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
|
package pgFormatter::Beautify;
use strict;
use warnings;
use warnings qw( FATAL );
use Encode qw( decode );
use utf8;
binmode STDIN, ':utf8';
binmode STDOUT, ':utf8';
binmode STDERR, ':utf8';
use Text::Wrap;
our $DEBUG = 0;
our $DEBUG_SP = 0;
# PostgreSQL functions that use a FROM clause
our @have_from_clause = qw( extract overlay substring trim );
our @extract_keywords = qw(century day decade dow doy epoch hour isodow isoyear microseconds millennium minute month quarter second timezone timezone_minute week year);
our $math_operators = qr{^(?:\+|\-|\*|\/|\%|\^|\|\/|\|\|\/|\!|\!\!|\@|\&|\||\#|\~|<<|>>)$};
=head1 NAME
pgFormatter::Beautify - Library for pretty-printing SQL queries
=head1 VERSION
Version 5.5
=cut
# Version of pgFormatter
our $VERSION = '5.5';
# Inclusion of code from Perl package SQL::Beautify
# Copyright (C) 2009 by Jonas Kramer
# Published under the terms of the Artistic License 2.0.
=head1 SYNOPSIS
This module can be used to reformat given SQL query, optionally anonymizing parameters.
Output can be either plain text, or it can be HTML with appropriate styles so that it can be displayed on a web page.
Example usage:
my $beautifier = pgFormatter::Beautify->new();
$beautifier->query( 'select a,b,c from d where e = f' );
$beautifier->beautify();
my $nice_txt = $beautifier->content();
$beautifier->format('html');
$beautifier->beautify();
my $nice_html = $beautifier->content();
$beautifier->format('html');
$beautifier->anonymize();
$beautifier->beautify();
my $nice_anonymized_html = $beautifier->content();
$beautifier->format();
$beautifier->beautify();
$beautifier->wrap_lines()
my $wrapped_txt = $beautifier->content();
=head1 FUNCTIONS
=head2 new
Generic constructor - creates object, sets defaults, and reads config from given hash with options.
Takes options as hash. Following options are recognized:
=over
=item * break - String that is used for linebreaks. Default is "\n".
=item * colorize - if set to false CSS style will not be applied to html output. Used internally to display errors in CGI mode withour style.
=item * comma - set comma at beginning or end of a line in a parameter list
=over
=item end - put comma at end of the list (default)
=item start - put comma at beginning of the list
=back
=item * comma_break - add new-line after each comma in INSERT statements
=item * format - set beautify format to apply to the content (default: text)
=over
=item text - output content as plain/text (command line mode default)
=item html - output text/html with CSS style applied to content (CGI mode default)
=back
=item * functions - list (arrayref) of strings that are function names
=item * keywords - list (arrayref) of strings that are keywords
=item * multiline - use multi-line search for placeholder regex, see placeholder.
=item * no_comments - if set to true comments will be removed from query
=item * no_grouping - if set to true statements will not be grouped in a transaction, an extra newline character will be added between statements like outside a transaction.
=item * placeholder - use the specified regex to find code that must not be changed in the query.
=item * query - query to beautify
=item * rules - hash of rules - uses rule semantics from SQL::Beautify
=item * space - character(s) to be used as space for indentation
=item * spaces - how many spaces to use for indentation
=item * uc_functions - what to do with function names:
=over
=item 0 - do not change
=item 1 - change to lower case
=item 2 - change to upper case
=item 3 - change to Capitalized
=back
=item * separator - string used as dynamic code separator, default is single quote
=item * uc_keywords - what to do with keywords - meaning of value like with uc_functions
=item * uc_types - what to do with data types - meaning of value like with uc_functions
=item * wrap - wraps given keywords in pre- and post- markup. Specific docs in SQL::Beautify
=item * format_type - try an other formatting
=item * wrap_limit - wrap queries at a certain length
=item * wrap_after - number of column after which lists must be wrapped
=item * wrap_comment - apply wrapping to comments starting with --
=item * numbering - statement numbering as a comment before each query
=item * redshift - add Redshift keywords (obsolete, use --extra-keyword)
=item * no_extra_line - do not add an extra empty line at end of the output
=item * keep_newline - preserve empty line in plpgsql code
=item * no_space_function - remove space before function call and open parenthesis
=back
For defaults, please check function L<set_defaults>.
=cut
sub new
{
my $class = shift;
my %options = @_;
my $self = bless {}, $class;
$self->set_defaults();
for my $key ( qw( query spaces space break wrap keywords functions rules uc_keywords uc_functions uc_types no_comments no_grouping placeholder multiline separator comma comma_break format colorize format_type wrap_limit wrap_after wrap_comment numbering redshift no_extra_line keep_newline no_space_function)) {
$self->{ $key } = $options{ $key } if defined $options{ $key };
}
$self->_refresh_functions_re();
# Make sure "break" is sensible
$self->{ 'break' } = ' ' if $self->{ 'spaces' } == 0;
# Initialize internal stuff.
$self->{ '_level' } = 0;
# Array to store placeholders values
@{ $self->{ 'placeholder_values' } } = ();
# Hash to store dynamic code
%{ $self->{ 'dynamic_code' } } = ();
# Hash to store and preserve constants
%{ $self->{ 'keyword_constant' } } = ();
# Hash to store and preserve aliases between double quote
%{ $self->{ 'alias_constant' } } = ();
# Check comma value, when invalid set to default: end
if (lc($self->{ 'comma' }) ne 'start') {
$self->{ 'comma' } = 'end';
} else {
$self->{ 'comma' } = lc($self->{ 'comma' });
}
$self->{ 'format' } //= 'text';
$self->{ 'colorize' } //= 1;
$self->{ 'format_type' } //= 0;
$self->{ 'wrap_limit' } //= 0;
$self->{ 'wrap_after' } //= 0;
$self->{ 'wrap_comment' } //= 0;
$self->{ 'no_extra_line' } //= 0;
return $self;
}
=head2 query
Accessor to query string. Both reads:
$object->query()
, and writes
$object->query( $something )
=cut
sub query
{
my $self = shift;
my $new_value = shift;
$self->{ 'query' } = $new_value if defined $new_value;
$self->{idx_code} = 0;
# Replace any COMMENT constant between single quote
while ($self->{ 'query' } =~ s/IS\s+([EU]*'(?:[^;]*)')\s*;/IS TEXTVALUE$self->{idx_code};/is)
{
$self->{dynamic_code}{$self->{idx_code}} = $1;
$self->{dynamic_code}{$self->{idx_code}} =~ s/([\n\r])\s+([EU]*'(?:[^']*)')/$1 . ($self->{ 'space' } x $self->{ 'spaces' }) . $2/gsei;
$self->{idx_code}++;
}
# Replace any \\ by BSLHPGF
$self->{ 'query' } =~ s/\\\\/BSLHPGF/sg;
# Replace any \' by PGFBSLHQ
$self->{ 'query' } =~ s/\\'/PGFBSLHQ/sg;
# Replace any '' by PGFESCQ1
while ($self->{ 'query' } =~ s/([^'])''([^'])/$1PGFESCQ1$2/s) {};
# Replace any '''' by PGFESCQ1PGFESCQ1
while ($self->{ 'query' } =~ s/([^'])''''([^'])/$1PGFESCQ1PGFESCQ1$2/s) {};
# Replace any '...''' by '.*PGFESCQ1'
while ($self->{ 'query' } =~ s/([^']'[^']+)''('[^'])/$1PGFESCQ1$2/s) {};
# Replace any '''...' by 'PGFESCQ1.*'
while ($self->{ 'query' } =~ s/([^']')''([^']+'[^'])/$1PGFESCQ1$2/s) {};
# Replace any multiline '''...''' by 'PGFESCQ1...PGFESCQ1'
$self->{ 'query' } =~ s/([^']')''([^']*)''('[^']|$)/$1PGFESCQ1$2PGFESCQ1$3/sg;
# Replace any "" by PGFESCQ2
while ($self->{ 'query' } =~ s/([^"])""([^"])/$1PGFESCQ2$2/s) {};
# Replace aliases using double quote
my $j = 0;
while ($self->{ 'query' } =~ s/(\s+AS\s*)("+[^"]+"+)/$1PGFALIAS$j/is)
{
$self->{ 'alias_constant' }{$j} = $2;
$j++;
}
# replace all constant between quote
$j = 0;
while ($self->{ 'query' } =~ s/('[^'\n\r]+')/AAKEYWCONST${j}AA/s)
{
$self->{ 'keyword_constant' }{$j} = $1;
$j++;
}
# Fix false positive generated by code above.
while ($self->{ 'query' } =~ s/(\s+AS\s+)AAKEYWCONST(\d+)AA/$1$self->{ 'keyword_constant' }{$2}/is) {
delete $self->{ 'keyword_constant' }{$2};
};
# Hide content of format() function when the code separator is not a single quote */
my $i = 0;
while ($self->{ 'query' } =~ s/\bformat\((\$(?:.*)?\$\s*)([,\)])/format\(CODEPARTB${i}CODEPARTB$2/i) {
push(@{ $self->{ 'placeholder_values' } }, $1);
$i++;
}
my %temp_placeholder = ();
my @temp_content = split(/(CREATE(?:\s+OR\s+REPLACE)?\s+(?:FUNCTION|PROCEDURE)\s+)/i, $self->{ 'query' });
if ($#temp_content > 0)
{
for (my $j = 0; $j <= $#temp_content; $j++)
{
next if ($temp_content[$j] =~ /^CREATE/i or $temp_content[$j] eq '');
# Replace single quote code delimiter into $PGFDLM$
if ($temp_content[$j] !~ s/(\s+AS\s+)'(\s+.*?;\s*)'/$1\$PGFDLM\$$2\$PGFDLM\$/is)
{
$temp_content[$j] =~ s/(\s+AS\s+)'(\s+.*?END[;]*\s*)'/$1\$PGFDLM\$$2\$PGFDLM\$/is;
}
# Remove any call too CREATE/DROP LANGUAGE to not break search of function code separator
$temp_content[$j] =~ s/(CREATE|DROP)\s+LANGUAGE\s+[^;]+;.*//is;
# Fix case where code separator with $ is associated to begin/end keywords
$temp_content[$j] =~ s/([^\s]+\$)(BEGIN\s)/$1 $2/igs;
$temp_content[$j] =~ s/(\sEND)(\$[^\s]+)/$1 $2/igs;
$temp_content[$j] =~ s/(CREATE|DROP)\s+LANGUAGE\s+[^;]+;.*//is;
my $fctname = '';
if ($temp_content[$j] =~ /^([^\s\(]+)/) {
$fctname = lc($1);
}
next if (!$fctname);
my $language = 'sql';
if ($temp_content[$j] =~ /\s+LANGUAGE\s+[']*([^'\s;]+)[']*/is)
{
$language = lc($1);
if ($language =~ /AAKEYWCONST(\d+)AA/i)
{
$language = lc($self->{ 'keyword_constant' }{$1});
$language =~ s/'//g;
}
}
if ($language =~ /^internal$/i)
{
if ($temp_content[$j] =~ s/AS ('[^\']+')/AS CODEPARTB${i}CODEPARTB/is)
{
push(@{ $self->{ 'placeholder_values' } }, $1);
$i++;
}
}
# C function language with AS obj_file, link_symbol
elsif ($language =~ /^c$/i)
{
if ($temp_content[$j] =~ s/AS ('[^\']+')\s*,\s*('[^\']+')/AS CODEPARTB${i}CODEPARTB/is)
{
push(@{ $self->{ 'placeholder_values' } }, "$1, $2");
$i++;
}
}
# if the function language is not SQL or PLPGSQL
elsif ($language !~ /^(?:plpg)?sql$/)
{
# Try to find the code separator
my $tmp_str = $temp_content[$j];
while ($tmp_str =~ s/\s+AS\s+([^\s]+)\s+//is)
{
my $code_sep = quotemeta($1);
foreach my $k (@{ $self->{ 'keywords' } }) {
last if ($code_sep =~ s/\b$k$//i);
}
next if (!$code_sep);
if ($tmp_str =~ /\s+$code_sep[\s;]+/)
{
while ( $temp_content[$j] =~ s/($code_sep(?:.+?)$code_sep)/CODEPART${i}CODEPART/s)
{
push(@{ $self->{ 'placeholder_values' } }, $1);
$i++;
}
last;
}
}
}
}
}
$self->{ 'query' } = join('', @temp_content);
# Store values of code that must not be changed following the given placeholder
if ($self->{ 'placeholder' })
{
if (!$self->{ 'multiline' })
{
while ( $self->{ 'query' } =~ s/($self->{ 'placeholder' })/PLACEHOLDER${i}PLACEHOLDER/)
{
push(@{ $self->{ 'placeholder_values' } }, $1);
$i++;
}
}
else
{
while ( $self->{ 'query' } =~ s/($self->{ 'placeholder' })/PLACEHOLDER${i}PLACEHOLDER/s)
{
push(@{ $self->{ 'placeholder_values' } }, $1);
$i++;
}
}
}
# Replace dynamic code with placeholder
$self->_remove_dynamic_code( \$self->{ 'query' }, $self->{ 'separator' } );
# Replace operator with placeholder
$self->_quote_operator( \$self->{ 'query' } );
# Replace comment with not quote delimiter with placeholder
$self->_quote_comment_stmt( \$self->{ 'query' } );
return $self->{ 'query' };
}
=head2 content
Accessor to content of results. Must be called after $object->beautify().
This can be either plain text or html following the format asked by the
client with the $object->format() method.
=cut
sub content
{
my $self = shift;
my $new_value = shift;
$self->{ 'content' } = $new_value if defined $new_value;
$self->{ 'content' } =~ s/\(\s+\(/\(\(/gs;
# Replace placeholders with their original dynamic code
$self->_restore_dynamic_code( \$self->{ 'content' } );
# Replace placeholders with their original operator
$self->_restore_operator( \$self->{ 'content' } );
# Replace placeholders with their original string
$self->_restore_comment_stmt( \$self->{ 'content' } );
# Replace placeholders by their original values
if ($#{ $self->{ 'placeholder_values' } } >= 0)
{
$self->{ 'content' } =~ s/PLACEHOLDER(\d+)PLACEHOLDER/$self->{ 'placeholder_values' }[$1]/igs;
$self->{ 'content' } =~ s/CODEPART[B]*(\d+)CODEPART[B]*/$self->{ 'placeholder_values' }[$1]/igs;
}
$self->{ 'content' } =~ s/PGFALIAS(\d+)/$self->{ 'alias_constant' }{$1}/gs;
while ( $self->{ 'content' } =~ s/AAKEYWCONST(\d+)AA/$self->{ 'keyword_constant' }{$1}/s ) {
delete $self->{ 'keyword_constant' }{$1};
};
# Replace any BSLHPGF by \\
$self->{ 'content' } =~ s/BSLHPGF/\\\\/g;
# Replace any PGFBSLHQ by \'
$self->{ 'content' } =~ s/PGFBSLHQ/\\'/g;
# Replace any $PGFDLM$ by code delimiter '
$self->{ 'content' } =~ s/\$PGFDLM\$/'/g;
# Replace any PGFESCQ1 by ''
$self->{ 'content' } =~ s/PGFESCQ1/''/g;
# Replace any PGFESCQ2 by ""
$self->{ 'content' } =~ s/PGFESCQ2/""/g;
return $self->{ 'content' };
}
=head2 highlight_code
Makes result html with styles set for highlighting.
=cut
sub highlight_code
{
my ($self, $token, $last_token, $next_token) = @_;
# Do not use uninitialized variable
$last_token //= '';
$next_token //= '';
# Colorize operators
while ( my ( $k, $v ) = each %{ $self->{ 'dict' }->{ 'symbols' } } ) {
if ($token eq $k) {
$token = '<span class="sy0">' . $v . '</span>';
return $token;
}
}
# lowercase/uppercase keywords taking care of function with same name
if ( $self->_is_keyword( $token, $next_token, $last_token ) && (!$self->_is_function( $token, $last_token, $next_token ) || $next_token ne '(') ) {
if ( $self->{ 'uc_keywords' } == 1 ) {
$token = '<span class="kw1_l">' . $token . '</span>';
} elsif ( $self->{ 'uc_keywords' } == 2 ) {
$token = '<span class="kw1_u">' . $token . '</span>';
} elsif ( $self->{ 'uc_keywords' } == 3 ) {
$token = '<span class="kw1_c">' . $token . '</span>';
} else {
$token = '<span class="kw1">' . $token . '</span>';
}
return $token;
}
# lowercase/uppercase known functions or words followed by an open parenthesis
# if the token is not a keyword, an open parenthesis or a comment
if (($self->_is_function( $token, $last_token, $next_token ) && $next_token eq '(')
|| (!$self->_is_keyword( $token, $next_token, $last_token ) && !$next_token eq '('
&& $token ne '(' && !$self->_is_comment( $token )) ) {
if ($self->{ 'uc_functions' } == 1) {
$token = '<span class="kw2_l">' . $token . '</span>';
} elsif ($self->{ 'uc_functions' } == 2) {
$token = '<span class="kw2_u">' . $token . '</span>';
} elsif ($self->{ 'uc_functions' } == 3) {
$token = '<span class="kw2_c">' . $token . '</span>';
} else {
$token = '<span class="kw2">' . $token . '</span>';
}
return $token;
}
# Colorize STDIN/STDOUT in COPY statement
if ( grep(/^\Q$token\E$/i, @{ $self->{ 'dict' }->{ 'copy_keywords' } }) ) {
if ($self->{ 'uc_keywords' } == 1) {
$token = '<span class="kw3_!">' . $token . '</span>';
} elsif ($self->{ 'uc_keywords' } == 2) {
$token = '<span class="kw3_u">' . $token . '</span>';
} elsif ($self->{ 'uc_keywords' } == 3) {
$token = '<span class="kw3_c">' . $token . '</span>';
} else {
$token = '<span class="kw3">' . $token . '</span>';
}
return $token;
}
# Colorize parenthesis
if ( grep(/^\Q$token\E$/i, @{ $self->{ 'dict' }->{ 'brackets' } }) ) {
$token = '<span class="br0">' . $token . '</span>';
return $token;
}
# Colorize comment
if ( $self->_is_comment( $token ) ) {
$token = '<span class="br1">' . $token . '</span>';
return $token;
}
# Colorize numbers
$token =~ s/\b(\d+)\b/<span class="nu0">$1<\/span>/igs;
# Colorize string
$token =~ s/('.*?(?<!\\)')/<span class="st0">$1<\/span>/gs;
$token =~ s/(`[^`]*`)/<span class="st0">$1<\/span>/gs;
return $token;
}
=head2 tokenize_sql
Splits input SQL into tokens
Code lifted from SQL::Beautify
=cut
sub tokenize_sql
{
my $self = shift;
my $query = shift;
$query ||= $self->{ 'query' };
# just in case it has not been called in the main script
$query = $self->query() if (!$query);
my $re = qr{
(
(?:\\(?:copyright|errverbose|gx|gexec|gset|gdesc|q|crosstabview|watch|\?|copy|qecho|echo|if|elif|else|endif|edit|ir|include_relative|include|warn|write|html|print|out|ef|ev|h|H|i|p|r|s|w|o|e|g|q|d(?:[aAbcCdDeEfFgilLmnoOpPrRstTuvwxy+]{0,3})?|l\+?|sf\+?|sv\+?|z|a|C|f|H|t|T|x|c|pset|connect|encoding|password|conninfo|cd|setenv|timing|prompt|reset|set|unset|lo_export|lo_import|lo_list|lo_unlink|\!))(?:$|[\n]|[\ \t](?:(?!\\(?:\\|pset|reset|connect|encoding|password|conninfo|cd|setenv|timing|prompt|set|unset|lo_export|lo_import|lo_list|lo_unlink|\!|copy|qecho|echo|edit|html|include_relative|include|print|out|warn|watch|write|q))[\ \t\S])*) # psql meta-command
|
AAKEYWCONST\d+AA(?:\s+AAKEYWCONST\d+AA)+ # preserved multiple constants with newline
|
AAKEYWCONST\d+AA # preserved constants
|
\/\/ # mysql delimiter ( $$ is handled later with PG code delimiters )
|
(?:COPY\s+[^\s]+\s+\((?:.*?)\\\.) # COPY and its content
|
[^\s\(,]+\%(?:ROWTYPE|TYPE) # single line comments
|
(?:\s*--)[\ \t\S]* # single line comments
|
(?:\-\|\-) # range operator "is adjacent to"
|
(?:<\%|\%>|<<\->|<\->>|<\->) # pg_trgm and some geometry operators
|
(?:\->>|\->|\#>>|\#>|\?\&|\?\||\?) # Json Operators
|
(?:\#<=|\#>=|\#<>|\#<|\#=) # compares tinterval and reltime
|
(?:>>=|<<=) # inet operators
|
(?:!!|\@\@\@) # deprecated factorial and full text search operators
|
(?:\|\|\/|\|\/) # square root and cube root
|
(?:\@\-\@|\@\@|\#\#|<<\||\|>>|\&<\||\&<|\|\&>|\&>|<\^|>\^|\?\#|\#|\?<\||\?\-\||\?\-|\?\|\||\?\||\@>|<\@|\~=)
# Geometric Operators
|
(?:~<=~|~>=~|~>~|~<~) # string comparison for pattern matching operator families
|
(?:!~~|!~~\*|~~\*|~~) # LIKE operators
|
(?:!~\*|!~|~\*) # regular expression operators
|
(?:\*=|\*<>|\*<=|\*>=|\*<|\*>) # composite type comparison operators
|
(?:\d+e[\+\-]\d+) # signed exponents
|
(?:<>|<=>|>=|<=|=>|==|!=|:=|=|!|<<|>>|<|>|\|\||\||&&|&|\-|\+|\*(?!/)|/(?!\*)|\%|~|\^|\?) # operators and tests
|
[\[\]\(\),;.] # punctuation (parenthesis, comma)
|
\"\"(?!\"") # empty double quoted string
|
"[^\"\s\(\)=<>!~\*&:\|\-\+\%\^\?\@\#\[\]\{\}\.,;']+"\.[^\"\s\(\)=<>!~\*&:\|\-\+\%\^\?\@\#\[\]\{\}\.,;']+ # fqdn identifier form "schema".table or "table".column
|
[^\"\s=<>!~\*&\(\):\|\-\+\%\^\?\@\#\[\]\{\}\.,;']+\."[^\"\s=<>!~\*&\(\):\|\-\+\%\^\?\@\#\[\]\{\}\.,;']+" # fqdn identifier form schema."table" or table."column"
|
"[^\"\s=<>!~\*&\(\):\|\-\+\%\^\?\@\#\[\]\{\}\.,;']+"\."[^\"\s=<>!~\*&\(\):\|\-\+\%\^\?\@\#\[\]\{\}\.,;']+" # fqdn identifier form "schema"."table" or "table"."column"
|
"(?>(?:(?>[^"\\]+)|""|\\.)*)+" # anything inside double quotes, ungreedy
|
`(?>(?:(?>[^`\\]+)|``|\\.)*)+` # anything inside backticks quotes, ungreedy
|
[EB]*'[^']+' # anything inside single quotes, ungreedy.
|
/\*[\ \t\r\n\S]*?\*/ # C style comments
|
(?:[\w:\@]+[\$]*[\w:\@]*(?:\.(?:\w+|\*)?)*) # words, standard named placeholders, db.table.*, db.*
|
(?:\$\w+\$)
|
(?: \$_\$ | \$\d+ | \${1,2} | \$\w+\$) # dollar expressions - eg $_$ $3 $$ $BODY$
|
(?:\r\n){2,} # empty line Windows
|
\n{2,} # empty line Unix
|
\r{2,} # empty line Mac
|
[\t\ ]+ # any kind of white spaces
|
[^\s\*\/\-\\;:,]+ # anything else
)
}ismx;
my @query = grep { /\S/ } $query =~ m{$re}simxg;
if ($self->{ 'keep_newline' }) {
@query = grep { /(?:\S|^[\r\n]+$)/ } $query =~ m{$re}simxg;
}
# Revert position when a comment is before a comma
if ($self->{ 'comma' } eq 'end')
{
for (my $i = 0; $i < ($#query - 1); $i++)
{
if ($query[$i+1] eq ',' and $self->_is_comment($query[$i]))
{
$query[$i+1] = $query[$i];
$query[$i] = ',';
}
}
}
# Fix token split of negative numbers
if ($#query > 2)
{
for (my $i = 2; $i <= $#query; $i++)
{
if ($query[$i] =~ /^[\d\.]+$/ && $query[$i-1] =~ /^[\+\-]$/
and ($query[$i-2] =~ /$math_operators/ or $query[$i-2] =~ /^(?:,|\(|\[)$/
or $self->_is_keyword( $query[$i-2]))
)
{
$query[$i] = $query[$i-1] . $query[$i];
$query[$i-1] = '';
}
}
}
@query = grep(!/^$/, @query);
#print STDERR "DEBUG KWDLIST: ", join(' | ', @query), "\n";
return @query if (wantarray);
$self->{ '_tokens' } = \@query;
}
sub _pop_level
{
my ($self, $token, $last_token) = @_;
if ($DEBUG)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_POP: line: $line => last=", ($last_token||''), ", token=$token\n";
}
return 0 if ($#{ $self->{ '_level_stack' } } == -1);
return pop( @{ $self->{ '_level_stack' } } ) || 0;
}
sub _reset_level
{
my ($self, $token, $last_token) = @_;
if ($DEBUG)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_RESET: line: $line => last=", ($last_token||''), ", token=$token\n";
}
@{ $self->{ '_level_stack' } } = ();
$self->{ '_level' } = 0;
$self->{ 'break' } = ' ' unless ( $self->{ 'spaces' } != 0 );
}
sub _set_level
{
my ($self, $position, $token, $last_token) = @_;
return 0 if (not defined $position);
if ($DEBUG)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_SET: line: $line => position=$position, last=", ($last_token||''), ", token=$token\n";
}
$self->{ '_level' } = ($position >= 0) ? $position : 0;
}
sub _push_level
{
my ($self, $position, $token, $last_token) = @_;
if ($DEBUG)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_PUSH: line: $line => position=$position, last=", ($last_token||''), ", token=$token\n";
}
push(@{ $self->{ '_level_stack' } }, (($position >= 0) ? $position : 0));
}
sub _set_last
{
my ($self, $token, $last_token) = @_;
if ($DEBUG)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_LAST: line: $line => last=", ($last_token||''), ", token=$token\n";
}
return $token;
}
=head2 beautify
Beautify SQL.
After calling this function, $object->content() will contain nicely indented result.
Code lifted from SQL::Beautify
=cut
sub beautify
{
my $self = shift;
# Use to store the token position in the array
my $pos = 0;
# Main variables used to store differents state
$self->content( '' );
$self->{ '_level' } = 0;
$self->{ '_level_stack' } = [];
$self->{ '_level_parenthesis' } = [];
$self->{ '_new_line' } = 1;
$self->{ '_current_sql_stmt' } = '';
$self->{ '_is_meta_command' } = 0;
$self->{ '_fct_code_delimiter' } = '';
$self->{ '_language_sql' } = 0;
$self->{ '_first_when_in_case' } = 0;
$self->{ '_is_in_if' } = 0;
$self->{ '_is_in_conversion' } = 0;
$self->{ '_is_in_case' } = 0;
$self->{ '_is_in_where' } = 0;
$self->{ '_is_in_from' } = 0;
$self->{ '_is_in_join' } = 0;
$self->{ '_is_in_create' } = 0;
$self->{ '_is_in_create_schema' } = 0;
$self->{ '_is_in_rule' } = 0;
$self->{ '_is_in_create_function' } = 0;
$self->{ '_is_in_drop_function' } = 0;
$self->{ '_is_in_alter' } = 0;
$self->{ '_is_in_trigger' } = 0;
$self->{ '_is_in_publication' } = 0;
$self->{ '_is_in_call' } = 0;
$self->{ '_is_in_type' } = 0;
$self->{ '_is_in_domain' } = 0;
$self->{ '_is_in_declare' } = 0;
$self->{ '_is_in_block' } = -1;
$self->{ '_is_in_work' } = 0;
$self->{ '_is_in_function' } = 0;
$self->{ '_current_function' } = '';
$self->{ '_is_in_statistics' } = 0;
$self->{ '_is_in_cast' } = 0;
$self->{ '_is_in_procedure' } = 0;
$self->{ '_is_in_index' } = 0;
$self->{ '_is_in_with' } = 0;
$self->{ '_is_in_explain' } = 0;
$self->{ '_is_in_overlaps' } = 0;
$self->{ '_parenthesis_level' } = 0;
$self->{ '_parenthesis_function_level' } = 0;
$self->{ '_has_order_by' } = 0;
$self->{ '_is_in_order_by' } = 0;
$self->{ '_has_over_in_join' } = 0;
$self->{ '_insert_values' } = 0;
$self->{ '_is_in_constraint' } = 0;
$self->{ '_is_in_distinct' } = 0;
$self->{ '_is_in_array' } = 0;
$self->{ '_is_in_filter' } = 0;
$self->{ '_parenthesis_filter_level' } = 0;
$self->{ '_is_in_within' } = 0;
$self->{ '_is_in_grouping' } = 0;
$self->{ '_is_in_partition' } = 0;
$self->{ '_is_in_over' } = 0;
$self->{ '_is_in_policy' } = 0;
$self->{ '_is_in_truncate' } = 0;
$self->{ '_is_in_using' } = 0;
$self->{ '_and_level' } = 0;
$self->{ '_col_count' } = 0;
$self->{ '_is_in_drop' } = 0;
$self->{ '_is_in_operator' } = 0;
$self->{ '_is_in_exception' } = 0;
$self->{ '_is_in_sub_query' } = 0;
$self->{ '_is_in_fetch' } = 0;
$self->{ '_is_in_aggregate' } = 0;
$self->{ '_is_in_value' } = 0;
$self->{ '_parenthesis_level_value' } = 0;
$self->{ '_parenthesis_with_level' } = 0;
$self->{ '_is_in_returns_table' } = 0;
$self->{ '_has_limit' } = 0;
$self->{ '_not_a_type' } = 0;
$self->{ 'stmt_number' } = 1;
$self->{ '_is_subquery' } = 0;
$self->{ '_mysql_delimiter' } = '';
$self->{ '_is_in_generated' } = 0;
$self->{ '_is_in_between' } = 0;
$self->{ '_is_in_materialized' } = 0;
@{ $self->{ '_begin_level' } } = ();
my $last = '';
$self->tokenize_sql();
$self->{ 'content' } .= "-- Statement # $self->{ 'stmt_number' }\n" if ($self->{ 'numbering' } and $#{ $self->{ '_tokens' } } > 0);
while ( defined( my $token = $self->_token ) )
{
my $rule = $self->_get_rule( $token );
if ($self->{ 'keep_newline' } and $self->{ '_is_in_block' } >= 0 and $token =~ /^[\r\n]+$/s
and defined $last and $last eq ';'
)
{
$self->_add_token( $token, $last );
next;
}
# Replace concat operator found in some SGBD into || for normalization
if (lc($token) eq 'concat' && defined $self->_next_token() && $self->_next_token ne '(') {
$token = '||';
}
# Case where a keyword is used as a column name.
if ( $self->{ '_is_in_create' } > 1 and $self->_is_keyword( $token, $self->_next_token(), $last )
and defined $self->_next_token and $self->_is_type($self->_next_token))
{
$self->_add_token($token, $last);
$last = $self->_set_last($token, $last);
next;
}
# COPY block
if ( $token =~ /^COPY\s+[^\s]+\s+\(/i )
{
$self->_new_line($token,$last);
$self->_add_token($token, $last);
$self->_new_line($token,$last);
$self->{ 'content' } .= "\n";
$last = $self->_set_last($token, $last);
next;
}
if (uc($token) eq 'BETWEEN')
{
$self->{ '_is_in_between' } = 1;
$self->_add_token($token, $last);
$last = $self->_set_last($token, $last);
next;
}
# mark when we are processing a materialized view to avoid formating issue with parameters
if (uc($token) eq 'MATERIALIZED' and uc($self->_next_token) eq 'VIEW') {
$self->{ '_is_in_materialized' } = 1;
}
####
# Find if the current keyword is a known function name
####
if (defined $last && $last && defined $self->_next_token and $self->_next_token eq '(')
{
my $word = lc($token);
$word =~ s/^[^\.]+\.//;
$word =~ s/^:://;
if (uc($last) eq 'FUNCTION' and $token =~ /^\d+$/) {
$self->{ '_is_in_function' }++;
} elsif ($word && exists $self->{ 'dict' }->{ 'pg_functions' }{$word}) {
$self->{ '_current_function' } = $word;
$self->{ '_is_in_function' }++ if ($self->{ '_is_in_create' } != 1 or $token =~ /^CAST$/i);
# Try to detect user defined functions
} elsif ($last ne '*' and !$self->_is_keyword($token, $self->_next_token(), $last)
and (exists $self->{ 'dict' }->{ 'symbols' }{ $last }
or $last =~ /^\d+$/)
)
{
$self->{ '_is_in_function' }++;
} elsif (uc($token) eq 'IN' and $self->{ '_tokens' }[1] !~ /^(SELECT|WITH|VALUES)$/i) {
$self->{ '_is_in_function' }++;
# try to detect if this is a user function
} elsif (!$self->{ '_is_in_function' } and !$self->{ '_is_in_create' }
and !$self->_is_comment($token) and length($token) > 2 # lazy exclusion of operators/comma
and $last !~ /^(?:AS|RECURSIVE|WITH|OPERATOR|INTO|TYPE|VIEW)/i
and !$self->_is_keyword($token, $self->_next_token(), $last))
{
$self->{ '_is_in_function' }++;
}
}
####
# Set open parenthesis position to know if we
# are in subqueries or function parameters
####
if ( $token eq ')')
{
$self->{ '_parenthesis_filter_level' }-- if ($self->{ '_parenthesis_filter_level' });
$self->{ '_parenthesis_with_level' }-- if ($self->{ '_parenthesis_with_level' });
$self->{ '_is_in_filter' } = 0 if (!$self->{ '_parenthesis_filter_level' });
if (!$self->{ '_is_in_function' }) {
$self->{ '_parenthesis_level' }-- if ($self->{ '_parenthesis_level' } > 0);
} else {
$self->{ '_parenthesis_function_level' }-- if ($self->{ '_parenthesis_function_level' } > 0);
if (!$self->{ '_parenthesis_function_level' }) {
$self->_set_level(pop(@{ $self->{ '_level_parenthesis_function' } }) || 0, $token, $last);
$self->_over($token,$last) if (!$self->{ '_is_in_create' } && !$self->{ '_is_in_operator' } && !$self->{ '_is_in_alter' } and uc($self->_next_token($token,$last)||'') ne 'LOOP');
}
}
$self->{ '_is_in_function' } = 0 if (!$self->{ '_parenthesis_function_level' });
$self->{ '_is_in_cast' } = 0 if ((not defined $self->_next_token or $self->_next_token !~ /^(WITH|WITHOUT)$/i) and (!$self->{ '_parenthesis_level' } or !$self->{ '_parenthesis_function_level' }));
if (!$self->{ '_parenthesis_level' } and $self->{ '_is_in_sub_query' } and ((!$self->{ '_is_in_order_by' } and defined $self->_next_token) or $self->_next_token =~ /^(FROM|GROUP)$/i)) {
$self->{ '_is_in_sub_query' }--;
$self->_back($token, $last);
}
if ($self->{ '_is_in_value' }) {
$self->{ '_parenthesis_level_value' }-- if ($self->{ '_parenthesis_level_value' });
}
}
elsif ( $token eq '(')
{
$self->{ '_parenthesis_filter_level' }++ if ($self->{ '_is_in_filter' });
$self->{ '_parenthesis_with_level' }++ if ($self->{ '_is_in_with' });
if ($self->{ '_is_in_function' }) {
$self->{ '_parenthesis_function_level' }++;
push(@{ $self->{ '_level_parenthesis_function' } } , $self->{ '_level' }) if ($self->{ '_parenthesis_function_level' } == 1);
} else {
if (!$self->{ '_parenthesis_level' } && $self->{ '_is_in_from' }) {
push(@{ $self->{ '_level_parenthesis' } } , $self->{ '_level' });
}
$self->{ '_parenthesis_level' }++;
if ($self->{ '_is_in_value' }) {
$self->{ '_parenthesis_level_value' }++;
}
}
if (defined $self->_next_token and $self->_next_token =~ /^(SELECT|WITH)$/i) {
$self->{ '_is_in_sub_query' }++ if (defined $last and uc($last) ne 'AS');
}
}
####
# Control case where we have to add a newline, go back and
# reset indentation after the last ) in the WITH statement
####
if ($token =~ /^WITH$/i and (!defined $last or ($last ne ')' and $self->_next_token !~ /^(TIME|FUNCTION)/i)))
{
if (!$self->{ '_is_in_partition' } and !$self->{ '_is_in_publication' } and !$self->{ '_is_in_policy' })
{
$self->{ '_is_in_with' } = 1 if (!$self->{ '_is_in_using' } and !$self->{ '_is_in_materialized' }
and uc($self->_next_token) ne 'ORDINALITY' and uc($last) ne 'START');
$self->{ 'no_break' } = 1 if (uc($self->_next_token) eq 'ORDINALITY');
}
$self->{ '_is_in_materialized' } = 0;
}
elsif ($token =~ /^WITH$/i && uc($self->_next_token) eq 'ORDINALITY')
{
$self->{ 'no_break' } = 1;
}
elsif ($token =~ /^(AS|IS)$/i && defined $self->_next_token && $self->_next_token =~ /^(NOT|\()$/)
{
$self->{ '_is_in_materialized' } = 0;
$self->{ '_is_in_with' }++ if ($self->{ '_is_in_with' } == 1);
}
elsif ($self->{ '_is_in_create' } && $token =~ /^AS$/i && defined $self->_next_token && uc($self->_next_token) eq 'SELECT')
{
$self->{ '_is_in_materialized' } = 0;
$self->{ '_is_in_create' } = 0;
}
elsif ( $token eq '[' )
{
$self->{ '_is_in_array' }++;
}
elsif ( $token eq ']' )
{
$self->{ '_is_in_array' }-- if ($self->{ '_is_in_array' });
}
elsif ( $token eq ')' )
{
$self->{ '_has_order_by' } = 0;
if ($self->{ '_is_in_distinct' }) {
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->{ '_is_in_distinct' } = 0;
$last = $self->_set_last($token, $last);
next;
}
$self->{ '_is_in_generated' } = 0 if ($self->{ '_is_in_create' } and $self->{ '_parenthesis_level' } == 1);
$self->{ '_is_in_using' } = 0 if ($self->{ '_is_in_using' } and !$self->{ '_parenthesis_level' } and !$self->{ '_is_in_policy' });
if (defined $self->_next_token and $self->_next_token !~ /^(AS|WITH|,)$/i
and (!$self->_is_comment($self->_next_token) or ($#{$self->{ '_tokens' }} >= 1 and $self->{ '_tokens' }[1] ne ','))
and !$self->{ '_parenthesis_with_level' })
{
$self->{ '_is_in_with' } = 0;
}
if ($self->{ '_is_in_create' } > 1 and defined $self->_next_token
and uc($self->_next_token) eq 'AS' and !$self->{ '_is_in_with'})
{
$self->{ '_is_in_materialized' } = 0;
$self->_new_line($token,$last) if ($last ne '(' and !$self->{ '_is_in_create' });
if ($self->{ '_is_in_returns_table' } and !$self->{ '_parenthesis_level' })
{
$self->{ '_is_in_returns_table' } = 0;
$self->_new_line($token,$last);
$self->_back($token, $last);
$self->_add_token( $token, $last );
$last = $self->_set_last($token, $last);
next;
} else {
$self->_over($token, $last) if ($self->{ '_is_in_procedure' });
}
}
if (($self->{ '_is_in_with' } > 1 || $self->{ '_is_in_operator' })
&& !$self->{ '_parenthesis_level' } && !$self->{ '_parenthesis_with_level' }
&& !$self->{ '_is_in_alter' } && !$self->{ '_is_in_policy' })
{
$self->_new_line($token,$last) if (!$self->{ '_is_in_operator' } ||
(!$self->{ '_is_in_drop' } and $self->_next_token eq ';'));
if (!$self->{ '_is_in_operator' })
{
$self->_set_level($self->_pop_level($token, $last), $token, $last);
$self->_back($token, $last);
}
$self->_add_token( $token );
if (!$self->{ '_is_in_operator' }) {
$self->_reset_level($token, $last);
}
if ($self->{ '_is_in_with' })
{
if (defined $self->_next_token && $self->_next_token eq ',') {
$self->{ '_is_in_with' } = 1;
} else {
$self->{ '_is_in_with' } = 0;
}
}
$last = $self->_set_last($token, $last);
next;
}
}
elsif (defined $self->_next_token && $self->_next_token eq '(')
{
$self->{ '_is_in_filter' } = 1 if (uc($token) eq 'FILTER');
$self->{ '_is_in_grouping' } = 1 if ($token =~ /^(GROUPING|ROLLUP)$/i);
}
elsif ( uc($token) eq 'PASSING' and defined $self->_next_token && uc($self->_next_token) eq 'BY')
{
$self->{ '_has_order_by' } = 1;
}
# Explain need indentation in option list
if ( uc($token) eq 'EXPLAIN' )
{
$self->{ '_is_in_explain' } = 1;
}
elsif ( uc($token) eq 'OVERLAPS' )
{
$self->{ '_is_in_overlaps' } = 1;
}
####
# Set the current kind of statement parsed
####
if ($token =~ /^(FUNCTION|PROCEDURE|SEQUENCE|INSERT|DELETE|UPDATE|SELECT|RAISE|ALTER|GRANT|REVOKE|COMMENT|DROP|RULE|COMMENT|LOCK)$/i) {
my $k_stmt = uc($1);
$self->{ '_is_in_explain' } = 0;
$self->{ '_is_in_where' } = 0;
# Set current statement with taking care to exclude of SELECT ... FOR UPDATE
# statement and ON CONFLICT DO UPDATE.
if ($k_stmt ne 'UPDATE' or (defined $self->_next_token and $self->_next_token ne ';' and $self->_next_token ne ')' and (not defined $last or $last !~ /^(DO|SHARE)$/i)))
{
if ($k_stmt !~ /^(UPDATE|DELETE)$/i || !$self->{ '_is_in_create' })
{
if ($self->{ '_current_sql_stmt' } !~ /^(GRANT|REVOKE)$/i and !$self->{ '_is_in_trigger' } and !$self->{ '_is_in_operator' } and !$self->{ '_is_in_alter' })
{
if ($k_stmt ne 'COMMENT' or $self->_next_token =~ /^(ON|IS)$/i)
{
$self->{ '_current_sql_stmt' } = $k_stmt if (not defined $last or uc($last) ne 'WITH');
}
}
}
}
}
####
# Mark that we are in CREATE statement that need newline
# after a comma in the parameter, declare or column lists.
####
if ($token =~ /^(FUNCTION|PROCEDURE)$/i and $self->{ '_is_in_create' } and !$self->{'_is_in_trigger'}) {
$self->{ '_is_in_create_function' } = 1;
} elsif ($token =~ /^(FUNCTION|PROCEDURE)$/i and defined $last and uc($last) eq 'DROP') {
$self->{ '_is_in_drop_function' } = 1;
} elsif ($token =~ /^(FUNCTION|PROCEDURE)$/i and $self->{'_is_in_trigger'}) {
$self->{ '_is_in_index' } = 1;
}
if ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token !~ /^(EVENT|UNIQUE|INDEX|EXTENSION|TYPE|PUBLICATION|OPERATOR|RULE|CONVERSION|DOMAIN)$/i)
{
if ($self->_next_token =~ /^SCHEMA$/i) {
$self->{ '_is_in_create_schema' } = 1;
}
elsif ($self->{ '_is_in_create_schema' })
{
# we are certainly in a create schema statement
$self->_new_line($token,$last);
$self->{ '_level' } = 1;
$self->{ '_is_in_create_schema' }++;
}
$self->{ '_is_in_create' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^RULE$/i) {
$self->{ '_is_in_rule' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^EVENT$/i) {
$self->{ '_is_in_trigger' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^TYPE$/i) {
$self->{ '_is_in_type' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^DOMAIN$/i) {
$self->{ '_is_in_domain' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^PUBLICATION$/i) {
$self->{ '_is_in_publication' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^CONVERSION$/i) {
$self->{ '_is_in_conversion' } = 1;
} elsif ($token =~ /^(CREATE|DROP)$/i and defined $self->_next_token && $self->_next_token =~ /^OPERATOR$/i) {
$self->{ '_is_in_operator' } = 1;
$self->{ '_is_in_drop' } = 1 if ($token =~ /^DROP$/i);
} elsif ($token =~ /^ALTER$/i) {
$self->{ '_is_in_alter' }++;
} elsif ($token =~ /^DROP$/i){
$self->{ '_is_in_drop' } = 1;
} elsif ($token =~ /^VIEW$/i and $self->{ '_is_in_create' }) {
$self->{ '_is_in_index' } = 1;
$self->{ '_is_in_create' } = 0;
} elsif ($token =~ /^STATISTICS$/i and $self->{ '_is_in_create' }) {
$self->{ '_is_in_statistics' } = 1;
$self->{ '_is_in_create' } = 0;
} elsif ($token =~ /^CAST$/i and defined $self->_next_token and $self->_next_token eq '(') {
$self->{ '_is_in_cast' } = 1;
} elsif ($token =~ /^AGGREGATE$/i and $self->{ '_is_in_create' }) {
$self->{ '_is_in_aggregate' } = 1;
$self->{ '_has_order_by' } = 1;
} elsif ($token =~ /^EVENT$/i and defined $self->_next_token && $self->_next_token =~ /^TRIGGER$/i) {
$self->_over($token, $last);
$self->{ '_is_in_index' } = 1;
} elsif ($token =~ /^CREATE$/i and defined $self->_next_token && $self->_next_token =~ /^INDEX|UNIQUE/i)
{
if ($self->{ '_is_in_create_schema' })
{
$self->_new_line($token,$last);
$self->{ '_level' } = 1;
$self->{ '_is_in_create_schema' }++;
}
}
if ($self->{ '_is_in_using' } and defined $self->_next_token and $self->_next_token =~ /^(OPERATOR|AS)$/i) {
$self->{ '_is_in_using' } = 0;
}
if ($token =~ /^ALTER$/i and $self->{ '_is_in_alter' } > 1) {
$self->_new_line($token,$last);
$self->_over($token, $last) if ($last ne ',');
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
# Special case for MySQL delimiter
if ( uc($token) eq 'DELIMITER' && defined $self->_next_token &&
($self->_next_token eq '//' or $self->_next_token eq '$$'))
{
$self->{ '_mysql_delimiter' } = $self->_next_token;
}
elsif (uc($token) eq 'DELIMITER' && defined $self->_next_token &&
$self->_next_token eq ';')
{
$self->{ '_mysql_delimiter' } = '';
}
# case of the delimiter alone
if ($self->{ '_mysql_delimiter' } && $token eq $self->{ '_mysql_delimiter' })
{
$self->{ 'content' } =~ s/\n\n$/\n/s;
$self->_add_token( $token );
$self->_new_line($token,$last);
$last = $self->_set_last(';', $last);
next
}
####
# Mark that we are in a CALL statement to remove any new line
####
if ($token =~ /^CALL$/i) {
$self->{ '_is_in_call' } = 1;
}
# Increment operator tag to add newline in alter operator statement
if (($self->{ '_is_in_alter' } or uc($last) eq 'AS') and uc($token) eq 'OPERATOR') {
$self->_new_line($token,$last) if (uc($last) eq 'AS' and uc($token) eq 'OPERATOR');
$self->{ '_is_in_operator' }++;
}
####
# Mark that we are in index/constraint creation statement to
# avoid inserting a newline after comma and AND/OR keywords.
# This also used in SET statement taking care that we are not
# in update statement. CREATE statement are not subject to this rule
####
if (! $self->{ '_is_in_create' } and $token =~ /^(INDEX|PRIMARY|CONSTRAINT)$/i) {
$self->{ '_is_in_index' } = 1 if ($last =~ /^(ALTER|CREATE|UNIQUE|USING|ADD)$/i);
} elsif (! $self->{ '_is_in_create' } and uc($token) eq 'SET') {
$self->{ '_is_in_index' } = 1 if ($self->{ '_current_sql_stmt' } ne 'UPDATE');
} elsif ($self->{ '_is_in_create' } and (uc($token) eq 'UNIQUE' or ($token =~ /^(PRIMARY|FOREIGN)$/i and uc($self->_next_token) eq 'KEY'))) {
$self->{ '_is_in_constraint' } = 1;
}
# Same as above but for ALTER FUNCTION/PROCEDURE/SEQUENCE or when
# we are in a CREATE FUNCTION/PROCEDURE statement
elsif ($token =~ /^(FUNCTION|PROCEDURE|SEQUENCE)$/i and !$self->{'_is_in_trigger'}) {
$self->{ '_is_in_index' } = 1 if (uc($last) eq 'ALTER' and !$self->{ '_is_in_operator' } and !$self->{ '_is_in_alter' });
if ($token =~ /^FUNCTION$/i && ($self->{ '_is_in_create' } || $self->{ '_current_sql_stmt' } eq 'COMMENT')) {
$self->{ '_is_in_index' } = 1 if (!$self->{ '_is_in_operator' });
} elsif ($token =~ /^PROCEDURE$/i && $self->{ '_is_in_create' }) {
$self->{ '_is_in_index' } = 1;
$self->{ '_is_in_procedure' } = 1;
}
}
# Desactivate index like formatting when RETURN(S) keyword is found
elsif ($token =~ /^(RETURN|RETURNS)$/i)
{
$self->{ '_is_in_index' } = 0;
if (uc($token) eq 'RETURNS' and uc ($self->_next_token()) eq 'TABLE') {
$self->{ '_is_in_returns_table' } = 1;
}
}
elsif ($token =~ /^AS$/i)
{
$self->{ '_is_in_materialized' } = 0;
if ( !$self->{ '_is_in_index' } and $self->{ '_is_in_from' } and $last eq ')' and uc($token) eq 'AS' and $self->_next_token() eq '(') {
$self->{ '_is_in_index' } = 1;
} else {
$self->{ '_is_in_index' } = 0;
}
$self->{ '_is_in_block' } = 1 if ($self->{ '_is_in_procedure' });
$self->{ '_is_in_over' } = 0;
}
if ($token =~ /^(BEGIN|DECLARE)$/i)
{
# print STDERR "JJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJJ $token\n" if (uc($token) eq 'DECLARE');
$self->{ '_is_in_create' }-- if ($self->{ '_is_in_create' });
if (uc($token) eq 'BEGIN')
{
push( @{ $self->{ '_begin_level' } }, ($#{ $self->{ '_begin_level' } } < 0) ? 0 : $self->{ '_level' } );
}
# $self->_add_token( $token );
# $self->_new_line($token,$last);
# $self->_over($token,$last);
# $last = $self->_set_last($token, $last);
# next;
}
####
# Mark statements that use string_agg() or group_concat() function
# as statement that can have an ORDER BY clause inside the call to
# prevent applying order by formatting.
####
if ($token =~ /^(string_agg|group_concat|array_agg|percentile_cont)$/i) {
$self->{ '_has_order_by' } = 1;
} elsif ( $token =~ /^(?:GENERATED)$/i and $self->_next_token =~ /^(ALWAYS|BY)$/i ) {
$self->{ '_is_in_generated' } = 1;
} elsif ( $token =~ /^(?:TRUNCATE)$/i ) {
$self->{ 'no_break' } = 1;
} elsif ( uc($token) eq 'IDENTITY' ) {
$self->{ '_has_order_by' } = 0;
$self->{ 'no_break' } = 0;
$self->{ '_is_in_generated' } = 0;
} elsif ( $self->{ '_has_order_by' } and uc($token) eq 'ORDER' and $self->_next_token =~ /^BY$/i) {
$self->_add_token( $token, $last );
$last = $self->_set_last($token, $last);
next;
} elsif ($self->{ '_has_order_by' } and uc($token) eq 'BY') {
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^OVER$/i)
{
$self->_add_token( $token );
$self->{ '_is_in_over' } = 1;
$self->{ '_has_order_by' } = 1;
$last = $self->_set_last($token, $last);
next;
}
# Fix case where we don't knwon if we are outside a SQL function
if (defined $last and uc($last) eq 'AS' and defined $self->_next_token and $self->_next_token eq ';'
and $self->{ '_is_in_create_function' }) {
$self->{ '_is_in_create_function' } = 0;
}
####
# Set function code delimiter, it can be any string found after
# the AS keyword in function or procedure creation code
####
# Toogle _fct_code_delimiter to force next token to be stored as the function code delimiter
if (uc($token) eq 'AS' and (!$self->{ '_fct_code_delimiter' } || $self->_next_token =~ /CODEPART/)
and $self->{ '_current_sql_stmt' } =~ /^(FUNCTION|PROCEDURE)$/i)
{
if ($self->{ '_is_in_create' } and !$self->{ '_is_in_with' } and !$self->{ '_is_in_cast' }
and $self->_next_token !~ /^(IMPLICIT|ASSIGNMENT)$/i)
{
$self->_new_line($token,$last);
$self->_add_token( $token );
$self->_reset_level($token, $last) if ($self->_next_token !~ /CODEPARTB/);
} else {
$self->_add_token( $token );
}
if ($self->_next_token !~ /(CODEPART|IMPLICIT|ASSIGNMENT)/ || $self->_next_token =~ /^'/)
{
if (!$self->{ '_is_in_cast' } and $self->{ '_is_in_create' })
{
# extract potential code joined with the code separator
if ($self->{ '_tokens' }->[0] =~ s/^'(.)/$1/)
{
$self->{ '_tokens' }->[0] =~ s/[;\s]*'$//;
my @tmp_arr = $self->tokenize_sql($self->{ '_tokens' }->[0]);
push(@tmp_arr, ";", "'");
shift(@{ $self->{ '_tokens' } });
unshift(@{ $self->{ '_tokens' } }, "'", @tmp_arr);
}
$self->{ '_fct_code_delimiter' } = '1';
}
}
$self->{ '_is_in_create' } = 0;
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^(INSTEAD|ALSO)$/i and defined $last and uc($last) eq 'DO')
{
$self->_add_token( $token );
$self->_new_line($token,$last);
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^DO$/i and defined $self->_next_token and $self->_next_token =~ /^(INSTEAD|ALSO|UPDATE|NOTHING)$/i)
{
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^DO$/i and !$self->{ '_fct_code_delimiter' } and $self->_next_token =~ /^\$[^\s]*/)
{
@{ $self->{ '_begin_level' } } = ();
$self->{ '_fct_code_delimiter' } = '1';
$self->{ '_is_in_create_function' } = 1;
$self->_new_line($token,$last) if ($self->{ 'content' } !~ /\n$/s);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
# Store function code delimiter
if ($self->{ '_fct_code_delimiter' } eq '1')
{
if ($self->_next_token =~ /CODEPART/) {
$self->{ '_fct_code_delimiter' } = '0';
} elsif ($token =~ /^'.*'$/) {
$self->{ '_fct_code_delimiter' } = "'";
} else {
$self->{ '_fct_code_delimiter' } = $token;
}
$self->_add_token( $token );
if (!$self->{ '_is_in_create_function' } or $self->_next_token ne ','
or $self->{ '_tokens' }[1] !~ /KEYWCONST/) {
$self->_new_line($token,$last);
}
if (defined $self->_next_token
and $self->_next_token !~ /^(DECLARE|BEGIN)$/i) {
$self->_over($token,$last);
$self->{ '_language_sql' } = 1;
}
if ($self->{ '_fct_code_delimiter' } eq "'")
{
$self->{ '_is_in_block' } = -1;
$self->{ '_is_in_exception' } = 0;
$self->_reset_level($token, $last) if ($self->_next_token eq ';');
$self->{ '_fct_code_delimiter' } = '';
$self->{ '_current_sql_stmt' } = '';
$self->{ '_is_in_procedure' } = 0;
$self->{ '_is_in_function' } = 0;
$self->{ '_is_in_create_function' } = 0;
$self->{ '_language_sql' } = 0;
}
$last = $self->_set_last($token, $last);
next;
}
# With SQL language the code delimiter can be include with the keyword, try to detect and fix it
if ($self->{ '_fct_code_delimiter' } and $token =~ s/(.)\Q$self->{ '_fct_code_delimiter' }\E$/$1/)
{
unshift(@{ $self->{ '_tokens' } }, $self->{ '_fct_code_delimiter' });
}
# Desactivate the block mode when code delimiter is found for the second time
if ($self->{ '_fct_code_delimiter' } && $token eq $self->{ '_fct_code_delimiter' })
{
$self->{ '_is_in_block' } = -1;
$self->{ '_is_in_exception' } = 0;
$self->{ '_is_in_create_function' } = 0;
$self->_reset_level($token, $last);
$self->{ '_fct_code_delimiter' } = '';
$self->{ '_current_sql_stmt' } = '';
$self->{ '_language_sql' } = 0;
$self->_new_line($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
####
# Mark when we are parsing a DECLARE or a BLOCK section. When
# entering a BLOCK section store the current indentation level
####
if (uc($token) eq 'DECLARE' and $self->{ '_is_in_create_function' })
{
$self->{ '_is_in_block' } = -1;
$self->{ '_is_in_exception' } = 0;
$self->{ '_is_in_declare' } = 1;
$self->_reset_level($token, $last);
$self->_new_line($token,$last);
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->_over($token,$last);
$last = $self->_set_last($token, $last);
$self->{ '_is_in_create_function' } = 0;
next;
}
elsif ( uc($token) eq 'BEGIN' )
{
$self->{ '_is_in_declare' } = 0;
if ($self->{ '_is_in_block' } == -1) {
$self->_reset_level($token, $last);
}
$self->_new_line($token,$last);
$self->_add_token( $token );
if (defined $self->_next_token && $self->_next_token !~ /^(WORK|TRANSACTION|ISOLATION|;)$/i) {
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->{ '_is_in_block' }++;
# Store current indent position to print END at the right level
$self->_push_level($self->{ '_level' }, $token, $last);
}
$self->{ '_is_in_work' }++ if (!$self->{ 'no_grouping' } and defined $self->_next_token && $self->_next_token =~ /^(WORK|TRANSACTION|ISOLATION|;)$/i);
$last = $self->_set_last($token, $last);
next;
}
elsif ( $token =~ /^(COMMIT|ROLLBACK)$/i and (not defined $last or uc($last) ne 'ON') and !$self->{ '_is_in_procedure' } )
{
$self->{ '_is_in_work' } = 0;
$self->{ '_is_in_declare' } = 0;
$self->{ '_is_in_create_function' } = 0;
$self->_new_line($token,$last);
$self->_set_level($self->_pop_level($token, $last), $token, $last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
@{ $self->{ '_begin_level' } } = ();
next;
}
elsif ( $token =~ /^(COMMIT|ROLLBACK)$/i and defined $self->_next_token and $self->_next_token eq ';' and $self->{ '_is_in_procedure' } )
{
$self->_new_line($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
@{ $self->{ '_begin_level' } } = ();
next;
}
elsif ( $token =~ /^FETCH$/i and defined $last and $last eq ';')
{
$self->_new_line($token,$last);
$self->_back($token, $last) if ($self->{ '_is_in_block' } == -1);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
$self->{ '_is_in_fetch' } = 1;
next;
}
####
# Special case where we want to add a newline into ) AS (
####
if (uc($token) eq 'AS' and $last eq ')' and $self->_next_token eq '(')
{
$self->_new_line($token,$last);
}
# and before RETURNS with increasing indent level
elsif (uc($token) eq 'RETURNS')
{
$self->_new_line($token,$last);
$self->_over($token,$last) if (uc($self->_next_token) ne 'NULL');
}
# and before WINDOW
elsif (uc($token) eq 'WINDOW')
{
$self->_new_line($token,$last);
$self->_set_level($self->_pop_level($token, $last), $token, $last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
$self->{ '_has_order_by' } = 1;
next;
}
# Treated DISTINCT as a modifier of the whole select clause, not only the first column only
if (uc($token) eq 'ON' && defined $last && uc($last) eq 'DISTINCT')
{
$self->{ '_is_in_distinct' } = 1;
$self->_over($token,$last);
}
elsif (uc($token) eq 'DISTINCT' && defined $last && uc($last) eq 'SELECT' && defined $self->_next_token && $self->_next_token !~ /^ON$/i)
{
$self->_add_token( $token );
$self->_new_line($token,$last) if (!$self->{'wrap_after'});
$self->_over($token,$last);
$last = $self->_set_last($token, $last);
next;
}
if ( $rule )
{
$self->_process_rule( $rule, $token );
}
elsif ($token =~ /^(LANGUAGE|SECURITY|COST)$/i && !$self->{ '_is_in_alter' } && !$self->{ '_is_in_drop' } )
{
@{ $self->{ '_begin_level' } } = ();
$self->_new_line($token,$last) if (uc($token) ne 'SECURITY' or (defined $last and uc($last) ne 'LEVEL'));
$self->_add_token( $token );
}
elsif ($token =~ /^PARTITION$/i && !$self->{ '_is_in_over' } && defined $last && $last ne '(')
{
$self->{ '_is_in_partition' } = 1;
if ($self->{ '_is_in_create' } && defined $last and $last eq ')')
{
$self->_new_line($token,$last);
$self->_set_level($self->_pop_level($token, $last), $token, $last) if ($self->{ '_level' });
$self->_add_token( $token );
}
else
{
$self->_add_token( $token );
}
}
elsif ($token =~ /^POLICY$/i)
{
$self->{ '_is_in_policy' } = 1;
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^TRUNCATE$/i && $self->_next_token !~ /^(TABLE|ONLY|,)$/i)
{
$self->{ '_is_in_truncate' } = 1;
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
my $str_tmp = join(' ', @{ $self->{ '_tokens' } });
$str_tmp =~ s/;.*//s;
if ($str_tmp =~ / , /s)
{
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->{ '_is_in_truncate' } = 2;
}
next;
}
elsif ($token =~ /^(TABLE|ONLY)$/i && uc($last) eq 'TRUNCATE')
{
$self->{ '_is_in_truncate' } = 1;
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
my $str_tmp = join(' ', @{ $self->{ '_tokens' } });
$str_tmp =~ s/;.*//s;
if ($str_tmp =~ / , /s)
{
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->{ '_is_in_truncate' } = 2;
}
next;
}
elsif ($token =~ /^(RESTART|CASCADE)$/i && $self->{ '_is_in_truncate' } == 2)
{
$self->_new_line($token,$last);
$self->_back($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^TRIGGER$/i and defined $last and $last =~ /^(CREATE|CONSTRAINT|REPLACE)$/i)
{
$self->{ '_is_in_trigger' } = 1;
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^(BEFORE|AFTER|INSTEAD)$/i and $self->{ '_is_in_trigger' })
{
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^EXECUTE$/i and ($self->{ '_is_in_trigger' } or (defined $last and uc($last) eq 'AS')))
{
$self->_new_line($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ( $token eq '(' )
{
if ($self->{ '_is_in_aggregate' } && defined $self->_next_token and ($self->_is_keyword($self->_next_token) or $self->_is_sql_keyword($self->_next_token)) and uc($self->_next_token) ne 'VARIADIC') {
$self->{ '_is_in_aggregate' } = 0;
$self->{ '_has_order_by' } = 0;
}
$self->{ '_is_in_create' }++ if ($self->{ '_is_in_create' });
$self->{ '_is_in_constraint' }++ if ($self->{ '_is_in_constraint' });
$self->_add_token( $token, $last );
if (defined $self->_next_token and uc($self->_next_token) eq 'SELECT')
{
$self->{ '_is_in_cast' } = 0;
$self->{ '_is_subquery' }++;
}
if (defined $self->_next_token and $self->_next_token eq ')' and !$self->{ '_is_in_create' }) {
$last = $self->_set_last($token, $last);
next;
}
if ( !$self->{ '_is_in_index' } && !$self->{ '_is_in_publication' }
&& !$self->{ '_is_in_distinct' } && !$self->{ '_is_in_filter' }
&& !$self->{ '_is_in_grouping' } && !$self->{ '_is_in_partition' }
&& !$self->{ '_is_in_over' } && !$self->{ '_is_in_trigger' }
&& !$self->{ '_is_in_policy' } && !$self->{ '_is_in_aggregate' }
&& !$self->{ 'no_break' } && !$self->{ '_is_in_generated' }
) {
if (uc($last) eq 'AS' || $self->{ '_is_in_create' } == 2 || uc($self->_next_token) eq 'CASE')
{
$self->_new_line($token,$last) if ((!$self->{'_is_in_function'} or $self->_next_token =~ /^CASE$/i) and $self->_next_token ne ')' and $self->_next_token !~ /^(PARTITION|ORDER)$/i);
}
if ($self->{ '_is_in_with' } == 1 or $self->{ '_is_in_explain' }) {
$self->_over($token,$last);
$self->_new_line($token,$last) if (!$self->{ 'wrap_after' });
$last = $self->_set_last($token, $last) if (!$self->{ '_is_in_explain' } || $self->{ 'wrap_after' });
next;
}
if (!$self->{ '_is_in_if' } and !$self->{ '_is_in_alter' } and (!$self->{ '_is_in_function' } or $last ne '('))
{
$self->_over($token,$last) if ($self->{ '_is_in_operator' } <= 2 && $self->{ '_is_in_create' } <= 2);
if (!$self->{ '_is_in_function' } and !$self->_is_type($self->_next_token))
{
if ($self->{ '_is_in_operator' } == 1) {
$self->_new_line($token,$last);
$self->{ '_is_in_operator' }++;
} elsif ($self->{ '_is_in_type' }) {
$self->_new_line($token,$last);
}
}
$last = $self->_set_last($token, $last);
}
if ($self->{ '_is_in_type' } == 1) {
$last = $self->_set_last($token, $last);
next;
}
}
if ($self->{ 'format_type' } && $self->{ '_current_sql_stmt' } =~ /(FUNCTION|PROCEDURE)/i
&& $self->{ '_is_in_create' } == 2
&& (not defined $self->_next_token or $self->_next_token ne ')')
) {
$self->_over($token,$last) if ($self->{ '_is_in_block' } < 0);
$self->_new_line($token,$last);
next;
}
}
elsif ( $token eq ')' )
{
if (defined $self->_next_token)
{
my $next = quotemeta($self->_next_token) || 'SELECT';
if (!$self->{ '_parenthesis_level' } and defined $self->_next_token
and $self->_is_keyword($self->_next_token) or (
!grep(/^$next$/, %{$self->{ 'dict' }->{ 'symbols' }})
)
)
{
$self->{ '_is_in_where' } = 0;
}
}
if ($self->{ '_is_in_constraint' } and defined $self->_next_token
and ($self->_next_token eq ',' or $self->_next_token eq ')')) {
$self->{ '_is_in_constraint' } = 0;
} elsif ($self->{ '_is_in_constraint' }) {
$self->{ '_is_in_constraint' }--;
}
# Case of CTE and explain
if ($self->{ '_is_in_with' } == 1 || $self->{ '_is_in_explain' })
{
$self->_back($token, $last);
$self->_new_line($token,$last) if (!$self->{ 'wrap_after' } && !$self->{ '_is_in_overlaps' });
$self->_add_token( $token );
$last = $self->_set_last($token, $last) if ($token ne ')' or uc($self->_next_token) ne 'AS');
$self->{ '_is_in_explain' } = 0;
next;
}
if ( ($self->{ 'format_type' } && $self->{ '_current_sql_stmt' } =~ /(FUNCTION|PROCEDURE)/i
&& $self->{ '_is_in_create' } == 2) || (defined $self->_next_token and uc($self->_next_token) eq 'INHERITS')
)
{
$self->_back($token, $last) if ($self->{ '_is_in_block' } < 0);
$self->_new_line($token,$last) if (defined $last && $last ne '(');
}
if ($self->{ '_is_in_index' } || $self->{ '_is_in_alter' }
|| $self->{ '_is_in_partition' } || $self->{ '_is_in_policy' }
|| (defined $self->_next_token and $self->_next_token =~ /^OVER$/i)
) {
$self->_add_token( '' );
$self->_add_token( $token );
$self->{ '_is_in_over' } = 0 if (!$self->{ '_parenthesis_level' });
$last = $self->_set_last($token, $last);
$self->{ '_is_in_create' }-- if ($self->{ '_is_in_create' });
next;
}
if (defined $self->_next_token && $self->_next_token !~ /FILTER/i)
{
my $add_nl = 0;
$add_nl = 1 if ($self->{ '_is_in_create' } > 1
and defined $last and $last ne '('
and !$self->{ '_is_in_cast' }
and (not defined $self->_next_token or $self->_next_token =~ /^(TABLESPACE|PARTITION|AS|;)$/i or ($self->_next_token =~ /^ON$/i and !$self->{ '_parenthesis_level' }))
);
$add_nl = 1 if ($self->{ '_is_in_type' } == 1
and $self->_next_token !~ /^AS$/i
and (not defined $self->_next_token or $self->_next_token eq ';')
);
$add_nl = 1 if ($self->{ '_current_sql_stmt' } ne 'INSERT'
and !$self->{ '_is_in_function' }
and (defined $self->_next_token
and $self->_next_token =~ /^(SELECT|WITH)$/i)
and $self->{ '_tokens' }[1] !~ /^(ORDINALITY|FUNCTION)$/i
and ($self->{ '_is_in_create' } or $last ne ')' and $last ne ']')
and (uc($self->_next_token) ne 'WITH' or uc($self->{ '_tokens' }->[ 1 ]) !~ /TIME|INOUT/i)
);
$self->_new_line($token,$last) if ($add_nl);
if (!$self->{ '_is_in_grouping' } and !$self->{ '_is_in_trigger' }
and !$self->{ 'no_break' }
and !$self->{ '_is_in_generated' }
and $self->{ '_is_in_create' } <= 2
and $self->_next_token !~ /^LOOP$/i
)
{
$self->_back($token, $last);
}
$self->{ '_is_in_create' }-- if ($self->{ '_is_in_create' });
if ($self->{ '_is_in_type' })
{
$self->_reset_level($token, $last) if ($self->{ '_is_in_block' } == -1 && !$self->{ '_parenthesis_level' });
$self->{ '_is_in_type' }--;
}
}
if (!$self->{ '_parenthesis_level' })
{
$self->{ '_is_in_filter' } = 0;
$self->{ '_is_in_within' } = 0;
$self->{ '_is_in_grouping' } = 0;
$self->{ '_is_in_over' } = 0;
$self->{ '_has_order_by' } = 0;
$self->{ '_is_in_policy' } = 0;
$self->{ '_is_in_aggregate' } = 0;
}
$self->_add_token( $token );
# Do not go further if this is the last token
if (not defined $self->_next_token) {
$last = $self->_set_last($token, $last);
next;
}
# When closing CTE statement go back again
if ( ($self->_next_token =~ /^(?:SELECT|INSERT|UPDATE|DELETE)$/i and !$self->{ '_is_in_policy' })
or ($self->{ '_is_in_with' } and $self->{ '_is_subquery' }
and $self->{ '_is_subquery' } % 2 == 0) ) {
$self->_back($token, $last) if ($self->{ '_current_sql_stmt' } ne 'INSERT'
and (!$self->{ '_parenthesis_level' } or !defined $self->_next_token
or uc($self->_next_token) eq 'AS'
or ($#{$self->{ '_tokens' }} >= 1 and $self->{ '_tokens' }->[ 1 ] eq ',')));
}
$self->{ '_is_subquery' }-- if ($self->{ '_is_subquery' }
and defined $self->_next_token and $#{$self->{ '_tokens' }} >= 1
and (uc($self->_next_token) eq 'AS' or $self->{ '_tokens' }->[ 1 ] eq ','));
if ($self->{ '_is_in_create' } <= 1)
{
my $next_tok = quotemeta($self->_next_token);
$self->_new_line($token,$last)
if (defined $self->_next_token
and $self->_next_token !~ /^(?:AS|IS|THEN|INTO|BETWEEN|ON|IN|FILTER|WITHIN|DESC|ASC|WITHOUT|CASCADE)$/i
and ($self->_next_token !~ /^(AND|OR)$/i or !$self->{ '_is_in_if' })
and $self->_next_token ne ')'
and $self->_next_token !~ /^:/
and $self->_next_token ne ';'
and $self->_next_token ne ','
and $self->_next_token ne '||'
and uc($self->_next_token) ne 'CONCAT'
and ($self->_is_keyword($self->_next_token) or $self->_is_function($self->_next_token))
and $self->{ '_current_sql_stmt' } !~ /^(GRANT|REVOKE)$/
and !exists $self->{ 'dict' }->{ 'symbols' }{ $next_tok }
and !$self->{ '_is_in_over' }
and !$self->{ '_is_in_cast' }
and !$self->{ '_is_in_domain' }
);
}
}
elsif ( $token eq ',' )
{
my $add_newline = 0;
# Format INSERT with multiple values
if ($self->{ '_current_sql_stmt' } eq 'INSERT' and $last eq ')' and $self->_next_token eq '(') {
$self->_new_line($token,$last) if ($self->{ 'comma' } eq 'start');
$self->_add_token( $token );
$self->_new_line($token,$last) if ($self->{ 'comma' } eq 'end');
next;
}
$self->{ '_is_in_constraint' } = 0 if ($self->{ '_is_in_constraint' } == 1);
$self->{ '_col_count' }++ if (!$self->{ '_is_in_function' });
if (($self->{ '_is_in_over' } or $self->{ '_has_order_by' }) and !$self->{ '_parenthesis_level' } and !$self->{ '_parenthesis_function_level' })
{
$self->{ '_is_in_over' } = 0;
$self->{ '_has_order_by' } = 0;
$self->_back($token, $last);
}
$add_newline = 1 if ( !$self->{ 'no_break' }
&& !$self->{ '_is_in_generated' }
&& !$self->{ '_is_in_function' }
&& !$self->{ '_is_in_distinct' }
&& !$self->{ '_is_in_array' }
&& ($self->{ 'comma_break' } || $self->{ '_current_sql_stmt' } ne 'INSERT')
&& ($self->{ '_current_sql_stmt' } ne 'RAISE')
&& ($self->{ '_current_sql_stmt' } !~ /^(FUNCTION|PROCEDURE)$/
|| $self->{ '_fct_code_delimiter' } ne '')
&& !$self->{ '_is_in_where' }
&& !$self->{ '_is_in_drop' }
&& !$self->{ '_is_in_index' }
&& !$self->{ '_is_in_aggregate' }
&& !$self->{ '_is_in_alter' }
&& !$self->{ '_is_in_publication' }
&& !$self->{ '_is_in_call' }
&& !$self->{ '_is_in_policy' }
&& !$self->{ '_is_in_grouping' }
&& !$self->{ '_is_in_partition' }
&& ($self->{ '_is_in_constraint' } <= 1)
&& ($self->{ '_is_in_create' } <= 2)
&& $self->{ '_is_in_operator' } != 1
&& !$self->{ '_has_order_by' }
&& $self->{ '_current_sql_stmt' } !~ /^(GRANT|REVOKE)$/
&& ($self->_next_token !~ /^('$|\s*\-\-)/is or ($self->_next_token !~ /^'$/is and $self->{ 'no_comments' }))
&& !$self->{ '_parenthesis_function_level' }
&& (!$self->{ '_col_count' } or $self->{ '_col_count' } > ($self->{ 'wrap_after' } - 1))
|| ($self->{ '_is_in_with' } and !$self->{ 'wrap_after' })
);
$self->{ '_col_count' } = 0 if ($self->{ '_col_count' } > ($self->{ 'wrap_after' } - 1));
$add_newline = 0 if ($self->{ '_is_in_using' } and $self->{ '_parenthesis_level' });
$add_newline = 0 if ($self->{ 'no_break' });
if ($self->{ '_is_in_with' } >= 1 && !$self->{ '_parenthesis_level' }) {
$add_newline = 1 if (!$self->{ 'wrap_after' });
}
if ($self->{ 'format_type' } && $self->{ '_current_sql_stmt' } =~ /(FUNCTION|PROCEDURE)/i && $self->{ '_is_in_create' } == 2) {
$add_newline = 1;
}
if ($self->{ '_is_in_alter' } && $self->{ '_is_in_operator' } >= 2) {
$add_newline = 1 if (defined $self->_next_token and $self->_next_token =~ /^(OPERATOR|FUNCTION)$/i);
}
$add_newline = 1 if ($self->{ '_is_in_returns_table' });
$self->_new_line($token,$last) if ($add_newline and $self->{ 'comma' } eq 'start');
$self->_add_token( $token );
$add_newline = 0 if ($self->{ '_is_in_value' } and $self->{ '_parenthesis_level_value' });
$add_newline = 0 if ($self->{ '_is_in_function' } or $self->{ '_is_in_statistics' });
$add_newline = 0 if (defined $self->_next_token and !$self->{ 'no_comments' } and $self->_is_comment($self->_next_token));
$add_newline = 0 if (defined $self->_next_token and $self->_next_token =~ /KEYWCONST/ and $self->{ '_tokens' }[1] =~ /^(LANGUAGE|STRICT)$/i);
$add_newline = 1 if ($self->{ '_is_in_truncate' });
$self->_new_line($token,$last) if ($add_newline and $self->{ 'comma' } eq 'end' and ($self->{ 'comma_break' } || $self->{ '_current_sql_stmt' } ne 'INSERT'));
}
elsif ( $token eq ';' or $token =~ /^\\(?:g|crosstabview|watch)/ )
{
# statement separator or executing psql meta command (prefix 'g' includes all its variants)
$self->_add_token($token);
next if ($token eq ';' and $self->{ '_is_in_case' } and uc($last) ne 'CASE');
if ($self->{ '_is_in_rule' }) {
$self->_back($token, $last);
}
elsif ($self->{ '_is_in_create' } && $self->{ '_is_in_block' } > -1)
{
$self->_pop_level($token, $last);
}
# Initialize most of statement related variables
$self->{ 'no_break' } = 0;
$self->{ '_is_in_generated' } = 0;
$self->{ '_is_in_where' } = 0;
$self->{ '_is_in_between' } = 0;
$self->{ '_is_in_from' } = 0;
$self->{ '_is_in_join' } = 0;
$self->{ '_is_in_create' } = 0;
$self->{ '_is_in_create_schema' } = 0;
$self->{ '_is_in_alter' } = 0;
$self->{ '_is_in_rule' } = 0;
$self->{ '_is_in_publication' } = 0;
$self->{ '_is_in_call' } = 0;
$self->{ '_is_in_type' } = 0;
$self->{ '_is_in_domain' } = 0;
$self->{ '_is_in_function' } = 0;
$self->{ '_current_function' } = '';
$self->{ '_is_in_prodedure' } = 0;
$self->{ '_is_in_index' } = 0;
$self->{ '_is_in_statistics' } = 0;
$self->{ '_is_in_cast' } = 0;
$self->{ '_is_in_if' } = 0;
$self->{ '_is_in_with' } = 0;
$self->{ '_is_in_overlaps' } = 0;
$self->{ '_has_order_by' } = 0;
$self->{ '_has_over_in_join' } = 0;
$self->{ '_parenthesis_level' } = 0;
$self->{ '_parenthesis_function_level' } = 0;
$self->{ '_is_in_constraint' } = 0;
$self->{ '_is_in_distinct' } = 0;
$self->{ '_is_in_array' } = 0;
$self->{ '_is_in_filter' } = 0;
$self->{ '_parenthesis_filter_level' } = 0;
$self->{ '_is_in_partition' } = 0;
$self->{ '_is_in_over' } = 0;
$self->{ '_is_in_policy' } = 0;
$self->{ '_is_in_truncate' } = 0;
$self->{ '_is_in_trigger' } = 0;
$self->{ '_is_in_using' } = 0;
$self->{ '_and_level' } = 0;
$self->{ '_col_count' } = 0;
$self->{ '_is_in_drop' } = 0;
$self->{ '_is_in_conversion' } = 0;
$self->{ '_is_in_operator' } = 0;
$self->{ '_is_in_explain' } = 0;
$self->{ '_is_in_sub_query' } = 0;
$self->{ '_is_in_fetch' } = 0;
$self->{ '_is_in_aggregate' } = 0;
$self->{ '_is_in_value' } = 0;
$self->{ '_parenthesis_level_value' } = 0;
$self->{ '_parenthesis_with_level' } = 0;
$self->{ '_is_in_returns_table' } = 0;
$self->{ '_has_limit' } = 0;
$self->{ '_not_a_type' } = 0;
$self->{ '_is_subquery' } = 0;
$self->{ '_is_in_order_by' } = 0;
$self->{ '_is_in_materialized' } = 0;
$self->{ '_is_in_drop_function' } = 0;
if ( $self->{ '_insert_values' } )
{
if ($self->{ '_is_in_block' } == -1 and !$self->{ '_is_in_declare' } and !$self->{ '_fct_code_delimiter' }) {
$self->_reset_level($token, $last);
}
elsif ($self->{ '_is_in_block' } == -1 and $self->{ '_current_sql_stmt' } eq 'INSERT' and !$self->{ '_is_in_create' } and !$self->{ '_is_in_create_function' })
{
$self->_back($token, $last);
$self->_pop_level($token, $last);
}
else
{
$self->_set_level($self->_pop_level($token, $last), $token, $last);
}
$self->{ '_insert_values' } = 0;
}
$self->{ '_current_sql_stmt' } = '';
$self->{ 'break' } = "\n" unless ( $self->{ 'spaces' } != 0 );
#$self->_new_line($token,$last) if ($last !~ /^(VALUES|IMPLICIT|ASSIGNMENT)$/i);
$self->_new_line($token,$last) if ($last !~ /^VALUES$/i);
# Add an additional newline after ; when we are not in a function
if ($self->{ '_is_in_block' } == -1 and !$self->{ '_is_in_work' } and !$self->{ '_language_sql' }
and !$self->{ '_is_in_declare' } and uc($last) ne 'VALUES')
{
$self->{ '_new_line' } = 0;
$self->_new_line($token,$last);
$self->{ 'stmt_number' }++;
$self->{ 'content' } .= "-- Statement # $self->{ 'stmt_number' }\n" if ($self->{ 'numbering' } and $#{ $self->{ '_tokens' } } > 0);
}
# End of statement; remove all indentation when we are not in a BEGIN/END block
if (!$self->{ '_is_in_declare' } and $self->{ '_is_in_block' } == -1 and !$self->{ '_fct_code_delimiter' })
{
$self->_reset_level($token, $last);
}
#elsif ((not defined $self->_next_token or $self->_next_token !~ /^INSERT$/) and !$self->{ '_fct_code_delimiter' })
elsif (!$self->{ '_language_sql' } and (not defined $self->_next_token or $self->_next_token !~ /^INSERT$/))
{
if ($#{ $self->{ '_level_stack' } } == -1) {
$self->_set_level(($self->{ '_is_in_declare' }) ? 1 : ($self->{ '_is_in_block' }+1), $token, $last);
} else {
$self->_set_level($self->{ '_level_stack' }[-1], $token, $last);
}
}
$last = $self->_set_last($token, $last);
}
elsif ($token =~ /^FOR$/i)
{
if ($self->{ '_is_in_policy' })
{
$self->_over($token,$last);
$self->_new_line($token,$last);
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
if ($self->_next_token =~ /^(UPDATE|KEY|NO|VALUES)$/i)
{
$self->_back($token, $last) if (!$self->{ '_has_limit' } and ($#{$self->{ '_level_stack' }} == -1
or $self->{ '_level' } > $self->{ '_level_stack' }[-1]));
$self->_new_line($token,$last);
$self->{ '_has_limit' } = 0;
}
elsif ($self->_next_token =~ /^EACH$/ and $self->{ '_is_in_trigger' })
{
$self->_new_line($token,$last);
}
$self->_add_token( $token );
# cover FOR in cursor
$self->_over($token,$last) if (uc($self->_next_token) eq 'SELECT');
$last = $self->_set_last($token, $last);
}
elsif ( $token =~ /^(?:FROM|WHERE|SET|RETURNING|HAVING|VALUES)$/i )
{
if (uc($token) eq 'FROM' and $self->{ '_has_order_by' } and !$self->{ '_parenthesis_level' })
{
$self->_back($token, $last) if ($self->{ '_has_order_by' });
}
$self->{ 'no_break' } = 0;
$self->{ '_col_count' } = 0;
# special cases for create partition statement
if ($token =~ /^VALUES$/i && defined $last and $last =~ /^(FOR|IN)$/i)
{
$self->_add_token( $token );
$self->{ 'no_break' } = 1;
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^FROM$/i && defined $last and uc($last) eq 'VALUES')
{
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
# Case of DISTINCT FROM clause
if ($token =~ /^FROM$/i)
{
if (uc($last) eq 'DISTINCT' || $self->{ '_is_in_fetch' } || $self->{ '_is_in_alter' } || $self->{ '_is_in_conversion' })
{
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
$self->{ '_is_in_from' }++ if (!$self->{ '_is_in_function' } && !$self->{ '_is_in_partition' });
}
if ($token =~ /^WHERE$/i && !$self->{ '_is_in_filter' })
{
$self->_back($token, $last) if ($self->{ '_has_over_in_join' });
$self->{ '_is_in_where' }++;
$self->{ '_is_in_from' }-- if ($self->{ '_is_in_from' });
$self->{ '_is_in_join' } = 0;
$self->{ '_has_over_in_join' } = 0;
}
elsif (!$self->{ '_is_in_function' })
{
$self->{ '_is_in_where' }-- if ($self->{ '_is_in_where' });
}
if ($token =~ /^SET$/i and $self->{ '_is_in_create' })
{
# Add newline before SET statement in function header
$self->_new_line($token,$last) if (not defined $last or $last !~ /^(DELETE|UPDATE)$/i);
}
elsif ($token =~ /^WHERE$/i and $self->{ '_current_sql_stmt' } eq 'DELETE')
{
$self->_new_line($token,$last);
$self->_add_token( $token );
$self->_over($token,$last);
$last = $self->_set_last($token, $last);
$self->{ '_is_in_join' } = 0;
$last = $self->_set_last($token, $last);
next;
}
elsif ($token =~ /^SET$/i and defined $last and uc($last) eq 'UPDATE' and !$self->_is_keyword($self->_next_token()))
{
$self->{ '_is_in_index' } = 0;
$self->{ '_is_in_from' } = 0;
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->_over($token,$last);
$last = $self->_set_last($token, $last);
next;
}
elsif ($token !~ /^FROM$/i or (!$self->{ '_is_in_function' } and !$self->{ '_is_in_statistics' }
and $self->{ '_current_sql_stmt' } !~ /(DELETE|REVOKE)/))
{
if (!$self->{ '_is_in_filter' } and ($token !~ /^SET$/i or !$self->{ '_is_in_index' }))
{
$self->_back($token, $last) if ((uc($token) ne 'VALUES' or $self->{ '_current_sql_stmt' } ne 'INSERT' and $last ne "'")and (uc($token) !~ /^WHERE$/i or $self->{'_is_in_with' } < 2 or $self->{ '_level' } > 1));
if (uc($token) eq 'WHERE' and $self->{'_is_in_function' }
and $self->{ '_is_subquery' } <= 2
)
{
$self->_over($token, $last);
}
$self->_new_line($token,$last) if (!$self->{ '_is_in_rule' } and ($last !~ /^DEFAULT$/i or $self->_next_token() ne ';'));
}
}
else
{
if (uc($token) eq 'FROM' and $self->{ '_is_in_sub_query' }
and !grep(/^\Q$last\E$/i, @extract_keywords)
and ($self->{ '_insert_values' } or $self->{ '_is_in_function' })
and (!$self->{ '_is_in_function' } or
!grep(/^$self->{ '_current_function' }$/, @have_from_clause))
)
{
$self->_new_line($token,$last);
$self->_back($token, $last);
}
if (uc($token) eq 'FROM') {
$self->{ '_current_function' } = '';
}
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
if ($token =~ /^VALUES$/i and !$self->{ '_is_in_rule' } and !$self->{ 'comma_break' } and ($self->{ '_current_sql_stmt' } eq 'INSERT' or $last eq '('))
{
$self->_over($token,$last);
if ($self->{ '_current_sql_stmt' } eq 'INSERT' or $last eq '(')
{
$self->{ '_insert_values' } = 1;
$self->_push_level($self->{ '_level' }, $token, $last);
}
}
if ($token =~ /^VALUES$/i and $last eq '(')
{
$self->{ '_is_in_value' } = 1;
}
if (uc($token) eq 'WHERE')
{
$self->_add_token( $token, $last );
$self->{ '_is_in_value' } = 0;
$self->{ '_parenthesis_level_value' } = 0;
}
else
{
$self->_add_token( $token );
}
if ($token =~ /^VALUES$/i and $last eq '(')
{
$self->_over($token,$last);
}
elsif ( $token =~ /^SET$/i && $self->{ '_current_sql_stmt' } eq 'UPDATE' )
{
$self->_new_line($token,$last) if (!$self->{ 'wrap_after' });
$self->_over($token,$last);
}
elsif ( !$self->{ '_is_in_over' } and !$self->{ '_is_in_filter' } and ($token !~ /^SET$/i or $self->{ '_current_sql_stmt' } eq 'UPDATE') )
{
if (defined $self->_next_token and $self->_next_token !~ /\(|;/
and ($self->_next_token !~ /^(UPDATE|KEY|NO)$/i || uc($token) eq 'WHERE'))
{
$self->_new_line($token,$last) if (!$self->{ 'wrap_after' });
$self->_over($token,$last);
}
}
}
# Add newline before INSERT and DELETE if last token was AS (prepared statement)
elsif (defined $last and $token =~ /^(?:INSERT|DELETE|UPDATE)$/i and uc($last) eq 'AS')
{
$self->_new_line($token,$last);
$self->_add_token( $token );
}
elsif ( $self->{ '_current_sql_stmt' } !~ /^(GRANT|REVOKE)$/
and $token =~ /^(?:SELECT|PERFORM|UPDATE|DELETE)$/i
and (!$self->{ '_is_in_policy' } || $self->{ 'format_type' })
)
{
$self->{ 'no_break' } = 0;
if ($token =~ /^(SELECT|UPDATE|DELETE|INSERT)$/i && $self->{ '_is_in_policy' })
{
$self->_over($token,$last);
}
# case of ON DELETE/UPDATE clause in create table statements
if ($token =~ /^(UPDATE|DELETE)$/i && $self->{ '_is_in_create' }) {
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
if ($token =~ /^UPDATE$/i and $last =~ /^(FOR|KEY|DO)$/i)
{
$self->_add_token( $token );
}
elsif (!$self->{ '_is_in_policy' } && $token !~ /^(DELETE|UPDATE)$/i && (!defined $self->_next_token || $self->_next_token !~ /^DISTINCT$/i))
{
$self->_new_line($token,$last) if (!defined $last or $last ne "\\\\");
$self->_add_token( $token );
$self->_new_line($token,$last) if (!$self->{ 'wrap_after' } and (!defined $last or $last ne "\\\\"));
$self->_over($token,$last);
}
else
{
if ($self->{ '_is_in_policy' } > 1) {
$self->_new_line($token,$last);
}
$self->_add_token( $token );
if ($self->{ '_is_in_policy' } > 1) {
$self->_new_line($token,$last);
$self->_over($token,$last);
}
$self->{ '_is_in_policy' }++ if ($self->{ '_is_in_policy' });
}
}
elsif ( $self->{ '_current_sql_stmt' } !~ /^(GRANT|REVOKE)$/
and uc($token) eq 'INSERT'
and $self->{ '_is_in_policy' } && $self->{ 'format_type' })
{
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->_over($token,$last);
}
elsif ( $token =~ /^(?:WITHIN)$/i )
{
$self->{ '_is_in_within' } = 1;
$self->{ '_has_order_by' } = 1;
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
elsif ( $token =~ /^(?:GROUP|ORDER|LIMIT|EXCEPTION)$/i or (uc($token) eq 'ON' and uc($self->_next_token()) eq 'CONFLICT'))
{
if ($self->{ 'format_type' } and uc($token) eq 'GROUP' and uc($self->_next_token()) eq 'BY') {
$self->{ 'no_break' } = 1;
}
if (uc($token) eq 'ORDER' and uc($self->_next_token()) eq 'BY') {
$self->{ '_is_in_order_by' } = 1;
} else {
$self->{ '_is_in_order_by' } = 0;
}
$self->{ '_is_in_value' } = 0;
$self->{ '_parenthesis_level_value' } = 0;
if (uc($token) eq 'GROUP' and !defined $last or uc($last) eq 'EXCLUDE') {
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
if (($self->{ '_is_in_within' } && uc($token) eq 'GROUP') || ($self->{ '_is_in_over' } && uc($token) eq 'ORDER')) {
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
next;
}
if ($self->{ '_has_over_in_join' } and uc($token) eq 'GROUP')
{
$self->_back($token, $last);
$self->{ '_has_over_in_join' } = 0;
}
$self->{ '_is_in_join' } = 0;
$self->{ '_has_limit' } = 1 if (uc($token) eq 'LIMIT');
if ($token !~ /^EXCEPTION/i) {
$self->_back($token, $last);
} else {
$self->_set_level($self->_pop_level($token, $last), $token, $last);
}
if (uc($token) ne 'EXCEPTION' or not defined $last or uc($last) ne 'RAISE')
{
# Excluding CREATE/DROP GROUP
if (uc($token) ne 'LIMIT' or !$self->{ '_is_in_create' })
{
$self->_new_line($token,$last) if (!$self->{ '_is_in_function' } and (not defined $last or $last !~ /^(CREATE|DROP)$/));
}
}
# Store current indent position to print END at the right level
if (uc($last) ne 'RAISE' and $token =~ /^EXCEPTION$/i)
{
$self->{ '_is_in_exception' } = 1;
if ($#{ $self->{ '_begin_level' } } >= 0) {
$self->_set_level($self->{ '_begin_level' }[-1], $token, $last);
}
} elsif (uc($last) eq 'RAISE' and $token =~ /^EXCEPTION$/i) {
$self->_push_level($self->{ '_level' }, $token, $last);
$self->_over($token,$last);
}
$self->{ '_is_in_where' }-- if ($self->{ '_is_in_where' });
$self->_add_token( $token );
if ($token =~ /^EXCEPTION$/i && $self->{ '_level' } == 0) {
$self->_over($token,$last);
}
}
elsif ( $token =~ /^(?:BY)$/i and $last !~ /^(?:INCREMENT|OWNED|PARTITION|GENERATED)$/i)
{
$self->_add_token( $token );
$self->{ '_col_count' } = 0 if (defined $last && $last =~ /^(?:GROUP|ORDER)/i);
if (!$self->{ '_has_order_by' } and !$self->{ '_is_in_over' }) {
$self->_new_line($token,$last) if (!$self->{ 'wrap_after' } and !$self->{ '_is_in_function' });
$self->_over($token,$last);
}
}
elsif ( $token =~ /^(?:CASE)$/i and uc($last) ne 'END')
{
if ($self->{ '_is_in_policy' })
{
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->_add_token( $token );
$self->{ '_is_in_policy' }++;
} else {
$self->_add_token( $token );
}
# Store current indent position to print END at the right level
$self->_push_level($self->{ '_level' }, $token, $last);
# Mark next WHEN statement as first element of a case
# to force indentation only after this element
$self->{ '_first_when_in_case' } = 1;
$self->{ '_is_in_case' }++;
}
elsif ( $token =~ /^(?:WHEN)$/i)
{
if (!$self->{ '_first_when_in_case' } and !$self->{'_is_in_trigger'}
and defined $last and uc($last) ne 'CASE'
)
{
if (!$self->{ '_is_in_exception' }) {
$self->_set_level($self->{ '_level_stack' }[-1], $token, $last) if ($#{ $self->{ '_level_stack' } } >= 0);
} elsif ($#{ $self->{ '_begin_level' }} >= 0) {
$self->_set_level($self->{ '_begin_level' }[-1]+1, $token, $last);
}
}
$self->_new_line($token,$last) if (not defined $last or $last !~ /^(CASE|,|\()$/i );
$self->_add_token( $token );
if (!$self->{ '_is_in_case' } && !$self->{ '_is_in_trigger' }) {
$self->_over($token,$last);
}
$self->{ '_first_when_in_case' } = 0;
}
elsif ( $token =~ /^(?:IF|LOOP)$/i && $self->{ '_current_sql_stmt' } ne 'GRANT')
{
if ($self->{ '_is_in_join' }) {
$self->{ '_is_in_join' } = 0;
$self->_back($token,$last);
$self->_add_token( $token );
} else {
$self->_add_token( $token );
}
$self->{ 'no_break' } = 0;
if (defined $self->_next_token and $self->_next_token !~ /^(EXISTS|;)$/i)
{
if (uc($self->_next_token) ne 'NOT' || uc($self->{ '_tokens' }->[ 1 ]) ne 'EXISTS')
{
$self->_new_line($token,$last) if ($token =~ /^LOOP$/i);
$self->_over($token,$last);
$self->_push_level($self->{ '_level' }, $token, $last);
if ($token =~ /^IF$/i) {
$self->{ '_is_in_if' } = 1;
}
}
}
}
elsif ($token =~ /^THEN$/i)
{
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->_set_level($self->{ '_level_stack' }[-1], $token, $last) if ($self->{ '_is_in_if' } and $#{ $self->{ '_level_stack' } } >= 0);
if ($self->{ '_is_in_case' } && defined $self->_next_token() and $self->_next_token() !~ /^(\(|RAISE)$/i) {
$self->_set_level($self->{ '_level_stack' }[-1], $token, $last) if ($#{ $self->{ '_level_stack' } } >= 0);
$self->_over($token,$last);
}
if ($self->{ '_is_in_case' } && defined $self->_next_token() and
$self->_next_token() eq '(' and $self->{ '_tokens' }[1] !~ /^(SELECT|CASE)$/i
)
{
$self->_set_level($self->{ '_level_stack' }[-1], $token, $last) if ($#{ $self->{ '_level_stack' } } >= 0);
$self->_over($token,$last);
}
$self->{ '_is_in_if' } = 0;
}
elsif ( $token =~ /^(?:ELSE|ELSIF)$/i )
{
$self->_back($token, $last);
$self->_new_line($token,$last);
$self->_add_token( $token );
$self->_new_line($token,$last) if ($token !~ /^ELSIF$/i);
$self->_over($token,$last);
}
elsif ( $token =~ /^(?:END)$/i )
{
$self->{ '_first_when_in_case' } = 0;
if ($self->{ '_is_in_case' })
{
$self->{ '_is_in_case' }--;
$self->_back($token, $last);
$self->_set_level($self->_pop_level($token, $last), $token, $last);
if (!$self->{ '_is_in_create_function' } or $self->_next_token eq ';')
{
$self->_new_line($token,$last);
$self->_add_token( $token );
next;
}
}
# When we are not in a function code block (0 is the main begin/end block of a function)
elsif ($self->{ '_is_in_block' } == -1 && $last ne ',')
{
# END is closing a create function statement so reset position to begining
if ($self->_next_token !~ /^(IF|LOOP|CASE|INTO|FROM|END|ELSE|AND|OR|WHEN|AS|,)$/i) {
$self->_reset_level($token, $last);
} else
{
# otherwise back to last level stored at CASE keyword
$self->_set_level($self->_pop_level($token, $last), $token, $last);
}
}
# We reach the last end of the code
elsif ($self->{ '_is_in_block' } > -1 and $self->_next_token =~/^(;|\$.*\$)$/ and !$self->{ '_is_in_exception' })
{
if ($self->{ '_is_in_block' } == 0)
{
$self->_reset_level($token, $last);
} else {
$self->_set_level($self->_pop_level($token, $last) - 1, $token, $last);
$self->{ '_is_in_block' }--;
}
}
# We are in code block
elsif ($last ne ',')
{
# decrease the block level if this is a END closing a BEGIN block
if ($self->_next_token !~ /^(IF|LOOP|CASE|INTO|FROM|END|ELSE|AND|OR|WHEN|AS|,)$/i)
{
$self->{ '_is_in_block' }--;
}
# Go back to level stored with IF/LOOP/BEGIN/EXCEPTION block
if ($self->{ '_is_in_block' } > -1)
{
$self->_set_level($self->_pop_level($token, $last), $token, $last);
} else {
$self->_reset_level($token, $last);
}
}
if ($self->_next_token eq ';') {
$self->_set_level(pop( @{ $self->{ '_begin_level' } } ), $token, $last);
} elsif (!$self->{ '_is_in_exception' } and $self->_next_token !~ /^(AS|CASE|FROM|,)$/i) {
$self->_back($token, $last) if ($self->_next_token =~ /^(IF|LOOP|CASE|INTO|FROM|END|ELSE|AND|OR|WHEN|AS|,)$/i);
}
$self->_new_line($token,$last);
$self->_add_token( $token );
}
elsif ( $token =~ /^(?:END::[^\s]+)$/i and $self->{ '_is_in_case' } )
{
$self->{ '_first_when_in_case' } = 0;
if ($self->{ '_is_in_case' })
{
$self->{ '_is_in_case' }--;
$self->_back($token, $last);
$self->_set_level($self->_pop_level($token, $last), $token, $last);
}
$self->_new_line($token,$last);
$self->_add_token( $token );
}
elsif ( $token =~ /^(?:UNION|INTERSECT|EXCEPT)$/i )
{
$self->{ 'no_break' } = 0;
if ($self->{ '_is_in_join' })
{
$self->_back($token, $last);
$self->{ '_is_in_join' } = 0;
}
$self->_back($token, $last) unless defined $last and $last eq '(';
$self->_new_line($token,$last);
$self->_add_token( $token );
$self->_new_line($token,$last) if ( defined $self->_next_token
and $self->_next_token ne '('
and $self->_next_token !~ /^ALL$/i
);
$self->{ '_is_in_where' }-- if ($self->{ '_is_in_where' });
$self->{ '_is_in_from' } = 0;
}
elsif ( $token =~ /^(?:LEFT|RIGHT|FULL|INNER|OUTER|CROSS|NATURAL)$/i and (not defined $last or uc($last) ne 'MATCH') )
{
$self->{ 'no_break' } = 0;
if (!$self->{ '_is_in_join' } and ($last and $last ne ')') )
{
$self->_back($token, $last);
}
if ($self->{ '_has_over_in_join' })
{
$self->{ '_has_over_in_join' } = 0;
$self->_back($token, $last);
}
if ( $token =~ /(?:LEFT|RIGHT|FULL|CROSS|NATURAL)$/i )
{
$self->_new_line($token,$last);
$self->_over($token,$last) if ( $self->{ '_level' } == 0 || ($self->{ '_is_in_with' } > 1 and $self->{ '_level' } == 1));
}
if ( ($token =~ /(?:INNER|OUTER)$/i) && ($last !~ /(?:LEFT|RIGHT|CROSS|NATURAL|FULL)$/i) )
{
$self->_new_line($token,$last);
$self->_over($token,$last) if (!$self->{ '_is_in_join' });
}
$self->_add_token( $token );
}
elsif ( $token =~ /^(?:JOIN)$/i and !$self->{ '_is_in_operator' })
{
$self->{ 'no_break' } = 0;
if ( not defined $last or $last !~ /^(?:LEFT|RIGHT|FULL|INNER|OUTER|CROSS|NATURAL)$/i )
{
$self->_new_line($token,$last);
$self->_back($token, $last) if ($self->{ '_has_over_in_join' });
$self->{ '_has_over_in_join' } = 0;
}
$self->_add_token( $token );
$self->{ '_is_in_join' } = 1;
}
elsif ( $token =~ /^(?:AND|OR)$/i )
{
$self->{ '_is_in_where' } = 0;
# Try to detect AND in BETWEEN clause to prevent newline insert
if (uc($token) eq 'AND' and ($self->{ '_is_in_between' }
|| (defined $last && $last =~ /^(PRECEDING|FOLLOWING|ROW)$/i)))
{
$self->_add_token( $token );
$last = $self->_set_last($token, $last);
$self->{ '_is_in_between' } = 0;
next;
}
$self->{ 'no_break' } = 0;
if ($self->{ '_is_in_join' })
{
$self->_over($token,$last);
$self->{ '_has_over_in_join' } = 1;
}
$self->{ '_is_in_join' } = 0;
if ( !$self->{ '_is_in_if' } and !$self->{ '_is_in_index' }
and (!$last or $last !~ /^(?:CREATE)$/i)
and ($self->{ '_is_in_create' } <= 2)
and !$self->{ '_is_in_trigger' }
)
{
$self->_new_line($token,$last);
if (!$self->{'_and_level'} and (!$self->{ '_level' } || $self->{ '_is_in_alter' })) {
$self->_over($token,$last);
} elsif ($self->{'_and_level'} and !$self->{ '_level' } and uc($token) eq 'OR') {
$self->_over($token,$last);
} elsif ($#{$self->{ '_level_stack' }} >= 0 and $self->{ '_level' } == $self->{ '_level_stack' }[-1]) {
$self->_over($token,$last);
}
}
$self->_add_token( $token );
$self->{'_and_level'}++;
}
elsif ( $token =~ /^\/\*.*\*\/$/s )
{
if ( !$self->{ 'no_comments' } )
{
$token =~ s/\n[\s\t]+\*/\n\*/gs;
if (!$self->{ '_is_in_over' } and !$self->{ '_is_in_function' })
{
$self->_new_line($token,$last), $self->_add_token('') if (defined $last and $last eq ';');
$self->_new_line($token,$last);
}
$self->_add_token( $token );
$self->{ 'break' } = "\n" unless ( $self->{ 'spaces' } != 0 );
if (!$self->{ '_is_in_function' } and !$self->{ '_is_in_over' }
and (!$self->_is_comment($token) or !defined $self->_next_token
or $self->_next_token ne ')')
)
{
$self->_new_line($token,$last);
}
$self->{ 'break' } = " " unless ( $self->{ 'spaces' } != 0 );
}
}
elsif (($token =~ /^USING$/i and !$self->{ '_is_in_order_by' } and !$self->{ '_is_in_exception' }
and ($self->{ '_current_sql_stmt' } ne 'DELETE' or uc($self->_next_token) !~ /^(\(|LATERAL)$/i))
or (uc($token) eq 'WITH' and uc($self->_next_token()) eq 'CHECK' and $self->{ '_is_in_policy' })
)
{
if (!$self->{ '_is_in_from' })
{
$self->_over($token,$last) if ($self->{ '_is_in_operator' } || ($self->{ '_is_in_policy' } && !$self->{ 'format_type' } && !$self->{ '_is_in_using' }));
$self->_push_level($self->{ '_level' }, $token, $last) if ($token =~ /^USING$/i);
$self->_set_level($self->_pop_level($token, $last), $token, $last) if (uc($token) eq 'WITH' and $self->{ '_is_in_policy' } > 1 && !$self->{ 'format_type' } && $self->{ '_is_in_using' });
$self->_new_line($token,$last) if (uc($last) ne 'EXCLUDE' and !$self->{ '_is_in_index' } and !$self->{ '_is_in_function' });
}
else
{
# USING from join clause disable line break like in function
$self->{ '_is_in_function' }++;
# Restore FROM position
$self->_set_level($self->_pop_level($token, $last), $token, $last) if (!$self->{ '_is_in_join' });
}
$self->_add_token($token);
$self->{ '_is_in_using' } = 1;
$self->{ '_is_in_policy' }++ if (!$self->{ '_is_in_from' } && !$self->{ '_is_in_join' }
&& uc($last) ne 'EXCLUDE' && !$self->{ '_is_in_function' }
&& !$self->{ '_is_in_operator' } && !$self->{ '_is_in_create' }
&& !$self->{ '_is_in_index' });
}
elsif ($token =~ /^EXCLUDE$/i)
{
if ($last !~ /^(FOLLOWING|ADD)$/i or $self->_next_token !~ /^USING$/i) {
$self->_new_line($token,$last) if ($last !~ /^(FOLLOWING|ADD)$/i);
}
$self->_add_token( $token );
$self->{ '_is_in_using' } = 1;
}
elsif ($token =~ /^\\\S/)
{
# treat everything starting with a \ and at least one character as psql meta command.
$self->_add_token( $token );
$self->_new_line($token,$last) if ($token ne "\\\\" and defined $self->_next_token and $self->_next_token ne "\\\\");
}
elsif ($token =~ /^(ADD|DROP)$/i && ($self->{ '_current_sql_stmt' } eq 'SEQUENCE'
|| $self->{ '_current_sql_stmt' } eq 'ALTER'))
{
if ($self->_next_token !~ /^(NOT|NULL|DEFAULT)$/i and (not defined $last or !$self->{ '_is_in_alter' } or $last ne '(')) {
$self->_new_line($token,$last);
if ($self->{ '_is_in_alter' } < 2) {
$self->_over($token,$last);
}
}
$self->_add_token($token, $last);
$self->{ '_is_in_alter' }++ if ($self->{ '_is_in_alter' } == 1);
}
elsif ($token =~ /^INCREMENT$/i && $self->{ '_current_sql_stmt' } eq 'SEQUENCE')
{
$self->_new_line($token,$last);
$self->_add_token($token);
}
elsif ($token =~ /^NO$/i and $self->_next_token =~ /^(MINVALUE|MAXVALUE)$/i)
{
$self->_new_line($token,$last);
$self->_add_token($token);
}
elsif ($last !~ /^(\(|NO)$/i and $token =~ /^(MINVALUE|MAXVALUE)$/i)
{
$self->_new_line($token,$last);
$self->_add_token($token);
}
elsif ($token =~ /^CACHE$/i)
{
$self->_new_line($token,$last);
$self->_add_token($token);
}
else
{
next if ($self->{'keep_newline'} and $token =~ /^\s+$/);
if ($self->{ '_fct_code_delimiter' } and $self->{ '_fct_code_delimiter' } =~ /^'.*'$/) {
$self->{ '_fct_code_delimiter' } = "";
$self->{ '_language_sql' } = 0;
}
if ($self->{ '_is_in_block' } != -1 and !$self->{ '_fct_code_delimiter' })
{
$self->{ '_is_in_block' } = -1;
$self->{ '_is_in_procedure' } = 0;
$self->{ '_is_in_function' } = 0;
}
# special case with comment
if ($token =~ /(?:\s*--)[\ \t\S]*/s)
{
if ( !$self->{ 'no_comments' } )
{
$token =~ s/^(\s*)(--.*)/$2/s;
my $start = $1 || '';
if ($start =~ /\n/s) {
$self->_new_line($token,$last), $self->_add_token('') if (defined $last and $last eq ';' and $self->{ 'content' } !~ /\n$/s);
$self->_new_line($token,$last);
}
$token =~ s/\s+$//s;
$token =~ s/^\s+//s;
$self->_add_token( $token );
$self->_new_line($token,$last) if ($start || ($self->{ 'content' } !~ /\n$/s && defined $self->_next_token && uc($self->_next_token) ne 'AS'));
# Add extra newline after the last comment if we are not in a block or a statement
if (defined $self->_next_token and $self->_next_token !~ /^\s*--/)
{
$self->{ 'content' } .= "\n" if ($self->{ '_is_in_block' } == -1
and !$self->{ '_is_in_declare' }
and !$self->{ '_fct_code_delimiter' }
and !$self->{ '_current_sql_stmt' }
and defined $last and $self->_is_comment($last)
and $self->{ 'content' } !~ /\n$/s
);
}
$last = $self->_set_last($token, $last);
}
next;
}
if ($last =~ /^(?:SEQUENCE)$/i and $self->_next_token !~ /^(OWNED|;)$/i)
{
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->_over($token,$last);
}
else
{
if (defined $last && $last eq ')' && (!defined $self->_next_token || $self->_next_token ne ';'))
{
if (!$self->{ '_parenthesis_level' } && $self->{ '_is_in_from' })
{
$self->_set_level(pop(@{ $self->{ '_level_parenthesis' } }) || 1, $token, $last);
}
}
if (defined $last and uc($last) eq 'UPDATE' and $self->{ '_current_sql_stmt' } eq 'UPDATE')
{
$self->_new_line($token,$last);
$self->_over($token,$last);
}
if (defined $last and uc($last) eq 'AS' and uc($token) eq 'WITH') {
$self->_new_line($token,$last);
}
if (uc($token) eq 'INSERT' and defined $last and $last eq ';')
{
if ($#{ $self->{ '_level_stack' } } >= 0) {
$self->_set_level($self->{ '_level_stack' }[-1], $token, $last);
} else {
$self->_back($token,$last);
}
}
if (($self->{ '_is_in_policy' } > 1 || ($self->{ '_is_in_policy' } && $self->{ '_is_in_sub_query' })) && $token =~ /^(ALL|SELECT|UPDATE|DELETE|INSERT)$/i)
{
$self->_new_line($token,$last);
$self->_over($token,$last);
$self->_add_token( $token );
$self->_new_line($token,$last);
$self->_over($token,$last);
$last = $self->_set_last($token, $last);
next;
}
$self->{ '_is_in_policy' }++ if ($token =~ /^SELECT$/i and $self->{ '_is_in_policy' });
if ($self->{ 'comma_break' } and $self->{ '_current_sql_stmt' } eq 'INSERT' && $last eq '(')
{
$self->_new_line($token,$last);
}
# Remove extra newline at end of code of SQL functions
if ($token eq "'" and $last eq ';' and $self->_next_token =~ /^(;|LANGUAGE|STRICT|SET|IMMUTABLE|STABLE|VOLATILE)$/i) {
$self->{ 'content' } =~ s/\s+$/\n/s;
}
# Finally add the token without further condition
$self->_add_token( $token, $last );
if ($last eq "'" and $token =~ /^(BEGIN|DECLARE)$/i)
{
$last = $self->_set_last($token, $last);
$self->_new_line($token,$last);
$self->_over($token,$last);
}
# Reset CREATE statement flag when using CTE
if ($self->{ '_is_in_create' } && $self->{ '_is_in_with' }
&& uc($token) eq 'WITH' && uc($last) eq 'AS')
{
$self->{ '_is_in_create' } = 0;
}
if (defined $last && uc($last) eq 'LANGUAGE' && (!defined $self->_next_token || $self->_next_token ne ';'))
{
$self->_new_line($token,$last);
}
}
}
$last = $self->_set_last($token, $last);
$pos++;
}
if ($self->{ 'no_extra_line' })
{
$self->_new_line() if ($self->{ 'content' } !~ /;$/s);
$self->{ 'content' } =~ s/\s+$/\n/s;
}
else
{
$self->_new_line();
}
# Attempt to eliminate redundant parenthesis in DML queries
while ($self->{ 'content' } =~ s/(\s+(?:WHERE|SELECT|FROM)\s+[^;]+)[\(]{2}([^\(\)]+)[\)]{2}([^;]+)/$1($2)$3/igs) {};
return;
}
sub _lower
{
my ( $self, $token ) = @_;
if ($DEBUG) {
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_ADD: line: $line => token=$token\n";
}
return lc($token);
}
=head2 _add_token
Add a token to the beautified string.
Code lifted from SQL::Beautify
=cut
sub _add_token
{
my ( $self, $token, $last_token ) = @_;
if ($DEBUG)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_ADD: line: $line => last=", ($last_token||''), ", token=$token\n";
}
if ( $self->{ 'wrap' } )
{
my $wrap;
if ( $self->_is_keyword( $token, $self->_next_token(), $last_token ) ) {
$wrap = $self->{ 'wrap' }->{ 'keywords' };
}
elsif ( $self->_is_constant( $token ) ) {
$wrap = $self->{ 'wrap' }->{ 'constants' };
}
if ( $wrap ) {
$token = $wrap->[ 0 ] . $token . $wrap->[ 1 ];
}
}
if ($self->{keep_newline} and $self->{ '_is_in_block' } >= 0 and $token =~ /^[\r\n]+$/s
and defined $last_token and $last_token eq ';'
)
{
$token =~ s/^[\r\n]+$/\n/s;
$self->{ 'content' } =~ s/\s+$/\n/s;
$self->{ 'content' } .= $token if ($self->{ 'content' } !~ /[\n]{2,}$/s);
return;
}
my $last_is_dot = defined( $last_token ) && $last_token eq '.';
my $sp = $self->_indent;
if ( !$self->_is_punctuation( $token ) and !$last_is_dot)
{
if ( (!defined($last_token) || $last_token ne '(') && $token ne ')' && $token !~ /^::/ )
{
if ($token ne ')'
&& defined($last_token)
&& $last_token !~ '::$'
&& $last_token ne '['
&& ($token ne '(' || !$self->_is_function( $last_token ) || $self->{ '_is_in_type' })
)
{
print STDERR "DEBUG_SPC: 1) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
if ( ($token !~ /PGFESCQ[12]/ or $last_token !~ /'$/)
and ($last_token !~ /PGFESCQ[12]/ or $token !~ /^'/)
)
{
if ($token !~ /^['"].*['"]$/ or $last_token ne ':')
{
if ($token =~ /AAKEYWCONST\d+AA\s+AAKEYWCONST\d+AA/) {
$token =~ s/(AAKEYWCONST\d+AA)/$sp$1/gs;
} else {
$self->{ 'content' } .= $sp if (!$self->{ 'no_space_function' } or $token ne '('
or (!$self->{ '_is_in_drop_function' }
and !$self->{ '_is_in_create_function' }
and !$self->{ '_is_in_trigger' }));
if ($self->{ 'no_space_function' } and $token eq '(' and !$self->_is_keyword( $last_token, $token, undef ))
{
$self->{ 'content' } =~ s/$sp$//s;
}
}
}
}
}
elsif (!defined($last_token) && $token)
{
print STDERR "DEBUG_SPC: 2) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
elsif ($token eq '(' and $self->{ '_is_in_create' } == 2 and $self->{ 'content' } !~ /$sp$/)
{
print STDERR "DEBUG_SPC: 2b) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
elsif (defined $last_token && $self->_is_comment($last_token))
{
print STDERR "DEBUG_SPC: 2c) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
}
elsif ( defined $last_token && $last_token eq '(' && $token ne ')'
&& $token !~ /^::/ && !$self->{'wrap_after'} && $self->{ '_is_in_with' } == 1)
{
print STDERR "DEBUG_SPC: 3) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
elsif ( $self->{ '_is_in_create' } == 2 && defined($last_token))
{
if ($last_token ne '::' and !$self->{ '_is_in_partition' }
and !$self->{ '_is_in_policy' }
and !$self->{ '_is_in_trigger' }
and !$self->{ '_is_in_aggregate' }
and ($last_token ne '(' || !$self->{ '_is_in_index' }))
{
print STDERR "DEBUG_SPC: 4) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp if ($last_token ne '(' or !$self->{ '_is_in_function' });
}
}
elsif (defined $last_token and (!$self->{ '_is_in_operator' } or !$self->{ '_is_in_alter' }))
{
if ($last_token eq '(' and ($self->{ '_is_in_type' } or ($self->{ '_is_in_operator' }
and !$self->_is_type($token, $last_token, $self->_next_token))))
{
print STDERR "DEBUG_SPC: 5a) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
elsif ($self->{ 'comma_break' } and $self->{ '_current_sql_stmt' } eq 'INSERT')
{
print STDERR "DEBUG_SPC: 5b) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
}
elsif ($token eq ')' and $self->{ '_is_in_block' } >= 0 && $self->{ '_is_in_create' })
{
print STDERR "DEBUG_SPC: 6) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
$self->{ 'content' } .= $sp;
}
else
{
print STDERR "DEBUG_SPC: 7) last=", ($last_token||''), ", token=$token\n" if ($DEBUG_SP);
}
if ($self->_is_comment($token))
{
my @lines = split(/\n/, $token);
for (my $i = 1; $i <= $#lines; $i++) {
if ($lines[$i] =~ /^\s*\*/) {
$lines[$i] =~ s/^\s*\*/$sp */;
} elsif ($lines[$i] =~ /^\s+[^\*]/) {
$lines[$i] =~ s/^\s+/$sp /;
}
}
$token = join("\n", @lines);
}
else
{
$token =~ s/\n/\n$sp/gs if ($self->{ '_is_in_function' } and $self->{ '_fct_code_delimiter' } eq "'");
}
}
my $next_token = $self->_next_token || '';
my @cast = ();
my @next_cast = ();
# Be sure that we not going to modify a constant
if ($self->{ '_is_in_create' } < 2 and $token !~ /^[E]*'.*'$/)
{
@cast = split(/::/, $token, -1);
$token = shift(@cast) if ($#cast >= 0);
@next_cast = split(/::/, $next_token);
$next_token = shift(@next_cast) if ($#next_cast >= 0);
}
# lowercase/uppercase keywords taking care of function with same name
if ($self->_is_keyword( $token, $next_token, $last_token ) and
(!$self->_is_type($next_token) or $self->{ '_is_in_create' } < 2 or $self->{ '_is_in_cast' }
or ($self->{ '_is_in_create' } == 2 and $token =~ /^(WITH|WITHOUT)$/i)
or $self->{ '_is_in_create_function' } or uc($token) eq 'AS')
and ($next_token ne '(' or (defined $last_token and $last_token =~ /^(CREATE|ALTER)$/i)
or !$self->_is_function( $token ))
)
{
# Be sure that we are not formating with time zone
if (uc($token) ne 'WITH' or not defined $next_token
or $next_token !~ /^(time|timestamp)$/i)
{
$token = lc( $token ) if ( $self->{ 'uc_keywords' } == 1 );
$token = uc( $token ) if ( $self->{ 'uc_keywords' } == 2 );
$token = ucfirst( lc( $token ) ) if ( $self->{ 'uc_keywords' } == 3 );
}
}
else
{
# lowercase/uppercase known functions or words followed by an open parenthesis
# if the token is not a keyword, an open parenthesis or a comment
my $fct = $self->_is_function( $token, $last_token, $next_token ) || '';
if (($fct and $next_token eq '(' and defined $last_token and uc($last_token) ne 'CREATE')
or (!$self->_is_keyword( $token, $next_token, $last_token ) and !$next_token eq '('
and $token ne '(' and !$self->_is_comment( $token )) )
{
$token =~ s/$fct/\L$fct\E/i if ( $self->{ 'uc_functions' } == 1 );
$token =~ s/$fct/\U$fct\E/i if ( $self->{ 'uc_functions' } == 2 );
$fct = ucfirst( lc( $fct ) );
$token =~ s/$fct/$fct/i if ( $self->{ 'uc_functions' } == 3 );
}
# case of (NEW|OLD).colname keyword that need to formatted too
if (($self->{ '_is_in_create_function' } or $self->{ '_fct_code_delimiter' } or $self->{ '_is_in_rule' })
and $token =~ /^(NEW|OLD)\./i)
{
$token =~ s/^(OLD|NEW)\./\L$1\E\./i if ( $self->{ 'uc_keywords' } == 1 );
$token =~ s/^(OLD|NEW)\./\U$1\E\./i if ( $self->{ 'uc_keywords' } == 2 );
$token =~ s/^OLD\./\UOld\E\./i if ( $self->{ 'uc_keywords' } == 3 );
$token =~ s/^NEW\./\UNew\E\./i if ( $self->{ 'uc_keywords' } == 3 );
}
}
my $tk_is_type = $self->_is_type($token, $last_token, $next_token);
if ($token =~ /^(AT|SET)$/i)
{
$self->{ '_not_a_type' } = 1;
}
elsif (!$tk_is_type)
{
$self->{ '_not_a_type' } = 0;
}
# Type are always lowercase
if (!$self->{ '_not_a_type' } and ($self->{ '_is_in_create' } or $self->{ '_is_in_declare' }
or $self->{ '_is_in_cast' } or $self->{ '_is_in_type' }))
{
if ($tk_is_type and defined $last_token
or ($token =~ /^(WITH|WITHOUT)$/i and $next_token =~ /^(time|timestamp)$/i)
)
{
if ($last_token =~ /^(AS|RETURNS|INOUT|IN|OUT)$/i or !$self->_is_keyword($last_token)
or $self->_is_type($last_token) or $self->_is_type($next_token))
{
$token = lc( $token ) if ( $self->{ 'uc_types' } == 1 );
$token = uc( $token ) if ( $self->{ 'uc_types' } == 2 );
$token = ucfirst( lc( $token ) ) if ( $self->{ 'uc_types' } == 3 );
}
}
}
# Add formatting for HTML output
if ( $self->{ 'colorize' } && $self->{ 'format' } eq 'html' ) {
$token = $self->highlight_code($token, $last_token, $next_token);
}
foreach my $c (@cast)
{
my @words = split(/(\s+)/, $c);
$c = '';
foreach my $w (@words)
{
if (!$self->_is_type($token))
{
$c .= $w;
}
else
{
$c .= lc($w) if ( $self->{ 'uc_types' } == 1 );
$c .= uc($w) if ( $self->{ 'uc_types' } == 2 );
$c .= ucfirst( lc( $w ) ) if ( $self->{ 'uc_types' } == 3 );
}
}
$token .= '::' . $c;
}
# Format cast in function code
my $reg = join('|', @{$self->{ 'types' }});
$reg = '(?:TIMESTAMP(\s*\(\s*\d+\s*\))? WITH TIME ZONE|TIMESTAMP(\s*\(\s*\d+\s*\))? WITHOUT TIME ZONE|CHARACTER VARYING|' . $reg . ')';
if ($token =~ /::/)
{
$token =~ s/::($reg)/'::' . lc($1)/igse if ( $self->{ 'uc_types' } == 1 );
$token =~ s/::($reg)/'::' . uc($1)/igse if ( $self->{ 'uc_types' } == 2 );
$token =~ s/::($reg)/'::' . ucfirst(lc($1))/igse if ( $self->{ 'uc_types' } == 3 );
}
# special case for MySQL
if ($token =~ /^(;|\$\$|\/\/)$/ and $self->{ 'content' } =~ /DELIMITER\s*$/)
{
$self->{ 'content' } .= ' ' if ($self->{ 'content' } !~ /DELIMITER\s$/);
}
$self->{ 'content' } .= $token;
# This can't be the beginning of a new line anymore.
$self->{ '_new_line' } = 0;
}
=head2 _over
Increase the indentation level.
Code lifted from SQL::Beautify
=cut
sub _over
{
my ( $self, $token, $last ) = @_;
if ($DEBUG) {
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_OVER: line: $line => last=$last, token=$token\n";
}
++$self->{ '_level' };
}
=head2 _back
Decrease the indentation level.
Code lifted from SQL::Beautify
=cut
sub _back
{
my ( $self, $token, $last ) = @_;
if ($DEBUG) {
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_BACK: line: $line => last=$last, token=$token\n";
}
--$self->{ '_level' } if ( $self->{ '_level' } > 0 );
}
=head2 _indent
Return a string of spaces according to the current indentation level and the
spaces setting for indenting.
Code lifted from SQL::Beautify
=cut
sub _indent
{
my ( $self ) = @_;
if ( $self->{ '_new_line' } )
{
return $self->{ 'space' } x ( $self->{ 'spaces' } * ( $self->{ '_level' } // 0 ) );
}
# When this is not for identation force using space
else
{
return ' ';
}
}
=head2 _new_line
Add a line break, but make sure there are no empty lines.
Code lifted from SQL::Beautify
=cut
sub _new_line
{
my ( $self, $token, $last ) = @_;
if ($DEBUG and defined $token) {
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_NL: line: $line => last=", ($last||''), ", token=$token\n";
}
$self->{ 'content' } .= $self->{ 'break' } unless ( $self->{ '_new_line' } );
$self->{ '_new_line' } = 1;
}
=head2 _next_token
Have a look at the token that's coming up next.
Code lifted from SQL::Beautify
=cut
sub _next_token
{
my ( $self ) = @_;
return @{ $self->{ '_tokens' } } ? $self->{ '_tokens' }->[ 0 ] : undef;
}
=head2 _token
Get the next token, removing it from the list of remaining tokens.
Code lifted from SQL::Beautify
=cut
sub _token
{
my ( $self ) = @_;
return shift @{ $self->{ '_tokens' } };
}
=head2 _is_keyword
Check if a token is a known SQL keyword.
Code lifted from SQL::Beautify
=cut
sub _is_keyword
{
my ( $self, $token, $next_token, $last_token ) = @_;
return 0 if (!$token);
# Remove cast if any
$token =~ s/::[^:]+$//;
# Fix some false positive
if (defined $next_token)
{
return 0 if (uc($token) eq 'LEVEL' and uc($next_token) ne 'SECURITY');
return 0 if (uc($token) eq 'EVENT' and uc($next_token) ne 'TRIGGER');
}
return 0 if ($token =~ /^(LOGIN|RULE)$/i and !$self->{ '_is_in_create' } and !$self->{ '_is_in_alter' } and !$self->{ '_is_in_drop' } and !$self->{ '_is_in_rule' });
return 0 if (uc($token) eq 'COMMENT' and (not defined $next_token or $next_token) !~ /^ON|IS$/i);
if (defined $last_token)
{
return 0 if (uc($token) eq 'KEY' and $last_token !~ /^(PRIMARY|FOREIGN|PARTITION|NO)$/i);
return 0 if ($token =~ /^(BTREE|HASH|GIST|SPGIST|GIN|BRIN)$/i and $last_token !~ /^(USING|BY)$/i);
return 0 if (uc($token) eq 'NOTICE' and uc($last_token) ne 'RAISE');
return 0 if ( ($self->{ '_is_in_type' } or $self->{ '_is_in_create' }) and $last_token =~ /^(OF|FROM)$/i);
return 0 if (uc($last_token) eq 'AS' and $token !~ /^(IDENTITY|SELECT|ENUM|TRANSACTION|UPDATE|DELETE|INSERT|MATERIALIZED|ON|VALUES|RESTRICTIVE|PERMISSIVE|UGLY|EXECUTE|STORAGE|OPERATOR|RANGE|NOT)$/i);
return 0 if ($token =~ /^(TYPE|SCHEMA)$/i and $last_token =~ /^(COLUMN|\(|,|\||\))/i);
return 0 if ($token =~ /^TYPE$/i and $last_token !~ /^(CREATE|DROP|ALTER|FOR)$/i
and !$self->{ '_is_in_alter' }
and !grep({ uc($_) eq uc( $next_token ) } @{ $self->{ 'types' } })
);
}
if ($DEBUG and defined $token and grep { $_ eq uc( $token ) } @{ $self->{ 'keywords' } }) {
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_KEYWORD: line: $line => last=", ($last_token||''), ", token=$token, next=", ($next_token||''), "\n";
}
return ~~ grep { $_ eq uc( $token ) } @{ $self->{ 'keywords' } };
}
=head2 _is_type
Check if a token is a known SQL type
=cut
sub _is_type
{
my ( $self, $token, $last_token, $next_token ) = @_;
return if (!defined $token);
return if (defined $next_token and $next_token =~ /^(SEARCH)$/i);
if ($DEBUG and defined $token)
{
my ($package, $filename, $line) = caller;
print STDERR "DEBUG_TYPE: line: $line => token=[$token], last=", ($last_token||''), ", next=", ($next_token||''), ", type=", (grep { uc($_) eq uc( $token ) } @{ $self->{ 'types' } }), "\n";
}
return 0 if ($token =~ /^(int4|int8|num|tstz|ts|date)range$/i
and (not defined $next_token or $next_token eq '('));
my @composite_types = (
'VARYING', 'PRECISION',
'WITH', 'WITHOUT', 'ZONE'
);
# Typically case of a data type used as an object name
if (defined $next_token)
{
if (grep { $_ eq uc( $token ) } @{ $self->{ 'types' } }
and grep { $_ eq uc( $next_token ) } @{ $self->{ 'types' } }
and !grep { $_ eq uc( $next_token ) } @composite_types)
{
return 0;
}
}
$token =~ s/\s*\(.*//; # remove any parameter to the type
return ~~ grep { $_ eq uc( $token ) } @{ $self->{ 'types' } };
}
sub _is_sql_keyword
{
my ( $self, $token ) = @_;
return ~~ grep { $_ eq uc( $token ) } @{ $self->{ 'sql_keywords' } };
}
=head2 _is_comment
Check if a token is a SQL or C style comment
=cut
sub _is_comment
{
my ( $self, $token ) = @_;
return 1 if ( $token =~ m#^\s*((?:--)[\ \t\S]*|/\*[\ \t\r\n\S]*?\*/)$#s );
return 0;
}
=head2 _is_function
Check if a token is a known SQL function.
Code lifted from SQL::Beautify and rewritten to check one long regexp instead of a lot of small ones.
=cut
sub _is_function
{
my ( $self, $token, $last_token, $next_token ) = @_;
return undef if (!$token);
if ( $token =~ $self->{ 'functions_re' } )
{
# Check the context of the function
if (defined $last_token and defined $next_token)
{
return undef if ($next_token ne '(');
return undef if ($self->{ '_is_in_create' } == 1);
}
return $1;
}
else
{
return undef;
}
}
=head2 add_keywords
Add new keywords to highlight.
Code lifted from SQL::Beautify
=cut
sub add_keywords
{
my $self = shift;
for my $keyword ( @_ ) {
push @{ $self->{ 'keywords' } }, ref( $keyword ) ? @{ $keyword } : $keyword;
}
}
=head2 _re_from_list
Create compiled regexp from prefix, suffix and and a list of values to match.
=cut
sub _re_from_list
{
my $prefix = shift;
my $suffix = shift;
my (@joined_list, $ret_re);
for my $list_item ( @_ ) {
push @joined_list, ref( $list_item ) ? @{ $list_item } : $list_item;
}
$ret_re = "$prefix(" . join('|', @joined_list) . ")$suffix";
return qr/$ret_re/i;
}
=head2 _refresh_functions_re
Refresh compiled regexp for functions.
=cut
sub _refresh_functions_re
{
my $self = shift;
$self->{ 'functions_re' } = _re_from_list( '\b[\.]*', '$', @{ $self->{ 'functions' } });
}
=head2 add_functions
Add new functions to highlight.
Code lifted from SQL::Beautify
=cut
sub add_functions
{
my $self = shift;
for my $function ( @_ ) {
push @{ $self->{ 'functions' } }, ref( $function ) ? @{ $function } : $function;
}
$self->_refresh_functions_re();
}
=head2 add_rule
Add new rules.
Code lifted from SQL::Beautify
=cut
sub add_rule
{
my ( $self, $format, $token ) = @_;
my $rules = $self->{ 'rules' } ||= {};
my $group = $rules->{ $format } ||= [];
push @{ $group }, ref( $token ) ? @{ $token } : $token;
}
=head2 _get_rule
Find custom rule for a token.
Code lifted from SQL::Beautify
=cut
sub _get_rule
{
my ( $self, $token ) = @_;
values %{ $self->{ 'rules' } }; # Reset iterator.
while ( my ( $rule, $list ) = each %{ $self->{ 'rules' } } ) {
return $rule if ( grep { uc( $token ) eq uc( $_ ) } @$list );
}
return;
}
=head2 _process_rule
Applies defined rule.
Code lifted from SQL::Beautify
=cut
sub _process_rule
{
my ( $self, $rule, $token ) = @_;
my $format = {
break => sub { $self->_new_line() },
over => sub { $self->_over() },
back => sub { $self->_back() },
token => sub { $self->_add_token( $token ) },
push => sub { push @{ $self->{ '_level_stack' } }, $self->{ '_level' } },
pop => sub { $self->{ '_level' } = $self->_pop_level($token, '') },
reset => sub { $self->{ '_level' } = 0; @{ $self->{ '_level_stack' } } = (); },
};
for ( split /-/, lc $rule ) {
&{ $format->{ $_ } } if ( $format->{ $_ } );
}
}
=head2 _is_constant
Check if a token is a constant.
Code lifted from SQL::Beautify
=cut
sub _is_constant
{
my ( $self, $token ) = @_;
return ( $token =~ /^\d+$/ or $token =~ /^(['"`]).*\1$/ );
}
=head2 _is_punctuation
Check if a token is punctuation.
Code lifted from SQL::Beautify
=cut
sub _is_punctuation
{
my ( $self, $token ) = @_;
if ($self->{ 'comma' } eq 'start' and $token eq ',') {
return 0;
}
return ( $token =~ /^[,;.\[\]]$/ );
}
=head2 _generate_anonymized_string
Simply generate a random string, thanks to Perlmonks.
Returns original in certain cases which don't require anonymization, like
timestamps, or intervals.
=cut
sub _generate_anonymized_string
{
my $self = shift;
my ( $before, $original, $after ) = @_;
# Prevent dates from being anonymized
return $original if $original =~ m{\A\d\d\d\d[/:-]\d\d[/:-]\d\d\z};
return $original if $original =~ m{\A\d\d[/:-]\d\d[/:-]\d\d\d\d\z};
# Prevent dates format like DD/MM/YYYY HH24:MI:SS from being anonymized
return $original if $original =~ m{
\A
(?:FM|FX|TM)?
(?:
HH | HH12 | HH24
| MI
| SS
| MS
| US
| SSSS
| AM | A\.M\. | am | a\.m\.
| PM | P\.M\. | pm | p\.m\.
| Y,YYY | YYYY | YYY | YY | Y
| IYYY | IYY | IY | I
| BC | B\.C\. | bc | b\.c\.
| AD | A\.D\. | ad | a\.d\.
| MONTH | Month | month | MON | Mon | mon | MM
| DAY | Day | day | DY | Dy | dy | DDD | DD | D
| W | WW | IW
| CC
| J
| Q
| RM | rm
| TZ | tz
| [\s/:-]
)+
(?:TH|th|SP)?
\z
};
# Prevent interval from being anonymized
return $original if ($before && ($before =~ /interval/i));
return $original if ($after && ($after =~ /^\)*::interval/i));
# Shortcut
my $cache = $self->{ '_anonymization_cache' };
# Range of characters to use in anonymized strings
my @chars = ( 'A' .. 'Z', 0 .. 9, 'a' .. 'z', '-', '_', '.' );
unless ( $cache->{ $original } ) {
# Actual anonymized version generation
$cache->{ $original } = join( '', map { $chars[ rand @chars ] } 1 .. 10 );
}
return $cache->{ $original };
}
=head2 anonymize
Anonymize litteral in SQL queries by replacing parameters with fake values
=cut
sub anonymize
{
my $self = shift;
my $query = $self->{ 'query' };
# just in case it has not been called in the main script
$query = $self->query() if (!$query);
return if ( !$query );
# Variable to hold anonymized versions, so we can provide the same value
# for the same input, within single query.
$self->{ '_anonymization_cache' } = {};
# Remove comments
$query =~ s/\/\*(.*?)\*\///gs;
# Clean query
$query =~ s/\\'//gs;
$query =~ s/('')+/\$EMPTYSTRING\$/gs;
# Anonymize each values
$query =~ s{
([^\s\']+[\s\(]*) # before
'([^']*)' # original
([\)]*::\w+)? # after
}{$1 . "'" . $self->_generate_anonymized_string($1, $2, $3) . "'" . ($3||'')}xeg;
$query =~ s/\$EMPTYSTRING\$/''/gs;
foreach my $k (keys %{ $self->{ 'keyword_constant' } }) {
$self->{ 'keyword_constant' }{$k} = "'" . $self->_generate_anonymized_string('', $self->{ 'keyword_constant' }{$k}, '') . "'";
}
$self->query( $query );
}
=head2 set_defaults
Sets defaults for newly created objects.
Currently defined defaults:
=over
=item spaces => 4
=item space => ' '
=item break => "\n"
=item uc_keywords => 2
=item uc_functions => 0
=item uc_types => 1
=item no_comments => 0
=item no_grouping => 0
=item placeholder => ''
=item multiline => 0
=item separator => ''
=item comma => 'end'
=item format => 'text'
=item colorize => 1
=item format_type => 0
=item wrap_limit => 0
=item wrap_after => 0
=item wrap_comment => 0
=item no_extra_line => 0
=item keep_newline => 0
=item no_space_function => 0
=back
=cut
sub set_defaults
{
my $self = shift;
$self->set_dicts();
# Set some defaults.
$self->{ 'query' } = '';
$self->{ 'spaces' } = 4;
$self->{ 'space' } = ' ';
$self->{ 'break' } = "\n";
$self->{ 'wrap' } = {};
$self->{ 'rules' } = {};
$self->{ 'uc_keywords' } = 2;
$self->{ 'uc_functions' } = 0;
$self->{ 'uc_types' } = 1;
$self->{ 'no_comments' } = 0;
$self->{ 'no_grouping' } = 0;
$self->{ 'placeholder' } = '';
$self->{ 'multiline' } = 0;
$self->{ 'keywords' } = $self->{ 'dict' }->{ 'pg_keywords' };
$self->{ 'types' } = $self->{ 'dict' }->{ 'pg_types' };
$self->{ 'functions' } = ();
push(@{ $self->{ 'functions' } }, keys %{ $self->{ 'dict' }->{ 'pg_functions' } });
$self->_refresh_functions_re();
$self->{ 'separator' } = '';
$self->{ 'comma' } = 'end';
$self->{ 'format' } = 'text';
$self->{ 'colorize' } = 1;
$self->{ 'format_type' } = 0;
$self->{ 'wrap_limit' } = 0;
$self->{ 'wrap_after' } = 0;
$self->{ 'wrap_comment' } = 0;
$self->{ 'no_extra_line' } = 0;
$self->{ 'keep_newline' } = 0;
$self->{ 'no_space_function' } = 0;
return;
}
=head2 format
Set output format - possible values: 'text' and 'html'
Default is text output. Returns 0 in case or wrong format and use default.
=cut
sub format
{
my $self = shift;
my $format = shift;
if ( grep(/^$format$/i, 'text', 'html') ) {
$self->{ 'format' } = lc($format);
return 1;
}
return 0;
}
=head2 set_dicts
Sets various dictionaries (lists of keywords, functions, symbols, and the like)
This was moved to separate function, so it can be put at the very end of module
so it will be easier to read the rest of the code.
=cut
sub set_dicts
{
my $self = shift;
# First load it all as "my" variables, to make it simpler to modify/map/grep/add
# Afterwards, when everything is ready, put it in $self->{'dict'}->{...}
my @pg_keywords = map { uc } qw(
ADD AFTER AGGREGATE ALL ALSO ALTER ALWAYS ANALYSE ANALYZE AND ANY ARRAY AS ASC ASYMMETRIC AUTHORIZATION ATTACH AUTO_INCREMENT
BACKWARD BEFORE BEGIN BERNOULLI BETWEEN BINARY BOTH BY CACHE CASCADE CASE CAST CHECK CHECKPOINT CLOSE CLUSTER
COLLATE COLLATION COLUMN COMMENT COMMIT COMMITTED CONCURRENTLY CONFLICT CONSTRAINT CONSTRAINT CONTINUE COPY
COST COSTS CREATE CROSS CUBE CURRENT CURRENT_DATE CURRENT_ROLE CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR
CYCLE DATABASE DEALLOCATE DECLARE DEFAULT DEFERRABLE DEFERRED DEFINER DELETE DELIMITER DESC DETACH DISABLE DISTINCT
DO DOMAIN DROP EACH ELSE ELSIF ENABLE ENCODING END EVENT EXCEPTION EXCEPT EXCLUDE EXCLUDING EXECUTE EXISTS EXPLAIN EXTENSION FALSE FETCH FILTER
FIRST FOLLOWING FOR FOREIGN FORWARD FREEZE FROM FULL FUNCTION GENERATED GRANT GROUP GROUPING HAVING HASHES HASH
IDENTITY IF ILIKE IMMUTABLE IN INCLUDING INCREMENT INDEX INHERITS INITIALLY INNER INOUT INSERT INSTEAD
INTERSECT INTO INVOKER IS ISNULL ISOLATION JOIN KEY LANGUAGE LAST LATERAL LC_COLLATE LC_CTYPE LEADING
LEAKPROOF LEFT LEFTARG LEVEL LIKE LIMIT LIST LISTEN LOAD LOCALTIME LOCALTIMESTAMP LOCK LOCKED LOGGED LOGIN
LOOP MAPPING MATCH MAXVALUE MERGES MINVALUE MODULUS MOVE NATURAL NEXT NOTHING NOTICE ORDINALITY
NO NOCREATEDB NOCREATEROLE NOSUPERUSER NOT NOTIFY NOTNULL NOWAIT NULL OFF OF OIDS ON ONLY OPEN OPERATOR OR ORDER
OUTER OVER OVERLAPS OWNER PARTITION PASSWORD PERFORM PLACING POLICY PRECEDING PREPARE PRIMARY PROCEDURE RANGE
REASSIGN RECURSIVE REFERENCES REINDEX REMAINDER RENAME REPEATABLE REPLACE REPLICA RESET RESTART RESTRICT RETURN RETURNING
RETURNS REVOKE RIGHT RIGHTARG ROLE ROLLBACK ROLLUP ROWS ROW RULE SAVEPOINT SCHEMA SCROLL SECURITY SELECT SEQUENCE
SEQUENCE SERIALIZABLE SERVER SESSION_USER SET SETOF SETS SHOW SIMILAR SKIP SNAPSHOT SOME STABLE START STRICT
SYMMETRIC SYSTEM TABLE TABLESAMPLE TABLESPACE TEMPLATE TEMPORARY THEN TO TRAILING TRANSACTION TRIGGER TRUE
TRUNCATE TYPE UNBOUNDED UNCOMMITTED UNION UNIQUE UNLISTEN UNLOCK UNLOGGED UPDATE USER USING VACUUM VALUES
VARIADIC VERBOSE VIEW VOLATILE WHEN WHERE WINDOW WITH WITHIN WORK XOR ZEROFILL
CALL GROUPS INCLUDE OTHERS PROCEDURES ROUTINE ROUTINES TIES READ_ONLY SHAREABLE READ_WRITE
BASETYPE SFUNC STYPE SFUNC1 STYPE1 SSPACE FINALFUNC FINALFUNC_EXTRA FINALFUNC_MODIFY COMBINEFUNC SERIALFUNC DESERIALFUNC
INITCOND MSFUNC MINVFUNC MSTYPE MSSPACE MFINALFUNC MFINALFUNC_EXTRA MFINALFUNC_MODIFY MINITCOND SORTOP
STORED REFRESH MATERIALIZED RAISE WITHOUT
);
my @pg_types = qw(
BIGINT BIGSERIAL BIT BOOLEAN BOOL BOX BYTEA CHARACTER CHAR CIDR CIRCLE DATE DOUBLE INET INTEGER INTERVAL
JSONB JSON LINE LSEG MACADDR8 MACADDR MONEY NUMERIC OID PG_LSN POINT POLYGON PRECISION REAL SMALLINT SMALLSERIAL
SERIAL TEXT TIMESTAMPTZ TIMESTAMP TSQUERY TSVECTOR TXID_SNAPSHOT UUID XML VARYING VARCHAR ZONE FLOAT4
FLOAT8 FLOAT NAME TID INT4RANGE INT8RANGE NUMRANGE TSRANGE TSTZRANGE DATERANGE INT2 INT4 INT8 INT TIME
REGCLASS REGCONFIG REGDICTIONARY REGNAMESPACE REGOPER REGOPERATOR REGPROC REGPROCEDURE REGROLE REGTYPE
);
my @sql_keywords = map { uc } qw(
ABORT ABSOLUTE ACCESS ACTION ADMIN ALSO ALWAYS ASSERTION ASSIGNMENT AT ATTRIBUTE BIGINT BOOLEAN
CALLED CASCADED CATALOG CHAIN CHANGE CHARACTER CHARACTERISTICS COLUMNS COMMENTS CONFIGURATION
CONNECTION CONSTRAINTS CONTENT CONVERSION CSV CURRENT DATA DATABASES DAY DEC DECIMAL DEFAULTS DELAYED
DELIMITERS DESCRIBE DICTIONARY DISABLE DISCARD DOCUMENT DOUBLE ENABLE ENCLOSED ENCRYPTED ENUM ESCAPE ESCAPED
EXCLUSIVE EXTERNAL FIELD FIELDS FLOAT FLUSH FOLLOWING FORCE FUNCTIONS GLOBAL GRANTED GREATEST HANDLER
HEADER HOLD HOUR IDENTIFIED IGNORE IMMEDIATE IMPLICIT INDEXES INFILE INHERIT INLINE INPUT INSENSITIVE
INT INTEGER KEYS KILL LABEL LARGE LEAST LEVEL LINES LOCAL LOW_PRIORITY MATCH MINUTE MODE MODIFY MONTH NAMES
NATIONAL NCHAR NONE NOTHING NULLIF NULLS OBJECT OFF OPERATOR OPTIMIZE OPTION OPTIONALLY OPTIONS OUT OUTFILE
OWNED PARSER PARTIAL PASSING PLANS PRECISION PREPARED PRESERVE PRIOR PRIVILEGES PROCEDURAL QUOTE READ
REAL RECHECK REF REGEXP RELATIVE RELEASE RLIKE ROW SEARCH SECOND SEQUENCES SESSION SHARE SIMPLE
SMALLINT SONAME STANDALONE STATEMENT STATISTICS STATUS STORAGE STRAIGHT_JOIN SYSID TABLES TEMP TERMINATED
TREAT TRUSTED TYPES UNENCRYPTED UNKNOWN UNSIGNED UNTIL USE VALID VALIDATE VALIDATOR VALUE VARIABLES VARYING
WHITESPACE WORK WRAPPER WRITE XMLATTRIBUTES YEAR YES ZONE
);
my @redshift_keywords = map { uc } qw(
AES128 AES256 ALLOWOVERWRITE BACKUP BLANKSASNULL BYTEDICT BZIP2 CREDENTIALS CURRENT_USER_ID DEFLATE DEFRAG
DELTA DELTA32K DISABLE DISTKEY EMPTYASNULL ENABLE ENCODE ENCRYPT ENCRYPTION ESCAPE EXPLICIT GLOBALDICT256
GLOBALDICT64K GZIP INTERLEAVED LUN LUNS LZO LZOP MINUS MOSTLY13 MOSTLY32 MOSTLY8 NEW OFFLINE OFFSET OLD OID
PARALLEL PERCENT PERMISSIONS RAW READRATIO RECOVER REJECTLOG RESORT RESPECT RESTORE SORTKEY SYSDATE TAG TDES
TEXT255 TEXT32K TIMESTAMP TOP TRUNCATECOLUMNS UNLOAD WALLET ADDQUOTES
);
for my $k ( @pg_keywords ) {
next if grep { $k eq $_ } @sql_keywords;
push @sql_keywords, $k;
}
my @pg_functions = map { lc } qw(
ascii age bit_length btrim cardinality cast char_length character_length coalesce
brin_summarize_range brin_summarize_new_values
convert chr current_date current_time current_timestamp count decode date_part date_trunc
encode extract get_byte get_bit initcap isfinite interval justify_hours justify_days
lower length lpad ltrim localtime localtimestamp md5 now octet_length overlay position pg_client_encoding
quote_ident quote_literal repeat replace rpad rtrim substring split_part strpos substr set_byte set_bit
trim to_ascii to_hex translate to_char to_date to_timestamp to_number timeofday upper
abbrev abs abstime abstimeeq abstimege abstimegt abstimein abstimele
abstimelt abstimene abstimeout abstimerecv abstimesend aclcontains acldefault
aclexplode aclinsert aclitemeq aclitemin aclitemout aclremove acos
any_in any_out anyarray_in anyarray_out anyarray_recv anyarray_send anyelement_in
anyelement_out anyenum_in anyenum_out anynonarray_in anynonarray_out anyrange_in anyrange_out
anytextcat area areajoinsel areasel armor array_agg array_agg_finalfn
array_agg_transfn array_append array_cat array_dims array_eq array_fill array_ge array_positions
array_gt array_in array_larger array_le array_length array_lower array_lt array_position
array_ndims array_ne array_out array_prepend array_recv array_remove array_replace array_send array_smaller
array_to_json array_to_string array_typanalyze array_upper arraycontained arraycontains arraycontjoinsel
arraycontsel arrayoverlap ascii_to_mic ascii_to_utf8 asin atan atan2
avg big5_to_euc_tw big5_to_mic big5_to_utf8 bit bit_and bit_in
bit_or bit_out bit_recv bit_send bitand bitcat bitcmp
biteq bitge bitgt bitle bitlt bitne bitnot
bitor bitshiftleft bitshiftright bittypmodin bittypmodout bitxor bool
bool_and bool_or booland_statefunc boolean booleq boolge boolgt boolin
boolle boollt boolne boolor_statefunc boolout boolrecv boolsend
box box_above box_above_eq box_add box_below box_below_eq box_center
box_contain box_contain_pt box_contained box_distance box_div box_eq box_ge
box_gt box_in box_intersect box_le box_left box_lt box_mul
box_out box_overabove box_overbelow box_overlap box_overleft box_overright box_recv
box_right box_same box_send box_sub bpchar bpchar_larger bpchar_pattern_ge
bpchar_pattern_gt bpchar_pattern_le bpchar_pattern_lt bpchar_smaller bpcharcmp bpchareq bpcharge
bpchargt bpchariclike bpcharicnlike bpcharicregexeq bpcharicregexne bpcharin bpcharle
bpcharlike bpcharlt bpcharne bpcharnlike bpcharout bpcharrecv bpcharregexeq
bpcharregexne bpcharsend bpchartypmodin bpchartypmodout broadcast btabstimecmp btarraycmp
btbeginscan btboolcmp btbpchar_pattern_cmp btbuild btbuildempty btbulkdelete btcanreturn
btcharcmp btcostestimate btendscan btfloat48cmp btfloat4cmp btfloat4sortsupport btfloat84cmp
btfloat8cmp btfloat8sortsupport btgetbitmap btgettuple btinsert btint24cmp btint28cmp
btint2cmp btint2sortsupport btint42cmp btint48cmp btint4cmp btint4sortsupport btint82cmp
btint84cmp btint8cmp btint8sortsupport btmarkpos btnamecmp btnamesortsupport btoidcmp
btoidsortsupport btoidvectorcmp btoptions btrecordcmp btreltimecmp btrescan btrestrpos
bttext_pattern_cmp bttextcmp bttidcmp bttintervalcmp btvacuumcleanup bytea_string_agg_finalfn
bytea_string_agg_transfn byteacat byteacmp byteaeq byteage byteagt byteain byteale
bytealike bytealt byteane byteanlike byteaout bytearecv byteasend
cash_cmp cash_div_cash cash_div_flt4 cash_div_flt8 cash_div_int2 cash_div_int4 cash_eq
cash_ge cash_gt cash_in cash_le cash_lt cash_mi cash_mul_flt4
cash_mul_flt8 cash_mul_int2 cash_mul_int4 cash_ne cash_out cash_pl cash_recv
cash_send cash_words cashlarger cashsmaller cbrt ceil ceiling
center char chareq charge chargt charin charle
charlt charne charout charrecv charsend cideq cidin
cidout cidr cidr_in cidr_out cidr_recv cidr_send cidrecv
cidsend circle circle_above circle_add_pt circle_below circle_center circle_contain
circle_contain_pt circle_contained circle_distance circle_div_pt circle_eq circle_ge circle_gt
circle_in circle_le circle_left circle_lt circle_mul_pt circle_ne circle_out
circle_overabove circle_overbelow circle_overlap circle_overleft circle_overright circle_recv circle_right
circle_same circle_send circle_sub_pt clock_timestamp close_lb close_ls close_lseg
close_pb close_pl close_ps close_sb close_sl col_description concat
concat_ws contjoinsel contsel convert_from convert_to corr cos
cot covar_pop covar_samp crypt cstring_in cstring_out cstring_recv
cstring_send cume_dist current_database current_query current_schema current_schemas current_setting
current_user currtid currtid2 currval date date_cmp date_cmp_timestamp date_cmp_timestamptz date_eq
date_eq_timestamp date_eq_timestamptz date_ge date_ge_timestamp date_ge_timestamptz date_gt date_gt_timestamp
date_gt_timestamptz date_in date_larger date_le date_le_timestamp date_le_timestamptz date_lt
date_lt_timestamp date_lt_timestamptz date_mi date_mi_interval date_mii date_ne date_ne_timestamp
date_ne_timestamptz date_out date_pl_interval date_pli date_recv date_send date_smaller
date_sortsupport daterange daterange_canonical daterange_subdiff datetime_pl datetimetz_pl
dblink_connect_u dblink_connect dblink_disconnect dblink_exec dblink_open dblink_fetch dblink_close
dblink_get_connections dblink_error_message dblink_send_query dblink_is_busy dblink_get_notify
dblink_get_result dblink_cancel_query dblink_get_pkey dblink_build_sql_insert dblink_build_sql_delete
dblink_build_sql_update dblink dcbrt dearmor decrypt decrypt_iv degrees dense_rank dexp diagonal
decimal diameter digest dispell_init dispell_lexize dist_cpoly dist_lb dist_pb
dist_pc dist_pl dist_ppath dist_ps dist_sb dist_sl div
dlog1 dlog10 domain_in domain_recv dpow dround dsimple_init
dsimple_lexize dsnowball_init dsnowball_lexize dsqrt dsynonym_init dsynonym_lexize dtrunc
elem_contained_by_range encrypt encrypt_iv enum_cmp enum_eq enum_first enum_ge
enum_gt enum_in enum_larger enum_last enum_le enum_lt enum_ne
enum_out enum_range enum_recv enum_send enum_smaller eqjoinsel eqsel
euc_cn_to_mic euc_cn_to_utf8 euc_jis_2004_to_shift_jis_2004 euc_jis_2004_to_utf8
euc_jp_to_mic euc_jp_to_sjis euc_jp_to_utf8
euc_kr_to_mic euc_kr_to_utf8 euc_tw_to_big5 euc_tw_to_mic euc_tw_to_utf8 every exp
factorial family fdw_handler_in fdw_handler_out first_value float4 float48div
float48eq float48ge float48gt float48le float48lt float48mi float48mul
float48ne float48pl float4_accum float4abs float4div float4eq float4ge
float4gt float4in float4larger float4le float4lt float4mi float4mul
float4ne float4out float4pl float4recv float4send float4smaller float4um
float4up float8 float84div float84eq float84ge float84gt float84le
float84lt float84mi float84mul float84ne float84pl float8_accum float8_avg
float8_combine float8_regr_combine float8_corr float8_covar_pop float8_covar_samp
float8_regr_accum float8_regr_avgx float8_regr_avgy float8_regr_intercept
float8_regr_r2 float8_regr_slope float8_regr_sxx float8_regr_sxy float8_regr_syy
float8_stddev_pop float8_stddev_samp
float8_var_pop float8_var_samp float8abs float8div float8eq float8ge float8gt
float8in float8larger float8le float8lt float8mi float8mul float8ne
float8out float8pl float8recv float8send float8smaller float8um float8up
floor flt4_mul_cash flt8_mul_cash fmgr_c_validator fmgr_internal_validator fmgr_sql_validator format
format_type gb18030_to_utf8 gbk_to_utf8 gen_random_bytes gen_salt generate_series generate_subscripts
geometry get_current_ts_config getdatabaseencoding getpgusername gin_cmp_prefix gin_cmp_tslexeme
gin_extract_tsquery gin_extract_tsvector gin_tsquery_consistent ginarrayconsistent ginarrayextract
ginbeginscan ginbuild ginbuildempty ginbulkdelete gincostestimate ginendscan gingetbitmap gininsert
ginmarkpos ginoptions ginqueryarrayextract ginrescan ginrestrpos ginvacuumcleanup gist_box_compress
gist_box_consistent gist_box_decompress gist_box_penalty gist_box_picksplit gist_box_same gist_box_union
gist_circle_compress gist_circle_consistent gist_point_compress gist_point_consistent gist_point_distance
gist_poly_compress gist_poly_consistent gistbeginscan gistbuild gistbuildempty gistbulkdelete
gistcostestimate gistendscan gistgetbitmap gistgettuple gistinsert gistmarkpos gistoptions gistrescan
gistrestrpos gistvacuumcleanup gtsquery_compress gtsquery_consistent gtsquery_decompress gtsquery_penalty
gtsquery_picksplit gtsquery_same gtsquery_union gtsvector_compress gtsvector_consistent gtsvector_decompress
gtsvector_penalty gtsvector_picksplit gtsvector_same gtsvector_union gtsvectorin gtsvectorout
has_any_column_privilege has_column_privilege has_database_privilege has_foreign_data_wrapper_privilege
has_function_privilege has_language_privilege has_schema_privilege has_sequence_privilege has_server_privilege
has_table_privilege has_tablespace_privilege has_type_privilege hash_aclitem hash_array hash_numeric hash_range
hashbeginscan hashbpchar hashbuild hashbuildempty hashbulkdelete hashchar hashcostestimate hash_aclitem_extended
hashendscan hashenum hashfloat4 hashfloat8 hashgetbitmap hashgettuple hashinet hashinsert hashint2
hashint2extended hashint2vector hashint4 hashint4extended hashint8 hashint8extended hashmacaddr
hashfloat4extended hashfloat8extended hashcharextended hashoidextended hashnameextended hashmarkpos
hashoidvectorextended hashmacaddrextended hashinetextended hashname hashoid hashoidvector hashoptions
hash_numeric_extended hashmacaddr8extended hash_array_extended hashrescan hashrestrpos hashtext
hashbpcharextended time_hash_extended timetz_hash_extended interval_hash_extended timestamp_hash_extended
uuid_hash_extended pg_lsn_hash_extended hashenumextended jsonb_hash_extended hash_range_extended
hashtextextended hashvacuumcleanup hashvarlena height hmac host hostmask iclikejoinsel
iclikesel icnlikejoinsel icnlikesel icregexeqjoinsel icregexeqsel icregexnejoinsel icregexnesel
inet_client_addr inet_client_port inet_in inet_out inet_recv inet_send inet_server_addr
inet_server_port inetand inetmi inetmi_int8 inetnot inetor inetpl
int int2 int24div int24eq int24ge int24gt int24le int24lt integer
int24mi int24mul int24ne int24pl int28div int28eq int28ge
int28gt int28le int28lt int28mi int28mul int28ne int28pl
int2_accum int2_avg_accum int2_mul_cash int2_sum int2abs int2and int2div
int2eq int2ge int2gt int2in int2larger int2le int2lt
int2mi int2mod int2mul int2ne int2not int2or int2out
int2pl int2recv int2send int2shl int2shr int2smaller int2um
int2up int2vectoreq int2vectorin int2vectorout int2vectorrecv int2vectorsend int2xor
int4 int42div int42eq int42ge int42gt int42le int42lt
int42mi int42mul int42ne int42pl int48div int48eq int48ge
int48gt int48le int48lt int48mi int48mul int48ne int48pl
int4_accum int4_avg_accum int4_mul_cash int4_sum int4abs int4and int4div
int4eq int4ge int4gt int4in int4inc int4larger int4le
int4lt int4mi int4mod int4mul int4ne int4not int4or
int4out int4pl int4range int4range_canonical int4range_subdiff int4recv int4send
int4shl int4shr int4smaller int4um int4up int4xor int8
int82div int82eq int82ge int82gt int82le int82lt int82mi
int82mul int82ne int82pl int84div int84eq int84ge int84gt
int84le int84lt int84mi int84mul int84ne int84pl int8_accum
int8_avg int8_avg_accum int8_sum int8abs int8and int8div int8eq
int8ge int8gt int8in int8inc int8inc_any int8inc_float8_float8 int8larger
int8le int8lt int8mi int8mod int8mul int8ne int8not
int8or int8out int8pl int8pl_inet int8range int8range_canonical int8range_subdiff
int8recv int8send int8shl int8shr int8smaller int8um int8up
int8xor integer_pl_date inter_lb inter_sb inter_sl internal_in internal_out
interval_accum interval_avg interval_cmp interval_div interval_eq interval_ge interval_gt
interval_hash interval_in interval_larger interval_le interval_lt interval_mi interval_mul
interval_ne interval_out interval_pl interval_pl_date interval_pl_time interval_pl_timestamp interval_pl_timestamptz
interval_pl_timetz interval_recv interval_send interval_smaller interval_transform interval_um intervaltypmodin
intervaltypmodout intinterval isclosed isempty ishorizontal iso8859_1_to_utf8 iso8859_to_utf8
iso_to_koi8r iso_to_mic iso_to_win1251 iso_to_win866 isopen isparallel isperp
isvertical johab_to_utf8 json_agg jsonb_agg json_array_elements jsonb_array_elements
json_array_elements_text jsonb_array_elements_text json_to_tsvector jsonb_insert
json_array_length jsonb_array_length json_build_array json_build_object json_each jsonb_each json_each_text
jsonb_each_text json_extract_path jsonb_extract_path json_extract_path_text jsonb_extract_path_text json_in
json_object json_object_agg jsonb_object_agg json_object_keys jsonb_object_keys json_out json_populate_record
jsonb_populate_record json_populate_recordset jsonb_pretty jsonb_populate_recordset json_recv json_send
jsonb_set json_typeof jsonb_typeof json_to_record jsonb_to_record json_to_recordset jsonb_to_recordset
justify_interval koi8r_to_iso koi8r_to_mic koi8r_to_utf8 koi8r_to_win1251 koi8r_to_win866 koi8u_to_utf8
jsonb_path_query jsonb_build_object jsonb_object jsonb_build_array jsonb_path_match jsonb_path_exists
lag language_handler_in language_handler_out last_value lastval latin1_to_mic latin2_to_mic latin2_to_win1250
latin3_to_mic latin4_to_mic lead like_escape likejoinsel jsonb_path_query_first jsonb_path_query_array
likesel line line_distance line_eq line_horizontal line_in line_interpt
line_intersect line_out line_parallel line_perp line_recv line_send line_vertical
ln lo_close lo_creat lo_create lo_export lo_import lo_lseek lo_compat lo_from_bytea lo_get lo_import_with_oid
lo_open lo_tell lo_truncate lo_unlink log lo_read lower_inc lo_seek64 lo_put lo_tell64 lo_truncate64 lo_write
lower_inf lowrite lseg lseg_center lseg_distance lseg_eq lseg_ge
lseg_gt lseg_horizontal lseg_in lseg_interpt lseg_intersect lseg_le lseg_length
lseg_lt lseg_ne lseg_out lseg_parallel lseg_perp lseg_recv lseg_send
lseg_vertical macaddr_and macaddr_cmp macaddr_eq macaddr_ge macaddr_gt macaddr_in
macaddr_le macaddr_lt macaddr_ne macaddr_not macaddr_or macaddr_out macaddr_recv
macaddr_send makeaclitem make_interval make_tsrange masklen max mic_to_ascii mic_to_big5 mic_to_euc_cn
mic_to_euc_jp mic_to_euc_kr mic_to_euc_tw mic_to_iso mic_to_koi8r mic_to_latin1 mic_to_latin2
mic_to_latin3 mic_to_latin4 mic_to_sjis mic_to_win1250 mic_to_win1251 mic_to_win866 min
mktinterval mode mod money mul_d_interval name nameeq namege make_timestamptz make_timestamp
namegt nameiclike nameicnlike nameicregexeq nameicregexne namein namele make_time make_date
namelike namelt namene namenlike nameout namerecv nameregexeq make_interval
nameregexne namesend neqjoinsel neqsel netmask network network_cmp
network_eq network_ge network_gt network_le network_lt network_ne network_sub
network_subeq network_sup network_supeq nextval nlikejoinsel nlikesel notlike
npoints nth_value ntile numeric numeric_abs numeric_accum numeric_add
numeric_avg numeric_avg_accum numeric_cmp numeric_div numeric_div_trunc numeric_eq numeric_exp
numeric_fac numeric_ge numeric_gt numeric_in numeric_inc numeric_larger numeric_le
numeric_ln numeric_log numeric_lt numeric_mod numeric_mul numeric_ne numeric_out
numeric_power numeric_recv numeric_send numeric_smaller numeric_sqrt numeric_stddev_pop numeric_stddev_samp
numeric_sub numeric_transform numeric_uminus numeric_uplus numeric_var_pop numeric_var_samp numerictypmodin
numerictypmodout numnode numrange numrange_subdiff obj_description oid oideq
oidge oidgt oidin oidlarger oidle oidlt oidne
oidout oidrecv oidsend oidsmaller oidvectoreq oidvectorge oidvectorgt
oidvectorin oidvectorle oidvectorlt oidvectorne oidvectorout oidvectorrecv oidvectorsend
oidvectortypes on_pb on_pl on_ppath on_ps on_sb on_sl
opaque_in opaque_out overlaps path path_add path_add_pt path_center
path_contain_pt path_distance path_div_pt path_in path_inter path_length path_mul_pt
path_n_eq path_n_ge path_n_gt path_n_le path_n_lt path_npoints path_out parse_ident
path_recv path_send path_sub_pt pclose percent_rank percentile_cont percentile_disc
pg_advisory_lock pg_advisory_lock_shared pg_advisory_unlock pg_advisory_unlock_all pg_advisory_unlock_shared
pg_advisory_xact_lock pg_advisory_xact_lock_shared pg_available_extension_versions pg_available_extensions
pg_backend_pid pg_cancel_backend pg_char_to_encoding pg_collation_for pg_collation_is_visible pg_column_size
pg_conf_load_time pg_conversion_is_visible pg_create_restore_point pg_current_xlog_insert_location
pg_current_xlog_location pg_cursor pg_database_size pg_describe_object pg_encoding_max_length
pg_encoding_to_char pg_export_snapshot pg_extension_config_dump pg_extension_update_paths pg_function_is_visible
pg_get_constraintdef pg_get_expr pg_get_function_arguments pg_filenode_relation pg_indexam_has_property
pg_get_function_identity_arguments pg_get_function_result pg_get_functiondef pg_get_indexdef pg_get_keywords
pg_get_ruledef pg_get_serial_sequence pg_get_triggerdef pg_get_userbyid pg_get_viewdef pg_has_role
pg_indexes_size pg_is_in_recovery pg_is_other_temp_schema pg_is_xlog_replay_paused pg_last_xact_replay_timestamp
pg_last_xlog_receive_location pg_last_xlog_replay_location pg_listening_channels pg_lock_status pg_ls_dir
pg_my_temp_schema pg_node_tree_in pg_node_tree_out pg_node_tree_recv pg_node_tree_send pg_notify
pg_opclass_is_visible pg_operator_is_visible pg_opfamily_is_visible pg_options_to_table pg_index_has_property
pg_postmaster_start_time pg_prepared_statement pg_prepared_xact pg_read_binary_file pg_read_file
pg_relation_filenode pg_relation_filepath pg_relation_size pg_reload_conf pg_rotate_logfile
pg_sequence_parameters pg_show_all_settings pg_size_pretty pg_sleep pg_start_backup pg_index_column_has_property
pg_stat_clear_snapshot pg_stat_file pg_stat_get_activity pg_stat_get_analyze_count pg_stat_get_autoanalyze_count
pg_stat_get_autovacuum_count pg_get_object_address pg_identify_object_as_address pg_stat_get_backend_activity
pg_stat_get_backend_activity_start pg_stat_get_backend_client_addr pg_stat_get_backend_client_port
pg_stat_get_backend_dbid pg_stat_get_backend_idset pg_stat_get_backend_pid pg_stat_get_backend_start
pg_stat_get_backend_userid pg_stat_get_backend_waiting pg_stat_get_backend_xact_start
pg_stat_get_bgwriter_buf_written_checkpoints pg_stat_get_bgwriter_buf_written_clean
pg_stat_get_bgwriter_maxwritten_clean pg_stat_get_bgwriter_requested_checkpoints
pg_stat_get_bgwriter_stat_reset_time pg_stat_get_bgwriter_timed_checkpoints pg_stat_get_blocks_fetched
pg_stat_get_blocks_hit pg_stat_get_buf_alloc pg_stat_get_buf_fsync_backend pg_stat_get_buf_written_backend
pg_stat_get_checkpoint_sync_time pg_stat_get_checkpoint_write_time pg_stat_get_db_blk_read_time
pg_stat_get_db_blk_write_time pg_stat_get_db_blocks_fetched pg_stat_get_db_blocks_hit
pg_stat_get_db_conflict_all pg_stat_get_db_conflict_bufferpin pg_stat_get_db_conflict_lock
pg_stat_get_db_conflict_snapshot pg_stat_get_db_conflict_startup_deadlock pg_stat_get_db_conflict_tablespace
pg_stat_get_db_deadlocks pg_stat_get_db_numbackends pg_stat_get_db_stat_reset_time pg_stat_get_db_temp_bytes
pg_stat_get_db_temp_files pg_stat_get_db_tuples_deleted pg_stat_get_db_tuples_fetched
pg_stat_get_db_tuples_inserted pg_stat_get_db_tuples_returned pg_stat_get_db_tuples_updated
pg_stat_get_db_xact_commit pg_stat_get_db_xact_rollback pg_stat_get_dead_tuples pg_stat_get_function_calls
pg_stat_get_function_self_time pg_stat_get_function_total_time pg_stat_get_last_analyze_time
pg_stat_get_last_autoanalyze_time pg_stat_get_last_autovacuum_time pg_stat_get_last_vacuum_time
pg_stat_get_live_tuples pg_stat_get_numscans pg_stat_get_tuples_deleted pg_stat_get_tuples_fetched
pg_stat_get_tuples_hot_updated pg_stat_get_tuples_inserted pg_stat_get_tuples_returned
pg_stat_get_tuples_updated pg_stat_get_vacuum_count pg_stat_get_wal_senders pg_stat_get_xact_blocks_fetched
pg_stat_get_xact_blocks_hit pg_stat_get_xact_function_calls pg_stat_get_xact_function_self_time
pg_stat_get_xact_function_total_time pg_stat_get_xact_numscans pg_stat_get_xact_tuples_deleted
pg_stat_get_xact_tuples_fetched pg_stat_get_xact_tuples_hot_updated pg_stat_get_xact_tuples_inserted
pg_stat_get_xact_tuples_returned pg_stat_get_xact_tuples_updated pg_stat_reset pg_stat_reset_shared
pg_stat_reset_single_function_counters pg_stat_reset_single_table_counters pg_stop_backup pg_switch_xlog
pg_table_is_visible pg_table_size pg_tablespace_databases pg_tablespace_location pg_tablespace_size
pg_terminate_backend pg_timezone_abbrevs pg_timezone_names pg_total_relation_size pg_trigger_depth
pg_try_advisory_lock pg_try_advisory_lock_shared pg_try_advisory_xact_lock pg_try_advisory_xact_lock_shared
pg_ts_config_is_visible pg_ts_dict_is_visible pg_ts_parser_is_visible pg_ts_template_is_visible
pg_type_is_visible pg_typeof pg_xact_commit_timestamp pg_last_committed_xact pg_xlog_location_diff
pg_xlog_replay_pause pg_xlog_replay_resume pg_xlogfile_name pg_xlogfile_name_offset pgp_key_id pgp_pub_decrypt
pgp_pub_decrypt_bytea pgp_pub_encrypt pgp_pub_encrypt_bytea pgp_sym_decrypt pgp_sym_decrypt_bytea
pgp_sym_encrypt pgp_sym_encrypt_bytea pi plainto_tsquery plpgsql_call_handler plpgsql_inline_handler
plpgsql_validator point point_above point_add point_below point_distance point_div point_eq
point_horiz point_in point_left point_mul point_ne point_out point_recv
point_right point_send point_sub point_vert poly_above poly_below poly_center
poly_contain poly_contain_pt poly_contained poly_distance poly_in poly_left poly_npoints
poly_out poly_overabove poly_overbelow poly_overlap poly_overleft poly_overright poly_recv
poly_right poly_same poly_send polygon popen positionjoinsel positionsel
postgresql_fdw_validator pow power prsd_end prsd_headline prsd_lextype prsd_nexttoken
prsd_start pt_contained_circle pt_contained_poly querytree
quote_nullable radians radius random range_adjacent range_after range_before
range_cmp range_contained_by range_contains range_contains_elem range_eq range_ge range_gist_compress
range_gist_consistent range_gist_decompress range_gist_penalty range_gist_picksplit range_gist_same
range_gist_union range_gt range_merge
range_in range_intersect range_le range_lt range_minus range_ne range_out
range_overlaps range_overleft range_overright range_recv range_send range_typanalyze range_union
rank record_eq record_ge record_gt record_in record_le record_lt regexp_match
record_ne record_out record_recv record_send regclass regclassin regclassout
regclassrecv regclasssend regconfigin regconfigout regconfigrecv regconfigsend regdictionaryin
regdictionaryout regdictionaryrecv regdictionarysend regexeqjoinsel regexeqsel regexnejoinsel regexnesel
regexp_matches regexp_replace regexp_split_to_array regexp_split_to_table regoperatorin regoperatorout regoperatorrecv
regoperatorsend regoperin regoperout regoperrecv regopersend regprocedurein regprocedureout
regprocedurerecv regproceduresend regprocin regprocout regprocrecv regprocsend regr_avgx
regr_avgy regr_count regr_intercept regr_r2 regr_slope regr_sxx regr_sxy
regr_syy regtypein regtypeout regtyperecv regtypesend reltime reltimeeq
reltimege reltimegt reltimein reltimele reltimelt reltimene reltimeout
reltimerecv reltimesend reverse round row_number row_to_json
scalargtjoinsel scalargtsel scalarltjoinsel scalarltsel
session_user set_config set_masklen setseed setval setweight shell_in
shell_out shift_jis_2004_to_euc_jis_2004 shift_jis_2004_to_utf8 shobj_description sign similar_escape sin
sjis_to_euc_jp sjis_to_mic sjis_to_utf8 slope smgreq smgrin smgrne
smgrout spg_kd_choose spg_kd_config spg_kd_inner_consistent spg_kd_picksplit spg_quad_choose spg_quad_config
spg_quad_inner_consistent spg_quad_leaf_consistent spg_quad_picksplit spg_text_choose spg_text_config spg_text_inner_consistent spg_text_leaf_consistent
spg_text_picksplit spgbeginscan spgbuild spgbuildempty spgbulkdelete spgcanreturn spgcostestimate
spgendscan spggetbitmap spggettuple spginsert spgmarkpos spgoptions spgrescan
spgrestrpos spgvacuumcleanup sqrt statement_timestamp stddev stddev_pop stddev_samp
string_agg string_agg_finalfn string_agg_transfn string_to_array strip sum
tan text text_ge text_gt text_larger
text_le text_lt text_pattern_ge text_pattern_gt text_pattern_le text_pattern_lt text_smaller
textanycat textcat texteq texticlike texticnlike texticregexeq texticregexne
textin textlen textlike textne textnlike textout textrecv
textregexeq textregexne textsend thesaurus_init thesaurus_lexize tideq tidge
tidgt tidin tidlarger tidle tidlt tidne tidout
tidrecv tidsend tidsmaller time time_cmp time_eq time_ge
time_gt time_hash time_in time_larger time_le time_lt time_mi_interval
time_mi_time time_ne time_out time_pl_interval time_recv time_send time_smaller
time_transform timedate_pl timemi timenow timepl timestamp timestamp_cmp
timestamp_cmp_date timestamp_cmp_timestamptz timestamp_eq timestamp_eq_date timestamp_eq_timestamptz timestamp_ge timestamp_ge_date
timestamp_ge_timestamptz timestamp_gt timestamp_gt_date timestamp_gt_timestamptz timestamp_hash timestamp_in timestamp_larger
timestamp_le timestamp_le_date timestamp_le_timestamptz timestamp_lt timestamp_lt_date timestamp_lt_timestamptz timestamp_mi
timestamp_mi_interval timestamp_ne timestamp_ne_date timestamp_ne_timestamptz timestamp_out timestamp_pl_interval timestamp_recv
timestamp_send timestamp_smaller timestamp_sortsupport timestamp_transform timestamptypmodin timestamptypmodout timestamptz
timestamptz_cmp timestamptz_cmp_date timestamptz_cmp_timestamp timestamptz_eq timestamptz_eq_date timestamptz_eq_timestamp timestamptz_ge
timestamptz_ge_date timestamptz_ge_timestamp timestamptz_gt timestamptz_gt_date timestamptz_gt_timestamp timestamptz_in timestamptz_larger
timestamptz_le timestamptz_le_date timestamptz_le_timestamp timestamptz_lt timestamptz_lt_date timestamptz_lt_timestamp timestamptz_mi
timestamptz_mi_interval timestamptz_ne timestamptz_ne_date timestamptz_ne_timestamp timestamptz_out timestamptz_pl_interval timestamptz_recv
timestamptz_send timestamptz_smaller timestamptztypmodin timestamptztypmodout timetypmodin timetypmodout timetz
timetz_cmp timetz_eq timetz_ge timetz_gt timetz_hash timetz_in timetz_larger
timetz_le timetz_lt timetz_mi_interval timetz_ne timetz_out timetz_pl_interval timetz_recv
timetz_send timetz_smaller timetzdate_pl timetztypmodin timetztypmodout timezone tinterval
tintervalct tintervalend tintervaleq tintervalge tintervalgt tintervalin tintervalle
tintervalleneq tintervallenge tintervallengt tintervallenle tintervallenlt tintervallenne tintervallt
tintervalne tintervalout tintervalov tintervalrecv tintervalrel tintervalsame tintervalsend
tintervalstart to_json to_tsquery to_tsvector transaction_timestamp trigger_out trunc ts_debug
ts_headline ts_lexize ts_match_qv ts_match_tq ts_match_tt ts_match_vq ts_parse ts_delete ts_filter
ts_rank ts_rank_cd ts_rewrite ts_stat ts_token_type ts_typanalyze tsmatchjoinsel tsquery_phrase
tsmatchsel tsq_mcontained tsq_mcontains tsquery_and tsquery_cmp tsquery_eq tsquery_ge
tsquery_gt tsquery_le tsquery_lt tsquery_ne tsquery_not tsquery_or tsqueryin websearch_to_tsquery
tsqueryout tsqueryrecv tsquerysend tsrange tsrange_subdiff tstzrange tstzrange_subdiff phraseto_tsquery
tsvector_cmp tsvector_concat tsvector_eq tsvector_ge tsvector_gt tsvector_le tsvector_lt
tsvector_ne tsvectorin tsvectorout tsvectorrecv tsvectorsend txid_current txid_current_snapshot
txid_snapshot_in txid_snapshot_out txid_snapshot_recv txid_snapshot_send txid_snapshot_xip
txid_snapshot_xmax txid_snapshot_xmin
txid_visible_in_snapshot uhc_to_utf8 unknownin unknownout unknownrecv unknownsend unnest
upper_inc upper_inf utf8_to_ascii utf8_to_big5 utf8_to_euc_cn utf8_to_euc_jis_2004 utf8_to_euc_jp
utf8_to_euc_kr utf8_to_euc_tw utf8_to_gb18030 utf8_to_gbk utf8_to_iso8859 utf8_to_iso8859_1 utf8_to_johab
utf8_to_koi8r utf8_to_koi8u utf8_to_shift_jis_2004 utf8_to_sjis utf8_to_uhc utf8_to_win uuid_cmp
uuid_eq uuid_ge uuid_gt uuid_hash uuid_in uuid_le uuid_lt
uuid_ne uuid_out uuid_recv uuid_send var_pop var_samp varbit
varbit_in varbit_out varbit_recv varbit_send varbit_transform varbitcmp varbiteq
varbitge varbitgt varbitle varbitlt varbitne varbittypmodin varbittypmodout
varchar varying varchar_transform varcharin varcharout varcharrecv varcharsend varchartypmodin
varchartypmodout variance version void_in void_out void_recv void_send
width width_bucket win1250_to_latin2 win1250_to_mic win1251_to_iso win1251_to_koi8r win1251_to_mic
win1251_to_win866 win866_to_iso win866_to_koi8r win866_to_mic win866_to_win1251 win_to_utf8 xideq
xideqint4 xidin xidout xidrecv xidsend xml xml_in xmlcomment xpath xpath_exists table_to_xmlschema
query_to_xmlschema cursor_to_xmlschema table_to_xml_and_xmlschema query_to_xml_and_xmlschema
schema_to_xml schema_to_xmlschema schema_to_xml_and_xmlschema database_to_xml database_to_xmlschema xmlroot
database_to_xml_and_xmlschema table_to_xml query_to_xmlcursor_to_xml xmlcomment xmlconcat xmlelement xmlforest
xml_is_well_formed_content xml_is_well_formed_document xml_is_well_formed xml_out xml_recv xml_send xmlagg
xmlpi query_to_xml cursor_to_xml xmlserialize xmltable
);
my @copy_keywords = ( 'STDIN', 'STDOUT' );
my %symbols = (
'=' => '=', '<' => '<', '>' => '>', '|' => '|', ',' => ',', '.' => '.', '+' => '+', '-' => '-',
'*' => '*', '/' => '/', '!=' => '!=', '%' => '%', '<=' => '<=', '>=' => '>=', '<>' => '<>'
);
my @brackets = ( '(', ')' );
# All setting and modification of dicts is done, can set them now to $self->{'dict'}->{...}
$self->{ 'dict' }->{ 'pg_keywords' } = \@pg_keywords;
$self->{ 'dict' }->{ 'pg_types' } = \@pg_types;
$self->{ 'dict' }->{ 'sql_keywords' } = \@sql_keywords;
$self->{ 'dict' }->{ 'redshift_keywords' } = \@redshift_keywords;
$self->{ 'dict' }->{ 'pg_functions' } = ();
map { $self->{ 'dict' }->{ 'pg_functions' }{$_} = ''; } @pg_functions;
$self->{ 'dict' }->{ 'copy_keywords' } = \@copy_keywords;
$self->{ 'dict' }->{ 'symbols' } = \%symbols;
$self->{ 'dict' }->{ 'brackets' } = \@brackets;
return;
}
=head2 _remove_dynamic_code
Internal function used to hide dynamic code in plpgsql to the parser.
The original values are restored with function _restore_dynamic_code().
=cut
sub _remove_dynamic_code
{
my ($self, $str, $code_sep) = @_;
my @dynsep = ();
push(@dynsep, $code_sep) if ($code_sep && $code_sep ne "'");
# Try to auto detect the string separator if none are provided.
# Note that default single quote separtor is natively supported.
if ($#dynsep == -1)
{
# if a dollar sign is found after EXECUTE then the following string
# until an other dollar is found will be understand as a text delimiter
@dynsep = $$str =~ /EXECUTE\s+(\$[^\$\s]*\$)/igs;
}
foreach my $sep (@dynsep)
{
while ($$str =~ s/(\Q$sep\E.*?\Q$sep\E)/TEXTVALUE$self->{idx_code}/s)
{
$self->{dynamic_code}{$self->{idx_code}} = $1;
$self->{idx_code}++;
}
}
# Replace any COMMENT constant between single quote
while ($$str =~ s/IS\s+('(?:.*?)')\s*;/IS TEXTVALUE$self->{idx_code};/s)
{
$self->{dynamic_code}{$self->{idx_code}} = $1;
$self->{idx_code}++;
}
# keep untouched parts between double single quotes
while ($$str =~ s/(PGFESCQ1(?:[^\r\n\|;]*?)PGFESCQ1)/TEXTVALUE$self->{idx_code}/s)
{
$self->{dynamic_code}{$self->{idx_code}} = $1;
$self->{idx_code}++;
}
}
=head2 _restore_dynamic_code
Internal function used to restore plpgsql dynamic code in plpgsql
that was removed by the _remove_dynamic_code() method.
=cut
sub _restore_dynamic_code
{
my ($self, $str) = @_;
$$str =~ s/TEXTVALUE(\d+)/$self->{dynamic_code}{$1}/gs;
}
=head2 _quote_operator
Internal function used to quote operator with multiple character
to be tokenized as a single word.
The original values are restored with function _restore_operator().
=cut
sub _quote_operator
{
my ($self, $str) = @_;
my @lines = split(/[\n]/, $$str);
for (my $i = 0; $i <= $#lines; $i++)
{
if ($lines[$i] =~ s/((?:CREATE|DROP|ALTER)\s+OPERATOR\s+(?:IF\s+EXISTS)?)\s*((:?[a-z0-9]+\.)?[\+\-\*\/<>=\~\!\@\#\%\^\&\|\`\?]+)\s*/$1 "$2" /i) {
push(@{ $self->{operator} }, $2) if (!grep(/^\Q$2\E$/, @{ $self->{operator} }));
}
}
$$str = join("\n", @lines);
my $idx = 0;
while ($$str =~ s/(NEGATOR|COMMUTATOR)\s*=\s*([^,\)\s]+)/\U$1\E$idx/is) {
$self->{uc($1)}{$idx} = "$1 = $2";
$idx++;
}
}
=head2 _restore_operator
Internal function used to restore operator that was removed
by the _quote_operator() method.
=cut
sub _restore_operator
{
my ($self, $str) = @_;
foreach my $op (@{ $self->{operator} })
{
$$str =~ s/"$op"/$op/gs;
}
if (exists $self->{COMMUTATOR}) {
$$str =~ s/COMMUTATOR(\d+)/$self->{COMMUTATOR}{$1}/igs;
}
if (exists $self->{NEGATOR}) {
$$str =~ s/NEGATOR(\d+)/$self->{NEGATOR}{$1}/igs;
}
}
=head2 _quote_comment_stmt
Internal function used to replace constant in a COMMENT statement
to be tokenized as a single word.
The original values are restored with function _restore_comment_stmt().
=cut
sub _quote_comment_stmt
{
my ($self, $str) = @_;
my $idx = 0;
while ($$str =~ s/(COMMENT\s+ON\s+(?:.*?)\s+IS)\s+(\$[^;]+?\$)\s*;/$1 PGF_CMTSTR$idx;/is) {
$self->{comment_str}{$idx} = $2;
$idx++;
}
}
=head2 _restore_comment_stmt
Internal function used to restore comment string that was removed
by the _quote_comment_stmt() method.
=cut
sub _restore_comment_stmt
{
my ($self, $str) = @_;
if (exists $self->{comment_str}) {
$$str =~ s/PGF_CMTSTR(\d+)/$self->{comment_str}{$1}/igs;
}
}
=head2 _remove_comments
Internal function used to remove comments in SQL code
to simplify the work of the wrap_lines. Comments must be
restored with the _restore_comments() method.
=cut
sub _remove_comments
{
my $self = shift;
my $idx = 0;
while ($self->{ 'content' } =~ s/(\/\*(.*?)\*\/)/PGF_COMMENT${idx}A/s) {
$self->{'comments'}{"PGF_COMMENT${idx}A"} = $1;
$idx++;
}
my @lines = split(/\n/, $self->{ 'content' });
for (my $j = 0; $j <= $#lines; $j++)
{
$lines[$j] //= '';
# Extract multiline comments as a single placeholder
my $old_j = $j;
my $cmt = '';
while ($j <= $#lines && $lines[$j] =~ /^(\s*\-\-.*)$/)
{
$cmt .= "$1\n";
$j++;
}
if ( $j > $old_j )
{
chomp($cmt);
$lines[$old_j] =~ s/^(\s*\-\-.*)$/PGF_COMMENT${idx}A/;
$self->{'comments'}{"PGF_COMMENT${idx}A"} = $cmt;
$idx++;
$j--;
while ($j > $old_j)
{
delete $lines[$j];
$j--;
}
}
if ($lines[$j] =~ s/(\s*\-\-.*)$/PGF_COMMENT${idx}A/)
{
$self->{'comments'}{"PGF_COMMENT${idx}A"} = $1;
$idx++;
}
# Mysql supports differents kinds of comment's starter
if ( ($lines[$j] =~ s/(\s*COMMENT\s+'.*)$/PGF_COMMENT${idx}A/) ||
($lines[$j] =~ s/(\s*\# .*)$/PGF_COMMENT${idx}A/) )
{
$self->{'comments'}{"PGF_COMMENT${idx}A"} = $1;
# Normalize start of comment
$self->{'comments'}{"PGF_COMMENT${idx}A"} =~ s/^(\s*)COMMENT/$1\-\- /;
$self->{'comments'}{"PGF_COMMENT${idx}A"} =~ s/^(\s*)\#/$1\-\- /;
$idx++;
}
}
$self->{ 'content' } = join("\n", @lines);
# Remove extra newline after comment
while ($self->{ 'content' } =~ s/(PGF_COMMENT\d+A[\n])[\n]+/$1/s) {};
# Replace subsequent comment by a single one
while ($self->{ 'content' } =~ s/(PGF_COMMENT\d+A\s*PGF_COMMENT\d+A)/PGF_COMMENT${idx}A/s)
{
$self->{'comments'}{"PGF_COMMENT${idx}A"} = $1;
$idx++;
}
}
=head2 _restore_comments
Internal function used to restore comments in SQL code
that was removed by the _remove_comments() method.
=cut
sub _restore_comments
{
my ($self, $wrap_comment) = @_;
if ($self->{'wrap_limit'} && $wrap_comment)
{
foreach my $k (keys %{$self->{'comments'}})
{
if ($self->{'comments'}{$k} =~ /^(\s*)--[\r\n]/s)
{
next;
}
elsif ($self->{'comments'}{$k} =~ /^(\s*)--/)
{
my $indent = $1 || '';
if (length($self->{'comments'}{$k}) > $self->{'wrap_limit'} + ($self->{'wrap_limit'}*10/100))
{
my @data = split(/\n/, $self->{'comments'}{$k});
map { s/^\s*--//; } @data;
$self->{'comments'}{$k} = join("\n", @data);
$Text::Wrap::columns = $self->{'wrap_limit'};
my $t = wrap('', ' ', $self->{'comments'}{$k});
@data = split(/\n/, $t);
map { s/^/$indent--/; } @data;
$self->{'comments'}{$k} = join("\n", @data);
} else {
$self->{'comments'}{$k} =~ s/^\s*--//s;
$self->{'comments'}{$k} = $indent . "--$self->{'comments'}{$k}";
}
}
}
}
while ($self->{ 'content' } =~ s/(PGF_COMMENT\d+A)/$self->{'comments'}{$1}/s) { delete $self->{'comments'}{$1}; };
}
=head2 wrap_lines
Internal function used to wrap line at a certain length.
=cut
sub wrap_lines
{
my ($self, $wrap_comment) = @_;
return if (!$self->{'wrap_limit'} || !$self->{ 'content' });
$self->_remove_comments();
my @lines = split(/\n/, $self->{ 'content' });
$self->{ 'content' } = '';
foreach my $l (@lines)
{
# Remove and store the indentation of the line
my $indent = '';
if ($l =~ s/^(\s+)//) {
$indent = $1;
}
if (length($l) > $self->{'wrap_limit'} + ($self->{'wrap_limit'}*10/100))
{
$Text::Wrap::columns = $self->{'wrap_limit'};
my $t = wrap($indent, " "x$self->{ 'spaces' } . $indent, $l);
$self->{ 'content' } .= "$t\n";
} else {
$self->{ 'content' } .= $indent . "$l\n";
}
}
$self->_restore_comments($wrap_comment || $self->{ 'wrap_comment' }) if ($self->{ 'content' });
return;
}
sub _dump_var
{
my $self = shift;
foreach my $v (sort keys %{$self})
{
next if ($v !~ /^_/);
if ($self->{$v} =~ /ARRAY/) {
print STDERR "$v => (", join(',', @{$self->{$v}}), ")\n";
} else {
print STDERR "$v => $self->{$v}\n";
}
}
}
=head1 AUTHOR
pgFormatter is an original work from Gilles Darold
=head1 BUGS
Please report any bugs or feature requests to: https://github.com/darold/pgFormatter/issues
=head1 COPYRIGHT
Copyright 2012-2023 Gilles Darold. All rights reserved.
=head1 LICENSE
pgFormatter is free software distributed under the PostgreSQL Licence.
A modified version of the SQL::Beautify Perl Module is embedded in pgFormatter
with copyright (C) 2009 by Jonas Kramer and is published under the terms of
the Artistic License 2.0.
=cut
1;
|