
if markerString:
line_str = "".join((line_str[:line_column],
markerString, line_str[line_column:]))
return line_str.strip()
def __dir__(self):
return "lineno col line".split() + dir(type(self))
class ParseException(ParseBaseException):
"""
Exception thrown when parse expressions don't match class;
supported attributes by name are:
- lineno - returns the line number of the exception text
- col - returns the column number of the exception text
- line - returns the line containing the exception text
Example::
try:
Word(nums).setName("integer").parseString("ABC")
except ParseException as pe:
print(pe)
print("column: {}".format(pe.col))
prints::
Expected integer (at char 0), (line:1, col:1)
column: 1
"""
pass
class ParseFatalException(ParseBaseException):
"""user-throwable exception thrown when inconsistent parse content
is found; stops all parsing immediately"""
pass
class ParseSyntaxException(ParseFatalException):
"""just like L{ParseFatalException}, but thrown internally when an
L{ErrorStop<And._ErrorStop>} ('-' operator) indicates that parsing is to stop
immediately because an unbacktrackable syntax error has been found"""
pass
#~ class ReparseException(ParseBaseException):
#~ """Experimental class - parse actions can raise this exception to cause
#~ pyparsing to reparse the input string:
#~ - with a modified input string, and/or
#~ - with a modified start location
#~ Set the values of the ReparseException in the constructor, and raise the
#~ exception in a parse action to cause pyparsing to use the new string/location.
#~ Setting the values as None causes no change to be made.
#~ """
#~ def __init_( self, newstring, restartLoc ):
#~ self.newParseText = newstring
#~ self.reparseLoc = restartLoc
class RecursiveGrammarException(Exception):
"""exception thrown by L{ParserElement.validate} if the grammar could be improperly recursive"""
def __init__( self, parseElementList ):
self.parseElementTrace = parseElementList
def __str__( self ):
return "RecursiveGrammarException: %s" % self.parseElementTrace
class _ParseResultsWithOffset(object):
def __init__(self,p1,p2):
self.tup = (p1,p2)
def __getitem__(self,i):
return self.tup[i]
def __repr__(self):
return repr(self.tup[0])
def setOffset(self,i):
self.tup = (self.tup[0],i)
class ParseResults(object):
"""
Structured parse results, to provide multiple means of access to the parsed data:
- as a list (C{len(results)})
- by list index (C{results[0], results[1]}, etc.)
- by attribute (C{results.<resultsName>} - see L{ParserElement.setResultsName})
Example::
integer = Word(nums)
date_str = (integer.setResultsName("year") + '/'
+ integer.setResultsName("month") + '/'
+ integer.setResultsName("day"))
# equivalent form:
# date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
# parseString returns a ParseResults object
result = date_str.parseString("1999/12/31")
def test(s, fn=repr):
print("%s -> %s" % (s, fn(eval(s))))
test("list(result)")
test("result[0]")
test("result['month']")
test("result.day")
test("'month' in result")
test("'minutes' in result")
test("result.dump()", str)
prints::
list(result) -> ['1999', '/', '12', '/', '31']
result[0] -> '1999'
result['month'] -> '12'
result.day -> '31'
'month' in result -> True
'minutes' in result -> False
result.dump() -> ['1999', '/', '12', '/', '31']
- day: 31
- month: 12
- year: 1999
"""
def __new__(cls, toklist=None, name=None, asList=True, modal=True ):
if isinstance(toklist, cls):
return toklist
retobj = object.__new__(cls)
retobj.__doinit = True
return retobj
# Performance tuning: we construct a *lot* of these, so keep this
# constructor as small and fast as possible
def __init__( self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance ):
if self.__doinit:
self.__doinit = False
self.__name = None
self.__parent = None
self.__accumNames = {}
self.__asList = asList
self.__modal = modal
if toklist is None:
toklist = []
if isinstance(toklist, list):
self.__toklist = toklist[:]
elif isinstance(toklist, _generatorType):
self.__toklist = list(toklist)
else:
self.__toklist = [toklist]
self.__tokdict = dict()
if name is not None and name:
if not modal:
self.__accumNames[name] = 0
if isinstance(name,int):
name = _ustr(name) # will always return a str, but use _ustr for consistency
self.__name = name
if not (isinstance(toklist, (type(None), basestring, list)) and toklist in (None,'',[])):
if isinstance(toklist,basestring):
toklist = [ toklist ]
if asList:
if isinstance(toklist,ParseResults):
self[name] = _ParseResultsWithOffset(toklist.copy(),0)
else:
self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0)
self[name].__name = name
else:
try:
self[name] = toklist[0]
except (KeyError,TypeError,IndexError):
self[name] = toklist
def __getitem__( self, i ):
if isinstance( i, (int,slice) ):
return self.__toklist[i]
else:
if i not in self.__accumNames:
return self.__tokdict[i][-1][0]
else:
return ParseResults([ v[0] for v in self.__tokdict[i] ])
def __setitem__( self, k, v, isinstance=isinstance ):
if isinstance(v,_ParseResultsWithOffset):
self.__tokdict[k] = self.__tokdict.get(k,list()) + [v]
sub = v[0]
elif isinstance(k,(int,slice)):
self.__toklist[k] = v
sub = v
else:
self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)]
sub = v
if isinstance(sub,ParseResults):
sub.__parent = wkref(self)
def __delitem__( self, i ):
if isinstance(i,(int,slice)):
mylen = len( self.__toklist )
del self.__toklist[i]
# convert int to slice
if isinstance(i, int):
if i < 0:
i += mylen
i = slice(i, i+1)
# get removed indices
removed = list(range(*i.indices(mylen)))
removed.reverse()
# fixup indices in token dictionary
for name,occurrences in self.__tokdict.items():
for j in removed:
for k, (value, position) in enumerate(occurrences):
occurrences[k] = _ParseResultsWithOffset(value, position - (position > j))
else:
del self.__tokdict[i]
def __contains__( self, k ):
return k in self.__tokdict
def __len__( self ): return len( self.__toklist )
def __bool__(self): return ( not not self.__toklist )
__nonzero__ = __bool__
def __iter__( self ): return iter( self.__toklist )
def __reversed__( self ): return iter( self.__toklist[::-1] )
def _iterkeys( self ):
if hasattr(self.__tokdict, "iterkeys"):
return self.__tokdict.iterkeys()
else:
return iter(self.__tokdict)
def _itervalues( self ):
return (self[k] for k in self._iterkeys())
def _iteritems( self ):
return ((k, self[k]) for k in self._iterkeys())
if PY_3:
keys = _iterkeys
"""Returns an iterator of all named result keys (Python 3.x only)."""
values = _itervalues
"""Returns an iterator of all named result values (Python 3.x only)."""
items = _iteritems
"""Returns an iterator of all named result key-value tuples (Python 3.x only)."""
else:
iterkeys = _iterkeys
"""Returns an iterator of all named result keys (Python 2.x only)."""
itervalues = _itervalues
"""Returns an iterator of all named result values (Python 2.x only)."""
iteritems = _iteritems
"""Returns an iterator of all named result key-value tuples (Python 2.x only)."""
def keys( self ):
"""Returns all named result keys (as a list in Python 2.x, as an iterator in Python 3.x)."""
return list(self.iterkeys())
def values( self ):
"""Returns all named result values (as a list in Python 2.x, as an iterator in Python 3.x)."""
return list(self.itervalues())
def items( self ):
"""Returns all named result key-values (as a list of tuples in Python 2.x, as an iterator in Python 3.x)."""
return list(self.iteritems())
def haskeys( self ):
"""Since keys() returns an iterator, this method is helpful in bypassing
code that looks for the existence of any defined results names."""
return bool(self.__tokdict)
def pop( self, *args, **kwargs):
"""
Removes and returns item at specified index (default=C{last}).
Supports both C{list} and C{dict} semantics for C{pop()}. If passed no
argument or an integer argument, it will use C{list} semantics
and pop tokens from the list of parsed tokens. If passed a
non-integer argument (most likely a string), it will use C{dict}
semantics and pop the corresponding value from any defined
results names. A second default return value argument is
supported, just as in C{dict.pop()}.
Example::
def remove_first(tokens):
tokens.pop(0)
print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
print(OneOrMore(Word(nums)).addParseAction(remove_first).parseString("0 123 321")) # -> ['123', '321']
label = Word(alphas)
patt = label("LABEL") + OneOrMore(Word(nums))
print(patt.parseString("AAB 123 321").dump())
# Use pop() in a parse action to remove named result (note that corresponding value is not
# removed from list form of results)
def remove_LABEL(tokens):
tokens.pop("LABEL")
return tokens
patt.addParseAction(remove_LABEL)
print(patt.parseString("AAB 123 321").dump())
prints::
['AAB', '123', '321']
- LABEL: AAB
['AAB', '123', '321']
"""
if not args:
args = [-1]
for k,v in kwargs.items():
if k == 'default':
args = (args[0], v)
else:
raise TypeError("pop() got an unexpected keyword argument '%s'" % k)
if (isinstance(args[0], int) or
len(args) == 1 or
args[0] in self):
index = args[0]
ret = self[index]
del self[index]
return ret
else:
defaultvalue = args[1]
return defaultvalue
def get(self, key, defaultValue=None):
"""
Returns named result matching the given key, or if there is no
such name, then returns the given C{defaultValue} or C{None} if no
C{defaultValue} is specified.
Similar to C{dict.get()}.
Example::
integer = Word(nums)
date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
result = date_str.parseString("1999/12/31")
print(result.get("year")) # -> '1999'
print(result.get("hour", "not specified")) # -> 'not specified'
print(result.get("hour")) # -> None
"""
if key in self:
return self[key]
else:
return defaultValue
def insert( self, index, insStr ):
"""
Inserts new element at location index in the list of parsed tokens.
Similar to C{list.insert()}.
Example::
print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
# use a parse action to insert the parse location in the front of the parsed results
def insert_locn(locn, tokens):
tokens.insert(0, locn)
print(OneOrMore(Word(nums)).addParseAction(insert_locn).parseString("0 123 321")) # -> [0, '0', '123', '321']
"""
self.__toklist.insert(index, insStr)
# fixup indices in token dictionary
for name,occurrences in self.__tokdict.items():
for k, (value, position) in enumerate(occurrences):
occurrences[k] = _ParseResultsWithOffset(value, position + (position > index))
def append( self, item ):
"""
Add single element to end of ParseResults list of elements.
Example::
print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
# use a parse action to compute the sum of the parsed integers, and add it to the end
def append_sum(tokens):
tokens.append(sum(map(int, tokens)))
print(OneOrMore(Word(nums)).addParseAction(append_sum).parseString("0 123 321")) # -> ['0', '123', '321', 444]
"""
self.__toklist.append(item)
def extend( self, itemseq ):
"""
Add sequence of elements to end of ParseResults list of elements.
Example::
patt = OneOrMore(Word(alphas))
# use a parse action to append the reverse of the matched strings, to make a palindrome
def make_palindrome(tokens):
tokens.extend(reversed([t[::-1] for t in tokens]))
return ''.join(tokens)
print(patt.addParseAction(make_palindrome).parseString("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl'
"""
if isinstance(itemseq, ParseResults):
self += itemseq
else:
self.__toklist.extend(itemseq)
def clear( self ):
"""
Clear all elements and results names.
"""
del self.__toklist[:]
self.__tokdict.clear()
def __getattr__( self, name ):
try:
return self[name]
except KeyError:
return ""
if name in self.__tokdict:
if name not in self.__accumNames:
return self.__tokdict[name][-1][0]
else:
return ParseResults([ v[0] for v in self.__tokdict[name] ])
else:
return ""
def __add__( self, other ):
ret = self.copy()
ret += other
return ret
def __iadd__( self, other ):
if other.__tokdict:
offset = len(self.__toklist)
addoffset = lambda a: offset if a<0 else a+offset
otheritems = other.__tokdict.items()
otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) )
for (k,vlist) in otheritems for v in vlist]
for k,v in otherdictitems:
self[k] = v
if isinstance(v[0],ParseResults):
v[0].__parent = wkref(self)
self.__toklist += other.__toklist
self.__accumNames.update( other.__accumNames )
return self
def __radd__(self, other):
if isinstance(other,int) and other == 0:
# useful for merging many ParseResults using sum() builtin
return self.copy()
else:
# this may raise a TypeError - so be it
return other + self
def __repr__( self ):
return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) )
def __str__( self ):
return '[' + ', '.join(_ustr(i) if isinstance(i, ParseResults) else repr(i) for i in self.__toklist) + ']'
def _asStringList( self, sep='' ):
out = []
for item in self.__toklist:
if out and sep:
out.append(sep)
if isinstance( item, ParseResults ):
out += item._asStringList()
else:
out.append( _ustr(item) )
return out
def asList( self ):
"""
Returns the parse results as a nested list of matching tokens, all converted to strings.
Example::
patt = OneOrMore(Word(alphas))
result = patt.parseString("sldkj lsdkj sldkj")
# even though the result prints in string-like form, it is actually a pyparsing ParseResults
print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj']
# Use asList() to create an actual list
result_list = result.asList()
print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj']
"""
return [res.asList() if isinstance(res,ParseResults) else res for res in self.__toklist]
def asDict( self ):
"""
Returns the named parse results as a nested dictionary.
Example::
integer = Word(nums)
date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
result = date_str.parseString('12/31/1999')
print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]})
result_dict = result.asDict()
print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'}
# even though a ParseResults supports dict-like access, sometime you just need to have a dict
import json
print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable
print(json.dumps(result.asDict())) # -> {"month": "31", "day": "1999", "year": "12"}
"""
if PY_3:
item_fn = self.items
else:
item_fn = self.iteritems
def toItem(obj):
if isinstance(obj, ParseResults):
if obj.haskeys():
return obj.asDict()
else:
return [toItem(v) for v in obj]
else:
return obj
return dict((k,toItem(v)) for k,v in item_fn())
def copy( self ):
"""
Returns a new copy of a C{ParseResults} object.
"""
ret = ParseResults( self.__toklist )
ret.__tokdict = self.__tokdict.copy()
ret.__parent = self.__parent
ret.__accumNames.update( self.__accumNames )
ret.__name = self.__name
return ret
def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ):
"""
(Deprecated) Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.
"""
nl = "\n"
out = []
namedItems = dict((v[1],k) for (k,vlist) in self.__tokdict.items()
for v in vlist)
nextLevelIndent = indent + " "
# collapse out indents if formatting is not desired
if not formatted:
indent = ""
nextLevelIndent = ""
nl = ""
selfTag = None
if doctag is not None:
selfTag = doctag
else:
if self.__name:
selfTag = self.__name
if not selfTag:
if namedItemsOnly:
return ""
else:
selfTag = "ITEM"
out += [ nl, indent, "<", selfTag, ">" ]
for i,res in enumerate(self.__toklist):
if isinstance(res,ParseResults):
if i in namedItems:
out += [ res.asXML(namedItems[i],
namedItemsOnly and doctag is None,
nextLevelIndent,
formatted)]
else:
out += [ res.asXML(None,
namedItemsOnly and doctag is None,
nextLevelIndent,
formatted)]
else:
# individual token, see if there is a name for it
resTag = None
if i in namedItems:
resTag = namedItems[i]
if not resTag:
if namedItemsOnly:
continue
else:
resTag = "ITEM"
xmlBodyText = _xml_escape(_ustr(res))
out += [ nl, nextLevelIndent, "<", resTag, ">",
xmlBodyText,
"</", resTag, ">" ]
out += [ nl, indent, "</", selfTag, ">" ]
return "".join(out)
def __lookup(self,sub):
for k,vlist in self.__tokdict.items():
for v,loc in vlist:
if sub is v:
return k
return None
def getName(self):
"""
Returns the results name for this token expression. Useful when several
different expressions might match at a particular location.
Example::
integer = Word(nums)
ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d")
house_number_expr = Suppress('#') + Word(nums, alphanums)
user_data = (Group(house_number_expr)("house_number")
| Group(ssn_expr)("ssn")
| Group(integer)("age"))
user_info = OneOrMore(user_data)
result = user_info.parseString("22 111-22-3333 #221B")
for item in result:
print(item.getName(), ':', item[0])
prints::
age : 22
ssn : 111-22-3333
house_number : 221B
"""
if self.__name:
return self.__name
elif self.__parent:
par = self.__parent()
if par:
return par.__lookup(self)
else:
return None
elif (len(self) == 1 and
len(self.__tokdict) == 1 and
next(iter(self.__tokdict.values()))[0][1] in (0,-1)):
return next(iter(self.__tokdict.keys()))
else:
return None
def dump(self, indent='', depth=0, full=True):
"""
Diagnostic method for listing out the contents of a C{ParseResults}.
Accepts an optional C{indent} argument so that this string can be embedded
in a nested display of other data.
Example::
integer = Word(nums)
date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
result = date_str.parseString('12/31/1999')
print(result.dump())
prints::
['12', '/', '31', '/', '1999']
- day: 1999
- month: 31
- year: 12
"""
out = []
NL = '\n'
out.append( indent+_ustr(self.asList()) )
if full:
if self.haskeys():
items = sorted((str(k), v) for k,v in self.items())
for k,v in items:
if out:
out.append(NL)
out.append( "%s%s- %s: " % (indent,(' '*depth), k) )
if isinstance(v,ParseResults):
if v:
out.append( v.dump(indent,depth+1) )
else:
out.append(_ustr(v))
else:
out.append(repr(v))
elif any(isinstance(vv,ParseResults) for vv in self):
v = self
for i,vv in enumerate(v):
if isinstance(vv,ParseResults):
out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),vv.dump(indent,depth+1) ))
else:
out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),_ustr(vv)))
return "".join(out)
def pprint(self, *args, **kwargs):
"""
Pretty-printer for parsed results as a list, using the C{pprint} module.
Accepts additional positional or keyword args as defined for the
C{pprint.pprint} method. (U{http://docs.python.org/3/library/pprint.html#pprint.pprint})
Example::
ident = Word(alphas, alphanums)
num = Word(nums)
func = Forward()
term = ident | num | Group('(' + func + ')')
func <<= ident + Group(Optional(delimitedList(term)))
result = func.parseString("fna a,b,(fnb c,d,200),100")
result.pprint(width=40)
prints::
['fna',
['a',
'b',
['(', 'fnb', ['c', 'd', '200'], ')'],
'100']]
"""
pprint.pprint(self.asList(), *args, **kwargs)
# add support for pickle protocol
def __getstate__(self):
return ( self.__toklist,
( self.__tokdict.copy(),
self.__parent is not None and self.__parent() or None,
self.__accumNames,
self.__name ) )
def __setstate__(self,state):
self.__toklist = state[0]
(self.__tokdict,
par,
inAccumNames,
self.__name) = state[1]
self.__accumNames = {}
self.__accumNames.update(inAccumNames)
if par is not None:
self.__parent = wkref(par)
else:
self.__parent = None
def __getnewargs__(self):
return self.__toklist, self.__name, self.__asList, self.__modal
def __dir__(self):
return (dir(type(self)) + list(self.keys()))
collections.MutableMapping.register(ParseResults)
def col (loc,strg):
"""Returns current column within a string, counting newlines as line separators.
The first column is number 1.
Note: the default parsing behavior is to expand tabs in the input string
before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
consistent view of the parsed string, the parse location, and line and column
positions within the parsed string.
"""
s = strg
return 1 if 0<loc<len(s) and s[loc-1] == '\n' else loc - s.rfind("\n", 0, loc)
def lineno(loc,strg):
"""Returns current line number within a string, counting newlines as line separators.
The first line is number 1.
Note: the default parsing behavior is to expand tabs in the input string
before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
consistent view of the parsed string, the parse location, and line and column
positions within the parsed string.
"""
return strg.count("\n",0,loc) + 1
def line( loc, strg ):
"""Returns the line of text containing loc within a string, counting newlines as line separators.
"""
lastCR = strg.rfind("\n", 0, loc)
nextCR = strg.find("\n", loc)
if nextCR >= 0:
return strg[lastCR+1:nextCR]
else:
return strg[lastCR+1:]
def _defaultStartDebugAction( instring, loc, expr ):
print (("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )))
def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ):
print ("Matched " + _ustr(expr) + " -> " + str(toks.asList()))
def _defaultExceptionDebugAction( instring, loc, expr, exc ):
print ("Exception raised:" + _ustr(exc))
def nullDebugAction(*args):
"""'Do-nothing' debug action, to suppress debugging output during parsing."""
pass
# Only works on Python 3.x - nonlocal is toxic to Python 2 installs
#~ 'decorator to trim function calls to match the arity of the target'
#~ def _trim_arity(func, maxargs=3):
#~ if func in singleArgBuiltins:
#~ return lambda s,l,t: func(t)
#~ limit = 0
#~ foundArity = False
#~ def wrapper(*args):
#~ nonlocal limit,foundArity
#~ while 1:
#~ try:
#~ ret = func(*args[limit:])
#~ foundArity = True
#~ return ret
#~ except TypeError:
#~ if limit == maxargs or foundArity:
#~ raise
#~ limit += 1
#~ continue
#~ return wrapper
# this version is Python 2.x-3.x cross-compatible
'decorator to trim function calls to match the arity of the target'
def _trim_arity(func, maxargs=2):
if func in singleArgBuiltins:
return lambda s,l,t: func(t)
limit = [0]
foundArity = [False]
# traceback return data structure changed in Py3.5 - normalize back to plain tuples
if system_version[:2] >= (3,5):
def extract_stack(limit=0):
# special handling for Python 3.5.0 - extra deep call stack by 1
offset = -3 if system_version == (3,5,0) else -2
frame_summary = traceback.extract_stack(limit=-offset+limit-1)[offset]
return [(frame_summary.filename, frame_summary.lineno)]
def extract_tb(tb, limit=0):
frames = traceback.extract_tb(tb, limit=limit)
frame_summary = frames[-1]
return [(frame_summary.filename, frame_summary.lineno)]
else:
extract_stack = traceback.extract_stack
extract_tb = traceback.extract_tb
# synthesize what would be returned by traceback.extract_stack at the call to
# user's parse action 'func', so that we don't incur call penalty at parse time
LINE_DIFF = 6
# IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND
# THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!!
this_line = extract_stack(limit=2)[-1]
pa_call_line_synth = (this_line[0], this_line[1]+LINE_DIFF)
def wrapper(*args):
while 1:
try:
ret = func(*args[limit[0]:])
foundArity[0] = True
return ret
except TypeError:
# re-raise TypeErrors if they did not come from our arity testing
if foundArity[0]:
raise
else:
try:
tb = sys.exc_info()[-1]
if not extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth:
raise
finally:
del tb
if limit[0] <= maxargs:
limit[0] += 1
continue
raise
# copy func name to wrapper for sensible debug output
func_name = "<parse action>"
try:
func_name = getattr(func, '__name__',
getattr(func, '__class__').__name__)
except Exception:
func_name = str(func)
wrapper.__name__ = func_name
return wrapper
class ParserElement(object):
"""Abstract base level parser element class."""
DEFAULT_WHITE_CHARS = " \n\t\r"
verbose_stacktrace = False
@staticmethod
def setDefaultWhitespaceChars( chars ):
r"""
Overrides the default whitespace chars
Example::
# default whitespace chars are space, <TAB> and newline
OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl']
# change to just treat newline as significant
ParserElement.setDefaultWhitespaceChars(" \t")
OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def']
"""
ParserElement.DEFAULT_WHITE_CHARS = chars
@staticmethod
def inlineLiteralsUsing(cls):
"""
Set class to be used for inclusion of string literals into a parser.
Example::
# default literal class used is Literal
integer = Word(nums)
date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
# change to Suppress
ParserElement.inlineLiteralsUsing(Suppress)
date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
date_str.parseString("1999/12/31") # -> ['1999', '12', '31']
"""
ParserElement._literalStringClass = cls
def __init__( self, savelist=False ):
self.parseAction = list()
self.failAction = None
#~ self.name = "<unknown>" # don't define self.name, let subclasses try/except upcall
self.strRepr = None
self.resultsName = None
self.saveAsList = savelist
self.skipWhitespace = True
self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
self.copyDefaultWhiteChars = True
self.mayReturnEmpty = False # used when checking for left-recursion
self.keepTabs = False
self.ignoreExprs = list()
self.debug = False
self.streamlined = False
self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index
self.errmsg = ""
self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all)
self.debugActions = ( None, None, None ) #custom debug actions
self.re = None
self.callPreparse = True # used to avoid redundant calls to preParse
self.callDuringTry = False
def copy( self ):
"""
Make a copy of this C{ParserElement}. Useful for defining different parse actions
for the same parsing pattern, using copies of the original parse element.
Example::
integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
integerK = integer.copy().addParseAction(lambda toks: toks[0]*1024) + Suppress("K")
integerM = integer.copy().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
print(OneOrMore(integerK | integerM | integer).parseString("5K 100 640K 256M"))
prints::
[5120, 100, 655360, 268435456]
Equivalent form of C{expr.copy()} is just C{expr()}::
integerM = integer().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
"""
cpy = copy.copy( self )
cpy.parseAction = self.parseAction[:]
cpy.ignoreExprs = self.ignoreExprs[:]
if self.copyDefaultWhiteChars:
cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
return cpy
def setName( self, name ):
"""
Define name for this expression, makes debugging and exception messages clearer.
Example::
Word(nums).parseString("ABC") # -> Exception: Expected W:(0123...) (at char 0), (line:1, col:1)
Word(nums).setName("integer").parseString("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1)
"""
self.name = name
self.errmsg = "Expected " + self.name
if hasattr(self,"exception"):
self.exception.msg = self.errmsg
return self
def setResultsName( self, name, listAllMatches=False ):
"""
Define name for referencing matching tokens as a nested attribute
of the returned parse results.
NOTE: this returns a *copy* of the original C{ParserElement} object;
this is so that the client can define a basic element, such as an
integer, and reference it in multiple places with different names.
You can also set results names using the abbreviated syntax,
C{expr("name")} in place of C{expr.setResultsName("name")} -
see L{I{__call__}<__call__>}.
Example::
date_str = (integer.setResultsName("year") + '/'
+ integer.setResultsName("month") + '/'
+ integer.setResultsName("day"))
# equivalent form:
date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
"""
newself = self.copy()
if name.endswith("*"):
name = name[:-1]
listAllMatches=True
newself.resultsName = name
newself.modalResults = not listAllMatches
return newself
def setBreak(self,breakFlag = True):
"""Method to invoke the Python pdb debugger when this element is
about to be parsed. Set C{breakFlag} to True to enable, False to
disable.
"""
if breakFlag:
_parseMethod = self._parse
def breaker(instring, loc, doActions=True, callPreParse=True):
import pdb
pdb.set_trace()
return _parseMethod( instring, loc, doActions, callPreParse )
breaker._originalParseMethod = _parseMethod
self._parse = breaker
else:
if hasattr(self._parse,"_originalParseMethod"):
self._parse = self._parse._originalParseMethod
return self
def setParseAction( self, *fns, **kwargs ):
"""
Define action to perform when successfully matching parse element definition.
Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)},
C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where:
- s = the original string being parsed (see note below)
- loc = the location of the matching substring
- toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object
If the functions in fns modify the tokens, they can return them as the return
value from fn, and the modified list of tokens will replace the original.
Otherwise, fn does not need to return any value.
Optional keyword arguments:
- callDuringTry = (default=C{False}) indicate if parse action should be run during lookaheads and alternate testing
Note: the default parsing behavior is to expand tabs in the input string
before starting the parsing process. See L{I{parseString}<parseString>} for more information
on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
consistent view of the parsed string, the parse location, and line and column
positions within the parsed string.
Example::
integer = Word(nums)
date_str = integer + '/' + integer + '/' + integer
date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
# use parse action to convert to ints at parse time
integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
date_str = integer + '/' + integer + '/' + integer
# note that integer fields are now ints, not strings
date_str.parseString("1999/12/31") # -> [1999, '/', 12, '/', 31]
"""
self.parseAction = list(map(_trim_arity, list(fns)))
self.callDuringTry = kwargs.get("callDuringTry", False)
return self
def addParseAction( self, *fns, **kwargs ):
"""
Add parse action to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}.
See examples in L{I{copy}<copy>}.
"""
self.parseAction += list(map(_trim_arity, list(fns)))
self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
return self
def addCondition(self, *fns, **kwargs):
"""Add a boolean predicate function to expression's list of parse actions. See
L{I{setParseAction}<setParseAction>} for function call signatures. Unlike C{setParseAction},
functions passed to C{addCondition} need to return boolean success/fail of the condition.
Optional keyword arguments:
- message = define a custom message to be used in the raised exception
- fatal = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise ParseException
Example::
integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
year_int = integer.copy()
year_int.addCondition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later")
date_str = year_int + '/' + integer + '/' + integer
result = date_str.parseString("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), (line:1, col:1)
"""
msg = kwargs.get("message", "failed user-defined condition")
exc_type = ParseFatalException if kwargs.get("fatal", False) else ParseException
for fn in fns:
def pa(s,l,t):
if not bool(_trim_arity(fn)(s,l,t)):
raise exc_type(s,l,msg)
self.parseAction.append(pa)
self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
return self
def setFailAction( self, fn ):
"""Define action to perform if parsing fails at this expression.
Fail acton fn is a callable function that takes the arguments
C{fn(s,loc,expr,err)} where:
- s = string being parsed
- loc = location where expression match was attempted and failed
- expr = the parse expression that failed
- err = the exception thrown
The function returns no value. It may throw C{L{ParseFatalException}}
if it is desired to stop parsing immediately."""
self.failAction = fn
return self
def _skipIgnorables( self, instring, loc ):
exprsFound = True
while exprsFound:
exprsFound = False
for e in self.ignoreExprs:
try:
while 1:
loc,dummy = e._parse( instring, loc )
exprsFound = True
except ParseException:
pass
return loc
def preParse( self, instring, loc ):
if self.ignoreExprs:
loc = self._skipIgnorables( instring, loc )
if self.skipWhitespace:
wt = self.whiteChars
instrlen = len(instring)
while loc < instrlen and instring[loc] in wt:
loc += 1
return loc
def parseImpl( self, instring, loc, doActions=True ):
return loc, []
def postParse( self, instring, loc, tokenlist ):
return tokenlist
#~ @profile
def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ):
debugging = ( self.debug ) #and doActions )
if debugging or self.failAction:
#~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) ))
if (self.debugActions[0] ):
self.debugActions[0]( instring, loc, self )
if callPreParse and self.callPreparse:
preloc = self.preParse( instring, loc )
else:
preloc = loc
tokensStart = preloc
try:
try:
loc,tokens = self.parseImpl( instring, preloc, doActions )
except IndexError:
raise ParseException( instring, len(instring), self.errmsg, self )
except ParseBaseException as err:
#~ print ("Exception raised:", err)
if self.debugActions[2]:
self.debugActions[2]( instring, tokensStart, self, err )
if self.failAction:
self.failAction( instring, tokensStart, self, err )
raise
else:
if callPreParse and self.callPreparse:
preloc = self.preParse( instring, loc )
else:
preloc = loc
tokensStart = preloc
if self.mayIndexError or loc >= len(instring):
try:
loc,tokens = self.parseImpl( instring, preloc, doActions )
except IndexError:
raise ParseException( instring, len(instring), self.errmsg, self )
else:
loc,tokens = self.parseImpl( instring, preloc, doActions )
tokens = self.postParse( instring, loc, tokens )
retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults )
if self.parseAction and (doActions or self.callDuringTry):
if debugging:
try:
for fn in self.parseAction:
tokens = fn( instring, tokensStart, retTokens )
if tokens is not None:
retTokens = ParseResults( tokens,
self.resultsName,
asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
modal=self.modalResults )
except ParseBaseException as err:
#~ print "Exception raised in user parse action:", err
if (self.debugActions[2] ):
self.debugActions[2]( instring, tokensStart, self, err )
raise
else:
for fn in self.parseAction:
tokens = fn( instring, tokensStart, retTokens )
if tokens is not None:
retTokens = ParseResults( tokens,
self.resultsName,
asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
modal=self.modalResults )
if debugging:
#~ print ("Matched",self,"->",retTokens.asList())
if (self.debugActions[1] ):
self.debugActions[1]( instring, tokensStart, loc, self, retTokens )
return loc, retTokens
def tryParse( self, instring, loc ):
try:
return self._parse( instring, loc, doActions=False )[0]
except ParseFatalException:
raise ParseException( instring, loc, self.errmsg, self)
def canParseNext(self, instring, loc):
try:
self.tryParse(instring, loc)
except (ParseException, IndexError):
return False
else:
return True
class _UnboundedCache(object):
def __init__(self):
cache = {}
self.not_in_cache = not_in_cache = object()
def get(self, key):
return cache.get(key, not_in_cache)
def set(self, key, value):
cache[key] = value
def clear(self):
cache.clear()
self.get = types.MethodType(get, self)
self.set = types.MethodType(set, self)
self.clear = types.MethodType(clear, self)
if _OrderedDict is not None:
class _FifoCache(object):
def __init__(self, size):
self.not_in_cache = not_in_cache = object()
cache = _OrderedDict()
def get(self, key):
return cache.get(key, not_in_cache)
def set(self, key, value):
cache[key] = value
if len(cache) > size:
cache.popitem(False)
def clear(self):
cache.clear()
self.get = types.MethodType(get, self)
self.set = types.MethodType(set, self)
self.clear = types.MethodType(clear, self)
else:
class _FifoCache(object):
def __init__(self, size):
self.not_in_cache = not_in_cache = object()
cache = {}
key_fifo = collections.deque([], size)
def get(self, key):
return cache.get(key, not_in_cache)
def set(self, key, value):
cache[key] = value
if len(cache) > size:
cache.pop(key_fifo.popleft(), None)
key_fifo.append(key)
def clear(self):
cache.clear()
key_fifo.clear()
self.get = types.MethodType(get, self)
self.set = types.MethodType(set, self)
self.clear = types.MethodType(clear, self)
# argument cache for optimizing repeated calls when backtracking through recursive expressions
packrat_cache = {} # this is set later by enabledPackrat(); this is here so that resetCache() doesn't fail
packrat_cache_lock = RLock()
packrat_cache_stats = [0, 0]
# this method gets repeatedly called during backtracking with the same arguments -
# we can cache these arguments and save ourselves the trouble of re-parsing the contained expression
def _parseCache( self, instring, loc, doActions=True, callPreParse=True ):
HIT, MISS = 0, 1
lookup = (self, instring, loc, callPreParse, doActions)
with ParserElement.packrat_cache_lock:
cache = ParserElement.packrat_cache
value = cache.get(lookup)
if value is cache.not_in_cache:
ParserElement.packrat_cache_stats[MISS] += 1
try:
value = self._parseNoCache(instring, loc, doActions, callPreParse)
except ParseBaseException as pe:
# cache a copy of the exception, without the traceback
cache.set(lookup, pe.__class__(*pe.args))
raise
else:
cache.set(lookup, (value[0], value[1].copy()))
return value
else:
ParserElement.packrat_cache_stats[HIT] += 1
if isinstance(value, Exception):
raise value
return (value[0], value[1].copy())
_parse = _parseNoCache
@staticmethod
def resetCache():
ParserElement.packrat_cache.clear()
ParserElement.packrat_cache_stats[:] = [0] * len(ParserElement.packrat_cache_stats)
_packratEnabled = False
@staticmethod
def enablePackrat(cache_size_limit=128):
"""Enables "packrat" parsing, which adds memoizing to the parsing logic.
Repeated parse attempts at the same string location (which happens
often in many complex grammars) can immediately return a cached value,
instead of re-executing parsing/validating code. Memoizing is done of
both valid results and parsing exceptions.
Parameters:
- cache_size_limit - (default=C{128}) - if an integer value is provided
will limit the size of the packrat cache; if None is passed, then
the cache size will be unbounded; if 0 is passed, the cache will
be effectively disabled.
This speedup may break existing programs that use parse actions that
have side-effects. For this reason, packrat parsing is disabled when
you first import pyparsing. To activate the packrat feature, your
program must call the class method C{ParserElement.enablePackrat()}. If
your program uses C{psyco} to "compile as you go", you must call
C{enablePackrat} before calling C{psyco.full()}. If you do not do this,
Python will crash. For best results, call C{enablePackrat()} immediately
after importing pyparsing.
Example::
import pyparsing
pyparsing.ParserElement.enablePackrat()
"""
if not ParserElement._packratEnabled:
ParserElement._packratEnabled = True
if cache_size_limit is None:
ParserElement.packrat_cache = ParserElement._UnboundedCache()
else:
ParserElement.packrat_cache = ParserElement._FifoCache(cache_size_limit)
ParserElement._parse = ParserElement._parseCache
def parseString( self, instring, parseAll=False ):
"""
Execute the parse expression with the given string.
This is the main interface to the client code, once the complete
expression has been built.
If you want the grammar to require that the entire input string be
successfully parsed, then set C{parseAll} to True (equivalent to ending
the grammar with C{L{StringEnd()}}).
Note: C{parseString} implicitly calls C{expandtabs()} on the input string,
in order to report proper column numbers in parse actions.
If the input string contains tabs and
the grammar uses parse actions that use the C{loc} argument to index into the
string being parsed, you can ensure you have a consistent view of the input
string by:
- calling C{parseWithTabs} on your grammar before calling C{parseString}
(see L{I{parseWithTabs}<parseWithTabs>})
- define your parse action using the full C{(s,loc,toks)} signature, and
reference the input string using the parse action's C{s} argument
- explictly expand the tabs in your input string before calling
C{parseString}
Example::
Word('a').parseString('aaaaabaaa') # -> ['aaaaa']
Word('a').parseString('aaaaabaaa', parseAll=True) # -> Exception: Expected end of text
"""
ParserElement.resetCache()
if not self.streamlined:
self.streamline()
#~ self.saveAsList = True
for e in self.ignoreExprs:
e.streamline()
if not self.keepTabs:
instring = instring.expandtabs()
try:
loc, tokens = self._parse( instring, 0 )
if parseAll:
loc = self.preParse( instring, loc )
se = Empty() + StringEnd()
se._parse( instring, loc )
except ParseBaseException as exc:
if ParserElement.verbose_stacktrace:
raise
else:
# catch and re-raise exception from here, clears out pyparsing internal stack trace
raise exc
else:
return tokens
def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ):
"""
Scan the input string for expression matches. Each match will return the
matching tokens, start location, and end location. May be called with optional
C{maxMatches} argument, to clip scanning after 'n' matches are found. If
C{overlap} is specified, then overlapping matches will be reported.
Note that the start and end locations are reported relative to the string
being parsed. See L{I{parseString}<parseString>} for more information on parsing
strings with embedded tabs.
Example::
source = "sldjf123lsdjjkf345sldkjf879lkjsfd987"
print(source)
for tokens,start,end in Word(alphas).scanString(source):
print(' '*start + '^'*(end-start))
print(' '*start + tokens[0])
prints::
sldjf123lsdjjkf345sldkjf879lkjsfd987
^^^^^
sldjf
^^^^^^^
lsdjjkf
^^^^^^
sldkjf
^^^^^^
lkjsfd
"""
if not self.streamlined:
self.streamline()
for e in self.ignoreExprs:
e.streamline()
if not self.keepTabs:
instring = _ustr(instring).expandtabs()
instrlen = len(instring)
loc = 0
preparseFn = self.preParse
parseFn = self._parse
ParserElement.resetCache()
matches = 0
try:
while loc <= instrlen and matches < maxMatches:
try:
preloc = preparseFn( instring, loc )
nextLoc,tokens = parseFn( instring, preloc, callPreParse=False )
except ParseException:
loc = preloc+1
else:
if nextLoc > loc:
matches += 1
yield tokens, preloc, nextLoc
if overlap:
nextloc = preparseFn( instring, loc )
if nextloc > loc:
loc = nextLoc
else:
loc += 1
else:
loc = nextLoc
else:
loc = preloc+1
except ParseBaseException as exc:
if ParserElement.verbose_stacktrace:
raise
else:
# catch and re-raise exception from here, clears out pyparsing internal stack trace
raise exc
def transformString( self, instring ):
"""
Extension to C{L{scanString}}, to modify matching text with modified tokens that may
be returned from a parse action. To use C{transformString}, define a grammar and
attach a parse action to it that modifies the returned token list.
Invoking C{transformString()} on a target string will then scan for matches,
and replace the matched text patterns according to the logic in the parse
action. C{transformString()} returns the resulting transformed string.
Example::
wd = Word(alphas)
wd.setParseAction(lambda toks: toks[0].title())
print(wd.transformString("now is the winter of our discontent made glorious summer by this sun of york."))
Prints::
Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York.
"""
out = []
lastE = 0
# force preservation of <TAB>s, to minimize unwanted transformation of string, and to
# keep string locs straight between transformString and scanString
self.keepTabs = True
try:
for t,s,e in self.scanString( instring ):
out.append( instring[lastE:s] )
if t:
if isinstance(t,ParseResults):
out += t.asList()
elif isinstance(t,list):
out += t
else:
out.append(t)
lastE = e
out.append(instring[lastE:])
out = [o for o in out if o]
return "".join(map(_ustr,_flatten(out)))
except ParseBaseException as exc:
if ParserElement.verbose_stacktrace:
raise
else:
# catch and re-raise exception from here, clears out pyparsing internal stack trace
raise exc
def searchString( self, instring, maxMatches=_MAX_INT ):
"""
Another extension to C{L{scanString}}, simplifying the access to the tokens found
to match the given parse expression. May be called with optional
C{maxMatches} argument, to clip searching after 'n' matches are found.
Example::
# a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters
cap_word = Word(alphas.upper(), alphas.lower())
print(cap_word.searchString("More than Iron, more than Lead, more than Gold I need Electricity"))
prints::
['More', 'Iron', 'Lead', 'Gold', 'I']
"""
try:
return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ])
except ParseBaseException as exc:
if ParserElement.verbose_stacktrace:
raise
else:
# catch and re-raise exception from here, clears out pyparsing internal stack trace
raise exc
def split(self, instring, maxsplit=_MAX_INT, includeSeparators=False):
"""
Generator method to split a string using the given expression as a separator.
May be called with optional C{maxsplit} argument, to limit the number of splits;
and the optional C{includeSeparators} argument (default=C{False}), if the separating
matching text should be included in the split results.
Example::
punc = oneOf(list(".,;:/-!?"))
print(list(punc.split("This, this?, this sentence, is badly punctuated!")))
prints::
['This', ' this', '', ' this sentence', ' is badly punctuated', '']
"""
splits = 0
last = 0
for t,s,e in self.scanString(instring, maxMatches=maxsplit):
yield instring[last:s]
if includeSeparators:
yield t[0]
last = e
yield instring[last:]
def __add__(self, other ):
"""
Implementation of + operator - returns C{L{And}}. Adding strings to a ParserElement
converts them to L{Literal}s by default.
Example::
greet = Word(alphas) + "," + Word(alphas) + "!"
hello = "Hello, World!"
print (hello, "->", greet.parseString(hello))
Prints::
Hello, World! -> ['Hello', ',', 'World', '!']
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return And( [ self, other ] )
def __radd__(self, other ):
"""
Implementation of + operator when left operand is not a C{L{ParserElement}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return other + self
def __sub__(self, other):
"""
Implementation of - operator, returns C{L{And}} with error stop
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return And( [ self, And._ErrorStop(), other ] )
def __rsub__(self, other ):
"""
Implementation of - operator when left operand is not a C{L{ParserElement}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return other - self
def __mul__(self,other):
"""
Implementation of * operator, allows use of C{expr * 3} in place of
C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer
tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples
may also include C{None} as in:
- C{expr*(n,None)} or C{expr*(n,)} is equivalent
to C{expr*n + L{ZeroOrMore}(expr)}
(read as "at least n instances of C{expr}")
- C{expr*(None,n)} is equivalent to C{expr*(0,n)}
(read as "0 to n instances of C{expr}")
- C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)}
- C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)}
Note that C{expr*(None,n)} does not raise an exception if
more than n exprs exist in the input stream; that is,
C{expr*(None,n)} does not enforce a maximum number of expr
occurrences. If this behavior is desired, then write
C{expr*(None,n) + ~expr}
"""
if isinstance(other,int):
minElements, optElements = other,0
elif isinstance(other,tuple):
other = (other + (None, None))[:2]
if other[0] is None:
other = (0, other[1])
if isinstance(other[0],int) and other[1] is None:
if other[0] == 0:
return ZeroOrMore(self)
if other[0] == 1:
return OneOrMore(self)
else:
return self*other[0] + ZeroOrMore(self)
elif isinstance(other[0],int) and isinstance(other[1],int):
minElements, optElements = other
optElements -= minElements
else:
raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1]))
else:
raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other))
if minElements < 0:
raise ValueError("cannot multiply ParserElement by negative value")
if optElements < 0:
raise ValueError("second tuple value must be greater or equal to first tuple value")
if minElements == optElements == 0:
raise ValueError("cannot multiply ParserElement by 0 or (0,0)")
if (optElements):
def makeOptionalList(n):
if n>1:
return Optional(self + makeOptionalList(n-1))
else:
return Optional(self)
if minElements:
if minElements == 1:
ret = self + makeOptionalList(optElements)
else:
ret = And([self]*minElements) + makeOptionalList(optElements)
else:
ret = makeOptionalList(optElements)
else:
if minElements == 1:
ret = self
else:
ret = And([self]*minElements)
return ret
def __rmul__(self, other):
return self.__mul__(other)
def __or__(self, other ):
"""
Implementation of | operator - returns C{L{MatchFirst}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return MatchFirst( [ self, other ] )
def __ror__(self, other ):
"""
Implementation of | operator when left operand is not a C{L{ParserElement}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return other | self
def __xor__(self, other ):
"""
Implementation of ^ operator - returns C{L{Or}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return Or( [ self, other ] )
def __rxor__(self, other ):
"""
Implementation of ^ operator when left operand is not a C{L{ParserElement}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return other ^ self
def __and__(self, other ):
"""
Implementation of & operator - returns C{L{Each}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return Each( [ self, other ] )
def __rand__(self, other ):
"""
Implementation of & operator when left operand is not a C{L{ParserElement}}
"""
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
if not isinstance( other, ParserElement ):
warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
SyntaxWarning, stacklevel=2)
return None
return other & self
def __invert__( self ):
"""
Implementation of ~ operator - returns C{L{NotAny}}
"""
return NotAny( self )
def __call__(self, name=None):
"""
Shortcut for C{L{setResultsName}}, with C{listAllMatches=False}.
If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be
passed as C{True}.
If C{name} is omitted, same as calling C{L{copy}}.
Example::
# these are equivalent
userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno")
userdata = Word(alphas)("name") + Word(nums+"-")("socsecno")
"""
if name is not None:
return self.setResultsName(name)
else:
return self.copy()
def suppress( self ):
"""
Suppresses the output of this C{ParserElement}; useful to keep punctuation from
cluttering up returned output.
"""
return Suppress( self )
def leaveWhitespace( self ):
"""
Disables the skipping of whitespace before matching the characters in the
C{ParserElement}'s defined pattern. This is normally only used internally by
the pyparsing module, but may be needed in some whitespace-sensitive grammars.
"""
self.skipWhitespace = False
return self
def setWhitespaceChars( self, chars ):
"""
Overrides the default whitespace chars
"""
self.skipWhitespace = True
self.whiteChars = chars
self.copyDefaultWhiteChars = False
return self
def parseWithTabs( self ):
"""
Overrides default behavior to expand C{<TAB>}s to spaces before parsing the input string.
Must be called before C{parseString} when the input grammar contains elements that
match C{<TAB>} characters.
"""
self.keepTabs = True
return self
def ignore( self, other ):
"""
Define expression to be ignored (e.g., comments) while doing pattern
matching; may be called repeatedly, to define multiple comment or other
ignorable patterns.
Example::
patt = OneOrMore(Word(alphas))
patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj']
patt.ignore(cStyleComment)
patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj', 'lskjd']
"""
if isinstance(other, basestring):
other = Suppress(other)
if isinstance( other, Suppress ):
if other not in self.ignoreExprs:
self.ignoreExprs.append(other)
else:
self.ignoreExprs.append( Suppress( other.copy() ) )
return self
def setDebugActions( self, startAction, successAction, exceptionAction ):
"""
Enable display of debugging messages while doing pattern matching.
"""
self.debugActions = (startAction or _defaultStartDebugAction,
successAction or _defaultSuccessDebugAction,
exceptionAction or _defaultExceptionDebugAction)
self.debug = True
return self
def setDebug( self, flag=True ):
"""
Enable display of debugging messages while doing pattern matching.
Set C{flag} to True to enable, False to disable.
Example::
wd = Word(alphas).setName("alphaword")
integer = Word(nums).setName("numword")
term = wd | integer
# turn on debugging for wd
wd.setDebug()
OneOrMore(term).parseString("abc 123 xyz 890")
prints::
Match alphaword at loc 0(1,1)
Matched alphaword -> ['abc']
Match alphaword at loc 3(1,4)
Exception raised:Expected alphaword (at char 4), (line:1, col:5)
Match alphaword at loc 7(1,8)
Matched alphaword -> ['xyz']
Match alphaword at loc 11(1,12)
Exception raised:Expected alphaword (at char 12), (line:1, col:13)
Match alphaword at loc 15(1,16)
Exception raised:Expected alphaword (at char 15), (line:1, col:16)
The output shown is that produced by the default debug actions - custom debug actions can be
specified using L{setDebugActions}. Prior to attempting
to match the C{wd} expression, the debugging message C{"Match <exprname> at loc <n>(<line>,<col>)"}
is shown. Then if the parse succeeds, a C{"Matched"} message is shown, or an C{"Exception raised"}
message is shown. Also note the use of L{setName} to assign a human-readable name to the expression,
which makes debugging and exception messages easier to understand - for instance, the default
name created for the C{Word} expression without calling C{setName} is C{"W:(ABCD...)"}.
"""
if flag:
self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction )
else:
self.debug = False
return self
def __str__( self ):
return self.name
def __repr__( self ):
return _ustr(self)
def streamline( self ):
self.streamlined = True
self.strRepr = None
return self
def checkRecursion( self, parseElementList ):
pass
def validate( self, validateTrace=[] ):
"""
Check defined expressions for valid structure, check for infinite recursive definitions.
"""
self.checkRecursion( [] )
def parseFile( self, file_or_filename, parseAll=False ):
"""
Execute the parse expression on the given file or filename.
If a filename is specified (instead of a file object),
the entire file is opened, read, and closed before parsing.
"""
try:
file_contents = file_or_filename.read()
except AttributeError:
with open(file_or_filename, "r") as f:
file_contents = f.read()
try:
return self.parseString(file_contents, parseAll)
except ParseBaseException as exc:
if ParserElement.verbose_stacktrace:
raise
else:
# catch and re-raise exception from here, clears out pyparsing internal stack trace
raise exc
def __eq__(self,other):
if isinstance(other, ParserElement):
return self is other or vars(self) == vars(other)
elif isinstance(other, basestring):
return self.matches(other)
else:
return super(ParserElement,self)==other
def __ne__(self,other):
return not (self == other)
def __hash__(self):
return hash(id(self))
def __req__(self,other):
return self == other
def __rne__(self,other):
return not (self == other)
def matches(self, testString, parseAll=True):
"""
Method for quick testing of a parser against a test string. Good for simple
inline microtests of sub expressions while building up larger parser.
Parameters:
- testString - to test against this expression for a match
- parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
Example::
expr = Word(nums)
assert expr.matches("100")
"""
try:
self.parseString(_ustr(testString), parseAll=parseAll)
return True
except ParseBaseException:
return False
def runTests(self, tests, parseAll=True, comment='#', fullDump=True, printResults=True, failureTests=False):
"""
Execute the parse expression on a series of test strings, showing each
test, the parsed results or where the parse failed. Quick and easy way to
run a parse expression against a list of sample strings.
Parameters:
- tests - a list of separate test strings, or a multiline string of test strings
- parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
- comment - (default=C{'#'}) - expression for indicating embedded comments in the test
string; pass None to disable comment filtering
- fullDump - (default=C{True}) - dump results as list followed by results names in nested outline;
if False, only dump nested list
- printResults - (default=C{True}) prints test output to stdout
- failureTests - (default=C{False}) indicates if these tests are expected to fail parsing
Returns: a (success, results) tuple, where success indicates that all tests succeeded
(or failed if C{failureTests} is True), and the results contain a list of lines of each
test's output
Example::
number_expr = pyparsing_common.number.copy()
result = number_expr.runTests('''
# unsigned integer
100
# negative integer
-100
# float with scientific notation
6.02e23
# integer with scientific notation
1e-12
''')
print("Success" if result[0] else "Failed!")
result = number_expr.runTests('''
# stray character
100Z
# missing leading digit before '.'
-.100
# too many '.'
3.14.159
''', failureTests=True)
print("Success" if result[0] else "Failed!")
prints::
# unsigned integer
100
[100]
# negative integer
-100
[-100]
# float with scientific notation
6.02e23
[6.02e+23]
# integer with scientific notation
1e-12
[1e-12]
Success
# stray character
100Z
^
FAIL: Expected end of text (at char 3), (line:1, col:4)
# missing leading digit before '.'
-.100
^
FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1)
# too many '.'
3.14.159
^
FAIL: Expected end of text (at char 4), (line:1, col:5)
Success
Each test string must be on a single line. If you want to test a string that spans multiple
lines, create a test like this::
expr.runTest(r"this is a test\\n of strings that spans \\n 3 lines")
(Note that this is a raw string literal, you must include the leading 'r'.)
"""
if isinstance(tests, basestring):
tests = list(map(str.strip, tests.rstrip().splitlines()))
if isinstance(comment, basestring):
comment = Literal(comment)
allResults = []
comments = []
success = True
for t in tests:
if comment is not None and comment.matches(t, False) or comments and not t:
comments.append(t)
continue
if not t:
continue
out = ['\n'.join(comments), t]
comments = []
try:
t = t.replace(r'\n','\n')
result = self.parseString(t, parseAll=parseAll)
out.append(result.dump(full=fullDump))
success = success and not failureTests
except ParseBaseException as pe:
fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else ""
if '\n' in t:
out.append(line(pe.loc, t))
out.append(' '*(col(pe.loc,t)-1) + '^' + fatal)
else:
out.append(' '*pe.loc + '^' + fatal)
out.append("FAIL: " + str(pe))
success = success and failureTests
result = pe
except Exception as exc:
out.append("FAIL-EXCEPTION: " + str(exc))
success = success and failureTests
result = exc
if printResults:
if fullDump:
out.append('')
print('\n'.join(out))
allResults.append((t, result))
return success, allResults
class Token(ParserElement):
"""
Abstract C{ParserElement} subclass, for defining atomic matching patterns.
"""
def __init__( self ):
super(Token,self).__init__( savelist=False )
class Empty(Token):
"""
An empty token, will always match.
"""
def __init__( self ):
super(Empty,self).__init__()
self.name = "Empty"
self.mayReturnEmpty = True
self.mayIndexError = False
class NoMatch(Token):
"""
A token that will never match.
"""
def __init__( self ):
super(NoMatch,self).__init__()
self.name = "NoMatch"
self.mayReturnEmpty = True
self.mayIndexError = False
self.errmsg = "Unmatchable token"
def parseImpl( self, instring, loc, doActions=True ):
raise ParseException(instring, loc, self.errmsg, self)
class Literal(Token):
"""
Token to exactly match a specified string.
Example::
Literal('blah').parseString('blah') # -> ['blah']
Literal('blah').parseString('blahfooblah') # -> ['blah']
Literal('blah').parseString('bla') # -> Exception: Expected "blah"
For case-insensitive matching, use L{CaselessLiteral}.
For keyword matching (force word break before and after the matched string),
use L{Keyword} or L{CaselessKeyword}.
"""
def __init__( self, matchString ):
super(Literal,self).__init__()
self.match = matchString
self.matchLen = len(matchString)
try:
self.firstMatchChar = matchString[0]
except IndexError:
warnings.warn("null string passed to Literal; use Empty() instead",
SyntaxWarning, stacklevel=2)
self.__class__ = Empty
self.name = '"%s"' % _ustr(self.match)
self.errmsg = "Expected " + self.name
self.mayReturnEmpty = False
self.mayIndexError = False
# Performance tuning: this routine gets called a *lot*
# if this is a single character match string and the first character matches,
# short-circuit as quickly as possible, and avoid calling startswith
#~ @profile
def parseImpl( self, instring, loc, doActions=True ):
if (instring[loc] == self.firstMatchChar and
(self.matchLen==1 or instring.startswith(self.match,loc)) ):
return loc+self.matchLen, self.match
raise ParseException(instring, loc, self.errmsg, self)
_L = Literal
ParserElement._literalStringClass = Literal
class Keyword(Token):
"""
Token to exactly match a specified string as a keyword, that is, it must be
immediately followed by a non-keyword character. Compare with C{L{Literal}}:
- C{Literal("if")} will match the leading C{'if'} in C{'ifAndOnlyIf'}.
- C{Keyword("if")} will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'}
Accepts two optional constructor arguments in addition to the keyword string:
- C{identChars} is a string of characters that would be valid identifier characters,
defaulting to all alphanumerics + "_" and "$"
- C{caseless} allows case-insensitive matching, default is C{False}.
Example::
Keyword("start").parseString("start") # -> ['start']
Keyword("start").parseString("starting") # -> Exception
For case-insensitive matching, use L{CaselessKeyword}.
"""
DEFAULT_KEYWORD_CHARS = alphanums+"_$"
def __init__( self, matchString, identChars=None, caseless=False ):
super(Keyword,self).__init__()
if identChars is None:
identChars = Keyword.DEFAULT_KEYWORD_CHARS
self.match = matchString
self.matchLen = len(matchString)
try:
self.firstMatchChar = matchString[0]
except IndexError:
warnings.warn("null string passed to Keyword; use Empty() instead",
SyntaxWarning, stacklevel=2)
self.name = '"%s"' % self.match
self.errmsg = "Expected " + self.name
self.mayReturnEmpty = False
self.mayIndexError = False
self.caseless = caseless
if caseless:
self.caselessmatch = matchString.upper()
identChars = identChars.upper()
self.identChars = set(identChars)
def parseImpl( self, instring, loc, doActions=True ):
if self.caseless:
if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and
(loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and
(loc == 0 or instring[loc-1].upper() not in self.identChars) ):
return loc+self.matchLen, self.match
else:
if (instring[loc] == self.firstMatchChar and
(self.matchLen==1 or instring.startswith(self.match,loc)) and
(loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and
(loc == 0 or instring[loc-1] not in self.identChars) ):
return loc+self.matchLen, self.match
raise ParseException(instring, loc, self.errmsg, self)
def copy(self):
c = super(Keyword,self).copy()
c.identChars = Keyword.DEFAULT_KEYWORD_CHARS
return c
@staticmethod
def setDefaultKeywordChars( chars ):
"""Overrides the default Keyword chars
"""
Keyword.DEFAULT_KEYWORD_CHARS = chars
class CaselessLiteral(Literal):
"""
Token to match a specified string, ignoring case of letters.
Note: the matched results will always be in the case of the given
match string, NOT the case of the input text.
Example::
OneOrMore(CaselessLiteral("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD', 'CMD']
(Contrast with example for L{CaselessKeyword}.)
"""
def __init__( self, matchString ):
super(CaselessLiteral,self).__init__( matchString.upper() )
# Preserve the defining literal.
self.returnString = matchString
self.name = "'%s'" % self.returnString
self.errmsg = "Expected " + self.name
def parseImpl( self, instring, loc, doActions=True ):
if instring[ loc:loc+self.matchLen ].upper() == self.match:
return loc+self.matchLen, self.returnString
raise ParseException(instring, loc, self.errmsg, self)
class CaselessKeyword(Keyword):
"""
Caseless version of L{Keyword}.
Example::
OneOrMore(CaselessKeyword("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD']
(Contrast with example for L{CaselessLiteral}.)
"""
def __init__( self, matchString, identChars=None ):
super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True )
def parseImpl( self, instring, loc, doActions=True ):
if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and
(loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ):
return loc+self.matchLen, self.match
raise ParseException(instring, loc, self.errmsg, self)
class CloseMatch(Token):
"""
A variation on L{Literal} which matches "close" matches, that is,
strings with at most 'n' mismatching characters. C{CloseMatch} takes parameters:
- C{match_string} - string to be matched
- C{maxMismatches} - (C{default=1}) maximum number of mismatches allowed to count as a match
The results from a successful parse will contain the matched text from the input string and the following named results:
- C{mismatches} - a list of the positions within the match_string where mismatches were found
- C{original} - the original match_string used to compare against the input string
If C{mismatches} is an empty list, then the match was an exact match.
Example::
patt = CloseMatch("ATCATCGAATGGA")
patt.parseString("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']})
patt.parseString("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1)
# exact match
patt.parseString("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']})
# close match allowing up to 2 mismatches
patt = CloseMatch("ATCATCGAATGGA", maxMismatches=2)
patt.parseString("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']})
"""
def __init__(self, match_string, maxMismatches=1):
super(CloseMatch,self).__init__()
self.name = match_string
self.match_string = match_string
self.maxMismatches = maxMismatches
self.errmsg = "Expected %r (with up to %d mismatches)" % (self.match_string, self.maxMismatches)
self.mayIndexError = False
self.mayReturnEmpty = False
def parseImpl( self, instring, loc, doActions=True ):
start = loc
instrlen = len(instring)
maxloc = start + len(self.match_string)
if maxloc <= instrlen:
match_string = self.match_string
match_stringloc = 0
mismatches = []
maxMismatches = self.maxMismatches
for match_stringloc,s_m in enumerate(zip(instring[loc:maxloc], self.match_string)):
src,mat = s_m
if src != mat:
mismatches.append(match_stringloc)
if len(mismatches) > maxMismatches:
break
else:
loc = match_stringloc + 1
results = ParseResults([instring[start:loc]])
results['original'] = self.match_string
results['mismatches'] = mismatches
return loc, results
raise ParseException(instring, loc, self.errmsg, self)
class Word(Token):
"""
Token for matching words composed of allowed character sets.
Defined with string containing all allowed initial characters,
an optional string containing allowed body characters (if omitted,
defaults to the initial character set), and an optional minimum,
maximum, and/or exact length. The default value for C{min} is 1 (a
minimum value < 1 is not valid); the default values for C{max} and C{exact}
are 0, meaning no maximum or exact length restriction. An optional
C{excludeChars} parameter can list characters that might be found in
the input C{bodyChars} string; useful to define a word of all printables
except for one or two characters, for instance.
L{srange} is useful for defining custom character set strings for defining
C{Word} expressions, using range notation from regular expression character sets.
A common mistake is to use C{Word} to match a specific literal string, as in
C{Word("Address")}. Remember that C{Word} uses the string argument to define
I{sets} of matchable characters. This expression would match "Add", "AAA",
"dAred", or any other word made up of the characters 'A', 'd', 'r', 'e', and 's'.
To match an exact literal string, use L{Literal} or L{Keyword}.
pyparsing includes helper strings for building Words:
- L{alphas}
- L{nums}
- L{alphanums}
- L{hexnums}
- L{alphas8bit} (alphabetic characters in ASCII range 128-255 - accented, tilded, umlauted, etc.)
- L{punc8bit} (non-alphabetic characters in ASCII range 128-255 - currency, symbols, superscripts, diacriticals, etc.)
- L{printables} (any non-whitespace character)
Example::
# a word composed of digits
integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9"))
# a word with a leading capital, and zero or more lowercase
capital_word = Word(alphas.upper(), alphas.lower())
# hostnames are alphanumeric, with leading alpha, and '-'
hostname = Word(alphas, alphanums+'-')
# roman numeral (not a strict parser, accepts invalid mix of characters)
roman = Word("IVXLCDM")
# any string of non-whitespace characters, except for ','
csv_value = Word(printables, excludeChars=",")
"""
def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ):
super(Word,self).__init__()
if excludeChars:
initChars = ''.join(c for c in initChars if c not in excludeChars)
if bodyChars:
bodyChars = ''.join(c for c in bodyChars if c not in excludeChars)
self.initCharsOrig = initChars
self.initChars = set(initChars)
if bodyChars :
self.bodyCharsOrig = bodyChars
self.bodyChars = set(bodyChars)
else:
self.bodyCharsOrig = initChars
self.bodyChars = set(initChars)
self.maxSpecified = max > 0
if min < 1:
raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted")
self.minLen = min
if max > 0:
self.maxLen = max
else:
self.maxLen = _MAX_INT
if exact > 0:
self.maxLen = exact
self.minLen = exact
self.name = _ustr(self)
self.errmsg = "Expected " + self.name
self.mayIndexError = False
self.asKeyword = asKeyword
if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0):
if self.bodyCharsOrig == self.initCharsOrig:
self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig)
elif len(self.initCharsOrig) == 1:
self.reString = "%s[%s]*" % \
(re.escape(self.initCharsOrig),
_escapeRegexRangeChars(self.bodyCharsOrig),)
else:
self.reString = "[%s][%s]*" % \
(_escapeRegexRangeChars(self.initCharsOrig),
_escapeRegexRangeChars(self.bodyCharsOrig),)
if self.asKeyword:
self.reString = r"\b"+self.reString+r"\b"
try:
self.re = re.compile( self.reString )
except Exception:
self.re = None
def parseImpl( self, instring, loc, doActions=True ):
if self.re:
result = self.re.match(instring,loc)
if not result:
raise ParseException(instring, loc, self.errmsg, self)
loc = result.end()
return loc, result.group()
if not(instring[ loc ] in self.initChars):
raise ParseException(instring, loc, self.errmsg, self)
start = loc
loc += 1
instrlen = len(instring)
bodychars = self.bodyChars
maxloc = start + self.maxLen
maxloc = min( maxloc, instrlen )
while loc < maxloc and instring[loc] in bodychars:
loc += 1
throwException = False
if loc - start < self.minLen:
throwException = True
if self.maxSpecified and loc < instrlen and instring[loc] in bodychars:
throwException = True
if self.asKeyword:
if (start>0 and instring[start-1] in bodychars) or (loc<instrlen and instring[loc] in bodychars):
throwException = True
if throwException:
raise ParseException(instring, loc, self.errmsg, self)
return loc, instring[start:loc]
def __str__( self ):
try:
return super(Word,self).__str__()
except Exception:
pass
if self.strRepr is None:
def charsAsStr(s):
if len(s)>4:
return s[:4]+"..."
else:
return s
if ( self.initCharsOrig != self.bodyCharsOrig ):
self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) )
else:
self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig)
return self.strRepr
class Regex(Token):
"""
Token for matching strings that match a given regular expression.
Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module.
If the given regex contains named groups (defined using C{(?P<name>...)}), these will be preserved as
named parse results.
Example::
realnum = Regex(r"[+-]?\d+\.\d*")
date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)')
# ref: http://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression
roman = Regex(r"M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})")
"""
compiledREtype = type(re.compile("[A-Z]"))
def __init__( self, pattern, flags=0):
"""The parameters C{pattern} and C{flags} are passed to the C{re.compile()} function as-is. See the Python C{re} module for an explanation of the acceptable patterns and flags."""
super(Regex,self).__init__()
if isinstance(pattern, basestring):
if not pattern:
warnings.warn("null string passed to Regex; use Empty() instead",
SyntaxWarning, stacklevel=2)
self.pattern = pattern
self.flags = flags
try:
self.re = re.compile(self.pattern, self.flags)
self.reString = self.pattern
except sre_constants.error:
warnings.warn("invalid pattern (%s) passed to Regex" % pattern,
SyntaxWarning, stacklevel=2)
raise
elif isinstance(pattern, Regex.compiledREtype):
self.re = pattern
self.pattern = \
self.reString = str(pattern)
self.flags = flags
else:
raise ValueError("Regex may only be constructed with a string or a compiled RE object")
self.name = _ustr(self)
self.errmsg = "Expected " + self.name
self.mayIndexError = False
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
result = self.re.match(instring,loc)
if not result:
raise ParseException(instring, loc, self.errmsg, self)
loc = result.end()
d = result.groupdict()
ret = ParseResults(result.group())
if d:
for k in d:
ret[k] = d[k]
return loc,ret
def __str__( self ):
try:
return super(Regex,self).__str__()
except Exception:
pass
if self.strRepr is None:
self.strRepr = "Re:(%s)" % repr(self.pattern)
return self.strRepr
class QuotedString(Token):
r"""
Token for matching strings that are delimited by quoting characters.
Defined with the following parameters:
- quoteChar - string of one or more characters defining the quote delimiting string
- escChar - character to escape quotes, typically backslash (default=C{None})
- escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=C{None})
- multiline - boolean indicating whether quotes can span multiple lines (default=C{False})
- unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True})
- endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar)
- convertWhitespaceEscapes - convert escaped whitespace (C{'\t'}, C{'\n'}, etc.) to actual whitespace (default=C{True})
Example::
qs = QuotedString('"')
print(qs.searchString('lsjdf "This is the quote" sldjf'))
complex_qs = QuotedString('{{', endQuoteChar='}}')
print(complex_qs.searchString('lsjdf {{This is the "quote"}} sldjf'))
sql_qs = QuotedString('"', escQuote='""')
print(sql_qs.searchString('lsjdf "This is the quote with ""embedded"" quotes" sldjf'))
prints::
[['This is the quote']]
[['This is the "quote"']]
[['This is the quote with "embedded" quotes']]
"""
def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None, convertWhitespaceEscapes=True):
super(QuotedString,self).__init__()
# remove white space from quote chars - wont work anyway
quoteChar = quoteChar.strip()
if not quoteChar:
warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
raise SyntaxError()
if endQuoteChar is None:
endQuoteChar = quoteChar
else:
endQuoteChar = endQuoteChar.strip()
if not endQuoteChar:
warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
raise SyntaxError()
self.quoteChar = quoteChar
self.quoteCharLen = len(quoteChar)
self.firstQuoteChar = quoteChar[0]
self.endQuoteChar = endQuoteChar
self.endQuoteCharLen = len(endQuoteChar)
self.escChar = escChar
self.escQuote = escQuote
self.unquoteResults = unquoteResults
self.convertWhitespaceEscapes = convertWhitespaceEscapes
if multiline:
self.flags = re.MULTILINE | re.DOTALL
self.pattern = r'%s(?:[^%s%s]' % \
( re.escape(self.quoteChar),
_escapeRegexRangeChars(self.endQuoteChar[0]),
(escChar is not None and _escapeRegexRangeChars(escChar) or '') )
else:
self.flags = 0
self.pattern = r'%s(?:[^%s\n\r%s]' % \
( re.escape(self.quoteChar),
_escapeRegexRangeChars(self.endQuoteChar[0]),
(escChar is not None and _escapeRegexRangeChars(escChar) or '') )
if len(self.endQuoteChar) > 1:
self.pattern += (
'|(?:' + ')|(?:'.join("%s[^%s]" % (re.escape(self.endQuoteChar[:i]),
_escapeRegexRangeChars(self.endQuoteChar[i]))
for i in range(len(self.endQuoteChar)-1,0,-1)) + ')'
)
if escQuote:
self.pattern += (r'|(?:%s)' % re.escape(escQuote))
if escChar:
self.pattern += (r'|(?:%s.)' % re.escape(escChar))
self.escCharReplacePattern = re.escape(self.escChar)+"(.)"
self.pattern += (r')*%s' % re.escape(self.endQuoteChar))
try:
self.re = re.compile(self.pattern, self.flags)
self.reString = self.pattern
except sre_constants.error:
warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern,
SyntaxWarning, stacklevel=2)
raise
self.name = _ustr(self)
self.errmsg = "Expected " + self.name
self.mayIndexError = False
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None
if not result:
raise ParseException(instring, loc, self.errmsg, self)
loc = result.end()
ret = result.group()
if self.unquoteResults:
# strip off quotes
ret = ret[self.quoteCharLen:-self.endQuoteCharLen]
if isinstance(ret,basestring):
# replace escaped whitespace
if '\\' in ret and self.convertWhitespaceEscapes:
ws_map = {
r'\t' : '\t',
r'\n' : '\n',
r'\f' : '\f',
r'\r' : '\r',
}
for wslit,wschar in ws_map.items():
ret = ret.replace(wslit, wschar)
# replace escaped characters
if self.escChar:
ret = re.sub(self.escCharReplacePattern,"\g<1>",ret)
# replace escaped quotes
if self.escQuote:
ret = ret.replace(self.escQuote, self.endQuoteChar)
return loc, ret
def __str__( self ):
try:
return super(QuotedString,self).__str__()
except Exception:
pass
if self.strRepr is None:
self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar)
return self.strRepr
class CharsNotIn(Token):
"""
Token for matching words composed of characters I{not} in a given set (will
include whitespace in matched characters if not listed in the provided exclusion set - see example).
Defined with string containing all disallowed characters, and an optional
minimum, maximum, and/or exact length. The default value for C{min} is 1 (a
minimum value < 1 is not valid); the default values for C{max} and C{exact}
are 0, meaning no maximum or exact length restriction.
Example::
# define a comma-separated-value as anything that is not a ','
csv_value = CharsNotIn(',')
print(delimitedList(csv_value).parseString("dkls,lsdkjf,s12 34,@!#,213"))
prints::
['dkls', 'lsdkjf', 's12 34', '@!#', '213']
"""
def __init__( self, notChars, min=1, max=0, exact=0 ):
super(CharsNotIn,self).__init__()
self.skipWhitespace = False
self.notChars = notChars
if min < 1:
raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted")
self.minLen = min
if max > 0:
self.maxLen = max
else:
self.maxLen = _MAX_INT
if exact > 0:
self.maxLen = exact
self.minLen = exact
self.name = _ustr(self)
self.errmsg = "Expected " + self.name
self.mayReturnEmpty = ( self.minLen == 0 )
self.mayIndexError = False
def parseImpl( self, instring, loc, doActions=True ):
if instring[loc] in self.notChars:
raise ParseException(instring, loc, self.errmsg, self)
start = loc
loc += 1
notchars = self.notChars
maxlen = min( start+self.maxLen, len(instring) )
while loc < maxlen and \
(instring[loc] not in notchars):
loc += 1
if loc - start < self.minLen:
raise ParseException(instring, loc, self.errmsg, self)
return loc, instring[start:loc]
def __str__( self ):
try:
return super(CharsNotIn, self).__str__()
except Exception:
pass
if self.strRepr is None:
if len(self.notChars) > 4:
self.strRepr = "!W:(%s...)" % self.notChars[:4]
else:
self.strRepr = "!W:(%s)" % self.notChars
return self.strRepr
class White(Token):
"""
Special matching class for matching whitespace. Normally, whitespace is ignored
by pyparsing grammars. This class is included when some whitespace structures
are significant. Define with a string containing the whitespace characters to be
matched; default is C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments,
as defined for the C{L{Word}} class.
"""
whiteStrs = {
" " : "<SPC>",
"\t": "<TAB>",
"\n": "<LF>",
"\r": "<CR>",
"\f": "<FF>",
}
def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0):
super(White,self).__init__()
self.matchWhite = ws
self.setWhitespaceChars( "".join(c for c in self.whiteChars if c not in self.matchWhite) )
#~ self.leaveWhitespace()
self.name = ("".join(White.whiteStrs[c] for c in self.matchWhite))
self.mayReturnEmpty = True
self.errmsg = "Expected " + self.name
self.minLen = min
if max > 0:
self.maxLen = max
else:
self.maxLen = _MAX_INT
if exact > 0:
self.maxLen = exact
self.minLen = exact
def parseImpl( self, instring, loc, doActions=True ):
if not(instring[ loc ] in self.matchWhite):
raise ParseException(instring, loc, self.errmsg, self)
start = loc
loc += 1
maxloc = start + self.maxLen
maxloc = min( maxloc, len(instring) )
while loc < maxloc and instring[loc] in self.matchWhite:
loc += 1
if loc - start < self.minLen:
raise ParseException(instring, loc, self.errmsg, self)
return loc, instring[start:loc]
class _PositionToken(Token):
def __init__( self ):
super(_PositionToken,self).__init__()
self.name=self.__class__.__name__
self.mayReturnEmpty = True
self.mayIndexError = False
class GoToColumn(_PositionToken):
"""
Token to advance to a specific column of input text; useful for tabular report scraping.
"""
def __init__( self, colno ):
super(GoToColumn,self).__init__()
self.col = colno
def preParse( self, instring, loc ):
if col(loc,instring) != self.col:
instrlen = len(instring)
if self.ignoreExprs:
loc = self._skipIgnorables( instring, loc )
while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col :
loc += 1
return loc
def parseImpl( self, instring, loc, doActions=True ):
thiscol = col( loc, instring )
if thiscol > self.col:
raise ParseException( instring, loc, "Text not in expected column", self )
newloc = loc + self.col - thiscol
ret = instring[ loc: newloc ]
return newloc, ret
class LineStart(_PositionToken):
"""
Matches if current position is at the beginning of a line within the parse string
Example::
test = '''\
AAA this line
AAA and this line
AAA but not this one
B AAA and definitely not this one
'''
for t in (LineStart() + 'AAA' + restOfLine).searchString(test):
print(t)
Prints::
['AAA', ' this line']
['AAA', ' and this line']
"""
def __init__( self ):
super(LineStart,self).__init__()
self.errmsg = "Expected start of line"
def parseImpl( self, instring, loc, doActions=True ):
if col(loc, instring) == 1:
return loc, []
raise ParseException(instring, loc, self.errmsg, self)
class LineEnd(_PositionToken):
"""
Matches if current position is at the end of a line within the parse string
"""
def __init__( self ):
super(LineEnd,self).__init__()
self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") )
self.errmsg = "Expected end of line"
def parseImpl( self, instring, loc, doActions=True ):
if loc<len(instring):
if instring[loc] == "\n":
return loc+1, "\n"
else:
raise ParseException(instring, loc, self.errmsg, self)
elif loc == len(instring):
return loc+1, []
else:
raise ParseException(instring, loc, self.errmsg, self)
class StringStart(_PositionToken):
"""
Matches if current position is at the beginning of the parse string
"""
def __init__( self ):
super(StringStart,self).__init__()
self.errmsg = "Expected start of text"
def parseImpl( self, instring, loc, doActions=True ):
if loc != 0:
# see if entire string up to here is just whitespace and ignoreables
if loc != self.preParse( instring, 0 ):
raise ParseException(instring, loc, self.errmsg, self)
return loc, []
class StringEnd(_PositionToken):
"""
Matches if current position is at the end of the parse string
"""
def __init__( self ):
super(StringEnd,self).__init__()
self.errmsg = "Expected end of text"
def parseImpl( self, instring, loc, doActions=True ):
if loc < len(instring):
raise ParseException(instring, loc, self.errmsg, self)
elif loc == len(instring):
return loc+1, []
elif loc > len(instring):
return loc, []
else:
raise ParseException(instring, loc, self.errmsg, self)
class WordStart(_PositionToken):
"""
Matches if the current position is at the beginning of a Word, and
is not preceded by any character in a given set of C{wordChars}
(default=C{printables}). To emulate the C{\b} behavior of regular expressions,
use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of
the string being parsed, or at the beginning of a line.
"""
def __init__(self, wordChars = printables):
super(WordStart,self).__init__()
self.wordChars = set(wordChars)
self.errmsg = "Not at the start of a word"
def parseImpl(self, instring, loc, doActions=True ):
if loc != 0:
if (instring[loc-1] in self.wordChars or
instring[loc] not in self.wordChars):
raise ParseException(instring, loc, self.errmsg, self)
return loc, []
class WordEnd(_PositionToken):
"""
Matches if the current position is at the end of a Word, and
is not followed by any character in a given set of C{wordChars}
(default=C{printables}). To emulate the C{\b} behavior of regular expressions,
use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of
the string being parsed, or at the end of a line.
"""
def __init__(self, wordChars = printables):
super(WordEnd,self).__init__()
self.wordChars = set(wordChars)
self.skipWhitespace = False
self.errmsg = "Not at the end of a word"
def parseImpl(self, instring, loc, doActions=True ):
instrlen = len(instring)
if instrlen>0 and loc<instrlen:
if (instring[loc] in self.wordChars or
instring[loc-1] not in self.wordChars):
raise ParseException(instring, loc, self.errmsg, self)
return loc, []
class ParseExpression(ParserElement):
"""
Abstract subclass of ParserElement, for combining and post-processing parsed tokens.
"""
def __init__( self, exprs, savelist = False ):
super(ParseExpression,self).__init__(savelist)
if isinstance( exprs, _generatorType ):
exprs = list(exprs)
if isinstance( exprs, basestring ):
self.exprs = [ ParserElement._literalStringClass( exprs ) ]
elif isinstance( exprs, collections.Iterable ):
exprs = list(exprs)
# if sequence of strings provided, wrap with Literal
if all(isinstance(expr, basestring) for expr in exprs):
exprs = map(ParserElement._literalStringClass, exprs)
self.exprs = list(exprs)
else:
try:
self.exprs = list( exprs )
except TypeError:
self.exprs = [ exprs ]
self.callPreparse = False
def __getitem__( self, i ):
return self.exprs[i]
def append( self, other ):
self.exprs.append( other )
self.strRepr = None
return self
def leaveWhitespace( self ):
"""Extends C{leaveWhitespace} defined in base class, and also invokes C{leaveWhitespace} on
all contained expressions."""
self.skipWhitespace = False
self.exprs = [ e.copy() for e in self.exprs ]
for e in self.exprs:
e.leaveWhitespace()
return self
def ignore( self, other ):
if isinstance( other, Suppress ):
if other not in self.ignoreExprs:
super( ParseExpression, self).ignore( other )
for e in self.exprs:
e.ignore( self.ignoreExprs[-1] )
else:
super( ParseExpression, self).ignore( other )
for e in self.exprs:
e.ignore( self.ignoreExprs[-1] )
return self
def __str__( self ):
try:
return super(ParseExpression,self).__str__()
except Exception:
pass
if self.strRepr is None:
self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.exprs) )
return self.strRepr
def streamline( self ):
super(ParseExpression,self).streamline()
for e in self.exprs:
e.streamline()
# collapse nested And's of the form And( And( And( a,b), c), d) to And( a,b,c,d )
# but only if there are no parse actions or resultsNames on the nested And's
# (likewise for Or's and MatchFirst's)
if ( len(self.exprs) == 2 ):
other = self.exprs[0]
if ( isinstance( other, self.__class__ ) and
not(other.parseAction) and
other.resultsName is None and
not other.debug ):
self.exprs = other.exprs[:] + [ self.exprs[1] ]
self.strRepr = None
self.mayReturnEmpty |= other.mayReturnEmpty
self.mayIndexError |= other.mayIndexError
other = self.exprs[-1]
if ( isinstance( other, self.__class__ ) and
not(other.parseAction) and
other.resultsName is None and
not other.debug ):
self.exprs = self.exprs[:-1] + other.exprs[:]
self.strRepr = None
self.mayReturnEmpty |= other.mayReturnEmpty
self.mayIndexError |= other.mayIndexError
self.errmsg = "Expected " + _ustr(self)
return self
def setResultsName( self, name, listAllMatches=False ):
ret = super(ParseExpression,self).setResultsName(name,listAllMatches)
return ret
def validate( self, validateTrace=[] ):
tmp = validateTrace[:]+[self]
for e in self.exprs:
e.validate(tmp)
self.checkRecursion( [] )
def copy(self):
ret = super(ParseExpression,self).copy()
ret.exprs = [e.copy() for e in self.exprs]
return ret
class And(ParseExpression):
"""
Requires all given C{ParseExpression}s to be found in the given order.
Expressions may be separated by whitespace.
May be constructed using the C{'+'} operator.
May also be constructed using the C{'-'} operator, which will suppress backtracking.
Example::
integer = Word(nums)
name_expr = OneOrMore(Word(alphas))
expr = And([integer("id"),name_expr("name"),integer("age")])
# more easily written as:
expr = integer("id") + name_expr("name") + integer("age")
"""
class _ErrorStop(Empty):
def __init__(self, *args, **kwargs):
super(And._ErrorStop,self).__init__(*args, **kwargs)
self.name = '-'
self.leaveWhitespace()
def __init__( self, exprs, savelist = True ):
super(And,self).__init__(exprs, savelist)
self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs)
self.setWhitespaceChars( self.exprs[0].whiteChars )
self.skipWhitespace = self.exprs[0].skipWhitespace
self.callPreparse = True
def parseImpl( self, instring, loc, doActions=True ):
# pass False as last arg to _parse for first element, since we already
# pre-parsed the string as part of our And pre-parsing
loc, resultlist = self.exprs[0]._parse( instring, loc, doActions, callPreParse=False )
errorStop = False
for e in self.exprs[1:]:
if isinstance(e, And._ErrorStop):
errorStop = True
continue
if errorStop:
try:
loc, exprtokens = e._parse( instring, loc, doActions )
except ParseSyntaxException:
raise
except ParseBaseException as pe:
pe.__traceback__ = None
raise ParseSyntaxException._from_exception(pe)
except IndexError:
raise ParseSyntaxException(instring, len(instring), self.errmsg, self)
else:
loc, exprtokens = e._parse( instring, loc, doActions )
if exprtokens or exprtokens.haskeys():
resultlist += exprtokens
return loc, resultlist
def __iadd__(self, other ):
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
return self.append( other ) #And( [ self, other ] )
def checkRecursion( self, parseElementList ):
subRecCheckList = parseElementList[:] + [ self ]
for e in self.exprs:
e.checkRecursion( subRecCheckList )
if not e.mayReturnEmpty:
break
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "{" + " ".join(_ustr(e) for e in self.exprs) + "}"
return self.strRepr
class Or(ParseExpression):
"""
Requires that at least one C{ParseExpression} is found.
If two expressions match, the expression that matches the longest string will be used.
May be constructed using the C{'^'} operator.
Example::
# construct Or using '^' operator
number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums))
print(number.searchString("123 3.1416 789"))
prints::
[['123'], ['3.1416'], ['789']]
"""
def __init__( self, exprs, savelist = False ):
super(Or,self).__init__(exprs, savelist)
if self.exprs:
self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs)
else:
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
maxExcLoc = -1
maxException = None
matches = []
for e in self.exprs:
try:
loc2 = e.tryParse( instring, loc )
except ParseException as err:
err.__traceback__ = None
if err.loc > maxExcLoc:
maxException = err
maxExcLoc = err.loc
except IndexError:
if len(instring) > maxExcLoc:
maxException = ParseException(instring,len(instring),e.errmsg,self)
maxExcLoc = len(instring)
else:
# save match among all matches, to retry longest to shortest
matches.append((loc2, e))
if matches:
matches.sort(key=lambda x: -x[0])
for _,e in matches:
try:
return e._parse( instring, loc, doActions )
except ParseException as err:
err.__traceback__ = None
if err.loc > maxExcLoc:
maxException = err
maxExcLoc = err.loc
if maxException is not None:
maxException.msg = self.errmsg
raise maxException
else:
raise ParseException(instring, loc, "no defined alternatives to match", self)
def __ixor__(self, other ):
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
return self.append( other ) #Or( [ self, other ] )
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "{" + " ^ ".join(_ustr(e) for e in self.exprs) + "}"
return self.strRepr
def checkRecursion( self, parseElementList ):
subRecCheckList = parseElementList[:] + [ self ]
for e in self.exprs:
e.checkRecursion( subRecCheckList )
class MatchFirst(ParseExpression):
"""
Requires that at least one C{ParseExpression} is found.
If two expressions match, the first one listed is the one that will match.
May be constructed using the C{'|'} operator.
Example::
# construct MatchFirst using '|' operator
# watch the order of expressions to match
number = Word(nums) | Combine(Word(nums) + '.' + Word(nums))
print(number.searchString("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']]
# put more selective expression first
number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums)
print(number.searchString("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']]
"""
def __init__( self, exprs, savelist = False ):
super(MatchFirst,self).__init__(exprs, savelist)
if self.exprs:
self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs)
else:
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
maxExcLoc = -1
maxException = None
for e in self.exprs:
try:
ret = e._parse( instring, loc, doActions )
return ret
except ParseException as err:
if err.loc > maxExcLoc:
maxException = err
maxExcLoc = err.loc
except IndexError:
if len(instring) > maxExcLoc:
maxException = ParseException(instring,len(instring),e.errmsg,self)
maxExcLoc = len(instring)
# only got here if no expression matched, raise exception for match that made it the furthest
else:
if maxException is not None:
maxException.msg = self.errmsg
raise maxException
else:
raise ParseException(instring, loc, "no defined alternatives to match", self)
def __ior__(self, other ):
if isinstance( other, basestring ):
other = ParserElement._literalStringClass( other )
return self.append( other ) #MatchFirst( [ self, other ] )
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "{" + " | ".join(_ustr(e) for e in self.exprs) + "}"
return self.strRepr
def checkRecursion( self, parseElementList ):
subRecCheckList = parseElementList[:] + [ self ]
for e in self.exprs:
e.checkRecursion( subRecCheckList )
class Each(ParseExpression):
"""
Requires all given C{ParseExpression}s to be found, but in any order.
Expressions may be separated by whitespace.
May be constructed using the C{'&'} operator.
Example::
color = oneOf("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN")
shape_type = oneOf("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON")
integer = Word(nums)
shape_attr = "shape:" + shape_type("shape")
posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn")
color_attr = "color:" + color("color")
size_attr = "size:" + integer("size")
# use Each (using operator '&') to accept attributes in any order
# (shape and posn are required, color and size are optional)
shape_spec = shape_attr & posn_attr & Optional(color_attr) & Optional(size_attr)
shape_spec.runTests('''
shape: SQUARE color: BLACK posn: 100, 120
shape: CIRCLE size: 50 color: BLUE posn: 50,80
color:GREEN size:20 shape:TRIANGLE posn:20,40
'''
)
prints::
shape: SQUARE color: BLACK posn: 100, 120
['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']]
- color: BLACK
- posn: ['100', ',', '120']
- x: 100
- y: 120
- shape: SQUARE
shape: CIRCLE size: 50 color: BLUE posn: 50,80
['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']]
- color: BLUE
- posn: ['50', ',', '80']
- x: 50
- y: 80
- shape: CIRCLE
- size: 50
color: GREEN size: 20 shape: TRIANGLE posn: 20,40
['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']]
- color: GREEN
- posn: ['20', ',', '40']
- x: 20
- y: 40
- shape: TRIANGLE
- size: 20
"""
def __init__( self, exprs, savelist = True ):
super(Each,self).__init__(exprs, savelist)
self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs)
self.skipWhitespace = True
self.initExprGroups = True
def parseImpl( self, instring, loc, doActions=True ):
if self.initExprGroups:
self.opt1map = dict((id(e.expr),e) for e in self.exprs if isinstance(e,Optional))
opt1 = [ e.expr for e in self.exprs if isinstance(e,Optional) ]
opt2 = [ e for e in self.exprs if e.mayReturnEmpty and not isinstance(e,Optional)]
self.optionals = opt1 + opt2
self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ]
self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ]
self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ]
self.required += self.multirequired
self.initExprGroups = False
tmpLoc = loc
tmpReqd = self.required[:]
tmpOpt = self.optionals[:]
matchOrder = []
keepMatching = True
while keepMatching:
tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired
failed = []
for e in tmpExprs:
try:
tmpLoc = e.tryParse( instring, tmpLoc )
except ParseException:
failed.append(e)
else:
matchOrder.append(self.opt1map.get(id(e),e))
if e in tmpReqd:
tmpReqd.remove(e)
elif e in tmpOpt:
tmpOpt.remove(e)
if len(failed) == len(tmpExprs):
keepMatching = False
if tmpReqd:
missing = ", ".join(_ustr(e) for e in tmpReqd)
raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing )
# add any unmatched Optionals, in case they have default values defined
matchOrder += [e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt]
resultlist = []
for e in matchOrder:
loc,results = e._parse(instring,loc,doActions)
resultlist.append(results)
finalResults = sum(resultlist, ParseResults([]))
return loc, finalResults
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "{" + " & ".join(_ustr(e) for e in self.exprs) + "}"
return self.strRepr
def checkRecursion( self, parseElementList ):
subRecCheckList = parseElementList[:] + [ self ]
for e in self.exprs:
e.checkRecursion( subRecCheckList )
class ParseElementEnhance(ParserElement):
"""
Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.
"""
def __init__( self, expr, savelist=False ):
super(ParseElementEnhance,self).__init__(savelist)
if isinstance( expr, basestring ):
if issubclass(ParserElement._literalStringClass, Token):
expr = ParserElement._literalStringClass(expr)
else:
expr = ParserElement._literalStringClass(Literal(expr))
self.expr = expr
self.strRepr = None
if expr is not None:
self.mayIndexError = expr.mayIndexError
self.mayReturnEmpty = expr.mayReturnEmpty
self.setWhitespaceChars( expr.whiteChars )
self.skipWhitespace = expr.skipWhitespace
self.saveAsList = expr.saveAsList
self.callPreparse = expr.callPreparse
self.ignoreExprs.extend(expr.ignoreExprs)
def parseImpl( self, instring, loc, doActions=True ):
if self.expr is not None:
return self.expr._parse( instring, loc, doActions, callPreParse=False )
else:
raise ParseException("",loc,self.errmsg,self)
def leaveWhitespace( self ):
self.skipWhitespace = False
self.expr = self.expr.copy()
if self.expr is not None:
self.expr.leaveWhitespace()
return self
def ignore( self, other ):
if isinstance( other, Suppress ):
if other not in self.ignoreExprs:
super( ParseElementEnhance, self).ignore( other )
if self.expr is not None:
self.expr.ignore( self.ignoreExprs[-1] )
else:
super( ParseElementEnhance, self).ignore( other )
if self.expr is not None:
self.expr.ignore( self.ignoreExprs[-1] )
return self
def streamline( self ):
super(ParseElementEnhance,self).streamline()
if self.expr is not None:
self.expr.streamline()
return self
def checkRecursion( self, parseElementList ):
if self in parseElementList:
raise RecursiveGrammarException( parseElementList+[self] )
subRecCheckList = parseElementList[:] + [ self ]
if self.expr is not None:
self.expr.checkRecursion( subRecCheckList )
def validate( self, validateTrace=[] ):
tmp = validateTrace[:]+[self]
if self.expr is not None:
self.expr.validate(tmp)
self.checkRecursion( [] )
def __str__( self ):
try:
return super(ParseElementEnhance,self).__str__()
except Exception:
pass
if self.strRepr is None and self.expr is not None:
self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) )
return self.strRepr
class FollowedBy(ParseElementEnhance):
"""
Lookahead matching of the given parse expression. C{FollowedBy}
does I{not} advance the parsing position within the input string, it only
verifies that the specified parse expression matches at the current
position. C{FollowedBy} always returns a null token list.
Example::
# use FollowedBy to match a label only if it is followed by a ':'
data_word = Word(alphas)
label = data_word + FollowedBy(':')
attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
OneOrMore(attr_expr).parseString("shape: SQUARE color: BLACK posn: upper left").pprint()
prints::
[['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']]
"""
def __init__( self, expr ):
super(FollowedBy,self).__init__(expr)
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
self.expr.tryParse( instring, loc )
return loc, []
class NotAny(ParseElementEnhance):
"""
Lookahead to disallow matching with the given parse expression. C{NotAny}
does I{not} advance the parsing position within the input string, it only
verifies that the specified parse expression does I{not} match at the current
position. Also, C{NotAny} does I{not} skip over leading whitespace. C{NotAny}
always returns a null token list. May be constructed using the '~' operator.
Example::
"""
def __init__( self, expr ):
super(NotAny,self).__init__(expr)
#~ self.leaveWhitespace()
self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs
self.mayReturnEmpty = True
self.errmsg = "Found unwanted token, "+_ustr(self.expr)
def parseImpl( self, instring, loc, doActions=True ):
if self.expr.canParseNext(instring, loc):
raise ParseException(instring, loc, self.errmsg, self)
return loc, []
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "~{" + _ustr(self.expr) + "}"
return self.strRepr
class _MultipleMatch(ParseElementEnhance):
def __init__( self, expr, stopOn=None):
super(_MultipleMatch, self).__init__(expr)
self.saveAsList = True
ender = stopOn
if isinstance(ender, basestring):
ender = ParserElement._literalStringClass(ender)
self.not_ender = ~ender if ender is not None else None
def parseImpl( self, instring, loc, doActions=True ):
self_expr_parse = self.expr._parse
self_skip_ignorables = self._skipIgnorables
check_ender = self.not_ender is not None
if check_ender:
try_not_ender = self.not_ender.tryParse
# must be at least one (but first see if we are the stopOn sentinel;
# if so, fail)
if check_ender:
try_not_ender(instring, loc)
loc, tokens = self_expr_parse( instring, loc, doActions, callPreParse=False )
try:
hasIgnoreExprs = (not not self.ignoreExprs)
while 1:
if check_ender:
try_not_ender(instring, loc)
if hasIgnoreExprs:
preloc = self_skip_ignorables( instring, loc )
else:
preloc = loc
loc, tmptokens = self_expr_parse( instring, preloc, doActions )
if tmptokens or tmptokens.haskeys():
tokens += tmptokens
except (ParseException,IndexError):
pass
return loc, tokens
class OneOrMore(_MultipleMatch):
"""
Repetition of one or more of the given expression.
Parameters:
- expr - expression that must match one or more times
- stopOn - (default=C{None}) - expression for a terminating sentinel
(only required if the sentinel would ordinarily match the repetition
expression)
Example::
data_word = Word(alphas)
label = data_word + FollowedBy(':')
attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
text = "shape: SQUARE posn: upper left color: BLACK"
OneOrMore(attr_expr).parseString(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']]
# use stopOn attribute for OneOrMore to avoid reading label string as part of the data
attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
OneOrMore(attr_expr).parseString(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']]
# could also be written as
(attr_expr * (1,)).parseString(text).pprint()
"""
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "{" + _ustr(self.expr) + "}..."
return self.strRepr
class ZeroOrMore(_MultipleMatch):
"""
Optional repetition of zero or more of the given expression.
Parameters:
- expr - expression that must match zero or more times
- stopOn - (default=C{None}) - expression for a terminating sentinel
(only required if the sentinel would ordinarily match the repetition
expression)
Example: similar to L{OneOrMore}
"""
def __init__( self, expr, stopOn=None):
super(ZeroOrMore,self).__init__(expr, stopOn=stopOn)
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
try:
return super(ZeroOrMore, self).parseImpl(instring, loc, doActions)
except (ParseException,IndexError):
return loc, []
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "[" + _ustr(self.expr) + "]..."
return self.strRepr
class _NullToken(object):
def __bool__(self):
return False
__nonzero__ = __bool__
def __str__(self):
return ""
_optionalNotMatched = _NullToken()
class Optional(ParseElementEnhance):
"""
Optional matching of the given expression.
Parameters:
- expr - expression that must match zero or more times
- default (optional) - value to be returned if the optional expression is not found.
Example::
# US postal code can be a 5-digit zip, plus optional 4-digit qualifier
zip = Combine(Word(nums, exact=5) + Optional('-' + Word(nums, exact=4)))
zip.runTests('''
# traditional ZIP code
12345
# ZIP+4 form
12101-0001
# invalid ZIP
98765-
''')
prints::
# traditional ZIP code
12345
['12345']
# ZIP+4 form
12101-0001
['12101-0001']
# invalid ZIP
98765-
^
FAIL: Expected end of text (at char 5), (line:1, col:6)
"""
def __init__( self, expr, default=_optionalNotMatched ):
super(Optional,self).__init__( expr, savelist=False )
self.saveAsList = self.expr.saveAsList
self.defaultValue = default
self.mayReturnEmpty = True
def parseImpl( self, instring, loc, doActions=True ):
try:
loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False )
except (ParseException,IndexError):
if self.defaultValue is not _optionalNotMatched:
if self.expr.resultsName:
tokens = ParseResults([ self.defaultValue ])
tokens[self.expr.resultsName] = self.defaultValue
else:
tokens = [ self.defaultValue ]
else:
tokens = []
return loc, tokens
def __str__( self ):
if hasattr(self,"name"):
return self.name
if self.strRepr is None:
self.strRepr = "[" + _ustr(self.expr) + "]"
return self.strRepr
class SkipTo(ParseElementEnhance):
"""
Token for skipping over all undefined text until the matched expression is found.
Parameters:
- expr - target expression marking the end of the data to be skipped
- include - (default=C{False}) if True, the target expression is also parsed
(the skipped text and target expression are returned as a 2-element list).
- ignore - (default=C{None}) used to define grammars (typically quoted strings and
comments) that might contain false matches to the target expression
- failOn - (default=C{None}) define expressions that are not allowed to be
included in the skipped test; if found before the target expression is found,
the SkipTo is not a match
Example::
report = '''
Outstanding Issues Report - 1 Jan 2000
# | Severity | Description | Days Open
-----+----------+-------------------------------------------+-----------
101 | Critical | Intermittent system crash | 6
94 | Cosmetic | Spelling error on Login ('log|n') | 14
79 | Minor | System slow when running too many reports | 47
'''
integer = Word(nums)
SEP = Suppress('|')
# use SkipTo to simply match everything up until the next SEP
# - ignore quoted strings, so that a '|' character inside a quoted string does not match
# - parse action will call token.strip() for each matched token, i.e., the description body
string_data = SkipTo(SEP, ignore=quotedString)
string_data.setParseAction(tokenMap(str.strip))
ticket_expr = (integer("issue_num") + SEP
+ string_data("sev") + SEP
+ string_data("desc") + SEP
+ integer("days_open"))
for tkt in ticket_expr.searchString(report):
print tkt.dump()
prints::
['101', 'Critical', 'Intermittent system crash', '6']
- days_open: 6
- desc: Intermittent system crash
- issue_num: 101
- sev: Critical
['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14']
- days_open: 14
- desc: Spelling error on Login ('log|n')
- issue_num: 94
- sev: Cosmetic
['79', 'Minor', 'System slow when running too many reports', '47']
- days_open: 47
- desc: System slow when running too many reports
- issue_num: 79
- sev: Minor
"""
def __init__( self, other, include=False, ignore=None, failOn=None ):
super( SkipTo, self ).__init__( other )
self.ignoreExpr = ignore
self.mayReturnEmpty = True
self.mayIndexError = False
self.includeMatch = include
self.asList = False
if isinstance(failOn, basestring):
self.failOn = ParserElement._literalStringClass(failOn)
else:
self.failOn = failOn
self.errmsg = "No match found for "+_ustr(self.expr)
def parseImpl( self, instring, loc, doActions=True ):
startloc = loc
instrlen = len(instring)
expr = self.expr
expr_parse = self.expr._parse
self_failOn_canParseNext = self.failOn.canParseNext if self.failOn is not None else None
self_ignoreExpr_tryParse = self.ignoreExpr.tryParse if self.ignoreExpr is not None else None
tmploc = loc
while tmploc <= instrlen:
if self_failOn_canParseNext is not None:
# break if failOn expression matches
if self_failOn_canParseNext(instring, tmploc):
break
if self_ignoreExpr_tryParse is not None:
# advance past ignore expressions
while 1:
try:
tmploc = self_ignoreExpr_tryParse(instring, tmploc)
except ParseBaseException:
break
try:
expr_parse(instring, tmploc, doActions=False, callPreParse=False)
except (ParseException, IndexError):
# no match, advance loc in string
tmploc += 1
else:
# matched skipto expr, done
break
else:
# ran off the end of the input string without matching skipto expr, fail
raise ParseException(instring, loc, self.errmsg, self)
# build up return values
loc = tmploc
skiptext = instring[startloc:loc]
skipresult = ParseResults(skiptext)
if self.includeMatch:
loc, mat = expr_parse(instring,loc,doActions,callPreParse=False)
skipresult += mat
return loc, skipresult
class Forward(ParseElementEnhance):
"""
Forward declaration of an expression to be defined later -
used for recursive grammars, such as algebraic infix notation.
When the expression is known, it is assigned to the C{Forward} variable using the '<<' operator.
Note: take care when assigning to C{Forward} not to overlook precedence of operators.
Specifically, '|' has a lower precedence than '<<', so that::
fwdExpr << a | b | c
will actually be evaluated as::
(fwdExpr << a) | b | c
thereby leaving b and c out as parseable alternatives. It is recommended that you
explicitly group the values inserted into the C{Forward}::
fwdExpr << (a | b | c)
Converting to use the '<<=' operator instead will avoid this problem.
See L{ParseResults.pprint} for an example of a recursive parser created using
C{Forward}.
"""
def __init__( self, other=None ):
super(Forward,self).__init__( other, savelist=False )
def __lshift__( self, other ):
if isinstance( other, basestring ):
other = ParserElement._literalStringClass(other)
self.expr = other
self.strRepr = None
self.mayIndexError = self.expr.mayIndexError
self.mayReturnEmpty = self.expr.mayReturnEmpty
self.setWhitespaceChars( self.expr.whiteChars )
self.skipWhitespace = self.expr.skipWhitespace
self.saveAsList = self.expr.saveAsList
self.ignoreExprs.extend(self.expr.ignoreExprs)
return self
def __ilshift__(self, other):
return self << other
def leaveWhitespace( self ):
self.skipWhitespace = False
return self
def streamline( self ):
if not self.streamlined:
self.streamlined = True
if self.expr is not None:
self.expr.streamline()
return self
def validate( self, validateTrace=[] ):
if self not in validateTrace:
tmp = validateTrace[:]+[self]
if self.expr is not None:
self.expr.validate(tmp)
self.checkRecursion([])
def __str__( self ):
if hasattr(self,"name"):
return self.name
return self.__class__.__name__ + ": ..."
# stubbed out for now - creates awful memory and perf issues
self._revertClass = self.__class__
self.__class__ = _ForwardNoRecurse
try:
if self.expr is not None:
retString = _ustr(self.expr)
else:
retString = "None"
finally:
self.__class__ = self._revertClass
return self.__class__.__name__ + ": " + retString
def copy(self):
if self.expr is not None:
return super(Forward,self).copy()
else:
ret = Forward()
ret <<= self
return ret
class _ForwardNoRecurse(Forward):
def __str__( self ):
return "..."
class TokenConverter(ParseElementEnhance):
"""
Abstract subclass of C{ParseExpression}, for converting parsed results.
"""
def __init__( self, expr, savelist=False ):
super(TokenConverter,self).__init__( expr )#, savelist )
self.saveAsList = False
class Combine(TokenConverter):
"""
Converter to concatenate all matching tokens to a single string.
By default, the matching patterns must also be contiguous in the input string;
this can be disabled by specifying C{'adjacent=False'} in the constructor.
Example::
real = Word(nums) + '.' + Word(nums)
print(real.parseString('3.1416')) # -> ['3', '.', '1416']
# will also erroneously match the following
print(real.parseString('3. 1416')) # -> ['3', '.', '1416']
real = Combine(Word(nums) + '.' + Word(nums))
print(real.parseString('3.1416')) # -> ['3.1416']
# no match when there are internal spaces
print(real.parseString('3. 1416')) # -> Exception: Expected W:(0123...)
"""
def __init__( self, expr, joinString="", adjacent=True ):
super(Combine,self).__init__( expr )
# suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself
if adjacent:
self.leaveWhitespace()
self.adjacent = adjacent
self.skipWhitespace = True
self.joinString = joinString
self.callPreparse = True
def ignore( self, other ):
if self.adjacent:
ParserElement.ignore(self, other)
else:
super( Combine, self).ignore( other )
return self
def postParse( self, instring, loc, tokenlist ):
retToks = tokenlist.copy()
del retToks[:]
retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults)
if self.resultsName and retToks.haskeys():
return [ retToks ]
else:
return retToks
class Group(TokenConverter):
"""
Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.
Example::
ident = Word(alphas)
num = Word(nums)
term = ident | num
func = ident + Optional(delimitedList(term))
print(func.parseString("fn a,b,100")) # -> ['fn', 'a', 'b', '100']
func = ident + Group(Optional(delimitedList(term)))
print(func.parseString("fn a,b,100")) # -> ['fn', ['a', 'b', '100']]
"""
def __init__( self, expr ):
super(Group,self).__init__( expr )
self.saveAsList = True
def postParse( self, instring, loc, tokenlist ):
return [ tokenlist ]
class Dict(TokenConverter):
"""
Converter to return a repetitive expression as a list, but also as a dictionary.
Each element can also be referenced using the first token in the expression as its key.
Useful for tabular report scraping when the first column can be used as a item key.
Example::
data_word = Word(alphas)
label = data_word + FollowedBy(':')
attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
# print attributes as plain groups
print(OneOrMore(attr_expr).parseString(text).dump())
# instead of OneOrMore(expr), parse using Dict(OneOrMore(Group(expr))) - Dict will auto-assign names
result = Dict(OneOrMore(Group(attr_expr))).parseString(text)
print(result.dump())
# access named fields as dict entries, or output as dict
print(result['shape'])
print(result.asDict())
prints::
['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap']
[['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
- color: light blue
- posn: upper left
- shape: SQUARE
- texture: burlap
SQUARE
{'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'}
See more examples at L{ParseResults} of accessing fields by results name.
"""
def __init__( self, expr ):
super(Dict,self).__init__( expr )
self.saveAsList = True
def postParse( self, instring, loc, tokenlist ):
for i,tok in enumerate(tokenlist):
if len(tok) == 0:
continue
ikey = tok[0]
if isinstance(ikey,int):
ikey = _ustr(tok[0]).strip()
if len(tok)==1:
tokenlist[ikey] = _ParseResultsWithOffset("",i)
elif len(tok)==2 and not isinstance(tok[1],ParseResults):
tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i)
else:
dictvalue = tok.copy() #ParseResults(i)
del dictvalue[0]
if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.haskeys()):
tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i)
else:
tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i)
if self.resultsName:
return [ tokenlist ]
else:
return tokenlist
class Suppress(TokenConverter):
"""
Converter for ignoring the results of a parsed expression.
Example::
source = "a, b, c,d"
wd = Word(alphas)
wd_list1 = wd + ZeroOrMore(',' + wd)
print(wd_list1.parseString(source))
# often, delimiters that are useful during parsing are just in the
# way afterward - use Suppress to keep them out of the parsed output
wd_list2 = wd + ZeroOrMore(Suppress(',') + wd)
print(wd_list2.parseString(source))
prints::
['a', ',', 'b', ',', 'c', ',', 'd']
['a', 'b', 'c', 'd']
(See also L{delimitedList}.)
"""
def postParse( self, instring, loc, tokenlist ):
return []
def suppress( self ):
return self
class OnlyOnce(object):
"""
Wrapper for parse actions, to ensure they are only called once.
"""
def __init__(self, methodCall):
self.callable = _trim_arity(methodCall)
self.called = False
def __call__(self,s,l,t):
if not self.called:
results = self.callable(s,l,t)
self.called = True
return results
raise ParseException(s,l,"")
def reset(self):
self.called = False
def traceParseAction(f):
"""
Decorator for debugging parse actions.
When the parse action is called, this decorator will print C{">> entering I{method-name}(line:I{current_source_line}, I{parse_location}, I{matched_tokens})".}
When the parse action completes, the decorator will print C{"<<"} followed by the returned value, or any exception that the parse action raised.
Example::
wd = Word(alphas)
@traceParseAction
def remove_duplicate_chars(tokens):
return ''.join(sorted(set(''.join(tokens)))
wds = OneOrMore(wd).setParseAction(remove_duplicate_chars)
print(wds.parseString("slkdjs sld sldd sdlf sdljf"))
prints::
>>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {}))
<<leaving remove_duplicate_chars (ret: 'dfjkls')
['dfjkls']
"""
f = _trim_arity(f)
def z(*paArgs):
thisFunc = f.__name__
s,l,t = paArgs[-3:]
if len(paArgs)>3:
thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc
sys.stderr.write( ">>entering %s(line: '%s', %d, %r)\n" % (thisFunc,line(l,s),l,t) )
try:
ret = f(*paArgs)
except Exception as exc:
sys.stderr.write( "<<leaving %s (exception: %s)\n" % (thisFunc,exc) )
raise
sys.stderr.write( "<<leaving %s (ret: %r)\n" % (thisFunc,ret) )
return ret
try:
z.__name__ = f.__name__
except AttributeError:
pass
return z
#
# global helpers
#
def delimitedList( expr, delim=",", combine=False ):
"""
Helper to define a delimited list of expressions - the delimiter defaults to ','.
By default, the list elements and delimiters can have intervening whitespace, and
comments, but this can be overridden by passing C{combine=True} in the constructor.
If C{combine} is set to C{True}, the matching tokens are returned as a single token
string, with the delimiters included; otherwise, the matching tokens are returned
as a list of tokens, with the delimiters suppressed.
Example::
delimitedList(Word(alphas)).parseString("aa,bb,cc") # -> ['aa', 'bb', 'cc']
delimitedList(Word(hexnums), delim=':', combine=True).parseString("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE']
"""
dlName = _ustr(expr)+" ["+_ustr(delim)+" "+_ustr(expr)+"]..."
if combine:
return Combine( expr + ZeroOrMore( delim + expr ) ).setName(dlName)
else:
return ( expr + ZeroOrMore( Suppress( delim ) + expr ) ).setName(dlName)
def countedArray( expr, intExpr=None ):
"""
Helper to define a counted list of expressions.
This helper defines a pattern of the form::
integer expr expr expr...
where the leading integer tells how many expr expressions follow.
The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed.
If C{intExpr} is specified, it should be a pyparsing expression that produces an integer value.
Example::
countedArray(Word(alphas)).parseString('2 ab cd ef') # -> ['ab', 'cd']
# in this parser, the leading integer value is given in binary,
# '10' indicating that 2 values are in the array
binaryConstant = Word('01').setParseAction(lambda t: int(t[0], 2))
countedArray(Word(alphas), intExpr=binaryConstant).parseString('10 ab cd ef') # -> ['ab', 'cd']
"""
arrayExpr = Forward()
def countFieldParseAction(s,l,t):
n = t[0]
arrayExpr << (n and Group(And([expr]*n)) or Group(empty))
return []
if intExpr is None:
intExpr = Word(nums).setParseAction(lambda t:int(t[0]))
else:
intExpr = intExpr.copy()
intExpr.setName("arrayLen")
intExpr.addParseAction(countFieldParseAction, callDuringTry=True)
return ( intExpr + arrayExpr ).setName('(len) ' + _ustr(expr) + '...')
def _flatten(L):
ret = []
for i in L:
if isinstance(i,list):
ret.extend(_flatten(i))
else:
ret.append(i)
return ret
def matchPreviousLiteral(expr):
"""
Helper to define an expression that is indirectly defined from
the tokens matched in a previous expression, that is, it looks
for a 'repeat' of a previous expression. For example::
first = Word(nums)
second = matchPreviousLiteral(first)
matchExpr = first + ":" + second
will match C{"1:1"}, but not C{"1:2"}. Because this matches a
previous literal, will also match the leading C{"1:1"} in C{"1:10"}.
If this is not desired, use C{matchPreviousExpr}.
Do I{not} use with packrat parsing enabled.
"""
rep = Forward()
def copyTokenToRepeater(s,l,t):
if t:
if len(t) == 1:
rep << t[0]
else:
# flatten t tokens
tflat = _flatten(t.asList())
rep << And(Literal(tt) for tt in tflat)
else:
rep << Empty()
expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
rep.setName('(prev) ' + _ustr(expr))
return rep
def matchPreviousExpr(expr):
"""
Helper to define an expression that is indirectly defined from
the tokens matched in a previous expression, that is, it looks
for a 'repeat' of a previous expression. For example::
first = Word(nums)
second = matchPreviousExpr(first)
matchExpr = first + ":" + second
will match C{"1:1"}, but not C{"1:2"}. Because this matches by
expressions, will I{not} match the leading C{"1:1"} in C{"1:10"};
the expressions are evaluated first, and then compared, so
C{"1"} is compared with C{"10"}.
Do I{not} use with packrat parsing enabled.
"""
rep = Forward()
e2 = expr.copy()
rep <<= e2
def copyTokenToRepeater(s,l,t):
matchTokens = _flatten(t.asList())
def mustMatchTheseTokens(s,l,t):
theseTokens = _flatten(t.asList())
if theseTokens != matchTokens:
raise ParseException("",0,"")
rep.setParseAction( mustMatchTheseTokens, callDuringTry=True )
expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
rep.setName('(prev) ' + _ustr(expr))
return rep
def _escapeRegexRangeChars(s):
#~ escape these chars: ^-]
for c in r"\^-]":
s = s.replace(c,_bslash+c)
s = s.replace("\n",r"\n")
s = s.replace("\t",r"\t")
return _ustr(s)
def oneOf( strs, caseless=False, useRegex=True ):
"""
Helper to quickly define a set of alternative Literals, and makes sure to do
longest-first testing when there is a conflict, regardless of the input order,
but returns a C{L{MatchFirst}} for best performance.
Parameters:
- strs - a string of space-delimited literals, or a collection of string literals
- caseless - (default=C{False}) - treat all literals as caseless
- useRegex - (default=C{True}) - as an optimization, will generate a Regex
object; otherwise, will generate a C{MatchFirst} object (if C{caseless=True}, or
if creating a C{Regex} raises an exception)
Example::
comp_oper = oneOf("< = > <= >= !=")
var = Word(alphas)
number = Word(nums)
term = var | number
comparison_expr = term + comp_oper + term
print(comparison_expr.searchString("B = 12 AA=23 B<=AA AA>12"))
prints::
[['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']]
"""
if caseless:
isequal = ( lambda a,b: a.upper() == b.upper() )
masks = ( lambda a,b: b.upper().startswith(a.upper()) )
parseElementClass = CaselessLiteral
else:
isequal = ( lambda a,b: a == b )
masks = ( lambda a,b: b.startswith(a) )
parseElementClass = Literal
symbols = []
if isinstance(strs,basestring):
symbols = strs.split()
elif isinstance(strs, collections.Iterable):
symbols = list(strs)
else:
warnings.warn("Invalid argument to oneOf, expected string or iterable",
SyntaxWarning, stacklevel=2)
if not symbols:
return NoMatch()
i = 0
while i < len(symbols)-1:
cur = symbols[i]
for j,other in enumerate(symbols[i+1:]):
if ( isequal(other, cur) ):
del symbols[i+j+1]
break
elif ( masks(cur, other) ):
del symbols[i+j+1]
symbols.insert(i,other)
cur = other
break
else:
i += 1
if not caseless and useRegex:
#~ print (strs,"->", "|".join( [ _escapeRegexChars(sym) for sym in symbols] ))
try:
if len(symbols)==len("".join(symbols)):
return Regex( "[%s]" % "".join(_escapeRegexRangeChars(sym) for sym in symbols) ).setName(' | '.join(symbols))
else:
return Regex( "|".join(re.escape(sym) for sym in symbols) ).setName(' | '.join(symbols))
except Exception:
warnings.warn("Exception creating Regex for oneOf, building MatchFirst",
SyntaxWarning, stacklevel=2)
# last resort, just use MatchFirst
return MatchFirst(parseElementClass(sym) for sym in symbols).setName(' | '.join(symbols))
def dictOf( key, value ):
"""
Helper to easily and clearly define a dictionary by specifying the respective patterns
for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{Group}} tokens
in the proper order. The key pattern can include delimiting markers or punctuation,
as long as they are suppressed, thereby leaving the significant key text. The value
pattern can include named results, so that the C{Dict} results can include named token
fields.
Example::
text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
print(OneOrMore(attr_expr).parseString(text).dump())
attr_label = label
attr_value = Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join)
# similar to Dict, but simpler call format
result = dictOf(attr_label, attr_value).parseString(text)
print(result.dump())
print(result['shape'])
print(result.shape) # object attribute access works too
print(result.asDict())
prints::
[['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
- color: light blue
- posn: upper left
- shape: SQUARE
- texture: burlap
SQUARE
SQUARE
{'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'}
"""
return Dict( ZeroOrMore( Group ( key + value ) ) )
def originalTextFor(expr, asString=True):
"""
Helper to return the original, untokenized text for a given expression. Useful to
restore the parsed fields of an HTML start tag into the raw tag text itself, or to
revert separate tokens with intervening whitespace back to the original matching
input text. By default, returns astring containing the original parsed text.
If the optional C{asString} argument is passed as C{False}, then the return value is a
C{L{ParseResults}} containing any results names that were originally matched, and a
single token containing the original matched text from the input string. So if
the expression passed to C{L{originalTextFor}} contains expressions with defined
results names, you must set C{asString} to C{False} if you want to preserve those
results name values.
Example::
src = "this is test <b> bold <i>text</i> </b> normal text "
for tag in ("b","i"):
opener,closer = makeHTMLTags(tag)
patt = originalTextFor(opener + SkipTo(closer) + closer)
print(patt.searchString(src)[0])
prints::
['<b> bold <i>text</i> </b>']
['<i>text</i>']
"""
locMarker = Empty().setParseAction(lambda s,loc,t: loc)
endlocMarker = locMarker.copy()
endlocMarker.callPreparse = False
matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end")
if asString:
extractText = lambda s,l,t: s[t._original_start:t._original_end]
else:
def extractText(s,l,t):
t[:] = [s[t.pop('_original_start'):t.pop('_original_end')]]
matchExpr.setParseAction(extractText)
matchExpr.ignoreExprs = expr.ignoreExprs
return matchExpr
def ungroup(expr):
"""
Helper to undo pyparsing's default grouping of And expressions, even
if all but one are non-empty.
"""
return TokenConverter(expr).setParseAction(lambda t:t[0])
def locatedExpr(expr):
"""
Helper to decorate a returned token with its starting and ending locations in the input string.
This helper adds the following results names:
- locn_start = location where matched expression begins
- locn_end = location where matched expression ends
- value = the actual parsed results
Be careful if the input text contains C{<TAB>} characters, you may want to call
C{L{ParserElement.parseWithTabs}}
Example::
wd = Word(alphas)
for match in locatedExpr(wd).searchString("ljsdf123lksdjjf123lkkjj1222"):
print(match)
prints::
[[0, 'ljsdf', 5]]
[[8, 'lksdjjf', 15]]
[[18, 'lkkjj', 23]]
"""
locator = Empty().setParseAction(lambda s,l,t: l)
return Group(locator("locn_start") + expr("value") + locator.copy().leaveWhitespace()("locn_end"))
# convenience constants for positional expressions
empty = Empty().setName("empty")
lineStart = LineStart().setName("lineStart")
lineEnd = LineEnd().setName("lineEnd")
stringStart = StringStart().setName("stringStart")
stringEnd = StringEnd().setName("stringEnd")
_escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1])
_escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16)))
_escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8)))
_singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(printables, excludeChars=r'\]', exact=1) | Regex(r"\w", re.UNICODE)
_charRange = Group(_singleChar + Suppress("-") + _singleChar)
_reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]"
def srange(s):
r"""
Helper to easily define string ranges for use in Word construction. Borrows
syntax from regexp '[]' string range definitions::
srange("[0-9]") -> "0123456789"
srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz"
srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_"
The input string must be enclosed in []'s, and the returned string is the expanded
character set joined into a single string.
The values enclosed in the []'s may be:
- a single character
- an escaped character with a leading backslash (such as C{\-} or C{\]})
- an escaped hex character with a leading C{'\x'} (C{\x21}, which is a C{'!'} character)
(C{\0x##} is also supported for backwards compatibility)
- an escaped octal character with a leading C{'\0'} (C{\041}, which is a C{'!'} character)
- a range of any of the above, separated by a dash (C{'a-z'}, etc.)
- any combination of the above (C{'aeiouy'}, C{'a-zA-Z0-9_$'}, etc.)
"""
_expanded = lambda p: p if not isinstance(p,ParseResults) else ''.join(unichr(c) for c in range(ord(p[0]),ord(p[1])+1))
try:
return "".join(_expanded(part) for part in _reBracketExpr.parseString(s).body)
except Exception:
return ""
def matchOnlyAtCol(n):
"""
Helper method for defining parse actions that require matching at a specific
column in the input text.
"""
def verifyCol(strg,locn,toks):
if col(locn,strg) != n:
raise ParseException(strg,locn,"matched token not at column %d" % n)
return verifyCol
def replaceWith(replStr):
"""
Helper method for common parse actions that simply return a literal value. Especially
useful when used with C{L{transformString<ParserElement.transformString>}()}.
Example::
num = Word(nums).setParseAction(lambda toks: int(toks[0]))
na = oneOf("N/A NA").setParseAction(replaceWith(math.nan))
term = na | num
OneOrMore(term).parseString("324 234 N/A 234") # -> [324, 234, nan, 234]
"""
return lambda s,l,t: [replStr]
def removeQuotes(s,l,t):
"""
Helper parse action for removing quotation marks from parsed quoted strings.
Example::
# by default, quotation marks are included in parsed results
quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"]
# use removeQuotes to strip quotation marks from parsed results
quotedString.setParseAction(removeQuotes)
quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"]
"""
return t[0][1:-1]
def tokenMap(func, *args):
"""
Helper to define a parse action by mapping a function to all elements of a ParseResults list.If any additional
args are passed, they are forwarded to the given function as additional arguments after
the token, as in C{hex_integer = Word(hexnums).setParseAction(tokenMap(int, 16))}, which will convert the
parsed data to an integer using base 16.
Example (compare the last to example in L{ParserElement.transformString}::
hex_ints = OneOrMore(Word(hexnums)).setParseAction(tokenMap(int, 16))
hex_ints.runTests('''
00 11 22 aa FF 0a 0d 1a
''')
upperword = Word(alphas).setParseAction(tokenMap(str.upper))
OneOrMore(upperword).runTests('''
my kingdom for a horse
''')
wd = Word(alphas).setParseAction(tokenMap(str.title))
OneOrMore(wd).setParseAction(' '.join).runTests('''
now is the winter of our discontent made glorious summer by this sun of york
''')
prints::
00 11 22 aa FF 0a 0d 1a
[0, 17, 34, 170, 255, 10, 13, 26]
my kingdom for a horse
['MY', 'KINGDOM', 'FOR', 'A', 'HORSE']
now is the winter of our discontent made glorious summer by this sun of york
['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York']
"""
def pa(s,l,t):
return [func(tokn, *args) for tokn in t]
try:
func_name = getattr(func, '__name__',
getattr(func, '__class__').__name__)
except Exception:
func_name = str(func)
pa.__name__ = func_name
return pa
upcaseTokens = tokenMap(lambda t: _ustr(t).upper())
"""(Deprecated) Helper parse action to convert tokens to upper case. Deprecated in favor of L{pyparsing_common.upcaseTokens}"""
downcaseTokens = tokenMap(lambda t: _ustr(t).lower())
"""(Deprecated) Helper parse action to convert tokens to lower case. Deprecated in favor of L{pyparsing_common.downcaseTokens}"""
def _makeTags(tagStr, xml):
"""Internal helper to construct opening and closing tag expressions, given a tag name"""
if isinstance(tagStr,basestring):
resname = tagStr
tagStr = Keyword(tagStr, caseless=not xml)
else:
resname = tagStr.name
tagAttrName = Word(alphas,alphanums+"_-:")
if (xml):
tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes )
openTag = Suppress("<") + tagStr("tag") + \
Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \
Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
else:
printablesLessRAbrack = "".join(c for c in printables if c not in ">")
tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack)
openTag = Suppress("<") + tagStr("tag") + \
Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \
Optional( Suppress("=") + tagAttrValue ) ))) + \
Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
closeTag = Combine(_L("</") + tagStr + ">")
openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % resname)
closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("</%s>" % resname)
openTag.tag = resname
closeTag.tag = resname
return openTag, closeTag
def makeHTMLTags(tagStr):
"""
Helper to construct opening and closing tag expressions for HTML, given a tag name. Matches
tags in either upper or lower case, attributes with namespaces and with quoted or unquoted values.
Example::
text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
# makeHTMLTags returns pyparsing expressions for the opening and closing tags as a 2-tuple
a,a_end = makeHTMLTags("A")
link_expr = a + SkipTo(a_end)("link_text") + a_end
for link in link_expr.searchString(text):
# attributes in the <A> tag (like "href" shown here) are also accessible as named results
print(link.link_text, '->', link.href)
prints::
pyparsing -> http://pyparsing.wikispaces.com
"""
return _makeTags( tagStr, False )
def makeXMLTags(tagStr):
"""
Helper to construct opening and closing tag expressions for XML, given a tag name. Matches
tags only in the given upper/lower case.
Example: similar to L{makeHTMLTags}
"""
return _makeTags( tagStr, True )
def withAttribute(*args,**attrDict):
"""
Helper to create a validating parse action to be used with start tags created
with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag
with a required attribute value, to avoid false matches on common tags such as
C{<TD>} or C{<DIV>}.
Call C{withAttribute} with a series of attribute names and values. Specify the list
of filter attributes names and values as:
- keyword arguments, as in C{(align="right")}, or
- as an explicit dict with C{**} operator, when an attribute name is also a Python
reserved word, as in C{**{"class":"Customer", "align":"right"}}
- a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") )
For attribute names with a namespace prefix, you must use the second form. Attribute
names are matched insensitive to upper/lower case.
If just testing for C{class} (with or without a namespace), use C{L{withClass}}.
To verify that the attribute exists, but without specifying a value, pass
C{withAttribute.ANY_VALUE} as the value.
Example::
html = '''
<div>
Some text
<div type="grid">1 4 0 1 0</div>
<div type="graph">1,3 2,3 1,1</div>
<div>this has no type</div>
</div>
'''
div,div_end = makeHTMLTags("div")
# only match div tag having a type attribute with value "grid"
div_grid = div().setParseAction(withAttribute(type="grid"))
grid_expr = div_grid + SkipTo(div | div_end)("body")
for grid_header in grid_expr.searchString(html):
print(grid_header.body)
# construct a match with any div tag having a type attribute, regardless of the value
div_any_type = div().setParseAction(withAttribute(type=withAttribute.ANY_VALUE))
div_expr = div_any_type + SkipTo(div | div_end)("body")
for div_header in div_expr.searchString(html):
print(div_header.body)
prints::
1 4 0 1 0
1 4 0 1 0
1,3 2,3 1,1
"""
if args:
attrs = args[:]
else:
attrs = attrDict.items()
attrs = [(k,v) for k,v in attrs]
def pa(s,l,tokens):
for attrName,attrValue in attrs:
if attrName not in tokens:
raise ParseException(s,l,"no matching attribute " + attrName)
if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue:
raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" %
(attrName, tokens[attrName], attrValue))
return pa
withAttribute.ANY_VALUE = object()
def withClass(classname, namespace=''):
"""
Simplified version of C{L{withAttribute}} when matching on a div class - made
difficult because C{class} is a reserved word in Python.
Example::
html = '''
<div>
Some text
<div class="grid">1 4 0 1 0</div>
<div class="graph">1,3 2,3 1,1</div>
<div>this <div> has no class</div>
</div>
'''
div,div_end = makeHTMLTags("div")
div_grid = div().setParseAction(withClass("grid"))
grid_expr = div_grid + SkipTo(div | div_end)("body")
for grid_header in grid_expr.searchString(html):
print(grid_header.body)
div_any_type = div().setParseAction(withClass(withAttribute.ANY_VALUE))
div_expr = div_any_type + SkipTo(div | div_end)("body")
for div_header in div_expr.searchString(html):
print(div_header.body)
prints::
1 4 0 1 0
1 4 0 1 0
1,3 2,3 1,1
"""
classattr = "%s:class" % namespace if namespace else "class"
return withAttribute(**{classattr : classname})
opAssoc = _Constants()
opAssoc.LEFT = object()
opAssoc.RIGHT = object()
def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ):
"""
Helper method for constructing grammars of expressions made up of
operators working in a precedence hierarchy. Operators may be unary or
binary, left- or right-associative. Parse actions can also be attached
to operator expressions. The generated parser will also recognize the use
of parentheses to override operator precedences (see example below).
Note: if you define a deep operator list, you may see performance issues
when using infixNotation. See L{ParserElement.enablePackrat} for a
mechanism to potentially improve your parser performance.
Parameters:
- baseExpr - expression representing the most basic element for the nested
- opList - list of tuples, one for each operator precedence level in the
expression grammar; each tuple is of the form
(opExpr, numTerms, rightLeftAssoc, parseAction), where:
- opExpr is the pyparsing expression for the operator;
may also be a string, which will be converted to a Literal;
if numTerms is 3, opExpr is a tuple of two expressions, for the
two operators separating the 3 terms
- numTerms is the number of terms for this operator (must
be 1, 2, or 3)
- rightLeftAssoc is the indicator whether the operator is
right or left associative, using the pyparsing-defined
constants C{opAssoc.RIGHT} and C{opAssoc.LEFT}.
- parseAction is the parse action to be associated with
expressions matching this operator expression (the
parse action tuple member may be omitted)
- lpar - expression for matching left-parentheses (default=C{Suppress('(')})
- rpar - expression for matching right-parentheses (default=C{Suppress(')')})
Example::
# simple example of four-function arithmetic with ints and variable names
integer = pyparsing_common.signed_integer
varname = pyparsing_common.identifier
arith_expr = infixNotation(integer | varname,
[
('-', 1, opAssoc.RIGHT),
(oneOf('* /'), 2, opAssoc.LEFT),
(oneOf('+ -'), 2, opAssoc.LEFT),
])
arith_expr.runTests('''
5+3*6
(5+3)*6
-2--11
''', fullDump=False)
prints::
5+3*6
[[5, '+', [3, '*', 6]]]
(5+3)*6
[[[5, '+', 3], '*', 6]]
-2--11
[[['-', 2], '-', ['-', 11]]]
"""
ret = Forward()
lastExpr = baseExpr | ( lpar + ret + rpar )
for i,operDef in enumerate(opList):
opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4]
termName = "%s term" % opExpr if arity < 3 else "%s%s term" % opExpr
if arity == 3:
if opExpr is None or len(opExpr) != 2:
raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions")
opExpr1, opExpr2 = opExpr
thisExpr = Forward().setName(termName)
if rightLeftAssoc == opAssoc.LEFT:
if arity == 1:
matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) )
elif arity == 2:
if opExpr is not None:
matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) )
else:
matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) )
elif arity == 3:
matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \
Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr )
else:
raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
elif rightLeftAssoc == opAssoc.RIGHT:
if arity == 1:
# try to avoid LR with this extra test
if not isinstance(opExpr, Optional):
opExpr = Optional(opExpr)
matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr )
elif arity == 2:
if opExpr is not None:
matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) )
else:
matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) )
elif arity == 3:
matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \
Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr )
else:
raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
else:
raise ValueError("operator must indicate right or left associativity")
if pa:
matchExpr.setParseAction( pa )
thisExpr <<= ( matchExpr.setName(termName) | lastExpr )
lastExpr = thisExpr
ret <<= lastExpr
return ret
operatorPrecedence = infixNotation
"""(Deprecated) Former name of C{L{infixNotation}}, will be dropped in a future release."""
dblQuotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"').setName("string enclosed in double quotes")
sglQuotedString = Combine(Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("string enclosed in single quotes")
quotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"'|
Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("quotedString using single or double quotes")
unicodeString = Combine(_L('u') + quotedString.copy()).setName("unicode string literal")
def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()):
"""
Helper method for defining nested lists enclosed in opening and closing
delimiters ("(" and ")" are the default).
Parameters:
- opener - opening character for a nested list (default=C{"("}); can also be a pyparsing expression
- closer - closing character for a nested list (default=C{")"}); can also be a pyparsing expression
- content - expression for items within the nested lists (default=C{None})
- ignoreExpr - expression for ignoring opening and closing delimiters (default=C{quotedString})
If an expression is not provided for the content argument, the nested
expression will capture all whitespace-delimited content between delimiters
as a list of separate values.
Use the C{ignoreExpr} argument to define expressions that may contain
opening or closing characters that should not be treated as opening
or closing characters for nesting, such as quotedString or a comment
expression. Specify multiple expressions using an C{L{Or}} or C{L{MatchFirst}}.
The default is L{quotedString}, but if no expressions are to be ignored,
then pass C{None} for this argument.
Example::
data_type = oneOf("void int short long char float double")
decl_data_type = Combine(data_type + Optional(Word('*')))
ident = Word(alphas+'_', alphanums+'_')
number = pyparsing_common.number
arg = Group(decl_data_type + ident)
LPAR,RPAR = map(Suppress, "()")
code_body = nestedExpr('{', '}', ignoreExpr=(quotedString | cStyleComment))
c_function = (decl_data_type("type")
+ ident("name")
+ LPAR + Optional(delimitedList(arg), [])("args") + RPAR
+ code_body("body"))
c_function.ignore(cStyleComment)
source_code = '''
int is_odd(int x) {
return (x%2);
}
int dec_to_hex(char hchar) {
if (hchar >= '0' && hchar <= '9') {
return (ord(hchar)-ord('0'));
} else {
return (10+ord(hchar)-ord('A'));
}
}
'''
for func in c_function.searchString(source_code):
print("%(name)s (%(type)s) args: %(args)s" % func)
prints::
is_odd (int) args: [['int', 'x']]
dec_to_hex (int) args: [['char', 'hchar']]
"""
if opener == closer:
raise ValueError("opening and closing strings cannot be the same")
if content is None:
if isinstance(opener,basestring) and isinstance(closer,basestring):
if len(opener) == 1 and len(closer)==1:
if ignoreExpr is not None:
content = (Combine(OneOrMore(~ignoreExpr +
CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1))
).setParseAction(lambda t:t[0].strip()))
else:
content = (empty.copy()+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS
).setParseAction(lambda t:t[0].strip()))
else:
if ignoreExpr is not None:
content = (Combine(OneOrMore(~ignoreExpr +
~Literal(opener) + ~Literal(closer) +
CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
).setParseAction(lambda t:t[0].strip()))
else:
content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) +
CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
).setParseAction(lambda t:t[0].strip()))
else:
raise ValueError("opening and closing arguments must be strings if no content expression is given")
ret = Forward()
if ignoreExpr is not None:
ret <<= Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) )
else:
ret <<= Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) )
ret.setName('nested %s%s expression' % (opener,closer))
return ret
def indentedBlock(blockStatementExpr, indentStack, indent=True):
"""
Helper method for defining space-delimited indentation blocks, such as
those used to define block statements in Python source code.
Parameters:
- blockStatementExpr - expression defining syntax of statement that
is repeated within the indented block
- indentStack - list created by caller to manage indentation stack
(multiple statementWithIndentedBlock expressions within a single grammar
should share a common indentStack)
- indent - boolean indicating whether block must be indented beyond the
the current level; set to False for block of left-most statements
(default=C{True})
A valid block must contain at least one C{blockStatement}.
Example::
data = '''
def A(z):
A1
B = 100
G = A2
A2
A3
B
def BB(a,b,c):
BB1
def BBA():
bba1
bba2
bba3
C
D
def spam(x,y):
def eggs(z):
pass
'''
indentStack = [1]
stmt = Forward()
identifier = Word(alphas, alphanums)
funcDecl = ("def" + identifier + Group( "(" + Optional( delimitedList(identifier) ) + ")" ) + ":")
func_body = indentedBlock(stmt, indentStack)
funcDef = Group( funcDecl + func_body )
rvalue = Forward()
funcCall = Group(identifier + "(" + Optional(delimitedList(rvalue)) + ")")
rvalue << (funcCall | identifier | Word(nums))
assignment = Group(identifier + "=" + rvalue)
stmt << ( funcDef | assignment | identifier )
module_body = OneOrMore(stmt)
parseTree = module_body.parseString(data)
parseTree.pprint()
prints::
[['def',
'A',
['(', 'z', ')'],
':',
[['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]],
'B',
['def',
'BB',
['(', 'a', 'b', 'c', ')'],
':',
[['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]],
'C',
'D',
['def',
'spam',
['(', 'x', 'y', ')'],
':',
[[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]]
"""
def checkPeerIndent(s,l,t):
if l >= len(s): return
curCol = col(l,s)
if curCol != indentStack[-1]:
if curCol > indentStack[-1]:
raise ParseFatalException(s,l,"illegal nesting")
raise ParseException(s,l,"not a peer entry")
def checkSubIndent(s,l,t):
curCol = col(l,s)
if curCol > indentStack[-1]:
indentStack.append( curCol )
else:
raise ParseException(s,l,"not a subentry")
def checkUnindent(s,l,t):
if l >= len(s): return
curCol = col(l,s)
if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]):
raise ParseException(s,l,"not an unindent")
indentStack.pop()
NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress())
INDENT = (Empty() + Empty().setParseAction(checkSubIndent)).setName('INDENT')
PEER = Empty().setParseAction(checkPeerIndent).setName('')
UNDENT = Empty().setParseAction(checkUnindent).setName('UNINDENT')
if indent:
smExpr = Group( Optional(NL) +
#~ FollowedBy(blockStatementExpr) +
INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT)
else:
smExpr = Group( Optional(NL) +
(OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) )
blockStatementExpr.ignore(_bslash + LineEnd())
return smExpr.setName('indented block')
alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]")
punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]")
anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:").setName('any tag'))
_htmlEntityMap = dict(zip("gt lt amp nbsp quot apos".split(),'><& "\''))
commonHTMLEntity = Regex('&(?P<entity>' + '|'.join(_htmlEntityMap.keys()) +");").setName("common HTML entity")
def replaceHTMLEntity(t):
"""Helper parser action to replace common HTML entities with their special characters"""
return _htmlEntityMap.get(t.entity)
# it's easy to get these comment structures wrong - they're very common, so may as well make them available
cStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/').setName("C style comment")
"Comment of the form C{/* ... */}"
htmlComment = Regex(r"<!--[\s\S]*?-->").setName("HTML comment")
"Comment of the form C{<!-- ... -->}"
restOfLine = Regex(r".*").leaveWhitespace().setName("rest of line")
dblSlashComment = Regex(r"//(?:\\\n|[^\n])*").setName("// comment")
"Comment of the form C{// ... (to end of line)}"
cppStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/'| dblSlashComment).setName("C++ style comment")
"Comment of either form C{L{cStyleComment}} or C{L{dblSlashComment}}"
javaStyleComment = cppStyleComment
"Same as C{L{cppStyleComment}}"
pythonStyleComment = Regex(r"#.*").setName("Python style comment")
"Comment of the form C{# ... (to end of line)}"
_commasepitem = Combine(OneOrMore(Word(printables, excludeChars=',') +
Optional( Word(" \t") +
~Literal(",") + ~LineEnd() ) ) ).streamline().setName("commaItem")
commaSeparatedList = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("commaSeparatedList")
"""(Deprecated) Predefined expression of 1 or more printable words or quoted strings, separated by commas.
This expression is deprecated in favor of L{pyparsing_common.comma_separated_list}."""
# some other useful expressions - using lower-case class name since we are really using this as a namespace
class pyparsing_common:
"""
Here are some common low-level expressions that may be useful in jump-starting parser development:
- numeric forms (L{integers<integer>}, L{reals<real>}, L{scientific notation<sci_real>})
- common L{programming identifiers<identifier>}
- network addresses (L{MAC<mac_address>}, L{IPv4<ipv4_address>}, L{IPv6<ipv6_address>})
- ISO8601 L{dates<iso8601_date>} and L{datetime<iso8601_datetime>}
- L{UUID<uuid>}
- L{comma-separated list<comma_separated_list>}
Parse actions:
- C{L{convertToInteger}}
- C{L{convertToFloat}}
- C{L{convertToDate}}
- C{L{convertToDatetime}}
- C{L{stripHTMLTags}}
- C{L{upcaseTokens}}
- C{L{downcaseTokens}}
Example::
pyparsing_common.number.runTests('''
# any int or real number, returned as the appropriate type
100
-100
+100
3.14159
6.02e23
1e-12
''')
pyparsing_common.fnumber.runTests('''
# any int or real number, returned as float
100
-100
+100
3.14159
6.02e23
1e-12
''')
pyparsing_common.hex_integer.runTests('''
# hex numbers
100
FF
''')
pyparsing_common.fraction.runTests('''
# fractions
1/2
-3/4
''')
pyparsing_common.mixed_integer.runTests('''
# mixed fractions
1
1/2
-3/4
1-3/4
''')
import uuid
pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
pyparsing_common.uuid.runTests('''
# uuid
12345678-1234-5678-1234-567812345678
''')
prints::
# any int or real number, returned as the appropriate type
100
[100]
-100
[-100]
+100
[100]
3.14159
[3.14159]
6.02e23
[6.02e+23]
1e-12
[1e-12]
# any int or real number, returned as float
100
[100.0]
-100
[-100.0]
+100
[100.0]
3.14159
[3.14159]
6.02e23
[6.02e+23]
1e-12
[1e-12]
# hex numbers
100
[256]
FF
[255]
# fractions
1/2
[0.5]
-3/4
[-0.75]
# mixed fractions
1
[1]
1/2
[0.5]
-3/4
[-0.75]
1-3/4
[1.75]
# uuid
12345678-1234-5678-1234-567812345678
[UUID('12345678-1234-5678-1234-567812345678')]
"""
convertToInteger = tokenMap(int)
"""
Parse action for converting parsed integers to Python int
"""
convertToFloat = tokenMap(float)
"""
Parse action for converting parsed numbers to Python float
"""
integer = Word(nums).setName("integer").setParseAction(convertToInteger)
"""expression that parses an unsigned integer, returns an int"""
hex_integer = Word(hexnums).setName("hex integer").setParseAction(tokenMap(int,16))
"""expression that parses a hexadecimal integer, returns an int"""
signed_integer = Regex(r'[+-]?\d+').setName("signed integer").setParseAction(convertToInteger)
"""expression that parses an integer with optional leading sign, returns an int"""
fraction = (signed_integer().setParseAction(convertToFloat) + '/' + signed_integer().setParseAction(convertToFloat)).setName("fraction")
"""fractional expression of an integer divided by an integer, returns a float"""
fraction.addParseAction(lambda t: t[0]/t[-1])
mixed_integer = (fraction | signed_integer + Optional(Optional('-').suppress() + fraction)).setName("fraction or mixed integer-fraction")
"""mixed integer of the form 'integer - fraction', with optional leading integer, returns float"""
mixed_integer.addParseAction(sum)
real = Regex(r'[+-]?\d+\.\d*').setName("real number").setParseAction(convertToFloat)
"""expression that parses a floating point number and returns a float"""
sci_real = Regex(r'[+-]?\d+([eE][+-]?\d+|\.\d*([eE][+-]?\d+)?)').setName("real number with scientific notation").setParseAction(convertToFloat)
"""expression that parses a floating point number with optional scientific notation and returns a float"""
# streamlining this expression makes the docs nicer-looking
number = (sci_real | real | signed_integer).streamline()
"""any numeric expression, returns the corresponding Python type"""
fnumber = Regex(r'[+-]?\d+\.?\d*([eE][+-]?\d+)?').setName("fnumber").setParseAction(convertToFloat)
"""any int or real number, returned as float"""
identifier = Word(alphas+'_', alphanums+'_').setName("identifier")
"""typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')"""
ipv4_address = Regex(r'(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}').setName("IPv4 address")
"IPv4 address (C{0.0.0.0 - 255.255.255.255})"
_ipv6_part = Regex(r'[0-9a-fA-F]{1,4}').setName("hex_integer")
_full_ipv6_address = (_ipv6_part + (':' + _ipv6_part)*7).setName("full IPv6 address")
_short_ipv6_address = (Optional(_ipv6_part + (':' + _ipv6_part)*(0,6)) + "::" + Optional(_ipv6_part + (':' + _ipv6_part)*(0,6))).setName("short IPv6 address")
_short_ipv6_address.addCondition(lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8)
_mixed_ipv6_address = ("::ffff:" + ipv4_address).setName("mixed IPv6 address")
ipv6_address = Combine((_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).setName("IPv6 address")).setName("IPv6 address")
"IPv6 address (long, short, or mixed form)"
mac_address = Regex(r'[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}').setName("MAC address")
"MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)"
@staticmethod
def convertToDate(fmt="%Y-%m-%d"):
"""
Helper to create a parse action for converting parsed date string to Python datetime.date
Params -
- fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%d"})
Example::
date_expr = pyparsing_common.iso8601_date.copy()
date_expr.setParseAction(pyparsing_common.convertToDate())
print(date_expr.parseString("1999-12-31"))
prints::
[datetime.date(1999, 12, 31)]
"""
def cvt_fn(s,l,t):
try:
return datetime.strptime(t[0], fmt).date()
except ValueError as ve:
raise ParseException(s, l, str(ve))
return cvt_fn
@staticmethod
def convertToDatetime(fmt="%Y-%m-%dT%H:%M:%S.%f"):
"""
Helper to create a parse action for converting parsed datetime string to Python datetime.datetime
Params -
- fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%dT%H:%M:%S.%f"})
Example::
dt_expr = pyparsing_common.iso8601_datetime.copy()
dt_expr.setParseAction(pyparsing_common.convertToDatetime())
print(dt_expr.parseString("1999-12-31T23:59:59.999"))
prints::
[datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)]
"""
def cvt_fn(s,l,t):
try:
return datetime.strptime(t[0], fmt)
except ValueError as ve:
raise ParseException(s, l, str(ve))
return cvt_fn
iso8601_date = Regex(r'(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?').setName("ISO8601 date")
"ISO8601 date (C{yyyy-mm-dd})"
iso8601_datetime = Regex(r'(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?').setName("ISO8601 datetime")
"ISO8601 datetime (C{yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)}) - trailing seconds, milliseconds, and timezone optional; accepts separating C{'T'} or C{' '}"
uuid = Regex(r'[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}').setName("UUID")
"UUID (C{xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx})"
_html_stripper = anyOpenTag.suppress() | anyCloseTag.suppress()
@staticmethod
def stripHTMLTags(s, l, tokens):
"""
Parse action to remove HTML tags from web page HTML source
Example::
# strip HTML links from normal text
text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
td,td_end = makeHTMLTags("TD")
table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end
print(table_text.parseString(text).body) # -> 'More info at the pyparsing wiki page'
"""
return pyparsing_common._html_stripper.transformString(tokens[0])
_commasepitem = Combine(OneOrMore(~Literal(",") + ~LineEnd() + Word(printables, excludeChars=',')
+ Optional( White(" \t") ) ) ).streamline().setName("commaItem")
comma_separated_list = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("comma separated list")
"""Predefined expression of 1 or more printable words or quoted strings, separated by commas."""
upcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).upper()))
"""Parse action to convert tokens to upper case."""
downcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).lower()))
"""Parse action to convert tokens to lower case."""
if __name__ == "__main__":
selectToken = CaselessLiteral("select")
fromToken = CaselessLiteral("from")
ident = Word(alphas, alphanums + "_$")
columnName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
columnNameList = Group(delimitedList(columnName)).setName("columns")
columnSpec = ('*' | columnNameList)
tableName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
tableNameList = Group(delimitedList(tableName)).setName("tables")
simpleSQL = selectToken("command") + columnSpec("columns") + fromToken + tableNameList("tables")
# demo runTests method, including embedded comments in test string
simpleSQL.runTests("""
# '*' as column list and dotted table name
select * from SYS.XYZZY
# caseless match on "SELECT", and casts back to "select"
SELECT * from XYZZY, ABC
# list of column names, and mixed case SELECT keyword
Select AA,BB,CC from Sys.dual
# multiple tables
Select A, B, C from Sys.dual, Table2
# invalid SELECT keyword - should fail
Xelect A, B, C from Sys.dual
# incomplete command - should fail
Select
# invalid column name - should fail
Select ^^^ frox Sys.dual
""")
pyparsing_common.number.runTests("""
100
-100
+100
3.14159
6.02e23
1e-12
""")
# any int or real number, returned as float
pyparsing_common.fnumber.runTests("""
100
-100
+100
3.14159
6.02e23
1e-12
""")
pyparsing_common.hex_integer.runTests("""
100
FF
""")
import uuid
pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
pyparsing_common.uuid.runTests("""
12345678-1234-5678-1234-567812345678
""")
|