1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692
// Copyright 2015-2016 Mozilla Foundation. See the COPYRIGHT
// file at the top-level directory of this distribution.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// https://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
#![cfg_attr(
feature = "cargo-clippy",
allow(
doc_markdown,
inline_always,
new_ret_no_self
)
)]
#![doc(html_root_url = "https://docs.rs/encoding_rs/0.8.13")]
//! encoding_rs is a Gecko-oriented Free Software / Open Source implementation
//! of the [Encoding Standard](https://encoding.spec.whatwg.org/) in Rust.
//! Gecko-oriented means that converting to and from UTF-16 is supported in
//! addition to converting to and from UTF-8, that the performance and
//! streamability goals are browser-oriented, and that FFI-friendliness is a
//! goal.
//!
//! Additionally, the `mem` module provides functions that are useful for
//! applications that need to be able to deal with legacy in-memory
//! representations of Unicode.
//!
//! For expectation setting, please be sure to read the sections
//! [_UTF-16LE, UTF-16BE and Unicode Encoding Schemes_](#utf-16le-utf-16be-and-unicode-encoding-schemes),
//! [_ISO-8859-1_](#iso-8859-1) and [_Web / Browser Focus_](#web--browser-focus) below.
//!
//! # Availability
//!
//! The code is available under the
//! [Apache license, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)
//! or the [MIT license](https://opensource.org/licenses/MIT), at your option.
//! See the
//! [`COPYRIGHT`](https://github.com/hsivonen/encoding_rs/blob/master/COPYRIGHT)
//! file for details.
//! The [repository is on GitHub](https://github.com/hsivonen/encoding_rs). The
//! [crate is available on crates.io](https://crates.io/crates/encoding_rs).
//!
//! # Integration with `std::io`
//!
//! This crate doesn't implement traits from `std::io`. However, for the case of
//! wrapping a `std::io::Read` in a decoder that implements `std::io::Read` and
//! presents the data from the wrapped `std::io::Read` as UTF-8 is addressed by
//! the [`encoding_rs_io`](https://docs.rs/encoding_rs_io/) crate.
//!
//! # Examples
//!
//! Example programs:
//!
//! * [Rust](https://github.com/hsivonen/recode_rs)
//! * [C](https://github.com/hsivonen/recode_c)
//! * [C++](https://github.com/hsivonen/recode_cpp)
//!
//! Decode using the non-streaming API:
//!
//! ```
//! use encoding_rs::*;
//!
//! let expectation = "\u{30CF}\u{30ED}\u{30FC}\u{30FB}\u{30EF}\u{30FC}\u{30EB}\u{30C9}";
//! let bytes = b"\x83n\x83\x8D\x81[\x81E\x83\x8F\x81[\x83\x8B\x83h";
//!
//! let (cow, encoding_used, had_errors) = SHIFT_JIS.decode(bytes);
//! assert_eq!(&cow[..], expectation);
//! assert_eq!(encoding_used, SHIFT_JIS);
//! assert!(!had_errors);
//! ```
//!
//! Decode using the streaming API with minimal `unsafe`:
//!
//! ```
//! use encoding_rs::*;
//!
//! let expectation = "\u{30CF}\u{30ED}\u{30FC}\u{30FB}\u{30EF}\u{30FC}\u{30EB}\u{30C9}";
//!
//! // Use an array of byte slices to demonstrate content arriving piece by
//! // piece from the network.
//! let bytes: [&'static [u8]; 4] = [b"\x83",
//! b"n\x83\x8D\x81",
//! b"[\x81E\x83\x8F\x81[\x83",
//! b"\x8B\x83h"];
//!
//! // Very short output buffer to demonstrate the output buffer getting full.
//! // Normally, you'd use something like `[0u8; 2048]`.
//! let mut buffer_bytes = [0u8; 8];
//! let mut buffer: &mut str = std::str::from_utf8_mut(&mut buffer_bytes[..]).unwrap();
//!
//! // How many bytes in the buffer currently hold significant data.
//! let mut bytes_in_buffer = 0usize;
//!
//! // Collect the output to a string for demonstration purposes.
//! let mut output = String::new();
//!
//! // The `Decoder`
//! let mut decoder = SHIFT_JIS.new_decoder();
//!
//! // Track whether we see errors.
//! let mut total_had_errors = false;
//!
//! // Decode using a fixed-size intermediate buffer (for demonstrating the
//! // use of a fixed-size buffer; normally when the output of an incremental
//! // decode goes to a `String` one would use `Decoder.decode_to_string()` to
//! // avoid the intermediate buffer).
//! for input in &bytes[..] {
//! // The number of bytes already read from current `input` in total.
//! let mut total_read_from_current_input = 0usize;
//!
//! loop {
//! let (result, read, written, had_errors) =
//! decoder.decode_to_str(&input[total_read_from_current_input..],
//! &mut buffer[bytes_in_buffer..],
//! false);
//! total_read_from_current_input += read;
//! bytes_in_buffer += written;
//! total_had_errors |= had_errors;
//! match result {
//! CoderResult::InputEmpty => {
//! // We have consumed the current input buffer. Break out of
//! // the inner loop to get the next input buffer from the
//! // outer loop.
//! break;
//! },
//! CoderResult::OutputFull => {
//! // Write the current buffer out and consider the buffer
//! // empty.
//! output.push_str(&buffer[..bytes_in_buffer]);
//! bytes_in_buffer = 0usize;
//! continue;
//! }
//! }
//! }
//! }
//!
//! // Process EOF
//! loop {
//! let (result, _, written, had_errors) =
//! decoder.decode_to_str(b"",
//! &mut buffer[bytes_in_buffer..],
//! true);
//! bytes_in_buffer += written;
//! total_had_errors |= had_errors;
//! // Write the current buffer out and consider the buffer empty.
//! // Need to do this here for both `match` arms, because we exit the
//! // loop on `CoderResult::InputEmpty`.
//! output.push_str(&buffer[..bytes_in_buffer]);
//! bytes_in_buffer = 0usize;
//! match result {
//! CoderResult::InputEmpty => {
//! // Done!
//! break;
//! },
//! CoderResult::OutputFull => {
//! continue;
//! }
//! }
//! }
//!
//! assert_eq!(&output[..], expectation);
//! assert!(!total_had_errors);
//! ```
//!
//! ## UTF-16LE, UTF-16BE and Unicode Encoding Schemes
//!
//! The Encoding Standard doesn't specify encoders for UTF-16LE and UTF-16BE,
//! __so this crate does not provide encoders for those encodings__!
//! Along with the replacement encoding, their _output encoding_ is UTF-8,
//! so you get an UTF-8 encoder if you request an encoder for them.
//!
//! Additionally, the Encoding Standard factors BOM handling into wrapper
//! algorithms so that BOM handling isn't part of the definition of the
//! encodings themselves. The Unicode _encoding schemes_ in the Unicode
//! Standard define BOM handling or lack thereof as part of the encoding
//! scheme.
//!
//! When used with the `_without_bom_handling` entry points, the UTF-16LE
//! and UTF-16BE _encodings_ match the same-named _encoding schemes_ from
//! the Unicode Standard.
//!
//! When used with the `_with_bom_removal` entry points, the UTF-8
//! _encoding_ matches the UTF-8 _encoding scheme_ from the Unicode
//! Standard.
//!
//! This crate does not provide a mode that matches the UTF-16 _encoding
//! scheme_ from the Unicode Stardard. The UTF-16BE encoding used with
//! the entry points without `_bom_` qualifiers is the closest match,
//! but in that case, the UTF-8 BOM triggers UTF-8 decoding, which is
//! not part of the behavior of the UTF-16 _encoding scheme_ per the
//! Unicode Standard.
//!
//! The UTF-32 family of Unicode encoding schemes is not supported
//! by this crate. The Encoding Standard doesn't define any UTF-32
//! family encodings, since they aren't necessary for consuming Web
//! content.
//!
//! ## ISO-8859-1
//!
//! ISO-8859-1 does not exist as a distinct encoding from windows-1252 in
//! the Encoding Standard. Therefore, an encoding that maps the unsigned
//! byte value to the same Unicode scalar value is not available via
//! `Encoding` in this crate.
//!
//! However, the functions whose name starts with `convert` and contains
//! `latin1` in the `mem` module support such conversions, which are known as
//! [_isomorphic decode_](https://infra.spec.whatwg.org/#isomorphic-decode)
//! and [_isomorphic encode_](https://infra.spec.whatwg.org/#isomorphic-encode)
//! in the [Infra Standard](https://infra.spec.whatwg.org/).
//!
//! ## Web / Browser Focus
//!
//! Both in terms of scope and performance, the focus is on the Web. For scope,
//! this means that encoding_rs implements the Encoding Standard fully and
//! doesn't implement encodings that are not specified in the Encoding
//! Standard. For performance, this means that decoding performance is
//! important as well as performance for encoding into UTF-8 or encoding the
//! Basic Latin range (ASCII) into legacy encodings. Non-Basic Latin needs to
//! be encoded into legacy encodings in only two places in the Web platform: in
//! the query part of URLs, in which case it's a matter of relatively rare
//! error handling, and in form submission, in which case the user action and
//! networking tend to hide the performance of the encoder.
//!
//! Deemphasizing performance of encoding non-Basic Latin text into legacy
//! encodings enables smaller code size thanks to the encoder side using the
//! decode-optimized data tables without having encode-optimized data tables at
//! all. Even in decoders, smaller lookup table size is preferred over avoiding
//! multiplication operations.
//!
//! Additionally, performance is a non-goal for the ASCII-incompatible
//! ISO-2022-JP encoding, which are rarely used on the Web. Instead of
//! performance, the decoder for ISO-2022-JP optimizes for ease/clarity
//! of implementation.
//!
//! Despite the browser focus, the hope is that non-browser applications
//! that wish to consume Web content or submit Web forms in a Web-compatible
//! way will find encoding_rs useful. While encoding_rs does not try to match
//! Windows behavior, many of the encodings are close enough to legacy
//! encodings implemented by Windows that applications that need to consume
//! data in legacy Windows encodins may find encoding_rs useful.
//!
//! For decoding email, UTF-7 support is needed (unfortunately) in additition
//! to the encodings defined in the Encoding Standard. The
//! [charset](https://crates.io/crates/charset) wraps encoding_rs and adds
//! UTF-7 decoding for email purposes.
//!
//! # Streaming & Non-Streaming; Rust & C/C++
//!
//! The API in Rust has two modes of operation: streaming and non-streaming.
//! The streaming API is the foundation of the implementation and should be
//! used when processing data that arrives piecemeal from an i/o stream. The
//! streaming API has an FFI wrapper (as a [separate crate][1]) that exposes it
//! to C callers. The non-streaming part of the API is for Rust callers only and
//! is smart about borrowing instead of copying when possible. When
//! streamability is not needed, the non-streaming API should be preferrer in
//! order to avoid copying data when a borrow suffices.
//!
//! There is no analogous C API exposed via FFI, mainly because C doesn't have
//! standard types for growable byte buffers and Unicode strings that know
//! their length.
//!
//! The C API (header file generated at `target/include/encoding_rs.h` when
//! building encoding_rs) can, in turn, be wrapped for use from C++. Such a
//! C++ wrapper can re-create the non-streaming API in C++ for C++ callers.
//! The C binding comes with a [C++14 wrapper][2] that uses standard library +
//! [GSL][3] types and that recreates the non-streaming API in C++ on top of
//! the streaming API. A C++ wrapper with XPCOM/MFBT types is being developed
//! as part of Mozilla [bug 1261841][4].
//!
//! The `Encoding` type is common to both the streaming and non-streaming
//! modes. In the streaming mode, decoding operations are performed with a
//! `Decoder` and encoding operations with an `Encoder` object obtained via
//! `Encoding`. In the non-streaming mode, decoding and encoding operations are
//! performed using methods on `Encoding` objects themselves, so the `Decoder`
//! and `Encoder` objects are not used at all.
//!
//! [1]: https://github.com/hsivonen/encoding_c
//! [2]: https://github.com/hsivonen/encoding_c/blob/master/include/encoding_rs_cpp.h
//! [3]: https://github.com/Microsoft/GSL/
//! [4]: https://bugzilla.mozilla.org/show_bug.cgi?id=encoding_rs
//!
//! # Memory management
//!
//! The non-streaming mode never performs heap allocations (even the methods
//! that write into a `Vec<u8>` or a `String` by taking them as arguments do
//! not reallocate the backing buffer of the `Vec<u8>` or the `String`). That
//! is, the non-streaming mode uses caller-allocated buffers exclusively.
//!
//! The methods of the streaming mode that return a `Vec<u8>` or a `String`
//! perform heap allocations but only to allocate the backing buffer of the
//! `Vec<u8>` or the `String`.
//!
//! `Encoding` is always statically allocated. `Decoder` and `Encoder` need no
//! `Drop` cleanup.
//!
//! # Buffer reading and writing behavior
//!
//! Based on experience gained with the `java.nio.charset` encoding converter
//! API and with the Gecko uconv encoding converter API, the buffer reading
//! and writing behaviors of encoding_rs are asymmetric: input buffers are
//! fully drained but output buffers are not always fully filled.
//!
//! When reading from an input buffer, encoding_rs always consumes all input
//! up to the next error or to the end of the buffer. In particular, when
//! decoding, even if the input buffer ends in the middle of a byte sequence
//! for a character, the decoder consumes all input. This has the benefit that
//! the caller of the API can always fill the next buffer from the start from
//! whatever source the bytes come from and never has to first copy the last
//! bytes of the previous buffer to the start of the next buffer. However, when
//! encoding, the UTF-8 input buffers have to end at a character boundary, which
//! is a requirement for the Rust `str` type anyway, and UTF-16 input buffer
//! boundaries falling in the middle of a surrogate pair result in both
//! suggorates being treated individually as unpaired surrogates.
//!
//! Additionally, decoders guarantee that they can be fed even one byte at a
//! time and encoders guarantee that they can be fed even one code point at a
//! time. This has the benefit of not placing restrictions on the size of
//! chunks the content arrives e.g. from network.
//!
//! When writing into an output buffer, encoding_rs makes sure that the code
//! unit sequence for a character is never split across output buffer
//! boundaries. This may result in wasted space at the end of an output buffer,
//! but the advantages are that the output side of both decoders and encoders
//! is greatly simplified compared to designs that attempt to fill output
//! buffers exactly even when that entails splitting a code unit sequence and
//! when encoding_rs methods return to the caller, the output produces thus
//! far is always valid taken as whole. (In the case of encoding to ISO-2022-JP,
//! the output needs to be considered as a whole, because the latest output
//! buffer taken alone might not be valid taken alone if the transition away
//! from the ASCII state occurred in an earlier output buffer. However, since
//! the ISO-2022-JP decoder doesn't treat streams that don't end in the ASCII
//! state as being in error despite the encoder generating a transition to the
//! ASCII state at the end, the claim about the partial output taken as a whole
//! being valid is true even for ISO-2022-JP.)
//!
//! # Error Reporting
//!
//! Based on experience gained with the `java.nio.charset` encoding converter
//! API and with the Gecko uconv encoding converter API, the error reporting
//! behaviors of encoding_rs are asymmetric: decoder errors include offsets
//! that leave it up to the caller to extract the erroneous bytes from the
//! input stream if the caller wishes to do so but encoder errors provide the
//! code point associated with the error without requiring the caller to
//! extract it from the input on its own.
//!
//! On the encoder side, an error is always triggered by the most recently
//! pushed Unicode scalar, which makes it simple to pass the `char` to the
//! caller. Also, it's very typical for the caller to wish to do something with
//! this data: generate a numeric escape for the character. Additionally, the
//! ISO-2022-JP encoder reports U+FFFD instead of the actual input character in
//! certain cases, so requiring the caller to extract the character from the
//! input buffer would require the caller to handle ISO-2022-JP details.
//! Furthermore, requiring the caller to extract the character from the input
//! buffer would require the caller to implement UTF-8 or UTF-16 math, which is
//! the job of an encoding conversion library.
//!
//! On the decoder side, errors are triggered in more complex ways. For
//! example, when decoding the sequence ESC, '$', _buffer boundary_, 'A' as
//! ISO-2022-JP, the ESC byte is in error, but this is discovered only after
//! the buffer boundary when processing 'A'. Thus, the bytes in error might not
//! be the ones most recently pushed to the decoder and the error might not even
//! be in the current buffer.
//!
//! Some encoding conversion APIs address the problem by not acknowledging
//! trailing bytes of an input buffer as consumed if it's still possible for
//! future bytes to cause the trailing bytes to be in error. This way, error
//! reporting can always refer to the most recently pushed buffer. This has the
//! problem that the caller of the API has to copy the unconsumed trailing
//! bytes to the start of the next buffer before being able to fill the rest
//! of the next buffer. This is annoying, error-prone and inefficient.
//!
//! A possible solution would be making the decoder remember recently consumed
//! bytes in order to be able to include a copy of the erroneous bytes when
//! reporting an error. This has two problem: First, callers a rarely
//! interested in the erroneous bytes, so attempts to identify them are most
//! often just overhead anyway. Second, the rare applications that are
//! interested typically care about the location of the error in the input
//! stream.
//!
//! To keep the API convenient for common uses and the overhead low while making
//! it possible to develop applications, such as HTML validators, that care
//! about which bytes were in error, encoding_rs reports the length of the
//! erroneous sequence and the number of bytes consumed after the erroneous
//! sequence. As long as the caller doesn't discard the 6 most recent bytes,
//! this makes it possible for callers that care about the erroneous bytes to
//! locate them.
//!
//! # No Convenience API for Custom Replacements
//!
//! The Web Platform and, therefore, the Encoding Standard supports only one
//! error recovery mode for decoders and only one error recovery mode for
//! encoders. The supported error recovery mode for decoders is emitting the
//! REPLACEMENT CHARACTER on error. The supported error recovery mode for
//! encoders is emitting an HTML decimal numeric character reference for
//! unmappable characters.
//!
//! Since encoding_rs is Web-focused, these are the only error recovery modes
//! for which convenient support is provided. Moreover, on the decoder side,
//! there aren't really good alternatives for emitting the REPLACEMENT CHARACTER
//! on error (other than treating errors as fatal). In particular, simply
//! ignoring errors is a
//! [security problem](http://www.unicode.org/reports/tr36/#Substituting_for_Ill_Formed_Subsequences),
//! so it would be a bad idea for encoding_rs to provide a mode that encouraged
//! callers to ignore errors.
//!
//! On the encoder side, there are plausible alternatives for HTML decimal
//! numeric character references. For example, when outputting CSS, CSS-style
//! escapes would seem to make sense. However, instead of facilitating the
//! output of CSS, JS, etc. in non-UTF-8 encodings, encoding_rs takes the design
//! position that you shouldn't generate output in encodings other than UTF-8,
//! except where backward compatibility with interacting with the legacy Web
//! requires it. The legacy Web requires it only when parsing the query strings
//! of URLs and when submitting forms, and those two both use HTML decimal
//! numeric character references.
//!
//! While encoding_rs doesn't make encoder replacements other than HTML decimal
//! numeric character references easy, it does make them _possible_.
//! `encode_from_utf8()`, which emits HTML decimal numeric character references
//! for unmappable characters, is implemented on top of
//! `encode_from_utf8_without_replacement()`. Applications that really, really
//! want other replacement schemes for unmappable characters can likewise
//! implement them on top of `encode_from_utf8_without_replacement()`.
//!
//! # No Extensibility by Design
//!
//! The set of encodings supported by encoding_rs is not extensible by design.
//! That is, `Encoding`, `Decoder` and `Encoder` are intentionally `struct`s
//! rather than `trait`s. encoding_rs takes the design position that all future
//! text interchange should be done using UTF-8, which can represent all of
//! Unicode. (It is, in fact, the only encoding supported by the Encoding
//! Standard and encoding_rs that can represent all of Unicode and that has
//! encoder support. UTF-16LE and UTF-16BE don't have encoder support, and
//! gb18030 cannot encode U+E5E5.) The other encodings are supported merely for
//! legacy compatibility and not due to non-UTF-8 encodings having benefits
//! other than being able to consume legacy content.
//!
//! Considering that UTF-8 can represent all of Unicode and is already supported
//! by all Web browsers, introducing a new encoding wouldn't add to the
//! expressiveness but would add to compatibility problems. In that sense,
//! adding new encodings to the Web Platform doesn't make sense, and, in fact,
//! post-UTF-8 attempts at encodings, such as BOCU-1, have been rejected from
//! the Web Platform. On the other hand, the set of legacy encodings that must
//! be supported for a Web browser to be able to be successful is not going to
//! expand. Empirically, the set of encodings specified in the Encoding Standard
//! is already sufficient and the set of legacy encodings won't grow
//! retroactively.
//!
//! Since extensibility doesn't make sense considering the Web focus of
//! encoding_rs and adding encodings to Web clients would be actively harmful,
//! it makes sense to make the set of encodings that encoding_rs supports
//! non-extensible and to take the (admittedly small) benefits arising from
//! that, such as the size of `Decoder` and `Encoder` objects being known ahead
//! of time, which enables stack allocation thereof.
//!
//! This does have downsides for applications that might want to put encoding_rs
//! to non-Web uses if those non-Web uses involve legacy encodings that aren't
//! needed for Web uses. The needs of such applications should not complicate
//! encoding_rs itself, though. It is up to those applications to provide a
//! framework that delegates the operations with encodings that encoding_rs
//! supports to encoding_rs and operations with other encodings to something
//! else (as opposed to encoding_rs itself providing an extensibility
//! framework).
//!
//! # Panics
//!
//! Methods in encoding_rs can panic if the API is used against the requirements
//! stated in the documentation, if a state that's supposed to be impossible
//! is reached due to an internal bug or on integer overflow. When used
//! according to documentation with buffer sizes that stay below integer
//! overflow, in the absence of internal bugs, encoding_rs does not panic.
//!
//! Panics arising from API misuse aren't documented beyond this on individual
//! methods.
//!
//! # At-Risk Parts of the API
//!
//! The foreseeable source of partially backward-incompatible API change is the
//! way the instances of `Encoding` are made available.
//!
//! If Rust changes to allow the entries of `[&'static Encoding; N]` to be
//! initialized with `static`s of type `&'static Encoding`, the non-reference
//! `FOO_INIT` public `Encoding` instances will be removed from the public API.
//!
//! If Rust changes to make the referent of `pub const FOO: &'static Encoding`
//! unique when the constant is used in different crates, the reference-typed
//! `static`s for the encoding instances will be changed from `static` to
//! `const` and the non-reference-typed `_INIT` instances will be removed.
//!
//! # Mapping Spec Concepts onto the API
//!
//! <table>
//! <thead>
//! <tr><th>Spec Concept</th><th>Streaming</th><th>Non-Streaming</th></tr>
//! </thead>
//! <tbody>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#encoding">encoding</a></td><td><code>&'static Encoding</code></td><td><code>&'static Encoding</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#utf-8">UTF-8 encoding</a></td><td><code>UTF_8</code></td><td><code>UTF_8</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#concept-encoding-get">get an encoding</a></td><td><code>Encoding::for_label(<var>label</var>)</code></td><td><code>Encoding::for_label(<var>label</var>)</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#name">name</a></td><td><code><var>encoding</var>.name()</code></td><td><code><var>encoding</var>.name()</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#get-an-output-encoding">get an output encoding</a></td><td><code><var>encoding</var>.output_encoding()</code></td><td><code><var>encoding</var>.output_encoding()</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#decode">decode</a></td><td><code>let d = <var>encoding</var>.new_decoder();<br>let res = d.decode_to_<var>*</var>(<var>src</var>, <var>dst</var>, false);<br>// …</br>let last_res = d.decode_to_<var>*</var>(<var>src</var>, <var>dst</var>, true);</code></td><td><code><var>encoding</var>.decode(<var>src</var>)</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#utf-8-decode">UTF-8 decode</a></td><td><code>let d = UTF_8.new_decoder_with_bom_removal();<br>let res = d.decode_to_<var>*</var>(<var>src</var>, <var>dst</var>, false);<br>// …</br>let last_res = d.decode_to_<var>*</var>(<var>src</var>, <var>dst</var>, true);</code></td><td><code>UTF_8.decode_with_bom_removal(<var>src</var>)</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#utf-8-decode-without-bom">UTF-8 decode without BOM</a></td><td><code>let d = UTF_8.new_decoder_without_bom_handling();<br>let res = d.decode_to_<var>*</var>(<var>src</var>, <var>dst</var>, false);<br>// …</br>let last_res = d.decode_to_<var>*</var>(<var>src</var>, <var>dst</var>, true);</code></td><td><code>UTF_8.decode_without_bom_handling(<var>src</var>)</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#utf-8-decode-without-bom-or-fail">UTF-8 decode without BOM or fail</a></td><td><code>let d = UTF_8.new_decoder_without_bom_handling();<br>let res = d.decode_to_<var>*</var>_without_replacement(<var>src</var>, <var>dst</var>, false);<br>// … (fail if malformed)</br>let last_res = d.decode_to_<var>*</var>_without_replacement(<var>src</var>, <var>dst</var>, true);<br>// (fail if malformed)</code></td><td><code>UTF_8.decode_without_bom_handling_and_without_replacement(<var>src</var>)</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#encode">encode</a></td><td><code>let e = <var>encoding</var>.new_encoder();<br>let res = e.encode_to_<var>*</var>(<var>src</var>, <var>dst</var>, false);<br>// …</br>let last_res = e.encode_to_<var>*</var>(<var>src</var>, <var>dst</var>, true);</code></td><td><code><var>encoding</var>.encode(<var>src</var>)</code></td></tr>
//! <tr><td><a href="https://encoding.spec.whatwg.org/#utf-8-encode">UTF-8 encode</a></td><td>Use the UTF-8 nature of Rust strings directly:<br><code><var>write</var>(<var>src</var>.as_bytes());<br>// refill src<br><var>write</var>(<var>src</var>.as_bytes());<br>// refill src<br><var>write</var>(<var>src</var>.as_bytes());<br>// …</code></td><td>Use the UTF-8 nature of Rust strings directly:<br><code><var>src</var>.as_bytes()</code></td></tr>
//! </tbody>
//! </table>
//!
//! # Compatibility with the rust-encoding API
//!
//! The crate
//! [encoding_rs_compat](https://github.com/hsivonen/encoding_rs_compat/)
//! is a drop-in replacement for rust-encoding 0.2.32 that implements (most of)
//! the API of rust-encoding 0.2.32 on top of encoding_rs.
//!
//! # Mapping rust-encoding concepts to encoding_rs concepts
//!
//! The following table provides a mapping from rust-encoding constructs to
//! encoding_rs ones.
//!
//! <table>
//! <thead>
//! <tr><th>rust-encoding</th><th>encoding_rs</th></tr>
//! </thead>
//! <tbody>
//! <tr><td><code>encoding::EncodingRef</code></td><td><code>&'static encoding_rs::Encoding</code></td></tr>
//! <tr><td><code>encoding::all::<var>WINDOWS_31J</var></code> (not based on the WHATWG name for some encodings)</td><td><code>encoding_rs::<var>SHIFT_JIS</var></code> (always the WHATWG name uppercased and hyphens replaced with underscores)</td></tr>
//! <tr><td><code>encoding::all::ERROR</code></td><td>Not available because not in the Encoding Standard</td></tr>
//! <tr><td><code>encoding::all::ASCII</code></td><td>Not available because not in the Encoding Standard</td></tr>
//! <tr><td><code>encoding::all::ISO_8859_1</code></td><td>Not available because not in the Encoding Standard</td></tr>
//! <tr><td><code>encoding::all::HZ</code></td><td>Not available because not in the Encoding Standard</td></tr>
//! <tr><td><code>encoding::label::encoding_from_whatwg_label(<var>string</var>)</code></td><td><code>encoding_rs::Encoding::for_label(<var>string</var>)</code></td></tr>
//! <tr><td><code><var>enc</var>.whatwg_name()</code> (always lower case)</td><td><code><var>enc</var>.name()</code> (potentially mixed case)</td></tr>
//! <tr><td><code><var>enc</var>.name()</code></td><td>Not available because not in the Encoding Standard</td></tr>
//! <tr><td><code>encoding::decode(<var>bytes</var>, encoding::DecoderTrap::Replace, <var>enc</var>)</code></td><td><code><var>enc</var>.decode(<var>bytes</var>)</code></td></tr>
//! <tr><td><code><var>enc</var>.decode(<var>bytes</var>, encoding::DecoderTrap::Replace)</code></td><td><code><var>enc</var>.decode_without_bom_handling(<var>bytes</var>)</code></td></tr>
//! <tr><td><code><var>enc</var>.encode(<var>string</var>, encoding::EncoderTrap::NcrEscape)</code></td><td><code><var>enc</var>.encode(<var>string</var>)</code></td></tr>
//! <tr><td><code><var>enc</var>.raw_decoder()</code></td><td><code><var>enc</var>.new_decoder_without_bom_handling()</code></td></tr>
//! <tr><td><code><var>enc</var>.raw_encoder()</code></td><td><code><var>enc</var>.new_encoder()</code></td></tr>
//! <tr><td><code>encoding::RawDecoder</code></td><td><code>encoding_rs::Decoder</code></td></tr>
//! <tr><td><code>encoding::RawEncoder</code></td><td><code>encoding_rs::Encoder</code></td></tr>
//! <tr><td><code><var>raw_decoder</var>.raw_feed(<var>src</var>, <var>dst_string</var>)</code></td><td><code><var>dst_string</var>.reserve(<var>decoder</var>.max_utf8_buffer_length_without_replacement(<var>src</var>.len()));<br><var>decoder</var>.decode_to_string_without_replacement(<var>src</var>, <var>dst_string</var>, false)</code></td></tr>
//! <tr><td><code><var>raw_encoder</var>.raw_feed(<var>src</var>, <var>dst_vec</var>)</code></td><td><code><var>dst_vec</var>.reserve(<var>encoder</var>.max_buffer_length_from_utf8_without_replacement(<var>src</var>.len()));<br><var>encoder</var>.encode_from_utf8_to_vec_without_replacement(<var>src</var>, <var>dst_vec</var>, false)</code></td></tr>
//! <tr><td><code><var>raw_decoder</var>.raw_finish(<var>dst</var>)</code></td><td><code><var>dst_string</var>.reserve(<var>decoder</var>.max_utf8_buffer_length_without_replacement(0));<br><var>decoder</var>.decode_to_string_without_replacement(b"", <var>dst</var>, true)</code></td></tr>
//! <tr><td><code><var>raw_encoder</var>.raw_finish(<var>dst</var>)</code></td><td><code><var>dst_vec</var>.reserve(<var>encoder</var>.max_buffer_length_from_utf8_without_replacement(0));<br><var>encoder</var>.encode_from_utf8_to_vec_without_replacement("", <var>dst</var>, true)</code></td></tr>
//! <tr><td><code>encoding::DecoderTrap::Strict</code></td><td><code>decode*</code> methods that have <code>_without_replacement</code> in their name (and treating the `Malformed` result as fatal).</td></tr>
//! <tr><td><code>encoding::DecoderTrap::Replace</code></td><td><code>decode*</code> methods that <i>do not</i> have <code>_without_replacement</code> in their name.</td></tr>
//! <tr><td><code>encoding::DecoderTrap::Ignore</code></td><td>It is a bad idea to ignore errors due to security issues, but this could be implemented using <code>decode*</code> methods that have <code>_without_replacement</code> in their name.</td></tr>
//! <tr><td><code>encoding::DecoderTrap::Call(DecoderTrapFunc)</code></td><td>Can be implemented using <code>decode*</code> methods that have <code>_without_replacement</code> in their name.</td></tr>
//! <tr><td><code>encoding::EncoderTrap::Strict</code></td><td><code>encode*</code> methods that have <code>_without_replacement</code> in their name (and treating the `Unmappable` result as fatal).</td></tr>
//! <tr><td><code>encoding::EncoderTrap::Replace</code></td><td>Can be implemented using <code>encode*</code> methods that have <code>_without_replacement</code> in their name.</td></tr>
//! <tr><td><code>encoding::EncoderTrap::Ignore</code></td><td>It is a bad idea to ignore errors due to security issues, but this could be implemented using <code>encode*</code> methods that have <code>_without_replacement</code> in their name.</td></tr>
//! <tr><td><code>encoding::EncoderTrap::NcrEscape</code></td><td><code>encode*</code> methods that <i>do not</i> have <code>_without_replacement</code> in their name.</td></tr>
//! <tr><td><code>encoding::EncoderTrap::Call(EncoderTrapFunc)</code></td><td>Can be implemented using <code>encode*</code> methods that have <code>_without_replacement</code> in their name.</td></tr>
//! </tbody>
//! </table>
//!
//! # Relationship with Windows Code Pages
//!
//! Despite the Web and browser focus, the encodings defined by the Encoding
//! Standard and implemented by this crate may be useful for decoding legacy
//! data that uses Windows code pages. The following table names the single-byte
//! encodings
//! that have a closely related Windows code page, the number of the closest
//! code page, a column indicating whether Windows maps unassigned code points
//! to the Unicode Private Use Area instead of U+FFFD and a remark number
//! indicating remarks in the list after the table.
//!
//! <table>
//! <thead>
//! <tr><th>Encoding</th><th>Code Page</th><th>PUA</th><th>Remarks</th></tr>
//! </thead>
//! <tbody>
//! <tr><td>Shift_JIS</td><td>932</td><td></td><td></td></tr>
//! <tr><td>GBK</td><td>936</td><td></td><td></td></tr>
//! <tr><td>EUC-KR</td><td>949</td><td></td><td></td></tr>
//! <tr><td>Big5</td><td>950</td><td></td><td></td></tr>
//! <tr><td>IBM866</td><td>866</td><td></td><td></td></tr>
//! <tr><td>windows-874</td><td>874</td><td>•</td><td></td></tr>
//! <tr><td>UTF-16LE</td><td>1200</td><td></td><td></td></tr>
//! <tr><td>UTF-16BE</td><td>1201</td><td></td><td></td></tr>
//! <tr><td>windows-1250</td><td>1250</td><td></td><td></td></tr>
//! <tr><td>windows-1251</td><td>1251</td><td></td><td></td></tr>
//! <tr><td>windows-1252</td><td>1252</td><td></td><td></td></tr>
//! <tr><td>windows-1253</td><td>1253</td><td>•</td><td></td></tr>
//! <tr><td>windows-1254</td><td>1254</td><td></td><td></td></tr>
//! <tr><td>windows-1255</td><td>1255</td><td>•</td><td></td></tr>
//! <tr><td>windows-1256</td><td>1256</td><td></td><td></td></tr>
//! <tr><td>windows-1257</td><td>1257</td><td>•</td><td></td></tr>
//! <tr><td>windows-1258</td><td>1258</td><td></td><td></td></tr>
//! <tr><td>macintosh</td><td>10000</td><td></td><td>1</td></tr>
//! <tr><td>x-mac-cyrillic</td><td>10017</td><td></td><td>2</td></tr>
//! <tr><td>KOI8-R</td><td>20866</td><td></td><td></td></tr>
//! <tr><td>EUC-JP</td><td>20932</td><td></td><td></td></tr>
//! <tr><td>KOI8-U</td><td>21866</td><td></td><td></td></tr>
//! <tr><td>ISO-8859-2</td><td>28592</td><td></td><td></td></tr>
//! <tr><td>ISO-8859-3</td><td>28593</td><td></td><td></td></tr>
//! <tr><td>ISO-8859-4</td><td>28594</td><td></td><td></td></tr>
//! <tr><td>ISO-8859-5</td><td>28595</td><td></td><td></td></tr>
//! <tr><td>ISO-8859-6</td><td>28596</td><td>•</td><td></td></tr>
//! <tr><td>ISO-8859-7</td><td>28597</td><td>•</td><td>3</td></tr>
//! <tr><td>ISO-8859-8</td><td>28598</td><td>•</td><td>4</td></tr>
//! <tr><td>ISO-8859-13</td><td>28603</td><td>•</td><td></td></tr>
//! <tr><td>ISO-8859-15</td><td>28605</td><td></td><td></td></tr>
//! <tr><td>ISO-8859-8-I</td><td>38598</td><td></td><td>5</td></tr>
//! <tr><td>ISO-2022-JP</td><td>50220</td><td></td><td></td></tr>
//! <tr><td>gb18030</td><td>54936</td><td></td><td></td></tr>
//! <tr><td>UTF-8</td><td>65001</td><td></td><td></td></tr>
//! </tbody>
//! </table>
//!
//! 1. Windows decodes 0xBD to U+2126 OHM SIGN instead of U+03A9 GREEK CAPITAL LETTER OMEGA.
//! 2. Windows decodes 0xFF to U+00A4 CURRENCY SIGN instead of U+20AC EURO SIGN.
//! 3. Windows decodes the currency signs at 0xA4 and 0xA5 as well as 0xAA,
//! which should be U+037A GREEK YPOGEGRAMMENI, to PUA code points. Windows
//! decodes 0xA1 to U+02BD MODIFIER LETTER REVERSED COMMA instead of U+2018
//! LEFT SINGLE QUOTATION MARK and 0xA2 to U+02BC MODIFIER LETTER APOSTROPHE
//! instead of U+2019 RIGHT SINGLE QUOTATION MARK.
//! 4. Windows decodes 0xAF to OVERLINE instead of MACRON and 0xFE and 0xFD to PUA instead
//! of LRM and RLM.
//! 5. Remarks from the previous item apply.
//!
//! The differences between this crate and Windows in the case of multibyte encodings
//! are not yet fully documented here. The lack of remarks above should not be taken
//! as indication of lack of differences.
//!
//! # Notable Differences from IANA Naming
//!
//! In some cases, the Encoding Standard specifies the popular unextended encoding
//! name where in IANA terms one of the other labels would be more precise considering
//! the extensions that the Encoding Standard has unified into the encoding.
//!
//! <table>
//! <thead>
//! <tr><th>Encoding</th><th>IANA</th></tr>
//! </thead>
//! <tbody>
//! <tr><td>Big5</td><td>Big5-HKSCS</td></tr>
//! <tr><td>EUC-KR</td><td>windows-949</td></tr>
//! <tr><td>Shift_JIS</td><td>windows-31j</td></tr>
//! <tr><td>x-mac-cyrillic</td><td>x-mac-ukrainian</td></tr>
//! </tbody>
//! </table>
//!
//! In other cases where the Encoding Standard unifies unextended and extended
//! variants of an encoding, the encoding gets the name of the extended
//! variant.
//!
//! <table>
//! <thead>
//! <tr><th>IANA</th><th>Unified into Encoding</th></tr>
//! </thead>
//! <tbody>
//! <tr><td>ISO-8859-1</td><td>windows-1252</td></tr>
//! <tr><td>ISO-8859-9</td><td>windows-1254</td></tr>
//! <tr><td>TIS-620</td><td>windows-874</td></tr>
//! </tbody>
//! </table>
//!
//! See the section [_UTF-16LE, UTF-16BE and Unicode Encoding Schemes_](#utf-16le-utf-16be-and-unicode-encoding-schemes)
//! for discussion about the UTF-16 family.
#![cfg_attr(
feature = "simd-accel",
feature(platform_intrinsics, core_intrinsics)
)]
#[macro_use]
extern crate cfg_if;
#[cfg(all(
feature = "simd-accel",
any(
target_feature = "sse2",
all(target_endian = "little", target_arch = "aarch64"),
all(target_endian = "little", target_feature = "neon")
)
))]
extern crate simd;
#[cfg(feature = "serde")]
extern crate serde;
#[cfg(all(test, feature = "serde"))]
extern crate bincode;
#[cfg(all(test, feature = "serde"))]
#[macro_use]
extern crate serde_derive;
#[cfg(all(test, feature = "serde"))]
extern crate serde_json;
#[macro_use]
mod macros;
#[cfg(all(
feature = "simd-accel",
any(
target_feature = "sse2",
all(target_endian = "little", target_arch = "aarch64"),
all(target_endian = "little", target_feature = "neon")
)
))]
mod simd_funcs;
#[cfg(test)]
mod testing;
mod big5;
mod euc_jp;
mod euc_kr;
mod gb18030;
mod iso_2022_jp;
mod replacement;
mod shift_jis;
mod single_byte;
mod utf_16;
mod utf_8;
mod x_user_defined;
mod ascii;
mod data;
mod handles;
mod variant;
pub mod mem;
use ascii::ascii_valid_up_to;
use ascii::iso_2022_jp_ascii_valid_up_to;
use utf_8::utf8_valid_up_to;
use variant::*;
use std::borrow::Cow;
use std::cmp::Ordering;
use std::hash::Hash;
use std::hash::Hasher;
#[cfg(feature = "serde")]
use serde::de::Visitor;
#[cfg(feature = "serde")]
use serde::{Deserialize, Deserializer, Serialize, Serializer};
/// This has to be the max length of an NCR instead of max
/// minus one, because we can't rely on getting the minus
/// one from the space reserved for the current unmappable,
/// because the ISO-2022-JP encoder can fill up that space
/// with a state transition escape.
const NCR_EXTRA: usize = 10; // 
// BEGIN GENERATED CODE. PLEASE DO NOT EDIT.
// Instead, please regenerate using generate-encoding-data.py
const LONGEST_LABEL_LENGTH: usize = 19; // cseucpkdfmtjapanese
/// The initializer for the [Big5](static.BIG5.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static BIG5_INIT: Encoding = Encoding {
name: "Big5",
variant: VariantEncoding::Big5,
};
/// The Big5 encoding.
///
/// This is Big5 with HKSCS with mappings to more recent Unicode assignments
/// instead of the Private Use Area code points that have been used historically.
/// It is believed to be able to decode existing Web content in a way that makes
/// sense.
///
/// To avoid form submissions generating data that Web servers don't understand,
/// the encoder doesn't use the HKSCS byte sequences that precede the unextended
/// Big5 in the lexical order.
///
/// [Index visualization](https://encoding.spec.whatwg.org/big5.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/big5-bmp.html)
///
/// This encoding is designed to be suited for decoding the Windows code page 950
/// and its HKSCS patched "951" variant such that the text makes sense, given
/// assignments that Unicode has made after those encodings used Private Use
/// Area characters.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static BIG5: &'static Encoding = &BIG5_INIT;
/// The initializer for the [EUC-JP](static.EUC_JP.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static EUC_JP_INIT: Encoding = Encoding {
name: "EUC-JP",
variant: VariantEncoding::EucJp,
};
/// The EUC-JP encoding.
///
/// This is the legacy Unix encoding for Japanese.
///
/// For compatibility with Web servers that don't expect three-byte sequences
/// in form submissions, the encoder doesn't generate three-byte sequences.
/// That is, the JIS X 0212 support is decode-only.
///
/// [Index visualization](https://encoding.spec.whatwg.org/euc-jp.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/euc-jp-bmp.html)
///
/// This encoding roughly matches the Windows code page 20932. There are error
/// handling differences and a handful of 2-byte sequences that decode differently.
/// Additionall, Windows doesn't support 3-byte sequences.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static EUC_JP: &'static Encoding = &EUC_JP_INIT;
/// The initializer for the [EUC-KR](static.EUC_KR.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static EUC_KR_INIT: Encoding = Encoding {
name: "EUC-KR",
variant: VariantEncoding::EucKr,
};
/// The EUC-KR encoding.
///
/// This is the Korean encoding for Windows. It extends the Unix legacy encoding
/// for Korean, based on KS X 1001 (which also formed the base of MacKorean on Mac OS
/// Classic), with all the characters from the Hangul Syllables block of Unicode.
///
/// [Index visualization](https://encoding.spec.whatwg.org/euc-kr.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/euc-kr-bmp.html)
///
/// This encoding matches the Windows code page 949, except Windows decodes byte 0x80
/// to U+0080 and some byte sequences that are error per the Encoding Standard to
/// the question mark or the Private Use Area.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static EUC_KR: &'static Encoding = &EUC_KR_INIT;
/// The initializer for the [GBK](static.GBK.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static GBK_INIT: Encoding = Encoding {
name: "GBK",
variant: VariantEncoding::Gbk,
};
/// The GBK encoding.
///
/// The decoder for this encoding is the same as the decoder for gb18030.
/// The encoder side of this encoding is GBK with Windows code page 936 euro
/// sign behavior. GBK extends GB2312-80 to cover the CJK Unified Ideographs
/// Unicode block as well as a handful of ideographs from the CJK Unified
/// Ideographs Extension A and CJK Compatibility Ideographs blocks.
///
/// Unlike e.g. in the case of ISO-8859-1 and windows-1252, GBK encoder wasn't
/// unified with the gb18030 encoder in the Encoding Standard out of concern
/// that servers that expect GBK form submissions might not be able to handle
/// the four-byte sequences.
///
/// [Index visualization for the two-byte sequences](https://encoding.spec.whatwg.org/gb18030.html),
/// [Visualization of BMP coverage of the two-byte index](https://encoding.spec.whatwg.org/gb18030-bmp.html)
///
/// The encoder of this encoding roughly matches the Windows code page 936.
/// The decoder side is a superset.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static GBK: &'static Encoding = &GBK_INIT;
/// The initializer for the [IBM866](static.IBM866.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static IBM866_INIT: Encoding = Encoding {
name: "IBM866",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.ibm866, 0x0440, 96, 16),
};
/// The IBM866 encoding.
///
/// This the most notable one of the DOS Cyrillic code pages. It has the same
/// box drawing characters as code page 437, so it can be used for decoding
/// DOS-era ASCII + box drawing data.
///
/// [Index visualization](https://encoding.spec.whatwg.org/ibm866.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/ibm866-bmp.html)
///
/// This encoding matches the Windows code page 866.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static IBM866: &'static Encoding = &IBM866_INIT;
/// The initializer for the [ISO-2022-JP](static.ISO_2022_JP.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_2022_JP_INIT: Encoding = Encoding {
name: "ISO-2022-JP",
variant: VariantEncoding::Iso2022Jp,
};
/// The ISO-2022-JP encoding.
///
/// This the primary pre-UTF-8 encoding for Japanese email. It uses the ASCII
/// byte range to encode non-Basic Latin characters. It's the only encoding
/// supported by this crate whose encoder is stateful.
///
/// [Index visualization](https://encoding.spec.whatwg.org/jis0208.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/jis0208-bmp.html)
///
/// This encoding roughly matches the Windows code page 50220. Notably, Windows
/// uses U+30FB in place of the REPLACEMENT CHARACTER and otherwise differs in
/// error handling.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_2022_JP: &'static Encoding = &ISO_2022_JP_INIT;
/// The initializer for the [ISO-8859-10](static.ISO_8859_10.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_10_INIT: Encoding = Encoding {
name: "ISO-8859-10",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_10, 0x00DA, 90, 6),
};
/// The ISO-8859-10 encoding.
///
/// This is the Nordic part of the ISO/IEC 8859 encoding family. This encoding
/// is also known as Latin 6.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-10.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-10-bmp.html)
///
/// The Windows code page number for this encoding is 28600, but kernel32.dll
/// does not support this encoding.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_10: &'static Encoding = &ISO_8859_10_INIT;
/// The initializer for the [ISO-8859-13](static.ISO_8859_13.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_13_INIT: Encoding = Encoding {
name: "ISO-8859-13",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_13, 0x00DF, 95, 1),
};
/// The ISO-8859-13 encoding.
///
/// This is the Baltic part of the ISO/IEC 8859 encoding family. This encoding
/// is also known as Latin 7.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-13.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-13-bmp.html)
///
/// This encoding matches the Windows code page 28603, except Windows decodes
/// unassigned code points to the Private Use Area of Unicode.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_13: &'static Encoding = &ISO_8859_13_INIT;
/// The initializer for the [ISO-8859-14](static.ISO_8859_14.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_14_INIT: Encoding = Encoding {
name: "ISO-8859-14",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_14, 0x00DF, 95, 17),
};
/// The ISO-8859-14 encoding.
///
/// This is the Celtic part of the ISO/IEC 8859 encoding family. This encoding
/// is also known as Latin 8.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-14.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-14-bmp.html)
///
/// The Windows code page number for this encoding is 28604, but kernel32.dll
/// does not support this encoding.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_14: &'static Encoding = &ISO_8859_14_INIT;
/// The initializer for the [ISO-8859-15](static.ISO_8859_15.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_15_INIT: Encoding = Encoding {
name: "ISO-8859-15",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_15, 0x00BF, 63, 65),
};
/// The ISO-8859-15 encoding.
///
/// This is the revised Western European part of the ISO/IEC 8859 encoding
/// family. This encoding is also known as Latin 9.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-15.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-15-bmp.html)
///
/// This encoding matches the Windows code page 28605.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_15: &'static Encoding = &ISO_8859_15_INIT;
/// The initializer for the [ISO-8859-16](static.ISO_8859_16.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_16_INIT: Encoding = Encoding {
name: "ISO-8859-16",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_16, 0x00DF, 95, 4),
};
/// The ISO-8859-16 encoding.
///
/// This is the South-Eastern European part of the ISO/IEC 8859 encoding
/// family. This encoding is also known as Latin 10.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-16.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-16-bmp.html)
///
/// The Windows code page number for this encoding is 28606, but kernel32.dll
/// does not support this encoding.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_16: &'static Encoding = &ISO_8859_16_INIT;
/// The initializer for the [ISO-8859-2](static.ISO_8859_2.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_2_INIT: Encoding = Encoding {
name: "ISO-8859-2",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_2, 0x00DF, 95, 1),
};
/// The ISO-8859-2 encoding.
///
/// This is the Central European part of the ISO/IEC 8859 encoding family. This encoding is also known as Latin 2.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-2.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-2-bmp.html)
///
/// This encoding matches the Windows code page 28592.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_2: &'static Encoding = &ISO_8859_2_INIT;
/// The initializer for the [ISO-8859-3](static.ISO_8859_3.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_3_INIT: Encoding = Encoding {
name: "ISO-8859-3",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_3, 0x00DF, 95, 4),
};
/// The ISO-8859-3 encoding.
///
/// This is the South European part of the ISO/IEC 8859 encoding family. This encoding is also known as Latin 3.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-3.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-3-bmp.html)
///
/// This encoding matches the Windows code page 28593.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_3: &'static Encoding = &ISO_8859_3_INIT;
/// The initializer for the [ISO-8859-4](static.ISO_8859_4.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_4_INIT: Encoding = Encoding {
name: "ISO-8859-4",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_4, 0x00DF, 95, 1),
};
/// The ISO-8859-4 encoding.
///
/// This is the North European part of the ISO/IEC 8859 encoding family. This encoding is also known as Latin 4.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-4.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-4-bmp.html)
///
/// This encoding matches the Windows code page 28594.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_4: &'static Encoding = &ISO_8859_4_INIT;
/// The initializer for the [ISO-8859-5](static.ISO_8859_5.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_5_INIT: Encoding = Encoding {
name: "ISO-8859-5",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_5, 0x040E, 46, 66),
};
/// The ISO-8859-5 encoding.
///
/// This is the Cyrillic part of the ISO/IEC 8859 encoding family.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-5.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-5-bmp.html)
///
/// This encoding matches the Windows code page 28595.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_5: &'static Encoding = &ISO_8859_5_INIT;
/// The initializer for the [ISO-8859-6](static.ISO_8859_6.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_6_INIT: Encoding = Encoding {
name: "ISO-8859-6",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_6, 0x0621, 65, 26),
};
/// The ISO-8859-6 encoding.
///
/// This is the Arabic part of the ISO/IEC 8859 encoding family.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-6.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-6-bmp.html)
///
/// This encoding matches the Windows code page 28596, except Windows decodes
/// unassigned code points to the Private Use Area of Unicode.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_6: &'static Encoding = &ISO_8859_6_INIT;
/// The initializer for the [ISO-8859-7](static.ISO_8859_7.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_7_INIT: Encoding = Encoding {
name: "ISO-8859-7",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_7, 0x03A3, 83, 44),
};
/// The ISO-8859-7 encoding.
///
/// This is the Greek part of the ISO/IEC 8859 encoding family.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-7.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-7-bmp.html)
///
/// This encoding roughly matches the Windows code page 28597. Windows decodes
/// unassigned code points, the currency signs at 0xA4 and 0xA5 as well as
/// 0xAA, which should be U+037A GREEK YPOGEGRAMMENI, to the Private Use Area
/// of Unicode. Windows decodes 0xA1 to U+02BD MODIFIER LETTER REVERSED COMMA
/// instead of U+2018 LEFT SINGLE QUOTATION MARK and 0xA2 to U+02BC MODIFIER
/// LETTER APOSTROPHE instead of U+2019 RIGHT SINGLE QUOTATION MARK.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_7: &'static Encoding = &ISO_8859_7_INIT;
/// The initializer for the [ISO-8859-8](static.ISO_8859_8.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_8_INIT: Encoding = Encoding {
name: "ISO-8859-8",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_8, 0x05D0, 96, 27),
};
/// The ISO-8859-8 encoding.
///
/// This is the Hebrew part of the ISO/IEC 8859 encoding family in visual order.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-8.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-8-bmp.html)
///
/// This encoding roughly matches the Windows code page 28598. Windows decodes
/// 0xAF to OVERLINE instead of MACRON and 0xFE and 0xFD to the Private Use
/// Area instead of LRM and RLM. Windows decodes unassigned code points to
/// the private use area.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_8: &'static Encoding = &ISO_8859_8_INIT;
/// The initializer for the [ISO-8859-8-I](static.ISO_8859_8_I.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static ISO_8859_8_I_INIT: Encoding = Encoding {
name: "ISO-8859-8-I",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.iso_8859_8, 0x05D0, 96, 27),
};
/// The ISO-8859-8-I encoding.
///
/// This is the Hebrew part of the ISO/IEC 8859 encoding family in logical order.
///
/// [Index visualization](https://encoding.spec.whatwg.org/iso-8859-8.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/iso-8859-8-bmp.html)
///
/// This encoding roughly matches the Windows code page 38598. Windows decodes
/// 0xAF to OVERLINE instead of MACRON and 0xFE and 0xFD to the Private Use
/// Area instead of LRM and RLM. Windows decodes unassigned code points to
/// the private use area.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static ISO_8859_8_I: &'static Encoding = &ISO_8859_8_I_INIT;
/// The initializer for the [KOI8-R](static.KOI8_R.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static KOI8_R_INIT: Encoding = Encoding {
name: "KOI8-R",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.koi8_r, 0x044E, 64, 1),
};
/// The KOI8-R encoding.
///
/// This is an encoding for Russian from [RFC 1489](https://tools.ietf.org/html/rfc1489).
///
/// [Index visualization](https://encoding.spec.whatwg.org/koi8-r.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/koi8-r-bmp.html)
///
/// This encoding matches the Windows code page 20866.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static KOI8_R: &'static Encoding = &KOI8_R_INIT;
/// The initializer for the [KOI8-U](static.KOI8_U.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static KOI8_U_INIT: Encoding = Encoding {
name: "KOI8-U",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.koi8_u, 0x044E, 64, 1),
};
/// The KOI8-U encoding.
///
/// This is an encoding for Ukrainian adapted from KOI8-R.
///
/// [Index visualization](https://encoding.spec.whatwg.org/koi8-u.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/koi8-u-bmp.html)
///
/// This encoding matches the Windows code page 21866.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static KOI8_U: &'static Encoding = &KOI8_U_INIT;
/// The initializer for the [Shift_JIS](static.SHIFT_JIS.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static SHIFT_JIS_INIT: Encoding = Encoding {
name: "Shift_JIS",
variant: VariantEncoding::ShiftJis,
};
/// The Shift_JIS encoding.
///
/// This is the Japanese encoding for Windows.
///
/// [Index visualization](https://encoding.spec.whatwg.org/shift_jis.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/shift_jis-bmp.html)
///
/// This encoding matches the Windows code page 932, except Windows decodes some byte
/// sequences that are error per the Encoding Standard to the question mark or the
/// Private Use Area and generally uses U+30FB in place of the REPLACEMENT CHARACTER.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static SHIFT_JIS: &'static Encoding = &SHIFT_JIS_INIT;
/// The initializer for the [UTF-16BE](static.UTF_16BE.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static UTF_16BE_INIT: Encoding = Encoding {
name: "UTF-16BE",
variant: VariantEncoding::Utf16Be,
};
/// The UTF-16BE encoding.
///
/// This decode-only encoding uses 16-bit code units due to Unicode originally
/// having been designed as a 16-bit reportoire. In the absence of a byte order
/// mark the big endian byte order is assumed.
///
/// There is no corresponding encoder in this crate or in the Encoding
/// Standard. The output encoding of this encoding is UTF-8.
///
/// This encoding matches the Windows code page 1201.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static UTF_16BE: &'static Encoding = &UTF_16BE_INIT;
/// The initializer for the [UTF-16LE](static.UTF_16LE.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static UTF_16LE_INIT: Encoding = Encoding {
name: "UTF-16LE",
variant: VariantEncoding::Utf16Le,
};
/// The UTF-16LE encoding.
///
/// This decode-only encoding uses 16-bit code units due to Unicode originally
/// having been designed as a 16-bit reportoire. In the absence of a byte order
/// mark the little endian byte order is assumed.
///
/// There is no corresponding encoder in this crate or in the Encoding
/// Standard. The output encoding of this encoding is UTF-8.
///
/// This encoding matches the Windows code page 1200.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static UTF_16LE: &'static Encoding = &UTF_16LE_INIT;
/// The initializer for the [UTF-8](static.UTF_8.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static UTF_8_INIT: Encoding = Encoding {
name: "UTF-8",
variant: VariantEncoding::Utf8,
};
/// The UTF-8 encoding.
///
/// This is the encoding that should be used for all new development it can
/// represent all of Unicode.
///
/// This encoding matches the Windows code page 65001, except Windows differs
/// in the number of errors generated for some erroneous byte sequences.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static UTF_8: &'static Encoding = &UTF_8_INIT;
/// The initializer for the [gb18030](static.GB18030.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static GB18030_INIT: Encoding = Encoding {
name: "gb18030",
variant: VariantEncoding::Gb18030,
};
/// The gb18030 encoding.
///
/// This encoding matches GB18030-2005 except the two-byte sequence 0xA3 0xA0
/// maps to U+3000 for compatibility with existing Web content. As a result,
/// this encoding can represent all of Unicode except for the private-use
/// character U+E5E5.
///
/// [Index visualization for the two-byte sequences](https://encoding.spec.whatwg.org/gb18030.html),
/// [Visualization of BMP coverage of the two-byte index](https://encoding.spec.whatwg.org/gb18030-bmp.html)
///
/// This encoding matches the Windows code page 54936.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static GB18030: &'static Encoding = &GB18030_INIT;
/// The initializer for the [macintosh](static.MACINTOSH.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static MACINTOSH_INIT: Encoding = Encoding {
name: "macintosh",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.macintosh, 0x00CD, 106, 3),
};
/// The macintosh encoding.
///
/// This is the MacRoman encoding from Mac OS Classic.
///
/// [Index visualization](https://encoding.spec.whatwg.org/macintosh.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/macintosh-bmp.html)
///
/// This encoding matches the Windows code page 10000, except Windows decodes
/// 0xBD to U+2126 OHM SIGN instead of U+03A9 GREEK CAPITAL LETTER OMEGA.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static MACINTOSH: &'static Encoding = &MACINTOSH_INIT;
/// The initializer for the [replacement](static.REPLACEMENT.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static REPLACEMENT_INIT: Encoding = Encoding {
name: "replacement",
variant: VariantEncoding::Replacement,
};
/// The replacement encoding.
///
/// This decode-only encoding decodes all non-zero-length streams to a single
/// REPLACEMENT CHARACTER. Its purpose is to avoid the use of an
/// ASCII-compatible fallback encoding (typically windows-1252) for some
/// encodings that are no longer supported by the Web Platform and that
/// would be dangerous to treat as ASCII-compatible.
///
/// There is no corresponding encoder. The output encoding of this encoding
/// is UTF-8.
///
/// This encoding does not have a Windows code page number.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static REPLACEMENT: &'static Encoding = &REPLACEMENT_INIT;
/// The initializer for the [windows-1250](static.WINDOWS_1250.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1250_INIT: Encoding = Encoding {
name: "windows-1250",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1250, 0x00DC, 92, 2),
};
/// The windows-1250 encoding.
///
/// This is the Central European encoding for Windows.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1250.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1250-bmp.html)
///
/// This encoding matches the Windows code page 1250.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1250: &'static Encoding = &WINDOWS_1250_INIT;
/// The initializer for the [windows-1251](static.WINDOWS_1251.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1251_INIT: Encoding = Encoding {
name: "windows-1251",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1251, 0x0410, 64, 64),
};
/// The windows-1251 encoding.
///
/// This is the Cyrillic encoding for Windows.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1251.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1251-bmp.html)
///
/// This encoding matches the Windows code page 1251.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1251: &'static Encoding = &WINDOWS_1251_INIT;
/// The initializer for the [windows-1252](static.WINDOWS_1252.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1252_INIT: Encoding = Encoding {
name: "windows-1252",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1252, 0x00A0, 32, 96),
};
/// The windows-1252 encoding.
///
/// This is the Western encoding for Windows. It is an extension of ISO-8859-1,
/// which is known as Latin 1.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1252.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1252-bmp.html)
///
/// This encoding matches the Windows code page 1252.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1252: &'static Encoding = &WINDOWS_1252_INIT;
/// The initializer for the [windows-1253](static.WINDOWS_1253.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1253_INIT: Encoding = Encoding {
name: "windows-1253",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1253, 0x03A3, 83, 44),
};
/// The windows-1253 encoding.
///
/// This is the Greek encoding for Windows. It is mostly an extension of
/// ISO-8859-7, but U+0386 is mapped to a different byte.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1253.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1253-bmp.html)
///
/// This encoding matches the Windows code page 1253, except Windows decodes
/// unassigned code points to the Private Use Area of Unicode.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1253: &'static Encoding = &WINDOWS_1253_INIT;
/// The initializer for the [windows-1254](static.WINDOWS_1254.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1254_INIT: Encoding = Encoding {
name: "windows-1254",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1254, 0x00DF, 95, 17),
};
/// The windows-1254 encoding.
///
/// This is the Turkish encoding for Windows. It is an extension of ISO-8859-9,
/// which is known as Latin 5.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1254.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1254-bmp.html)
///
/// This encoding matches the Windows code page 1254.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1254: &'static Encoding = &WINDOWS_1254_INIT;
/// The initializer for the [windows-1255](static.WINDOWS_1255.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1255_INIT: Encoding = Encoding {
name: "windows-1255",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1255, 0x05D0, 96, 27),
};
/// The windows-1255 encoding.
///
/// This is the Hebrew encoding for Windows. It is an extension of ISO-8859-8-I,
/// except for a currency sign swap.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1255.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1255-bmp.html)
///
/// This encoding matches the Windows code page 1255, except Windows decodes
/// unassigned code points to the Private Use Area of Unicode.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1255: &'static Encoding = &WINDOWS_1255_INIT;
/// The initializer for the [windows-1256](static.WINDOWS_1256.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1256_INIT: Encoding = Encoding {
name: "windows-1256",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1256, 0x0621, 65, 22),
};
/// The windows-1256 encoding.
///
/// This is the Arabic encoding for Windows.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1256.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1256-bmp.html)
///
/// This encoding matches the Windows code page 1256.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1256: &'static Encoding = &WINDOWS_1256_INIT;
/// The initializer for the [windows-1257](static.WINDOWS_1257.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1257_INIT: Encoding = Encoding {
name: "windows-1257",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1257, 0x00DF, 95, 1),
};
/// The windows-1257 encoding.
///
/// This is the Baltic encoding for Windows.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1257.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1257-bmp.html)
///
/// This encoding matches the Windows code page 1257, except Windows decodes
/// unassigned code points to the Private Use Area of Unicode.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1257: &'static Encoding = &WINDOWS_1257_INIT;
/// The initializer for the [windows-1258](static.WINDOWS_1258.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_1258_INIT: Encoding = Encoding {
name: "windows-1258",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_1258, 0x00DF, 95, 4),
};
/// The windows-1258 encoding.
///
/// This is the Vietnamese encoding for Windows.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-1258.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-1258-bmp.html)
///
/// This encoding matches the Windows code page 1258 when used in the
/// non-normalizing mode. Unlike with the other single-byte encodings, the
/// result of decoding is not necessarily in Normalization Form C. On the
/// other hand, input in the Normalization Form C is not encoded without
/// replacement. In general, it's a bad idea to encode to encodings other
/// than UTF-8, but this encoding is especially hazardous to encode to.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_1258: &'static Encoding = &WINDOWS_1258_INIT;
/// The initializer for the [windows-874](static.WINDOWS_874.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static WINDOWS_874_INIT: Encoding = Encoding {
name: "windows-874",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.windows_874, 0x0E01, 33, 58),
};
/// The windows-874 encoding.
///
/// This is the Thai encoding for Windows. It is an extension of TIS-620 / ISO-8859-11.
///
/// [Index visualization](https://encoding.spec.whatwg.org/windows-874.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/windows-874-bmp.html)
///
/// This encoding matches the Windows code page 874, except Windows decodes
/// unassigned code points to the Private Use Area of Unicode.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static WINDOWS_874: &'static Encoding = &WINDOWS_874_INIT;
/// The initializer for the [x-mac-cyrillic](static.X_MAC_CYRILLIC.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static X_MAC_CYRILLIC_INIT: Encoding = Encoding {
name: "x-mac-cyrillic",
variant: VariantEncoding::SingleByte(&data::SINGLE_BYTE_DATA.x_mac_cyrillic, 0x0430, 96, 31),
};
/// The x-mac-cyrillic encoding.
///
/// This is the MacUkrainian encoding from Mac OS Classic.
///
/// [Index visualization](https://encoding.spec.whatwg.org/x-mac-cyrillic.html),
/// [Visualization of BMP coverage](https://encoding.spec.whatwg.org/x-mac-cyrillic-bmp.html)
///
/// This encoding matches the Windows code page 10017.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static X_MAC_CYRILLIC: &'static Encoding = &X_MAC_CYRILLIC_INIT;
/// The initializer for the [x-user-defined](static.X_USER_DEFINED.html) encoding.
///
/// For use only for taking the address of this form when
/// Rust prohibits the use of the non-`_INIT` form directly,
/// such as in initializers of other `static`s. If in doubt,
/// use the corresponding non-`_INIT` reference-typed `static`.
///
/// This part of the public API will go away if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate or if Rust starts allowing static arrays
/// to be initialized with `pub static FOO: &'static Encoding`
/// items.
pub static X_USER_DEFINED_INIT: Encoding = Encoding {
name: "x-user-defined",
variant: VariantEncoding::UserDefined,
};
/// The x-user-defined encoding.
///
/// This encoding offsets the non-ASCII bytes by `0xF700` thereby decoding
/// them to the Private Use Area of Unicode. It was used for loading binary
/// data into a JavaScript string using `XMLHttpRequest` before XHR supported
/// the `"arraybuffer"` response type.
///
/// This encoding does not have a Windows code page number.
///
/// This will change from `static` to `const` if Rust changes
/// to make the referent of `pub const FOO: &'static Encoding`
/// unique cross-crate, so don't take the address of this
/// `static`.
pub static X_USER_DEFINED: &'static Encoding = &X_USER_DEFINED_INIT;
static LABELS_SORTED: [&'static str; 219] = [
"l1",
"l2",
"l3",
"l4",
"l5",
"l6",
"l9",
"866",
"mac",
"koi",
"gbk",
"big5",
"utf8",
"koi8",
"sjis",
"ms932",
"cp866",
"utf-8",
"cp819",
"ascii",
"x-gbk",
"greek",
"cp1250",
"cp1251",
"latin1",
"gb2312",
"cp1252",
"latin2",
"cp1253",
"latin3",
"cp1254",
"latin4",
"cp1255",
"csbig5",
"latin5",
"utf-16",
"cp1256",
"ibm866",
"latin6",
"cp1257",
"cp1258",
"greek8",
"ibm819",
"arabic",
"visual",
"korean",
"euc-jp",
"koi8-r",
"koi8_r",
"euc-kr",
"x-sjis",
"koi8-u",
"hebrew",
"tis-620",
"gb18030",
"ksc5601",
"gb_2312",
"dos-874",
"cn-big5",
"chinese",
"logical",
"cskoi8r",
"cseuckr",
"koi8-ru",
"x-cp1250",
"ksc_5601",
"x-cp1251",
"iso88591",
"csgb2312",
"x-cp1252",
"iso88592",
"x-cp1253",
"iso88593",
"ecma-114",
"x-cp1254",
"iso88594",
"x-cp1255",
"iso88595",
"x-x-big5",
"x-cp1256",
"csibm866",
"iso88596",
"x-cp1257",
"iso88597",
"asmo-708",
"ecma-118",
"elot_928",
"x-cp1258",
"iso88598",
"iso88599",
"cyrillic",
"utf-16be",
"utf-16le",
"us-ascii",
"ms_kanji",
"x-euc-jp",
"iso885910",
"iso8859-1",
"iso885911",
"iso8859-2",
"iso8859-3",
"iso885913",
"iso8859-4",
"iso885914",
"iso8859-5",
"iso885915",
"iso8859-6",
"iso8859-7",
"iso8859-8",
"iso-ir-58",
"iso8859-9",
"macintosh",
"shift-jis",
"shift_jis",
"iso-ir-100",
"iso8859-10",
"iso-ir-110",
"gb_2312-80",
"iso-8859-1",
"iso_8859-1",
"iso-ir-101",
"iso8859-11",
"iso-8859-2",
"iso_8859-2",
"hz-gb-2312",
"iso-8859-3",
"iso_8859-3",
"iso8859-13",
"iso-8859-4",
"iso_8859-4",
"iso8859-14",
"iso-ir-144",
"iso-8859-5",
"iso_8859-5",
"iso8859-15",
"iso-8859-6",
"iso_8859-6",
"iso-ir-126",
"iso-8859-7",
"iso_8859-7",
"iso-ir-127",
"iso-ir-157",
"iso-8859-8",
"iso_8859-8",
"iso-ir-138",
"iso-ir-148",
"iso-8859-9",
"iso_8859-9",
"iso-ir-109",
"iso-ir-149",
"big5-hkscs",
"csshiftjis",
"iso-8859-10",
"iso-8859-11",
"csisolatin1",
"csisolatin2",
"iso-8859-13",
"csisolatin3",
"iso-8859-14",
"windows-874",
"csisolatin4",
"iso-8859-15",
"iso_8859-15",
"csisolatin5",
"iso-8859-16",
"csisolatin6",
"windows-949",
"csisolatin9",
"csiso88596e",
"csiso88598e",
"csmacintosh",
"csiso88596i",
"csiso88598i",
"windows-31j",
"x-mac-roman",
"iso-2022-cn",
"iso-2022-jp",
"csiso2022jp",
"iso-2022-kr",
"csiso2022kr",
"replacement",
"windows-1250",
"windows-1251",
"windows-1252",
"windows-1253",
"windows-1254",
"windows-1255",
"windows-1256",
"windows-1257",
"windows-1258",
"iso-8859-6-e",
"iso-8859-8-e",
"iso-8859-6-i",
"iso-8859-8-i",
"sun_eu_greek",
"csksc56011987",
"ks_c_5601-1987",
"ansi_x3.4-1968",
"ks_c_5601-1989",
"x-mac-cyrillic",
"x-user-defined",
"csiso58gb231280",
"iso_8859-1:1987",
"iso_8859-2:1987",
"iso_8859-6:1987",
"iso_8859-7:1987",
"iso_8859-3:1988",
"iso_8859-4:1988",
"iso_8859-5:1988",
"iso_8859-8:1988",
"iso_8859-9:1989",
"csisolatingreek",
"x-mac-ukrainian",
"iso-2022-cn-ext",
"csisolatinarabic",
"csisolatinhebrew",
"unicode-1-1-utf-8",
"csisolatincyrillic",
"cseucpkdfmtjapanese",
];
static ENCODINGS_IN_LABEL_SORT: [&'static Encoding; 219] = [
&WINDOWS_1252_INIT,
&ISO_8859_2_INIT,
&ISO_8859_3_INIT,
&ISO_8859_4_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_10_INIT,
&ISO_8859_15_INIT,
&IBM866_INIT,
&MACINTOSH_INIT,
&KOI8_R_INIT,
&GBK_INIT,
&BIG5_INIT,
&UTF_8_INIT,
&KOI8_R_INIT,
&SHIFT_JIS_INIT,
&SHIFT_JIS_INIT,
&IBM866_INIT,
&UTF_8_INIT,
&WINDOWS_1252_INIT,
&WINDOWS_1252_INIT,
&GBK_INIT,
&ISO_8859_7_INIT,
&WINDOWS_1250_INIT,
&WINDOWS_1251_INIT,
&WINDOWS_1252_INIT,
&GBK_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_2_INIT,
&WINDOWS_1253_INIT,
&ISO_8859_3_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_4_INIT,
&WINDOWS_1255_INIT,
&BIG5_INIT,
&WINDOWS_1254_INIT,
&UTF_16LE_INIT,
&WINDOWS_1256_INIT,
&IBM866_INIT,
&ISO_8859_10_INIT,
&WINDOWS_1257_INIT,
&WINDOWS_1258_INIT,
&ISO_8859_7_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_6_INIT,
&ISO_8859_8_INIT,
&EUC_KR_INIT,
&EUC_JP_INIT,
&KOI8_R_INIT,
&KOI8_R_INIT,
&EUC_KR_INIT,
&SHIFT_JIS_INIT,
&KOI8_U_INIT,
&ISO_8859_8_INIT,
&WINDOWS_874_INIT,
&GB18030_INIT,
&EUC_KR_INIT,
&GBK_INIT,
&WINDOWS_874_INIT,
&BIG5_INIT,
&GBK_INIT,
&ISO_8859_8_I_INIT,
&KOI8_R_INIT,
&EUC_KR_INIT,
&KOI8_U_INIT,
&WINDOWS_1250_INIT,
&EUC_KR_INIT,
&WINDOWS_1251_INIT,
&WINDOWS_1252_INIT,
&GBK_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_2_INIT,
&WINDOWS_1253_INIT,
&ISO_8859_3_INIT,
&ISO_8859_6_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_4_INIT,
&WINDOWS_1255_INIT,
&ISO_8859_5_INIT,
&BIG5_INIT,
&WINDOWS_1256_INIT,
&IBM866_INIT,
&ISO_8859_6_INIT,
&WINDOWS_1257_INIT,
&ISO_8859_7_INIT,
&ISO_8859_6_INIT,
&ISO_8859_7_INIT,
&ISO_8859_7_INIT,
&WINDOWS_1258_INIT,
&ISO_8859_8_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_5_INIT,
&UTF_16BE_INIT,
&UTF_16LE_INIT,
&WINDOWS_1252_INIT,
&SHIFT_JIS_INIT,
&EUC_JP_INIT,
&ISO_8859_10_INIT,
&WINDOWS_1252_INIT,
&WINDOWS_874_INIT,
&ISO_8859_2_INIT,
&ISO_8859_3_INIT,
&ISO_8859_13_INIT,
&ISO_8859_4_INIT,
&ISO_8859_14_INIT,
&ISO_8859_5_INIT,
&ISO_8859_15_INIT,
&ISO_8859_6_INIT,
&ISO_8859_7_INIT,
&ISO_8859_8_INIT,
&GBK_INIT,
&WINDOWS_1254_INIT,
&MACINTOSH_INIT,
&SHIFT_JIS_INIT,
&SHIFT_JIS_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_10_INIT,
&ISO_8859_4_INIT,
&GBK_INIT,
&WINDOWS_1252_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_2_INIT,
&WINDOWS_874_INIT,
&ISO_8859_2_INIT,
&ISO_8859_2_INIT,
&REPLACEMENT_INIT,
&ISO_8859_3_INIT,
&ISO_8859_3_INIT,
&ISO_8859_13_INIT,
&ISO_8859_4_INIT,
&ISO_8859_4_INIT,
&ISO_8859_14_INIT,
&ISO_8859_5_INIT,
&ISO_8859_5_INIT,
&ISO_8859_5_INIT,
&ISO_8859_15_INIT,
&ISO_8859_6_INIT,
&ISO_8859_6_INIT,
&ISO_8859_7_INIT,
&ISO_8859_7_INIT,
&ISO_8859_7_INIT,
&ISO_8859_6_INIT,
&ISO_8859_10_INIT,
&ISO_8859_8_INIT,
&ISO_8859_8_INIT,
&ISO_8859_8_INIT,
&WINDOWS_1254_INIT,
&WINDOWS_1254_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_3_INIT,
&EUC_KR_INIT,
&BIG5_INIT,
&SHIFT_JIS_INIT,
&ISO_8859_10_INIT,
&WINDOWS_874_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_2_INIT,
&ISO_8859_13_INIT,
&ISO_8859_3_INIT,
&ISO_8859_14_INIT,
&WINDOWS_874_INIT,
&ISO_8859_4_INIT,
&ISO_8859_15_INIT,
&ISO_8859_15_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_16_INIT,
&ISO_8859_10_INIT,
&EUC_KR_INIT,
&ISO_8859_15_INIT,
&ISO_8859_6_INIT,
&ISO_8859_8_INIT,
&MACINTOSH_INIT,
&ISO_8859_6_INIT,
&ISO_8859_8_I_INIT,
&SHIFT_JIS_INIT,
&MACINTOSH_INIT,
&REPLACEMENT_INIT,
&ISO_2022_JP_INIT,
&ISO_2022_JP_INIT,
&REPLACEMENT_INIT,
&REPLACEMENT_INIT,
&REPLACEMENT_INIT,
&WINDOWS_1250_INIT,
&WINDOWS_1251_INIT,
&WINDOWS_1252_INIT,
&WINDOWS_1253_INIT,
&WINDOWS_1254_INIT,
&WINDOWS_1255_INIT,
&WINDOWS_1256_INIT,
&WINDOWS_1257_INIT,
&WINDOWS_1258_INIT,
&ISO_8859_6_INIT,
&ISO_8859_8_INIT,
&ISO_8859_6_INIT,
&ISO_8859_8_I_INIT,
&ISO_8859_7_INIT,
&EUC_KR_INIT,
&EUC_KR_INIT,
&WINDOWS_1252_INIT,
&EUC_KR_INIT,
&X_MAC_CYRILLIC_INIT,
&X_USER_DEFINED_INIT,
&GBK_INIT,
&WINDOWS_1252_INIT,
&ISO_8859_2_INIT,
&ISO_8859_6_INIT,
&ISO_8859_7_INIT,
&ISO_8859_3_INIT,
&ISO_8859_4_INIT,
&ISO_8859_5_INIT,
&ISO_8859_8_INIT,
&WINDOWS_1254_INIT,
&ISO_8859_7_INIT,
&X_MAC_CYRILLIC_INIT,
&REPLACEMENT_INIT,
&ISO_8859_6_INIT,
&ISO_8859_8_INIT,
&UTF_8_INIT,
&ISO_8859_5_INIT,
&EUC_JP_INIT,
];
// END GENERATED CODE
/// An encoding as defined in the [Encoding Standard][1].
///
/// An _encoding_ defines a mapping from a `u8` sequence to a `char` sequence
/// and, in most cases, vice versa. Each encoding has a name, an output
/// encoding, and one or more labels.
///
/// _Labels_ are ASCII-case-insensitive strings that are used to identify an
/// encoding in formats and protocols. The _name_ of the encoding is the
/// preferred label in the case appropriate for returning from the
/// [`characterSet`][2] property of the `Document` DOM interface.
///
/// The _output encoding_ is the encoding used for form submission and URL
/// parsing on Web pages in the encoding. This is UTF-8 for the replacement,
/// UTF-16LE and UTF-16BE encodings and the encoding itself for other
/// encodings.
///
/// [1]: https://encoding.spec.whatwg.org/
/// [2]: https://dom.spec.whatwg.org/#dom-document-characterset
///
/// # Streaming vs. Non-Streaming
///
/// When you have the entire input in a single buffer, you can use the
/// methods [`decode()`][3], [`decode_with_bom_removal()`][3],
/// [`decode_without_bom_handling()`][5],
/// [`decode_without_bom_handling_and_without_replacement()`][6] and
/// [`encode()`][7]. (These methods are available to Rust callers only and are
/// not available in the C API.) Unlike the rest of the API available to Rust,
/// these methods perform heap allocations. You should the `Decoder` and
/// `Encoder` objects when your input is split into multiple buffers or when
/// you want to control the allocation of the output buffers.
///
/// [3]: #method.decode
/// [4]: #method.decode_with_bom_removal
/// [5]: #method.decode_without_bom_handling
/// [6]: #method.decode_without_bom_handling_and_without_replacement
/// [7]: #method.encode
///
/// # Instances
///
/// All instances of `Encoding` are statically allocated and have the `'static`
/// lifetime. There is precisely one unique `Encoding` instance for each
/// encoding defined in the Encoding Standard.
///
/// To obtain a reference to a particular encoding whose identity you know at
/// compile time, use a `static` that refers to encoding. There is a `static`
/// for each encoding. The `static`s are named in all caps with hyphens
/// replaced with underscores (and in C/C++ have `_ENCODING` appended to the
/// name). For example, if you know at compile time that you will want to
/// decode using the UTF-8 encoding, use the `UTF_8` `static` (`UTF_8_ENCODING`
/// in C/C++).
///
/// Additionally, there are non-reference-typed forms ending with `_INIT` to
/// work around the problem that `static`s of the type `&'static Encoding`
/// cannot be used to initialize items of an array whose type is
/// `[&'static Encoding; N]`.
///
/// If you don't know what encoding you need at compile time and need to
/// dynamically get an encoding by label, use
/// <code>Encoding::<a href="#method.for_label">for_label</a>(<var>label</var>)</code>.
///
/// Instances of `Encoding` can be compared with `==` (in both Rust and in
/// C/C++).
pub struct Encoding {
name: &'static str,
variant: VariantEncoding,
}
impl Encoding {
/// Implements the
/// [_get an encoding_](https://encoding.spec.whatwg.org/#concept-encoding-get)
/// algorithm.
///
/// If, after ASCII-lowercasing and removing leading and trailing
/// whitespace, the argument matches a label defined in the Encoding
/// Standard, `Some(&'static Encoding)` representing the corresponding
/// encoding is returned. If there is no match, `None` is returned.
///
/// This is the right method to use if the action upon the method returning
/// `None` is to use a fallback encoding (e.g. `WINDOWS_1252`) instead.
/// When the action upon the method returning `None` is not to proceed with
/// a fallback but to refuse processing, `for_label_no_replacement()` is more
/// appropriate.
///
/// The argument is of type `&[u8]` instead of `&str` to save callers
/// that are extracting the label from a non-UTF-8 protocol the trouble
/// of conversion to UTF-8. (If you have a `&str`, just call `.as_bytes()`
/// on it.)
///
/// Available via the C wrapper.
pub fn for_label(label: &[u8]) -> Option<&'static Encoding> {
let mut trimmed = [0u8; LONGEST_LABEL_LENGTH];
let mut trimmed_pos = 0usize;
let mut iter = label.into_iter();
// before
loop {
match iter.next() {
None => {
return None;
}
Some(byte) => {
// The characters used in labels are:
// a-z (except q, but excluding it below seems excessive)
// 0-9
// . _ - :
match *byte {
0x09u8 | 0x0Au8 | 0x0Cu8 | 0x0Du8 | 0x20u8 => {
continue;
}
b'A'...b'Z' => {
trimmed[trimmed_pos] = *byte + 0x20u8;
trimmed_pos = 1usize;
break;
}
b'a'...b'z' | b'0'...b'9' | b'-' | b'_' | b':' | b'.' => {
trimmed[trimmed_pos] = *byte;
trimmed_pos = 1usize;
break;
}
_ => {
return None;
}
}
}
}
}
// inside
loop {
match iter.next() {
None => {
break;
}
Some(byte) => {
match *byte {
0x09u8 | 0x0Au8 | 0x0Cu8 | 0x0Du8 | 0x20u8 => {
break;
}
b'A'...b'Z' => {
if trimmed_pos == LONGEST_LABEL_LENGTH {
// There's no encoding with a label this long
return None;
}
trimmed[trimmed_pos] = *byte + 0x20u8;
trimmed_pos += 1usize;
continue;
}
b'a'...b'z' | b'0'...b'9' | b'-' | b'_' | b':' | b'.' => {
if trimmed_pos == LONGEST_LABEL_LENGTH {
// There's no encoding with a label this long
return None;
}
trimmed[trimmed_pos] = *byte;
trimmed_pos += 1usize;
continue;
}
_ => {
return None;
}
}
}
}
}
// after
loop {
match iter.next() {
None => {
break;
}
Some(byte) => {
match *byte {
0x09u8 | 0x0Au8 | 0x0Cu8 | 0x0Du8 | 0x20u8 => {
continue;
}
_ => {
// There's no label with space in the middle
return None;
}
}
}
}
}
let candidate = &trimmed[..trimmed_pos];
match LABELS_SORTED.binary_search_by(|probe| {
let bytes = probe.as_bytes();
let c = bytes.len().cmp(&candidate.len());
if c != Ordering::Equal {
return c;
}
let probe_iter = bytes.iter().rev();
let candidate_iter = candidate.iter().rev();
probe_iter.cmp(candidate_iter)
}) {
Ok(i) => Some(ENCODINGS_IN_LABEL_SORT[i]),
Err(_) => None,
}
}
/// This method behaves the same as `for_label()`, except when `for_label()`
/// would return `Some(REPLACEMENT)`, this method returns `None` instead.
///
/// This method is useful in scenarios where a fatal error is required
/// upon invalid label, because in those cases the caller typically wishes
/// to treat the labels that map to the replacement encoding as fatal
/// errors, too.
///
/// It is not OK to use this method when the action upon the method returning
/// `None` is to use a fallback encoding (e.g. `WINDOWS_1252`). In such a
/// case, the `for_label()` method should be used instead in order to avoid
/// unsafe fallback for labels that `for_label()` maps to `Some(REPLACEMENT)`.
///
/// Available via the C wrapper.
#[inline]
pub fn for_label_no_replacement(label: &[u8]) -> Option<&'static Encoding> {
match Encoding::for_label(label) {
None => None,
Some(encoding) => {
if encoding == REPLACEMENT {
None
} else {
Some(encoding)
}
}
}
}
/// Performs non-incremental BOM sniffing.
///
/// The argument must either be a buffer representing the entire input
/// stream (non-streaming case) or a buffer representing at least the first
/// three bytes of the input stream (streaming case).
///
/// Returns `Some((UTF_8, 3))`, `Some((UTF_16LE, 2))` or
/// `Some((UTF_16BE, 2))` if the argument starts with the UTF-8, UTF-16LE
/// or UTF-16BE BOM or `None` otherwise.
///
/// Available via the C wrapper.
#[inline]
pub fn for_bom(buffer: &[u8]) -> Option<(&'static Encoding, usize)> {
if buffer.starts_with(b"\xEF\xBB\xBF") {
Some((UTF_8, 3))
} else if buffer.starts_with(b"\xFF\xFE") {
Some((UTF_16LE, 2))
} else if buffer.starts_with(b"\xFE\xFF") {
Some((UTF_16BE, 2))
} else {
None
}
}
/// Returns the name of this encoding.
///
/// This name is appropriate to return as-is from the DOM
/// `document.characterSet` property.
///
/// Available via the C wrapper.
#[inline]
pub fn name(&'static self) -> &'static str {
self.name
}
/// Checks whether the _output encoding_ of this encoding can encode every
/// `char`. (Only true if the output encoding is UTF-8.)
///
/// Available via the C wrapper.
#[inline]
pub fn can_encode_everything(&'static self) -> bool {
self.output_encoding() == UTF_8
}
/// Checks whether the bytes 0x00...0x7F map exclusively to the characters
/// U+0000...U+007F and vice versa.
///
/// Available via the C wrapper.
#[inline]
pub fn is_ascii_compatible(&'static self) -> bool {
!(self == REPLACEMENT || self == UTF_16BE || self == UTF_16LE || self == ISO_2022_JP)
}
/// Checks whether this encoding maps one byte to one Basic Multilingual
/// Plane code point (i.e. byte length equals decoded UTF-16 length) and
/// vice versa (for mappable characters).
///
/// `true` iff this encoding is on the list of [Legacy single-byte
/// encodings](https://encoding.spec.whatwg.org/#legacy-single-byte-encodings)
/// in the spec or x-user-defined.
///
/// Available via the C wrapper.
#[inline]
pub fn is_single_byte(&'static self) -> bool {
self.variant.is_single_byte()
}
/// Checks whether the bytes 0x00...0x7F map mostly to the characters
/// U+0000...U+007F and vice versa.
#[inline]
fn is_potentially_borrowable(&'static self) -> bool {
!(self == REPLACEMENT || self == UTF_16BE || self == UTF_16LE)
}
/// Returns the _output encoding_ of this encoding. This is UTF-8 for
/// UTF-16BE, UTF-16LE and replacement and the encoding itself otherwise.
///
/// Available via the C wrapper.
#[inline]
pub fn output_encoding(&'static self) -> &'static Encoding {
if self == REPLACEMENT || self == UTF_16BE || self == UTF_16LE {
UTF_8
} else {
self
}
}
/// Decode complete input to `Cow<'a, str>` _with BOM sniffing_ and with
/// malformed sequences replaced with the REPLACEMENT CHARACTER when the
/// entire input is available as a single buffer (i.e. the end of the
/// buffer marks the end of the stream).
///
/// This method implements the (non-streaming version of) the
/// [_decode_](https://encoding.spec.whatwg.org/#decode) spec concept.
///
/// The second item in the returned tuple is the encoding that was actually
/// used (which may differ from this encoding thanks to BOM sniffing).
///
/// The third item in the returned tuple indicates whether there were
/// malformed sequences (that were replaced with the REPLACEMENT CHARACTER).
///
/// _Note:_ It is wrong to use this when the input buffer represents only
/// a segment of the input instead of the whole input. Use `new_decoder()`
/// when decoding segmented input.
///
/// This method performs a one or two heap allocations for the backing
/// buffer of the `String` when unable to borrow. (One allocation if not
/// errors and potentially another one in the presence of errors.) The
/// first allocation assumes jemalloc and may not be optimal with
/// allocators that do not use power-of-two buckets. A borrow is performed
/// if decoding UTF-8 and the input is valid UTF-8, if decoding an
/// ASCII-compatible encoding and the input is ASCII-only, or when decoding
/// ISO-2022-JP and the input is entirely in the ASCII state without state
/// transitions.
///
/// # Panics
///
/// If the size calculation for a heap-allocated backing buffer overflows
/// `usize`.
///
/// Available to Rust only.
#[inline]
pub fn decode<'a>(&'static self, bytes: &'a [u8]) -> (Cow<'a, str>, &'static Encoding, bool) {
let (encoding, without_bom) = match Encoding::for_bom(bytes) {
Some((encoding, bom_length)) => (encoding, &bytes[bom_length..]),
None => (self, bytes),
};
let (cow, had_errors) = encoding.decode_without_bom_handling(without_bom);
(cow, encoding, had_errors)
}
/// Decode complete input to `Cow<'a, str>` _with BOM removal_ and with
/// malformed sequences replaced with the REPLACEMENT CHARACTER when the
/// entire input is available as a single buffer (i.e. the end of the
/// buffer marks the end of the stream).
///
/// When invoked on `UTF_8`, this method implements the (non-streaming
/// version of) the
/// [_UTF-8 decode_](https://encoding.spec.whatwg.org/#utf-8-decode) spec
/// concept.
///
/// The second item in the returned pair indicates whether there were
/// malformed sequences (that were replaced with the REPLACEMENT CHARACTER).
///
/// _Note:_ It is wrong to use this when the input buffer represents only
/// a segment of the input instead of the whole input. Use
/// `new_decoder_with_bom_removal()` when decoding segmented input.
///
/// This method performs a one or two heap allocations for the backing
/// buffer of the `String` when unable to borrow. (One allocation if not
/// errors and potentially another one in the presence of errors.) The
/// first allocation assumes jemalloc and may not be optimal with
/// allocators that do not use power-of-two buckets. A borrow is performed
/// if decoding UTF-8 and the input is valid UTF-8, if decoding an
/// ASCII-compatible encoding and the input is ASCII-only, or when decoding
/// ISO-2022-JP and the input is entirely in the ASCII state without state
/// transitions.
///
/// # Panics
///
/// If the size calculation for a heap-allocated backing buffer overflows
/// `usize`.
///
/// Available to Rust only.
#[inline]
pub fn decode_with_bom_removal<'a>(&'static self, bytes: &'a [u8]) -> (Cow<'a, str>, bool) {
let without_bom = if self == UTF_8 && bytes.starts_with(b"\xEF\xBB\xBF") {
&bytes[3..]
} else if (self == UTF_16LE && bytes.starts_with(b"\xFF\xFE"))
|| (self == UTF_16BE && bytes.starts_with(b"\xFE\xFF"))
{
&bytes[2..]
} else {
bytes
};
self.decode_without_bom_handling(without_bom)
}
/// Decode complete input to `Cow<'a, str>` _without BOM handling_ and
/// with malformed sequences replaced with the REPLACEMENT CHARACTER when
/// the entire input is available as a single buffer (i.e. the end of the
/// buffer marks the end of the stream).
///
/// When invoked on `UTF_8`, this method implements the (non-streaming
/// version of) the
/// [_UTF-8 decode without BOM_](https://encoding.spec.whatwg.org/#utf-8-decode-without-bom)
/// spec concept.
///
/// The second item in the returned pair indicates whether there were
/// malformed sequences (that were replaced with the REPLACEMENT CHARACTER).
///
/// _Note:_ It is wrong to use this when the input buffer represents only
/// a segment of the input instead of the whole input. Use
/// `new_decoder_without_bom_handling()` when decoding segmented input.
///
/// This method performs a one or two heap allocations for the backing
/// buffer of the `String` when unable to borrow. (One allocation if not
/// errors and potentially another one in the presence of errors.) The
/// first allocation assumes jemalloc and may not be optimal with
/// allocators that do not use power-of-two buckets. A borrow is performed
/// if decoding UTF-8 and the input is valid UTF-8, if decoding an
/// ASCII-compatible encoding and the input is ASCII-only, or when decoding
/// ISO-2022-JP and the input is entirely in the ASCII state without state
/// transitions.
///
/// # Panics
///
/// If the size calculation for a heap-allocated backing buffer overflows
/// `usize`.
///
/// Available to Rust only.
pub fn decode_without_bom_handling<'a>(&'static self, bytes: &'a [u8]) -> (Cow<'a, str>, bool) {
let (mut decoder, mut string, mut total_read) = if self.is_potentially_borrowable() {
let valid_up_to = if self == UTF_8 {
utf8_valid_up_to(bytes)
} else if self == ISO_2022_JP {
iso_2022_jp_ascii_valid_up_to(bytes)
} else {
ascii_valid_up_to(bytes)
};
if valid_up_to == bytes.len() {
let str: &str = unsafe { std::str::from_utf8_unchecked(bytes) };
return (Cow::Borrowed(str), false);
}
let decoder = self.new_decoder_without_bom_handling();
let rounded_without_replacement = checked_next_power_of_two(checked_add(
valid_up_to,
decoder.max_utf8_buffer_length_without_replacement(bytes.len() - valid_up_to),
));
let with_replacement = checked_add(
valid_up_to,
decoder.max_utf8_buffer_length(bytes.len() - valid_up_to),
);
let mut string = String::with_capacity(
checked_min(rounded_without_replacement, with_replacement).unwrap(),
);
unsafe {
let vec = string.as_mut_vec();
vec.set_len(valid_up_to);
std::ptr::copy_nonoverlapping(bytes.as_ptr(), vec.as_mut_ptr(), valid_up_to);
}
(decoder, string, valid_up_to)
} else {
let decoder = self.new_decoder_without_bom_handling();
let rounded_without_replacement = checked_next_power_of_two(
decoder.max_utf8_buffer_length_without_replacement(bytes.len()),
);
let with_replacement = decoder.max_utf8_buffer_length(bytes.len());
let string = String::with_capacity(
checked_min(rounded_without_replacement, with_replacement).unwrap(),
);
(decoder, string, 0)
};
let mut total_had_errors = false;
loop {
let (result, read, had_errors) =
decoder.decode_to_string(&bytes[total_read..], &mut string, true);
total_read += read;
total_had_errors |= had_errors;
match result {
CoderResult::InputEmpty => {
debug_assert_eq!(total_read, bytes.len());
return (Cow::Owned(string), total_had_errors);
}
CoderResult::OutputFull => {
// Allocate for the worst case. That is, we should come
// here at most once per invocation of this method.
let needed = decoder.max_utf8_buffer_length(bytes.len() - total_read);
string.reserve(needed.unwrap());
}
}
}
}
/// Decode complete input to `Cow<'a, str>` _without BOM handling_ and
/// _with malformed sequences treated as fatal_ when the entire input is
/// available as a single buffer (i.e. the end of the buffer marks the end
/// of the stream).
///
/// When invoked on `UTF_8`, this method implements the (non-streaming
/// version of) the
/// [_UTF-8 decode without BOM or fail_](https://encoding.spec.whatwg.org/#utf-8-decode-without-bom-or-fail)
/// spec concept.
///
/// Returns `None` if a malformed sequence was encountered and the result
/// of the decode as `Some(String)` otherwise.
///
/// _Note:_ It is wrong to use this when the input buffer represents only
/// a segment of the input instead of the whole input. Use
/// `new_decoder_without_bom_handling()` when decoding segmented input.
///
/// This method performs a single heap allocation for the backing
/// buffer of the `String` when unable to borrow. A borrow is performed if
/// decoding UTF-8 and the input is valid UTF-8, if decoding an
/// ASCII-compatible encoding and the input is ASCII-only, or when decoding
/// ISO-2022-JP and the input is entirely in the ASCII state without state
/// transitions.
///
/// # Panics
///
/// If the size calculation for a heap-allocated backing buffer overflows
/// `usize`.
///
/// Available to Rust only.
pub fn decode_without_bom_handling_and_without_replacement<'a>(
&'static self,
bytes: &'a [u8],
) -> Option<Cow<'a, str>> {
if self == UTF_8 {
let valid_up_to = utf8_valid_up_to(bytes);
if valid_up_to == bytes.len() {
let str: &str = unsafe { std::str::from_utf8_unchecked(bytes) };
return Some(Cow::Borrowed(str));
}
return None;
}
let (mut decoder, mut string, input) = if self.is_potentially_borrowable() {
let valid_up_to = if self == ISO_2022_JP {
iso_2022_jp_ascii_valid_up_to(bytes)
} else {
ascii_valid_up_to(bytes)
};
if valid_up_to == bytes.len() {
let str: &str = unsafe { std::str::from_utf8_unchecked(bytes) };
return Some(Cow::Borrowed(str));
}
let decoder = self.new_decoder_without_bom_handling();
let mut string = String::with_capacity(
checked_add(
valid_up_to,
decoder.max_utf8_buffer_length_without_replacement(bytes.len() - valid_up_to),
)
.unwrap(),
);
unsafe {
let vec = string.as_mut_vec();
vec.set_len(valid_up_to);
std::ptr::copy_nonoverlapping(bytes.as_ptr(), vec.as_mut_ptr(), valid_up_to);
}
(decoder, string, &bytes[valid_up_to..])
} else {
let decoder = self.new_decoder_without_bom_handling();
let string = String::with_capacity(
decoder
.max_utf8_buffer_length_without_replacement(bytes.len())
.unwrap(),
);
(decoder, string, bytes)
};
let (result, read) = decoder.decode_to_string_without_replacement(input, &mut string, true);
match result {
DecoderResult::InputEmpty => {
debug_assert_eq!(read, input.len());
Some(Cow::Owned(string))
}
DecoderResult::Malformed(_, _) => None,
DecoderResult::OutputFull => unreachable!(),
}
}
/// Encode complete input to `Cow<'a, [u8]>` with unmappable characters
/// replaced with decimal numeric character references when the entire input
/// is available as a single buffer (i.e. the end of the buffer marks the
/// end of the stream).
///
/// This method implements the (non-streaming version of) the
/// [_encode_](https://encoding.spec.whatwg.org/#encode) spec concept. For
/// the [_UTF-8 encode_](https://encoding.spec.whatwg.org/#utf-8-encode)
/// spec concept, it is slightly more efficient to use
/// <code><var>string</var>.as_bytes()</code> instead of invoking this
/// method on `UTF_8`.
///
/// The second item in the returned tuple is the encoding that was actually
/// used (which may differ from this encoding thanks to some encodings
/// having UTF-8 as their output encoding).
///
/// The third item in the returned tuple indicates whether there were
/// unmappable characters (that were replaced with HTML numeric character
/// references).
///
/// _Note:_ It is wrong to use this when the input buffer represents only
/// a segment of the input instead of the whole input. Use `new_encoder()`
/// when encoding segmented output.
///
/// When encoding to UTF-8 or when encoding an ASCII-only input to a
/// ASCII-compatible encoding, this method returns a borrow of the input
/// without a heap allocation. Otherwise, this method performs a single
/// heap allocation for the backing buffer of the `Vec<u8>` if there are no
/// unmappable characters and potentially multiple heap allocations if
/// there are. These allocations are tuned for jemalloc and may not be
/// optimal when using a different allocator that doesn't use power-of-two
/// buckets.
///
/// # Panics
///
/// If the size calculation for a heap-allocated backing buffer overflows
/// `usize`.
///
/// Available to Rust only.
pub fn encode<'a>(&'static self, string: &'a str) -> (Cow<'a, [u8]>, &'static Encoding, bool) {
let output_encoding = self.output_encoding();
if output_encoding == UTF_8 {
return (Cow::Borrowed(string.as_bytes()), output_encoding, false);
}
debug_assert!(output_encoding.is_potentially_borrowable());
let bytes = string.as_bytes();
let valid_up_to = if output_encoding == ISO_2022_JP {
iso_2022_jp_ascii_valid_up_to(bytes)
} else {
ascii_valid_up_to(bytes)
};
if valid_up_to == bytes.len() {
return (Cow::Borrowed(bytes), output_encoding, false);
}
let mut encoder = output_encoding.new_encoder();
let mut vec: Vec<u8> = Vec::with_capacity(
(checked_add(
valid_up_to,
encoder.max_buffer_length_from_utf8_if_no_unmappables(string.len() - valid_up_to),
))
.unwrap()
.next_power_of_two(),
);
unsafe {
vec.set_len(valid_up_to);
std::ptr::copy_nonoverlapping(bytes.as_ptr(), vec.as_mut_ptr(), valid_up_to);
}
let mut total_read = valid_up_to;
let mut total_had_errors = false;
loop {
let (result, read, had_errors) =
encoder.encode_from_utf8_to_vec(&string[total_read..], &mut vec, true);
total_read += read;
total_had_errors |= had_errors;
match result {
CoderResult::InputEmpty => {
debug_assert_eq!(total_read, string.len());
return (Cow::Owned(vec), output_encoding, total_had_errors);
}
CoderResult::OutputFull => {
// reserve_exact wants to know how much more on top of current
// length--not current capacity.
let needed = encoder
.max_buffer_length_from_utf8_if_no_unmappables(string.len() - total_read);
let rounded = (checked_add(vec.capacity(), needed))
.unwrap()
.next_power_of_two();
let additional = rounded - vec.len();
vec.reserve_exact(additional);
}
}
}
}
fn new_variant_decoder(&'static self) -> VariantDecoder {
self.variant.new_variant_decoder()
}
/// Instantiates a new decoder for this encoding with BOM sniffing enabled.
///
/// BOM sniffing may cause the returned decoder to morph into a decoder
/// for UTF-8, UTF-16LE or UTF-16BE instead of this encoding.
///
/// Available via the C wrapper.
#[inline]
pub fn new_decoder(&'static self) -> Decoder {
Decoder::new(self, self.new_variant_decoder(), BomHandling::Sniff)
}
/// Instantiates a new decoder for this encoding with BOM removal.
///
/// If the input starts with bytes that are the BOM for this encoding,
/// those bytes are removed. However, the decoder never morphs into a
/// decoder for another encoding: A BOM for another encoding is treated as
/// (potentially malformed) input to the decoding algorithm for this
/// encoding.
///
/// Available via the C wrapper.
#[inline]
pub fn new_decoder_with_bom_removal(&'static self) -> Decoder {
Decoder::new(self, self.new_variant_decoder(), BomHandling::Remove)
}
/// Instantiates a new decoder for this encoding with BOM handling disabled.
///
/// If the input starts with bytes that look like a BOM, those bytes are
/// not treated as a BOM. (Hence, the decoder never morphs into a decoder
/// for another encoding.)
///
/// _Note:_ If the caller has performed BOM sniffing on its own but has not
/// removed the BOM, the caller should use `new_decoder_with_bom_removal()`
/// instead of this method to cause the BOM to be removed.
///
/// Available via the C wrapper.
#[inline]
pub fn new_decoder_without_bom_handling(&'static self) -> Decoder {
Decoder::new(self, self.new_variant_decoder(), BomHandling::Off)
}
/// Instantiates a new encoder for the output encoding of this encoding.
///
/// Available via the C wrapper.
#[inline]
pub fn new_encoder(&'static self) -> Encoder {
let enc = self.output_encoding();
enc.variant.new_encoder(enc)
}
/// Validates UTF-8.
///
/// Returns the index of the first byte that makes the input malformed as
/// UTF-8 or the length of the slice if the slice is entirely valid.
///
/// This is currently faster than the corresponding standard library
/// functionality. If this implementation gets upstreamed to the standard
/// library, this method may be removed in the future.
///
/// Available via the C wrapper.
pub fn utf8_valid_up_to(bytes: &[u8]) -> usize {
utf8_valid_up_to(bytes)
}
/// Validates ASCII.
///
/// Returns the index of the first byte that makes the input malformed as
/// ASCII or the length of the slice if the slice is entirely valid.
///
/// Available via the C wrapper.
pub fn ascii_valid_up_to(bytes: &[u8]) -> usize {
ascii_valid_up_to(bytes)
}
/// Validates ISO-2022-JP ASCII-state data.
///
/// Returns the index of the first byte that makes the input not
/// representable in the ASCII state of ISO-2022-JP or the length of the
/// slice if the slice is entirely representable in the ASCII state of
/// ISO-2022-JP.
///
/// Available via the C wrapper.
pub fn iso_2022_jp_ascii_valid_up_to(bytes: &[u8]) -> usize {
iso_2022_jp_ascii_valid_up_to(bytes)
}
}
impl PartialEq for Encoding {
#[inline]
fn eq(&self, other: &Encoding) -> bool {
(self as *const Encoding) == (other as *const Encoding)
}
}
impl Eq for Encoding {}
impl Hash for Encoding {
#[inline]
fn hash<H: Hasher>(&self, state: &mut H) {
(self as *const Encoding).hash(state);
}
}
impl std::fmt::Debug for Encoding {
#[inline]
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
write!(f, "Encoding {{ {} }}", self.name)
}
}
#[cfg(feature = "serde")]
impl Serialize for Encoding {
#[inline]
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
serializer.serialize_str(self.name)
}
}
#[cfg(feature = "serde")]
struct EncodingVisitor;
#[cfg(feature = "serde")]
impl<'de> Visitor<'de> for EncodingVisitor {
type Value = &'static Encoding;
fn expecting(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
formatter.write_str("a valid encoding label")
}
fn visit_str<E>(self, value: &str) -> Result<&'static Encoding, E>
where
E: serde::de::Error,
{
if let Some(enc) = Encoding::for_label(value.as_bytes()) {
Ok(enc)
} else {
Err(E::custom(format!("invalid encoding label: {}", value)))
}
}
}
#[cfg(feature = "serde")]
impl<'de> Deserialize<'de> for &'static Encoding {
fn deserialize<D>(deserializer: D) -> Result<&'static Encoding, D::Error>
where
D: Deserializer<'de>,
{
deserializer.deserialize_str(EncodingVisitor)
}
}
/// Tracks the life cycle of a decoder from BOM sniffing to conversion to end.
#[derive(PartialEq, Debug, Copy, Clone)]
enum DecoderLifeCycle {
/// The decoder has seen no input yet.
AtStart,
/// The decoder has seen no input yet but expects UTF-8.
AtUtf8Start,
/// The decoder has seen no input yet but expects UTF-16BE.
AtUtf16BeStart,
/// The decoder has seen no input yet but expects UTF-16LE.
AtUtf16LeStart,
/// The decoder has seen EF.
SeenUtf8First,
/// The decoder has seen EF, BB.
SeenUtf8Second,
/// The decoder has seen FE.
SeenUtf16BeFirst,
/// The decoder has seen FF.
SeenUtf16LeFirst,
/// Saw EF, BB but not BF, there was a buffer boundary after BB and the
/// underlying decoder reported EF as an error, so we need to remember to
/// push BB before the next buffer.
ConvertingWithPendingBB,
/// No longer looking for a BOM and EOF not yet seen.
Converting,
/// EOF has been seen.
Finished,
}
/// Communicate the BOM handling mode.
#[derive(Debug, Copy, Clone)]
enum BomHandling {
/// Don't handle the BOM
Off,
/// Sniff for UTF-8, UTF-16BE or UTF-16LE BOM
Sniff,
/// Remove the BOM only if it's the BOM for this encoding
Remove,
}
/// Result of a (potentially partial) decode or encode operation with
/// replacement.
#[must_use]
#[derive(Debug, PartialEq, Eq)]
pub enum CoderResult {
/// The input was exhausted.
///
/// If this result was returned from a call where `last` was `true`, the
/// conversion process has completed. Otherwise, the caller should call a
/// decode or encode method again with more input.
InputEmpty,
/// The converter cannot produce another unit of output, because the output
/// buffer does not have enough space left.
///
/// The caller must provide more output space upon the next call and re-push
/// the remaining input to the converter.
OutputFull,
}
/// Result of a (potentially partial) decode operation without replacement.
#[must_use]
#[derive(Debug, PartialEq, Eq)]
pub enum DecoderResult {
/// The input was exhausted.
///
/// If this result was returned from a call where `last` was `true`, the
/// decoding process has completed. Otherwise, the caller should call a
/// decode method again with more input.
InputEmpty,
/// The decoder cannot produce another unit of output, because the output
/// buffer does not have enough space left.
///
/// The caller must provide more output space upon the next call and re-push
/// the remaining input to the decoder.
OutputFull,
/// The decoder encountered a malformed byte sequence.
///
/// The caller must either treat this as a fatal error or must append one
/// REPLACEMENT CHARACTER (U+FFFD) to the output and then re-push the
/// the remaining input to the decoder.
///
/// The first wrapped integer indicates the length of the malformed byte
/// sequence. The second wrapped integer indicates the number of bytes
/// that were consumed after the malformed sequence. If the second
/// integer is zero, the last byte that was consumed is the last byte of
/// the malformed sequence. Note that the malformed bytes may have been part
/// of an earlier input buffer.
///
/// The first wrapped integer can have values 1, 2, 3 or 4. The second
/// wrapped integer can have values 0, 1, 2 or 3. The worst-case sum
/// of the two is 6, which happens with ISO-2022-JP.
Malformed(u8, u8), // u8 instead of usize to avoid useless bloat
}
/// A converter that decodes a byte stream into Unicode according to a
/// character encoding in a streaming (incremental) manner.
///
/// The various `decode_*` methods take an input buffer (`src`) and an output
/// buffer `dst` both of which are caller-allocated. There are variants for
/// both UTF-8 and UTF-16 output buffers.
///
/// A `decode_*` method decodes bytes from `src` into Unicode characters stored
/// into `dst` until one of the following three things happens:
///
/// 1. A malformed byte sequence is encountered (`*_without_replacement`
/// variants only).
///
/// 2. The output buffer has been filled so near capacity that the decoder
/// cannot be sure that processing an additional byte of input wouldn't
/// cause so much output that the output buffer would overflow.
///
/// 3. All the input bytes have been processed.
///
/// The `decode_*` method then returns tuple of a status indicating which one
/// of the three reasons to return happened, how many input bytes were read,
/// how many output code units (`u8` when decoding into UTF-8 and `u16`
/// when decoding to UTF-16) were written (except when decoding into `String`,
/// whose length change indicates this), and in the case of the
/// variants performing replacement, a boolean indicating whether an error was
/// replaced with the REPLACEMENT CHARACTER during the call.
///
/// The number of bytes "written" is what's logically written. Garbage may be
/// written in the output buffer beyond the point logically written to.
/// Therefore, if you wish to decode into an `&mut str`, you should use the
/// methods that take an `&mut str` argument instead of the ones that take an
/// `&mut [u8]` argument. The former take care of overwriting the trailing
/// garbage to ensure the UTF-8 validity of the `&mut str` as a whole, but the
/// latter don't.
///
/// In the case of the `*_without_replacement` variants, the status is a
/// [`DecoderResult`][1] enumeration (possibilities `Malformed`, `OutputFull` and
/// `InputEmpty` corresponding to the three cases listed above).
///
/// In the case of methods whose name does not end with
/// `*_without_replacement`, malformed sequences are automatically replaced
/// with the REPLACEMENT CHARACTER and errors do not cause the methods to
/// return early.
///
/// When decoding to UTF-8, the output buffer must have at least 4 bytes of
/// space. When decoding to UTF-16, the output buffer must have at least two
/// UTF-16 code units (`u16`) of space.
///
/// When decoding to UTF-8 without replacement, the methods are guaranteed
/// not to return indicating that more output space is needed if the length
/// of the output buffer is at least the length returned by
/// [`max_utf8_buffer_length_without_replacement()`][2]. When decoding to UTF-8
/// with replacement, the length of the output buffer that guarantees the
/// methods not to return indicating that more output space is needed is given
/// by [`max_utf8_buffer_length()`][3]. When decoding to UTF-16 with
/// or without replacement, the length of the output buffer that guarantees
/// the methods not to return indicating that more output space is needed is
/// given by [`max_utf16_buffer_length()`][4].
///
/// The output written into `dst` is guaranteed to be valid UTF-8 or UTF-16,
/// and the output after each `decode_*` call is guaranteed to consist of
/// complete characters. (I.e. the code unit sequence for the last character is
/// guaranteed not to be split across output buffers.)
///
/// The boolean argument `last` indicates that the end of the stream is reached
/// when all the bytes in `src` have been consumed.
///
/// A `Decoder` object can be used to incrementally decode a byte stream.
///
/// During the processing of a single stream, the caller must call `decode_*`
/// zero or more times with `last` set to `false` and then call `decode_*` at
/// least once with `last` set to `true`. If `decode_*` returns `InputEmpty`,
/// the processing of the stream has ended. Otherwise, the caller must call
/// `decode_*` again with `last` set to `true` (or treat a `Malformed` result as
/// a fatal error).
///
/// Once the stream has ended, the `Decoder` object must not be used anymore.
/// That is, you need to create another one to process another stream.
///
/// When the decoder returns `OutputFull` or the decoder returns `Malformed` and
/// the caller does not wish to treat it as a fatal error, the input buffer
/// `src` may not have been completely consumed. In that case, the caller must
/// pass the unconsumed contents of `src` to `decode_*` again upon the next
/// call.
///
/// [1]: enum.DecoderResult.html
/// [2]: #method.max_utf8_buffer_length_without_replacement
/// [3]: #method.max_utf8_buffer_length
/// [4]: #method.max_utf16_buffer_length
///
/// # Infinite loops
///
/// When converting with a fixed-size output buffer whose size is too small to
/// accommodate one character or (when applicable) one numeric character
/// reference of output, an infinite loop ensues. When converting with a
/// fixed-size output buffer, it generally makes sense to make the buffer
/// fairly large (e.g. couple of kilobytes).
pub struct Decoder {
encoding: &'static Encoding,
variant: VariantDecoder,
life_cycle: DecoderLifeCycle,
}
impl Decoder {
fn new(enc: &'static Encoding, decoder: VariantDecoder, sniffing: BomHandling) -> Decoder {
Decoder {
encoding: enc,
variant: decoder,
life_cycle: match sniffing {
BomHandling::Off => DecoderLifeCycle::Converting,
BomHandling::Sniff => DecoderLifeCycle::AtStart,
BomHandling::Remove => {
if enc == UTF_8 {
DecoderLifeCycle::AtUtf8Start
} else if enc == UTF_16BE {
DecoderLifeCycle::AtUtf16BeStart
} else if enc == UTF_16LE {
DecoderLifeCycle::AtUtf16LeStart
} else {
DecoderLifeCycle::Converting
}
}
},
}
}
/// The `Encoding` this `Decoder` is for.
///
/// BOM sniffing can change the return value of this method during the life
/// of the decoder.
///
/// Available via the C wrapper.
#[inline]
pub fn encoding(&self) -> &'static Encoding {
self.encoding
}
/// Query the worst-case UTF-8 output size _with replacement_.
///
/// Returns the size of the output buffer in UTF-8 code units (`u8`)
/// that will not overflow given the current state of the decoder and
/// `byte_length` number of additional input bytes when decoding with
/// errors handled by outputting a REPLACEMENT CHARACTER for each malformed
/// sequence or `None` if `usize` would overflow.
///
/// Available via the C wrapper.
pub fn max_utf8_buffer_length(&self, byte_length: usize) -> Option<usize> {
// Need to consider a) the decoder morphing due to the BOM and b) a partial
// BOM getting pushed to the underlying decoder.
match self.life_cycle {
DecoderLifeCycle::Converting
| DecoderLifeCycle::AtUtf8Start
| DecoderLifeCycle::AtUtf16LeStart
| DecoderLifeCycle::AtUtf16BeStart => {
return self.variant.max_utf8_buffer_length(byte_length)
}
DecoderLifeCycle::AtStart => {
if let Some(utf8_bom) = checked_add(3, byte_length.checked_mul(3)) {
if let Some(utf16_bom) = checked_add(
1,
checked_mul(3, checked_div(byte_length.checked_add(1), 2)),
) {
let utf_bom = std::cmp::max(utf8_bom, utf16_bom);
let encoding = self.encoding();
if encoding == UTF_8 || encoding == UTF_16LE || encoding == UTF_16BE {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf_bom);
} else if let Some(non_bom) =
self.variant.max_utf8_buffer_length(byte_length)
{
return Some(std::cmp::max(utf_bom, non_bom));
}
}
}
}
DecoderLifeCycle::SeenUtf8First | DecoderLifeCycle::SeenUtf8Second => {
// Add two bytes even when only one byte has been seen,
// because the one byte can become a lead byte in multibyte
// decoders, but only after the decoder has been queried
// for max length, so the decoder's own logic for adding
// one for a pending lead cannot work.
if let Some(sum) = byte_length.checked_add(2) {
if let Some(utf8_bom) = checked_add(3, sum.checked_mul(3)) {
if self.encoding() == UTF_8 {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf8_bom);
} else if let Some(non_bom) = self.variant.max_utf8_buffer_length(sum) {
return Some(std::cmp::max(utf8_bom, non_bom));
}
}
}
}
DecoderLifeCycle::ConvertingWithPendingBB => {
if let Some(sum) = byte_length.checked_add(2) {
return self.variant.max_utf8_buffer_length(sum);
}
}
DecoderLifeCycle::SeenUtf16LeFirst | DecoderLifeCycle::SeenUtf16BeFirst => {
// Add two bytes even when only one byte has been seen,
// because the one byte can become a lead byte in multibyte
// decoders, but only after the decoder has been queried
// for max length, so the decoder's own logic for adding
// one for a pending lead cannot work.
if let Some(sum) = byte_length.checked_add(2) {
if let Some(utf16_bom) =
checked_add(1, checked_mul(3, checked_div(sum.checked_add(1), 2)))
{
let encoding = self.encoding();
if encoding == UTF_16LE || encoding == UTF_16BE {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf16_bom);
} else if let Some(non_bom) = self.variant.max_utf8_buffer_length(sum) {
return Some(std::cmp::max(utf16_bom, non_bom));
}
}
}
}
DecoderLifeCycle::Finished => panic!("Must not use a decoder that has finished."),
}
None
}
/// Query the worst-case UTF-8 output size _without replacement_.
///
/// Returns the size of the output buffer in UTF-8 code units (`u8`)
/// that will not overflow given the current state of the decoder and
/// `byte_length` number of additional input bytes when decoding without
/// replacement error handling or `None` if `usize` would overflow.
///
/// Note that this value may be too small for the `_with_replacement` case.
/// Use `max_utf8_buffer_length()` for that case.
///
/// Available via the C wrapper.
pub fn max_utf8_buffer_length_without_replacement(&self, byte_length: usize) -> Option<usize> {
// Need to consider a) the decoder morphing due to the BOM and b) a partial
// BOM getting pushed to the underlying decoder.
match self.life_cycle {
DecoderLifeCycle::Converting
| DecoderLifeCycle::AtUtf8Start
| DecoderLifeCycle::AtUtf16LeStart
| DecoderLifeCycle::AtUtf16BeStart => {
return self
.variant
.max_utf8_buffer_length_without_replacement(byte_length)
}
DecoderLifeCycle::AtStart => {
if let Some(utf8_bom) = byte_length.checked_add(3) {
if let Some(utf16_bom) = checked_add(
1,
checked_mul(3, checked_div(byte_length.checked_add(1), 2)),
) {
let utf_bom = std::cmp::max(utf8_bom, utf16_bom);
let encoding = self.encoding();
if encoding == UTF_8 || encoding == UTF_16LE || encoding == UTF_16BE {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf_bom);
} else if let Some(non_bom) = self
.variant
.max_utf8_buffer_length_without_replacement(byte_length)
{
return Some(std::cmp::max(utf_bom, non_bom));
}
}
}
}
DecoderLifeCycle::SeenUtf8First | DecoderLifeCycle::SeenUtf8Second => {
// Add two bytes even when only one byte has been seen,
// because the one byte can become a lead byte in multibyte
// decoders, but only after the decoder has been queried
// for max length, so the decoder's own logic for adding
// one for a pending lead cannot work.
if let Some(sum) = byte_length.checked_add(2) {
if let Some(utf8_bom) = sum.checked_add(3) {
if self.encoding() == UTF_8 {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf8_bom);
} else if let Some(non_bom) =
self.variant.max_utf8_buffer_length_without_replacement(sum)
{
return Some(std::cmp::max(utf8_bom, non_bom));
}
}
}
}
DecoderLifeCycle::ConvertingWithPendingBB => {
if let Some(sum) = byte_length.checked_add(2) {
return self.variant.max_utf8_buffer_length_without_replacement(sum);
}
}
DecoderLifeCycle::SeenUtf16LeFirst | DecoderLifeCycle::SeenUtf16BeFirst => {
// Add two bytes even when only one byte has been seen,
// because the one byte can become a lead byte in multibyte
// decoders, but only after the decoder has been queried
// for max length, so the decoder's own logic for adding
// one for a pending lead cannot work.
if let Some(sum) = byte_length.checked_add(2) {
if let Some(utf16_bom) =
checked_add(1, checked_mul(3, checked_div(sum.checked_add(1), 2)))
{
let encoding = self.encoding();
if encoding == UTF_16LE || encoding == UTF_16BE {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf16_bom);
} else if let Some(non_bom) =
self.variant.max_utf8_buffer_length_without_replacement(sum)
{
return Some(std::cmp::max(utf16_bom, non_bom));
}
}
}
}
DecoderLifeCycle::Finished => panic!("Must not use a decoder that has finished."),
}
None
}
/// Incrementally decode a byte stream into UTF-8 with malformed sequences
/// replaced with the REPLACEMENT CHARACTER.
///
/// See the documentation of the struct for documentation for `decode_*`
/// methods collectively.
///
/// Available via the C wrapper.
pub fn decode_to_utf8(
&mut self,
src: &[u8],
dst: &mut [u8],
last: bool,
) -> (CoderResult, usize, usize, bool) {
let mut had_errors = false;
let mut total_read = 0usize;
let mut total_written = 0usize;
loop {
let (result, read, written) = self.decode_to_utf8_without_replacement(
&src[total_read..],
&mut dst[total_written..],
last,
);
total_read += read;
total_written += written;
match result {
DecoderResult::InputEmpty => {
return (
CoderResult::InputEmpty,
total_read,
total_written,
had_errors,
);
}
DecoderResult::OutputFull => {
return (
CoderResult::OutputFull,
total_read,
total_written,
had_errors,
);
}
DecoderResult::Malformed(_, _) => {
had_errors = true;
// There should always be space for the U+FFFD, because
// otherwise we'd have gotten OutputFull already.
// XXX: is the above comment actually true for UTF-8 itself?
// TODO: Consider having fewer bound checks here.
dst[total_written] = 0xEFu8;
total_written += 1;
dst[total_written] = 0xBFu8;
total_written += 1;
dst[total_written] = 0xBDu8;
total_written += 1;
}
}
}
}
/// Incrementally decode a byte stream into UTF-8 with malformed sequences
/// replaced with the REPLACEMENT CHARACTER with type system signaling
/// of UTF-8 validity.
///
/// This methods calls `decode_to_utf8` and then zeroes
/// out up to three bytes that aren't logically part of the write in order
/// to retain the UTF-8 validity even for the unwritten part of the buffer.
///
/// See the documentation of the struct for documentation for `decode_*`
/// methods collectively.
///
/// Available to Rust only.
pub fn decode_to_str(
&mut self,
src: &[u8],
dst: &mut str,
last: bool,
) -> (CoderResult, usize, usize, bool) {
let bytes: &mut [u8] = unsafe { dst.as_bytes_mut() };
let (result, read, written, replaced) = self.decode_to_utf8(src, bytes, last);
let len = bytes.len();
let mut trail = written;
// Non-UTF-8 ASCII-compatible decoders may write up to `MAX_STRIDE_SIZE`
// bytes of trailing garbage. No need to optimize non-ASCII-compatible
// encodings to avoid overwriting here.
if self.encoding != UTF_8 {
let max = std::cmp::min(len, trail + ascii::MAX_STRIDE_SIZE);
while trail < max {
bytes[trail] = 0;
trail += 1;
}
}
while trail < len && ((bytes[trail] & 0xC0) == 0x80) {
bytes[trail] = 0;
trail += 1;
}
(result, read, written, replaced)
}
/// Incrementally decode a byte stream into UTF-8 with malformed sequences
/// replaced with the REPLACEMENT CHARACTER using a `String` receiver.
///
/// Like the others, this method follows the logic that the output buffer is
/// caller-allocated. This method treats the capacity of the `String` as
/// the output limit. That is, this method guarantees not to cause a
/// reallocation of the backing buffer of `String`.
///
/// The return value is a tuple that contains the `DecoderResult`, the
/// number of bytes read and a boolean indicating whether replacements
/// were done. The number of bytes written is signaled via the length of
/// the `String` changing.
///
/// See the documentation of the struct for documentation for `decode_*`
/// methods collectively.
///
/// Available to Rust only.
pub fn decode_to_string(
&mut self,
src: &[u8],
dst: &mut String,
last: bool,
) -> (CoderResult, usize, bool) {
unsafe {
let vec = dst.as_mut_vec();
let old_len = vec.len();
let capacity = vec.capacity();
vec.set_len(capacity);
let (result, read, written, replaced) =
self.decode_to_utf8(src, &mut vec[old_len..], last);
vec.set_len(old_len + written);
(result, read, replaced)
}
}
public_decode_function!(/// Incrementally decode a byte stream into UTF-8
/// _without replacement_.
///
/// See the documentation of the struct for
/// documentation for `decode_*` methods
/// collectively.
///
/// Available via the C wrapper.
,
decode_to_utf8_without_replacement,
decode_to_utf8_raw,
decode_to_utf8_checking_end,
decode_to_utf8_after_one_potential_bom_byte,
decode_to_utf8_after_two_potential_bom_bytes,
decode_to_utf8_checking_end_with_offset,
u8);
/// Incrementally decode a byte stream into UTF-8 with type system signaling
/// of UTF-8 validity.
///
/// This methods calls `decode_to_utf8` and then zeroes out up to three
/// bytes that aren't logically part of the write in order to retain the
/// UTF-8 validity even for the unwritten part of the buffer.
///
/// See the documentation of the struct for documentation for `decode_*`
/// methods collectively.
///
/// Available to Rust only.
pub fn decode_to_str_without_replacement(
&mut self,
src: &[u8],
dst: &mut str,
last: bool,
) -> (DecoderResult, usize, usize) {
let bytes: &mut [u8] = unsafe { dst.as_bytes_mut() };
let (result, read, written) = self.decode_to_utf8_without_replacement(src, bytes, last);
let len = bytes.len();
let mut trail = written;
// Non-UTF-8 ASCII-compatible decoders may write up to `MAX_STRIDE_SIZE`
// bytes of trailing garbage. No need to optimize non-ASCII-compatible
// encodings to avoid overwriting here.
if self.encoding != UTF_8 {
let max = std::cmp::min(len, trail + ascii::MAX_STRIDE_SIZE);
while trail < max {
bytes[trail] = 0;
trail += 1;
}
}
while trail < len && ((bytes[trail] & 0xC0) == 0x80) {
bytes[trail] = 0;
trail += 1;
}
(result, read, written)
}
/// Incrementally decode a byte stream into UTF-8 using a `String` receiver.
///
/// Like the others, this method follows the logic that the output buffer is
/// caller-allocated. This method treats the capacity of the `String` as
/// the output limit. That is, this method guarantees not to cause a
/// reallocation of the backing buffer of `String`.
///
/// The return value is a pair that contains the `DecoderResult` and the
/// number of bytes read. The number of bytes written is signaled via
/// the length of the `String` changing.
///
/// See the documentation of the struct for documentation for `decode_*`
/// methods collectively.
///
/// Available to Rust only.
pub fn decode_to_string_without_replacement(
&mut self,
src: &[u8],
dst: &mut String,
last: bool,
) -> (DecoderResult, usize) {
unsafe {
let vec = dst.as_mut_vec();
let old_len = vec.len();
let capacity = vec.capacity();
vec.set_len(capacity);
let (result, read, written) =
self.decode_to_utf8_without_replacement(src, &mut vec[old_len..], last);
vec.set_len(old_len + written);
(result, read)
}
}
/// Query the worst-case UTF-16 output size (with or without replacement).
///
/// Returns the size of the output buffer in UTF-16 code units (`u16`)
/// that will not overflow given the current state of the decoder and
/// `byte_length` number of additional input bytes or `None` if `usize`
/// would overflow.
///
/// Since the REPLACEMENT CHARACTER fits into one UTF-16 code unit, the
/// return value of this method applies also in the
/// `_without_replacement` case.
///
/// Available via the C wrapper.
pub fn max_utf16_buffer_length(&self, byte_length: usize) -> Option<usize> {
// Need to consider a) the decoder morphing due to the BOM and b) a partial
// BOM getting pushed to the underlying decoder.
match self.life_cycle {
DecoderLifeCycle::Converting
| DecoderLifeCycle::AtUtf8Start
| DecoderLifeCycle::AtUtf16LeStart
| DecoderLifeCycle::AtUtf16BeStart => {
return self.variant.max_utf16_buffer_length(byte_length)
}
DecoderLifeCycle::AtStart => {
if let Some(utf8_bom) = byte_length.checked_add(1) {
if let Some(utf16_bom) =
checked_add(1, checked_div(byte_length.checked_add(1), 2))
{
let utf_bom = std::cmp::max(utf8_bom, utf16_bom);
let encoding = self.encoding();
if encoding == UTF_8 || encoding == UTF_16LE || encoding == UTF_16BE {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf_bom);
} else if let Some(non_bom) =
self.variant.max_utf16_buffer_length(byte_length)
{
return Some(std::cmp::max(utf_bom, non_bom));
}
}
}
}
DecoderLifeCycle::SeenUtf8First | DecoderLifeCycle::SeenUtf8Second => {
// Add two bytes even when only one byte has been seen,
// because the one byte can become a lead byte in multibyte
// decoders, but only after the decoder has been queried
// for max length, so the decoder's own logic for adding
// one for a pending lead cannot work.
if let Some(sum) = byte_length.checked_add(2) {
if let Some(utf8_bom) = sum.checked_add(1) {
if self.encoding() == UTF_8 {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf8_bom);
} else if let Some(non_bom) = self.variant.max_utf16_buffer_length(sum) {
return Some(std::cmp::max(utf8_bom, non_bom));
}
}
}
}
DecoderLifeCycle::ConvertingWithPendingBB => {
if let Some(sum) = byte_length.checked_add(2) {
return self.variant.max_utf16_buffer_length(sum);
}
}
DecoderLifeCycle::SeenUtf16LeFirst | DecoderLifeCycle::SeenUtf16BeFirst => {
// Add two bytes even when only one byte has been seen,
// because the one byte can become a lead byte in multibyte
// decoders, but only after the decoder has been queried
// for max length, so the decoder's own logic for adding
// one for a pending lead cannot work.
if let Some(sum) = byte_length.checked_add(2) {
if let Some(utf16_bom) = checked_add(1, checked_div(sum.checked_add(1), 2)) {
let encoding = self.encoding();
if encoding == UTF_16LE || encoding == UTF_16BE {
// No need to consider the internal state of the underlying decoder,
// because it is at start, because no data has reached it yet.
return Some(utf16_bom);
} else if let Some(non_bom) = self.variant.max_utf16_buffer_length(sum) {
return Some(std::cmp::max(utf16_bom, non_bom));
}
}
}
}
DecoderLifeCycle::Finished => panic!("Must not use a decoder that has finished."),
}
None
}
/// Incrementally decode a byte stream into UTF-16 with malformed sequences
/// replaced with the REPLACEMENT CHARACTER.
///
/// See the documentation of the struct for documentation for `decode_*`
/// methods collectively.
///
/// Available via the C wrapper.
pub fn decode_to_utf16(
&mut self,
src: &[u8],
dst: &mut [u16],
last: bool,
) -> (CoderResult, usize, usize, bool) {
let mut had_errors = false;
let mut total_read = 0usize;
let mut total_written = 0usize;
loop {
let (result, read, written) = self.decode_to_utf16_without_replacement(
&src[total_read..],
&mut dst[total_written..],
last,
);
total_read += read;
total_written += written;
match result {
DecoderResult::InputEmpty => {
return (
CoderResult::InputEmpty,
total_read,
total_written,
had_errors,
);
}
DecoderResult::OutputFull => {
return (
CoderResult::OutputFull,
total_read,
total_written,
had_errors,
);
}
DecoderResult::Malformed(_, _) => {
had_errors = true;
// There should always be space for the U+FFFD, because
// otherwise we'd have gotten OutputFull already.
dst[total_written] = 0xFFFD;
total_written += 1;
}
}
}
}
public_decode_function!(/// Incrementally decode a byte stream into UTF-16
/// _without replacement_.
///
/// See the documentation of the struct for
/// documentation for `decode_*` methods
/// collectively.
///
/// Available via the C wrapper.
,
decode_to_utf16_without_replacement,
decode_to_utf16_raw,
decode_to_utf16_checking_end,
decode_to_utf16_after_one_potential_bom_byte,
decode_to_utf16_after_two_potential_bom_bytes,
decode_to_utf16_checking_end_with_offset,
u16);
}
/// Result of a (potentially partial) encode operation without replacement.
#[must_use]
#[derive(Debug, PartialEq, Eq)]
pub enum EncoderResult {
/// The input was exhausted.
///
/// If this result was returned from a call where `last` was `true`, the
/// decoding process has completed. Otherwise, the caller should call a
/// decode method again with more input.
InputEmpty,
/// The encoder cannot produce another unit of output, because the output
/// buffer does not have enough space left.
///
/// The caller must provide more output space upon the next call and re-push
/// the remaining input to the decoder.
OutputFull,
/// The encoder encountered an unmappable character.
///
/// The caller must either treat this as a fatal error or must append
/// a placeholder to the output and then re-push the remaining input to the
/// encoder.
Unmappable(char),
}
impl EncoderResult {
fn unmappable_from_bmp(bmp: u16) -> EncoderResult {
EncoderResult::Unmappable(::std::char::from_u32(u32::from(bmp)).unwrap())
}
}
/// A converter that encodes a Unicode stream into bytes according to a
/// character encoding in a streaming (incremental) manner.
///
/// The various `encode_*` methods take an input buffer (`src`) and an output
/// buffer `dst` both of which are caller-allocated. There are variants for
/// both UTF-8 and UTF-16 input buffers.
///
/// An `encode_*` method encode characters from `src` into bytes characters
/// stored into `dst` until one of the following three things happens:
///
/// 1. An unmappable character is encountered (`*_without_replacement` variants
/// only).
///
/// 2. The output buffer has been filled so near capacity that the decoder
/// cannot be sure that processing an additional character of input wouldn't
/// cause so much output that the output buffer would overflow.
///
/// 3. All the input characters have been processed.
///
/// The `encode_*` method then returns tuple of a status indicating which one
/// of the three reasons to return happened, how many input code units (`u8`
/// when encoding from UTF-8 and `u16` when encoding from UTF-16) were read,
/// how many output bytes were written (except when encoding into `Vec<u8>`,
/// whose length change indicates this), and in the case of the variants that
/// perform replacement, a boolean indicating whether an unmappable
/// character was replaced with a numeric character reference during the call.
///
/// The number of bytes "written" is what's logically written. Garbage may be
/// written in the output buffer beyond the point logically written to.
///
/// In the case of the methods whose name ends with
/// `*_without_replacement`, the status is an [`EncoderResult`][1] enumeration
/// (possibilities `Unmappable`, `OutputFull` and `InputEmpty` corresponding to
/// the three cases listed above).
///
/// In the case of methods whose name does not end with
/// `*_without_replacement`, unmappable characters are automatically replaced
/// with the corresponding numeric character references and unmappable
/// characters do not cause the methods to return early.
///
/// When encoding from UTF-8 without replacement, the methods are guaranteed
/// not to return indicating that more output space is needed if the length
/// of the output buffer is at least the length returned by
/// [`max_buffer_length_from_utf8_without_replacement()`][2]. When encoding from
/// UTF-8 with replacement, the length of the output buffer that guarantees the
/// methods not to return indicating that more output space is needed in the
/// absence of unmappable characters is given by
/// [`max_buffer_length_from_utf8_if_no_unmappables()`][3]. When encoding from
/// UTF-16 without replacement, the methods are guaranteed not to return
/// indicating that more output space is needed if the length of the output
/// buffer is at least the length returned by
/// [`max_buffer_length_from_utf16_without_replacement()`][4]. When encoding
/// from UTF-16 with replacement, the the length of the output buffer that
/// guarantees the methods not to return indicating that more output space is
/// needed in the absence of unmappable characters is given by
/// [`max_buffer_length_from_utf16_if_no_unmappables()`][5].
/// When encoding with replacement, applications are not expected to size the
/// buffer for the worst case ahead of time but to resize the buffer if there
/// are unmappable characters. This is why max length queries are only available
/// for the case where there are no unmappable characters.
///
/// When encoding from UTF-8, each `src` buffer _must_ be valid UTF-8. (When
/// calling from Rust, the type system takes care of this.) When encoding from
/// UTF-16, unpaired surrogates in the input are treated as U+FFFD REPLACEMENT
/// CHARACTERS. Therefore, in order for astral characters not to turn into a
/// pair of REPLACEMENT CHARACTERS, the caller must ensure that surrogate pairs
/// are not split across input buffer boundaries.
///
/// After an `encode_*` call returns, the output produced so far, taken as a
/// whole from the start of the stream, is guaranteed to consist of a valid
/// byte sequence in the target encoding. (I.e. the code unit sequence for a
/// character is guaranteed not to be split across output buffers. However, due
/// to the stateful nature of ISO-2022-JP, the stream needs to be considered
/// from the start for it to be valid. For other encodings, the validity holds
/// on a per-output buffer basis.)
///
/// The boolean argument `last` indicates that the end of the stream is reached
/// when all the characters in `src` have been consumed. This argument is needed
/// for ISO-2022-JP and is ignored for other encodings.
///
/// An `Encoder` object can be used to incrementally encode a byte stream.
///
/// During the processing of a single stream, the caller must call `encode_*`
/// zero or more times with `last` set to `false` and then call `encode_*` at
/// least once with `last` set to `true`. If `encode_*` returns `InputEmpty`,
/// the processing of the stream has ended. Otherwise, the caller must call
/// `encode_*` again with `last` set to `true` (or treat an `Unmappable` result
/// as a fatal error).
///
/// Once the stream has ended, the `Encoder` object must not be used anymore.
/// That is, you need to create another one to process another stream.
///
/// When the encoder returns `OutputFull` or the encoder returns `Unmappable`
/// and the caller does not wish to treat it as a fatal error, the input buffer
/// `src` may not have been completely consumed. In that case, the caller must
/// pass the unconsumed contents of `src` to `encode_*` again upon the next
/// call.
///
/// [1]: enum.EncoderResult.html
/// [2]: #method.max_buffer_length_from_utf8_without_replacement
/// [3]: #method.max_buffer_length_from_utf8_if_no_unmappables
/// [4]: #method.max_buffer_length_from_utf16_without_replacement
/// [5]: #method.max_buffer_length_from_utf16_if_no_unmappables
///
/// # Infinite loops
///
/// When converting with a fixed-size output buffer whose size is too small to
/// accommodate one character of output, an infinite loop ensues. When
/// converting with a fixed-size output buffer, it generally makes sense to
/// make the buffer fairly large (e.g. couple of kilobytes).
pub struct Encoder {
encoding: &'static Encoding,
variant: VariantEncoder,
}
impl Encoder {
fn new(enc: &'static Encoding, encoder: VariantEncoder) -> Encoder {
Encoder {
encoding: enc,
variant: encoder,
}
}
/// The `Encoding` this `Encoder` is for.
#[inline]
pub fn encoding(&self) -> &'static Encoding {
self.encoding
}
/// Returns `true` if this is an ISO-2022-JP encoder that's not in the
/// ASCII state and `false` otherwise.
#[inline]
pub fn has_pending_state(&self) -> bool {
self.variant.has_pending_state()
}
/// Query the worst-case output size when encoding from UTF-8 with
/// replacement.
///
/// Returns the size of the output buffer in bytes that will not overflow
/// given the current state of the encoder and `byte_length` number of
/// additional input code units if there are no unmappable characters in
/// the input or `None` if `usize` would overflow.
///
/// Available via the C wrapper.
pub fn max_buffer_length_from_utf8_if_no_unmappables(
&self,
byte_length: usize,
) -> Option<usize> {
checked_add(
if self.encoding().can_encode_everything() {
0
} else {
NCR_EXTRA
},
self.max_buffer_length_from_utf8_without_replacement(byte_length),
)
}
/// Query the worst-case output size when encoding from UTF-8 without
/// replacement.
///
/// Returns the size of the output buffer in bytes that will not overflow
/// given the current state of the encoder and `byte_length` number of
/// additional input code units or `None` if `usize` would overflow.
///
/// Available via the C wrapper.
pub fn max_buffer_length_from_utf8_without_replacement(
&self,
byte_length: usize,
) -> Option<usize> {
self.variant
.max_buffer_length_from_utf8_without_replacement(byte_length)
}
/// Incrementally encode into byte stream from UTF-8 with unmappable
/// characters replaced with HTML (decimal) numeric character references.
///
/// See the documentation of the struct for documentation for `encode_*`
/// methods collectively.
///
/// Available via the C wrapper.
pub fn encode_from_utf8(
&mut self,
src: &str,
dst: &mut [u8],
last: bool,
) -> (CoderResult, usize, usize, bool) {
let dst_len = dst.len();
let effective_dst_len = if self.encoding().can_encode_everything() {
dst_len
} else {
if dst_len < NCR_EXTRA {
if src.is_empty() && !(last && self.has_pending_state()) {
return (CoderResult::InputEmpty, 0, 0, false);
}
return (CoderResult::OutputFull, 0, 0, false);
}
dst_len - NCR_EXTRA
};
let mut had_unmappables = false;
let mut total_read = 0usize;
let mut total_written = 0usize;
loop {
let (result, read, written) = self.encode_from_utf8_without_replacement(
&src[total_read..],
&mut dst[total_written..effective_dst_len],
last,
);
total_read += read;
total_written += written;
match result {
EncoderResult::InputEmpty => {
return (
CoderResult::InputEmpty,
total_read,
total_written,
had_unmappables,
);
}
EncoderResult::OutputFull => {
return (
CoderResult::OutputFull,
total_read,
total_written,
had_unmappables,
);
}
EncoderResult::Unmappable(unmappable) => {
had_unmappables = true;
debug_assert!(dst.len() - total_written >= NCR_EXTRA);
debug_assert_ne!(self.encoding(), UTF_16BE);
debug_assert_ne!(self.encoding(), UTF_16LE);
// Additionally, Iso2022JpEncoder is responsible for
// transitioning to ASCII when returning with Unmappable.
total_written += write_ncr(unmappable, &mut dst[total_written..]);
if total_written >= effective_dst_len {
if total_read == src.len() && !(last && self.has_pending_state()) {
return (
CoderResult::InputEmpty,
total_read,
total_written,
had_unmappables,
);
}
return (
CoderResult::OutputFull,
total_read,
total_written,
had_unmappables,
);
}
}
}
}
}
/// Incrementally encode into byte stream from UTF-8 with unmappable
/// characters replaced with HTML (decimal) numeric character references.
///
/// See the documentation of the struct for documentation for `encode_*`
/// methods collectively.
///
/// Available to Rust only.
pub fn encode_from_utf8_to_vec(
&mut self,
src: &str,
dst: &mut Vec<u8>,
last: bool,
) -> (CoderResult, usize, bool) {
unsafe {
let old_len = dst.len();
let capacity = dst.capacity();
dst.set_len(capacity);
let (result, read, written, replaced) =
self.encode_from_utf8(src, &mut dst[old_len..], last);
dst.set_len(old_len + written);
(result, read, replaced)
}
}
/// Incrementally encode into byte stream from UTF-8 _without replacement_.
///
/// See the documentation of the struct for documentation for `encode_*`
/// methods collectively.
///
/// Available via the C wrapper.
pub fn encode_from_utf8_without_replacement(
&mut self,
src: &str,
dst: &mut [u8],
last: bool,
) -> (EncoderResult, usize, usize) {
self.variant.encode_from_utf8_raw(src, dst, last)
}
/// Incrementally encode into byte stream from UTF-8 _without replacement_.
///
/// See the documentation of the struct for documentation for `encode_*`
/// methods collectively.
///
/// Available to Rust only.
pub fn encode_from_utf8_to_vec_without_replacement(
&mut self,
src: &str,
dst: &mut Vec<u8>,
last: bool,
) -> (EncoderResult, usize) {
unsafe {
let old_len = dst.len();
let capacity = dst.capacity();
dst.set_len(capacity);
let (result, read, written) =
self.encode_from_utf8_without_replacement(src, &mut dst[old_len..], last);
dst.set_len(old_len + written);
(result, read)
}
}
/// Query the worst-case output size when encoding from UTF-16 with
/// replacement.
///
/// Returns the size of the output buffer in bytes that will not overflow
/// given the current state of the encoder and `u16_length` number of
/// additional input code units if there are no unmappable characters in
/// the input or `None` if `usize` would overflow.
///
/// Available via the C wrapper.
pub fn max_buffer_length_from_utf16_if_no_unmappables(
&self,
u16_length: usize,
) -> Option<usize> {
checked_add(
if self.encoding().can_encode_everything() {
0
} else {
NCR_EXTRA
},
self.max_buffer_length_from_utf16_without_replacement(u16_length),
)
}
/// Query the worst-case output size when encoding from UTF-16 without
/// replacement.
///
/// Returns the size of the output buffer in bytes that will not overflow
/// given the current state of the encoder and `u16_length` number of
/// additional input code units or `None` if `usize` would overflow.
///
/// Available via the C wrapper.
pub fn max_buffer_length_from_utf16_without_replacement(
&self,
u16_length: usize,
) -> Option<usize> {
self.variant
.max_buffer_length_from_utf16_without_replacement(u16_length)
}
/// Incrementally encode into byte stream from UTF-16 with unmappable
/// characters replaced with HTML (decimal) numeric character references.
///
/// See the documentation of the struct for documentation for `encode_*`
/// methods collectively.
///
/// Available via the C wrapper.
pub fn encode_from_utf16(
&mut self,
src: &[u16],
dst: &mut [u8],
last: bool,
) -> (CoderResult, usize, usize, bool) {
let dst_len = dst.len();
let effective_dst_len = if self.encoding().can_encode_everything() {
dst_len
} else {
if dst_len < NCR_EXTRA {
if src.is_empty() && !(last && self.has_pending_state()) {
return (CoderResult::InputEmpty, 0, 0, false);
}
return (CoderResult::OutputFull, 0, 0, false);
}
dst_len - NCR_EXTRA
};
let mut had_unmappables = false;
let mut total_read = 0usize;
let mut total_written = 0usize;
loop {
let (result, read, written) = self.encode_from_utf16_without_replacement(
&src[total_read..],
&mut dst[total_written..effective_dst_len],
last,
);
total_read += read;
total_written += written;
match result {
EncoderResult::InputEmpty => {
return (
CoderResult::InputEmpty,
total_read,
total_written,
had_unmappables,
);
}
EncoderResult::OutputFull => {
return (
CoderResult::OutputFull,
total_read,
total_written,
had_unmappables,
);
}
EncoderResult::Unmappable(unmappable) => {
had_unmappables = true;
debug_assert!(dst.len() - total_written >= NCR_EXTRA);
// There are no UTF-16 encoders and even if there were,
// they'd never have unmappables.
debug_assert_ne!(self.encoding(), UTF_16BE);
debug_assert_ne!(self.encoding(), UTF_16LE);
// Additionally, Iso2022JpEncoder is responsible for
// transitioning to ASCII when returning with Unmappable
// from the jis0208 state. That is, when we encode
// ISO-2022-JP and come here, the encoder is in either the
// ASCII or the Roman state. We are allowed to generate any
// printable ASCII excluding \ and ~.
total_written += write_ncr(unmappable, &mut dst[total_written..]);
if total_written >= effective_dst_len {
if total_read == src.len() && !(last && self.has_pending_state()) {
return (
CoderResult::InputEmpty,
total_read,
total_written,
had_unmappables,
);
}
return (
CoderResult::OutputFull,
total_read,
total_written,
had_unmappables,
);
}
}
}
}
}
/// Incrementally encode into byte stream from UTF-16 _without replacement_.
///
/// See the documentation of the struct for documentation for `encode_*`
/// methods collectively.
///
/// Available via the C wrapper.
pub fn encode_from_utf16_without_replacement(
&mut self,
src: &[u16],
dst: &mut [u8],
last: bool,
) -> (EncoderResult, usize, usize) {
self.variant.encode_from_utf16_raw(src, dst, last)
}
}
/// Format an unmappable as NCR without heap allocation.
fn write_ncr(unmappable: char, dst: &mut [u8]) -> usize {
// len is the number of decimal digits needed to represent unmappable plus
// 3 (the length of "&#" and ";").
let mut number = unmappable as u32;
let len = if number >= 1_000_000u32 {
10usize
} else if number >= 100_000u32 {
9usize
} else if number >= 10_000u32 {
8usize
} else if number >= 1_000u32 {
7usize
} else if number >= 100u32 {
6usize
} else {
// Review the outcome of https://github.com/whatwg/encoding/issues/15
// to see if this case is possible
5usize
};
debug_assert!(number >= 10u32);
debug_assert!(len <= dst.len());
let mut pos = len - 1;
dst[pos] = b';';
pos -= 1;
loop {
let rightmost = number % 10;
dst[pos] = rightmost as u8 + b'0';
pos -= 1;
if number < 10 {
break;
}
number /= 10;
}
dst[1] = b'#';
dst[0] = b'&';
len
}
#[inline(always)]
fn in_range16(i: u16, start: u16, end: u16) -> bool {
i.wrapping_sub(start) < (end - start)
}
#[inline(always)]
fn in_range32(i: u32, start: u32, end: u32) -> bool {
i.wrapping_sub(start) < (end - start)
}
#[inline(always)]
fn in_inclusive_range8(i: u8, start: u8, end: u8) -> bool {
i.wrapping_sub(start) <= (end - start)
}
#[inline(always)]
fn in_inclusive_range16(i: u16, start: u16, end: u16) -> bool {
i.wrapping_sub(start) <= (end - start)
}
#[inline(always)]
fn in_inclusive_range32(i: u32, start: u32, end: u32) -> bool {
i.wrapping_sub(start) <= (end - start)
}
#[inline(always)]
fn in_inclusive_range(i: usize, start: usize, end: usize) -> bool {
i.wrapping_sub(start) <= (end - start)
}
#[inline(always)]
fn checked_add(num: usize, opt: Option<usize>) -> Option<usize> {
if let Some(n) = opt {
n.checked_add(num)
} else {
None
}
}
#[inline(always)]
fn checked_add_opt(one: Option<usize>, other: Option<usize>) -> Option<usize> {
if let Some(n) = one {
checked_add(n, other)
} else {
None
}
}
#[inline(always)]
fn checked_mul(num: usize, opt: Option<usize>) -> Option<usize> {
if let Some(n) = opt {
n.checked_mul(num)
} else {
None
}
}
#[inline(always)]
fn checked_div(opt: Option<usize>, num: usize) -> Option<usize> {
if let Some(n) = opt {
n.checked_div(num)
} else {
None
}
}
#[inline(always)]
fn checked_next_power_of_two(opt: Option<usize>) -> Option<usize> {
opt.map(|n| n.next_power_of_two())
}
#[inline(always)]
fn checked_min(one: Option<usize>, other: Option<usize>) -> Option<usize> {
if let Some(a) = one {
if let Some(b) = other {
Some(::std::cmp::min(a, b))
} else {
Some(a)
}
} else {
other
}
}
// ############## TESTS ###############
#[cfg(all(test, feature = "serde"))]
#[derive(Serialize, Deserialize, Debug, PartialEq)]
struct Demo {
num: u32,
name: String,
enc: &'static Encoding,
}
#[cfg(test)]
mod test_labels_names;
#[cfg(test)]
mod tests {
use super::*;
use std::borrow::Cow;
fn sniff_to_utf16(
initial_encoding: &'static Encoding,
expected_encoding: &'static Encoding,
bytes: &[u8],
expect: &[u16],
breaks: &[usize],
) {
let mut decoder = initial_encoding.new_decoder();
let mut dest: Vec<u16> =
Vec::with_capacity(decoder.max_utf16_buffer_length(bytes.len()).unwrap());
let capacity = dest.capacity();
dest.resize(capacity, 0u16);
let mut total_written = 0usize;
let mut start = 0usize;
for br in breaks {
let (result, read, written, _) =
decoder.decode_to_utf16(&bytes[start..*br], &mut dest[total_written..], false);
total_written += written;
assert_eq!(read, *br - start);
match result {
CoderResult::InputEmpty => {}
CoderResult::OutputFull => {
unreachable!();
}
}
start = *br;
}
let (result, read, written, _) =
decoder.decode_to_utf16(&bytes[start..], &mut dest[total_written..], true);
total_written += written;
match result {
CoderResult::InputEmpty => {}
CoderResult::OutputFull => {
unreachable!();
}
}
assert_eq!(read, bytes.len() - start);
assert_eq!(total_written, expect.len());
assert_eq!(&dest[..total_written], expect);
assert_eq!(decoder.encoding(), expected_encoding);
}
// Any copyright to the test code below this comment is dedicated to the
// Public Domain. http://creativecommons.org/publicdomain/zero/1.0/
#[test]
fn test_bom_sniffing() {
// ASCII
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\x61\x62",
&[0x0061u16, 0x0062u16],
&[],
);
// UTF-8
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[1],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[2],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[3],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[4],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[2, 3],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[1, 2],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[1, 3],
);
sniff_to_utf16(
WINDOWS_1252,
UTF_8,
b"\xEF\xBB\xBF\x61\x62",
&[0x0061u16, 0x0062u16],
&[1, 2, 3, 4],
);
sniff_to_utf16(WINDOWS_1252, UTF_8, b"\xEF\xBB\xBF", &[], &[]);
// Not UTF-8
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xEF\xBB\x61\x62",
&[0x00EFu16, 0x00BBu16, 0x0061u16, 0x0062u16],
&[],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xEF\xBB\x61\x62",
&[0x00EFu16, 0x00BBu16, 0x0061u16, 0x0062u16],
&[1],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xEF\x61\x62",
&[0x00EFu16, 0x0061u16, 0x0062u16],
&[],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xEF\x61\x62",
&[0x00EFu16, 0x0061u16, 0x0062u16],
&[1],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xEF\xBB",
&[0x00EFu16, 0x00BBu16],
&[],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xEF\xBB",
&[0x00EFu16, 0x00BBu16],
&[1],
);
sniff_to_utf16(WINDOWS_1252, WINDOWS_1252, b"\xEF", &[0x00EFu16], &[]);
// Not UTF-16
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xFE\x61\x62",
&[0x00FEu16, 0x0061u16, 0x0062u16],
&[],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xFE\x61\x62",
&[0x00FEu16, 0x0061u16, 0x0062u16],
&[1],
);
sniff_to_utf16(WINDOWS_1252, WINDOWS_1252, b"\xFE", &[0x00FEu16], &[]);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xFF\x61\x62",
&[0x00FFu16, 0x0061u16, 0x0062u16],
&[],
);
sniff_to_utf16(
WINDOWS_1252,
WINDOWS_1252,
b"\xFF\x61\x62",
&[0x00FFu16, 0x0061u16, 0x0062u16],
&[1],
);
sniff_to_utf16(WINDOWS_1252, WINDOWS_1252, b"\xFF", &[0x00FFu16], &[]);
// UTF-16
sniff_to_utf16(WINDOWS_1252, UTF_16BE, b"\xFE\xFF", &[], &[]);
sniff_to_utf16(WINDOWS_1252, UTF_16BE, b"\xFE\xFF", &[], &[1]);
sniff_to_utf16(WINDOWS_1252, UTF_16LE, b"\xFF\xFE", &[], &[]);
sniff_to_utf16(WINDOWS_1252, UTF_16LE, b"\xFF\xFE", &[], &[1]);
}
#[test]
fn test_output_encoding() {
assert_eq!(REPLACEMENT.output_encoding(), UTF_8);
assert_eq!(UTF_16BE.output_encoding(), UTF_8);
assert_eq!(UTF_16LE.output_encoding(), UTF_8);
assert_eq!(UTF_8.output_encoding(), UTF_8);
assert_eq!(WINDOWS_1252.output_encoding(), WINDOWS_1252);
assert_eq!(REPLACEMENT.new_encoder().encoding(), UTF_8);
assert_eq!(UTF_16BE.new_encoder().encoding(), UTF_8);
assert_eq!(UTF_16LE.new_encoder().encoding(), UTF_8);
assert_eq!(UTF_8.new_encoder().encoding(), UTF_8);
assert_eq!(WINDOWS_1252.new_encoder().encoding(), WINDOWS_1252);
}
#[test]
fn test_label_resolution() {
assert_eq!(Encoding::for_label(b"utf-8"), Some(UTF_8));
assert_eq!(Encoding::for_label(b"UTF-8"), Some(UTF_8));
assert_eq!(
Encoding::for_label(b" \t \n \x0C \n utf-8 \r \n \t \x0C "),
Some(UTF_8)
);
assert_eq!(Encoding::for_label(b"utf-8 _"), None);
assert_eq!(Encoding::for_label(b"bogus"), None);
assert_eq!(Encoding::for_label(b"bogusbogusbogusbogus"), None);
}
#[test]
fn test_decode_valid_windows_1257_to_cow() {
let (cow, encoding, had_errors) = WINDOWS_1257.decode(b"abc\x80\xE4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{00E4}");
}
}
assert_eq!(encoding, WINDOWS_1257);
assert!(!had_errors);
}
#[test]
fn test_decode_invalid_windows_1257_to_cow() {
let (cow, encoding, had_errors) = WINDOWS_1257.decode(b"abc\x80\xA1\xE4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{FFFD}\u{00E4}");
}
}
assert_eq!(encoding, WINDOWS_1257);
assert!(had_errors);
}
#[test]
fn test_decode_ascii_only_windows_1257_to_cow() {
let (cow, encoding, had_errors) = WINDOWS_1257.decode(b"abc");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "abc");
}
Cow::Owned(_) => unreachable!(),
}
assert_eq!(encoding, WINDOWS_1257);
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_valid_utf8_as_windows_1257_to_cow() {
let (cow, encoding, had_errors) = WINDOWS_1257.decode(b"\xEF\xBB\xBF\xE2\x82\xAC\xC3\xA4");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "\u{20AC}\u{00E4}");
}
Cow::Owned(_) => unreachable!(),
}
assert_eq!(encoding, UTF_8);
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_invalid_utf8_as_windows_1257_to_cow() {
let (cow, encoding, had_errors) =
WINDOWS_1257.decode(b"\xEF\xBB\xBF\xE2\x82\xAC\x80\xC3\xA4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "\u{20AC}\u{FFFD}\u{00E4}");
}
}
assert_eq!(encoding, UTF_8);
assert!(had_errors);
}
#[test]
fn test_decode_bomful_valid_utf8_as_utf_8_to_cow() {
let (cow, encoding, had_errors) = UTF_8.decode(b"\xEF\xBB\xBF\xE2\x82\xAC\xC3\xA4");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "\u{20AC}\u{00E4}");
}
Cow::Owned(_) => unreachable!(),
}
assert_eq!(encoding, UTF_8);
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_invalid_utf8_as_utf_8_to_cow() {
let (cow, encoding, had_errors) = UTF_8.decode(b"\xEF\xBB\xBF\xE2\x82\xAC\x80\xC3\xA4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "\u{20AC}\u{FFFD}\u{00E4}");
}
}
assert_eq!(encoding, UTF_8);
assert!(had_errors);
}
#[test]
fn test_decode_bomful_valid_utf8_as_utf_8_to_cow_with_bom_removal() {
let (cow, had_errors) = UTF_8.decode_with_bom_removal(b"\xEF\xBB\xBF\xE2\x82\xAC\xC3\xA4");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "\u{20AC}\u{00E4}");
}
Cow::Owned(_) => unreachable!(),
}
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_valid_utf8_as_windows_1257_to_cow_with_bom_removal() {
let (cow, had_errors) =
WINDOWS_1257.decode_with_bom_removal(b"\xEF\xBB\xBF\xE2\x82\xAC\xC3\xA4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(
s,
"\u{013C}\u{00BB}\u{00E6}\u{0101}\u{201A}\u{00AC}\u{0106}\u{00A4}"
);
}
}
assert!(!had_errors);
}
#[test]
fn test_decode_valid_windows_1257_to_cow_with_bom_removal() {
let (cow, had_errors) = WINDOWS_1257.decode_with_bom_removal(b"abc\x80\xE4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{00E4}");
}
}
assert!(!had_errors);
}
#[test]
fn test_decode_invalid_windows_1257_to_cow_with_bom_removal() {
let (cow, had_errors) = WINDOWS_1257.decode_with_bom_removal(b"abc\x80\xA1\xE4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{FFFD}\u{00E4}");
}
}
assert!(had_errors);
}
#[test]
fn test_decode_ascii_only_windows_1257_to_cow_with_bom_removal() {
let (cow, had_errors) = WINDOWS_1257.decode_with_bom_removal(b"abc");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "abc");
}
Cow::Owned(_) => unreachable!(),
}
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_valid_utf8_to_cow_without_bom_handling() {
let (cow, had_errors) =
UTF_8.decode_without_bom_handling(b"\xEF\xBB\xBF\xE2\x82\xAC\xC3\xA4");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "\u{FEFF}\u{20AC}\u{00E4}");
}
Cow::Owned(_) => unreachable!(),
}
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_invalid_utf8_to_cow_without_bom_handling() {
let (cow, had_errors) =
UTF_8.decode_without_bom_handling(b"\xEF\xBB\xBF\xE2\x82\xAC\x80\xC3\xA4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "\u{FEFF}\u{20AC}\u{FFFD}\u{00E4}");
}
}
assert!(had_errors);
}
#[test]
fn test_decode_valid_windows_1257_to_cow_without_bom_handling() {
let (cow, had_errors) = WINDOWS_1257.decode_without_bom_handling(b"abc\x80\xE4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{00E4}");
}
}
assert!(!had_errors);
}
#[test]
fn test_decode_invalid_windows_1257_to_cow_without_bom_handling() {
let (cow, had_errors) = WINDOWS_1257.decode_without_bom_handling(b"abc\x80\xA1\xE4");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{FFFD}\u{00E4}");
}
}
assert!(had_errors);
}
#[test]
fn test_decode_ascii_only_windows_1257_to_cow_without_bom_handling() {
let (cow, had_errors) = WINDOWS_1257.decode_without_bom_handling(b"abc");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "abc");
}
Cow::Owned(_) => unreachable!(),
}
assert!(!had_errors);
}
#[test]
fn test_decode_bomful_valid_utf8_to_cow_without_bom_handling_and_without_replacement() {
match UTF_8.decode_without_bom_handling_and_without_replacement(
b"\xEF\xBB\xBF\xE2\x82\xAC\xC3\xA4",
) {
Some(cow) => match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "\u{FEFF}\u{20AC}\u{00E4}");
}
Cow::Owned(_) => unreachable!(),
},
None => unreachable!(),
}
}
#[test]
fn test_decode_bomful_invalid_utf8_to_cow_without_bom_handling_and_without_replacement() {
assert!(
UTF_8
.decode_without_bom_handling_and_without_replacement(
b"\xEF\xBB\xBF\xE2\x82\xAC\x80\xC3\xA4"
)
.is_none()
);
}
#[test]
fn test_decode_valid_windows_1257_to_cow_without_bom_handling_and_without_replacement() {
match WINDOWS_1257.decode_without_bom_handling_and_without_replacement(b"abc\x80\xE4") {
Some(cow) => match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, "abc\u{20AC}\u{00E4}");
}
},
None => unreachable!(),
}
}
#[test]
fn test_decode_invalid_windows_1257_to_cow_without_bom_handling_and_without_replacement() {
assert!(
WINDOWS_1257
.decode_without_bom_handling_and_without_replacement(b"abc\x80\xA1\xE4")
.is_none()
);
}
#[test]
fn test_decode_ascii_only_windows_1257_to_cow_without_bom_handling_and_without_replacement() {
match WINDOWS_1257.decode_without_bom_handling_and_without_replacement(b"abc") {
Some(cow) => match cow {
Cow::Borrowed(s) => {
assert_eq!(s, "abc");
}
Cow::Owned(_) => unreachable!(),
},
None => unreachable!(),
}
}
#[test]
fn test_encode_ascii_only_windows_1257_to_cow() {
let (cow, encoding, had_errors) = WINDOWS_1257.encode("abc");
match cow {
Cow::Borrowed(s) => {
assert_eq!(s, b"abc");
}
Cow::Owned(_) => unreachable!(),
}
assert_eq!(encoding, WINDOWS_1257);
assert!(!had_errors);
}
#[test]
fn test_encode_valid_windows_1257_to_cow() {
let (cow, encoding, had_errors) = WINDOWS_1257.encode("abc\u{20AC}\u{00E4}");
match cow {
Cow::Borrowed(_) => unreachable!(),
Cow::Owned(s) => {
assert_eq!(s, b"abc\x80\xE4");
}
}
assert_eq!(encoding, WINDOWS_1257);
assert!(!had_errors);
}
#[test]
fn test_utf16_space_with_one_bom_byte() {
let mut decoder = UTF_16LE.new_decoder();
let mut dst = [0u16; 12];
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF", &mut dst[..needed], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF", &mut dst[..needed], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_utf8_space_with_one_bom_byte() {
let mut decoder = UTF_8.new_decoder();
let mut dst = [0u16; 12];
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF", &mut dst[..needed], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF", &mut dst[..needed], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_utf16_space_with_two_bom_bytes() {
let mut decoder = UTF_16LE.new_decoder();
let mut dst = [0u16; 12];
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xEF", &mut dst[..needed], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xBB", &mut dst[..needed], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF", &mut dst[..needed], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_utf8_space_with_two_bom_bytes() {
let mut decoder = UTF_8.new_decoder();
let mut dst = [0u16; 12];
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xEF", &mut dst[..needed], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xBB", &mut dst[..needed], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let needed = decoder.max_utf16_buffer_length(1).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF", &mut dst[..needed], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_utf16_space_with_one_bom_byte_and_a_second_byte_in_same_call() {
let mut decoder = UTF_16LE.new_decoder();
let mut dst = [0u16; 12];
{
let needed = decoder.max_utf16_buffer_length(2).unwrap();
let (result, _, _, _) = decoder.decode_to_utf16(b"\xFF\xFF", &mut dst[..needed], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_too_short_buffer_with_iso_2022_jp_ascii_from_utf8() {
let mut dst = [0u8; 8];
let mut encoder = ISO_2022_JP.new_encoder();
{
let (result, _, _, _) = encoder.encode_from_utf8("", &mut dst[..], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let (result, _, _, _) = encoder.encode_from_utf8("", &mut dst[..], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_too_short_buffer_with_iso_2022_jp_roman_from_utf8() {
let mut dst = [0u8; 16];
let mut encoder = ISO_2022_JP.new_encoder();
{
let (result, _, _, _) = encoder.encode_from_utf8("\u{A5}", &mut dst[..], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let (result, _, _, _) = encoder.encode_from_utf8("", &mut dst[..8], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let (result, _, _, _) = encoder.encode_from_utf8("", &mut dst[..8], true);
assert_eq!(result, CoderResult::OutputFull);
}
}
#[test]
fn test_buffer_end_iso_2022_jp_from_utf8() {
let mut dst = [0u8; 18];
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf8("\u{A5}\u{1F4A9}", &mut dst[..], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) = encoder.encode_from_utf8("\u{A5}\u{1F4A9}", &mut dst[..], true);
assert_eq!(result, CoderResult::OutputFull);
}
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) = encoder.encode_from_utf8("\u{1F4A9}", &mut dst[..13], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) = encoder.encode_from_utf8("\u{1F4A9}", &mut dst[..13], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_too_short_buffer_with_iso_2022_jp_ascii_from_utf16() {
let mut dst = [0u8; 8];
let mut encoder = ISO_2022_JP.new_encoder();
{
let (result, _, _, _) = encoder.encode_from_utf16(&[0u16; 0], &mut dst[..], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let (result, _, _, _) = encoder.encode_from_utf16(&[0u16; 0], &mut dst[..], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_too_short_buffer_with_iso_2022_jp_roman_from_utf16() {
let mut dst = [0u8; 16];
let mut encoder = ISO_2022_JP.new_encoder();
{
let (result, _, _, _) = encoder.encode_from_utf16(&[0xA5u16], &mut dst[..], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let (result, _, _, _) = encoder.encode_from_utf16(&[0u16; 0], &mut dst[..8], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let (result, _, _, _) = encoder.encode_from_utf16(&[0u16; 0], &mut dst[..8], true);
assert_eq!(result, CoderResult::OutputFull);
}
}
#[test]
fn test_buffer_end_iso_2022_jp_from_utf16() {
let mut dst = [0u8; 18];
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf16(&[0xA5u16, 0xD83Du16, 0xDCA9u16], &mut dst[..], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf16(&[0xA5u16, 0xD83Du16, 0xDCA9u16], &mut dst[..], true);
assert_eq!(result, CoderResult::OutputFull);
}
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf16(&[0xD83Du16, 0xDCA9u16], &mut dst[..13], false);
assert_eq!(result, CoderResult::InputEmpty);
}
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf16(&[0xD83Du16, 0xDCA9u16], &mut dst[..13], true);
assert_eq!(result, CoderResult::InputEmpty);
}
}
#[test]
fn test_hash() {
let mut encodings = ::std::collections::HashSet::new();
encodings.insert(UTF_8);
encodings.insert(ISO_2022_JP);
assert!(encodings.contains(UTF_8));
assert!(encodings.contains(ISO_2022_JP));
assert!(!encodings.contains(WINDOWS_1252));
encodings.remove(ISO_2022_JP);
assert!(!encodings.contains(ISO_2022_JP));
}
#[test]
fn test_iso_2022_jp_ncr_extra_from_utf16() {
let mut dst = [0u8; 17];
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf16(&[0x3041u16, 0xFFFFu16], &mut dst[..], true);
assert_eq!(result, CoderResult::OutputFull);
}
}
#[test]
fn test_iso_2022_jp_ncr_extra_from_utf8() {
let mut dst = [0u8; 17];
{
let mut encoder = ISO_2022_JP.new_encoder();
let (result, _, _, _) =
encoder.encode_from_utf8("\u{3041}\u{FFFF}", &mut dst[..], true);
assert_eq!(result, CoderResult::OutputFull);
}
}
#[test]
fn test_max_length_with_bom_to_utf8() {
let mut output = [0u8; 20];
let mut decoder = REPLACEMENT.new_decoder();
let input = b"\xEF\xBB\xBFA";
{
let needed = decoder
.max_utf8_buffer_length_without_replacement(input.len())
.unwrap();
let (result, read, written) =
decoder.decode_to_utf8_without_replacement(input, &mut output[..needed], true);
assert_eq!(result, DecoderResult::InputEmpty);
assert_eq!(read, input.len());
assert_eq!(written, 1);
assert_eq!(output[0], 0x41);
}
}
#[cfg(feature = "serde")]
#[test]
fn test_serde() {
let demo = Demo {
num: 42,
name: "foo".into(),
enc: UTF_8,
};
let serialized = serde_json::to_string(&demo).unwrap();
let deserialized: Demo = serde_json::from_str(&serialized).unwrap();
assert_eq!(deserialized, demo);
let bincoded = bincode::serialize(&demo, bincode::Infinite).unwrap();
let debincoded: Demo = bincode::deserialize(&bincoded[..]).unwrap();
assert_eq!(debincoded, demo);
}
#[test]
fn test_is_single_byte() {
assert!(!BIG5.is_single_byte());
assert!(!EUC_JP.is_single_byte());
assert!(!EUC_KR.is_single_byte());
assert!(!GB18030.is_single_byte());
assert!(!GBK.is_single_byte());
assert!(!REPLACEMENT.is_single_byte());
assert!(!SHIFT_JIS.is_single_byte());
assert!(!UTF_8.is_single_byte());
assert!(!UTF_16BE.is_single_byte());
assert!(!UTF_16LE.is_single_byte());
assert!(!ISO_2022_JP.is_single_byte());
assert!(IBM866.is_single_byte());
assert!(ISO_8859_2.is_single_byte());
assert!(ISO_8859_3.is_single_byte());
assert!(ISO_8859_4.is_single_byte());
assert!(ISO_8859_5.is_single_byte());
assert!(ISO_8859_6.is_single_byte());
assert!(ISO_8859_7.is_single_byte());
assert!(ISO_8859_8.is_single_byte());
assert!(ISO_8859_10.is_single_byte());
assert!(ISO_8859_13.is_single_byte());
assert!(ISO_8859_14.is_single_byte());
assert!(ISO_8859_15.is_single_byte());
assert!(ISO_8859_16.is_single_byte());
assert!(ISO_8859_8_I.is_single_byte());
assert!(KOI8_R.is_single_byte());
assert!(KOI8_U.is_single_byte());
assert!(MACINTOSH.is_single_byte());
assert!(WINDOWS_874.is_single_byte());
assert!(WINDOWS_1250.is_single_byte());
assert!(WINDOWS_1251.is_single_byte());
assert!(WINDOWS_1252.is_single_byte());
assert!(WINDOWS_1253.is_single_byte());
assert!(WINDOWS_1254.is_single_byte());
assert!(WINDOWS_1255.is_single_byte());
assert!(WINDOWS_1256.is_single_byte());
assert!(WINDOWS_1257.is_single_byte());
assert!(WINDOWS_1258.is_single_byte());
assert!(X_MAC_CYRILLIC.is_single_byte());
assert!(X_USER_DEFINED.is_single_byte());
}
}