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
|
#!/usr/bin/env python
'''
asciidoc - converts an AsciiDoc text file to DocBook, HTML or LinuxDoc
SYNOPSIS
asciidoc -b backend [ -d doctype ] [ -a attribute ]
[ -e ] [-n] [ -s ] [ -f configfile ] [ -o outfile ]
[ --help | -h ] [ --version ] [ -v ] [ -c ]
infile
DESCRIPTION
The asciidoc(1) command translates the AsciiDoc text file 'infile'
to the 'backend' formatted file 'outfile'. If 'infile' is '-' then
the standard input is used.
OPTIONS
--help, -h
Print this documentation.
-a attribute
Define document attribute. 'attribute' is formatted like
'name=value'. Alternate acceptable forms are 'name' (the
'value' defaults to an empty string) and '^name' (delete the
'name' attribute).
-b backend
Backend output file format: 'docbook', 'docbook-sgml',
'xhtml', 'html'. 'css', 'css-embedded', 'linuxdoc'.
'docbbok' generates DocBook XML; 'xhtml' generates XHTML;
'html' generates HTML 4.
-c
Dump configuration to stdout.
-e
Exclude implicitly loaded configuration files except for those
named like the input file ('infile.conf' and
'infile-backend.conf').
-d doctype
Document type: 'article', 'manpage' or 'book'. The 'book'
document type is only supported by the 'docbook' backend and
the 'manpage' document type is not supported by the 'linuxdoc'
backend.
-f configfile
Use configuration file 'configfile'.
-n
Auto-number HTML article section titles.
Synonym for '-a section-numbers'.
-o outfile
Write output to file 'outfile'. Defaults to the base name of
input file with 'backend' extension. If the input is stdin
then the outfile defaults to stdout. If 'outfile' is '-' then
the standard output is used.
-s
Suppress document header and footer output.
-v
Verbosely print processing information and configuration file
checks to stderr.
--version
Print program version number.
BUGS
See the AsciiDoc distribution BUGS file.
AUTHOR
Written by Stuart Rackham, <srackham@methods.co.nz>
RESOURCES
SourceForge: http://sourceforge.net/projects/asciidoc/
Main website: http://www.methods.co.nz/asciidoc/
COPYING
Copyright (C) 2002,2005 Stuart Rackham. Free use of this software
is granted under the terms of the GNU General Public License
(GPL).
'''
import sys, os, re, string, time, traceback, tempfile, popen2
from types import *
VERSION = '6.0.3' # See CHANGLOG file for version history.
#---------------------------------------------------------------------------
# Utility functions and classes.
#---------------------------------------------------------------------------
# Allowed substitution options for subs List options and presubs and postsubs
# Paragraph options.
#DEPRECATED: 'glossary'
SUBS_OPTIONS = ('specialcharacters','quotes','specialwords','replacements',
'glossary','attributes','macros','none','default','callouts')
# Default value for unspecified subs and presubs configuration file entries.
SUBS_DEFAULT = ('specialcharacters','quotes','specialwords','replacements',
'attributes','macros')
class EAsciiDoc(Exception):
pass
from UserDict import UserDict
class OrderedDict(UserDict):
'''Python Cookbook: Ordered Dictionary, Submitter: David Benjamin'''
def __init__(self, d = None):
self._keys = []
UserDict.__init__(self, d)
def __delitem__(self, key):
UserDict.__delitem__(self, key)
self._keys.remove(key)
def __setitem__(self, key, item):
UserDict.__setitem__(self, key, item)
if key not in self._keys: self._keys.append(key)
def clear(self):
UserDict.clear(self)
self._keys = []
def copy(self):
d = UserDict.copy(self)
d._keys = self._keys[:]
return d
def items(self):
return zip(self._keys, self.values())
def keys(self):
return self._keys
def popitem(self):
try:
key = self._keys[-1]
except IndexError:
raise KeyError('dictionary is empty')
val = self[key]
del self[key]
return (key, val)
def setdefault(self, key, failobj = None):
UserDict.setdefault(self, key, failobj)
if key not in self._keys: self._keys.append(key)
def update(self, d):
UserDict.update(self, d)
for key in d.keys():
if key not in self._keys: self._keys.append(key)
def values(self):
return map(self.get, self._keys)
def print_stderr(line):
sys.stderr.write(line+os.linesep)
def verbose(msg,linenos=True):
'''-v option messages.'''
if config.verbose:
console(msg,linenos=linenos)
def warning(msg,linenos=True):
console(msg,'WARNING: ',linenos)
def deprecated(old, new, linenos=True):
console("%s: %s" % (old,new), 'DEPRECATED: ', linenos)
def error(msg):
'''Report fatal error but don't exit application, continue in the hope of
reporting all fatal errors finishing with a non-zero exit code.'''
console(msg,'ERROR: ')
document.invalid = True
def console(msg, prefix='', linenos=True):
'''Print message to stderr. 'offset' is added to reported line number for
warnings emitted when reading ahead.'''
s = prefix
if linenos and reader.cursor:
s = s + "%s: line %d: " \
% (os.path.basename(reader.cursor[0]),reader.cursor[1])
s = s + msg
print_stderr(s)
def realpath(fname):
'''Return the absolute pathname of the file fname. Follow symbolic links.
os.realpath() not available in Python prior to 2.2 and not portable.'''
# Follow symlinks to the actual executable.
wd = os.getcwd()
try:
while os.path.islink(fname):
linkdir = os.path.dirname(fname)
fname = os.readlink(fname)
if linkdir: os.chdir(linkdir) # Symlinks can be relative.
fname = os.path.abspath(fname)
finally:
os.chdir(wd)
return fname
def syseval(cmd):
# Run shell command and return stdout.
child = os.popen(cmd)
data = child.read()
err = child.close()
if not err:
return data
else:
return ''
def assign(dst,src):
'''Assign all attributes from 'src' object to 'dst' object.'''
for a,v in src.__dict__.items():
setattr(dst,a,v)
def strip_quotes(s):
'''Trim white space and, if necessary, quote characters from s.'''
s = string.strip(s)
# Strip quotation mark characters from quoted strings.
if len(s) >= 3 and s[0] == '"' and s[-1] == '"':
s = s[1:-1]
return s
def is_regexp(s):
'''Return True if s is a valid regular expression else return False.'''
try: re.compile(s)
except: return False
else: return True
def join_regexp(relist):
'''Join list of regular expressions re1,re2,... to single regular
expression (re1)|(re2)|...'''
if len(relist) == 0:
return ''
result = []
# Delete named groups to avoid ambiguity.
for s in relist:
result.append(re.sub(r'\?P<\S+?>','',s))
result = string.join(result,')|(')
result = '('+result+')'
return result
def validate(value,rule,errmsg):
'''Validate value against rule expression. Throw EAsciiDoc exception with
errmsg if validation fails.'''
try:
if not eval(string.replace(rule,'$',str(value))):
raise EAsciiDoc,errmsg
except:
raise EAsciiDoc,errmsg
return value
def join_lines(lines):
'''Return a list in which lines terminated with the backslash line
continuation character are joined.'''
result = []
s = ''
continuation = False
for line in lines:
if line and line[-1] == '\\':
s = s + line[:-1]
continuation = True
continue
if continuation:
result.append(s+line)
s = ''
continuation = False
else:
result.append(line)
if continuation:
result.append(s)
return result
def parse_attrs(attrs,dict,default_arg=None):
'''Update a dictionary with name/value attributes from the attrs string.
The attrs string is a comma separated list of values and keyword name=value
pairs. Values must preceed keywords and are named '1','2'... The entire
attributes list is named '0'. If keywords are specified string values must
be quoted. Examples:
attrs: ''
dict: {}
attrs: 'hello,world'
dict: {'2': 'world', '0': 'hello,world', '1': 'hello'}
attrs: 'hello,,world'
default_arg: 'attrs'
dict: {'3': 'world', 'attrs': 'hello', '0': 'hello,,world', '1': 'hello'}
attrs: '"hello",planet="earth"'
dict: {'planet': 'earth', '0': '"hello",planet="earth"', '1': 'hello'}
'''
def f(*args,**keywords):
# Name and add aguments '1','2'... to keywords.
for i in range(len(args)):
if not keywords.has_key(str(i+1)):
keywords[str(i+1)] = args[i]
return keywords
if not attrs: return
dict['0'] = attrs
# Replace line separators with spaces so line spanning works.
s = re.sub(r'\s', ' ', attrs)
try:
d = eval('f('+s+')')
# Parse special 'options' argument.
if d.has_key('options') and d['options']:
for opt in re.split(r'\s*,\s*',d['options']):
if not is_name(opt):
warning('illegal option name in "%s"' % (d['options'],))
else:
d[opt] = '' # Create blank entry for each option.
dict.update(d)
except:
# Try quoting the attrs.
s = string.replace(s,'"',r'\"') # Escape double-quotes.
s = string.split(s,',')
s = map(lambda x: '"'+string.strip(x)+'"',s)
s = string.join(s,',')
try:
d = eval('f('+s+')')
except:
return # If there's a syntax error leave with {0}=attrs.
for k in d.keys(): # Drop any arguments that were missing.
if d[k] == '': del d[k]
dict.update(d)
assert len(d) > 0
if default_arg is not None and not d.has_key(default_arg) \
and d.has_key('1'):
dict[default_arg] = dict['1']
def parse_list(s):
'''Parse comma separated string of Python literals. Return a tuple of of
parsed values.'''
try:
result = eval('tuple(['+s+'])')
except:
raise EAsciiDoc,'malformed list: '+s
return result
def parse_options(options,allowed,errmsg):
'''Parse comma separated string of unquoted option names and return as a
tuple of valid options. 'allowed' is a list of allowed option values.
'errmsg' isan error message prefix if an illegal option error is thrown.'''
result = []
if options:
for s in re.split(r'\s*,\s*',options):
if s not in allowed:
raise EAsciiDoc,'%s "%s"' % (errmsg,s)
result.append(s)
return tuple(result)
def is_name(s):
'''Return True if s is valid attribute, macro or tag name
(starts with alpha containing alphanumeric and dashes only).'''
return re.match(r'[^\W\d][-\w]*',s) is not None
def subs_quotes(text):
'''Quoted text is marked up and the resulting text is
returned.'''
quotes = config.quotes.keys()
# The quotes are iterated in reverse sort order to avoid ambiguity,
# for example, '' is processed before '.
quotes.sort()
quotes.reverse()
for quote in quotes:
i = string.find(quote,'|')
if i != -1 and quote != '|' and quote != '||':
lq = quote[:i]
rq = quote[i+1:]
else:
lq = rq = quote
# Non-word (\W) characters are allowed at boundaries to accomodate
# enveloping quotes. re.S flag for line spanning.
reo = re.compile(r'(?ms)(^|\W)(?:' + re.escape(lq) + r')' \
+ r'(.*?)(?:'+re.escape(rq)+r')(?=\W|$)')
pos = 0
while True:
mo = reo.search(text,pos)
if not mo: break
if text[mo.start()] == '\\':
pos = mo.end()
else:
stag,etag = config.tag(config.quotes[quote])
if stag == etag == None:
s = ''
else:
s = mo.group(1) + stag + mo.group(2) + etag
text = text[:mo.start()] + s + text[mo.end():]
pos = mo.start() + len(s)
# Unescape escaped quotes.
text = string.replace(text,'\\'+lq, lq)
if lq != rq:
text = string.replace(text,'\\'+rq, rq)
return text
def subs_tag(tag,dict={}):
'''Perform attribute substitution and split tag string returning start, end
tag tuple (c.f. Config.tag()).'''
s = subs_attrs(tag,dict)
result = string.split(s,'|')
if len(result) == 1:
return result+[None]
elif len(result) == 2:
return result
else:
raise EAsciiDoc,'malformed tag "%s"' % (tag,)
def parse_entry(entry,dict=None,unquote=False,unique_values=False):
'''Parse name=value entry to dictionary 'dict'. Return tuple (name,value)
or None if illegal entry. If value is omitted (name=) then it is set to ''.
If only the name is present the value is set to None).
Leading and trailing white space is striped from 'name' and 'value'.
'name' can contain any printable characters. If 'name includes the equals
'=' character it must be escaped with a backslash.
If 'unquote' is True leading and trailing double-quotes are stripped from
'name' and 'value'.
If unique_values' is True then dictionary entries with the same value are
removed before the parsed entry is added.'''
mo=re.search(r'[^\\](=)',entry)
if mo: # name=value entry.
name = entry[:mo.start(1)]
value = entry[mo.end(1):]
else: # name entry.
name = entry
value = None
if unquote:
name = strip_quotes(name)
if value is not None:
value = strip_quotes(value)
else:
name = string.strip(name)
if value is not None:
value = string.strip(value)
if not name:
return None
if dict is not None:
if unique_values:
for k,v in dict.items():
if v == value: del dict[k]
dict[name] = value
return name,value
def parse_entries(entries, dict, unquote=False, unique_values=False):
'''Parse name=value entries from from lines of text in 'entries' into
dictionary 'dict'. Blank lines are skipped.'''
for entry in entries:
if entry and not parse_entry(entry,dict,unquote,unique_values):
raise EAsciiDoc,'malformed section entry "%s"' % (entry,)
def undefine_entries(entries):
'''All dictionary entries with None values are deleted.'''
for k,v in entries.items():
if v is None:
del entries[k]
def dump_section(name,dict,f=sys.stdout):
'''Write parameters in 'dict' as in configuration file section format with
section 'name'.'''
f.write('[%s]%s' % (name,writer.newline))
for k,v in dict.items():
k = str(k)
# Quote if necessary.
if len(k) != len(string.strip(k)):
k = '"'+k+'"'
if v and len(v) != len(string.strip(v)):
v = '"'+v+'"'
if v is None:
# Don't dump undefined entries.
continue
else:
s = k+'='+v
f.write('%s%s' % (s,writer.newline))
f.write(writer.newline)
def update_attrs(attrs,dict):
'''Update 'attrs' dictionary with parsed attributes in dictionary 'dict'.'''
for k,v in dict.items():
if not is_name(k):
raise EAsciiDoc,'illegal "%s" attribute name' % (k,)
attrs[k] = v
def readlines(fname):
'''Read lines from file named 'fname' and strip trailing white space.'''
# Read include file.
f = open(fname)
try:
lines = f.readlines()
finally:
f.close()
# Strip newlines.
for i in range(len(lines)):
lines[i] = string.rstrip(lines[i])
return lines
def filter_lines(filter,lines,dict={}):
'''Run 'lines' through the 'filter' shell command and return the result. The
'dict' dictionary contains additional filter attributes.'''
# BUG: Has problems finding filters with spaces in command name.
if not filter:
return lines
if os.name != 'posix':
warning('filters do not work in a non-posix environment')
return lines
# Perform attributes substitution on the filter command.
s = subs_attrs(filter,dict)
if not s:
raise EAsciiDoc,'filter "%s" has undefined attribute' % (filter,)
filter = s
# Search for the filter command in both user and application 'filters'
# sub-directories.
mo = re.match(r'^(?P<cmd>\S+)(?P<tail>.*)$', filter)
if mo:
cmd = mo.group('cmd')
found = False
if not os.path.dirname(cmd):
# Check in asciidoc user and application directories for unqualified
# file name.
if USER_DIR:
cmd2 = os.path.join(USER_DIR,'filters',cmd)
if os.path.isfile(cmd2):
found = True
if not found:
cmd2 = os.path.join(GLOBAL_CONFIG_DIR,'filters',cmd)
if os.path.isfile(cmd2):
found = True
if not found:
cmd2 = os.path.join(APP_DIR,'filters',cmd)
if os.path.isfile(cmd2):
found = True
if found:
filter = cmd2 + mo.group('tail')
else:
if os.uname()[0][:6] == 'CYGWIN':
# popen2() does not like non-drive letter path names under
# Cygwin.
s = string.strip(syseval('cygpath -m "'+cmd+'"'))
if s:
cmd = s
if not os.path.isfile(cmd):
warning('filter not found: "%s"' % (cmd,))
return lines
# Put the real filter path into the filter command.
verbose('filtering: '+filter)
try:
import select
result = []
r,w = popen2.popen2(filter)
# Polled I/O loop to alleviate full buffer deadlocks.
i = 0
while i < len(lines):
line = lines[i]
if select.select([],[w.fileno()],[],0)[1]:
w.write(line+os.linesep) # Use platform line terminator.
i = i+1
if select.select([r.fileno()],[],[],0)[0]:
s = r.readline()
if not s: break # Exit if filter output closes.
result.append(string.rstrip(s))
w.close()
for s in r.readlines():
result.append(string.rstrip(s))
r.close()
except:
raise EAsciiDoc,'filter "%s" error' % (filter,)
# There's no easy way to guage whether popen2() found and executed the
# filter, so guess that if it produced no output there is probably a
# problem.
if lines and not result:
warning('no output from filter "%s"' % (filter,))
return result
def system(name, args, is_macro=False):
'''Evaluate a system attribute ({name:args}) or system block macro
(name::[args]). If is_macro is True then we are processing a system
block macro otherwise it's a system attribute.'''
if is_macro:
syntax = '%s::[%s]'
separator = '\n'
else:
syntax = '{%s:%s}'
separator = writer.newline
verbose(('evaluating: '+syntax) % (name,args))
result = None
if name == 'eval':
try:
result = eval(args)
if result is None:
result = ''
result = str(result)
except:
warning((syntax+': expression evaluation error') % (name,args))
elif name in ('sys','sys2'):
result = ''
fd,tmp = tempfile.mkstemp()
os.close(fd)
try:
cmd = args
cmd = cmd + (' > %s' % tmp)
if name == 'sys2':
cmd = cmd + ' 2>&1'
if os.system(cmd):
warning((syntax+': non-zero exit status') % (name,args))
try:
if os.path.isfile(tmp):
lines = readlines(tmp)
else:
lines = []
except:
raise EAsciiDoc,(syntax+': temp file read error') % (name,args)
result = string.join(lines, separator)
finally:
if os.path.isfile(tmp):
os.remove(tmp)
elif name == 'include':
if not os.path.exists(args):
warning((syntax+': file does not exist') % (name,args))
else:
result = readlines(args)
result = subs_attrs(result)
result = string.join(result, separator)
result = string.expandtabs(result, reader.tabsize)
else:
warning(('Illegal '+syntax+': executable attribute name') % (name,args))
return result
def subs_attrs(lines,dict={}):
'''Substitute 'lines' of text with attributes from the global
document.attributes dictionary and from the 'dict' dictionary ('dict'
entries take precedence). Return a tuple of the substituted lines. 'lines'
containing undefined attributes are deleted. If 'lines' is a string then
return a string.'''
def end_brace(text,start):
'''Return index following end brace that matches brace at start in
text.'''
assert text[start] == '{'
n = 0
result = start
for c in text[start:]:
# Skip braces that are followed by a backslash.
if result == len(text)-1 or text[result+1] != '\\':
if c == '{': n = n + 1
elif c == '}': n = n - 1
result = result + 1
if n == 0: break
return result
if isinstance(lines,StringType):
string_result = True
lines = [lines]
else:
string_result = False
lines = list(lines)
attrs = document.attributes.copy()
attrs.update(dict)
# Substitute all attributes in all lines.
for i in range(len(lines)-1,-1,-1): # Reverse iterate lines.
text = lines[i]
# Make it easier for regular expressions.
text = string.replace(text,'\\{','{\\')
text = string.replace(text,'\\}','}\\')
# Expand simple attributes ({name}).
# Nested attributes not allowed.
reo = re.compile(r'\{(?P<name>[^\\\W][-\w]*?)\}(?!\\)', re.DOTALL)
pos = 0
while True:
mo = reo.search(text,pos)
if not mo: break
s = attrs.get(mo.group('name'))
if s is None:
pos = mo.end()
else:
s = str(s)
text = text[:mo.start()] + s + text[mo.end():]
pos = mo.start() + len(s)
# Expand calculated attributes ({name=value},
# {name?value}, {name!value} and {name#value}).
reo = re.compile(r'\{(?P<name>[^\\\W][-\w]*?)(?P<op>\=|\?|!|#|%)' \
r'(?P<value>.*?)\}(?!\\)',re.DOTALL)
pos = 0
while True:
mo = reo.search(text,pos)
if not mo: break
name = mo.group('name')
lval = attrs.get(name)
op = mo.group('op')
# mo.end() is not good enough because '{x={y}}' matches '{x={y}'.
end = end_brace(text,mo.start())
rval = text[mo.start('value'):end-1]
if lval is None:
if op == '=': s = rval
elif op == '?': s = ''
elif op == '!': s = rval
elif op == '#': s = '{'+name+'}' # So the line is deleted.
elif op == '%': s = rval
else: assert True,'illegal calculated attribute operator'
else:
if op == '=': s = lval
elif op == '?': s = rval
elif op == '!': s = ''
elif op == '#': s = rval
elif op == '%': s = '{zzzzz}' # So the line is deleted.
else: assert True,'illegal calculated attribute operator'
s = str(s)
text = text[:mo.start()] + s + text[end:]
pos = mo.start() + len(s)
# Drop line if it contains unsubstituted {name} references.
skipped = re.search(r'\{[^\\\W][-\w]*?\}(?!\\)', text, re.DOTALL)
if skipped:
del lines[i]
continue;
# Expand executable attributes ({name:expression}).
reo = re.compile(r'\{(?P<action>[^\\\W][-\w]*?):(?P<expr>.*?)\}(?!\\)',
re.DOTALL)
skipped = False
pos = 0
while True:
mo = reo.search(text,pos)
if not mo: break
expr = mo.group('expr')
expr = string.replace(expr,'{\\','{')
expr = string.replace(expr,'}\\','}')
s = system(mo.group('action'),expr)
if s is None:
skipped = True
break
text = text[:mo.start()] + s + text[mo.end():]
pos = mo.start() + len(s)
# Drop line if the action returns None.
if skipped:
del lines[i]
continue;
# Remove backslash from escaped entries.
text = string.replace(text,'{\\','{')
text = string.replace(text,'}\\','}')
lines[i] = text
if string_result:
if lines:
return string.join(lines,'\n')
else:
return None
else:
return tuple(lines)
class Lex:
'''Lexical analysis routines. Static methods and attributes only.'''
prev_element = None
prev_cursor = None
def __init__(self):
raise AssertionError,'no class instances allowed'
def next():
'''Returns class of next element on the input (None if EOF). The
reader is assumed to be at the first line following a previous element,
end of file or line one. Exits with the reader pointing to the first
line of the next element or EOF (leading blank lines are skipped).'''
reader.skip_blank_lines()
if reader.eof(): return None
# Optimization: If we've already checked for an element at this
# position return the element.
if Lex.prev_element and Lex.prev_cursor == reader.cursor:
return Lex.prev_element
result = None
# Check for BlockTitle.
if not result and BlockTitle.isnext():
result = BlockTitle
# Check for Title.
if not result and Title.isnext():
result = Title
# Check for Block Macro.
if not result and macros.isnext():
result = macros.current
# Check for List.
if not result and lists.isnext():
result = lists.current
# Check for DelimitedBlock.
if not result and blocks.isnext():
# Skip comment blocks.
if 'skip' in blocks.current.options:
blocks.current.translate()
return Lex.next()
else:
result = blocks.current
# Check for Table.
if not result and tables.isnext():
result = tables.current
# Check for AttributeEntry.
if not result and AttributeEntry.isnext():
result = AttributeEntry
# Check for AttributeList.
if not result and AttributeList.isnext():
result = AttributeList
# If it's none of the above then it must be an Paragraph.
if not result:
if not paragraphs.isnext():
raise EAsciiDoc,'paragraph expected'
result = paragraphs.current
# Cache answer.
Lex.prev_cursor = reader.cursor
Lex.prev_element = result
return result
next = staticmethod(next)
def subs_1(s,options):
'''Perform substitution specified in 'options' (in 'options' order) on
a single line 's' of text. Returns the substituted string.'''
if not s:
return s
result = s
for o in options:
if o == 'specialcharacters':
result = config.subs_specialchars(result)
# Quoted text.
elif o == 'quotes':
result = subs_quotes(result)
# Special words.
elif o == 'specialwords':
result = config.subs_specialwords(result)
# Replacements.
elif o == 'replacements':
result = config.subs_replacements(result)
# Inline macros.
elif o == 'macros':
result = macros.subs(result)
elif o == 'callouts':
result = macros.subs(result,callouts=True)
else:
raise EAsciiDoc,'illegal "%s" substitution option' % (o,)
return result
subs_1 = staticmethod(subs_1)
def subs(lines,options):
'''Perform inline processing specified by 'options' (in 'options'
order) on sequence of 'lines'.'''
if len(options) == 1:
if options[0] == 'none':
options = ()
elif options[0] == 'default':
options = SUBS_DEFAULT
if not lines or not options:
return lines
# Join lines so quoting can span multiple lines.
para = string.join(lines,"\n")
for o in options:
if o == 'glossary' or o == 'attributes':
if o == 'glossary':
deprecated("'glossary' substitution option",
"change to 'attributes'")
# If we don't substitute attributes line-by-line then a single
# undefined attribute will drop the entire paragraph.
# But this is probably what we want.
lines = subs_attrs(para.split("\n"))
para = string.join(lines,"\n")
else:
para = Lex.subs_1(para,(o,))
return para.split("\n")
subs = staticmethod(subs)
def set_margin(lines, margin=0):
'''Utility routine that sets the left margin to 'margin' space in a
block of non-blank lines.'''
# Calculate width of block margin.
lines = list(lines)
width = len(lines[0])
for s in lines:
i = re.search(r'\S',s).start()
if i < width: width = i
# Strip margin width from all lines.
for i in range(len(lines)):
lines[i] = ' '*margin + lines[i][width:]
return lines
set_margin = staticmethod(set_margin)
#---------------------------------------------------------------------------
# Document element classes parse AsciiDoc reader input and write DocBook writer
# output.
#---------------------------------------------------------------------------
class Document:
def __init__(self):
self.doctype = None # 'article','manpage' or 'book'.
self.backend = None # -b option argument.
self.infile = None # Source file name.
self.outfile = None # Output file name.
self.attributes = {}
self.level = 0 # 0 => front matter. 1,2,3 => sect1,2,3.
self.invalid = False # Set true if translated document is invalid.
def init_attrs(self):
# Set implicit attributes.
d = time.localtime(time.time())
self.attributes['localdate'] = time.strftime('%d-%b-%Y',d)
s = time.strftime('%H:%M:%S',d)
if time.daylight:
self.attributes['localtime'] = s + ' ' + time.tzname[1]
else:
self.attributes['localtime'] = s + ' ' + time.tzname[0]
self.attributes['asciidoc-version'] = VERSION
self.attributes['backend'] = document.backend
self.attributes['doctype'] = document.doctype
self.attributes['backend-'+document.backend] = ''
self.attributes['doctype-'+document.doctype] = ''
self.attributes[document.backend+'-'+document.doctype] = ''
self.attributes['asciidoc-dir'] = APP_DIR
self.attributes['user-dir'] = USER_DIR
if self.infile != '<stdin>':
self.attributes['infile'] = self.infile
self.attributes['docdir'] = os.path.dirname(self.infile)
self.attributes['docname'] = os.path.splitext(
os.path.basename(self.infile))[0]
# Update with configuration file attributes.
self.attributes.update(config.conf_attrs)
# Update with command-line attributes.
self.attributes.update(config.cmd_attrs)
# Filter miscelaneous configuration section entries from attributes.
config.load_miscellaneous(config.conf_attrs)
config.load_miscellaneous(config.cmd_attrs)
self.attributes['newline'] = config.newline # Use raw (unescaped) value.
if self.outfile:
if self.outfile != '<stdout>':
self.attributes['outfile'] = self.outfile
ext = os.path.splitext(self.outfile)[1][1:]
elif config.outfilesuffix:
ext = config.outfilesuffix[1:]
else:
ext = ''
if ext:
self.attributes['filetype'] = ext
self.attributes['filetype-'+ext] = ''
def translate(self):
assert self.doctype in ('article','manpage','book'), \
'illegal document type'
assert self.level == 0
# Process document header.
AttributeEntry.translate_all()
has_header = Lex.next() is Title and Title.level == 0
if self.doctype == 'manpage' and not has_header:
error('manpage document title is mandatory')
if has_header:
Header.translate()
# Command-line entries override header derived entries.
self.attributes.update(config.cmd_attrs)
if not config.suppress_headers:
hdr = config.subs_section('header',{})
writer.write(hdr)
if self.doctype in ('article','book'):
# Translate 'preamble' (untitled elements between header
# and first section title).
if Lex.next() is not Title:
stag,etag = config.section2tags('preamble')
writer.write(stag)
Section.translate_body()
writer.write(etag)
else:
# Translate manpage SYNOPSIS.
if Lex.next() is not Title:
error('SYNOPSIS section expected')
else:
Title.translate()
if string.upper(Title.dict['title']) <> 'SYNOPSIS':
error('second section must be named SYNOPSIS')
if Title.level != 1:
error('SYNOPSIS section title must be at level 1')
stag,etag = config.section2tags('sect-synopsis')
writer.write(stag)
Section.translate_body()
writer.write(etag)
else:
if not config.suppress_headers:
hdr = config.subs_section('header',{})
writer.write(hdr)
if Lex.next() is not Title:
Section.translate_body()
# Process remaining sections.
while not reader.eof():
if Lex.next() is not Title:
raise EAsciiDoc,'section title expected'
Section.translate()
Section.setlevel(0) # Write remaining unwritten section close tags.
# Substitute document parameters and write document footer.
if not config.suppress_headers:
ftr = config.subs_section('footer',{})
writer.write(ftr)
def parse_author(self,s):
attrs = self.attributes # Alias for readability.
s = subs_attrs(s)
s = string.strip(s)
mo = re.match(r'^(?P<name1>[^<>\s]+)'
'(\s+(?P<name2>[^<>\s]+))?'
'(\s+(?P<name3>[^<>\s]+))?'
'(\s+<(?P<email>\S+)>)?$',s)
if not mo:
error('malformed author line')
firstname = mo.group('name1')
if mo.group('name3'):
middlename = mo.group('name2')
lastname = mo.group('name3')
else:
middlename = None
lastname = mo.group('name2')
email = mo.group('email')
author = firstname
initials = firstname[0]
if middlename:
author += ' '+middlename
initials += middlename[0]
if lastname:
author += ' '+lastname
initials += lastname[0]
initials = string.upper(initials)
if firstname:
attrs['firstname'] = config.subs_specialchars(firstname)
if middlename:
attrs['middlename'] = config.subs_specialchars(middlename)
if lastname:
attrs['lastname'] = config.subs_specialchars(lastname)
if author:
attrs['author'] = config.subs_specialchars(author)
if initials:
attrs['authorinitials'] = config.subs_specialchars(initials)
if email:
attrs['email'] = email
class Header:
'''Static methods and attributes only.'''
def __init__(self):
raise AssertionError,'no class instances allowed'
def translate():
assert Lex.next() is Title and Title.level == 0
Title.translate()
attrs = document.attributes # Alias for readability.
attrs['doctitle'] = Title.dict['title']
if document.doctype == 'manpage':
# manpage title formatted like mantitle(manvolnum).
mo = re.match(r'^(?P<mantitle>.*)\((?P<manvolnum>.*)\)$',
Title.dict['title'])
if not mo: error('malformed manpage title')
attrs['mantitle'] = string.strip(string.lower(mo.group('mantitle')))
attrs['manvolnum'] = string.strip(mo.group('manvolnum'))
AttributeEntry.translate_all()
s = reader.read_next()
if s:
s = reader.read()
document.parse_author(s)
AttributeEntry.translate_all()
if reader.read_next():
# Parse revision line.
s = reader.read()
s = subs_attrs(s)
# Match RCS/CVS $Id$ marker format.
mo = re.match(r'^\$Id: \S+ (?P<revision>\S+)'
' (?P<date>\S+) \S+ \S+ \S+ \$$',s)
if not mo:
# Match AsciiDoc revision,date format.
mo = re.match(r'^\D*(?P<revision>.*?),(?P<date>.+)$',s)
if mo:
revision = string.strip(mo.group('revision'))
date = string.strip(mo.group('date'))
else:
revision = None
date = string.strip(s)
if revision:
attrs['revision'] = config.subs_specialchars(revision)
if date:
attrs['date'] = config.subs_specialchars(date)
AttributeEntry.translate_all()
if document.backend == 'linuxdoc' and not attrs.has_key('author'):
warning('linuxdoc requires author name')
if document.doctype == 'manpage':
# Translate mandatory NAME section.
if Lex.next() is not Title:
error('NAME section expected')
else:
Title.translate()
if string.upper(Title.dict['title']) <> 'NAME':
error('first section must be named NAME')
if Title.level != 1:
error('NAME section title must be at level 1')
if not isinstance(Lex.next(),Paragraph):
error('malformed NAME section body')
lines = reader.read_until(r'^$')
s = string.join(lines)
mo = re.match(r'^(?P<manname>.*?)-(?P<manpurpose>.*)$',s)
if not mo:
error('malformed NAME section body')
attrs['manname'] = string.strip(mo.group('manname'))
attrs['manpurpose'] = string.strip(mo.group('manpurpose'))
if attrs.get('author',None) or attrs.get('email',None):
attrs['authored'] = ''
translate = staticmethod(translate)
class AttributeEntry:
'''Static methods and attributes only.'''
pattern = None
name = None
value = None
def __init__(self):
raise AssertionError,'no class instances allowed'
def isnext():
result = False # Assume not next.
if not AttributeEntry.pattern:
pat = document.attributes.get('attributeentry-pattern')
if not pat:
error("[attributes] missing 'attributeentry-pattern' entry")
AttributeEntry.pattern = pat
line = reader.read_next()
if line:
mo = re.match(AttributeEntry.pattern,line)
if mo:
name = mo.group('attrname')
# Strip white space and illegal name chars.
name = string.lower(re.sub(r'[^\w\-_]', '', name))
AttributeEntry.name = name
# Trim value.
AttributeEntry.value = string.strip(mo.group('attrvalue'))
result = True
return result
isnext = staticmethod(isnext)
def translate():
assert Lex.next() is AttributeEntry
attr = AttributeEntry # Alias for brevity.
reader.read() # Discard attribute from reader.
# Don't override command-line attributes.
if config.cmd_attrs.has_key(attr.name):
return
# Update document.attributes from previously parsed attribute.
if attr.value:
attr.value = config.subs_specialchars(attr.value)
attr.value = subs_attrs(attr.value)
if attr.value is not None:
document.attributes[attr.name] = attr.value
# Some document Header attributes get special treatment.
if attr.name == 'author':
document.parse_author(attr.value)
elif document.attributes.has_key(attr.name):
del document.attributes[attr.name]
translate = staticmethod(translate)
def translate_all():
''' Process all contiguous attribute lines on reader.'''
while AttributeEntry.isnext():
AttributeEntry.translate()
translate_all = staticmethod(translate_all)
class AttributeList:
'''Static methods and attributes only.'''
pattern = None
match = None
attrs = {}
def __init__(self):
raise AssertionError,'no class instances allowed'
def isnext():
result = False # Assume not next.
if not AttributeList.pattern:
if not document.attributes.has_key('attributelist-pattern'):
error("[miscellaneous] missing 'attributelist-pattern' entry")
AttributeList.pattern = document.attributes['attributelist-pattern']
line = reader.read_next()
if line:
mo = re.match(AttributeList.pattern, line)
if mo:
AttributeList.match = mo
result = True
return result
isnext = staticmethod(isnext)
def translate():
assert Lex.next() is AttributeList
reader.read() # Discard attribute list from reader.
dict = AttributeList.match.groupdict()
for k,v in dict.items():
if v is not None:
if k == 'attrlist':
parse_attrs(v, AttributeList.attrs)
else:
AttributeList.attrs[k] = v
translate = staticmethod(translate)
def consume(dict):
'''Add attribute list to the dictionary 'dict' and reset the
list.'''
if AttributeList.attrs:
verbose('attribute list: %s' % AttributeList.attrs)
dict.update(AttributeList.attrs)
AttributeList.attrs = {}
consume = staticmethod(consume)
class BlockTitle:
'''Static methods and attributes only.'''
title = None
pattern = None
def __init__(self):
raise AssertionError,'no class instances allowed'
def isnext():
result = False # Assume not next.
line = reader.read_next()
if line:
mo = re.match(BlockTitle.pattern,line)
if mo:
BlockTitle.title = mo.group('title')
result = True
return result
isnext = staticmethod(isnext)
def translate():
assert Lex.next() is BlockTitle
reader.read() # Discard title from reader.
# Perform title substitutions.
s = Lex.subs((BlockTitle.title,), Title.subs)
s = string.join(s,writer.newline)
if not s:
warning('blank block title')
BlockTitle.title = s
translate = staticmethod(translate)
def consume(dict):
'''If there is a title add it to dict then reset title.'''
if BlockTitle.title:
dict['title'] = BlockTitle.title
BlockTitle.title = None
consume = staticmethod(consume)
class Title:
'''Processes Header and Section titles. Static methods and attributes
only.'''
# Class variables
underlines = ('==','--','~~','^^','++') # Levels 0,1,2,3,4.
subs = ('specialcharacters','quotes','replacements','attributes','macros')
pattern = None
level = 0
dict = {}
sectname = None
section_numbers = [0]*len(underlines)
dump_dict = {}
linecount = None # Number of lines in title (1 or 2).
def __init__(self):
raise AssertionError,'no class instances allowed'
def translate():
'''Parse the Title.dict and Title.level from the reader. The
real work has already been done by parse().'''
assert Lex.next() is Title
# Discard title from reader.
for i in range(Title.linecount):
reader.read()
Title.setsectname()
# Perform title substitutions.
s = Lex.subs((Title.dict['title'],), Title.subs)
s = string.join(s,writer.newline)
if not s:
warning('blank section title')
Title.dict['title'] = s
translate = staticmethod(translate)
def isnext():
lines = reader.read_ahead(2)
return Title.parse(lines)
isnext = staticmethod(isnext)
def parse(lines):
'''Parse title at start of lines tuple.'''
if len(lines) == 0: return False
if len(lines[0]) == 0: return False # Title can't be blank.
# Check for single-line titles.
result = False
for level in range(len(Title.underlines)):
k = 'sect%s' % level
if Title.dump_dict.has_key(k):
mo = re.match(Title.dump_dict[k], lines[0])
if mo:
Title.dict = mo.groupdict()
Title.level = level
Title.linecount = 1
result = True
break
if not result:
# Check for double-line titles.
if not Title.pattern: return False # Single-line titles only.
if len(lines) < 2: return False
title,ul = lines[:2]
if len(ul) < 2: return False
# Fast elimination check.
if ul[:2] not in Title.underlines: return False
# Length of underline must be within +-3 of title.
if not (len(ul)-3 < len(title) < len(ul)+3): return False
# Check for valid repetition of underline character pairs.
s = ul[:2]*((len(ul)+1)/2)
if ul != s[:len(ul)]: return False
# Don't be fooled by back-to-back delimited blocks, require at
# least one alphanumeric character in title.
if not re.search(r'\w',title): return False
mo = re.match(Title.pattern, title)
if mo:
Title.dict = mo.groupdict()
Title.level = list(Title.underlines).index(ul[:2])
Title.linecount = 2
result = True
# Check for expected pattern match groups.
if result:
if Title.dict.has_key('args'):
if Title.dict['args'] is not None:
deprecated('title arguments','use attribute lists')
parse_attrs(Title.dict['args'],Title.dict)
if not Title.dict.has_key('title'):
warning('[titles] entry has no <title> group')
Title.dict['title'] = lines[0]
for k,v in Title.dict.items():
if v is None: del Title.dict[k]
return result
parse = staticmethod(parse)
def load(dict):
'''Load and validate [titles] section entries from dict.'''
if dict.has_key('underlines'):
errmsg = 'malformed [titles] underlines entry'
try:
underlines = parse_list(dict['underlines'])
except:
raise EAsciiDoc,errmsg
if len(underlines) != len(Title.underlines):
raise EAsciiDoc,errmsg
for s in underlines:
if len(s) !=2:
raise EAsciiDoc,errmsg
Title.underlines = tuple(underlines)
Title.dump_dict['underlines'] = dict['underlines']
if dict.has_key('subs'):
Title.subs = parse_options(dict['subs'], SUBS_OPTIONS,
'illegal [titles] subs entry')
Title.dump_dict['subs'] = dict['subs']
if dict.has_key('sectiontitle'):
pat = dict['sectiontitle']
if not pat or not is_regexp(pat):
raise EAsciiDoc,'malformed [titles] sectiontitle entry'
Title.pattern = pat
Title.dump_dict['sectiontitle'] = pat
if dict.has_key('blocktitle'):
pat = dict['blocktitle']
if not pat or not is_regexp(pat):
raise EAsciiDoc,'malformed [titles] blocktitle entry'
BlockTitle.pattern = pat
Title.dump_dict['blocktitle'] = pat
# Load single-line title patterns.
for k in ('sect0','sect1','sect2','sect3','sect4'):
if dict.has_key(k):
pat = dict[k]
if not pat or not is_regexp(pat):
raise EAsciiDoc,'malformed [titles] %s entry' % k
Title.dump_dict[k] = pat
# TODO: Check we have either a Title.pattern or at least one
# single-line title pattern -- can this be done here or do we need
# check routine like the other block checkers?
load = staticmethod(load)
def dump():
dump_section('titles',Title.dump_dict)
dump = staticmethod(dump)
def setsectname():
'''Set Title section name. First search for section title in
[specialsections], if not found use default 'sect<level>' name.'''
for pat,sect in config.specialsections.items():
mo = re.match(pat,Title.dict['title'])
if mo:
title = mo.groupdict().get('title')
if title is not None:
Title.dict['title'] = string.strip(title)
else:
Title.dict['title'] = string.strip(mo.group())
Title.sectname = sect
break
else:
Title.sectname = 'sect%d' % (Title.level,)
setsectname = staticmethod(setsectname)
def getnumber(level):
'''Return next section number at section 'level' formatted like
1.2.3.4.'''
number = ''
for l in range(len(Title.section_numbers)):
n = Title.section_numbers[l]
if l == 0:
continue
elif l < level:
number = '%s%d.' % (number, n)
elif l == level:
number = '%s%d.' % (number, n + 1)
Title.section_numbers[l] = n + 1
elif l > level:
# Reset unprocessed section levels.
Title.section_numbers[l] = 0
return number
getnumber = staticmethod(getnumber)
class Section:
'''Static methods and attributes only.'''
endtags = [] # Stack of currently open section (level,endtag) tuples.
def __init__(self):
raise AssertionError,'no class instances allowed'
def savetag(level,etag):
'''Save section end.'''
Section.endtags.append((level,etag))
savetag = staticmethod(savetag)
def setlevel(level):
'''Set document level and write open section close tags up to level.'''
while Section.endtags and Section.endtags[-1][0] >= level:
writer.write(Section.endtags.pop()[1])
document.level = level
setlevel = staticmethod(setlevel)
def translate():
assert Lex.next() is Title
prev_sectname = Title.sectname
Title.translate()
if Title.level == 0 and document.doctype != 'book':
error('only book doctypes can contain level 0 sections')
if Title.level > document.level \
and document.backend == 'docbook' \
and prev_sectname in ('sect-colophon','sect-abstract', \
'sect-dedication','sect-glossary','sect-bibliography'):
error('%s section cannot contain sub-sections' % (prev_sectname,))
if Title.level > document.level+1:
# Sub-sections of multi-part book level zero Preface and Appendices
# are meant to be out of sequence.
if document.doctype == 'book' \
and document.level == 0 \
and Title.level == 2 \
and prev_sectname in ('sect-preface','sect-appendix'):
pass
else:
warning('section title out of sequence: '
'expected level %d, got level %d'
% (document.level+1, Title.level))
Section.setlevel(Title.level)
Title.dict['sectnum'] = Title.getnumber(document.level)
AttributeList.consume(Title.dict)
stag,etag = config.section2tags(Title.sectname,Title.dict)
Section.savetag(Title.level,etag)
writer.write(stag)
Section.translate_body()
translate = staticmethod(translate)
def translate_body(terminator=Title):
isempty = True
next = Lex.next()
while next and next is not terminator:
if next is Title and isinstance(terminator,DelimitedBlock):
error('title not permitted in sidebar body')
if document.backend == 'linuxdoc' \
and document.level == 0 \
and not isinstance(next,Paragraph):
warning('only paragraphs are permitted in linuxdoc synopsis')
next.translate()
next = Lex.next()
isempty = False
# The section is not empty if contains a subsection.
if next and isempty and Title.level > document.level:
isempty = False
# Report empty sections if invalid markup will result.
if isempty:
if document.backend == 'docbook' and Title.sectname != 'sect-index':
error('empty section is not valid')
translate_body = staticmethod(translate_body)
class Paragraphs:
'''List of paragraph definitions.'''
def __init__(self):
self.current=None
self.paragraphs = [] # List of Paragraph objects.
self.default = None # The default [paradef-default] paragraph.
def load(self,sections):
'''Update paragraphs defined in 'sections' dictionary.'''
for k in sections.keys():
if re.match(r'^paradef.+$',k):
dict = {}
parse_entries(sections.get(k,()),dict)
for p in self.paragraphs:
if p.name == k: break
else:
p = Paragraph()
self.paragraphs.append(p)
try:
p.load(k,dict)
except EAsciiDoc,e:
raise EAsciiDoc,'[%s] %s' % (k,str(e))
def dump(self):
for p in self.paragraphs:
p.dump()
def isnext(self):
for p in self.paragraphs:
if p.isnext():
self.current = p
return True;
return False
def check(self):
# Check all paragraphs have valid delimiter.
for p in self.paragraphs:
if not p.delimiter or not is_regexp(p.delimiter):
raise EAsciiDoc,'[%s] missing or illegal delimiter' % (p.name,)
# Check all paragraph template sections exist.
for p in self.paragraphs:
if not p.template:
warning('[%s] missing template entry' % (p.name,))
if not config.sections.has_key(p.template):
warning('[%s] missing paragraph template section'
% (p.template,))
# Check we have a default paragraph definition, put it last in list.
for i in range(len(self.paragraphs)):
if self.paragraphs[i].name == 'paradef-default':
p = self.paragraphs[i]
del self.paragraphs[i]
self.paragraphs.append(p)
self.default = p
break
else:
raise EAsciiDoc,'missing [paradef-default] section'
class Paragraph:
OPTIONS = ('listelement',)
def __init__(self):
self.name=None # Configuration file section name.
self.delimiter=None # Regular expression matching paragraph delimiter.
self.template=None # Name of section defining paragraph start/end tags.
self.options=() # List of paragraph option names.
self.presubs=SUBS_DEFAULT # List of pre-filter substitution option names.
self.postsubs=() # List of post-filter substitution option names.
self.filter=None # Executable paragraph filter command.
self.text=None # Text in first line of paragraph.
def load(self,name,dict):
'''Update paragraph definition from section entries in 'dict'.'''
self.name = name
for k,v in dict.items():
if k == 'delimiter':
if v and is_regexp(v):
self.delimiter = v
else:
raise EAsciiDoc,'malformed paragraph delimiter "%s"' % (v,)
elif k == 'template' or k == 'section':
if k == 'section':
deprecated('[%s] "section" entry' % self.name,
'rename to "template"')
if is_name(v):
self.template = v
else:
raise EAsciiDoc,'malformed paragraph template name "%s"' \
% (v,)
elif k == 'options':
self.options = parse_options(v,Paragraph.OPTIONS,
'illegal Paragraph %s option' % (k,))
elif k == 'presubs':
self.presubs = parse_options(v,SUBS_OPTIONS,
'illegal Paragraph %s option' % (k,))
elif k == 'postsubs':
self.postsubs = parse_options(v,SUBS_OPTIONS,
'illegal Paragraph %s option' % (k,))
elif k == 'filter':
self.filter = v
else:
raise EAsciiDoc,'illegal paragraph parameter name "%s"' % (k,)
def dump(self):
write = lambda s: sys.stdout.write('%s%s' % (s,writer.newline))
write('['+self.name+']')
write('delimiter='+self.delimiter)
if self.template:
write('template='+self.template)
if self.options:
write('options='+string.join(self.options,','))
if self.presubs:
write('presubs='+string.join(self.presubs,','))
if self.postsubs:
write('postsubs='+string.join(self.postsubs,','))
if self.filter:
write('filter='+self.filter)
write('')
def isnext(self):
result = False
reader.skip_blank_lines()
if reader.read_next():
mo = re.match(self.delimiter,reader.read_next())
if mo:
self.text = mo.groupdict().get('text')
result = True
return result
def write_body(self,body):
dict = {}
BlockTitle.consume(dict)
AttributeList.consume(dict)
stag,etag = config.section2tags(self.template, dict)
# Writes blank line if the tag is empty (to separate LinuxDoc
# paragraphs).
if not stag: stag = ['']
if not etag: etag = ['']
writer.write(list(stag)+list(body)+list(etag))
def translate(self):
reader.read() # Discard (already parsed item first line).
# The next line introduces the requirement that a List cannot
# immediately follow a preceding Paragraph (introduced in v3.2.2).
# '+' delimiter is for list element continuation.
body = reader.read_until(r'^\+|^$|'+blocks.delimiter+r'|'+tables.delimiter)
body = [self.text] + list(body)
body = join_lines(body)
body = Lex.set_margin(body) # Move body to left margin.
body = Lex.subs(body,self.presubs)
if self.filter:
body = filter_lines(self.filter,body)
body = Lex.subs(body,self.postsubs)
self.write_body(body)
class Lists:
'''List of List objects.'''
def __init__(self):
self.current = None
self.lists = [] # List objects.
self.delimiter = '' # Combined blocks delimiter regular expression.
self.open = [] # A stack of the current and parent lists.
self.continuation = None # Current list continuation block.
def load(self,sections):
'''Update lists defined in 'sections' dictionary.'''
for k in sections.keys():
if re.match(r'^listdef.+$',k):
dict = {}
parse_entries(sections.get(k,()),dict)
for l in self.lists:
if l.name == k: break
else:
l = List() # Create a new list if it doesn't exist.
self.lists.append(l)
try:
l.load(k,dict)
except EAsciiDoc,e:
raise EAsciiDoc,'[%s] %s' % (k,str(e))
def dump(self):
for l in self.lists:
l.dump()
def isnext(self):
for l in self.lists:
if l.isnext():
self.current = l
return True;
return False
def check(self):
for l in self.lists:
# Check list has valid type .
if not l.type in l.TYPES:
raise EAsciiDoc,'[%s] illegal type' % (l.name,)
# Check list has valid delimiter.
if not l.delimiter or not is_regexp(l.delimiter):
raise EAsciiDoc,'[%s] missing or illegal delimiter' % (l.name,)
# Check all list tags.
if not l.listtag or not config.tags.has_key(l.listtag):
warning('[%s] missing listtag' % (l.name,))
if not l.itemtag or not config.tags.has_key(l.itemtag):
warning('[%s] missing tag itemtag' % (l.name,))
if not l.texttag or not config.tags.has_key(l.texttag):
warning('[%s] missing tag texttag' % (l.name,))
if l.type == 'labeled':
if not l.entrytag or not config.tags.has_key(l.entrytag):
warning('[%s] missing entrytag' % (l.name,))
if not l.labeltag or not config.tags.has_key(l.labeltag):
warning('[%s] missing labeltag' % (l.name,))
# Build combined lists delimiter pattern.
delimiters = []
for l in self.lists:
delimiters.append(l.delimiter)
self.delimiter = join_regexp(delimiters)
class List:
# DEPRECATED: 'termtag'
TAGS = ('listtag','itemtag','texttag','entrytag','termtag','labeltag')
# DEPRECATED: 'simple','variable'
TYPES = ('simple','variable','bulleted','numbered','labeled','callout')
def __init__(self):
self.name=None # List definition configuration file section name.
self.type=None
self.delimiter=None # Regular expression matching list item delimiter.
self.subs=SUBS_DEFAULT # List of substitution option names.
self.listtag=None
self.itemtag=None
self.texttag=None # Tag for list item text.
self.labeltag=None # Variable lists only.
self.entrytag=None # Variable lists only.
self.label=None # List item label (labeled lists only).
self.text=None # Text in first line of list item.
self.attrs={} # Attributes from preceding attribute list element.
self.index=None # Matched optional delimiter 'index' group.
def load(self,name,dict):
'''Update block definition from section entries in 'dict'.'''
self.name = name
for k,v in dict.items():
if k == 'type':
if v in self.TYPES:
if v == 'simple':
deprecated("'simple' list type",
"rename to 'bulleted' or 'numbered'")
v = 'bulleted'
elif v == 'variable':
deprecated("'variable' list type",
"rename to 'labeled'")
v = 'labeled'
self.type = v
else:
raise EAsciiDoc,'illegal list type "%s"' % (v,)
elif k == 'delimiter':
if v and is_regexp(v):
self.delimiter = v
else:
raise EAsciiDoc,'malformed list delimiter "%s"' % (v,)
elif k == 'subs':
self.subs = parse_options(v,SUBS_OPTIONS,
'illegal List %s option' % (k,))
elif k in self.TAGS:
if is_name(v):
if k == 'termtag':
deprecated("'termtag' list tag name",
"rename to 'labeltag'")
k = 'labeltag'
setattr(self,k,v)
else:
raise EAsciiDoc,'illegal list %s name "%s"' % (k,v)
else:
raise EAsciiDoc,'illegal list parameter name "%s"' % (k,)
def dump(self):
write = lambda s: sys.stdout.write('%s%s' % (s,writer.newline))
write('['+self.name+']')
write('type='+self.type)
write('delimiter='+self.delimiter)
if self.subs:
write('subs='+string.join(self.subs,','))
write('listtag='+self.listtag)
write('itemtag='+self.itemtag)
write('texttag='+self.texttag)
if self.type == 'labeled':
write('entrytag='+self.entrytag)
write('labeltag='+self.labeltag)
write('')
def isnext(self):
result = False
reader.skip_blank_lines()
if reader.read_next():
mo = re.match(self.delimiter,reader.read_next())
if mo:
self.label = mo.groupdict().get('label')
self.text = mo.groupdict().get('text')
self.index = mo.groupdict().get('index')
result = True
return result
def translate_entry(self):
assert self.type == 'labeled'
stag,etag = config.tag(self.entrytag, self.attrs)
if stag: writer.write(stag)
if self.text:
# Horizontal label list.
reader.read() # Discard (already parsed item first line).
writer.write_tag(self.labeltag, [self.label],
self.subs, self.attrs)
else:
# Write multiple labels (vertical label list).
while Lex.next() is self and not self.text:
reader.read() # Discard (already parsed item first line).
writer.write_tag(self.labeltag, [self.label],
self.subs, self.attrs)
# Write item text.
self.translate_item()
if etag: writer.write(etag)
def iscontinued(self):
if reader.read_next() == '+':
reader.read() # Discard.
# Allow attribute list to precede continued list item element.
if Lex.next() is AttributeList:
Lex.next().translate()
return True
else:
return False
def translate_item(self,listindex=None):
if lists.continuation:
self.translate_item_2(listindex)
else:
self.translate_item_1(listindex)
def translate_item_1(self,listindex=None):
'''Translation for '+' style list continuation.'''
if self.type == 'callout':
self.attrs['coids'] = calloutmap.calloutids(listindex)
stag,etag = config.tag(self.itemtag, self.attrs)
if stag:
writer.write(stag)
if self.text and self.text == '+':
# Pathalogical case: continued Horizontal Labeled List with no
# item text.
continued = True
elif not self.text and self.iscontinued():
# Pathalogical case: continued Vertical Labeled List with no
# item text.
continued = True
else:
# Write ItemText.
text = reader.read_until(lists.delimiter + '|^\+$|^--$|^$|' +
blocks.delimiter + r'|' + tables.delimiter)
if self.text is not None:
text = [self.text] + list(text)
text = join_lines(text)
writer.write_tag(self.texttag, text, self.subs, self.attrs)
continued = self.iscontinued()
while True:
next = Lex.next()
if next in lists.open:
break
elif isinstance(next,List):
next.translate()
elif isinstance(next,Paragraph) and 'listelement' in next.options:
next.translate()
elif continued:
if next is Title or next is BlockTitle:
error('title not allowed in list item continuation')
next.translate()
else:
break
continued = self.iscontinued()
if etag:
writer.write(etag)
def translate_item_2(self,listindex=None):
'''Translation for new ListBlock style list continuation.'''
if self.type == 'callout':
self.attrs['coids'] = calloutmap.calloutids(listindex)
stag,etag = config.tag(self.itemtag, self.attrs)
if stag:
writer.write(stag)
if self.text or reader.read_next():
# Write ItemText.
text = reader.read_until(lists.delimiter + r'|^$|' +
blocks.delimiter + r'|' + tables.delimiter)
if self.text is not None:
text = [self.text] + list(text)
text = join_lines(text)
writer.write_tag(self.texttag, text, self.subs, self.attrs)
while True:
next = Lex.next()
if next in lists.open:
break
elif next is lists.continuation:
break
elif isinstance(next,List):
next.translate()
elif isinstance(next,Paragraph) and 'listelement' in next.options:
next.translate()
elif lists.continuation:
if next is Title or next is BlockTitle:
error('title not allowed in list item continuation')
next.translate()
else:
break
if etag:
writer.write(etag)
def check_index(self,listindex):
''' Check calculated listindex (1,2,...) against the item index in the
document (self.index).'''
if self.index:
matched = False
if re.match(r'\d+', self.index):
i = int(self.index)
matched = True
elif re.match(r'[a-z]', self.index):
i = ord(self.index) - ord('a') + 1
matched = True
if matched and i != listindex:
warning("list item %s out of sequence" % self.index)
def translate(self):
lists.open.append(self)
self.attrs = {}
BlockTitle.consume(self.attrs)
AttributeList.consume(self.attrs)
stag,etag = config.tag(self.listtag, self.attrs)
if stag:
writer.write(stag)
listindex = 0
while Lex.next() is self:
listindex += 1
self.check_index(listindex)
if self.type in ('bulleted','numbered','callout'):
reader.read() # Discard (already parsed item first line).
self.translate_item(listindex)
elif self.type == 'labeled':
self.translate_entry()
else:
raise AssertionError,'illegal [%s] list type"' % (self.name,)
if etag:
writer.write(etag)
if self.type == 'callout':
calloutmap.check(listindex)
calloutmap.listclose()
lists.open.pop()
class DelimitedBlocks:
'''List of delimited blocks.'''
def __init__(self):
self.current=None
self.blocks = [] # List of DelimitedBlock objects.
self.delimiter = '' # Combined blocks delimiter regular expression.
def load(self,sections):
'''Update blocks defined in 'sections' dictionary.'''
for k in sections.keys():
if re.match(r'^blockdef.+$',k):
dict = {}
parse_entries(sections.get(k,()),dict)
for b in self.blocks:
if b.name == k: break
else:
b = DelimitedBlock()
self.blocks.append(b)
try:
b.load(k,dict)
except EAsciiDoc,e:
raise EAsciiDoc,'[%s] %s' % (k,str(e))
def dump(self):
for b in self.blocks:
b.dump()
def isnext(self):
for b in self.blocks:
if b.isnext():
self.current = b
return True;
return False
def check(self):
# Check all blocks have valid delimiter.
for b in self.blocks:
if not b.delimiter or not is_regexp(b.delimiter):
raise EAsciiDoc,'[%s] missing or illegal delimiter' % (b.name,)
# Check all block sections exist.
for b in self.blocks:
if 'skip' not in b.options:
if not b.template:
warning('[%s] missing template entry' % (b.name,))
if not config.sections.has_key(b.template):
warning('[%s] missing template section' % (b.template,))
# Build combined block delimiter pattern.
delimiters = []
for b in self.blocks:
delimiters.append(b.delimiter)
self.delimiter = join_regexp(delimiters)
class DelimitedBlock:
#DEPRECATED: 'section', 'argsline' options.
OPTIONS = ('section','skip','argsline','variants','sectionbody','listcontinuation')
def __init__(self):
self.name=None # Block definition configuration file section name.
self.delimiter=None # Regular expression matching block delimiter.
self.template=None # Name of section defining block header/footer.
self.options=() # List of block option names.
self.presubs=() # List of pre-filter substitution option names.
self.postsubs=() # List of post-filter substitution option names.
self.filter=None # Executable block filter command.
def load(self,name,dict):
'''Update block definition from section entries in 'dict'.'''
self.name = name
for k,v in dict.items():
if k == 'delimiter':
if v and is_regexp(v):
self.delimiter = v
else:
raise EAsciiDoc,'malformed block delimiter "%s"' % (v,)
elif k == 'template' or k == 'section':
if k == 'section':
deprecated('[%s] "section" entry' % self.name,
'rename to "template"')
if is_name(v):
self.template = v
else:
raise EAsciiDoc, 'malformed template section name "%s"' \
% (v,)
elif k == 'options':
self.options = parse_options(v,DelimitedBlock.OPTIONS,
'illegal DelimitedBlock %s option' % (k,))
elif k == 'presubs':
self.presubs = parse_options(v,SUBS_OPTIONS,
'illegal DelimitedBlock %s option' % (k,))
elif k == 'postsubs':
self.postsubs = parse_options(v,SUBS_OPTIONS,
'illegal DelimitedBlock %s option' % (k,))
elif k == 'filter':
self.filter = v
else:
raise EAsciiDoc,'illegal block parameter name "%s"' % (k,)
def dump(self):
write = lambda s: sys.stdout.write('%s%s' % (s,writer.newline))
write('['+self.name+']')
write('delimiter='+self.delimiter)
if self.template:
write('template='+self.template)
if self.options:
write('options='+string.join(self.options,','))
if self.presubs:
write('presubs='+string.join(self.presubs,','))
if self.postsubs:
write('postsubs='+string.join(self.postsubs,','))
if self.filter:
write('filter='+self.filter)
write('')
def isnext(self):
reader.skip_blank_lines()
if reader.read_next():
return re.match(self.delimiter,reader.read_next())
else:
return False
def translate(self):
if 'listcontinuation' in self.options:
lists.continuation = self
dict = {}
# Leave list block title and attributes for the list element.
if lists.continuation is not self:
BlockTitle.consume(dict)
AttributeList.consume(dict)
if 'variants' in self.options and dict.get('1'):
# Synthesize template section name from attribute {1}.
# Strip white space and illegal name chars.
template = string.lower(re.sub(r'[^\w\-_]', '', dict['1']))+'block'
if not config.sections.has_key(template):
warning('missing [%s] template section' % (template,))
template = self.template
else:
template = self.template
delimiter = reader.read()
mo = re.match(self.delimiter,delimiter)
assert mo
dict.update(mo.groupdict()) # Deprecated: no delimiter args.
for k,v in dict.items():
if v is None: del dict[k]
if dict.has_key('args'):
deprecated('delimited block arguments','use attribute lists')
# Extract embedded arguments from leading delimiter line.
parse_attrs(dict['args'],dict)
elif 'argsline' in self.options:
# DEPRECATED: 'argsline' block option.
# Parse block arguments line.
reader.parse_arguments(dict)
# Process block contents.
if 'skip' in self.options:
# Discard block body.
reader.read_until(self.delimiter,same_file=True)
elif 'section' in self.options or 'sectionbody' in self.options \
or 'listcontinuation' in self.options:
if 'section' in self.options:
deprecated('[%s] "section" option' % self.name,
'rename to "sectionbody"')
stag,etag = config.section2tags(template,dict)
# The body is treated like a SimpleSection.
writer.write(stag)
Section.translate_body(self)
writer.write(etag)
else:
stag,etag = config.section2tags(template,dict)
body = reader.read_until(self.delimiter,same_file=True)
body = Lex.subs(body,self.presubs)
if self.filter:
body = filter_lines(self.filter,body,dict)
body = Lex.subs(body,self.postsubs)
# Write start tag, content, end tag.
writer.write(list(stag)+list(body)+list(etag))
if 'listcontinuation' in self.options:
lists.continuation = None
if reader.eof():
error('closing [%s] delimiter expected' % (self.name,))
else:
delimiter = reader.read() # Discard delimiter line.
assert re.match(self.delimiter,delimiter)
class Tables:
'''List of tables.'''
def __init__(self):
self.current=None
self.tables = [] # List of Table objects.
self.delimiter = '' # Combined tables delimiter regular expression.
def load(self,sections):
'''Update tables defined in 'sections' dictionary.'''
for k in sections.keys():
if re.match(r'^tabledef.+$',k):
dict = {}
parse_entries(sections.get(k,()),dict)
for t in self.tables:
if t.name == k: break
else:
t = Table()
self.tables.append(t)
try:
t.load(k,dict)
except EAsciiDoc,e:
raise EAsciiDoc,'[%s] %s' % (k,str(e))
def dump(self):
for t in self.tables:
t.dump()
def isnext(self):
for t in self.tables:
if t.isnext():
self.current = t
return True;
return False
def check(self):
# Check we have a default table definition,
for i in range(len(self.tables)):
if self.tables[i].name == 'tabledef-default':
default = self.tables[i]
break
else:
raise EAsciiDoc,'missing [table-default] section'
# Set default table defaults.
if default.subs is None: default.subs = SUBS_DEFAULT
if default.format is None: default.subs = 'fixed'
# Propagate defaults to unspecified table parameters.
for t in self.tables:
if t is not default:
if t.fillchar is None: t.fillchar = default.fillchar
if t.subs is None: t.subs = default.subs
if t.format is None: t.format = default.format
if t.template is None: t.template = default.template
if t.colspec is None: t.colspec = default.colspec
if t.headrow is None: t.headrow = default.headrow
if t.footrow is None: t.footrow = default.footrow
if t.bodyrow is None: t.bodyrow = default.bodyrow
if t.headdata is None: t.headdata = default.headdata
if t.footdata is None: t.footdata = default.footdata
if t.bodydata is None: t.bodydata = default.bodydata
# Check all tables have valid fill character.
for t in self.tables:
if not t.fillchar or len(t.fillchar) != 1:
raise EAsciiDoc,'[%s] missing or illegal fillchar' % (t.name,)
# Build combined tables delimiter patterns and assign defaults.
delimiters = []
for t in self.tables:
# Ruler is:
# (ColStop,(ColWidth,FillChar+)?)+, FillChar+, TableWidth?
t.delimiter = r'^(' + Table.COL_STOP \
+ r'(\d*|' + re.escape(t.fillchar) + r'*)' \
+ r')+' \
+ re.escape(t.fillchar) + r'+' \
+ '([\d\.]*)$'
delimiters.append(t.delimiter)
if not t.headrow:
t.headrow = t.bodyrow
if not t.footrow:
t.footrow = t.bodyrow
if not t.headdata:
t.headdata = t.bodydata
if not t.footdata:
t.footdata = t.bodydata
self.delimiter = join_regexp(delimiters)
# Check table definitions are valid.
for t in self.tables:
t.check()
if config.verbose:
if t.check_msg:
warning('[%s] table definition: %s' % (t.name,t.check_msg))
class Column:
'''Table column.'''
def __init__(self):
self.colalign = None # 'left','right','center'
self.rulerwidth = None
self.colwidth = None # Output width in page units.
class Table:
COL_STOP = r"(`|'|\.)" # RE.
ALIGNMENTS = {'`':'left', "'":'right', '.':'center'}
FORMATS = ('fixed','csv','dsv')
def __init__(self):
# Configuration parameters.
self.name=None # Table definition configuration file section name.
self.fillchar=None
self.subs=None
self.format=None # 'fixed','csv','dsv'
self.template=None
self.colspec=None
self.headrow=None
self.footrow=None
self.bodyrow=None
self.headdata=None
self.footdata=None
self.bodydata=None
# Calculated parameters.
self.delimiter=None # RE matching any table ruler.
self.underline=None # RE matching current table underline.
self.isnumeric=False # True if numeric ruler, false if character ruler.
self.tablewidth=None # Optional table width scale factor.
self.columns=[] # List of Columns.
self.dict={} # Substitutions dictionary.
# Other.
self.check_msg='' # Message set by previous self.check() call.
def load(self,name,dict):
'''Update table definition from section entries in 'dict'.'''
self.name = name
for k,v in dict.items():
if k == 'fillchar':
if v and len(v) == 1:
self.fillchar = v
else:
raise EAsciiDoc,'malformed table fillchar "%s"' % (v,)
elif k == 'template' or k == 'section':
if k == 'section':
deprecated('[%s] "section" entry' % self.name,
'rename to "template"')
if is_name(v):
self.template = v
else:
raise EAsciiDoc,'malformed table template name "%s"' % (v,)
elif k == 'subs':
self.subs = parse_options(v,SUBS_OPTIONS,
'illegal Table %s option' % (k,))
elif k == 'format':
if v in Table.FORMATS:
self.format = v
else:
raise EAsciiDoc,'illegal table format "%s"' % (v,)
elif k == 'colspec':
self.colspec = v
elif k == 'headrow':
self.headrow = v
elif k == 'footrow':
self.footrow = v
elif k == 'bodyrow':
self.bodyrow = v
elif k == 'headdata':
self.headdata = v
elif k == 'footdata':
self.footdata = v
elif k == 'bodydata':
self.bodydata = v
else:
raise EAsciiDoc,'illegal entry name "%s"' % (k,)
def dump(self):
write = lambda s: sys.stdout.write('%s%s' % (s,writer.newline))
write('['+self.name+']')
write('fillchar='+self.fillchar)
write('subs='+string.join(self.subs,','))
write('format='+self.format)
write('template='+self.template)
if self.colspec:
write('colspec='+self.colspec)
if self.headrow:
write('headrow='+self.headrow)
if self.footrow:
write('footrow='+self.footrow)
write('bodyrow='+self.bodyrow)
if self.headdata:
write('headdata='+self.headdata)
if self.footdata:
write('footdata='+self.footdata)
write('bodydata='+self.bodydata)
write('')
def check(self):
'''Check table definition and set self.check_msg if invalid else set
self.check_msg to blank string.'''
# Check global table parameters.
if config.textwidth is None:
self.check_msg = 'missing [miscellaneous] textwidth entry'
elif config.pagewidth is None:
self.check_msg = 'missing [miscellaneous] pagewidth entry'
elif config.pageunits is None:
self.check_msg = 'missing [miscellaneous] pageunits entry'
elif not self.template:
self.check_msg = 'missing template entry'
elif not config.sections.has_key(self.template):
self.check_msg = 'missing template section [%s]' % self.template
elif self.headrow is None:
self.check_msg = 'missing headrow entry'
elif self.footrow is None:
self.check_msg = 'missing footrow entry'
elif self.bodyrow is None:
self.check_msg = 'missing bodyrow entry'
elif self.headdata is None:
self.check_msg = 'missing headdata entry'
elif self.footdata is None:
self.check_msg = 'missing footdata entry'
elif self.bodydata is None:
self.check_msg = 'missing bodydata entry'
else:
# No errors.
self.check_msg = ''
def isnext(self):
reader.skip_blank_lines()
if reader.read_next():
return re.match(self.delimiter,reader.read_next())
else:
return False
def parse_ruler(self,ruler):
'''Parse ruler calculating underline and ruler column widths.'''
fc = re.escape(self.fillchar)
# Strip and save optional tablewidth from end of ruler.
mo = re.match(r'^(.*'+fc+r'+)([\d\.]+)$',ruler)
if mo:
ruler = mo.group(1)
self.tablewidth = float(mo.group(2))
self.dict['tablewidth'] = str(float(self.tablewidth))
else:
self.tablewidth = None
self.dict['tablewidth'] = '100.0'
# Guess whether column widths are specified numerically or not.
if ruler[1] != self.fillchar:
# If the first column does not start with a fillchar then numeric.
self.isnumeric = True
elif ruler[1:] == self.fillchar*len(ruler[1:]):
# The case of one column followed by fillchars is numeric.
self.isnumeric = True
else:
self.isnumeric = False
# Underlines must be 3 or more fillchars.
self.underline = r'^' + fc + r'{3,}$'
splits = re.split(self.COL_STOP,ruler)[1:]
# Build self.columns.
for i in range(0,len(splits),2):
c = Column()
c.colalign = self.ALIGNMENTS[splits[i]]
s = splits[i+1]
if self.isnumeric:
# Strip trailing fillchars.
s = re.sub(fc+r'+$','',s)
if s == '':
c.rulerwidth = None
else:
c.rulerwidth = int(validate(s,'int($)>0',
'malformed ruler: bad width'))
else: # Calculate column width from inter-fillchar intervals.
if not re.match(r'^'+fc+r'+$',s):
raise EAsciiDoc,'malformed ruler: illegal fillchars'
c.rulerwidth = len(s)+1
self.columns.append(c)
# Fill in unspecified ruler widths.
if self.isnumeric:
if self.columns[0].rulerwidth is None:
prevwidth = 1
for c in self.columns:
if c.rulerwidth is None:
c.rulerwidth = prevwidth
prevwidth = c.rulerwidth
def build_colspecs(self):
'''Generate colwidths and colspecs. This can only be done after the
table arguments have been parsed since we use the table format.'''
self.dict['cols'] = len(self.columns)
# Calculate total ruler width.
totalwidth = 0
for c in self.columns:
totalwidth = totalwidth + c.rulerwidth
if totalwidth <= 0:
raise EAsciiDoc,'zero width table'
# Calculate marked up colwidths from rulerwidths.
for c in self.columns:
# Convert ruler width to output page width.
width = float(c.rulerwidth)
if self.format == 'fixed':
if self.tablewidth is None:
# Size proportional to ruler width.
colfraction = width/config.textwidth
else:
# Size proportional to page width.
colfraction = width/totalwidth
else:
# Size proportional to page width.
colfraction = width/totalwidth
c.colwidth = colfraction * config.pagewidth # To page units.
if self.tablewidth is not None:
c.colwidth = c.colwidth * self.tablewidth # Scale factor.
if self.tablewidth > 1:
c.colwidth = c.colwidth/100 # tablewidth is in percent.
# Build colspecs.
if self.colspec:
s = []
for c in self.columns:
self.dict['colalign'] = c.colalign
self.dict['colwidth'] = str(int(c.colwidth))
s.append(subs_attrs(self.colspec,self.dict))
self.dict['colspecs'] = string.join(s,writer.newline)
def parse_attrs(self):
'''Parse table arguments string.'''
d = {}
AttributeList.consume(d)
reader.parse_arguments(d) # DEPRECATED: Drop only this statement.
# Update table with overridable parameters.
if d.has_key('subs'):
self.subs = parse_options(d['subs'],SUBS_OPTIONS,
'illegal table subs %s option' % ('subs',))
if d.has_key('format'):
self.format = d['format']
if d.has_key('tablewidth'):
self.tablewidth = float(d['tablewidth'])
# Add attributes for template substitution.
self.dict.update(d)
def split_rows(self,rows):
'''Return a two item tuple containing a list of lines up to but not
including the next underline (continued lines are joined ) and the
tuple of all lines after the underline.'''
reo = re.compile(self.underline)
i = 0
while not reo.match(rows[i]):
i = i+1
if i == 0:
raise EAsciiDoc,'missing [%s] table rows' % (self.name,)
if i >= len(rows):
raise EAsciiDoc,'closing [%s] underline expected' % (self.name,)
return (join_lines(rows[:i]), rows[i+1:])
def parse_rows(self, rows, rtag, dtag):
'''Parse rows list using the row and data tags. Returns a substituted
list of output lines.'''
result = []
# Source rows are parsed as single block, rather than line by line, to
# allow the CSV reader to handle multi-line rows.
if self.format == 'fixed':
rows = self.parse_fixed(rows)
elif self.format == 'csv':
rows = self.parse_csv(rows)
elif self.format == 'dsv':
rows = self.parse_dsv(rows)
else:
assert True,'illegal table format'
# Substitute and indent all data in all rows.
stag,etag = subs_tag(rtag,self.dict)
for row in rows:
result.append(' '+stag)
for data in self.subs_row(row,dtag):
result.append(' '+data)
result.append(' '+etag)
return result
def subs_row(self, data, dtag):
'''Substitute the list of source row data elements using the data tag.
Returns a substituted list of output table data items.'''
result = []
if len(data) < len(self.columns):
warning('fewer row data items then table columns')
if len(data) > len(self.columns):
warning('more row data items than table columns')
for i in range(len(self.columns)):
if i > len(data) - 1:
d = '' # Fill missing column data with blanks.
else:
d = data[i]
c = self.columns[i]
self.dict['colalign'] = c.colalign
self.dict['colwidth'] = str(int(c.colwidth)) + config.pageunits
stag,etag = subs_tag(dtag,self.dict)
# Insert AsciiDoc line break (' +') where row data has newlines
# ('\n'). This is really only useful when the table format is csv
# and the output markup is HTML. It's also a bit dubious in that it
# assumes the user has not modified the shipped line break pattern.
if 'replacements' in self.subs:
# Insert line breaks in cell data.
d = re.sub(r'(?m)\n',r' +\n',d)
d = string.split(d,'\n') # So writer.newline is written.
else:
d = [d]
result = result + [stag] + Lex.subs(d,self.subs) + [etag]
return result
def parse_fixed(self,rows):
'''Parse the list of source table rows. Each row item in the returned
list contains a list of cell data elements.'''
result = []
for row in rows:
data = []
start = 0
for c in self.columns:
end = start + c.rulerwidth
if c is self.columns[-1]:
# Text in last column can continue forever.
data.append(string.strip(row[start:]))
else:
data.append(string.strip(row[start:end]))
start = end
result.append(data)
return result
def parse_csv(self,rows):
'''Parse the list of source table rows. Each row item in the returned
list contains a list of cell data elements.'''
import StringIO
import csv
result = []
rdr = csv.reader(StringIO.StringIO(string.join(rows,'\r\n')),
skipinitialspace=True)
try:
for row in rdr:
result.append(row)
except:
raise EAsciiDoc,'csv parse error "%s"' % (row,)
return result
def parse_dsv(self,rows):
'''Parse the list of source table rows. Each row item in the returned
list contains a list of cell data elements.'''
separator = self.dict.get('separator',':')
separator = eval('"'+separator+'"')
if len(separator) != 1:
raise EAsciiDoc,'malformed dsv separator: %s' % (separator,)
# TODO If separator is preceeded by an odd number of backslashes then
# it is escaped and should not delimit.
result = []
for row in rows:
# Skip blank lines
if row == '': continue
# Unescape escaped characters.
row = eval('"'+string.replace(row,'"','\\"')+'"')
data = string.split(row,separator)
result.append(data)
return result
def translate(self):
# Reset instance specific properties.
self.underline = None
self.columns = []
self.dict = {}
BlockTitle.consume(self.dict)
# Add relevant globals to table substitutions.
self.dict['pagewidth'] = str(config.pagewidth)
self.dict['pageunits'] = config.pageunits
# Save overridable table parameters.
save_subs = self.subs
save_format = self.format
# Parse table ruler.
ruler = reader.read()
assert re.match(self.delimiter,ruler)
self.parse_ruler(ruler)
# Parse table attributes list.
self.parse_attrs()
# Read the entire table.
table = []
while True:
line = reader.read_next()
# Table terminated by underline followed by a blank line or EOF.
if len(table) > 0 and re.match(self.underline,table[-1]):
if line in ('',None):
break;
if line is None:
raise EAsciiDoc,'closing [%s] underline expected' % (self.name,)
table.append(reader.read())
if self.check_msg: # Skip if table definition was marked invalid.
warning('skipping %s table: %s' % (self.name,self.check_msg))
return
# Generate colwidths and colspecs.
self.build_colspecs()
# Generate headrows, footrows, bodyrows.
headrows = footrows = []
bodyrows,table = self.split_rows(table)
if table:
headrows = bodyrows
bodyrows,table = self.split_rows(table)
if table:
footrows,table = self.split_rows(table)
if headrows:
headrows = self.parse_rows(headrows, self.headrow, self.headdata)
self.dict['headrows'] = string.join(headrows,writer.newline)
if footrows:
footrows = self.parse_rows(footrows, self.footrow, self.footdata)
self.dict['footrows'] = string.join(footrows,writer.newline)
bodyrows = self.parse_rows(bodyrows, self.bodyrow, self.bodydata)
self.dict['bodyrows'] = string.join(bodyrows,writer.newline)
table = subs_attrs(config.sections[self.template],self.dict)
writer.write(table)
# Restore overridable table parameters.
self.subs = save_subs
self.format = save_format
class Macros:
def __init__(self):
self.macros = [] # List of Macros.
self.current = None # The last matched block macro.
def load(self,entries):
for entry in entries:
m = Macro()
m.load(entry)
if m.name is None:
# Delete undefined macro.
for i in range(len(self.macros)-1,-1,-1):
if self.macros[i].pattern == m.pattern:
del self.macros[i]
else:
# Check for duplicates.
for m2 in self.macros:
if m.equals(m2):
verbose('duplicate macro: '+entry)
break
else:
self.macros.append(m)
def dump(self):
write = lambda s: sys.stdout.write('%s%s' % (s,writer.newline))
write('[macros]')
for m in self.macros:
write('%s=%s%s' % (m.pattern,m.prefix,m.name))
write('')
def check(self):
# Check all named sections exist.
if config.verbose:
for m in self.macros:
if m.name and m.prefix != '+':
m.section_name()
def subs(self,text,prefix='',callouts=False):
# If callouts is True then only callout macros are processed, if False
# then all non-callout macros are processed.
result = text
for m in self.macros:
if m.prefix == prefix:
if callouts ^ (m.name != 'callout'):
result = m.subs(result)
return result
def isnext(self):
'''Return matching macro if block macro is next on reader.'''
reader.skip_blank_lines()
line = reader.read_next()
if line:
for m in self.macros:
if m.prefix == '#':
if m.reo.match(line):
self.current = m
return m
return False
def match(self,prefix,name,text):
'''Return re match object matching 'text' with macro type 'prefix',
macro name 'name'.'''
for m in self.macros:
if m.prefix == prefix:
mo = m.reo.match(text)
if mo:
if m.name == name:
return mo
if re.match(name,mo.group('name')):
return mo
return None
# Macro set just prior to calling _subs_macro(). Ugly but there's no way
# to pass optional arguments with _subs_macro().
_macro = None
def _subs_macro(mo):
'''Function called to perform inline macro substitution. Uses matched macro
regular expression object and returns string containing the substituted
macro body. Called by Macros().subs().'''
# Check if macro reference is escaped.
if mo.group()[0] == '\\':
return mo.group()[1:] # Strip leading backslash.
dict = mo.groupdict()
# Delete groups that didn't participate in match.
for k,v in dict.items():
if v is None: del dict[k]
if _macro.name:
name = _macro.name
else:
if not dict.has_key('name'):
warning('missing macro name group: %s' % (mo.re.pattern,))
return ''
name = dict['name']
section_name = _macro.section_name(name)
if not section_name:
return ''
# If we're dealing with a block macro get optional block ID and block title.
if _macro.prefix == '#':
AttributeList.consume(dict)
BlockTitle.consume(dict)
# Parse macro attributes.
if dict.has_key('attrlist'):
if dict['attrlist'] in (None,''):
del dict['attrlist']
else:
parse_attrs(dict['attrlist'],dict)
if name == 'callout':
listindex =int(dict['index'])
dict['coid'] = calloutmap.add(listindex)
# It gets a bit tricky here. We've already done attribute substitution on
# the macro attribute list this means that any escaped attributes will
# have been unescaped so withhold passing them for substitution.
a0 = dict.get('0')
if a0:
dict['0'] = chr(0) # Replace temporarily with unused character.
body = config.subs_section(section_name,dict)
if len(body) == 0:
result = ''
elif len(body) == 1:
result = body[0]
else:
result = string.join(body,writer.newline)
if a0:
result = string.replace(result, chr(0), a0)
return result
class Macro:
def __init__(self):
self.pattern = None # Matching regular expression.
self.name = '' # Conf file macro name (None if implicit).
self.prefix = '' # '' if inline, '+' if system, '#' if block.
self.reo = None # Compiled pattern re object.
def section_name(self,name=None):
'''Return macro markup template section name based on macro name and
prefix. Return None section not found.'''
assert self.prefix != '+'
if not name:
assert self.name
name = self.name
if self.prefix == '#':
suffix = '-blockmacro'
else:
suffix = '-inlinemacro'
if name == 'icon':
deprecated('icon macro', 'use image macro')
return name
elif name == 'graphic':
deprecated('graphic macro', 'use image macro')
return name
elif config.sections.has_key(name):
deprecated('macro section name: ['+name+']',
'renamed to ['+name+suffix+']')
return name
elif config.sections.has_key(name+suffix):
return name+suffix
else:
warning('missing macro section: [%s]' % (name+suffix,))
return None
def equals(self,m):
if self.pattern != m.pattern:
return False
if self.name != m.name:
return False
if self.prefix != m.prefix:
return False
return True
def load(self,entry):
e = parse_entry(entry)
if not e:
raise EAsciiDoc,'malformed macro entry "%s"' % (entry,)
self.pattern, self.name = e
if not is_regexp(self.pattern):
raise EAsciiDoc,'illegal regular expression in macro entry "%s"' \
% (entry,)
self.reo = re.compile(self.pattern)
if self.name:
if self.name[0] in ('+','#'):
self.prefix, self.name = self.name[0], self.name[1:]
if self.name and not is_name(self.name):
raise EAsciiDoc,'illegal section name in macro entry "%s"' % \
(entry,)
def subs(self,text):
global _macro
_macro = self # Pass the macro to _subs_macro().
return self.reo.sub(_subs_macro,text)
def translate(self):
assert self.prefix == '#'
s = self.subs(reader.read())
if s:
writer.write(s)
class CalloutMap:
def __init__(self):
self.comap = {} # key = list index, value = callouts list.
self.calloutindex = 0 # Current callout index number.
self.listnumber = 1 # Current callout list number.
def listclose(self):
# Called when callout list is closed.
self.listnumber += 1
self.calloutindex = 0
self.comap = {}
def add(self,listindex):
# Add next callout index to listindex map entry. Return the callout id.
self.calloutindex += 1
# Append the coindex to a list in the comap dictionary.
if not self.comap.has_key(listindex):
self.comap[listindex] = [self.calloutindex]
else:
self.comap[listindex].append(self.calloutindex)
return self.calloutid(self.listnumber, self.calloutindex)
def calloutid(listnumber,calloutindex):
return 'CO%d-%d' % (listnumber,calloutindex)
calloutid = staticmethod(calloutid)
def calloutids(self,listindex):
# Retieve list of callout indexes that refer to listindex.
if self.comap.has_key(listindex):
result = ''
for coindex in self.comap[listindex]:
result += ' ' + self.calloutid(self.listnumber,coindex)
return result.strip()
else:
error('no callouts refer to list item '+str(listindex))
return ''
def check(self,maxlistindex):
# Check that all list indexes referenced by callouts exist.
for listindex in self.comap.keys():
if listindex > maxlistindex:
warning('callout refers to non-existent list item '
+ str(listindex))
#---------------------------------------------------------------------------
# Input stream Reader and output stream writer classes.
#---------------------------------------------------------------------------
class Reader1:
'''Line oriented AsciiDoc input file reader. Processes non lexical
entities: transparently handles included files. Tabs are expanded and lines
are right trimmed.'''
# This class is not used directly, use Reader class instead.
READ_BUFFER_MIN = 10 # Read buffer low level.
def __init__(self):
self.f = None # Input file object.
self.fname = None # Input file name.
self.next = [] # Read ahead buffer containing
# [filename,linenumber,linetext] lists.
self.cursor = None # Last read() [filename,linenumber,linetext].
self.tabsize = 8 # Tab expansion number of spaces.
self.parent = None # Included reader's parent reader.
self._lineno = 0 # The last line read from file object f.
self.include_enabled = True # Enables/disables file inclusion.
self.include_depth = 0 # Current include depth.
self.include_max = 5 # Maxiumum allowed include depth.
def open(self,fname):
self.fname = fname
verbose('reading: '+fname)
if fname == '<stdin>':
self.f = sys.stdin
else:
self.f = open(fname,"rb")
self._lineno = 0 # The last line read from file object f.
self.next = []
# Prefill buffer by reading the first line and then pushing it back.
if Reader1.read(self):
self.unread(self.cursor)
self.cursor = None
def closefile(self):
'''Used by class methods to close nested include files.'''
self.f.close()
self.next = []
def close(self):
self.closefile()
self.__init__()
def read(self):
'''Read next line. Return None if EOF. Expand tabs. Strip trailing
white space. Maintain self.next read ahead buffer.'''
# Top up buffer.
if len(self.next) <= self.READ_BUFFER_MIN:
s = self.f.readline()
if s:
self._lineno = self._lineno + 1
while s:
if self.tabsize != 0:
s = string.expandtabs(s,self.tabsize)
s = string.rstrip(s)
self.next.append([self.fname,self._lineno,s])
if len(self.next) > self.READ_BUFFER_MIN:
break
s = self.f.readline()
if s:
self._lineno = self._lineno + 1
# Return first (oldest) buffer entry.
if len(self.next) > 0:
self.cursor = self.next[0]
del self.next[0]
result = self.cursor[2]
# Check for include macro.
mo = macros.match('+',r'include[1]?',result)
if mo and self.include_enabled:
# Perform attribute substitution on inlcude macro.
fname = subs_attrs(mo.group('target'))
# If undefined attribute then skip to next line of input.
if not fname:
return Reader1.read(self)
if self.include_depth >= self.include_max:
raise EAsciiDoc,'maxiumum inlude depth exceeded'
if not os.path.isabs(fname) and self.fname != '<stdin>':
# Include files are relative to parent document directory.
fname = os.path.join(os.path.dirname(self.fname),fname)
if self.fname != '<stdin>' and not os.path.isfile(fname):
raise EAsciiDoc,'include file "%s" not found' % (fname,)
# Parse include macro attributes.
attrs = {}
parse_attrs(mo.group('attrlist'),attrs)
# Clone self and set as parent (self assumes the role of child).
parent = Reader1()
assign(parent,self)
self.parent = parent
if attrs.has_key('tabsize'):
self.tabsize = int(validate(attrs['tabsize'],'int($)>=0', \
'illegal include macro tabsize argument'))
# The include1 variant does not allow nested includes.
if mo.group('name') == 'include1':
self.include_enabled = False
self.open(fname)
self.include_depth = self.include_depth + 1
result = Reader1.read(self)
else:
if not Reader1.eof(self):
result = Reader1.read(self)
else:
result = None
return result
def eof(self):
'''Returns True if all lines have been read.'''
if len(self.next) == 0:
# End of current file.
if self.parent:
self.closefile()
assign(self,self.parent) # Restore parent reader.
return Reader1.eof(self)
else:
return True
else:
return False
def read_next(self):
'''Like read() but does not advance file pointer.'''
if Reader1.eof(self):
return None
else:
return self.next[0][2]
def unread(self,cursor):
'''Push the line (filename,linenumber,linetext) tuple back into the read
buffer. Note that it's up to the caller to restore the previous
cursor.'''
assert cursor
self.next.insert(0,cursor)
class Reader(Reader1):
''' Wraps (well, sought of) Reader1 class and implements conditional text
inclusion.'''
def __init__(self):
Reader1.__init__(self)
self.depth = 0 # if nesting depth.
self.skip = False # true if we're skipping ifdef...endif.
self.skipname = '' # Name of current endif macro target.
self.skipto = -1 # The depth at which skipping is reenabled.
def read_super(self):
result = Reader1.read(self)
if result is None and self.skip:
raise EAsciiDoc,'missing endif::%s[]' %(self.skipname,)
return result
def read(self):
result = self.read_super()
if result is None:
return None
while self.skip:
mo = macros.match('+',r'ifdef|ifndef|endif',result)
if mo:
name = mo.group('name')
target = mo.group('target')
if name == 'endif':
self.depth = self.depth-1
if self.depth < 0:
raise EAsciiDoc,'"%s" is mismatched' % (result,)
if self.depth == self.skipto:
self.skip = False
if target and self.skipname != target:
raise EAsciiDoc,'"%s" is mismatched' % (result,)
else: # ifdef or ifndef.
if not target:
raise EAsciiDoc,'"%s" missing macro target' % (result,)
self.depth = self.depth+1
result = self.read_super()
if result is None:
return None
mo = macros.match('+',r'ifdef|ifndef|endif',result)
if mo:
name = mo.group('name')
target = mo.group('target')
if name == 'endif':
self.depth = self.depth-1
else: # ifdef or ifndef.
if not target:
raise EAsciiDoc,'"%s" missing macro target' % (result,)
defined = document.attributes.get(target) is not None
if name == 'ifdef':
self.skip = not defined
else: # ifndef.
self.skip = defined
if self.skip:
self.skipto = self.depth
self.skipname = target
self.depth = self.depth+1
result = self.read()
if result:
# Expand executable block macros.
mo = macros.match('+',r'eval|sys|sys2',result)
if mo:
action = mo.group('name')
cmd = mo.group('attrlist')
s = system(action, cmd, is_macro=True)
if s is not None:
self.cursor[2] = s # So we don't re-evaluate.
result = s
return result
def eof(self):
return self.read_next() is None
def read_next(self):
save_cursor = self.cursor
result = self.read()
if result is not None:
self.unread(self.cursor)
self.cursor = save_cursor
return result
def read_all(self,fname):
'''Read all lines from file fname and return as list. Use like class
method: Reader().read_all(fname)'''
result = []
self.open(fname)
try:
while not self.eof():
result.append(self.read())
finally:
self.close()
return result
def read_lines(self,count=1):
'''Return tuple containing count lines.'''
result = []
i = 0
while i < count and not self.eof():
result.append(self.read())
return tuple(result)
def read_ahead(self,count=1):
'''Same as read_lines() but does not advance the file pointer.'''
result = []
putback = []
save_cursor = self.cursor
try:
i = 0
while i < count and not self.eof():
result.append(self.read())
putback.append(self.cursor)
i = i+1
while putback:
self.unread(putback.pop())
finally:
self.cursor = save_cursor
return tuple(result)
def skip_blank_lines(self):
reader.read_until(r'\s*\S+')
def read_until(self,pattern,same_file=False):
'''Like read() but reads lines up to (but not including) the first line
that matches the pattern regular expression. If same_file is True
then the terminating pattern must occur in the file the was being read
when the routine was called.'''
if same_file:
fname = self.cursor[0]
result = []
reo = re.compile(pattern)
while not self.eof():
save_cursor = self.cursor
s = self.read()
if (not same_file or fname == self.cursor[0]) and reo.match(s):
self.unread(self.cursor)
self.cursor = save_cursor
break
result.append(s)
return tuple(result)
def read_continuation(self):
'''Like read() but treats trailing backslash as line continuation
character.'''
s = self.read()
if s is None:
return None
result = ''
while s is not None and len(s) > 0 and s[-1] == '\\':
result = result + s[:-1]
s = self.read()
if s is not None:
result = result + s
return result
def parse_arguments(self,dict,default_arg=None):
'''If an arguments line is in the reader parse it to dict.'''
# DEPRECATED: This routine -- deprecated delimited block and table arguments.
s = self.read_next()
if s is not None:
if s[:2] == '\\[':
# Unescape next line.
save_cursor = self.cursor
self.read()
self.cursor = self.cursor[0:2] + (s[1:],)
self.unread(self.cursor)
self.cursor = save_cursor
elif re.match(r'^\[.*[\\\]]$',s):
s = self.read_continuation()
if not re.match(r'^\[.*\]$',s):
warning('malformed arguments line')
else:
deprecated('delimited block and table arguments line',
'use attribute lists')
parse_attrs(s[1:-1],dict,default_arg)
class Writer:
'''Writes lines to output file.'''
newline = '\r\n' # End of line terminator.
f = None # Output file object.
fname= None # Output file name.
lines_out = 0 # Number of lines written.
def open(self,fname):
self.fname = fname
verbose('writing: '+fname)
if fname == '<stdout>':
self.f = sys.stdout
else:
self.f = open(fname,"wb+")
self.lines_out = 0
def close(self,):
if self.fname != '<stdout>':
self.f.close()
def write(self,*args):
'''Iterates arguments, writes tuple and list arguments one line per
element, else writes argument as single line. If no arguments writes
blank line. self.newline is appended to each line.'''
if len(args) == 0:
self.f.write(self.newline)
self.lines_out = self.lines_out + 1
else:
for arg in args:
if type(arg) in (TupleType,ListType):
for s in arg:
self.f.write(s+self.newline)
self.lines_out = self.lines_out + len(arg)
else:
self.f.write(arg+self.newline)
self.lines_out = self.lines_out + 1
def write_tag(self,tagname,content,subs=SUBS_DEFAULT,dict=None):
'''Write content enveloped by configuration file tag tagname.
Substitutions specified in the 'subs' list are perform on the
'content'.'''
stag,etag = config.tag(tagname,dict)
self.write(stag,Lex.subs(content,subs),etag)
#---------------------------------------------------------------------------
# Configuration file processing.
#---------------------------------------------------------------------------
def _subs_specialwords(mo):
'''Special word substitution function called by
Config.subs_specialwords().'''
word = mo.re.pattern # The special word.
macro = config.specialwords[word] # The corresponding inline macro.
if not config.sections.has_key(macro):
raise EAsciiDoc,'missing special word macro [%s]' % (macro,)
args = {}
args['words'] = mo.group() # The full match string is argument 'words'.
args.update(mo.groupdict()) # Add named match groups to the arguments.
# Delete groups that didn't participate in match.
for k,v in args.items():
if v is None: del args[k]
lines = subs_attrs(config.sections[macro],args)
if len(lines) == 0:
result = ''
elif len(lines) == 1:
result = lines[0]
else:
result = string.join(lines,writer.newline)
return result
class Config:
'''Methods to process configuration files.'''
# Predefined section name regexp's.
# DEPRECATED: 'glossary'
SPECIAL_SECTIONS= ('tags','miscellaneous','attributes','glossary','specialcharacters',
'specialwords','macros','replacements','quotes','titles',
r'paradef.+',r'listdef.+',r'blockdef.+',r'tabledef.*')
def __init__(self):
self.sections = OrderedDict() # Keyed by section name containing
# lists of section lines.
# Command-line options.
self.verbose = False
self.suppress_headers = False # -s option.
# [miscellaneous] section.
self.tabsize = 8
self.textwidth = 70
self.newline = '\r\n'
self.pagewidth = None
self.pageunits = None
self.outfilesuffix = ''
self.tags = {} # Values contain (stag,etag) tuples.
self.specialchars = {} # Values of special character substitutions.
self.specialwords = {} # Name is special word pattern, value is macro.
self.replacements = {} # Key is find pattern, value is replace pattern.
self.specialsections = {} # Name is special section name pattern, value
# is corresponding section name.
self.quotes = {} # Values contain corresponding tag name.
self.fname = '' # Most recently loaded configuration file name.
self.conf_attrs = {} # Glossary entries from conf files.
self.cmd_attrs = {} # Attributes from command-line -a options.
self.loaded = [] # Loaded conf files.
def load(self,fname,dir=None):
'''Loads sections dictionary with sections from file fname.
Existing sections are overlaid. Silently skips missing configuration
files.'''
if dir:
fname = os.path.join(dir, fname)
# Sliently skip missing configuration file.
if not os.path.isfile(fname):
return
# Don't load conf files twice (local and application conf files are the
# same if the source file is in the application directory).
if realpath(fname) in self.loaded:
return
rdr = Reader() # Use instead of file so we can use include:[] macro.
rdr.open(fname)
self.fname = fname
reo = re.compile(r'^\[(?P<section>[^\W\d][\w-]*)\]\s*$')
sections = OrderedDict()
section,contents = '',[]
while not rdr.eof():
s = rdr.read()
if s and s[0] == '#': # Skip comment lines.
continue
s = string.rstrip(s)
found = reo.findall(s)
if found:
if section: # Store previous section.
if sections.has_key(section) \
and self.is_special_section(section):
# Merge line oriented special sections.
contents = sections[section] + contents
sections[section] = contents
section = string.lower(found[0])
contents = []
else:
contents.append(s)
if section and contents: # Store last section.
if sections.has_key(section) \
and self.is_special_section(section):
# Merge line oriented special sections.
contents = sections[section] + contents
sections[section] = contents
rdr.close()
# Delete blank lines from sections.
for k in sections.keys():
for i in range(len(sections[k])-1,-1,-1):
if not sections[k][i]:
del sections[k][i]
elif not self.is_special_section(k):
break # Only trailing blanks from non-special sections.
# Merge new sections.
self.sections.update(sections)
self.parse_tags()
# Internally [miscellaneous] section entries are just attributes.
dict = {}
parse_entries(sections.get('miscellaneous',()),dict,unquote=True)
update_attrs(self.conf_attrs,dict)
dict = {}
if sections.has_key('glossary'):
deprecated("[glossary] section", "rename to [attributes]")
parse_entries(sections.get('glossary',()),dict,unquote=True)
parse_entries(sections.get('attributes',()),dict,unquote=True)
update_attrs(self.conf_attrs,dict)
# Update document attributes so they are available immediately.
document.init_attrs()
dict = {}
parse_entries(sections.get('titles',()),dict)
Title.load(dict)
parse_entries(sections.get('specialcharacters',()),self.specialchars)
undefine_entries(self.specialchars)
parse_entries(sections.get('quotes',()),self.quotes,unique_values=True)
undefine_entries(self.quotes)
self.parse_specialwords()
self.parse_replacements()
self.parse_specialsections()
paragraphs.load(sections)
lists.load(sections)
blocks.load(sections)
tables.load(sections)
macros.load(sections.get('macros',()))
self.loaded.append(realpath(fname))
def load_all(self,dir):
'''Load the standard configuration files from directory 'dir'.'''
self.load('asciidoc.conf',dir)
conf = document.backend + '.conf'
self.load(conf,dir)
conf = document.backend + '-' + document.doctype + '.conf'
self.load(conf,dir)
# Load ./filters/*.conf files if they exist.
filters = os.path.join(dir,'filters')
if os.path.isdir(filters):
for f in os.listdir(filters):
if re.match(r'^.+\.conf$',f):
self.load(f,filters)
def load_miscellaneous(self,dict):
'''Set miscellaneous configuration entries from dictionary 'dict'.'''
def set_misc(name,rule='True',intval=False):
if dict.has_key(name):
errmsg = 'illegal [miscellaneous] %s entry' % name
if intval:
setattr(self, name, int(validate(dict[name],rule,errmsg)))
else:
setattr(self, name, validate(dict[name],rule,errmsg))
set_misc('tabsize','int($)>0',intval=True)
set_misc('textwidth','int($)>0',intval=True)
set_misc('pagewidth','int($)>0',intval=True)
set_misc('pageunits')
set_misc('outfilesuffix')
if dict.has_key('newline'):
# Convert escape sequences to their character values.
self.newline = eval('"'+dict['newline']+'"')
def check(self):
'''Check the configuration for internal consistancy. Called after all
configuration files have been loaded.'''
# Heuristic check that at least one configuration file was loaded.
if not self.specialchars or not self.tags or not lists:
raise EAsciiDoc,'incomplete configuration files'
# Check special characters are only one character long.
for k in self.specialchars.keys():
if len(k) != 1:
raise EAsciiDoc,'[specialcharacters] "%s" ' \
'must be a single character' % (k,)
# Check all special words have a corresponding inline macro body.
for macro in self.specialwords.values():
if not is_name(macro):
raise EAsciiDoc,'illegal "%s" special word name' % (macro,)
if not self.sections.has_key(macro):
warning('missing special word macro [%s]' % (macro,))
# Check all text quotes have a corresponding tag.
for q in self.quotes.keys():
tag = self.quotes[q]
if not self.tags.has_key(tag):
warning('[quotes] %s missing "%s" tag definition'
% (q,tag))
# Check all specialsections section names exist.
for k,v in self.specialsections.items():
if not self.sections.has_key(v):
warning('[%s] missing specialsections section' % (v,))
paragraphs.check()
lists.check()
blocks.check()
tables.check()
macros.check()
def is_special_section(self,section_name):
for name in self.SPECIAL_SECTIONS:
if re.match(name,section_name):
return True
return False
def dump(self):
'''Dump configuration to stdout.'''
# Header.
hdr = ''
hdr = hdr + '#' + writer.newline
hdr = hdr + '# Generated by AsciiDoc %s for %s %s.%s' % \
(VERSION,document.backend,document.doctype,writer.newline)
t = time.asctime(time.localtime(time.time()))
hdr = hdr + '# %s%s' % (t,writer.newline)
hdr = hdr + '#' + writer.newline
sys.stdout.write(hdr)
# Dump special sections.
# Dump only the configuration file and command-line attributes.
# [miscellanous] entries are dumped as part of the [attributes].
dict = {}
dict.update(self.conf_attrs)
dict.update(self.cmd_attrs)
dump_section('attributes',dict)
Title.dump()
dump_section('quotes',self.quotes)
dump_section('specialcharacters',self.specialchars)
dict = {}
for k,v in self.specialwords.items():
if dict.has_key(v):
dict[v] = '%s "%s"' % (dict[v],k) # Append word list.
else:
dict[v] = '"%s"' % (k,)
dump_section('specialwords',dict)
dump_section('replacements',self.replacements)
dump_section('specialsections',self.specialsections)
dict = {}
for k,v in self.tags.items():
dict[k] = '%s|%s' % v
dump_section('tags',dict)
paragraphs.dump()
lists.dump()
blocks.dump()
tables.dump()
macros.dump()
# Dump remaining sections.
for k in self.sections.keys():
if not self.is_special_section(k):
sys.stdout.write('[%s]%s' % (k,writer.newline))
for line in self.sections[k]:
sys.stdout.write('%s%s' % (line,writer.newline))
sys.stdout.write(writer.newline)
def subs_section(self,section,dict):
'''Section attribute substitution using attributes from
document.attributes and 'dict'. Lines containing undefinded
attributes are deleted.'''
if self.sections.has_key(section):
return subs_attrs(self.sections[section],dict)
else:
warning('missing [%s] section' % (section,))
return ()
def parse_tags(self):
'''Parse [tags] section entries into self.tags dictionary.'''
dict = {}
parse_entries(self.sections.get('tags',()),dict)
for k,v in dict.items():
if not is_name(k):
raise EAsciiDoc,'[tag] %s malformed' % (k,)
if v is None:
if self.tags.has_key(k):
del self.tags[k]
elif v == 'none':
self.tags[k] = (None,None)
else:
mo = re.match(r'(?P<stag>.*)\|(?P<etag>.*)',v)
if mo:
self.tags[k] = (mo.group('stag'), mo.group('etag'))
else:
raise EAsciiDoc,'[tag] %s value malformed' % (k,)
def tag(self, name, dict=None):
'''Returns (starttag,endtag) tuple named name from configuration file
[tags] section. Raise error if not found. If a dictionary 'dict' is
passed then merge with document attributes and perform attribute
substitution on tags.'''
# TODO: Tags should be stored a single string, not split into start
# and end tags since most are going to be substituted anyway (see
# subs_tag() for how we should process them. parse_tags() (above)
# should only check i.e. parse_check(). This routine should be renamed
# split_tag() and would call subs_tag(). self.tags dictionary values
# would be strings not tuples.
if not self.tags.has_key(name):
raise EAsciiDoc, 'missing tag "%s"' % (name,)
stag,etag = self.tags[name]
if dict is not None:
# TODO: Should we warn if substitution drops a tag?
if stag:
stag = subs_attrs(stag,dict)
if etag:
etag = subs_attrs(etag,dict)
return (stag,etag)
def parse_specialsections(self):
'''Parse specialsections section to self.specialsections dictionary.'''
# TODO: This is virtually the same as parse_replacements() and should
# be factored to single routine.
dict = {}
parse_entries(self.sections.get('specialsections',()),dict,unquote=True)
for pat,sectname in dict.items():
pat = strip_quotes(pat)
if not is_regexp(pat):
raise EAsciiDoc,'[specialsections] entry "%s" ' \
'is not a valid regular expression' % (pat,)
if sectname is None:
if self.specialsections.has_key(pat):
del self.specialsections[pat]
else:
self.specialsections[pat] = sectname
def parse_replacements(self):
'''Parse replacements section into self.replacements dictionary.'''
dict = {}
#TODO: Deprecate
if self.sections.has_key('substitutions'):
parse_entries(self.sections.get('substitutions',()), dict,
unquote=True)
deprecated('[substitutions]', 'renamed [replacements]', False)
else:
parse_entries(self.sections.get('replacements',()), dict,
unquote=True)
for pat,rep in dict.items():
# The search pattern and the replacement are regular expressions so
# check them both.
pat = strip_quotes(pat)
if not is_regexp(pat):
raise EAsciiDoc,'"%s" ([replacements] entry in %s) ' \
'is not a valid regular expression' % (pat,self.fname)
if rep is None:
if self.replacements.has_key(pat):
del self.replacements[pat]
else:
rep = strip_quotes(rep)
if not is_regexp(pat):
raise EAsciiDoc,'[replacements] entry "%s=%s" in %s ' \
'is an invalid find regular expression combination' \
% (pat,rep,self.fname)
self.replacements[pat] = rep
def subs_replacements(self,s):
'''Substitute patterns from self.replacements in 's'.'''
result = s
for pat,rep in self.replacements.items():
result = re.sub(pat, rep, result)
return result
def parse_specialwords(self):
'''Parse special words section into self.specialwords dictionary.'''
reo = re.compile(r'(?:\s|^)(".+?"|[^"\s]+)(?=\s|$)')
for line in self.sections.get('specialwords',()):
e = parse_entry(line)
if not e:
raise EAsciiDoc,'[specialwords] entry "%s" in %s is malformed' \
% (line,self.fname)
name,wordlist = e
if not is_name(name):
raise EAsciiDoc,'[specialwords] name "%s" in %s is illegal' \
% (name,self.fname)
if wordlist is None:
# Undefine all words associated with 'name'.
for k,v in self.specialwords.items():
if v == name:
del self.specialwords[k]
else:
words = reo.findall(wordlist)
for word in words:
word = strip_quotes(word)
if not is_regexp(word):
raise EAsciiDoc,'"%s" (%s [specialwords] entry in %s)' \
'is not a valid regular expression' \
% (word,name,self.fname)
self.specialwords[word] = name
def subs_specialchars(self,s):
'''Perform special character substitution on string 's'.'''
'''It may seem like a good idea to escape special characters with a '\'
character, the reason we don't is because the escape character itself
then has to be escaped and this makes including code listings
problematic. Use the predefined {amp},{lt},{gt} attributes instead.'''
result = ''
for ch in s:
result = result + self.specialchars.get(ch,ch)
return result
def subs_specialwords(self,s):
'''Search for word patterns from self.specialwords in 's' and
substitute using corresponding macro.'''
result = s
for word in self.specialwords.keys():
result = re.sub(word, _subs_specialwords, result)
return result
def section2tags(self,section,dict={}):
'''Perform attribute substitution on 'section' using document
attributes plus 'dict' attributes. Return tuple (stag,etag) containing
pre and post | placeholder tags.'''
if self.sections.has_key(section):
body = self.sections[section]
else:
warning('missing [%s] section' % (section,))
body = ()
# Split macro body into start and end tag lists.
stag = []
etag = []
in_stag = True
for s in body:
if in_stag:
mo = re.match(r'(?P<stag>.*)\|(?P<etag>.*)',s)
if mo:
if mo.group('stag'):
stag.append(mo.group('stag'))
if mo.group('etag'):
etag.append(mo.group('etag'))
in_stag = False
else:
stag.append(s)
else:
etag.append(s)
# Do attribute substitution last so {brkbar} can be used to escape |.
stag = subs_attrs(stag,dict)
etag = subs_attrs(etag,dict)
return (stag,etag)
#---------------------------------------------------------------------------
# Application code.
#---------------------------------------------------------------------------
# Constants
# ---------
APP_DIR = None # This file's directory.
USER_DIR = None # ~/.asciidoc
GLOBAL_CONFIG_DIR = "/etc/asciidoc"
# Globals
# -------
document = Document() # The document being processed.
config = Config() # Configuration file reader.
reader = Reader() # Input stream line reader.
writer = Writer() # Output stream line writer.
paragraphs = Paragraphs() # Paragraph definitions.
lists = Lists() # List definitions.
blocks = DelimitedBlocks() # DelimitedBlock definitions.
tables = Tables() # Table definitions.
macros = Macros() # Macro definitions.
calloutmap = CalloutMap() # Coordinates callouts and callout list.
def asciidoc(backend, doctype, confiles, infile, outfile, options):
'''Convert AsciiDoc document to DocBook document of type doctype
The AsciiDoc document is read from file object src the translated
DocBook file written to file object dst.'''
try:
if doctype not in ('article','manpage','book'):
raise EAsciiDoc,'illegal document type'
if backend == 'linuxdoc' and doctype != 'article':
raise EAsciiDoc,'%s %s documents are not supported' \
% (backend,doctype)
document.backend = backend
if not os.path.exists(os.path.join(APP_DIR, backend+'.conf')) and not \
os.path.exists(os.path.join(GLOBAL_CONFIG_DIR, backend+'.conf')):
warning('non-standard %s backend' % backend, linenos=False)
document.doctype = doctype
document.infile = infile
document.init_attrs()
# Set processing options.
for o in options:
if o == '-s': config.suppress_headers = True
if o == '-v': config.verbose = True
# Check the infile exists.
if infile != '<stdin>' and not os.path.isfile(infile):
raise EAsciiDoc,'input file %s missing' % (infile,)
if '-e' not in options:
# Load global configuration from system configuration directory.
config.load_all(GLOBAL_CONFIG_DIR)
# Load global configuration files from asciidoc directory.
config.load_all(APP_DIR)
# Load configuration files from ~/.asciidoc if it exists.
if USER_DIR is not None:
config.load_all(USER_DIR)
# Load configuration files from document directory.
config.load_all(os.path.dirname(infile))
if infile != '<stdin>':
# Load implicit document specific configuration files if they exist.
config.load(os.path.splitext(infile)[0] + '.conf')
config.load(os.path.splitext(infile)[0] + '-' + backend + '.conf')
# If user specified configuration file(s) overlay the defaults.
if confiles:
for conf in confiles:
# First look in current working directory.
if os.path.isfile(conf):
config.load(conf)
else:
raise EAsciiDoc,'configuration file %s missing' % (conf,)
document.init_attrs() # Add conf file.
# Check configuration for consistency.
config.check()
# Build outfile name now all conf files have been read.
if outfile is None:
outfile = os.path.splitext(infile)[0] + '.' + backend
if config.outfilesuffix:
# Change file extension.
outfile = os.path.splitext(outfile)[0] + config.outfilesuffix
document.outfile = outfile
if '-c' in options:
config.dump()
else:
reader.tabsize = config.tabsize
reader.open(infile)
try:
writer.newline = config.newline
writer.open(outfile)
try:
document.init_attrs() # Add file name related entries.
document.translate()
finally:
writer.close()
finally:
reader.closefile() # Keep reader state for postmortem.
except (KeyboardInterrupt, SystemExit):
print
except Exception,e:
# Cleanup.
if outfile and outfile != '<stdout>' and os.path.isfile(outfile):
os.unlink(outfile)
# Build and print error description.
msg = 'FAILED: '
if reader.cursor:
msg = msg + "%s: line %d: " % (reader.cursor[0],reader.cursor[1])
if isinstance(e,EAsciiDoc):
print_stderr(msg+str(e))
else:
print_stderr(msg+'unexpected error:')
print_stderr('-'*60)
traceback.print_exc(file=sys.stderr)
print_stderr('-'*60)
sys.exit(1)
def usage(msg=''):
if msg:
print_stderr(msg)
print_stderr('Usage: asciidoc -b backend [-d doctype] [-a attribute]')
print_stderr(' [-e] [-n] [-s] [-f configfile] [-o outfile]')
print_stderr(' [--help | -h] [--version] [-v] [ -c ]')
print_stderr(' infile')
def main():
if float(sys.version[:3]) < 2.3:
print_stderr('FAILED: Python 2.3 or better required.')
sys.exit(1)
# Locate the executable and configuration files directory.
global APP_DIR,USER_DIR
APP_DIR = os.path.dirname(realpath(sys.argv[0]))
USER_DIR = os.environ.get('HOME')
if USER_DIR is not None:
USER_DIR = os.path.join(USER_DIR,'.asciidoc')
if not os.path.isdir(USER_DIR):
USER_DIR = None
# Process command line options.
import getopt
# DEPRECATED: 'g:' option.
opts,args = getopt.getopt(sys.argv[1:],
'a:b:cd:ef:g:hno:svw:',
['help','profile','version'])
if len(args) > 1:
usage()
sys.exit(1)
backend = None
doctype = 'article'
confiles = []
outfile = None
options = []
prof = False
for o,v in opts:
if o in ('--help','-h'):
print __doc__
sys.exit(0)
if o == '--profile':
prof = True
if o == '--version':
print_stderr('asciidoc %s' % (VERSION,))
sys.exit(0)
if o == '-b': backend = v
if o == '-c': options.append('-c')
if o == '-d': doctype = v
if o == '-e': options.append('-e')
if o == '-f': confiles.append(v)
if o == '-n':
o = '-a'
v = 'section-numbers'
if o == '-a' or o == '-g':
if o == '-g':
deprecated("-g command option", "use -a instead")
e = parse_entry(v)
if not e:
usage('Illegal -a %s option' % (v,))
sys.exit(1)
k,v = e
if v is None:
if k[0] == '^':
k = k[1:]
else:
v = ''
config.cmd_attrs[k] = v
if o == '-o':
if v == '-':
outfile = '<stdout>'
else:
outfile = v
if o == '-n': outfile = v
if o == '-s': options.append('-s')
if o == '-v': options.append('-v')
if len(args) == 0 and len(opts) == 0:
usage()
sys.exit(1)
if len(args) == 0:
usage('No source file specified')
sys.exit(1)
if not backend:
usage('No backend (-b) option specified')
sys.exit(1)
if args[0] == '-':
infile = '<stdin>'
else:
infile = args[0]
if infile == '<stdin>' and not outfile:
outfile = '<stdout>'
# Convert in and out files to absolute paths.
if infile != '<stdin>': infile = os.path.abspath(infile)
if outfile and outfile != '<stdout>': outfile = os.path.abspath(outfile)
# Do the work.
if prof:
import profile
profile.run("asciidoc('%s','%s',(),'%s',None,())"
% (backend,doctype,infile))
else:
asciidoc(backend, doctype, confiles, infile, outfile, options)
if document.invalid:
sys.exit(1)
if __name__ == "__main__":
try:
main()
except (KeyboardInterrupt, SystemExit):
pass
except:
print_stderr("%s: unexpected exit status: %s" %
(os.path.basename(sys.argv[0]), sys.exc_info()[1]))
# Exit with previous sys.exit() status or zero if no sys.exit().
sys.exit(sys.exc_info()[1])
|