package gapi-ocaml
A simple OCaml client for Google Services
Install
Dune Dependency
Authors
Maintainers
Sources
v0.4.6.tar.gz
sha256=b84b680528a5e050014103a8e7a60a5d43efd5fefc3f838310bd46769775ab48
md5=8ee26acf1f6c6f5e24c7b57fa070a0a2
doc/src/gapi-ocaml.netstring-local/netconversion.ml.html
Source file netconversion.ml
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929(* $Id$ * ---------------------------------------------------------------------- *) open Netsys_types open Netaux.ArrayAux exception Malformed_code exception Cannot_represent of int let multibyte_limit = (* 6 *) 50;; (* The longest multibyte character of all supported encodings, * and the longest substitution string. *) let big_slice = (* 3 *) 250;; (* The typical length of slices *) (* Seems to be a good source: ftp://dkuug.dk/i18n/charmaps *) type encoding = [ `Enc_utf8 (* UTF-8 *) | `Enc_utf8_opt_bom | `Enc_java | `Enc_utf16 (* UTF-16 with unspecified endianess (restricted usage) *) | `Enc_utf16_le (* UTF-16 little endian *) | `Enc_utf16_be (* UTF-16 big endian *) | `Enc_utf32 (* UTF-32 with unspecified endianess (restricted usage) *) | `Enc_utf32_le (* UTF-32 little endian *) | `Enc_utf32_be (* UTF-32 big endian *) | `Enc_usascii (* US-ASCII (only 7 bit) *) | `Enc_iso88591 (* ISO-8859-1 *) | `Enc_iso88592 (* ISO-8859-2 *) | `Enc_iso88593 (* ISO-8859-3 *) | `Enc_iso88594 (* ISO-8859-4 *) | `Enc_iso88595 (* ISO-8859-5 *) | `Enc_iso88596 (* ISO-8859-6 *) | `Enc_iso88597 (* ISO-8859-7 *) | `Enc_iso88598 (* ISO-8859-8 *) | `Enc_iso88599 (* ISO-8859-9 *) | `Enc_iso885910 (* ISO-8859-10 *) | `Enc_iso885911 (* ISO-8859-11 *) | `Enc_iso885913 (* ISO-8859-13 *) | `Enc_iso885914 (* ISO-8859-14 *) | `Enc_iso885915 (* ISO-8859-15 *) | `Enc_iso885916 (* ISO-8859-16 *) | `Enc_koi8r (* KOI8-R *) (* http://koi8.pp.ru *) (*| `Enc_koi8u (* KOI8-U *) (* http://www.net.ua/KOI8-U/index.html *)*) | `Enc_jis0201 (* JIS-X-0201 *) (* | `Enc_jis0201_roman (* JIS-X-0201 only roman half *) | `Enc_jis0201_kana (* JIS-X-0201 katakana half remapped to 0x21..XXX *) | `Enc_jis0208_94x94 (* JIS-X-0208 in ISO-2022-style two byte encoding *) | `Enc_jis0212_94x94 (* JIS-X-0212 in ISO-2022-style two byte encoding *) *) | `Enc_eucjp (* EUC-JP *) | `Enc_euckr (* EUC-KR *) (* | `Enc_iso2022 of iso2022_state | `Enc_iso2022jp of iso2022jp_state *) (* Older standards: *) | `Enc_asn1_iso646 (* only the language-neutral subset *) | `Enc_asn1_T61 (* ITU T.61 ("Teletex") *) | `Enc_asn1_printable (* Microsoft: *) | `Enc_windows1250 (* WINDOWS-1250 *) | `Enc_windows1251 (* WINDOWS-1251 *) | `Enc_windows1252 (* WINDOWS-1252 *) | `Enc_windows1253 (* WINDOWS-1253 *) | `Enc_windows1254 (* WINDOWS-1254 *) | `Enc_windows1255 (* WINDOWS-1255 *) | `Enc_windows1256 (* WINDOWS-1256 *) | `Enc_windows1257 (* WINDOWS-1257 *) | `Enc_windows1258 (* WINDOWS-1258 *) (* IBM, ASCII-based: *) | `Enc_cp437 | `Enc_cp737 | `Enc_cp775 | `Enc_cp850 | `Enc_cp852 | `Enc_cp855 | `Enc_cp856 | `Enc_cp857 | `Enc_cp860 | `Enc_cp861 | `Enc_cp862 | `Enc_cp863 | `Enc_cp864 | `Enc_cp865 | `Enc_cp866 (* Russian *) | `Enc_cp869 | `Enc_cp874 | `Enc_cp1006 (* IBM, EBCDIC-based: *) | `Enc_cp037 (* EBCDIC USA Canada *) (* 273: EBCDIC Germany, Austria, * 277: Denmark, Norway, * 278: Finland, Sweden, * 280: Italy, * 284: Spain, Latin America, * 285: United Kingdom, * 297: France, * 871: Iceland, *) | `Enc_cp424 | `Enc_cp500 (* EBCDIC International *) | `Enc_cp875 (* EBCDIC Modern Greek *) | `Enc_cp1026 (* EBCDIC Turkish *) | `Enc_cp1047 (* EBCDIC Latin1, OS 390 System Services *) (* Adobe: *) | `Enc_adobe_standard_encoding | `Enc_adobe_symbol_encoding | `Enc_adobe_zapf_dingbats_encoding (* Apple: *) | `Enc_macroman (* Encoding subset: *) | `Enc_subset of (encoding * (int -> bool)) | `Enc_empty ] ;; type charset = [ `Set_unicode (* The full Unicode repertoire *) | `Set_usascii (* US-ASCII (only 7 bit) *) | `Set_iso88591 (* ISO-8859-1 *) | `Set_iso88592 (* ISO-8859-2 *) | `Set_iso88593 (* ISO-8859-3 *) | `Set_iso88594 (* ISO-8859-4 *) | `Set_iso88595 (* ISO-8859-5 *) | `Set_iso88596 (* ISO-8859-6 *) | `Set_iso88597 (* ISO-8859-7 *) | `Set_iso88598 (* ISO-8859-8 *) | `Set_iso88599 (* ISO-8859-9 *) | `Set_iso885910 (* ISO-8859-10 *) | `Set_iso885911 (* ISO-8859-11 *) | `Set_iso885913 (* ISO-8859-13 *) | `Set_iso885914 (* ISO-8859-14 *) | `Set_iso885915 (* ISO-8859-15 *) | `Set_iso885916 (* ISO-8859-16 *) | `Set_koi8r (* KOI8-R *) | `Set_jis0201 (* JIS-X-0201 *) | `Set_jis0208 (* JIS-X-0208 *) | `Set_jis0212 (* JIS-X-0212 *) | `Set_ks1001 (* KS-X-1001 *) | `Set_asn1_iso646 | `Set_asn1_T61 | `Set_asn1_printable (* Microsoft: *) | `Set_windows1250 (* WINDOWS-1250 *) | `Set_windows1251 (* WINDOWS-1251 *) | `Set_windows1252 (* WINDOWS-1252 *) | `Set_windows1253 (* WINDOWS-1253 *) | `Set_windows1254 (* WINDOWS-1254 *) | `Set_windows1255 (* WINDOWS-1255 *) | `Set_windows1256 (* WINDOWS-1256 *) | `Set_windows1257 (* WINDOWS-1257 *) | `Set_windows1258 (* WINDOWS-1258 *) (* IBM, ASCII-based: *) | `Set_cp437 | `Set_cp737 | `Set_cp775 | `Set_cp850 | `Set_cp852 | `Set_cp855 | `Set_cp856 | `Set_cp857 | `Set_cp860 | `Set_cp861 | `Set_cp862 | `Set_cp863 | `Set_cp864 | `Set_cp865 | `Set_cp866 | `Set_cp869 | `Set_cp874 | `Set_cp1006 (* IBM, EBCDIC-based: *) | `Set_cp037 | `Set_cp424 | `Set_cp500 | `Set_cp875 | `Set_cp1026 | `Set_cp1047 (* Adobe: *) | `Set_adobe_standard_encoding | `Set_adobe_symbol_encoding | `Set_adobe_zapf_dingbats_encoding (* Apple: *) | `Set_macroman ] ;; let ascii_compat_encodings = [ `Enc_utf8; `Enc_utf8_opt_bom; `Enc_java; `Enc_usascii; `Enc_iso88591; `Enc_iso88592; `Enc_iso88593; `Enc_iso88594; `Enc_iso88595; `Enc_iso88596; `Enc_iso88597; `Enc_iso88598; `Enc_iso88599; `Enc_iso885910; `Enc_iso885911; `Enc_iso885913; `Enc_iso885914; `Enc_iso885915; `Enc_iso885916; `Enc_koi8r; `Enc_windows1250; `Enc_windows1251; `Enc_windows1252; `Enc_windows1253; `Enc_windows1254; `Enc_windows1255; `Enc_windows1256; `Enc_windows1257; `Enc_windows1258; `Enc_cp437; `Enc_cp737; `Enc_cp775; `Enc_cp850; `Enc_cp852; `Enc_cp855; `Enc_cp856; `Enc_cp857; `Enc_cp860; `Enc_cp861; `Enc_cp862; `Enc_cp863; `Enc_cp864; `Enc_cp865; `Enc_cp866; `Enc_cp869; `Enc_cp874; `Enc_cp1006; `Enc_eucjp; `Enc_euckr; `Enc_macroman; ] ;; let rec is_ascii_compatible = function | `Enc_subset(e,_) -> is_ascii_compatible e | e -> List.mem e ascii_compat_encodings ;; let rec is_single_byte = function `Enc_utf8 | `Enc_utf8_opt_bom | `Enc_java | `Enc_utf16 | `Enc_utf16_le | `Enc_utf16_be | `Enc_utf32 | `Enc_utf32_le | `Enc_utf32_be -> false | `Enc_eucjp -> false | `Enc_euckr -> false | `Enc_subset(e,_) -> is_single_byte e | _ -> true ;; let punct_re = Netstring_str.regexp "[-_.]";; let ibm_re = Netstring_str.regexp "^IBM\\([0-9]+\\)$";; let year_re = Netstring_str.regexp ":[0-9][0-9][0-9][0-9]$";; let norm_enc_name e = (* Removes some punctuation characters from e; uppercase; * converts "IBM#" to "CP#"; drops ":YEAR" suffixes *) let e1 = STRING_UPPERCASE e in let e2 = Netstring_str.global_replace punct_re "" e1 in let e3 = Netstring_str.global_replace year_re "" e2 in match Netstring_str.string_match ibm_re e3 0 with Some r -> "CP" ^ Netstring_str.matched_group r 1 e3 | None -> e3 ;; let names = (* The first name is the official name, the other are aliases. * The aliases must not contain any of the punctuation characters * - _ . * `Enc_subset is missing in this list, of course. * * http://www.iana.org/assignments/character-sets * * A good reference is also: * http://www.firstobject.com/character-set-name-alias-code-page.htm *) [ `Enc_utf16, [ "UTF-16"; "UTF16"; "UCS2"; "ISO10646UCS2" ]; `Enc_utf16_be, [ "UTF-16BE"; "UTF16BE" ]; `Enc_utf16_le, [ "UTF-16LE"; "UTF16LE" ]; `Enc_utf32, [ "UTF-32"; "UTF32"; "UCS4"; "ISO10646UCS4" ]; `Enc_utf32_be, [ "UTF-32BE"; "UTF32BE" ]; `Enc_utf32_le, [ "UTF-32LE"; "UTF32LE" ]; `Enc_utf8, [ "UTF-8"; "UTF8" ]; `Enc_utf8_opt_bom, [ "UTF-8"; "UTF8" ]; `Enc_java, [ "UTF-8-JAVA"; "UTF8JAVA"; "JAVA" ]; `Enc_usascii, [ "US-ASCII"; "USASCII"; "ASCII"; "ISO646US"; "CP367"; "ISOIR6"; "ANSIX341968" ]; `Enc_iso88591, [ "ISO-8859-1"; "ISO88591"; "LATIN1"; "CP819"; "ISOIR100" ]; `Enc_iso88592, [ "ISO-8859-2"; "ISO88592"; "LATIN2"; "ISOIR101"; "CP912" ]; `Enc_iso88593, [ "ISO-8859-3"; "ISO88593"; "LATIN3"; "ISOIR109" ]; `Enc_iso88594, [ "ISO-8859-4"; "ISO88594"; "LATIN4"; "ISOIR110" ]; `Enc_iso88595, [ "ISO-8859-5"; "ISO88595"; "CYRILLIC"; "ISOIR144"; "CP915" ]; `Enc_iso88596, [ "ISO-8859-6"; "ISO88596"; "ARABIC"; "ECMA114"; "ASMO708"; "ISOIR127"; "CP1089" ]; `Enc_iso88597, [ "ISO-8859-7"; "ISO88597"; "GREEK"; "GREEK8"; "ELOT928"; "ECMA118"; "ISOIR126"; "CP813" ]; `Enc_iso88598, [ "ISO-8859-8"; "ISO88598"; "HEBREW"; "ISOIR138"; "CP916" ]; `Enc_iso88599, [ "ISO-8859-9"; "ISO88599"; "LATIN5"; "ISOIR148"; "CP920" ]; `Enc_iso885910, [ "ISO-8859-10"; "ISO885910"; "LATIN6"; "ISOIR157" ]; `Enc_iso885911, [ "ISO-8859-11"; "ISO885911"; ]; `Enc_iso885913, [ "ISO-8859-13"; "ISO885913"; "LATIN7" ]; `Enc_iso885914, [ "ISO-8859-14"; "ISO885914"; "LATIN8"; "ISOIR199"; "ISOCELTIC" ]; `Enc_iso885915, [ "ISO-8859-15"; "ISO885915"; "LATIN9"; "ISOIR203" ]; `Enc_iso885916, [ "ISO-8859-16"; "ISO885916"; "LATIN10"; "SR14111"; "ROMANIAN"; "ISOIR226" ]; `Enc_koi8r, [ "KOI8-R"; "KOI8R"; "CP878" ]; `Enc_jis0201, [ "JIS_X0201"; "JIS0201"; "JISX0201"; "X0201" ]; `Enc_eucjp, [ "EUC-JP"; "EUCJP"; ]; `Enc_euckr, [ "EUC-KR"; "EUCKR"; ]; `Enc_windows1250, [ "WINDOWS-1250"; "WINDOWS1250" ]; `Enc_windows1251, [ "WINDOWS-1251"; "WINDOWS1251" ]; `Enc_windows1252, [ "WINDOWS-1252"; "WINDOWS1252" ]; `Enc_windows1253, [ "WINDOWS-1253"; "WINDOWS1253" ]; `Enc_windows1254, [ "WINDOWS-1254"; "WINDOWS1254" ]; `Enc_windows1255, [ "WINDOWS-1255"; "WINDOWS1255" ]; `Enc_windows1256, [ "WINDOWS-1256"; "WINDOWS1256" ]; `Enc_windows1257, [ "WINDOWS-1257"; "WINDOWS1257" ]; `Enc_windows1258, [ "WINDOWS-1258"; "WINDOWS1258" ]; `Enc_cp437, [ "IBM437"; "CP437" ]; `Enc_cp737, [ "IBM737"; "CP737" ]; `Enc_cp775, [ "IBM775"; "CP775" ]; `Enc_cp850, [ "IBM850"; "CP850" ]; `Enc_cp852, [ "IBM852"; "CP852" ]; `Enc_cp855, [ "IBM855"; "CP855" ]; `Enc_cp856, [ "IBM856"; "CP856" ]; `Enc_cp857, [ "IBM857"; "CP857" ]; `Enc_cp860, [ "IBM860"; "CP860" ]; `Enc_cp861, [ "IBM861"; "CP861"; "CPIS" ]; `Enc_cp862, [ "IBM862"; "CP862" ]; `Enc_cp863, [ "IBM863"; "CP863" ]; `Enc_cp864, [ "IBM864"; "CP864" ]; `Enc_cp865, [ "IBM865"; "CP865" ]; `Enc_cp866, [ "IBM866"; "CP866" ]; `Enc_cp869, [ "IBM869"; "CP869"; "CPGR" ]; `Enc_cp874, [ "IBM874"; "CP874" ]; `Enc_cp1006, [ "IBM1006"; "CP1006" ]; `Enc_cp037, [ "IBM037"; "CP037"; "EBCDICCPUS"; "EBCDICCPCA"; "EBCDICCPWT"; "EBCDICCPNL" ]; `Enc_cp424, [ "IBM424"; "CP424"; "EBCDICCPHE" ]; `Enc_cp500, [ "IBM500"; "CP500"; "EBCDICCPBE"; "EBCDICCPCH" ]; `Enc_cp875, [ "IBM875"; "CP875" ]; `Enc_cp1026, [ "IBM1026"; "CP1026" ]; `Enc_cp1047, [ "IBM1047"; "CP1047"; ]; `Enc_adobe_standard_encoding, [ "ADOBE-STANDARD-ENCODING"; "ADOBESTANDARDENCODING" ]; `Enc_adobe_symbol_encoding, [ "ADOBE-SYMBOL-ENCODING"; "ADOBESYMBOLENCODING" ]; `Enc_adobe_zapf_dingbats_encoding, [ "ADOBE-ZAPF-DINGBATS-ENCODING"; "ADOBEZAPFDINGBATSENCODING" ]; `Enc_macroman, [ "MACINTOSH"; "MACINTOSH"; "MACROMAN"; "MAC" ]; (* The ASN.1 encodings are intentionally not member of this list *) ] ;; let encoding_of_string e = let ne = norm_enc_name e in try fst (List.find (fun (enc, nlist) -> List.mem ne (List.tl nlist)) names ) with Not_found -> failwith "Netconversion.encoding_of_string: unknown encoding" ;; let rec string_of_encoding (e : encoding) = (* If there is a "preferred MIME name", this name is returned (see IANA). *) match e with | `Enc_subset(e,_) -> string_of_encoding e | _ -> try let l = List.assoc e names in List.hd l with Not_found -> assert false (* Because [names] must be complete *) ;; let internal_name (cs : charset) = (* The name used for netdb lookups *) match cs with | `Set_unicode -> "unicode" | `Set_usascii -> "usascii" | `Set_iso88591 -> "iso88591" | `Set_iso88592 -> "iso88592" | `Set_iso88593 -> "iso88593" | `Set_iso88594 -> "iso88594" | `Set_iso88595 -> "iso88595" | `Set_iso88596 -> "iso88596" | `Set_iso88597 -> "iso88597" | `Set_iso88598 -> "iso88598" | `Set_iso88599 -> "iso88599" | `Set_iso885910 -> "iso885910" | `Set_iso885911 -> "iso885911" | `Set_iso885913 -> "iso885913" | `Set_iso885914 -> "iso885914" | `Set_iso885915 -> "iso885915" | `Set_iso885916 -> "iso885916" | `Set_koi8r -> "koi8r" | `Set_jis0201 -> "jis0201" | `Set_jis0208 -> "jis0208" | `Set_jis0212 -> "jis0212" | `Set_ks1001 -> "ks1001" | `Set_asn1_iso646 -> "asn1_iso646" | `Set_asn1_T61 -> "asn1_t61" | `Set_asn1_printable -> "asn1_printable" | `Set_windows1250 -> "windows1250" | `Set_windows1251 -> "windows1251" | `Set_windows1252 -> "windows1252" | `Set_windows1253 -> "windows1253" | `Set_windows1254 -> "windows1254" | `Set_windows1255 -> "windows1255" | `Set_windows1256 -> "windows1256" | `Set_windows1257 -> "windows1257" | `Set_windows1258 -> "windows1258" | `Set_cp437 -> "cp437" | `Set_cp737 -> "cp737" | `Set_cp775 -> "cp775" | `Set_cp850 -> "cp850" | `Set_cp852 -> "cp852" | `Set_cp855 -> "cp855" | `Set_cp856 -> "cp856" | `Set_cp857 -> "cp857" | `Set_cp860 -> "cp860" | `Set_cp861 -> "cp861" | `Set_cp862 -> "cp862" | `Set_cp863 -> "cp863" | `Set_cp864 -> "cp864" | `Set_cp865 -> "cp865" | `Set_cp866 -> "cp866" | `Set_cp869 -> "cp869" | `Set_cp874 -> "cp874" | `Set_cp1006 -> "cp1006" | `Set_cp037 -> "cp037" | `Set_cp424 -> "cp424" | `Set_cp500 -> "cp500" | `Set_cp875 -> "cp875" | `Set_cp1026 -> "cp1026" | `Set_cp1047 -> "cp1047" | `Set_adobe_standard_encoding -> "adobe_standard_encoding" | `Set_adobe_symbol_encoding -> "adobe_symbol_encoding" | `Set_adobe_zapf_dingbats_encoding -> "adobe_zapf_dingbats_encoding" | `Set_macroman -> "macroman" ;; let rec required_charsets (e : encoding) = (* The name is a bit misleading. The function returns the charsets that * correspond to the conversion tables that are required to support the * encoding. *) match e with | `Enc_utf8 | `Enc_utf8_opt_bom | `Enc_java | `Enc_utf16 | `Enc_utf16_le | `Enc_utf16_be | `Enc_utf32 | `Enc_utf32_le | `Enc_utf32_be -> [] | `Enc_usascii -> [] | `Enc_iso88591 -> [] | `Enc_iso88592 -> [ `Set_iso88592 ] | `Enc_iso88593 -> [ `Set_iso88593 ] | `Enc_iso88594 -> [ `Set_iso88594 ] | `Enc_iso88595 -> [ `Set_iso88595 ] | `Enc_iso88596 -> [ `Set_iso88596 ] | `Enc_iso88597 -> [ `Set_iso88597 ] | `Enc_iso88598 -> [ `Set_iso88598 ] | `Enc_iso88599 -> [ `Set_iso88599 ] | `Enc_iso885910 -> [ `Set_iso885910 ] | `Enc_iso885911 -> [ `Set_iso885911 ] | `Enc_iso885913 -> [ `Set_iso885913 ] | `Enc_iso885914 -> [ `Set_iso885914 ] | `Enc_iso885915 -> [ `Set_iso885915 ] | `Enc_iso885916 -> [ `Set_iso885916 ] | `Enc_koi8r -> [ `Set_koi8r ] | `Enc_jis0201 -> [ `Set_jis0201 ] | `Enc_eucjp -> [ `Set_jis0201; `Set_jis0208; `Set_jis0212 ] | `Enc_euckr -> [ `Set_ks1001 ] | `Enc_asn1_iso646 -> [ `Set_asn1_iso646 ] | `Enc_asn1_T61 -> [ `Set_asn1_T61 ] | `Enc_asn1_printable -> [ `Set_asn1_printable ] | `Enc_windows1250 -> [ `Set_windows1250 ] | `Enc_windows1251 -> [ `Set_windows1251 ] | `Enc_windows1252 -> [ `Set_windows1252 ] | `Enc_windows1253 -> [ `Set_windows1253 ] | `Enc_windows1254 -> [ `Set_windows1254 ] | `Enc_windows1255 -> [ `Set_windows1255 ] | `Enc_windows1256 -> [ `Set_windows1256 ] | `Enc_windows1257 -> [ `Set_windows1257 ] | `Enc_windows1258 -> [ `Set_windows1258 ] | `Enc_cp437 -> [ `Set_cp437 ] | `Enc_cp737 -> [ `Set_cp737 ] | `Enc_cp775 -> [ `Set_cp775 ] | `Enc_cp850 -> [ `Set_cp850 ] | `Enc_cp852 -> [ `Set_cp852 ] | `Enc_cp855 -> [ `Set_cp855 ] | `Enc_cp856 -> [ `Set_cp856 ] | `Enc_cp857 -> [ `Set_cp857 ] | `Enc_cp860 -> [ `Set_cp860 ] | `Enc_cp861 -> [ `Set_cp861 ] | `Enc_cp862 -> [ `Set_cp862 ] | `Enc_cp863 -> [ `Set_cp863 ] | `Enc_cp864 -> [ `Set_cp864 ] | `Enc_cp865 -> [ `Set_cp865 ] | `Enc_cp866 -> [ `Set_cp866 ] | `Enc_cp869 -> [ `Set_cp869 ] | `Enc_cp874 -> [ `Set_cp874 ] | `Enc_cp1006 -> [ `Set_cp1006 ] | `Enc_cp037 -> [ `Set_cp037 ] | `Enc_cp424 -> [ `Set_cp424 ] | `Enc_cp500 -> [ `Set_cp500 ] | `Enc_cp875 -> [ `Set_cp875 ] | `Enc_cp1026 -> [ `Set_cp1026 ] | `Enc_cp1047 -> [ `Set_cp1047 ] | `Enc_adobe_standard_encoding -> [ `Set_adobe_standard_encoding ] | `Enc_adobe_symbol_encoding -> [ `Set_adobe_symbol_encoding ] | `Enc_adobe_zapf_dingbats_encoding -> [ `Set_adobe_zapf_dingbats_encoding ] | `Enc_macroman -> [ `Set_macroman ] | `Enc_subset(e',_) -> required_charsets e' | `Enc_empty -> [] ;; let rec same_encoding e1 e2 = match (e1,e2) with (`Enc_subset(e1_sub, f1), `Enc_subset(e2_sub, f2)) -> same_encoding e1_sub e2_sub && f1 == f2 | (_,_) -> e1 = e2 ;; let rec byte_order_mark = function `Enc_utf16_le -> "\255\254" | `Enc_utf16_be -> "\254\255" | `Enc_utf32_le -> "\255\254\000\000" | `Enc_utf32_be -> "\000\000\254\255" | `Enc_subset(e,_) -> byte_order_mark e | _ -> "" ;; let available_input_encodings() = let l = ref [] in List.iter (fun (e,_) -> let charsets = required_charsets e in if List.for_all (fun cs -> Netdb.exists_db ("cmapf." ^ internal_name cs)) charsets then l := e :: !l ) names; !l ;; let available_output_encodings() = let exclude = [ `Enc_utf16; `Enc_utf32 ] in let l = ref [] in List.iter (fun (e,_) -> if not (List.mem e exclude) then begin let charsets = required_charsets e in if List.for_all (fun cs -> Netdb.exists_db ("cmapr." ^ internal_name cs)) charsets then l := e :: !l end ) names; !l ;; let (win32_code_pages : (_ * encoding) list) = [ 65001, `Enc_utf8; 1200, `Enc_utf16_le; 1201, `Enc_utf16_be; 20127, `Enc_usascii; 28591, `Enc_iso88591; 28592, `Enc_iso88592; 28593, `Enc_iso88593; 28594, `Enc_iso88594; 28595, `Enc_iso88595; 28596, `Enc_iso88596; 28597, `Enc_iso88597; 28598, `Enc_iso88598; 28599, `Enc_iso88599; (* `Enc_iso885910 *) (* `Enc_iso885911 *) 28603, `Enc_iso885913; (* `Enc_iso885914 *) 28605, `Enc_iso885915; (* `Enc_iso885916 *) 20866, `Enc_koi8r; (* `Enc_jis0201 *) 20932, `Enc_eucjp; 51949, `Enc_euckr; 1250, `Enc_windows1250; 1251, `Enc_windows1251; 1252, `Enc_windows1252; 1253, `Enc_windows1253; 1254, `Enc_windows1254; 1255, `Enc_windows1255; 1256, `Enc_windows1256; 1257, `Enc_windows1257; 1258, `Enc_windows1258; 437, `Enc_cp437; 737, `Enc_cp737; 775, `Enc_cp775; 850, `Enc_cp850; 852, `Enc_cp852; 855, `Enc_cp855; (* `Enc_cp856 *) 857, `Enc_cp857; 860, `Enc_cp860; 861, `Enc_cp861; 862, `Enc_cp862; 863, `Enc_cp863; 864, `Enc_cp864; 865, `Enc_cp865; 866, `Enc_cp866; 869, `Enc_cp869; 874, `Enc_cp874; (* `Enc_cp1006 *) 37, `Enc_cp037; 20424, `Enc_cp424; 500, `Enc_cp500; 875, `Enc_cp875; 1026, `Enc_cp1026; 1047, `Enc_cp1047; (* `Enc_adobe_standard_encoding *) (* `Enc_adobe_symbol_encoding *) (* `Enc_adobe_zapf_dingbats_encoding *) 10000, `Enc_macroman; ] let user_encoding() = match Sys.os_type with | "Win32" -> let cp = Netsys_win32.get_active_code_page() in ( try Some(List.assoc cp win32_code_pages) with Not_found -> None ) | _ -> ( try let codeset = (Netsys_posix.query_langinfo "").Netsys_posix.nl_CODESET in Some(encoding_of_string codeset) with | _ -> None ) (* Internal conversion interface: * * let (n_char, n_byte, enc') = read_XXX slice_char slice_blen s_in p_in l_in: * * - Scans the bytes from position p_in until the slice is decoded, but at * most until the last position p_in+l_in-1 of the input string s_in, and * decodes the character for the selected encoding. * - "slice_char" is a preallocated array of ints storing the code points * of the characters. It is allowed that "slice_char" is only partially * filled with characters. In this case, there must be a -1 after the * last valid code point. * - "slice_blen" is another "int array" with the same size as "slice_char". * It contains the byte length of every character. It is initialized with * a sequence of ones, so single-byte readers don't have to worry about * this array. * - Returns: * * n_char: the number of decoded characters * * n_byte: the number of scanned bytes ( <= l_in ) * * enc': the new encoding * - In the case of multi-byte encodings it is possible that * the last byte to read at position p_in+l_in-1 is the beginning of * a character. This character is excluded from being decoded. * - Errors: If an invalid byte sequence is found, the exception * Malformed_code_read(_,_,_) is raised. The exception returns the * triple (n_char, n_byte, enc') describing how much could be read * before the reader ran into the bad sequence. slice_char and slice_blen * are only partially initialized, with a (-1) at the end of slice_char. * * let (n_char, n_byte) = * write_XXX slice_char slice_pos slice_length s_out p_out l_out subst * * - Writes the characters found in slice_char to s_out. Only the elements * from slice_pos to slice_pos + slice_length -1 are written. The resulting * bytes are written to s_out from byte position p_out to p_out+l_out-1. * - There must not be a -1 (EOF mark) in the first slice_length characters * of slice_char. * - Only whole characters must be written. * - For code points p that cannot be represented in the output * encoding, the function subst is called. The function must return * the (already encoded) string to substitute. This must be a small string. * - Of course, p >= 0. As special case, p >= 0x110000 may be used to force * that subst is called (it is assumed that max_int can be never * represented). * - Returns: * * n_char: the number of processed characters * * n_byte: the number of written bytes ( <= l_in ) * * let (n_char, n_byte) = * back_XXX s_in range_in range_in_len p_in n_char: * * - The substring of s_in beginning at range_in and with length * range_in_len is considered as the valid range * - The cursor is at byte position p_in and goes n_char characters back * - The routine returns: * * n_char: the characters the cursor was actually moved backwards * * n_byte: the bytes the cursor was actually moved backwards * - The validity of the input encoding needs not to be checked *) exception Malformed_code_read of (int * int * encoding);; (* not exported! *) Callback.register_exception "Netconversion.Malformed_code_read" (Malformed_code_read(0,0,`Enc_empty));; (* Needed by netaccel_c.c *) (* UNSAFE_OPT: A number of functions have been optimized by using * unsafe features of O'Caml (unsafe_get, unsafe_set, unsafe_chr). * These functions have been checked very carefully, and there are * a lot of comments arguing about the correctness of the array * and string accesses. *) type poly_reader = { read : 's . 's Netstring_tstring.tstring_ops -> int array -> int array -> 's -> int -> int -> (int * int * encoding) } let read_iso88591 maxcode enc = (* UNSAFE_OPT *) let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); let m = min l_in (Array.length slice_char) in let m3 = m/3 in for k3 = 0 to m3-1 do let k = 3*k3 in (* let ch = Char.code s_in.[ p_in + k ] in *) let chars = ops.unsafe_get3 s_in (p_in + k) in let c0 = chars lsr 16 in let c1 = (chars lsr 8) land 0xff in let c2 = chars land 0xff in if c0 > maxcode then ( slice_char.(k) <- (-1); raise(Malformed_code_read(k,k,enc)) ); Array.unsafe_set slice_char k c0; if c1 > maxcode then ( slice_char.(k+1) <- (-1); raise(Malformed_code_read(k+1,k+1,enc)) ); Array.unsafe_set slice_char (k+1) c1; if c2 > maxcode then ( slice_char.(k+2) <- (-1); raise(Malformed_code_read(k+2,k+2,enc)) ); Array.unsafe_set slice_char (k+2) c2; done; for k = 3*m3 to m-1 do let c0 = Char.code (ops.unsafe_get s_in (p_in + k)) in if c0 > maxcode then ( slice_char.(k) <- (-1); raise(Malformed_code_read(k,k,enc)) ); Array.unsafe_set slice_char k c0; done; if m < Array.length slice_char then ( slice_char.(m) <- (-1); ); (m,m,enc) in { read } ;; let read_iso88591_ref = ref read_iso88591;; let get_8bit_to_unicode_map enc = let cs = match required_charsets enc with [ cs ] -> cs | _ -> failwith "get_8bit_to_unicode_map" in let to_unicode = Netmappings.get_to_unicode (internal_name cs) in assert(Array.length to_unicode = 256); to_unicode ;; let read_8bit enc = let m_to_unicode = get_8bit_to_unicode_map enc in (* the 256-byte array mapping the character set to unicode *) let read ops slice_char slice_blen s_in p_in l_in = (* UNSAFE_OPT *) let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); let m = min l_in (Array.length slice_char) in let m3 = m/3 in for k3 = 0 to m3-1 do let k = 3*k3 in let chars = ops.unsafe_get3 s_in k in let c0 = chars lsr 16 in let c1 = (chars lsr 8) land 0xff in let c2 = chars land 0xff in let c0_uni = Array.unsafe_get m_to_unicode c0 in if c0_uni < 0 then ( slice_char.(k) <- (-1); raise(Malformed_code_read(k,k,enc)); ); Array.unsafe_set slice_char k c0_uni; let c1_uni = Array.unsafe_get m_to_unicode c1 in if c1_uni < 0 then ( slice_char.(k+1) <- (-1); raise(Malformed_code_read(k+1,k+1,enc)); ); Array.unsafe_set slice_char (k+1) c1_uni; let c2_uni = Array.unsafe_get m_to_unicode c2 in if c2_uni < 0 then ( slice_char.(k+2) <- (-1); raise(Malformed_code_read(k+2,k+2,enc)); ); Array.unsafe_set slice_char (k+2) c2_uni; done; for k = 3*m3 to m-1 do let c0 = Char.code (ops.get s_in k) in let c0_uni = Array.unsafe_get m_to_unicode c0 in if c0_uni < 0 then ( slice_char.(k) <- (-1); raise(Malformed_code_read(k,k,enc)); ); Array.unsafe_set slice_char k c0_uni; done; if m < Array.length slice_char then ( slice_char.(m) <- (-1); ); (m,m,enc) in { read } ;; let read_utf8 is_java = (* UNSAFE_OPT *) let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); (* k: counts the bytes * n: counts the characters *) let p = ref p_in in let p_max = p_in + l_in in let n = ref 0 in let n_ret = ref (-1) in let malformed_code() = slice_char.( !n ) <- (-1); raise(Malformed_code_read(!n, !p - p_in, `Enc_utf8)); in let slice_length = Array.length slice_char in while !p < p_max && !n < slice_length do let k_inc = (* length of the character in bytes; 0 means: stop *) (* We know: * (1) p_in >= 0 ==> !p >= 0 * (2) !p < p_max = p_in + l_in <= String.length s_in * ==> unsafe get ok *) (* match s_in.[k_in + k] with *) match ops.unsafe_get s_in !p with '\000' -> if is_java then malformed_code(); (* slice_char.(n) <- 0; *) Array.unsafe_set slice_char !n 0; (* ok *) 1 | ('\001'..'\127' as x) -> (* slice_char.(n) <- Char.code x; *) Array.unsafe_set slice_char !n (Char.code x); (* ok *) 1 | ('\128'..'\223' as x) -> if !p+1 >= p_max then 0 else begin (* ==> !p+1 < p_max = p_in + l_in <= String.length s_in * ==> unsafe get ok *) let n1 = Char.code x in let n2 = (* Char.code (s_in.[!p + 1]) *) Char.code(ops.unsafe_get s_in (!p + 1)) in if is_java && (n1 = 0x80 && n2 = 0xc0) then begin (* slice_char.(n) <- 0; *) Array.unsafe_set slice_char !n 0; (* ok *) 2 end else begin if n2 < 128 || n2 > 191 then malformed_code(); let p = ((n1 land 0b11111) lsl 6) lor (n2 land 0b111111) in if p < 128 then malformed_code(); (* slice_char.(n) <- p; *) Array.unsafe_set slice_char !n p; (* ok *) 2 end end | ('\224'..'\239' as x) -> if !p + 2 >= p_max then 0 else begin (* ==> !p+2 < p_max = p_in + l_in <= String.length s_in * ==> unsafe get ok *) let n1 = Char.code x in let n2 = (* Char.code (s_in.[!p + 1]) *) Char.code(ops.unsafe_get s_in (!p + 1)) in let n3 = (* Char.code (s_in.[!p + 2]) *) Char.code(ops.unsafe_get s_in (!p + 2)) in if n2 < 128 || n2 > 191 then malformed_code(); if n3 < 128 || n3 > 191 then malformed_code(); let p = ((n1 land 0b1111) lsl 12) lor ((n2 land 0b111111) lsl 6) lor (n3 land 0b111111) in if p < 0x800 then malformed_code(); if (p >= 0xd800 && p < 0xe000) then (* Surrogate pairs are not supported in UTF-8 *) malformed_code(); if (p >= 0xfffe && p <= 0xffff) then malformed_code(); (* slice_char.(n) <- p; *) Array.unsafe_set slice_char !n p; (* ok *) 3 end | ('\240'..'\247' as x) -> if !p + 3 >= p_max then 0 else begin (* ==> !p+3 < p_max = p_in + l_in <= String.length s_in * ==> unsafe get ok *) let n1 = Char.code x in let chars = ops.unsafe_get3 s_in (!p + 1) in let n2 = chars lsr 16 in let n3 = (chars lsr 8) land 0xff in let n4 = chars land 0xff in if n2 < 128 || n2 > 191 then malformed_code(); if n3 < 128 || n3 > 191 then malformed_code(); if n4 < 128 || n4 > 191 then malformed_code(); let p = ((n1 land 0b111) lsl 18) lor ((n2 land 0b111111) lsl 12) lor ((n3 land 0b111111) lsl 6) lor (n4 land 0b111111) in if p < 0x10000 then malformed_code(); if p >= 0x110000 then (* These code points are not supported. *) malformed_code(); (* slice_char.(n) <- p; *) Array.unsafe_set slice_char !n p; (* ok *) 4 end | _ -> (* Outside the valid range of XML characters *) malformed_code(); in (* If k_inc = 0, the character was partially outside the processed * range of the string, and could not be decoded. *) if k_inc > 0 then begin (* We know: * (1) n >= 0, because n starts with 0 and is only increased * (2) n < Array.length slice_char = Array.length slice_blen * ==> unsafe set ok *) (* slice_blen.(n) <- k_inc; *) Array.unsafe_set slice_blen !n k_inc; (* next iteration: *) p := !p + k_inc; incr n; end else begin (* Stop loop: *) n_ret := !n; n := slice_length; end done; if (!n_ret = (-1)) then n_ret := !n; if !n_ret < slice_length then ( (* EOF marker *) slice_char.(!n_ret) <- (-1); ); (!n_ret,!p-p_in,`Enc_utf8) in { read } ;; let read_utf8_ref = ref read_utf8;; let have_utf8_bom ops s p = let open Netstring_tstring in let c0 = ops.get s (p + 0) in let c1 = ops.get s (p + 1) in let c2 = ops.get s (p + 2) in c0 = '\xEF' && c1 = '\xBB' && c2 = '\xBF' let read_utf8_opt_bom expose_bom = let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); (* Expect a BOM at the beginning of the text *) if l_in >= 3 then ( if have_utf8_bom ops s_in p_in then ( let p_in1, l_in1 = if expose_bom then p_in, l_in else p_in+3, l_in-3 in let (n_ret, p_ret, enc) = (!read_utf8_ref false).read ops slice_char slice_blen s_in p_in1 l_in1 in let p_ret1 = if expose_bom then p_ret else p_ret+3 in if expose_bom && n_ret >= 1 then slice_char.(0) <- (-3); (n_ret, p_ret1, enc) ) else (!read_utf8_ref false).read ops slice_char slice_blen s_in p_in l_in ) else ( let bom_possible = l_in=0 || (l_in=1 && ops.get s_in 0 = '\xEF') || (l_in=2 && ops.get s_in 0 = '\xEF' && ops.get s_in 1 = '\xBB') in if bom_possible then (0, 0, `Enc_utf8_opt_bom) else (!read_utf8_ref false).read ops slice_char slice_blen s_in p_in l_in ) in { read } ;; let surrogate_offset = 0x10000 - (0xD800 lsl 10) - 0xDC00;; let read_utf16_lebe lo hi n_start enc = (* lo=0, hi=1: little endian * lo=1, hi=0: big endian * n_start: First cell in slice to use *) let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); let malformed_code k n = slice_char.(n) <- (-1); raise(Malformed_code_read(n,k,enc)) in (* k: counts the bytes * n: counts the characters *) let rec put_loop k n = if k+1 < l_in && n < Array.length slice_char then begin let p = (Char.code (ops.get s_in (p_in + k + lo))) lor ((Char.code (ops.get s_in (p_in + k + hi))) lsl 8) in if p >= 0xd800 && p < 0xe000 then begin (* This is a surrogate pair. *) if k+3 < l_in then begin if p <= 0xdbff then begin let q = (Char.code (ops.get s_in (p_in + k + 2 + lo))) lor ((Char.code (ops.get s_in (p_in + k + 2 + hi))) lsl 8) in if q < 0xdc00 || q > 0xdfff then malformed_code k n; let eff_p = (p lsl 10) + q + surrogate_offset in slice_char.(n) <- eff_p; slice_blen.(n) <- 4; put_loop (k+4) (n+1) end else (* Malformed pair: *) malformed_code k n; end else (n,k) end else (* Normal 2-byte character *) if p = 0xfffe then (* Wrong byte order mark: It is illegal here *) malformed_code k n else begin (* A regular code point *) slice_char.(n) <- p; slice_blen.(n) <- 2; put_loop (k+2) (n+1) end end else (n,k) in let (n,k) = put_loop 0 n_start in if n < Array.length slice_char then ( (* EOF marker *) slice_char.(n) <- (-1); ); (n,k,enc) in { read } ;; let get_endianess ops s_in p_in = let open Netstring_tstring in let c0 = ops.get s_in (p_in + 0) in let c1 = ops.get s_in (p_in + 1) in if c0 = '\254' && c1 = '\255' then `Big_endian else if c0 = '\255' && c1 = '\254' then `Little_endian else `No_BOM ;; (* expose_bom: when true, the BOM is considered as a character and * put as value (-3) into slice_char *) let read_utf16 expose_bom = let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); (* Expect a BOM at the beginning of the text *) if l_in >= 2 then begin if expose_bom then ( slice_char.(0) <- (-3); slice_blen.(0) <- 0; (* Later corrected *) ); match get_endianess ops s_in p_in with `Big_endian -> let n_start = if expose_bom then 1 else 0 in let (n, k, enc') = (read_utf16_lebe 1 0 n_start `Enc_utf16_be).read ops slice_char slice_blen s_in (p_in+2) (l_in-2) in if n > 0 then slice_blen.(0) <- slice_blen.(0) + 2; (n, k+2, enc') | `Little_endian -> let n_start = if expose_bom then 1 else 0 in let (n, k, enc') = (read_utf16_lebe 0 1 n_start `Enc_utf16_le).read ops slice_char slice_blen s_in (p_in+2) (l_in-2) in if n > 0 then slice_blen.(0) <- slice_blen.(0) + 2; (n, k+2, enc') | `No_BOM -> (* byte order mark missing *) slice_char.(0) <- (-1); raise(Malformed_code_read(0,0,`Enc_utf16)) end else ( slice_char.(0) <- (-1); (0, 0, `Enc_utf16) ) in { read } ;; let read_utf32_lebe little n_start enc = (* little: whether little endian * n_start: First cell in slice to use *) let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); let malformed_code k n = slice_char.(n) <- (-1); raise(Malformed_code_read(n,k,enc)) in let b0 = if little then 0 else 3 in let b1 = if little then 1 else 2 in let b2 = if little then 2 else 1 in let b3 = if little then 3 else 0 in (* k: counts the bytes * n: counts the characters *) let rec put_loop k n = if k+3 < l_in && n < Array.length slice_char then begin let p3 = Char.code (ops.get s_in (p_in + k + b3)) in if p3 <> 0 then malformed_code k n; let p = (Char.code (ops.get s_in (p_in + k + b0))) lor ((Char.code (ops.get s_in (p_in + k + b1))) lsl 8) lor ((Char.code (ops.get s_in (p_in + k + b2))) lsl 16) in if (p >= 0xD800 && p <= 0xDFFF) || p >= 0x10FFFF then malformed_code k n; if p = 0xfffe then (* Wrong byte order mark: It is illegal here *) malformed_code k n; slice_char.(n) <- p; slice_blen.(n) <- 4; put_loop (k+4) (n+1) end else (n,k) in let (n,k) = put_loop 0 n_start in if n < Array.length slice_char then ( (* EOF marker *) slice_char.(n) <- (-1); ); (n,k,enc) in { read } ;; let get_endianess32 ops s_in p_in = let open Netstring_tstring in let c0 = ops.get s_in (p_in + 0) in let c1 = ops.get s_in (p_in + 1) in let c2 = ops.get s_in (p_in + 2) in let c3 = ops.get s_in (p_in + 3) in if c0 = '\000' && c1 = '\000' && c2 = '\254' && c3 = '\255' then `Big_endian else if c0 = '\255' && c1 = '\254' && c2 = '\000' && c3 = '\000' then `Little_endian else `No_BOM ;; let read_utf32 expose_bom = let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); (* Expect a BOM at the beginning of the text *) if l_in >= 4 then begin if expose_bom then ( slice_char.(0) <- (-3); slice_blen.(0) <- 0; (* Later corrected *) ); match get_endianess32 ops s_in p_in with `Big_endian -> let n_start = if expose_bom then 1 else 0 in let (n, k, enc') = (read_utf32_lebe false n_start `Enc_utf32_be).read ops slice_char slice_blen s_in (p_in+4) (l_in-4) in if n > 0 then slice_blen.(0) <- slice_blen.(0) + 4; (n, k+4, enc') | `Little_endian -> let n_start = if expose_bom then 1 else 0 in let (n, k, enc') = (read_utf32_lebe true n_start `Enc_utf32_le).read ops slice_char slice_blen s_in (p_in+4) (l_in-4) in if n > 0 then slice_blen.(0) <- slice_blen.(0) + 4; (n, k+4, enc') | `No_BOM -> (* byte order mark missing *) slice_char.(0) <- (-1); raise(Malformed_code_read(0,0,`Enc_utf32)) end else ( slice_char.(0) <- (-1); (0, 0, `Enc_utf32) ) in { read } ;; let read_euc len1 len2 len3 map1 map2 map3 enc = (* Code set 0 is US-ASCII. * Code sets 1, 2, 3 may be anything. lenX = 0: code set is not supported. * lenX is either 0, 1, or 2. *) (* UNSAFE_OPT *) let open Netstring_tstring in assert(len1 >= 0 && len1 <= 2); assert(len2 >= 0 && len2 <= 2); assert(len3 >= 0 && len3 <= 2); let read ops slice_char slice_blen s_in p_in l_in = assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); (* k: counts the bytes * n: counts the characters *) let p = ref p_in in let p_max = p_in + l_in in let n = ref 0 in let n_ret = ref (-1) in let malformed_code() = slice_char.( !n ) <- (-1); raise(Malformed_code_read(!n, !p - p_in, enc)); in let slice_length = Array.length slice_char in while !p < p_max && !n < slice_length do let k_inc = (* length of the character in bytes; 0 means: stop *) (* We know: * (1) p_in >= 0 ==> !p >= 0 * (2) !p < p_max = p_in + l_in <= String.length s_in * ==> unsafe get ok *) (* match s_in.[k_in + k] with *) match ops.unsafe_get s_in !p with '\000'..'\127' as x -> (* US-ASCII *) Array.unsafe_set slice_char !n (Char.code x); (* ok *) 1 | '\142' -> (* Code set 2 *) if len2 = 0 then malformed_code(); if !p+len2 >= p_max then 0 else begin let x1 = Char.code (ops.get s_in (!p + 1)) in let x2 = if len2=1 then 256 else Char.code (ops.get s_in (!p + 2)) in if x1 < 160 || x2 < 160 then malformed_code(); let uni = map2 x1 x2 in Array.unsafe_set slice_char !n uni; (* ok *) len2+1 end | '\143' -> (* Code set 3 *) if len3 = 0 then malformed_code(); if !p+len3 >= p_max then 0 else begin let x1 = Char.code (ops.get s_in (!p + 1)) in let x2 = if len3=1 then 256 else Char.code (ops.get s_in (!p + 2)) in if x1 < 160 || x2 < 160 then malformed_code(); let uni = map3 x1 x2 in Array.unsafe_set slice_char !n uni; (* ok *) len3+1 end | '\160'..'\255' as x1_code -> (* Code set 1 *) if !p+len1 > p_max then 0 else begin let x1 = Char.code x1_code in let x2 = if len1=1 then 256 else Char.code (ops.get s_in (!p + 1)) in if x2 < 160 then malformed_code(); let uni = map1 x1 x2 in Array.unsafe_set slice_char !n uni; (* ok *) len1 end | _ -> (* illegal *) malformed_code() in (* If k_inc = 0, the character was partially outside the processed * range of the string, and could not be decoded. *) if k_inc > 0 then begin (* We know: * (1) n >= 0, because n starts with 0 and is only increased * (2) n < Array.length slice_char = Array.length slice_blen * ==> unsafe set ok *) (* slice_blen.(n) <- k_inc; *) Array.unsafe_set slice_blen !n k_inc; (* next iteration: *) p := !p + k_inc; incr n; end else begin (* Stop loop: *) n_ret := !n; n := slice_length; end done; if (!n_ret = (-1)) then n_ret := !n; if !n_ret < slice_length then ( (* EOF marker *) slice_char.(!n_ret) <- (-1); ); (!n_ret,!p-p_in,enc) in { read } ;; let read_eucjp () = let jis0201 = Netmappings.get_to_unicode "jis0201" in let jis0208 = Netmappings.get_to_unicode "jis0208" in let jis0212 = lazy (Netmappings.get_to_unicode "jis0212") in (* seldom *) let map1 x1 x2 = jis0208.( (x1-160) * 96 + x2 - 160 ) in let map2 x1 _ = jis0201.( x1 ) in let map3 x1 x2 = (Lazy.force jis0212).( (x1-160) * 96 + x2 - 160 ) in read_euc 2 1 2 map1 map2 map3 `Enc_eucjp ;; let read_euckr () = let ks1001 = Netmappings.get_to_unicode "ks1001" in let map x1 x2 = ks1001.( (x1-160) * 96 + x2 - 160 ) in read_euc 2 0 0 map map map `Enc_euckr ;; let read_subset inner_read def = let read ops slice_char slice_blen s_in p_in l_in = let open Netstring_tstring in assert(Array.length slice_char = Array.length slice_blen); assert(p_in >= 0 && p_in + l_in <= ops.length s_in && l_in >= 0); let (n,k,enc') = inner_read.read ops slice_char slice_blen s_in p_in l_in in (* check codepoints: *) for j = 0 to n-1 do if not(def(slice_char.(j))) then ( (* raise Malformed_code_read... *) (* to get enc'' read again: *) let slice_char' = Array.make j (-1) in let slice_blen' = Array.make j 1 in let (n', k', enc'') = try inner_read.read ops slice_char' slice_blen' s_in p_in l_in with Malformed_code_read(_,_,_) -> assert false in assert(n' = j); int_blit slice_char' 0 slice_char 0 j; int_blit slice_blen' 0 slice_blen 0 j; slice_char.(j) <- (-1); raise (Malformed_code_read(j, k', enc'')) ); done; (n,k,enc') in { read } ;; (* * let (n_char, b_byte) = * write_XXX slice_char slice_length s_out p_out l_out subst *) let write_iso88591 maxcode slice_char slice_pos slice_length s_out p_out l_out subst = (* UNSAFE_OPT *) (* Use maxcode=255 for ISO-8859-1, and maxcode=127 for US-ASCII, * and maxcode=(-1) for `Enc_empty. *) assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); assert(maxcode <= 255); let n = ref slice_pos in (* index of slice *) let n_ret = ref (-1) in (* returned number of characters *) let n_max = slice_pos + slice_length in let p = ref p_out in (* current output position *) let p_max = p_out + l_out in (* maximum output position *) while ( !n < n_max ) && ( !p < p_max ) do (* We know: * (1) !n >= 0, because it starts with 0 and is only increased * (2) !n < n_max = slice_pos + slice_length <= Array.length slice_char * ==> unsafe get ok *) let ch = Array.unsafe_get slice_char !n in if ch >= 0 && ch <= maxcode then begin (* Because !p < p_max: * !p < p_max = p_out + l_out <= String.length s_out * Furthermore, p_out >= 0, !p >= 0. * ==> unsafe set ok *) (* s_out.[ !p ] <- Char.chr ch; *) Bytes.unsafe_set s_out !p (Char.unsafe_chr ch); incr n; incr p; end else begin assert(ch >= 0); let replacement = subst ch in let l_repl = String.length replacement in if l_repl > multibyte_limit then failwith "Netconversion.write_iso88591: Substitution string too long"; if !p + l_repl <= p_max then begin (* Enough space to store 'replacement': *) Bytes.blit_string replacement 0 s_out !p l_repl; p := !p + l_repl; incr n end else begin (* Exit whole conversion *) n_ret := !n; n := n_max; end end done; if !n_ret >= 0 then (!n_ret - slice_pos, !p - p_out) else (!n - slice_pos, !p - p_out) ;; let get_8bit_from_unicode_map enc = let cs = match required_charsets enc with [ cs ] -> cs | _ -> failwith "get_8bit_from_unicode_map" in let from_unicode = Netmappings.get_from_unicode (internal_name cs) in assert(Array.length from_unicode = 256); from_unicode ;; let write_8bit enc = (* UNSAFE_OPT *) let m_from_unicode = get_8bit_from_unicode_map enc in let m_mask = Array.length m_from_unicode - 1 in fun slice_char slice_pos slice_length s_out p_out l_out subst -> assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); let n = ref slice_pos in (* index of slice *) let n_max = slice_pos + slice_length in let k = ref 0 in (* written bytes *) let n_ret = ref (-1) in (* returned number of characters *) while ( !n < n_max ) && ( !k < l_out ) do (* We know: * (1) !n >= 0, because it starts with 0 and is only increased * (2) !n < n_max = slice_pos + slice_length <= Array.length slice * ==> unsafe get ok *) let p = (* slice_char.( !n ) *) Array.unsafe_get slice_char !n in let p' = match Array.unsafe_get m_from_unicode (p land m_mask) with Netmappings.U_nil -> -1 | Netmappings.U_single (p0,q0) -> if p0 = p then q0 else -1 | Netmappings.U_double (p0,q0,p1,q1) -> if p0 = p then q0 else if p1 = p then q1 else -1 | Netmappings.U_array pq -> let r = ref (-1) in let h = ref 0 in while !r < 0 && !h < Array.length pq do if pq.( !h ) = p then r := pq.( !h+1 ) else h := !h + 2 done; !r in (* If p=-1 ==> p'=-1, because -1 is never mapped to any code point *) if p' < 0 then begin if p < 0 then assert false (* EOF mark found *) else begin let replacement = subst p in let l_repl = String.length replacement in if l_repl > multibyte_limit then failwith "Netconversion.write_8bit: Substitution string too long"; if !k + l_repl <= l_out then begin (* Enough space to store 'replacement': *) Bytes.blit_string replacement 0 s_out (p_out + !k) l_repl; k := !k + l_repl; incr n end else begin (* Exit whole conversion *) n_ret := !n; n := n_max; end end end else begin (* Because !k < l_out: * p_out + !k < p_out + l_out <= String.length s_out * Furthermore, p_out >= 0, !k >= 0. * ==> unsafe set ok *) (* s_out.[ p_out + !k ] <- Char.chr p'; *) Bytes.unsafe_set s_out (p_out + !k) (Char.unsafe_chr(p' land 0xff)); incr n; incr k end; done; if !n_ret >= 0 then (!n_ret - slice_pos, !k) else (!n - slice_pos, !k) ;; let write_utf8 is_java slice_char slice_pos slice_length s_out p_out l_out subst = (* UNSAFE_OPT *) assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); let n = ref slice_pos in (* index of slice *) let n_max = slice_pos + slice_length in let k = ref 0 in (* written bytes *) let n_ret = ref (-1) in (* returned number of characters *) while ( !n < n_max ) do (* We know: * (1) !n >= 0, because it starts with 0 and is only increased * (2) !n < n_max = slice_pos + slice_length <= Array.length slice * ==> unsafe get ok *) let p = (* slice.( !n ) *) Array.unsafe_get slice_char !n in let index = p_out + !k in let k_inc = (* k_inc: how many bytes are written. (-1) means: stop *) if p <= 127 && (not is_java || p <> 0) then begin if p < 0 then assert false; (* EOF mark *) if !k < l_out then begin (* (1) index = p_out + !k < p_out + l_out <= * String.length s_out * (2) p_out, !n >= 0 * ==> unsafe set ok * * 0 <= p <= 127 ==> unsafe_chr ok *) (* s_out.[index] <- Char.chr p; *) Bytes.unsafe_set s_out index (Char.unsafe_chr p); 1 end else (-1) end else if p <= 0x7ff then begin if !k + 1 < l_out then begin (* (1) index+1 = p_out + !k + 1 < p_out + l_out <= * String.length s_out * (2) p_out, !k >= 0 * ==> unsafe set ok * * p <= 0x7ff ==> p lsr 6 <= 0x1f * ==> 0xc0 lor (p lsr 6) <= df * p land 0x3f <= 0x3f ==> 0x80 lor (p land 0x3f) <= 0xbf * ==> unsafe_chr ok *) (* s_out.[index] <- Char.chr (0xc0 lor (p lsr 6)); *) (* s_out.[index + 1] <- Char.chr (0x80 lor (p land 0x3f)); *) Bytes.unsafe_set s_out index (Char.unsafe_chr (0xc0 lor (p lsr 6))); Bytes.unsafe_set s_out (index+1) (Char.unsafe_chr (0x80 lor (p land 0x3f))); 2 end else (-1) end else if p <= 0xffff then begin (* Refuse writing surrogate pairs, and fffe, ffff *) if (p >= 0xd800 && p < 0xe000) || (p >= 0xfffe) then failwith "Netconversion.write_utf8"; if !k + 2 < l_out then begin (* (1) index+2 = p_out + !k + 2 < p_out + l_out <= * String.length s_out * (2) p_out, !k >= 0 * ==> unsafe set ok * * Well, and it can be proven that unsafe_chr is ok, too... *) (* s_out.[index] <- Char.chr (0xe0 lor (p lsr 12)); *) (* s_out.[index + 1] <- Char.chr (0x80 lor ((p lsr 6) land 0x3f)); *) (* s_out.[index + 2] <- Char.chr (0x80 lor (p land 0x3f)); *) Bytes.unsafe_set s_out index (Char.unsafe_chr (0xe0 lor (p lsr 12))); Bytes.unsafe_set s_out (index+1) (Char.unsafe_chr (0x80 lor ((p lsr 6) land 0x3f))); Bytes.unsafe_set s_out (index+2) (Char.unsafe_chr (0x80 lor (p land 0x3f))); 3 end else (-1) end else if p <= 0x10ffff then begin if !k + 3 < l_out then begin (* No such characters are defined... *) Bytes.set s_out index (Char.chr (0xf0 lor (p lsr 18))); Bytes.set s_out (index + 1) (Char.chr (0x80 lor ((p lsr 12) land 0x3f))); Bytes.set s_out (index + 2) (Char.chr (0x80 lor ((p lsr 6) land 0x3f))); Bytes.set s_out (index + 3) (Char.chr (0x80 lor (p land 0x3f))); 4 end else (-1) end else begin (* Higher code points are not possible in XML; call subst *) let replacement = subst p in let l_repl = String.length replacement in if l_repl > multibyte_limit then failwith "Netconversion.write_utf8: Substitution string too long"; if !k + l_repl <= l_out then begin (* Enough space to store 'replacement': *) Bytes.blit_string replacement 0 s_out (p_out + !k) l_repl; l_repl (* may be 0! *) end else (-1) (* Exit whole conversion *) end in if k_inc >= 0 then ( k := !k + k_inc; incr n ) else ( n_ret := !n; n := n_max ); done; if !n_ret >= 0 then (!n_ret - slice_pos, !k) else (!n - slice_pos, !k) ;; let write_utf16_lebe lo hi slice_char slice_pos slice_length s_out p_out l_out subst = (* lo=0, hi=1: little endian * lo=1, hi=0: big endian *) assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); let n = ref slice_pos in (* index of slice *) let n_max = slice_pos + slice_length in let k = ref 0 in (* written bytes *) let n_ret = ref (-1) in (* returned number of characters *) while ( !n < n_max ) do let p = slice_char.( !n ) in let index = p_out + !k in let k_inc = if p >= 0xfffe then begin if p <= 0x10ffff then begin if p <= 0xffff then failwith "Netconversion.write_utf16_le"; (* Must be written as surrogate pair *) if !k + 3 < l_out then begin let high = ((p - 0x10000) lsr 10) + 0xd800 in let low = (p land 0x3ff) + 0xdc00 in Bytes.set s_out (index + lo) (Char.chr (high land 0xff)); Bytes.set s_out (index + hi) (Char.chr (high lsr 8)); Bytes.set s_out (index + 2 + lo) (Char.chr (low land 0xff)); Bytes.set s_out (index + 2 + hi) (Char.chr (low lsr 8)); 4 end else (-1) end else begin (* Higher code points are not possible in XML; call subst *) let replacement = subst p in let l_repl = String.length replacement in if l_repl > multibyte_limit then failwith "Netconversion.write_utf16_le: Substitution string too long"; if !k + l_repl <= l_out then begin (* Enough space to store 'replacement': *) Bytes.blit_string replacement 0 s_out (p_out + !k) l_repl; l_repl (* may be 0! *) end else (-1) (* Exit whole conversion *) end end else begin (* 2-byte character *) if !k + 1 < l_out then begin Bytes.set s_out (index + lo) (Char.unsafe_chr (p land 0xff)); Bytes.set s_out (index + hi) (Char.unsafe_chr ((p lsr 8) land 0xff)); 2 end else (-1) end in if k_inc >= 0 then ( k := !k + k_inc; incr n ) else ( n_ret := !n; n := n_max ); done; if !n_ret >= 0 then (!n_ret - slice_pos, !k) else (!n - slice_pos, !k) ;; let write_utf32_lebe little slice_char slice_pos slice_length s_out p_out l_out subst = assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); let n = ref slice_pos in (* index of slice *) let n_max = slice_pos + slice_length in let k = ref 0 in (* written bytes *) let n_ret = ref (-1) in (* returned number of characters *) let b0 = if little then 0 else 3 in let b1 = if little then 1 else 2 in let b2 = if little then 2 else 1 in let b3 = if little then 3 else 0 in while ( !n < n_max ) do let p = slice_char.( !n ) in let index = p_out + !k in let k_inc = if p <= 0x10ffff then ( if !k + 3 < l_out then ( Bytes.set s_out (index + b0) (Char.unsafe_chr (p land 0xff)); Bytes.set s_out (index + b1) (Char.unsafe_chr ((p lsr 8) land 0xff)); Bytes.set s_out (index + b2) (Char.unsafe_chr ((p lsr 16) land 0xff)); Bytes.set s_out (index + b3) (Char.unsafe_chr 0); 4 ) else (-1) ) else ( (* Higher code points are not possible in XML; call subst *) let replacement = subst p in let l_repl = String.length replacement in if l_repl > multibyte_limit then failwith "Netconversion.write_utf32: Substitution string too long"; if !k + l_repl <= l_out then begin (* Enough space to store 'replacement': *) Bytes.blit_string replacement 0 s_out (p_out + !k) l_repl; l_repl (* may be 0! *) end else (-1) (* Exit whole conversion *) ) in if k_inc >= 0 then ( k := !k + k_inc; incr n ) else ( n_ret := !n; n := n_max ); done; if !n_ret >= 0 then (!n_ret - slice_pos, !k) else (!n - slice_pos, !k) ;; let write_euc map enc = (* Code set 0 is US-ASCII. * let (set, byte1, byte2) = map unicode: * - set is 1, 2, 3, or 4. 4 means that the code point cannot be mapped. * - byte1 >= 160, <= 255 * - byte2 >= 160, <= 255, or byte2=256 meaning that it is not used *) (* UNSAFE_OPT *) fun slice_char slice_pos slice_length s_out p_out l_out subst -> assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); let n = ref slice_pos in (* index of slice *) let n_max = slice_pos + slice_length in let k = ref 0 in (* written bytes *) let n_ret = ref (-1) in (* returned number of characters *) while ( !n < n_max ) do (* We know: * (1) !n >= 0, because it starts with 0 and is only increased * (2) !n < n_max = slice_pos + slice_length <= Array.length slice * ==> unsafe get ok *) let p = (* slice.( !n ) *) Array.unsafe_get slice_char !n in assert (p >= 0); let index = p_out + !k in let (set, b1, b2) = if p <= 127 then (0, p, 256) else map p in let k_inc = (* k_inc: how many bytes are written *) match set with 0 -> if !k < l_out then begin (* s_out.[index] <- Char.chr p; *) Bytes.unsafe_set s_out index (Char.unsafe_chr (b1 land 127)); 1 end else (-1) | 1 -> let bl = if b2 = 256 then 1 else 2 in if !k + bl < l_out then begin assert(b1 >= 160 && b1 <= 255 && b2 >= 160 && b2 <= 256); Bytes.set s_out (index) (Char.chr b1); if b2 <> 256 then Bytes.set s_out (index+1) (Char.chr b2); bl end else (-1) | 2 -> let bl = if b2 = 256 then 2 else 3 in if !k + bl < l_out then begin assert(b1 >= 160 && b1 <= 255 && b2 >= 160 && b2 <= 256); Bytes.set s_out index '\142'; Bytes.set s_out (index+1) (Char.chr b1); if b2 <> 256 then Bytes.set s_out (index+2) (Char.chr b2); bl end else (-1) | 3 -> let bl = if b2 = 256 then 2 else 3 in if !k + bl < l_out then begin assert(b1 >= 160 && b1 <= 255 && b2 >= 160 && b2 <= 256); Bytes.set s_out index '\143'; Bytes.set s_out (index+1) (Char.chr b1); if b2 <> 256 then Bytes.set s_out (index+2) (Char.chr b2); bl end else (-1) | 4 -> let replacement = subst p in let l_repl = String.length replacement in if l_repl > multibyte_limit then failwith "Netconversion.write_euc: Substitution string too long"; if !k + l_repl <= l_out then begin (* Enough space to store 'replacement': *) Bytes.blit_string replacement 0 s_out (p_out + !k) l_repl; l_repl end else (-1) (* Exit whole conversion *) | _ -> assert false in if k_inc >= 0 then ( k := !k + k_inc; incr n ) else ( n_ret := !n; n := n_max ); done; if !n_ret >= 0 then (!n_ret - slice_pos, !k) else (!n - slice_pos, !k) ;; let write_eucjp () = let jis0201 = Netmappings.get_from_unicode "jis0201" in let jis0208 = Netmappings.get_from_unicode "jis0208" in let jis0212 = Netmappings.get_from_unicode "jis0212" in let jis0201_mask = Array.length jis0201 - 1 in let jis0208_mask = Array.length jis0208 - 1 in let jis0212_mask = Array.length jis0212 - 1 in let map p = (* Try in order: jis0208, jis0201, jis0212 *) let map_tbl jistbl jistbl_mask = match jistbl.(p land jistbl_mask) with Netmappings.U_nil -> -1 | Netmappings.U_single (p0,q0) -> if p0 = p then q0 else -1 | Netmappings.U_double (p0,q0,p1,q1) -> if p0 = p then q0 else if p1 = p then q1 else -1 | Netmappings.U_array pq -> let r = ref (-1) in let h = ref 0 in while !r < 0 && !h < Array.length pq do if pq.( !h ) = p then r := pq.( !h+1 ) else h := !h + 2 done; !r in let cp_0208 = map_tbl jis0208 jis0208_mask in if cp_0208 >= 0 then let row = cp_0208 / 96 in let col = cp_0208 - row * 96 in (1, row + 160, col + 160) else let cp_0201 = map_tbl jis0201 jis0201_mask in if cp_0201 >= 128 then (* Ignore especially 0x5c, 0x7e *) (2, cp_0201, 256) else let cp_0212 = map_tbl jis0212 jis0212_mask in if cp_0212 >= 0 then let row = cp_0212 / 96 in let col = cp_0212 - row * 96 in (3, row + 160, col + 160) else (4,256,256) in write_euc map `Enc_eucjp ;; let write_euckr () = let ks1001 = Netmappings.get_from_unicode "ks1001" in let ks1001_mask = Array.length ks1001 - 1 in let map p = let map_tbl kstbl kstbl_mask = match kstbl.(p land kstbl_mask) with Netmappings.U_nil -> -1 | Netmappings.U_single (p0,q0) -> if p0 = p then q0 else -1 | Netmappings.U_double (p0,q0,p1,q1) -> if p0 = p then q0 else if p1 = p then q1 else -1 | Netmappings.U_array pq -> let r = ref (-1) in let h = ref 0 in while !r < 0 && !h < Array.length pq do if pq.( !h ) = p then r := pq.( !h+1 ) else h := !h + 2 done; !r in let cp_1001 = map_tbl ks1001 ks1001_mask in if cp_1001 >= 0 then let row = cp_1001 / 96 in let col = cp_1001 - row * 96 in (1, row + 160, col + 160) else (4,256,256) in write_euc map `Enc_euckr ;; let special_cpoint = 0x110000;; let write_subset inner_writer def slice_char slice_pos slice_length s_out p_out l_out subst = assert(p_out >= 0 && p_out + l_out <= Bytes.length s_out && l_out >= 0); assert(slice_pos >= 0 && slice_pos+slice_length <= Array.length slice_char); (* Force that the subst' function is called for all undefined code * points *) let slice_char' = Array.sub slice_char slice_pos slice_length in for n = 0 to slice_length - 1 do let ch = slice_char'.(n) in if ch >= special_cpoint || not (def ch) then slice_char'.(n) <- special_cpoint + n done; let subst' ch = if ch >= special_cpoint then subst (slice_char.(slice_pos + ch - special_cpoint)) else subst ch in inner_writer slice_char' 0 slice_length s_out p_out l_out subst' ;; let back_8bit ops s_in range_in p_in n_char = let p_rel = p_in - range_in in let n = min p_rel n_char in (n,n) ;; let back_utf8 ops s_in range_in p_in n_char = let open Netstring_tstring in let n = ref 0 in let k = ref 0 in let k_out = ref 0 in while p_in - !k > range_in && !n < n_char do incr k; let ch = Char.code (ops.get s_in (p_in - !k)) in if ch < 0x80 || ( ch >= 0xc0 && ch <=0xfd) then ( incr n; k_out := !k ) done; ( !n, !k_out ) ;; let back_utf16_lebe lo hi ops s_in range_in p_in n_char = (* lo=0, hi=1: little endian * lo=1, hi=0: big endian *) let open Netstring_tstring in let n = ref 0 in let k = ref 0 in let k_out = ref 0 in while p_in - !k > range_in + 1 && !n < n_char do incr k; incr k; let ch = (Char.code (ops.get s_in (p_in - !k + lo))) lor ((Char.code (ops.get s_in (p_in - !k + hi))) lsl 8) in if ch < 0xdc00 || ch >= 0xe000 then ( incr n; k_out := !k ); (* else: ch is the second half of a surrogate pair *) done; ( !n, !k_out ) ;; let back_utf32 ops s_in range_in p_in n_char = let open Netstring_tstring in let p_rel = p_in - range_in in let n = min p_rel (n_char lsl 2) in (n asr 2,n) ;; let back_euc ops s_in range_in p_in n_char = (* Works for 1-byte and 2-byte encodings *) let open Netstring_tstring in let n = ref 0 in let k = ref 0 in let k_out = ref 0 in while p_in - !k > range_in && !n < n_char do incr k; let ch1 = Char.code (ops.get s_in (p_in - !k)) in if ch1 < 0x80 then ( incr n; k_out := !k ) else if p_in - !k > range_in then ( incr k; let ch2 = Char.code (ops.get s_in (p_in - !k)) in (* ch2 < 0x80: wrong, but we do not report errors here *) if ch2 < 0x80 then ( incr n; k_out := !k ) else if ch2 = 142 || ch2 = 143 then ( incr n; k_out := !k ) else if p_in - !k > range_in then ( let ch3 = Char.code (ops.get s_in (p_in - !k - 1)) in if ch3 = 142 || ch3 = 143 then ( incr k; incr n; k_out := !k ) else ( incr n; k_out := !k ) ) else ( (* At the beginning of the string *) incr n; k_out := !k ) ) done; ( !n, !k_out ) ;; let check_unicode p = if p < 0 || (p > 0xd7ff && p < 0xe000) || p = 0xfffe || p = 0xffff || p > 0x10ffff then raise Malformed_code ;; let rec to_unicode cs = match cs with `Set_iso88591 -> (fun p -> if p < 0 || p > 255 then raise Malformed_code; p) | `Set_usascii -> (fun p -> if p < 0 || p > 127 then raise Malformed_code; p) | `Set_unicode -> (fun p -> check_unicode p; p) | _ -> let m_to_uni = Netmappings.get_to_unicode (internal_name cs) in (fun p -> if p < 0 || p >= Array.length m_to_uni then raise Malformed_code; let uni = m_to_uni.(p) in if uni < 0 then raise Malformed_code; uni ) ;; let rec from_unicode cs = match cs with `Set_iso88591 -> (fun p -> check_unicode p; if p > 255 then raise (Cannot_represent p); p) | `Set_usascii -> (fun p -> check_unicode p; if p > 127 then raise (Cannot_represent p); p) | `Set_unicode -> (fun p -> check_unicode p; p) | _ -> let m_from_unicode = Netmappings.get_from_unicode (internal_name cs) in let m_mask = Array.length m_from_unicode - 1 in (fun p -> check_unicode p; let p' = match Array.unsafe_get m_from_unicode (p land m_mask) with Netmappings.U_nil -> -1 | Netmappings.U_single (p0,q0) -> if p0 = p then q0 else -1 | Netmappings.U_double (p0,q0,p1,q1) -> if p0 = p then q0 else if p1 = p then q1 else -1 | Netmappings.U_array pq -> let r = ref (-1) in let h = ref 0 in while !r < 0 && !h < Array.length pq do if pq.( !h ) = p then r := pq.( !h+1 ) else h := !h + 2 done; !r in if p' < 0 then raise(Cannot_represent p); p' ) ;; type encoding1 = [ encoding | `Enc_utf16_bom | `Enc_utf32_bom | `Enc_utf8_bom ] ;; (* `Enc_*_bom considers the BOM as a character with code point -3. * This encoding is only internally used. *) let rec get_reader1 (enc : encoding1) = (* get_reader1 supports the additional internal encodings of * encoding1. get_reader (below) only supports the exported * encodings. *) match enc with `Enc_iso88591 -> !read_iso88591_ref 255 `Enc_iso88591 | `Enc_usascii -> !read_iso88591_ref 127 `Enc_usascii | `Enc_empty -> !read_iso88591_ref (-1) `Enc_empty | `Enc_utf8 -> !read_utf8_ref false | `Enc_java -> !read_utf8_ref true | `Enc_utf8_opt_bom -> read_utf8_opt_bom false | `Enc_utf8_bom -> read_utf8_opt_bom true | `Enc_utf16 -> read_utf16 false | `Enc_utf16_bom -> read_utf16 true | `Enc_utf16_le -> read_utf16_lebe 0 1 0 `Enc_utf16_le | `Enc_utf16_be -> read_utf16_lebe 1 0 0 `Enc_utf16_be | `Enc_utf32 -> read_utf32 false | `Enc_utf32_bom -> read_utf32 true | `Enc_utf32_le -> read_utf32_lebe true 0 `Enc_utf32_le | `Enc_utf32_be -> read_utf32_lebe false 0 `Enc_utf32_be | `Enc_eucjp -> read_eucjp () | `Enc_euckr -> read_euckr () | `Enc_subset(e,def) -> let reader' = get_reader1 (e :> encoding1) in read_subset reader' def | #encoding as e -> read_8bit (e :> encoding) ;; let get_reader = (get_reader1 : encoding1 -> 'a :> encoding -> 'a);; let rec get_writer enc = match enc with `Enc_iso88591 -> write_iso88591 255 | `Enc_usascii -> write_iso88591 127 | `Enc_empty -> write_iso88591 (-1) | `Enc_utf8 -> write_utf8 false | `Enc_java -> write_utf8 true | `Enc_utf16 -> failwith "Netconversion: Cannot output text as `Enc_utf16, use `Enc_utf16_le or `Enc_utf16_be" | `Enc_utf16_le -> write_utf16_lebe 0 1 | `Enc_utf16_be -> write_utf16_lebe 1 0 | `Enc_utf32 -> failwith "Netconversion: Cannot output text as `Enc_utf32, use `Enc_utf32_le or `Enc_utf32_be" | `Enc_utf32_le -> write_utf32_lebe true | `Enc_utf32_be -> write_utf32_lebe false | `Enc_eucjp -> write_eucjp () | `Enc_euckr -> write_euckr () | `Enc_subset(e,def) -> let writer' = get_writer e in write_subset writer' def | _ -> write_8bit enc ;; let rec get_back_fn enc = match enc with | `Enc_utf8 | `Enc_java -> back_utf8 | `Enc_utf16 -> failwith "Netconversion: Cannot go back in text encoded as `Enc_utf16, use `Enc_utf16_le or `Enc_utf16_be" | `Enc_utf16_le -> back_utf16_lebe 0 1 | `Enc_utf16_be -> back_utf16_lebe 1 0 | `Enc_utf32 | `Enc_utf32_le | `Enc_utf32_be -> back_utf32 | `Enc_eucjp -> back_euc | `Enc_euckr -> back_euc | `Enc_subset(e,def) -> get_back_fn e | _ -> back_8bit ;; let recode_poly ~in_ops ~in_enc ~in_buf ~in_pos ~in_len ~out_enc ~out_buf ~out_pos ~out_len ~max_chars ~subst = let open Netstring_tstring in if (in_pos < 0 || in_len < 0 || in_pos + in_len > in_ops.length in_buf || out_pos < 0 || out_len < 0 || out_pos + out_len > Bytes.length out_buf) then invalid_arg "Netconversion.recode"; (* An array with 250 elements can be allocated in the minor heap. *) let slice_length = big_slice in let slice_char = Array.make slice_length (-1) in let slice_blen = Array.make slice_length 1 in let in_k = ref 0 in (* read bytes *) let in_n = ref 0 in (* read characters *) let in_eof = ref (!in_k >= in_len) in let out_k = ref 0 in (* written bytes *) let out_n = ref 0 in (* written characters *) let out_eof = ref (!out_k >= out_len || !out_n >= max_chars) in let rd_enc = ref in_enc in let reader = ref (get_reader in_enc) in let writer = get_writer out_enc in while not !in_eof && not !out_eof do let in_n_inc, in_k_inc, rd_enc' = try !reader.read in_ops slice_char slice_blen in_buf (in_pos + !in_k) (in_len - !in_k) with Malformed_code_read(in_n_inc, in_k_inc, rd_enc') -> if in_n_inc = 0 then raise Malformed_code; (in_n_inc, in_k_inc, rd_enc') in let out_n_inc_max = min in_n_inc (max_chars - !out_n) in (* do not write more than max_chars *) let out_n_inc, out_k_inc = if out_n_inc_max > 0 then writer slice_char 0 out_n_inc_max out_buf (out_pos + !out_k) (out_len - !out_k) subst else (0,0) in let in_n_inc', in_k_inc' = if in_n_inc > out_n_inc then begin (* Not all read characters could be written *) let sum = ref 0 in for j = 0 to out_n_inc - 1 do sum := !sum + slice_blen.(j) done; (out_n_inc, !sum) end else (in_n_inc, in_k_inc) in in_k := !in_k + in_k_inc'; in_n := !in_n + in_n_inc'; out_k := !out_k + out_k_inc; out_n := !out_n + out_n_inc; (* Detect change of input encoding: *) if rd_enc' <> !rd_enc then begin rd_enc := rd_enc'; reader := get_reader rd_enc'; Array.fill slice_blen 0 slice_length 1; end; (* EOF criteria: * - It is possible that !in_k never reaches in_len because there is a * multibyte character at the end that is partially outside the input * range * - For the same reason it is possible that !out_k never reaches out_len * - It is accepted as reader EOF if not even one character can be * scanned * - It is accepted as writer EOF if fewer than in_n_inc characters * could be written *) in_eof := (!in_k >= in_len || in_n_inc = 0); out_eof := (!out_k >= out_len || !out_n >= max_chars || out_n_inc < in_n_inc); done; ( !in_k, !out_k, !rd_enc ) ;; let recode = recode_poly ~in_ops:Netstring_tstring.string_ops let recode_bytes = recode_poly ~in_ops:Netstring_tstring.bytes_ops let recode_tstring ~in_enc ~in_buf ~in_pos ~in_len ~out_enc ~out_buf ~out_pos ~out_len ~max_chars ~subst = let f = { Netstring_tstring.with_fun = (fun in_ops in_buf -> recode_poly ~in_ops ~in_enc ~in_buf ~in_pos ~in_len ~out_enc ~out_buf ~out_pos ~out_len ~max_chars ~subst ) } in Netstring_tstring.with_tstring f in_buf let rec ustring_of_uchar enc = let multi_byte writer n p = let s = Bytes.create n in let _,n_act = writer [|p|] 0 1 s 0 n (fun _ -> raise (Cannot_represent p)) in Bytes.sub_string s 0 n_act in match enc with `Enc_iso88591 -> (fun p -> if p > 255 then raise (Cannot_represent p); String.make 1 (Char.chr p)) | `Enc_usascii -> (fun p ->if p > 127 then raise (Cannot_represent p); String.make 1 (Char.chr p)) | `Enc_utf8 | `Enc_utf8_opt_bom -> multi_byte (write_utf8 false) 4 | `Enc_java -> multi_byte (write_utf8 true) 4 | `Enc_utf16_le -> multi_byte (write_utf16_lebe 0 1) 4 | `Enc_utf16_be -> multi_byte (write_utf16_lebe 1 0) 4 | `Enc_utf16 -> invalid_arg "Netconversion.ustring_of_uchar: UTF-16 not possible" | `Enc_utf32_le -> multi_byte (write_utf32_lebe true) 4 | `Enc_utf32_be -> multi_byte (write_utf32_lebe false) 4 | `Enc_utf32 -> invalid_arg "Netconversion.ustring_of_uchar: UTF-32 not possible" | `Enc_eucjp -> multi_byte (write_eucjp()) 3 | `Enc_euckr -> multi_byte (write_euckr()) 2 | `Enc_subset(e,def) -> (fun p -> if def p then ustring_of_uchar e p else raise (Cannot_represent p)) | _ -> let writer = write_8bit enc in multi_byte writer 1 ;; let makechar enc = let us = ustring_of_uchar enc in (fun p -> try us p with Cannot_represent _ -> raise Not_found) ;; (* The following algorithms assume that there is an upper limit of the length * of a multibyte character. Currently, UTF8 is the encoding with the longest * multibyte characters (6 bytes). * Because of this limit, it is allowed to allocate a buffer that is "large * enough" in order to ensure that at least one character is recoded in every * loop cycle. If the buffer was not large enough, no character would be * processed in a cycle, and the algorithm would hang. *) let convert_poly : type s t . in_ops:s Netstring_tstring.tstring_ops -> out_kind:t Netstring_tstring.tstring_kind -> ?subst:(int -> string) -> in_enc:encoding -> out_enc:encoding -> ?range_pos:int -> ?range_len:int -> s -> t = fun ~in_ops ~out_kind ?(subst = (fun p -> raise (Cannot_represent p))) ~in_enc ~out_enc ?(range_pos=0) ?range_len s -> let open Netstring_tstring in let range_len = match range_len with Some l -> l | None -> in_ops.length s - range_pos in if range_pos < 0 || range_len < 0 || range_pos+range_len > in_ops.length s then invalid_arg "Netconversion.convert"; (* Estimate the size of the output string: * length * 2 is just guessed. It is assumed that this number is usually * too large, and to avoid that too much memory is wasted, the buffer is * limited by 10000. *) let size = ref (max multibyte_limit (min 10000 (range_len * 2))) in let out_buf = ref (Bytes.create !size) in let k_in = ref 0 in let k_out = ref 0 in while !k_in < range_len do let in_len = range_len - !k_in in let out_len = !size - !k_out in assert (out_len >= multibyte_limit); (* space for at least one char *) let k_in_inc, k_out_inc, in_enc' = recode_poly ~in_ops ~in_enc ~in_buf:s ~in_pos:(range_pos + !k_in) ~in_len ~out_enc ~out_buf:(!out_buf) ~out_pos:(!k_out) ~out_len ~max_chars:max_int ~subst in if k_in_inc = 0 then raise Malformed_code; (* Reasons for k_in_inc = 0: * (1) There is not enough space in out_buf to add a single character * (2) in_buf ends with a prefix of a multi-byte character * Because there is always space for at least one character * ( = multibyte_limit ), reason (1) can be excluded. So it must * be (2), and we can raise Malformed_code. *) k_in := !k_in + k_in_inc; k_out := !k_out + k_out_inc; (* double the size of out_buf: *) let size' = min Sys.max_string_length (!size + !size) in if size' < !size + multibyte_limit then failwith "Netconversion.convert: string too long"; let out_buf' = Bytes.create size' in Bytes.blit !out_buf 0 out_buf' 0 !k_out; out_buf := out_buf'; size := size'; done; match out_kind with | Netstring_tstring.String_kind -> Bytes.sub_string !out_buf 0 !k_out | Netstring_tstring.Bytes_kind -> Bytes.sub !out_buf 0 !k_out | Netstring_tstring.Memory_kind -> let m = Bigarray.Array1.create Bigarray.char Bigarray.c_layout !k_out in Netsys_mem.blit_bytes_to_memory !out_buf 0 m 0 !k_out; m ;; let convert ?subst ~in_enc ~out_enc ?range_pos ?range_len s = convert_poly ?subst ~in_ops:Netstring_tstring.string_ops ~out_kind:Netstring_tstring.String_kind ~in_enc ~out_enc ?range_pos ?range_len s let convert_bytes ?subst ~in_enc ~out_enc ?range_pos ?range_len s = convert_poly ?subst ~in_ops:Netstring_tstring.bytes_ops ~out_kind:Netstring_tstring.Bytes_kind ~in_enc ~out_enc ?range_pos ?range_len s let convert_tstring ?subst ~in_enc ~out_enc ~out_kind ?range_pos ?range_len ts = let f = { Netstring_tstring.with_fun = (fun in_ops s -> convert_poly ?subst ~in_ops ~out_kind ~in_enc ~out_enc ?range_pos ?range_len s ) } in Netstring_tstring.with_tstring f ts class conversion_pipe ?(subst = (fun p -> raise (Cannot_represent p))) ~in_enc ~out_enc () = let current_in_enc = ref in_enc in let conv in_netbuf at_eof out_netbuf = if at_eof then (* TODO: avoid the extra allocations *) let s = convert_bytes ~subst ~in_enc:!current_in_enc ~out_enc (Netbuffer.unsafe_buffer in_netbuf) in Netbuffer.add_bytes out_netbuf s else let in_buf = Netbuffer.unsafe_buffer in_netbuf in let in_pos = 0 in let in_len = Netbuffer.length in_netbuf in let n = Netbuffer.add_inplace out_netbuf (fun out_buf out_pos out_len -> let (in_n,out_n,in_enc') = recode_bytes ~in_enc:!current_in_enc ~in_buf ~in_pos ~in_len ~out_enc ~out_buf ~out_pos ~out_len ~max_chars:out_len ~subst in Netbuffer.delete in_netbuf 0 in_n; current_in_enc := in_enc'; out_n ) in if n = 0 && in_len > 0 then begin (* To avoid endless loops, ensure here that there is enough space * in out_netbuf *) ignore(Netbuffer.add_inplace ~len:multibyte_limit out_netbuf (fun _ _ _ -> 0)); end; () in Netchannels.pipe ~conv () ;; (**********************************************************************) (* Cursors *) (**********************************************************************) (* The "read_*" functions are used to scan the string, and to move * the cursor forward. The slice array stores the scanned characters. * If the read call raises Malformed_code, the size of the slice * is decreased to 1, so the exact position can be calculated. *) (* Notes UTF-8/16/32 with BOM handling: * * cursor_enc is updated after the first slice has been read. This * usually changes this field to either the big or little endian * encoding variant. No update is needed when previous slices are * scanned, because the BOM is only allowed at the beginning of the * string, so can at most go back to exactly the BOM. * * cursor_encoding returns `Enc_utf16 when the cursor is over the * BOM, and cursor_enc otherwise. *) exception End_of_string;; exception Cursor_out_of_range;; exception Partial_character;; exception Byte_order_mark;; type 's poly_cursor = { (* configuration: *) cursor_ops : 's Netstring_tstring.tstring_ops; mutable cursor_target : 's; mutable cursor_range_pos : int; mutable cursor_range_len : int; mutable cursor_offset : int; mutable cursor_enc : encoding; (* `Enc_utf16: Only used if the slice or string is too short to * recognize the endianess. Otherwise, the encoding is set * to the endian-aware variant. * `Enc_utf32: same *) mutable cursor_has_bom : bool; (* Whether there is a BOM. Only when initially cursor_enc=`Enc_utf16 or utf32 *) (* conversion: *) mutable cursor_slice_char : int array; (* Contains the characters of the slice. Special values: * -1: EOF * -2: Incomplete multi-byte character at end * -3: BOM at the beginning *) mutable cursor_slice_blen : int array; (* Contains the byte length of the characters. * Recall that this array must contain 1s when single-byte * encodings are scanned, and must not be modified. The * "reader" does not fill this array for single-byte encodings, * so modifications would persist! *) mutable cursor_imbchar_len : int; (* This is always 0, except in the special case when the first * character of this slice is EOF, and EOF is preceded by an * incomplete multi-byte character (imbchar). In this case, * the length of the imbchar is stored here. *) mutable cursor_slice_char_pos : int; (* char pos of the beginning of the slice *) mutable cursor_slice_byte_pos : int; (* byte pos of the beginning of the slice *) mutable cursor_slice_length : int; (* number of characters *) mutable cursor_slice_bytes : int; (* number of bytes *) (* bookkeeping: *) mutable cursor_char_pos : int; mutable cursor_byte_pos : int; mutable cursor_index : int; (* index in the slice array *) mutable cursor_problem_range_start : int; mutable cursor_problem_range_end : int; (* The character positions >= range_start and < range_end are * considered as problem range. It is known that there is a * coding error (Malformed_code), so slices with length 1 must * be used. *) (* methods: *) mutable load_next_slice : unit -> unit; (* Precondition: cursor is one char right of the end of the slice * Action: load the next slice * Postcondition: cursor is at the beginning of the new slice *) mutable load_prev_slice : unit -> unit; (* Precondition: cursor is at the beginning of current slice * Action: load the previous slice * Postcondition: the cursor is at the end of the new slice * or the function raises Cursor_out_of_range * Note that this function actually moves the cursor one character * back (in contrast to load_next_slice that only reloads the * slice array, but does not move the cursor). The function may * choose to allocate a new, shorter slice array. *) } ;; type cursor = string poly_cursor let cursor_target cs = cs.cursor_target;; let cursor_range cs = (cs.cursor_range_pos, cs.cursor_range_len);; let cursor_initial_rel_pos cs = cs.cursor_offset;; let cursor_char_count cs = cs.cursor_char_pos;; let cursor_pos cs = cs.cursor_byte_pos;; let cursor_encoding cs = let enc = cs.cursor_enc in match enc with ( `Enc_utf16_le | `Enc_utf16_be ) when cs.cursor_has_bom -> if cs.cursor_byte_pos = cs.cursor_range_pos then `Enc_utf16 else enc | ( `Enc_utf32_le | `Enc_utf32_be ) when cs.cursor_has_bom -> if cs.cursor_byte_pos = cs.cursor_range_pos then `Enc_utf32 else enc | (`Enc_utf8 | `Enc_utf8_opt_bom) when cs.cursor_has_bom -> if cs.cursor_byte_pos = cs.cursor_range_pos then `Enc_utf8_opt_bom else enc | _ -> enc ;; exception Failing_in_Netconversion_uchar_at let uchar_at cs = let ch = cs.cursor_slice_char.(cs.cursor_index) in if ch < 0 then match ch with -1 -> raise End_of_string | -2 -> raise Partial_character | -3 -> raise Byte_order_mark | _ -> (* assert false *) raise Failing_in_Netconversion_uchar_at (* "assert false" isn't inlined! *) else ch ;; let cursor_byte_length cs = let ch = cs.cursor_slice_char.(cs.cursor_index) in if ch = -1 then raise End_of_string else cs.cursor_slice_blen.(cs.cursor_index) ;; let cursor_at_end cs = let ch = cs.cursor_slice_char.(cs.cursor_index) in ch = (-1) ;; let move_right num cs = let rec go num = let sl = Array.length cs.cursor_slice_char in if num >= sl - cs.cursor_index then begin (* Case: go at least to the next slice *) (* If the current slice is not completely filled, we will be * definitely outside of the valid range *) if cs.cursor_slice_length < sl then begin (* move to rightmost position, and raise the approriate exception *) cs.cursor_byte_pos <- cs.cursor_slice_byte_pos + cs.cursor_slice_bytes; cs.cursor_char_pos <- cs.cursor_slice_char_pos + cs.cursor_slice_length; cs.cursor_index <- cs.cursor_slice_length; assert(cs.cursor_slice_char.(cs.cursor_index) = (-1)); raise Cursor_out_of_range; end; assert(cs.cursor_slice_length = sl); let n = sl - cs.cursor_index in cs.cursor_byte_pos <- cs.cursor_slice_byte_pos + cs.cursor_slice_bytes; cs.cursor_char_pos <- cs.cursor_slice_char_pos + cs.cursor_slice_length; cs.cursor_index <- sl; cs.load_next_slice(); (* may raise Malformed_code *) go (num - n); end else begin (* Case: do not leave this slice *) let bl_sum = ref 0 in for k = cs.cursor_index to cs.cursor_index + num - 1 do let bl = cs.cursor_slice_blen.(k) in if k >= cs.cursor_slice_length then begin (* Cursor is beyond EOF *) cs.cursor_byte_pos <- cs.cursor_byte_pos + !bl_sum; cs.cursor_char_pos <- cs.cursor_char_pos + (k - cs.cursor_index); cs.cursor_index <- k; raise Cursor_out_of_range end; bl_sum := !bl_sum + bl done; cs.cursor_byte_pos <- cs.cursor_byte_pos + !bl_sum; cs.cursor_char_pos <- cs.cursor_char_pos + num; cs.cursor_index <- cs.cursor_index + num; end in assert(num >= 0); try go num with Malformed_code -> (* This happens when load_next_slice fails to decode the next slice * of length 1. In this case, load_next_slice keeps the state of * the cursor, so we have the chance to correct it now. *) cs.cursor_index <- cs.cursor_index - 1; cs.cursor_char_pos <- cs.cursor_char_pos - 1; cs.cursor_byte_pos <- cs.cursor_byte_pos - cs.cursor_slice_blen.(cs.cursor_index); raise Malformed_code ;; let move_left num cs = let rec go num = if num > cs.cursor_index then begin let n = cs.cursor_index in cs.cursor_byte_pos <- cs.cursor_slice_byte_pos; cs.cursor_char_pos <- cs.cursor_slice_char_pos; cs.cursor_index <- 0; (* cursor is now at the beginning of the slice *) cs.load_prev_slice(); (* go another character back *) go (num-n-1) (* so we went n+1 characters in this round *) end else begin (* num <= cs.cursor_index *) let bl_sum = ref 0 in let n = cs.cursor_index - num in for k = cs.cursor_index - 1 downto n do bl_sum := !bl_sum + cs.cursor_slice_blen.(k) done; cs.cursor_byte_pos <- cs.cursor_byte_pos - !bl_sum; cs.cursor_char_pos <- cs.cursor_char_pos - num; cs.cursor_index <- n; end in assert(num < 0); go (-num) ;; let move ?(num = 1) cs = if num >= 0 then move_right num cs else move_left num cs ;; let init_load_slice cs enc = let open Netstring_tstring in let ops = cs.cursor_ops in let reader0 = (get_reader enc).read ops in let back0 = lazy(get_back_fn enc ops) in (* For most encodings, [reader] and [back] never change. * For UTF-16, there may be refinements, however. *) let reader() = match cs.cursor_enc with ( `Enc_utf16 | `Enc_utf16_le | `Enc_utf16_be ) when cs.cursor_has_bom -> (* Ensure we use `Enc_utf16_bom when we read the beginning * of the range *) (fun slice_char slice_blen s bp bl -> if bp = cs.cursor_range_pos then (get_reader1 `Enc_utf16_bom).read ops slice_char slice_blen s bp bl else (get_reader cs.cursor_enc).read ops slice_char slice_blen s bp bl ) | ( `Enc_utf32 | `Enc_utf32_le | `Enc_utf32_be ) when cs.cursor_has_bom -> (* Ensure we use `Enc_utf32_bom when we read the beginning * of the range *) (fun slice_char slice_blen s bp bl -> if bp = cs.cursor_range_pos then (get_reader1 `Enc_utf32_bom).read ops slice_char slice_blen s bp bl else (get_reader cs.cursor_enc).read ops slice_char slice_blen s bp bl ) | ( `Enc_utf8 | `Enc_utf8_opt_bom ) when cs.cursor_has_bom -> (fun slice_char slice_blen s bp bl -> if bp = cs.cursor_range_pos then (get_reader1 `Enc_utf8_bom).read ops slice_char slice_blen s bp bl else (get_reader cs.cursor_enc).read ops slice_char slice_blen s bp bl ) | _ -> reader0 in let back() = match cs.cursor_enc with ( `Enc_utf16 | `Enc_utf16_le | `Enc_utf16_be ) when cs.cursor_has_bom -> get_back_fn cs.cursor_enc ops | ( `Enc_utf32 | `Enc_utf32_le | `Enc_utf32_be ) when cs.cursor_has_bom -> get_back_fn cs.cursor_enc ops | ( `Enc_utf8 | `Enc_utf8_opt_bom ) when cs.cursor_has_bom -> get_back_fn cs.cursor_enc ops | _ -> Lazy.force back0 in let record_imbchar rd_chars rd_bytes scan_bytes = (* Put a (-2) at position rd_chars of the current slice *) cs.cursor_slice_char.(rd_chars) <- (-2); cs.cursor_slice_blen.(rd_chars) <- scan_bytes - rd_bytes; if rd_chars+1 < Array.length cs.cursor_slice_char then ( cs.cursor_slice_char.(rd_chars+1) <- (-1); ); cs.cursor_slice_length <- rd_chars+1; cs.cursor_slice_bytes <- scan_bytes; in let repair_slice slice_size = (* When the reader raises Malformed_code, the slice has been * modified. This function reloads the old slice again. * * This function repairs these fields from the other fields: * - cursor_slice_char * - cursor_slice_blen * - cursor_slice_length * - cursor_slice_bytes *) let bp = cs.cursor_slice_byte_pos in let ep = cs.cursor_range_pos + cs.cursor_range_len in let (slice_char, slice_blen) = (Array.make slice_size (-1), Array.make slice_size 1) in let rd_chars, rd_bytes, _ = try reader () slice_char slice_blen cs.cursor_target bp (ep-bp) with (* should not happen: *) Malformed_code_read(_,_,_) -> raise Malformed_code in cs.cursor_slice_length <- rd_chars; cs.cursor_slice_bytes <- rd_bytes; cs.cursor_slice_char <- slice_char; cs.cursor_slice_blen <- slice_blen; (* Check for imbchars: *) if rd_chars < slice_size && rd_bytes < ep-bp then ( record_imbchar rd_chars rd_bytes (ep-bp); ); in let load_next_slice() = let cp = cs.cursor_char_pos in let bp = cs.cursor_byte_pos in let ep = cs.cursor_range_pos + cs.cursor_range_len in let load slice_size = let old_partial_len = (* Handle the case that the last character is (-2), and thus the first * character of the next slice will be (-1). Then, cursor_imbchar_len * must be set to the length of the (-2) character. *) if cs.cursor_slice_char.(cs.cursor_slice_length-1) = (-2) then cs.cursor_slice_blen.(cs.cursor_slice_length-1) else 0 in (* Check if the current array can be reused, or if we need new * arrays with different sizes *) let (slice_char, slice_blen) = if slice_size = Array.length cs.cursor_slice_char then (cs.cursor_slice_char, cs.cursor_slice_blen) (* use old arrays again *) else (Array.make slice_size (-1), Array.make slice_size 1) (* create new arrays with different size *) in (* Use the reader to decode the bytes and to put the characters into * slice_char. *) let rd_chars, rd_bytes, enc' = reader () slice_char slice_blen cs.cursor_target bp (ep-bp) in (* may raise Malformed_code_read *) (* Update cursor record: *) cs.cursor_index <- 0; cs.cursor_slice_char <- slice_char; cs.cursor_slice_blen <- slice_blen; cs.cursor_slice_length <- rd_chars; cs.cursor_slice_bytes <- rd_bytes; cs.cursor_slice_char_pos <- cp; cs.cursor_slice_byte_pos <- bp; cs.cursor_imbchar_len <- old_partial_len; cs.cursor_enc <- enc'; (* Check for imbchars: *) if rd_chars < slice_size && rd_bytes < ep-bp then ( record_imbchar rd_chars rd_bytes (ep-bp); ); in (* Is the cursor positioned in a problem range? If yes, decode only * one character. If not, try to decode a block of characters. * If the latter fails, the current position turns out to be * problematic, and is remembered as such. *) let old_slice_size = Array.length cs.cursor_slice_char in if cp >= cs.cursor_problem_range_start && cp < cs.cursor_problem_range_end then begin try load 1 with Malformed_code_read(_,_,_) -> repair_slice old_slice_size; raise Malformed_code end else begin try load big_slice with Malformed_code_read(_,_,_) -> cs.cursor_problem_range_start <- cp; cs.cursor_problem_range_end <- cp+big_slice; try load 1 with Malformed_code_read(_,_,_) -> repair_slice old_slice_size; raise Malformed_code end in let load_prev_slice() = let cp = cs.cursor_char_pos in let bp = cs.cursor_byte_pos in let ep = cs.cursor_range_pos + cs.cursor_range_len in let load slice_size = (* Check if the current array can be reused, or if we need new * arrays with different sizes *) let (slice_char, slice_blen) = if slice_size = Array.length cs.cursor_slice_char then (cs.cursor_slice_char, cs.cursor_slice_blen) (* use old arrays again *) else (Array.make slice_size (-1), Array.make slice_size 1) (* create new arrays with different size *) in (* Go back 1 character (must always succeed): *) if bp = cs.cursor_range_pos then raise Cursor_out_of_range; let bk1_chars, bk1_bytes = if cs.cursor_imbchar_len > 0 then (* Special case: the last character of this slice is an imbchar. * Assume imbchar_len *) (1, cs.cursor_imbchar_len) else back () cs.cursor_target cs.cursor_range_pos bp 1 in if bk1_chars = 0 then raise Malformed_code; (* bk1_chars = 0: this means there is a multi-byte suffix at the * beginning of the range * ==> bk1_chars = 1 *) (* Go back further slice_size-1 characters (or less): *) let bk_chars, bk_bytes = back () cs.cursor_target cs.cursor_range_pos (bp-bk1_bytes) (slice_size-1) in let bp' = bp - bk1_bytes - bk_bytes in (* Use the reader to decode the bytes and to put the characters into * slice_char. *) let rd_chars, rd_bytes, _ = reader () slice_char slice_blen cs.cursor_target bp' (ep-bp') in (* may raise Malformed_code_read *) assert(rd_chars >= bk_chars); (* Update cursor record: *) cs.cursor_index <- bk_chars; cs.cursor_slice_char <- slice_char; cs.cursor_slice_blen <- slice_blen; cs.cursor_slice_length <- rd_chars; cs.cursor_slice_bytes <- rd_bytes; cs.cursor_slice_char_pos <- cp - bk_chars - 1; cs.cursor_slice_byte_pos <- bp'; cs.cursor_imbchar_len <- 0; (* Cannot happen *) (* Don't need to update cursor_enc! *) (* Check for imbchars: *) if rd_chars < slice_size && rd_bytes < ep-bp' then ( record_imbchar rd_chars rd_bytes (ep-bp'); ); (* Implicitly go one character back: *) cs.cursor_char_pos <- cp - 1; cs.cursor_byte_pos <- bp - bk1_bytes; in (* Is the cursor positioned in a problem range? If yes, decode only * one character. If not, try to decode a block of characters. * If the latter fails, the current position turns out to be * problematic, and is remembered as such. *) let old_slice_size = Array.length cs.cursor_slice_char in if cp > cs.cursor_problem_range_start && cp <= cs.cursor_problem_range_end then begin try load 1 with Malformed_code_read(_,_,_) -> repair_slice old_slice_size; raise Malformed_code end else begin try load big_slice with Malformed_code_read(_,_,_) -> cs.cursor_problem_range_start <- cp-big_slice; cs.cursor_problem_range_end <- cp; try load 1 with Malformed_code_read(_,_,_) -> repair_slice old_slice_size; raise Malformed_code end in (* Important note: These two functions either modify the cursor state * as requested, or they raise an exception, and keep the cursor state * as before. Considered exceptions are Malformed_code, and * Cursor_out_of_range. *) cs.load_next_slice <- load_next_slice; cs.load_prev_slice <- load_prev_slice ;; let create_poly_cursor ?(range_pos = 0) ?range_len ?(initial_rel_pos = 0) enc ops s = let open Netstring_tstring in if range_pos < 0 || range_pos > ops.length s then invalid_arg "Netconversion.create_cursor"; let range_len = match range_len with Some l -> l | None -> ops.length s - range_pos in if range_len < 0 || range_pos + range_len > ops.length s then invalid_arg "Netconversion.create_cursor"; if initial_rel_pos < 0 || initial_rel_pos > range_len then invalid_arg "Netconversion.create_cursor"; if enc = `Enc_utf16 && initial_rel_pos <> 0 then failwith "Netconversion.create_cursor: The encoding `Enc_utf16 only supported when initial_rel_pos=0"; if enc = `Enc_utf32 && initial_rel_pos <> 0 then failwith "Netconversion.create_cursor: The encoding `Enc_utf32 only supported when initial_rel_pos=0"; let cs = { cursor_ops = ops; cursor_target = s; cursor_range_pos = range_pos; cursor_range_len = range_len; cursor_offset = initial_rel_pos; cursor_enc = enc; cursor_has_bom = (enc = `Enc_utf16 || enc = `Enc_utf32 || enc = `Enc_utf8_opt_bom); cursor_slice_char = [| 1 |]; cursor_slice_blen = [| 1 |]; cursor_imbchar_len = 0; cursor_slice_char_pos = 0; cursor_slice_byte_pos = range_pos + initial_rel_pos; cursor_slice_length = 1; cursor_slice_bytes = 0; cursor_char_pos = 0; cursor_byte_pos = range_pos + initial_rel_pos; cursor_index = 1; cursor_problem_range_start = max_int; cursor_problem_range_end = max_int; load_next_slice = (fun () -> assert false); load_prev_slice = (fun () -> assert false); } in init_load_slice cs enc; (* load the next slice to do the rest of the initialization: *) cs.load_next_slice(); cs ;; let create_cursor ?range_pos ?range_len ?initial_rel_pos enc s = let ops = Netstring_tstring.string_ops in create_poly_cursor ?range_pos ?range_len ?initial_rel_pos enc ops s type 'a with_cursor_fun = { with_cursor_fun : 's . 's Netstring_tstring.tstring_ops -> 's poly_cursor -> 'a } let with_tstring_cursor ?range_pos ?range_len ?initial_rel_pos enc ts f = let f = { Netstring_tstring.with_fun = (fun ops s -> f.with_cursor_fun ops (create_poly_cursor ?range_pos ?range_len ?initial_rel_pos enc ops s) ) } in Netstring_tstring.with_tstring f ts let reinit_cursor ?(range_pos = 0) ?range_len ?(initial_rel_pos = 0) ?enc s cs = let open Netstring_tstring in let ops = cs.cursor_ops in if range_pos < 0 || range_pos > ops.length s then invalid_arg "Netconversion.reinit_cursor"; let range_len = match range_len with Some l -> l | None -> ops.length s - range_pos in if range_len < 0 || range_pos + range_len > ops.length s then invalid_arg "Netconversion.reinit_cursor"; if initial_rel_pos < 0 || initial_rel_pos > range_len then invalid_arg "Netconversion.reinit_cursor"; let enc = match enc with None -> cs.cursor_enc | Some e -> e in if enc = `Enc_utf16 && initial_rel_pos <> 0 then failwith "Netconversion.reinit_cursor: The encoding `Enc_utf16 only supported when initial_rel_pos=0"; if enc = `Enc_utf32 && initial_rel_pos <> 0 then failwith "Netconversion.reinit_cursor: The encoding `Enc_utf32 only supported when initial_rel_pos=0"; let old_enc = cs.cursor_enc in cs.cursor_target <- s; cs.cursor_range_pos <- range_pos; cs.cursor_range_len <- range_len; cs.cursor_offset <- initial_rel_pos; cs.cursor_enc <- enc; cs.cursor_has_bom <- (enc = `Enc_utf16 || enc = `Enc_utf32 || enc = `Enc_utf8_opt_bom); cs.cursor_imbchar_len <- 0; cs.cursor_slice_char_pos <- 0; cs.cursor_slice_byte_pos <- range_pos + initial_rel_pos; cs.cursor_slice_length <- 1; cs.cursor_slice_bytes <- 0; cs.cursor_char_pos <- 0; cs.cursor_byte_pos <- range_pos + initial_rel_pos; cs.cursor_index <- 1; cs.cursor_problem_range_start <- max_int; cs.cursor_problem_range_end <- max_int; cs.load_next_slice <- (fun () -> assert false); cs.load_prev_slice <- (fun () -> assert false); cs.cursor_slice_char.(0) <- 1; if not (same_encoding enc old_enc) then (* slice_blen: It might have happened that the new encoding is an * 8 bit charset, but the old was not. Re-initialize this array * to ensure it contains only "1" in this case. *) Array.fill cs.cursor_slice_blen 0 (Array.length cs.cursor_slice_blen) 1; init_load_slice cs enc; (* load the next slice to do the rest of the initialization: *) cs.load_next_slice(); ;; let copy_cursor ?enc cs = let enc = match enc with None -> cs.cursor_enc | Some e -> e in if same_encoding enc cs.cursor_enc then { cs with cursor_slice_char = Array.copy cs.cursor_slice_char; cursor_slice_blen = Array.copy cs.cursor_slice_blen; } else begin if enc = `Enc_utf16 then failwith "Netconversion.copy_cursor: The encoding `Enc_utf16 is not supported"; if enc = `Enc_utf32 then failwith "Netconversion.copy_cursor: The encoding `Enc_utf32 is not supported"; let cs' = { cs with cursor_enc = enc; cursor_slice_char = [| 1 |]; cursor_slice_blen = [| 1 |]; cursor_slice_length = 1; cursor_problem_range_start = max_int; cursor_problem_range_end = max_int; } in init_load_slice cs' enc; (* load the next slice to do the rest of the initialization: *) cs'.load_next_slice(); cs' end ;; let cursor_blit_maxlen cs = let l = cs.cursor_slice_length - cs.cursor_index in (* Test on special situations: *) match cs.cursor_slice_char.(cs.cursor_index) with -1 -> (* EOF *) raise End_of_string | -3 -> (* BOM *) 0 | _ -> if cs.cursor_slice_char.(cs.cursor_slice_length - 1) = (-2) then (* Partial character *) l-1 else l ;; let cursor_blit cs ua pos len = if pos < 0 || len < 0 || pos+len > Array.length ua then invalid_arg "Netconversion.cursor_blit"; let cs_len = cursor_blit_maxlen cs in let l = min cs_len len in int_blit cs.cursor_slice_char cs.cursor_index ua pos l; l ;; let cursor_blit_positions cs ua pos len = if pos < 0 || len < 0 || pos+len > Array.length ua then invalid_arg "Netconversion.cursor_blit_positions"; let cs_len = cursor_blit_maxlen cs in let l = min cs_len len in let p = cs.cursor_byte_pos in let blen = cs.cursor_slice_blen in let cidx = cs.cursor_index in assert(pos+l <= Array.length ua); assert(cidx+l <= Array.length cs.cursor_slice_blen); Netaux.ArrayAux.int_series blen cidx ua pos l p; l ;; (**********************************************************************) (* String functions *) (**********************************************************************) (* CHECK * - ustring_length: Count imbchars? No! * * DOC: * - imbchar handling (additional exceptions) *) let ustring_length_poly ops enc = let open Netstring_tstring in if is_single_byte enc then fun ?(range_pos=0) ?range_len s -> let range_len = match range_len with None -> ops.length s - range_pos | Some l -> l in if range_pos < 0 || range_len < 0 || range_pos+range_len > ops.length s then invalid_arg "Netconversion.ustring_length"; range_len else fun ?range_pos ?range_len s -> (* Assumption: There is no string that has more than max_int * characters *) let cs = create_poly_cursor ?range_pos ?range_len enc ops s in ( try move ~num:max_int cs with Cursor_out_of_range -> ()); let n = cursor_char_count cs in (* Check that the last char is not an imbchar *) ( try move ~num:(-1) cs; let _ = uchar_at cs in () with Cursor_out_of_range -> () | Partial_character -> raise Malformed_code ); n ;; let ustring_length enc = ustring_length_poly Netstring_tstring.string_ops enc let ustring_length_ts enc ?range_pos ?range_len ts = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops s -> ustring_length_poly ops enc ?range_pos ?range_len s ) } ts exception Malformed_code_at of int;; let verify_poly ops enc ?range_pos ?range_len s = let cs = try create_poly_cursor ?range_pos ?range_len enc ops s with Malformed_code -> raise (Malformed_code_at 0) | _ -> assert false in ( try move ~num:max_int cs with Cursor_out_of_range -> () | Malformed_code -> (* Now cursor_pos is the byte position of the last valid * character. Add the length of this character. *) let n = cs.cursor_slice_blen.(cs.cursor_index) in raise (Malformed_code_at (cs.cursor_byte_pos + n)) ); (* Now we are at EOF. Check this. Furthermore, check whether there is * an imbchar just before EOF: *) ( try let _ = uchar_at cs in assert false with End_of_string -> () ); ( try move ~num:(-1) cs; let _ = uchar_at cs in () with Cursor_out_of_range -> () (* empty string *) | Partial_character -> raise (Malformed_code_at (cs.cursor_byte_pos)) ); () ;; let verify enc = verify_poly Netstring_tstring.string_ops enc let verify_ts enc ?range_pos ?range_len ts = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops s -> verify_poly ops enc ?range_pos ?range_len s ) } ts let ustring_iter_poly ops enc f ?range_pos ?range_len s = let cs = create_poly_cursor ?range_pos ?range_len enc ops s in try while true do let ch = uchar_at cs in (* or End_of_string *) f ch; move cs done; assert false with End_of_string -> () | Partial_character -> raise Malformed_code ;; let ustring_iter enc = ustring_iter_poly Netstring_tstring.string_ops enc let ustring_iter_ts enc f ?range_pos ?range_len ts = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops s -> ustring_iter_poly ops enc f ?range_pos ?range_len s ) } ts let ustring_map_poly ops out_kind enc f ?range_pos ?range_len s = (* The following algorithm works only if the mapped lists are short: let mkch = ustring_of_uchar enc in let subst p = let p' = f p in String.concat "" (List.map mkch p') in convert ~subst ~in_enc:enc ~out_enc:`Enc_empty ?range_pos ?range_len s *) let buf = Netbuffer.create 250 in ustring_iter_poly ops enc (fun p -> let l = f p in Netbuffer.add_string buf (String.concat "" (List.map (ustring_of_uchar enc) l)) ) ?range_pos ?range_len s; Netbuffer.to_tstring_poly buf out_kind ;; let ustring_map enc = ustring_map_poly Netstring_tstring.string_ops Netstring_tstring.String_kind enc let ustring_map_ts enc f ?range_pos ?range_len ts = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops s -> match ts with | `String _ -> let kind = Netstring_tstring.String_kind in `String( ustring_map_poly ops kind enc f ?range_pos ?range_len s) | `Bytes _ -> let kind = Netstring_tstring.Bytes_kind in `Bytes( ustring_map_poly ops kind enc f ?range_pos ?range_len s) | `Memory _ -> let kind = Netstring_tstring.Memory_kind in `Memory( ustring_map_poly ops kind enc f ?range_pos ?range_len s) ) } ts let ustring_to_lower enc ?range_pos ?range_len s = let f x = [ Netunichar.to_lower x ] in ustring_map enc f ?range_pos ?range_len s ;; let ustring_to_lower_ts enc ?range_pos ?range_len ts = let f x = [ Netunichar.to_lower x ] in ustring_map_ts enc f ?range_pos ?range_len ts ;; let ustring_to_lower_poly ops kind enc ?range_pos ?range_len ts = let f x = [ Netunichar.to_lower x ] in ustring_map_poly ops kind enc f ?range_pos ?range_len ts ;; let ustring_to_upper enc ?range_pos ?range_len s = let f x = [ Netunichar.to_upper x ] in ustring_map enc f ?range_pos ?range_len s ;; let ustring_to_upper_ts enc ?range_pos ?range_len ts = let f x = [ Netunichar.to_upper x ] in ustring_map_ts enc f ?range_pos ?range_len ts ;; let ustring_to_upper_poly ops kind enc ?range_pos ?range_len ts = let f x = [ Netunichar.to_upper x ] in ustring_map_poly ops kind enc f ?range_pos ?range_len ts ;; let ustring_to_title enc ?range_pos ?range_len s = let f x = [ Netunichar.to_title x ] in ustring_map enc f ?range_pos ?range_len s ;; let ustring_to_title_ts enc ?range_pos ?range_len ts = let f x = [ Netunichar.to_title x ] in ustring_map_ts enc f ?range_pos ?range_len ts ;; let ustring_to_title_poly ops kind enc ?range_pos ?range_len s = let f x = [ Netunichar.to_title x ] in ustring_map_poly ops kind enc f ?range_pos ?range_len s ;; let ustring_sub_poly ops out_kind enc pos len ?range_pos ?range_len s = let open Netstring_tstring in try if pos < 0 || len < 0 then raise Cursor_out_of_range; let cs = create_poly_cursor ?range_pos ?range_len enc ops s in move ~num:pos cs; let byte_pos_0 = cursor_pos cs in move ~num:len cs; let byte_pos_1 = cursor_pos cs in (* Check: The last character of the string must not be an imbchar *) if len > 0 then ( move ~num:(-1) cs; let _ = uchar_at cs in (); (* or Partial_character *) ); ops.subpoly out_kind s byte_pos_0 (byte_pos_1 - byte_pos_0) with Cursor_out_of_range -> invalid_arg "Netconversion.ustring_sub" | Partial_character -> raise Malformed_code ;; let ustring_sub enc = ustring_sub_poly Netstring_tstring.string_ops Netstring_tstring.String_kind enc let ustring_sub_ts enc pos len ?range_pos ?range_len ts = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops s -> match ts with | `String _ -> let kind = Netstring_tstring.String_kind in `String( ustring_sub_poly ops kind enc pos len ?range_pos ?range_len s) | `Bytes _ -> let kind = Netstring_tstring.Bytes_kind in `Bytes( ustring_sub_poly ops kind enc pos len ?range_pos ?range_len s) | `Memory _ -> let kind = Netstring_tstring.Memory_kind in `Memory( ustring_sub_poly ops kind enc pos len ?range_pos ?range_len s) ) } ts let ustring_compare_poly ops1 ops2 enc f ?range_pos:rp1 ?range_len:rl1 s1 ?range_pos:rp2 ?range_len:rl2 s2 = let cs1 = create_poly_cursor ?range_pos:rp1 ?range_len:rl1 enc ops1 s1 in let cs2 = create_poly_cursor ?range_pos:rp2 ?range_len:rl2 enc ops2 s2 in let r = ref 0 in try while !r = 0 do let ch1 = uchar_at cs1 in (* or End_of_string *) let ch2 = uchar_at cs2 in (* or End_of_string *) r := f ch1 ch2 done; !r with End_of_string -> ( match cursor_at_end cs1, cursor_at_end cs2 with true, false -> (-1) | false, true -> 1 | true, true -> 0 | _ -> assert false ) | Partial_character -> raise Malformed_code ;; let ustring_compare enc = ustring_compare_poly Netstring_tstring.string_ops Netstring_tstring.string_ops enc let ustring_compare_ts enc f ?range_pos:rp1 ?range_len:rl1 ts1 ?range_pos:rp2 ?range_len:rl2 ts2 = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops1 s1 -> Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops2 s2 -> ustring_compare_poly ops1 ops2 enc f ?range_pos:rp1 ?range_len:rl1 s1 ?range_pos:rp2 ?range_len:rl2 s2 ) } ts2 ) } ts1 let uarray_of_ustring_poly ops enc ?(range_pos=0) ?range_len s = let open Netstring_tstring in let range_len = match range_len with Some l -> l | None -> ops.length s - range_pos in if range_pos < 0 || range_len < 0 || range_pos+range_len > ops.length s then invalid_arg "Netconversion.uarray_of_ustring"; let slice_length = big_slice in let slice_char = Array.make slice_length (-1) in let slice_blen = Array.make slice_length 1 in let k = ref 0 in let e = ref enc in let reader = ref (get_reader enc) in let buf = ref [] in while !k < range_len do let (n_inc, k_inc, enc') = try (!reader).read ops slice_char slice_blen s (range_pos + !k) (range_len - !k) with Malformed_code_read(_,_,_) -> raise Malformed_code in k := !k + k_inc; buf := (Array.sub slice_char 0 n_inc) :: !buf ; if enc' <> !e then begin e := enc'; reader := get_reader enc'; Array.fill slice_blen 0 slice_length 1; end; if n_inc < slice_length then ( (* EOF *) if !k < range_len then raise Malformed_code; (* s ends with multi-byte prefix*) k := range_len; ); done; Array.concat (List.rev !buf) ;; let uarray_of_ustring enc = uarray_of_ustring_poly Netstring_tstring.string_ops enc let uarray_of_ustring_ts enc ?range_pos ?range_len ts = Netstring_tstring.with_tstring { Netstring_tstring.with_fun = (fun ops s -> uarray_of_ustring_poly ops enc ?range_pos ?range_len s ) } ts let ustring_of_uarray_poly out_kind ?(subst = fun code -> raise (Cannot_represent code)) enc ?(pos=0) ?len ua = let len = match len with Some l -> l | None -> Array.length ua - pos in if pos < 0 || len < 0 || pos+len > Array.length ua then invalid_arg "Netconversion.ustring_of_uarray"; (* Estimate the size of the output string: * length * 2 is just guessed. It is assumed that this number is usually * too large, and to avoid that too much memory is wasted, the buffer is * limited by 10000. *) let size = ref (max multibyte_limit (min 10000 (len * 2))) in let out_buf = ref (Bytes.create !size) in let writer = get_writer enc in let k_in = ref 0 in let k_out = ref 0 in while !k_in < len do let k_in_inc, k_out_inc = writer ua (pos + !k_in) (len - !k_in) !out_buf !k_out (!size - !k_out) subst in k_in := !k_in + k_in_inc; k_out := !k_out + k_out_inc; (* double the size of out_buf: *) let size' = min Sys.max_string_length (!size + !size) in if size' < !size + multibyte_limit then failwith "Netconversion.ustring_of_uarray: string too long"; let out_buf' = Bytes.create size' in Bytes.blit !out_buf 0 out_buf' 0 !k_out; out_buf := out_buf'; size := size'; done; Netstring_tstring.bytes_subpoly out_kind !out_buf 0 !k_out ;; let ustring_of_uarray ?subst = ustring_of_uarray_poly Netstring_tstring.String_kind ?subst let ustring_of_uarray_ts : type t . t Netstring_tstring.tstring_kind -> ?subst:(int->string) -> encoding -> ?pos:int -> ?len:int -> int array -> tstring = fun out_kind ?subst enc ?pos ?len ua -> let s = ustring_of_uarray_poly out_kind ?subst enc ?pos ?len ua in match out_kind with | Netstring_tstring.String_kind -> `String s | Netstring_tstring.Bytes_kind -> `Bytes s | Netstring_tstring.Memory_kind -> `Memory s let code_cmp x1 x2 = x1-x2 let ci_code_cmp x1 x2 = let x1_lc = Netunichar.to_lower x1 in let x2_lc = Netunichar.to_lower x2 in x1_lc - x2_lc