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
|
/*
An implementation of Text I/O as defined by PEP 3116 - "New I/O"
Classes defined here: TextIOBase, IncrementalNewlineDecoder, TextIOWrapper.
Written by Amaury Forgeot d'Arc and Antoine Pitrou
*/
#include "Python.h"
#include "pycore_call.h" // _PyObject_CallMethod()
#include "pycore_codecs.h" // _PyCodecInfo_GetIncrementalDecoder()
#include "pycore_fileutils.h" // _Py_GetLocaleEncoding()
#include "pycore_interp.h" // PyInterpreterState.fs_codec
#include "pycore_long.h" // _PyLong_GetZero()
#include "pycore_object.h" // _PyObject_GC_UNTRACK()
#include "pycore_pyerrors.h" // _PyErr_ChainExceptions1()
#include "pycore_pystate.h" // _PyInterpreterState_GET()
#include "pycore_weakref.h" // FT_CLEAR_WEAKREFS()
#include "_iomodule.h"
/*[clinic input]
module _io
class _io.IncrementalNewlineDecoder "nldecoder_object *" "clinic_state()->PyIncrementalNewlineDecoder_Type"
class _io.TextIOWrapper "textio *" "clinic_state()->TextIOWrapper_Type"
class _io._TextIOBase "PyObject *" "&PyTextIOBase_Type"
[clinic start generated code]*/
/*[clinic end generated code: output=da39a3ee5e6b4b0d input=8b7f24fa13bfdd7f]*/
typedef struct nldecoder_object nldecoder_object;
typedef struct textio textio;
#define clinic_state() (find_io_state_by_def(Py_TYPE(self)))
#include "clinic/textio.c.h"
#undef clinic_state
/* TextIOBase */
PyDoc_STRVAR(textiobase_doc,
"Base class for text I/O.\n"
"\n"
"This class provides a character and line based interface to stream\n"
"I/O. There is no readinto method because Python's character strings\n"
"are immutable.\n"
);
static PyObject *
_unsupported(_PyIO_State *state, const char *message)
{
PyErr_SetString(state->unsupported_operation, message);
return NULL;
}
/*[clinic input]
_io._TextIOBase.detach
cls: defining_class
/
Separate the underlying buffer from the TextIOBase and return it.
After the underlying buffer has been detached, the TextIO is in an unusable state.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_detach_impl(PyObject *self, PyTypeObject *cls)
/*[clinic end generated code: output=50915f40c609eaa4 input=987ca3640d0a3776]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "detach");
}
/*[clinic input]
_io._TextIOBase.read
cls: defining_class
size: int(unused=True) = -1
/
Read at most size characters from stream.
Read from underlying buffer until we have size characters or we hit EOF.
If size is negative or omitted, read until EOF.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_read_impl(PyObject *self, PyTypeObject *cls,
int Py_UNUSED(size))
/*[clinic end generated code: output=51a5178a309ce647 input=f5e37720f9fc563f]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "read");
}
/*[clinic input]
_io._TextIOBase.readline
cls: defining_class
size: int(unused=True) = -1
/
Read until newline or EOF.
Return an empty string if EOF is hit immediately.
If size is specified, at most size characters will be read.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_readline_impl(PyObject *self, PyTypeObject *cls,
int Py_UNUSED(size))
/*[clinic end generated code: output=3f47d7966d6d074e input=42eafec94107fa27]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "readline");
}
/*[clinic input]
_io._TextIOBase.write
cls: defining_class
s: str(unused=True)
/
Write string s to stream.
Return the number of characters written
(which is always equal to the length of the string).
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_write_impl(PyObject *self, PyTypeObject *cls,
const char *Py_UNUSED(s))
/*[clinic end generated code: output=18b28231460275de input=e9cabaa5f6732b07]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "write");
}
/*[clinic input]
@getter
_io._TextIOBase.encoding
Encoding of the text stream.
Subclasses should override.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_encoding_get_impl(PyObject *self)
/*[clinic end generated code: output=e0f5d8f548b92432 input=4736d7621dd38f43]*/
{
Py_RETURN_NONE;
}
/*[clinic input]
@getter
_io._TextIOBase.newlines
Line endings translated so far.
Only line endings translated during reading are considered.
Subclasses should override.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_newlines_get_impl(PyObject *self)
/*[clinic end generated code: output=46ec147fb9f00c2a input=a5b196d076af1164]*/
{
Py_RETURN_NONE;
}
/*[clinic input]
@getter
_io._TextIOBase.errors
The error setting of the decoder or encoder.
Subclasses should override.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_errors_get_impl(PyObject *self)
/*[clinic end generated code: output=c6623d6addcd087d input=974aa52d1db93a82]*/
{
Py_RETURN_NONE;
}
static PyMethodDef textiobase_methods[] = {
_IO__TEXTIOBASE_DETACH_METHODDEF
_IO__TEXTIOBASE_READ_METHODDEF
_IO__TEXTIOBASE_READLINE_METHODDEF
_IO__TEXTIOBASE_WRITE_METHODDEF
{NULL, NULL}
};
static PyGetSetDef textiobase_getset[] = {
_IO__TEXTIOBASE_ENCODING_GETSETDEF
_IO__TEXTIOBASE_NEWLINES_GETSETDEF
_IO__TEXTIOBASE_ERRORS_GETSETDEF
{NULL}
};
static PyType_Slot textiobase_slots[] = {
{Py_tp_doc, (void *)textiobase_doc},
{Py_tp_methods, textiobase_methods},
{Py_tp_getset, textiobase_getset},
{0, NULL},
};
/* Do not set Py_TPFLAGS_HAVE_GC so that tp_traverse and tp_clear are inherited */
PyType_Spec textiobase_spec = {
.name = "_io._TextIOBase",
.flags = (Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE |
Py_TPFLAGS_IMMUTABLETYPE),
.slots = textiobase_slots,
};
/* IncrementalNewlineDecoder */
struct nldecoder_object {
PyObject_HEAD
PyObject *decoder;
PyObject *errors;
unsigned int pendingcr: 1;
unsigned int translate: 1;
unsigned int seennl: 3;
};
/*[clinic input]
_io.IncrementalNewlineDecoder.__init__
decoder: object
translate: bool
errors: object(c_default="NULL") = "strict"
Codec used when reading a file in universal newlines mode.
It wraps another incremental decoder, translating \r\n and \r into \n.
It also records the types of newlines encountered. When used with
translate=False, it ensures that the newline sequence is returned in
one piece. When used with decoder=None, it expects unicode strings as
decode input and translates newlines without first invoking an external
decoder.
[clinic start generated code]*/
static int
_io_IncrementalNewlineDecoder___init___impl(nldecoder_object *self,
PyObject *decoder, int translate,
PyObject *errors)
/*[clinic end generated code: output=fbd04d443e764ec2 input=ed547aa257616b0e]*/
{
if (errors == NULL) {
errors = &_Py_ID(strict);
}
else {
errors = Py_NewRef(errors);
}
Py_XSETREF(self->errors, errors);
Py_XSETREF(self->decoder, Py_NewRef(decoder));
self->translate = translate ? 1 : 0;
self->seennl = 0;
self->pendingcr = 0;
return 0;
}
static int
incrementalnewlinedecoder_traverse(nldecoder_object *self, visitproc visit,
void *arg)
{
Py_VISIT(Py_TYPE(self));
Py_VISIT(self->decoder);
Py_VISIT(self->errors);
return 0;
}
static int
incrementalnewlinedecoder_clear(nldecoder_object *self)
{
Py_CLEAR(self->decoder);
Py_CLEAR(self->errors);
return 0;
}
static void
incrementalnewlinedecoder_dealloc(nldecoder_object *self)
{
PyTypeObject *tp = Py_TYPE(self);
_PyObject_GC_UNTRACK(self);
(void)incrementalnewlinedecoder_clear(self);
tp->tp_free((PyObject *)self);
Py_DECREF(tp);
}
static int
check_decoded(PyObject *decoded)
{
if (decoded == NULL)
return -1;
if (!PyUnicode_Check(decoded)) {
PyErr_Format(PyExc_TypeError,
"decoder should return a string result, not '%.200s'",
Py_TYPE(decoded)->tp_name);
Py_DECREF(decoded);
return -1;
}
return 0;
}
#define CHECK_INITIALIZED_DECODER(self) \
if (self->errors == NULL) { \
PyErr_SetString(PyExc_ValueError, \
"IncrementalNewlineDecoder.__init__() not called"); \
return NULL; \
}
#define SEEN_CR 1
#define SEEN_LF 2
#define SEEN_CRLF 4
#define SEEN_ALL (SEEN_CR | SEEN_LF | SEEN_CRLF)
PyObject *
_PyIncrementalNewlineDecoder_decode(PyObject *myself,
PyObject *input, int final)
{
PyObject *output;
Py_ssize_t output_len;
nldecoder_object *self = (nldecoder_object *) myself;
CHECK_INITIALIZED_DECODER(self);
/* decode input (with the eventual \r from a previous pass) */
if (self->decoder != Py_None) {
output = PyObject_CallMethodObjArgs(self->decoder,
&_Py_ID(decode), input, final ? Py_True : Py_False, NULL);
}
else {
output = Py_NewRef(input);
}
if (check_decoded(output) < 0)
return NULL;
output_len = PyUnicode_GET_LENGTH(output);
if (self->pendingcr && (final || output_len > 0)) {
/* Prefix output with CR */
int kind;
PyObject *modified;
char *out;
modified = PyUnicode_New(output_len + 1,
PyUnicode_MAX_CHAR_VALUE(output));
if (modified == NULL)
goto error;
kind = PyUnicode_KIND(modified);
out = PyUnicode_DATA(modified);
PyUnicode_WRITE(kind, out, 0, '\r');
memcpy(out + kind, PyUnicode_DATA(output), kind * output_len);
Py_SETREF(output, modified); /* output remains ready */
self->pendingcr = 0;
output_len++;
}
/* retain last \r even when not translating data:
* then readline() is sure to get \r\n in one pass
*/
if (!final) {
if (output_len > 0
&& PyUnicode_READ_CHAR(output, output_len - 1) == '\r')
{
PyObject *modified = PyUnicode_Substring(output, 0, output_len -1);
if (modified == NULL)
goto error;
Py_SETREF(output, modified);
self->pendingcr = 1;
}
}
/* Record which newlines are read and do newline translation if desired,
all in one pass. */
{
const void *in_str;
Py_ssize_t len;
int seennl = self->seennl;
int only_lf = 0;
int kind;
in_str = PyUnicode_DATA(output);
len = PyUnicode_GET_LENGTH(output);
kind = PyUnicode_KIND(output);
if (len == 0)
return output;
/* If, up to now, newlines are consistently \n, do a quick check
for the \r *byte* with the libc's optimized memchr.
*/
if (seennl == SEEN_LF || seennl == 0) {
only_lf = (memchr(in_str, '\r', kind * len) == NULL);
}
if (only_lf) {
/* If not already seen, quick scan for a possible "\n" character.
(there's nothing else to be done, even when in translation mode)
*/
if (seennl == 0 &&
memchr(in_str, '\n', kind * len) != NULL) {
if (kind == PyUnicode_1BYTE_KIND)
seennl |= SEEN_LF;
else {
Py_ssize_t i = 0;
for (;;) {
Py_UCS4 c;
/* Fast loop for non-control characters */
while (PyUnicode_READ(kind, in_str, i) > '\n')
i++;
c = PyUnicode_READ(kind, in_str, i++);
if (c == '\n') {
seennl |= SEEN_LF;
break;
}
if (i >= len)
break;
}
}
}
/* Finished: we have scanned for newlines, and none of them
need translating */
}
else if (!self->translate) {
Py_ssize_t i = 0;
/* We have already seen all newline types, no need to scan again */
if (seennl == SEEN_ALL)
goto endscan;
for (;;) {
Py_UCS4 c;
/* Fast loop for non-control characters */
while (PyUnicode_READ(kind, in_str, i) > '\r')
i++;
c = PyUnicode_READ(kind, in_str, i++);
if (c == '\n')
seennl |= SEEN_LF;
else if (c == '\r') {
if (PyUnicode_READ(kind, in_str, i) == '\n') {
seennl |= SEEN_CRLF;
i++;
}
else
seennl |= SEEN_CR;
}
if (i >= len)
break;
if (seennl == SEEN_ALL)
break;
}
endscan:
;
}
else {
void *translated;
int kind = PyUnicode_KIND(output);
const void *in_str = PyUnicode_DATA(output);
Py_ssize_t in, out;
/* XXX: Previous in-place translation here is disabled as
resizing is not possible anymore */
/* We could try to optimize this so that we only do a copy
when there is something to translate. On the other hand,
we already know there is a \r byte, so chances are high
that something needs to be done. */
translated = PyMem_Malloc(kind * len);
if (translated == NULL) {
PyErr_NoMemory();
goto error;
}
in = out = 0;
for (;;) {
Py_UCS4 c;
/* Fast loop for non-control characters */
while ((c = PyUnicode_READ(kind, in_str, in++)) > '\r')
PyUnicode_WRITE(kind, translated, out++, c);
if (c == '\n') {
PyUnicode_WRITE(kind, translated, out++, c);
seennl |= SEEN_LF;
continue;
}
if (c == '\r') {
if (PyUnicode_READ(kind, in_str, in) == '\n') {
in++;
seennl |= SEEN_CRLF;
}
else
seennl |= SEEN_CR;
PyUnicode_WRITE(kind, translated, out++, '\n');
continue;
}
if (in > len)
break;
PyUnicode_WRITE(kind, translated, out++, c);
}
Py_DECREF(output);
output = PyUnicode_FromKindAndData(kind, translated, out);
PyMem_Free(translated);
if (!output)
return NULL;
}
self->seennl |= seennl;
}
return output;
error:
Py_DECREF(output);
return NULL;
}
/*[clinic input]
_io.IncrementalNewlineDecoder.decode
input: object
final: bool = False
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_decode_impl(nldecoder_object *self,
PyObject *input, int final)
/*[clinic end generated code: output=0d486755bb37a66e input=90e223c70322c5cd]*/
{
return _PyIncrementalNewlineDecoder_decode((PyObject *) self, input, final);
}
/*[clinic input]
_io.IncrementalNewlineDecoder.getstate
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_getstate_impl(nldecoder_object *self)
/*[clinic end generated code: output=f0d2c9c136f4e0d0 input=f8ff101825e32e7f]*/
{
PyObject *buffer;
unsigned long long flag;
CHECK_INITIALIZED_DECODER(self);
if (self->decoder != Py_None) {
PyObject *state = PyObject_CallMethodNoArgs(self->decoder,
&_Py_ID(getstate));
if (state == NULL)
return NULL;
if (!PyTuple_Check(state)) {
PyErr_SetString(PyExc_TypeError,
"illegal decoder state");
Py_DECREF(state);
return NULL;
}
if (!PyArg_ParseTuple(state, "OK;illegal decoder state",
&buffer, &flag))
{
Py_DECREF(state);
return NULL;
}
Py_INCREF(buffer);
Py_DECREF(state);
}
else {
buffer = PyBytes_FromString("");
flag = 0;
}
flag <<= 1;
if (self->pendingcr)
flag |= 1;
return Py_BuildValue("NK", buffer, flag);
}
/*[clinic input]
_io.IncrementalNewlineDecoder.setstate
state: object
/
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_setstate(nldecoder_object *self,
PyObject *state)
/*[clinic end generated code: output=c10c622508b576cb input=c53fb505a76dbbe2]*/
{
PyObject *buffer;
unsigned long long flag;
CHECK_INITIALIZED_DECODER(self);
if (!PyTuple_Check(state)) {
PyErr_SetString(PyExc_TypeError, "state argument must be a tuple");
return NULL;
}
if (!PyArg_ParseTuple(state, "OK;setstate(): illegal state argument",
&buffer, &flag))
{
return NULL;
}
self->pendingcr = (int) (flag & 1);
flag >>= 1;
if (self->decoder != Py_None) {
return _PyObject_CallMethod(self->decoder, &_Py_ID(setstate),
"((OK))", buffer, flag);
}
else {
Py_RETURN_NONE;
}
}
/*[clinic input]
_io.IncrementalNewlineDecoder.reset
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_reset_impl(nldecoder_object *self)
/*[clinic end generated code: output=32fa40c7462aa8ff input=728678ddaea776df]*/
{
CHECK_INITIALIZED_DECODER(self);
self->seennl = 0;
self->pendingcr = 0;
if (self->decoder != Py_None)
return PyObject_CallMethodNoArgs(self->decoder, &_Py_ID(reset));
else
Py_RETURN_NONE;
}
static PyObject *
incrementalnewlinedecoder_newlines_get(nldecoder_object *self, void *context)
{
CHECK_INITIALIZED_DECODER(self);
switch (self->seennl) {
case SEEN_CR:
return PyUnicode_FromString("\r");
case SEEN_LF:
return PyUnicode_FromString("\n");
case SEEN_CRLF:
return PyUnicode_FromString("\r\n");
case SEEN_CR | SEEN_LF:
return Py_BuildValue("ss", "\r", "\n");
case SEEN_CR | SEEN_CRLF:
return Py_BuildValue("ss", "\r", "\r\n");
case SEEN_LF | SEEN_CRLF:
return Py_BuildValue("ss", "\n", "\r\n");
case SEEN_CR | SEEN_LF | SEEN_CRLF:
return Py_BuildValue("sss", "\r", "\n", "\r\n");
default:
Py_RETURN_NONE;
}
}
/* TextIOWrapper */
typedef PyObject *
(*encodefunc_t)(PyObject *, PyObject *);
struct textio
{
PyObject_HEAD
int ok; /* initialized? */
int detached;
Py_ssize_t chunk_size;
PyObject *buffer;
PyObject *encoding;
PyObject *encoder;
PyObject *decoder;
PyObject *readnl;
PyObject *errors;
const char *writenl; /* ASCII-encoded; NULL stands for \n */
char line_buffering;
char write_through;
char readuniversal;
char readtranslate;
char writetranslate;
char seekable;
char has_read1;
char telling;
char finalizing;
/* Specialized encoding func (see below) */
encodefunc_t encodefunc;
/* Whether or not it's the start of the stream */
char encoding_start_of_stream;
/* Reads and writes are internally buffered in order to speed things up.
However, any read will first flush the write buffer if itsn't empty.
Please also note that text to be written is first encoded before being
buffered. This is necessary so that encoding errors are immediately
reported to the caller, but it unfortunately means that the
IncrementalEncoder (whose encode() method is always written in Python)
becomes a bottleneck for small writes.
*/
PyObject *decoded_chars; /* buffer for text returned from decoder */
Py_ssize_t decoded_chars_used; /* offset into _decoded_chars for read() */
PyObject *pending_bytes; // data waiting to be written.
// ascii unicode, bytes, or list of them.
Py_ssize_t pending_bytes_count;
/* snapshot is either NULL, or a tuple (dec_flags, next_input) where
* dec_flags is the second (integer) item of the decoder state and
* next_input is the chunk of input bytes that comes next after the
* snapshot point. We use this to reconstruct decoder states in tell().
*/
PyObject *snapshot;
/* Bytes-to-characters ratio for the current chunk. Serves as input for
the heuristic in tell(). */
double b2cratio;
/* Cache raw object if it's a FileIO object */
PyObject *raw;
PyObject *weakreflist;
PyObject *dict;
_PyIO_State *state;
};
static void
textiowrapper_set_decoded_chars(textio *self, PyObject *chars);
/* A couple of specialized cases in order to bypass the slow incremental
encoding methods for the most popular encodings. */
static PyObject *
ascii_encode(textio *self, PyObject *text)
{
return _PyUnicode_AsASCIIString(text, PyUnicode_AsUTF8(self->errors));
}
static PyObject *
utf16be_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF16(text,
PyUnicode_AsUTF8(self->errors), 1);
}
static PyObject *
utf16le_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF16(text,
PyUnicode_AsUTF8(self->errors), -1);
}
static PyObject *
utf16_encode(textio *self, PyObject *text)
{
if (!self->encoding_start_of_stream) {
/* Skip the BOM and use native byte ordering */
#if PY_BIG_ENDIAN
return utf16be_encode(self, text);
#else
return utf16le_encode(self, text);
#endif
}
return _PyUnicode_EncodeUTF16(text,
PyUnicode_AsUTF8(self->errors), 0);
}
static PyObject *
utf32be_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF32(text,
PyUnicode_AsUTF8(self->errors), 1);
}
static PyObject *
utf32le_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF32(text,
PyUnicode_AsUTF8(self->errors), -1);
}
static PyObject *
utf32_encode(textio *self, PyObject *text)
{
if (!self->encoding_start_of_stream) {
/* Skip the BOM and use native byte ordering */
#if PY_BIG_ENDIAN
return utf32be_encode(self, text);
#else
return utf32le_encode(self, text);
#endif
}
return _PyUnicode_EncodeUTF32(text,
PyUnicode_AsUTF8(self->errors), 0);
}
static PyObject *
utf8_encode(textio *self, PyObject *text)
{
return _PyUnicode_AsUTF8String(text, PyUnicode_AsUTF8(self->errors));
}
static PyObject *
latin1_encode(textio *self, PyObject *text)
{
return _PyUnicode_AsLatin1String(text, PyUnicode_AsUTF8(self->errors));
}
// Return true when encoding can be skipped when text is ascii.
static inline int
is_asciicompat_encoding(encodefunc_t f)
{
return f == (encodefunc_t) ascii_encode
|| f == (encodefunc_t) latin1_encode
|| f == (encodefunc_t) utf8_encode;
}
/* Map normalized encoding names onto the specialized encoding funcs */
typedef struct {
const char *name;
encodefunc_t encodefunc;
} encodefuncentry;
static const encodefuncentry encodefuncs[] = {
{"ascii", (encodefunc_t) ascii_encode},
{"iso8859-1", (encodefunc_t) latin1_encode},
{"utf-8", (encodefunc_t) utf8_encode},
{"utf-16-be", (encodefunc_t) utf16be_encode},
{"utf-16-le", (encodefunc_t) utf16le_encode},
{"utf-16", (encodefunc_t) utf16_encode},
{"utf-32-be", (encodefunc_t) utf32be_encode},
{"utf-32-le", (encodefunc_t) utf32le_encode},
{"utf-32", (encodefunc_t) utf32_encode},
{NULL, NULL}
};
static int
validate_newline(const char *newline)
{
if (newline && newline[0] != '\0'
&& !(newline[0] == '\n' && newline[1] == '\0')
&& !(newline[0] == '\r' && newline[1] == '\0')
&& !(newline[0] == '\r' && newline[1] == '\n' && newline[2] == '\0')) {
PyErr_Format(PyExc_ValueError,
"illegal newline value: %s", newline);
return -1;
}
return 0;
}
static int
set_newline(textio *self, const char *newline)
{
PyObject *old = self->readnl;
if (newline == NULL) {
self->readnl = NULL;
}
else {
self->readnl = PyUnicode_FromString(newline);
if (self->readnl == NULL) {
self->readnl = old;
return -1;
}
}
self->readuniversal = (newline == NULL || newline[0] == '\0');
self->readtranslate = (newline == NULL);
self->writetranslate = (newline == NULL || newline[0] != '\0');
if (!self->readuniversal && self->readnl != NULL) {
// validate_newline() accepts only ASCII newlines.
assert(PyUnicode_KIND(self->readnl) == PyUnicode_1BYTE_KIND);
self->writenl = (const char *)PyUnicode_1BYTE_DATA(self->readnl);
if (strcmp(self->writenl, "\n") == 0) {
self->writenl = NULL;
}
}
else {
#ifdef MS_WINDOWS
self->writenl = "\r\n";
#else
self->writenl = NULL;
#endif
}
Py_XDECREF(old);
return 0;
}
static int
_textiowrapper_set_decoder(textio *self, PyObject *codec_info,
const char *errors)
{
PyObject *res;
int r;
res = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(readable));
if (res == NULL)
return -1;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r == -1)
return -1;
if (r != 1)
return 0;
Py_CLEAR(self->decoder);
self->decoder = _PyCodecInfo_GetIncrementalDecoder(codec_info, errors);
if (self->decoder == NULL)
return -1;
if (self->readuniversal) {
_PyIO_State *state = self->state;
PyObject *incrementalDecoder = PyObject_CallFunctionObjArgs(
(PyObject *)state->PyIncrementalNewlineDecoder_Type,
self->decoder, self->readtranslate ? Py_True : Py_False, NULL);
if (incrementalDecoder == NULL)
return -1;
Py_XSETREF(self->decoder, incrementalDecoder);
}
return 0;
}
static PyObject*
_textiowrapper_decode(_PyIO_State *state, PyObject *decoder, PyObject *bytes,
int eof)
{
PyObject *chars;
if (Py_IS_TYPE(decoder, state->PyIncrementalNewlineDecoder_Type))
chars = _PyIncrementalNewlineDecoder_decode(decoder, bytes, eof);
else
chars = PyObject_CallMethodObjArgs(decoder, &_Py_ID(decode), bytes,
eof ? Py_True : Py_False, NULL);
if (check_decoded(chars) < 0)
// check_decoded already decreases refcount
return NULL;
return chars;
}
static int
_textiowrapper_set_encoder(textio *self, PyObject *codec_info,
const char *errors)
{
PyObject *res;
int r;
res = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(writable));
if (res == NULL)
return -1;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r == -1)
return -1;
if (r != 1)
return 0;
Py_CLEAR(self->encoder);
self->encodefunc = NULL;
self->encoder = _PyCodecInfo_GetIncrementalEncoder(codec_info, errors);
if (self->encoder == NULL)
return -1;
/* Get the normalized named of the codec */
if (PyObject_GetOptionalAttr(codec_info, &_Py_ID(name), &res) < 0) {
return -1;
}
if (res != NULL && PyUnicode_Check(res)) {
const encodefuncentry *e = encodefuncs;
while (e->name != NULL) {
if (_PyUnicode_EqualToASCIIString(res, e->name)) {
self->encodefunc = e->encodefunc;
break;
}
e++;
}
}
Py_XDECREF(res);
return 0;
}
static int
_textiowrapper_fix_encoder_state(textio *self)
{
if (!self->seekable || !self->encoder) {
return 0;
}
self->encoding_start_of_stream = 1;
PyObject *cookieObj = PyObject_CallMethodNoArgs(
self->buffer, &_Py_ID(tell));
if (cookieObj == NULL) {
return -1;
}
int cmp = PyObject_RichCompareBool(cookieObj, _PyLong_GetZero(), Py_EQ);
Py_DECREF(cookieObj);
if (cmp < 0) {
return -1;
}
if (cmp == 0) {
self->encoding_start_of_stream = 0;
PyObject *res = PyObject_CallMethodOneArg(
self->encoder, &_Py_ID(setstate), _PyLong_GetZero());
if (res == NULL) {
return -1;
}
Py_DECREF(res);
}
return 0;
}
static int
io_check_errors(PyObject *errors)
{
assert(errors != NULL && errors != Py_None);
PyInterpreterState *interp = _PyInterpreterState_GET();
#ifndef Py_DEBUG
/* In release mode, only check in development mode (-X dev) */
if (!_PyInterpreterState_GetConfig(interp)->dev_mode) {
return 0;
}
#else
/* Always check in debug mode */
#endif
/* Avoid calling PyCodec_LookupError() before the codec registry is ready:
before_PyUnicode_InitEncodings() is called. */
if (!interp->unicode.fs_codec.encoding) {
return 0;
}
const char *name = _PyUnicode_AsUTF8NoNUL(errors);
if (name == NULL) {
return -1;
}
PyObject *handler = PyCodec_LookupError(name);
if (handler != NULL) {
Py_DECREF(handler);
return 0;
}
return -1;
}
/*[clinic input]
_io.TextIOWrapper.__init__
buffer: object
encoding: str(accept={str, NoneType}) = None
errors: object = None
newline: str(accept={str, NoneType}) = None
line_buffering: bool = False
write_through: bool = False
Character and line based layer over a BufferedIOBase object, buffer.
encoding gives the name of the encoding that the stream will be
decoded or encoded with. It defaults to locale.getencoding().
errors determines the strictness of encoding and decoding (see
help(codecs.Codec) or the documentation for codecs.register) and
defaults to "strict".
newline controls how line endings are handled. It can be None, '',
'\n', '\r', and '\r\n'. It works as follows:
* On input, if newline is None, universal newlines mode is
enabled. Lines in the input can end in '\n', '\r', or '\r\n', and
these are translated into '\n' before being returned to the
caller. If it is '', universal newline mode is enabled, but line
endings are returned to the caller untranslated. If it has any of
the other legal values, input lines are only terminated by the given
string, and the line ending is returned to the caller untranslated.
* On output, if newline is None, any '\n' characters written are
translated to the system default line separator, os.linesep. If
newline is '' or '\n', no translation takes place. If newline is any
of the other legal values, any '\n' characters written are translated
to the given string.
If line_buffering is True, a call to flush is implied when a call to
write contains a newline character.
[clinic start generated code]*/
static int
_io_TextIOWrapper___init___impl(textio *self, PyObject *buffer,
const char *encoding, PyObject *errors,
const char *newline, int line_buffering,
int write_through)
/*[clinic end generated code: output=72267c0c01032ed2 input=e6cfaaaf6059d4f5]*/
{
PyObject *raw, *codec_info = NULL;
PyObject *res;
int r;
self->ok = 0;
self->detached = 0;
if (encoding == NULL) {
PyInterpreterState *interp = _PyInterpreterState_GET();
if (_PyInterpreterState_GetConfig(interp)->warn_default_encoding) {
if (PyErr_WarnEx(PyExc_EncodingWarning,
"'encoding' argument not specified", 1)) {
return -1;
}
}
}
if (errors == Py_None) {
errors = &_Py_ID(strict);
}
else if (!PyUnicode_Check(errors)) {
// Check 'errors' argument here because Argument Clinic doesn't support
// 'str(accept={str, NoneType})' converter.
PyErr_Format(
PyExc_TypeError,
"TextIOWrapper() argument 'errors' must be str or None, not %.50s",
Py_TYPE(errors)->tp_name);
return -1;
}
else if (io_check_errors(errors)) {
return -1;
}
const char *errors_str = _PyUnicode_AsUTF8NoNUL(errors);
if (errors_str == NULL) {
return -1;
}
if (validate_newline(newline) < 0) {
return -1;
}
Py_CLEAR(self->buffer);
Py_CLEAR(self->encoding);
Py_CLEAR(self->encoder);
Py_CLEAR(self->decoder);
Py_CLEAR(self->readnl);
Py_CLEAR(self->decoded_chars);
Py_CLEAR(self->pending_bytes);
Py_CLEAR(self->snapshot);
Py_CLEAR(self->errors);
Py_CLEAR(self->raw);
self->decoded_chars_used = 0;
self->pending_bytes_count = 0;
self->encodefunc = NULL;
self->b2cratio = 0.0;
if (encoding == NULL && _PyRuntime.preconfig.utf8_mode) {
_Py_DECLARE_STR(utf_8, "utf-8");
self->encoding = &_Py_STR(utf_8);
}
else if (encoding == NULL || (strcmp(encoding, "locale") == 0)) {
self->encoding = _Py_GetLocaleEncodingObject();
if (self->encoding == NULL) {
goto error;
}
assert(PyUnicode_Check(self->encoding));
}
if (self->encoding != NULL) {
encoding = PyUnicode_AsUTF8(self->encoding);
if (encoding == NULL)
goto error;
}
else if (encoding != NULL) {
self->encoding = PyUnicode_FromString(encoding);
if (self->encoding == NULL)
goto error;
}
else {
PyErr_SetString(PyExc_OSError,
"could not determine default encoding");
goto error;
}
/* Check we have been asked for a real text encoding */
codec_info = _PyCodec_LookupTextEncoding(encoding, "codecs.open()");
if (codec_info == NULL) {
Py_CLEAR(self->encoding);
goto error;
}
/* XXX: Failures beyond this point have the potential to leak elements
* of the partially constructed object (like self->encoding)
*/
self->errors = Py_NewRef(errors);
self->chunk_size = 8192;
self->line_buffering = line_buffering;
self->write_through = write_through;
if (set_newline(self, newline) < 0) {
goto error;
}
self->buffer = Py_NewRef(buffer);
/* Build the decoder object */
_PyIO_State *state = find_io_state_by_def(Py_TYPE(self));
self->state = state;
if (_textiowrapper_set_decoder(self, codec_info, errors_str) != 0)
goto error;
/* Build the encoder object */
if (_textiowrapper_set_encoder(self, codec_info, errors_str) != 0)
goto error;
/* Finished sorting out the codec details */
Py_CLEAR(codec_info);
if (Py_IS_TYPE(buffer, state->PyBufferedReader_Type) ||
Py_IS_TYPE(buffer, state->PyBufferedWriter_Type) ||
Py_IS_TYPE(buffer, state->PyBufferedRandom_Type))
{
if (PyObject_GetOptionalAttr(buffer, &_Py_ID(raw), &raw) < 0)
goto error;
/* Cache the raw FileIO object to speed up 'closed' checks */
if (raw != NULL) {
if (Py_IS_TYPE(raw, state->PyFileIO_Type))
self->raw = raw;
else
Py_DECREF(raw);
}
}
res = PyObject_CallMethodNoArgs(buffer, &_Py_ID(seekable));
if (res == NULL)
goto error;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r < 0)
goto error;
self->seekable = self->telling = r;
r = PyObject_HasAttrWithError(buffer, &_Py_ID(read1));
if (r < 0) {
goto error;
}
self->has_read1 = r;
self->encoding_start_of_stream = 0;
if (_textiowrapper_fix_encoder_state(self) < 0) {
goto error;
}
self->ok = 1;
return 0;
error:
Py_XDECREF(codec_info);
return -1;
}
/* Return *default_value* if ob is None, 0 if ob is false, 1 if ob is true,
* -1 on error.
*/
static int
convert_optional_bool(PyObject *obj, int default_value)
{
long v;
if (obj == Py_None) {
v = default_value;
}
else {
v = PyLong_AsLong(obj);
if (v == -1 && PyErr_Occurred())
return -1;
}
return v != 0;
}
static int
textiowrapper_change_encoding(textio *self, PyObject *encoding,
PyObject *errors, int newline_changed)
{
/* Use existing settings where new settings are not specified */
if (encoding == Py_None && errors == Py_None && !newline_changed) {
return 0; // no change
}
if (encoding == Py_None) {
encoding = self->encoding;
if (errors == Py_None) {
errors = self->errors;
}
Py_INCREF(encoding);
}
else {
if (_PyUnicode_EqualToASCIIString(encoding, "locale")) {
encoding = _Py_GetLocaleEncodingObject();
if (encoding == NULL) {
return -1;
}
} else {
Py_INCREF(encoding);
}
if (errors == Py_None) {
errors = &_Py_ID(strict);
}
}
Py_INCREF(errors);
const char *c_encoding = PyUnicode_AsUTF8(encoding);
if (c_encoding == NULL) {
Py_DECREF(encoding);
Py_DECREF(errors);
return -1;
}
const char *c_errors = PyUnicode_AsUTF8(errors);
if (c_errors == NULL) {
Py_DECREF(encoding);
Py_DECREF(errors);
return -1;
}
// Create new encoder & decoder
PyObject *codec_info = _PyCodec_LookupTextEncoding(
c_encoding, "codecs.open()");
if (codec_info == NULL) {
Py_DECREF(encoding);
Py_DECREF(errors);
return -1;
}
if (_textiowrapper_set_decoder(self, codec_info, c_errors) != 0 ||
_textiowrapper_set_encoder(self, codec_info, c_errors) != 0) {
Py_DECREF(codec_info);
Py_DECREF(encoding);
Py_DECREF(errors);
return -1;
}
Py_DECREF(codec_info);
Py_SETREF(self->encoding, encoding);
Py_SETREF(self->errors, errors);
return _textiowrapper_fix_encoder_state(self);
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.reconfigure
*
encoding: object = None
errors: object = None
newline as newline_obj: object(c_default="NULL") = None
line_buffering as line_buffering_obj: object = None
write_through as write_through_obj: object = None
Reconfigure the text stream with new parameters.
This also does an implicit stream flush.
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_reconfigure_impl(textio *self, PyObject *encoding,
PyObject *errors, PyObject *newline_obj,
PyObject *line_buffering_obj,
PyObject *write_through_obj)
/*[clinic end generated code: output=52b812ff4b3d4b0f input=dc3bd35ebda702a7]*/
{
int line_buffering;
int write_through;
const char *newline = NULL;
if (encoding != Py_None && !PyUnicode_Check(encoding)) {
PyErr_Format(PyExc_TypeError,
"reconfigure() argument 'encoding' must be str or None, not %s",
Py_TYPE(encoding)->tp_name);
return NULL;
}
if (errors != Py_None && !PyUnicode_Check(errors)) {
PyErr_Format(PyExc_TypeError,
"reconfigure() argument 'errors' must be str or None, not %s",
Py_TYPE(errors)->tp_name);
return NULL;
}
if (newline_obj != NULL && newline_obj != Py_None &&
!PyUnicode_Check(newline_obj))
{
PyErr_Format(PyExc_TypeError,
"reconfigure() argument 'newline' must be str or None, not %s",
Py_TYPE(newline_obj)->tp_name);
return NULL;
}
/* Check if something is in the read buffer */
if (self->decoded_chars != NULL) {
if (encoding != Py_None || errors != Py_None || newline_obj != NULL) {
_unsupported(self->state,
"It is not possible to set the encoding or newline "
"of stream after the first read");
return NULL;
}
}
if (newline_obj != NULL && newline_obj != Py_None) {
newline = PyUnicode_AsUTF8(newline_obj);
if (newline == NULL || validate_newline(newline) < 0) {
return NULL;
}
}
line_buffering = convert_optional_bool(line_buffering_obj,
self->line_buffering);
if (line_buffering < 0) {
return NULL;
}
write_through = convert_optional_bool(write_through_obj,
self->write_through);
if (write_through < 0) {
return NULL;
}
if (_PyFile_Flush((PyObject *)self) < 0) {
return NULL;
}
self->b2cratio = 0;
if (newline_obj != NULL && set_newline(self, newline) < 0) {
return NULL;
}
if (textiowrapper_change_encoding(
self, encoding, errors, newline_obj != NULL) < 0) {
return NULL;
}
self->line_buffering = line_buffering;
self->write_through = write_through;
Py_RETURN_NONE;
}
static int
textiowrapper_clear(textio *self)
{
self->ok = 0;
Py_CLEAR(self->buffer);
Py_CLEAR(self->encoding);
Py_CLEAR(self->encoder);
Py_CLEAR(self->decoder);
Py_CLEAR(self->readnl);
Py_CLEAR(self->decoded_chars);
Py_CLEAR(self->pending_bytes);
Py_CLEAR(self->snapshot);
Py_CLEAR(self->errors);
Py_CLEAR(self->raw);
Py_CLEAR(self->dict);
return 0;
}
static void
textiowrapper_dealloc(textio *self)
{
PyTypeObject *tp = Py_TYPE(self);
self->finalizing = 1;
if (_PyIOBase_finalize((PyObject *) self) < 0)
return;
self->ok = 0;
_PyObject_GC_UNTRACK(self);
FT_CLEAR_WEAKREFS((PyObject *)self, self->weakreflist);
(void)textiowrapper_clear(self);
tp->tp_free((PyObject *)self);
Py_DECREF(tp);
}
static int
textiowrapper_traverse(textio *self, visitproc visit, void *arg)
{
Py_VISIT(Py_TYPE(self));
Py_VISIT(self->buffer);
Py_VISIT(self->encoding);
Py_VISIT(self->encoder);
Py_VISIT(self->decoder);
Py_VISIT(self->readnl);
Py_VISIT(self->decoded_chars);
Py_VISIT(self->pending_bytes);
Py_VISIT(self->snapshot);
Py_VISIT(self->errors);
Py_VISIT(self->raw);
Py_VISIT(self->dict);
return 0;
}
static PyObject *
_io_TextIOWrapper_closed_get_impl(textio *self);
/* This macro takes some shortcuts to make the common case faster. */
#define CHECK_CLOSED(self) \
do { \
int r; \
PyObject *_res; \
if (Py_IS_TYPE(self, self->state->PyTextIOWrapper_Type)) { \
if (self->raw != NULL) \
r = _PyFileIO_closed(self->raw); \
else { \
_res = _io_TextIOWrapper_closed_get_impl(self); \
if (_res == NULL) \
return NULL; \
r = PyObject_IsTrue(_res); \
Py_DECREF(_res); \
if (r < 0) \
return NULL; \
} \
if (r > 0) { \
PyErr_SetString(PyExc_ValueError, \
"I/O operation on closed file."); \
return NULL; \
} \
} \
else if (_PyIOBase_check_closed((PyObject *)self, Py_True) == NULL) \
return NULL; \
} while (0)
#define CHECK_INITIALIZED(self) \
if (self->ok <= 0) { \
PyErr_SetString(PyExc_ValueError, \
"I/O operation on uninitialized object"); \
return NULL; \
}
#define CHECK_ATTACHED(self) \
CHECK_INITIALIZED(self); \
if (self->detached) { \
PyErr_SetString(PyExc_ValueError, \
"underlying buffer has been detached"); \
return NULL; \
}
#define CHECK_ATTACHED_INT(self) \
if (self->ok <= 0) { \
PyErr_SetString(PyExc_ValueError, \
"I/O operation on uninitialized object"); \
return -1; \
} else if (self->detached) { \
PyErr_SetString(PyExc_ValueError, \
"underlying buffer has been detached"); \
return -1; \
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.detach
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_detach_impl(textio *self)
/*[clinic end generated code: output=7ba3715cd032d5f2 input=c908a3b4ef203b0f]*/
{
PyObject *buffer;
CHECK_ATTACHED(self);
if (_PyFile_Flush((PyObject *)self) < 0) {
return NULL;
}
buffer = self->buffer;
self->buffer = NULL;
self->detached = 1;
return buffer;
}
/* Flush the internal write buffer. This doesn't explicitly flush the
underlying buffered object, though. */
static int
_textiowrapper_writeflush(textio *self)
{
_Py_CRITICAL_SECTION_ASSERT_OBJECT_LOCKED(self);
if (self->pending_bytes == NULL)
return 0;
PyObject *pending = self->pending_bytes;
PyObject *b;
if (PyBytes_Check(pending)) {
b = Py_NewRef(pending);
}
else if (PyUnicode_Check(pending)) {
assert(PyUnicode_IS_ASCII(pending));
assert(PyUnicode_GET_LENGTH(pending) == self->pending_bytes_count);
b = PyBytes_FromStringAndSize(
PyUnicode_DATA(pending), PyUnicode_GET_LENGTH(pending));
if (b == NULL) {
return -1;
}
}
else {
assert(PyList_Check(pending));
b = PyBytes_FromStringAndSize(NULL, self->pending_bytes_count);
if (b == NULL) {
return -1;
}
char *buf = PyBytes_AsString(b);
Py_ssize_t pos = 0;
for (Py_ssize_t i = 0; i < PyList_GET_SIZE(pending); i++) {
PyObject *obj = PyList_GET_ITEM(pending, i);
char *src;
Py_ssize_t len;
if (PyUnicode_Check(obj)) {
assert(PyUnicode_IS_ASCII(obj));
src = PyUnicode_DATA(obj);
len = PyUnicode_GET_LENGTH(obj);
}
else {
assert(PyBytes_Check(obj));
if (PyBytes_AsStringAndSize(obj, &src, &len) < 0) {
Py_DECREF(b);
return -1;
}
}
memcpy(buf + pos, src, len);
pos += len;
}
assert(pos == self->pending_bytes_count);
}
self->pending_bytes_count = 0;
self->pending_bytes = NULL;
Py_DECREF(pending);
PyObject *ret;
do {
ret = PyObject_CallMethodOneArg(self->buffer, &_Py_ID(write), b);
} while (ret == NULL && _PyIO_trap_eintr());
Py_DECREF(b);
// NOTE: We cleared buffer but we don't know how many bytes are actually written
// when an error occurred.
if (ret == NULL)
return -1;
Py_DECREF(ret);
return 0;
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.write
text: unicode
/
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_write_impl(textio *self, PyObject *text)
/*[clinic end generated code: output=d2deb0d50771fcec input=73ec95c5c4a3489c]*/
{
PyObject *ret;
PyObject *b;
Py_ssize_t textlen;
int haslf = 0;
int needflush = 0, text_needflush = 0;
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
if (self->encoder == NULL) {
return _unsupported(self->state, "not writable");
}
Py_INCREF(text);
textlen = PyUnicode_GET_LENGTH(text);
if ((self->writetranslate && self->writenl != NULL) || self->line_buffering)
if (PyUnicode_FindChar(text, '\n', 0, PyUnicode_GET_LENGTH(text), 1) != -1)
haslf = 1;
if (haslf && self->writetranslate && self->writenl != NULL) {
PyObject *newtext = _PyObject_CallMethod(text, &_Py_ID(replace),
"ss", "\n", self->writenl);
Py_DECREF(text);
if (newtext == NULL)
return NULL;
text = newtext;
}
if (self->write_through)
text_needflush = 1;
if (self->line_buffering &&
(haslf ||
PyUnicode_FindChar(text, '\r', 0, PyUnicode_GET_LENGTH(text), 1) != -1))
needflush = 1;
/* XXX What if we were just reading? */
if (self->encodefunc != NULL) {
if (PyUnicode_IS_ASCII(text) &&
// See bpo-43260
PyUnicode_GET_LENGTH(text) <= self->chunk_size &&
is_asciicompat_encoding(self->encodefunc)) {
b = Py_NewRef(text);
}
else {
b = (*self->encodefunc)((PyObject *) self, text);
}
self->encoding_start_of_stream = 0;
}
else {
b = PyObject_CallMethodOneArg(self->encoder, &_Py_ID(encode), text);
}
Py_DECREF(text);
if (b == NULL)
return NULL;
if (b != text && !PyBytes_Check(b)) {
PyErr_Format(PyExc_TypeError,
"encoder should return a bytes object, not '%.200s'",
Py_TYPE(b)->tp_name);
Py_DECREF(b);
return NULL;
}
Py_ssize_t bytes_len;
if (b == text) {
bytes_len = PyUnicode_GET_LENGTH(b);
}
else {
bytes_len = PyBytes_GET_SIZE(b);
}
// We should avoid concatinating huge data.
// Flush the buffer before adding b to the buffer if b is not small.
// https://github.com/python/cpython/issues/87426
if (bytes_len >= self->chunk_size) {
// _textiowrapper_writeflush() calls buffer.write().
// self->pending_bytes can be appended during buffer->write()
// or other thread.
// We need to loop until buffer becomes empty.
// https://github.com/python/cpython/issues/118138
// https://github.com/python/cpython/issues/119506
while (self->pending_bytes != NULL) {
if (_textiowrapper_writeflush(self) < 0) {
Py_DECREF(b);
return NULL;
}
}
}
if (self->pending_bytes == NULL) {
assert(self->pending_bytes_count == 0);
self->pending_bytes = b;
}
else if (!PyList_CheckExact(self->pending_bytes)) {
PyObject *list = PyList_New(2);
if (list == NULL) {
Py_DECREF(b);
return NULL;
}
// Since Python 3.12, allocating GC object won't trigger GC and release
// GIL. See https://github.com/python/cpython/issues/97922
assert(!PyList_CheckExact(self->pending_bytes));
PyList_SET_ITEM(list, 0, self->pending_bytes);
PyList_SET_ITEM(list, 1, b);
self->pending_bytes = list;
}
else {
if (PyList_Append(self->pending_bytes, b) < 0) {
Py_DECREF(b);
return NULL;
}
Py_DECREF(b);
}
self->pending_bytes_count += bytes_len;
if (self->pending_bytes_count >= self->chunk_size || needflush ||
text_needflush) {
if (_textiowrapper_writeflush(self) < 0)
return NULL;
}
if (needflush) {
if (_PyFile_Flush(self->buffer) < 0) {
return NULL;
}
}
if (self->snapshot != NULL) {
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
}
if (self->decoder) {
ret = PyObject_CallMethodNoArgs(self->decoder, &_Py_ID(reset));
if (ret == NULL)
return NULL;
Py_DECREF(ret);
}
return PyLong_FromSsize_t(textlen);
}
/* Steal a reference to chars and store it in the decoded_char buffer;
*/
static void
textiowrapper_set_decoded_chars(textio *self, PyObject *chars)
{
Py_XSETREF(self->decoded_chars, chars);
self->decoded_chars_used = 0;
}
static PyObject *
textiowrapper_get_decoded_chars(textio *self, Py_ssize_t n)
{
PyObject *chars;
Py_ssize_t avail;
if (self->decoded_chars == NULL)
return PyUnicode_FromStringAndSize(NULL, 0);
/* decoded_chars is guaranteed to be "ready". */
avail = (PyUnicode_GET_LENGTH(self->decoded_chars)
- self->decoded_chars_used);
assert(avail >= 0);
if (n < 0 || n > avail)
n = avail;
if (self->decoded_chars_used > 0 || n < avail) {
chars = PyUnicode_Substring(self->decoded_chars,
self->decoded_chars_used,
self->decoded_chars_used + n);
if (chars == NULL)
return NULL;
}
else {
chars = Py_NewRef(self->decoded_chars);
}
self->decoded_chars_used += n;
return chars;
}
/* Read and decode the next chunk of data from the BufferedReader.
*/
static int
textiowrapper_read_chunk(textio *self, Py_ssize_t size_hint)
{
PyObject *dec_buffer = NULL;
PyObject *dec_flags = NULL;
PyObject *input_chunk = NULL;
Py_buffer input_chunk_buf;
PyObject *decoded_chars, *chunk_size;
Py_ssize_t nbytes, nchars;
int eof;
/* The return value is True unless EOF was reached. The decoded string is
* placed in self._decoded_chars (replacing its previous value). The
* entire input chunk is sent to the decoder, though some of it may remain
* buffered in the decoder, yet to be converted.
*/
if (self->decoder == NULL) {
_unsupported(self->state, "not readable");
return -1;
}
if (self->telling) {
/* To prepare for tell(), we need to snapshot a point in the file
* where the decoder's input buffer is empty.
*/
PyObject *state = PyObject_CallMethodNoArgs(self->decoder,
&_Py_ID(getstate));
if (state == NULL)
return -1;
/* Given this, we know there was a valid snapshot point
* len(dec_buffer) bytes ago with decoder state (b'', dec_flags).
*/
if (!PyTuple_Check(state)) {
PyErr_SetString(PyExc_TypeError,
"illegal decoder state");
Py_DECREF(state);
return -1;
}
if (!PyArg_ParseTuple(state,
"OO;illegal decoder state", &dec_buffer, &dec_flags))
{
Py_DECREF(state);
return -1;
}
if (!PyBytes_Check(dec_buffer)) {
PyErr_Format(PyExc_TypeError,
"illegal decoder state: the first item should be a "
"bytes object, not '%.200s'",
Py_TYPE(dec_buffer)->tp_name);
Py_DECREF(state);
return -1;
}
Py_INCREF(dec_buffer);
Py_INCREF(dec_flags);
Py_DECREF(state);
}
/* Read a chunk, decode it, and put the result in self._decoded_chars. */
if (size_hint > 0) {
size_hint = (Py_ssize_t)(Py_MAX(self->b2cratio, 1.0) * size_hint);
}
chunk_size = PyLong_FromSsize_t(Py_MAX(self->chunk_size, size_hint));
if (chunk_size == NULL)
goto fail;
input_chunk = PyObject_CallMethodOneArg(self->buffer,
(self->has_read1 ? &_Py_ID(read1): &_Py_ID(read)),
chunk_size);
Py_DECREF(chunk_size);
if (input_chunk == NULL)
goto fail;
if (PyObject_GetBuffer(input_chunk, &input_chunk_buf, 0) != 0) {
PyErr_Format(PyExc_TypeError,
"underlying %s() should have returned a bytes-like object, "
"not '%.200s'", (self->has_read1 ? "read1": "read"),
Py_TYPE(input_chunk)->tp_name);
goto fail;
}
nbytes = input_chunk_buf.len;
eof = (nbytes == 0);
decoded_chars = _textiowrapper_decode(self->state, self->decoder,
input_chunk, eof);
PyBuffer_Release(&input_chunk_buf);
if (decoded_chars == NULL)
goto fail;
textiowrapper_set_decoded_chars(self, decoded_chars);
nchars = PyUnicode_GET_LENGTH(decoded_chars);
if (nchars > 0)
self->b2cratio = (double) nbytes / nchars;
else
self->b2cratio = 0.0;
if (nchars > 0)
eof = 0;
if (self->telling) {
/* At the snapshot point, len(dec_buffer) bytes before the read, the
* next input to be decoded is dec_buffer + input_chunk.
*/
PyObject *next_input = dec_buffer;
PyBytes_Concat(&next_input, input_chunk);
dec_buffer = NULL; /* Reference lost to PyBytes_Concat */
if (next_input == NULL) {
goto fail;
}
PyObject *snapshot = Py_BuildValue("NN", dec_flags, next_input);
if (snapshot == NULL) {
dec_flags = NULL;
goto fail;
}
Py_XSETREF(self->snapshot, snapshot);
}
Py_DECREF(input_chunk);
return (eof == 0);
fail:
Py_XDECREF(dec_buffer);
Py_XDECREF(dec_flags);
Py_XDECREF(input_chunk);
return -1;
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.read
size as n: Py_ssize_t(accept={int, NoneType}) = -1
/
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_read_impl(textio *self, Py_ssize_t n)
/*[clinic end generated code: output=7e651ce6cc6a25a6 input=67d14c5661121377]*/
{
PyObject *result = NULL, *chunks = NULL;
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
if (self->decoder == NULL) {
return _unsupported(self->state, "not readable");
}
if (_textiowrapper_writeflush(self) < 0)
return NULL;
if (n < 0) {
/* Read everything */
PyObject *bytes = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(read));
PyObject *decoded;
if (bytes == NULL)
goto fail;
_PyIO_State *state = self->state;
if (Py_IS_TYPE(self->decoder, state->PyIncrementalNewlineDecoder_Type))
decoded = _PyIncrementalNewlineDecoder_decode(self->decoder,
bytes, 1);
else
decoded = PyObject_CallMethodObjArgs(
self->decoder, &_Py_ID(decode), bytes, Py_True, NULL);
Py_DECREF(bytes);
if (check_decoded(decoded) < 0)
goto fail;
result = textiowrapper_get_decoded_chars(self, -1);
if (result == NULL) {
Py_DECREF(decoded);
return NULL;
}
PyUnicode_AppendAndDel(&result, decoded);
if (result == NULL)
goto fail;
if (self->snapshot != NULL) {
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
}
return result;
}
else {
int res = 1;
Py_ssize_t remaining = n;
result = textiowrapper_get_decoded_chars(self, n);
if (result == NULL)
goto fail;
remaining -= PyUnicode_GET_LENGTH(result);
/* Keep reading chunks until we have n characters to return */
while (remaining > 0) {
res = textiowrapper_read_chunk(self, remaining);
if (res < 0) {
/* NOTE: PyErr_SetFromErrno() calls PyErr_CheckSignals()
when EINTR occurs so we needn't do it ourselves. */
if (_PyIO_trap_eintr()) {
continue;
}
goto fail;
}
if (res == 0) /* EOF */
break;
if (chunks == NULL) {
chunks = PyList_New(0);
if (chunks == NULL)
goto fail;
}
if (PyUnicode_GET_LENGTH(result) > 0 &&
PyList_Append(chunks, result) < 0)
goto fail;
Py_DECREF(result);
result = textiowrapper_get_decoded_chars(self, remaining);
if (result == NULL)
goto fail;
remaining -= PyUnicode_GET_LENGTH(result);
}
if (chunks != NULL) {
if (result != NULL && PyList_Append(chunks, result) < 0)
goto fail;
_Py_DECLARE_STR(empty, "");
Py_XSETREF(result, PyUnicode_Join(&_Py_STR(empty), chunks));
if (result == NULL)
goto fail;
Py_CLEAR(chunks);
}
return result;
}
fail:
Py_XDECREF(result);
Py_XDECREF(chunks);
return NULL;
}
/* NOTE: `end` must point to the real end of the Py_UCS4 storage,
that is to the NUL character. Otherwise the function will produce
incorrect results. */
static const char *
find_control_char(int kind, const char *s, const char *end, Py_UCS4 ch)
{
if (kind == PyUnicode_1BYTE_KIND) {
assert(ch < 256);
return (char *) memchr((const void *) s, (char) ch, end - s);
}
for (;;) {
while (PyUnicode_READ(kind, s, 0) > ch)
s += kind;
if (PyUnicode_READ(kind, s, 0) == ch)
return s;
if (s == end)
return NULL;
s += kind;
}
}
Py_ssize_t
_PyIO_find_line_ending(
int translated, int universal, PyObject *readnl,
int kind, const char *start, const char *end, Py_ssize_t *consumed)
{
Py_ssize_t len = (end - start)/kind;
if (translated) {
/* Newlines are already translated, only search for \n */
const char *pos = find_control_char(kind, start, end, '\n');
if (pos != NULL)
return (pos - start)/kind + 1;
else {
*consumed = len;
return -1;
}
}
else if (universal) {
/* Universal newline search. Find any of \r, \r\n, \n
* The decoder ensures that \r\n are not split in two pieces
*/
const char *s = start;
for (;;) {
Py_UCS4 ch;
/* Fast path for non-control chars. The loop always ends
since the Unicode string is NUL-terminated. */
while (PyUnicode_READ(kind, s, 0) > '\r')
s += kind;
if (s >= end) {
*consumed = len;
return -1;
}
ch = PyUnicode_READ(kind, s, 0);
s += kind;
if (ch == '\n')
return (s - start)/kind;
if (ch == '\r') {
if (PyUnicode_READ(kind, s, 0) == '\n')
return (s - start)/kind + 1;
else
return (s - start)/kind;
}
}
}
else {
/* Non-universal mode. */
Py_ssize_t readnl_len = PyUnicode_GET_LENGTH(readnl);
const Py_UCS1 *nl = PyUnicode_1BYTE_DATA(readnl);
/* Assume that readnl is an ASCII character. */
assert(PyUnicode_KIND(readnl) == PyUnicode_1BYTE_KIND);
if (readnl_len == 1) {
const char *pos = find_control_char(kind, start, end, nl[0]);
if (pos != NULL)
return (pos - start)/kind + 1;
*consumed = len;
return -1;
}
else {
const char *s = start;
const char *e = end - (readnl_len - 1)*kind;
const char *pos;
if (e < s)
e = s;
while (s < e) {
Py_ssize_t i;
const char *pos = find_control_char(kind, s, end, nl[0]);
if (pos == NULL || pos >= e)
break;
for (i = 1; i < readnl_len; i++) {
if (PyUnicode_READ(kind, pos, i) != nl[i])
break;
}
if (i == readnl_len)
return (pos - start)/kind + readnl_len;
s = pos + kind;
}
pos = find_control_char(kind, e, end, nl[0]);
if (pos == NULL)
*consumed = len;
else
*consumed = (pos - start)/kind;
return -1;
}
}
}
static PyObject *
_textiowrapper_readline(textio *self, Py_ssize_t limit)
{
PyObject *line = NULL, *chunks = NULL, *remaining = NULL;
Py_ssize_t start, endpos, chunked, offset_to_buffer;
int res;
CHECK_CLOSED(self);
if (_textiowrapper_writeflush(self) < 0)
return NULL;
chunked = 0;
while (1) {
const char *ptr;
Py_ssize_t line_len;
int kind;
Py_ssize_t consumed = 0;
/* First, get some data if necessary */
res = 1;
while (!self->decoded_chars ||
!PyUnicode_GET_LENGTH(self->decoded_chars)) {
res = textiowrapper_read_chunk(self, 0);
if (res < 0) {
/* NOTE: PyErr_SetFromErrno() calls PyErr_CheckSignals()
when EINTR occurs so we needn't do it ourselves. */
if (_PyIO_trap_eintr()) {
continue;
}
goto error;
}
if (res == 0)
break;
}
if (res == 0) {
/* end of file */
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
start = endpos = offset_to_buffer = 0;
break;
}
if (remaining == NULL) {
line = Py_NewRef(self->decoded_chars);
start = self->decoded_chars_used;
offset_to_buffer = 0;
}
else {
assert(self->decoded_chars_used == 0);
line = PyUnicode_Concat(remaining, self->decoded_chars);
start = 0;
offset_to_buffer = PyUnicode_GET_LENGTH(remaining);
Py_CLEAR(remaining);
if (line == NULL)
goto error;
}
ptr = PyUnicode_DATA(line);
line_len = PyUnicode_GET_LENGTH(line);
kind = PyUnicode_KIND(line);
endpos = _PyIO_find_line_ending(
self->readtranslate, self->readuniversal, self->readnl,
kind,
ptr + kind * start,
ptr + kind * line_len,
&consumed);
if (endpos >= 0) {
endpos += start;
if (limit >= 0 && (endpos - start) + chunked >= limit)
endpos = start + limit - chunked;
break;
}
/* We can put aside up to `endpos` */
endpos = consumed + start;
if (limit >= 0 && (endpos - start) + chunked >= limit) {
/* Didn't find line ending, but reached length limit */
endpos = start + limit - chunked;
break;
}
if (endpos > start) {
/* No line ending seen yet - put aside current data */
PyObject *s;
if (chunks == NULL) {
chunks = PyList_New(0);
if (chunks == NULL)
goto error;
}
s = PyUnicode_Substring(line, start, endpos);
if (s == NULL)
goto error;
if (PyList_Append(chunks, s) < 0) {
Py_DECREF(s);
goto error;
}
chunked += PyUnicode_GET_LENGTH(s);
Py_DECREF(s);
}
/* There may be some remaining bytes we'll have to prepend to the
next chunk of data */
if (endpos < line_len) {
remaining = PyUnicode_Substring(line, endpos, line_len);
if (remaining == NULL)
goto error;
}
Py_CLEAR(line);
/* We have consumed the buffer */
textiowrapper_set_decoded_chars(self, NULL);
}
if (line != NULL) {
/* Our line ends in the current buffer */
self->decoded_chars_used = endpos - offset_to_buffer;
if (start > 0 || endpos < PyUnicode_GET_LENGTH(line)) {
PyObject *s = PyUnicode_Substring(line, start, endpos);
Py_CLEAR(line);
if (s == NULL)
goto error;
line = s;
}
}
if (remaining != NULL) {
if (chunks == NULL) {
chunks = PyList_New(0);
if (chunks == NULL)
goto error;
}
if (PyList_Append(chunks, remaining) < 0)
goto error;
Py_CLEAR(remaining);
}
if (chunks != NULL) {
if (line != NULL) {
if (PyList_Append(chunks, line) < 0)
goto error;
Py_DECREF(line);
}
line = PyUnicode_Join(&_Py_STR(empty), chunks);
if (line == NULL)
goto error;
Py_CLEAR(chunks);
}
if (line == NULL) {
line = &_Py_STR(empty);
}
return line;
error:
Py_XDECREF(chunks);
Py_XDECREF(remaining);
Py_XDECREF(line);
return NULL;
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.readline
size: Py_ssize_t = -1
/
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_readline_impl(textio *self, Py_ssize_t size)
/*[clinic end generated code: output=344afa98804e8b25 input=b65bab871dc3ddba]*/
{
CHECK_ATTACHED(self);
return _textiowrapper_readline(self, size);
}
/* Seek and Tell */
typedef struct {
Py_off_t start_pos;
int dec_flags;
int bytes_to_feed;
int chars_to_skip;
char need_eof;
} cookie_type;
/*
To speed up cookie packing/unpacking, we store the fields in a temporary
string and call _PyLong_FromByteArray() or _PyLong_AsByteArray (resp.).
The following macros define at which offsets in the intermediary byte
string the various CookieStruct fields will be stored.
*/
#define COOKIE_BUF_LEN (sizeof(Py_off_t) + 3 * sizeof(int) + sizeof(char))
#if PY_BIG_ENDIAN
/* We want the least significant byte of start_pos to also be the least
significant byte of the cookie, which means that in big-endian mode we
must copy the fields in reverse order. */
# define OFF_START_POS (sizeof(char) + 3 * sizeof(int))
# define OFF_DEC_FLAGS (sizeof(char) + 2 * sizeof(int))
# define OFF_BYTES_TO_FEED (sizeof(char) + sizeof(int))
# define OFF_CHARS_TO_SKIP (sizeof(char))
# define OFF_NEED_EOF 0
#else
/* Little-endian mode: the least significant byte of start_pos will
naturally end up the least significant byte of the cookie. */
# define OFF_START_POS 0
# define OFF_DEC_FLAGS (sizeof(Py_off_t))
# define OFF_BYTES_TO_FEED (sizeof(Py_off_t) + sizeof(int))
# define OFF_CHARS_TO_SKIP (sizeof(Py_off_t) + 2 * sizeof(int))
# define OFF_NEED_EOF (sizeof(Py_off_t) + 3 * sizeof(int))
#endif
static int
textiowrapper_parse_cookie(cookie_type *cookie, PyObject *cookieObj)
{
unsigned char buffer[COOKIE_BUF_LEN];
PyLongObject *cookieLong = (PyLongObject *)PyNumber_Long(cookieObj);
if (cookieLong == NULL)
return -1;
if (_PyLong_AsByteArray(cookieLong, buffer, sizeof(buffer),
PY_LITTLE_ENDIAN, 0, 1) < 0) {
Py_DECREF(cookieLong);
return -1;
}
Py_DECREF(cookieLong);
memcpy(&cookie->start_pos, buffer + OFF_START_POS, sizeof(cookie->start_pos));
memcpy(&cookie->dec_flags, buffer + OFF_DEC_FLAGS, sizeof(cookie->dec_flags));
memcpy(&cookie->bytes_to_feed, buffer + OFF_BYTES_TO_FEED, sizeof(cookie->bytes_to_feed));
memcpy(&cookie->chars_to_skip, buffer + OFF_CHARS_TO_SKIP, sizeof(cookie->chars_to_skip));
memcpy(&cookie->need_eof, buffer + OFF_NEED_EOF, sizeof(cookie->need_eof));
return 0;
}
static PyObject *
textiowrapper_build_cookie(cookie_type *cookie)
{
unsigned char buffer[COOKIE_BUF_LEN];
memcpy(buffer + OFF_START_POS, &cookie->start_pos, sizeof(cookie->start_pos));
memcpy(buffer + OFF_DEC_FLAGS, &cookie->dec_flags, sizeof(cookie->dec_flags));
memcpy(buffer + OFF_BYTES_TO_FEED, &cookie->bytes_to_feed, sizeof(cookie->bytes_to_feed));
memcpy(buffer + OFF_CHARS_TO_SKIP, &cookie->chars_to_skip, sizeof(cookie->chars_to_skip));
memcpy(buffer + OFF_NEED_EOF, &cookie->need_eof, sizeof(cookie->need_eof));
return _PyLong_FromByteArray(buffer, sizeof(buffer),
PY_LITTLE_ENDIAN, 0);
}
static int
_textiowrapper_decoder_setstate(textio *self, cookie_type *cookie)
{
PyObject *res;
/* When seeking to the start of the stream, we call decoder.reset()
rather than decoder.getstate().
This is for a few decoders such as utf-16 for which the state value
at start is not (b"", 0) but e.g. (b"", 2) (meaning, in the case of
utf-16, that we are expecting a BOM).
*/
if (cookie->start_pos == 0 && cookie->dec_flags == 0) {
res = PyObject_CallMethodNoArgs(self->decoder, &_Py_ID(reset));
}
else {
res = _PyObject_CallMethod(self->decoder, &_Py_ID(setstate),
"((yi))", "", cookie->dec_flags);
}
if (res == NULL) {
return -1;
}
Py_DECREF(res);
return 0;
}
static int
_textiowrapper_encoder_reset(textio *self, int start_of_stream)
{
PyObject *res;
if (start_of_stream) {
res = PyObject_CallMethodNoArgs(self->encoder, &_Py_ID(reset));
self->encoding_start_of_stream = 1;
}
else {
res = PyObject_CallMethodOneArg(self->encoder, &_Py_ID(setstate),
_PyLong_GetZero());
self->encoding_start_of_stream = 0;
}
if (res == NULL)
return -1;
Py_DECREF(res);
return 0;
}
static int
_textiowrapper_encoder_setstate(textio *self, cookie_type *cookie)
{
/* Same as _textiowrapper_decoder_setstate() above. */
return _textiowrapper_encoder_reset(
self, cookie->start_pos == 0 && cookie->dec_flags == 0);
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.seek
cookie as cookieObj: object
Zero or an opaque number returned by tell().
whence: int(c_default='0') = os.SEEK_SET
The relative position to seek from.
/
Set the stream position, and return the new stream position.
Four operations are supported, given by the following argument
combinations:
- seek(0, SEEK_SET): Rewind to the start of the stream.
- seek(cookie, SEEK_SET): Restore a previous position;
'cookie' must be a number returned by tell().
- seek(0, SEEK_END): Fast-forward to the end of the stream.
- seek(0, SEEK_CUR): Leave the current stream position unchanged.
Any other argument combinations are invalid,
and may raise exceptions.
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_seek_impl(textio *self, PyObject *cookieObj, int whence)
/*[clinic end generated code: output=0a15679764e2d04d input=4bea78698be23d7e]*/
{
PyObject *posobj;
cookie_type cookie;
PyObject *res;
int cmp;
PyObject *snapshot;
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
Py_INCREF(cookieObj);
if (!self->seekable) {
_unsupported(self->state, "underlying stream is not seekable");
goto fail;
}
PyObject *zero = _PyLong_GetZero(); // borrowed reference
switch (whence) {
case SEEK_CUR:
/* seek relative to current position */
cmp = PyObject_RichCompareBool(cookieObj, zero, Py_EQ);
if (cmp < 0)
goto fail;
if (cmp == 0) {
_unsupported(self->state, "can't do nonzero cur-relative seeks");
goto fail;
}
/* Seeking to the current position should attempt to
* sync the underlying buffer with the current position.
*/
Py_DECREF(cookieObj);
cookieObj = PyObject_CallMethodNoArgs((PyObject *)self, &_Py_ID(tell));
if (cookieObj == NULL)
goto fail;
break;
case SEEK_END:
/* seek relative to end of file */
cmp = PyObject_RichCompareBool(cookieObj, zero, Py_EQ);
if (cmp < 0)
goto fail;
if (cmp == 0) {
_unsupported(self->state, "can't do nonzero end-relative seeks");
goto fail;
}
if (_PyFile_Flush((PyObject *)self) < 0) {
goto fail;
}
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
if (self->decoder) {
res = PyObject_CallMethodNoArgs(self->decoder, &_Py_ID(reset));
if (res == NULL)
goto fail;
Py_DECREF(res);
}
res = _PyObject_CallMethod(self->buffer, &_Py_ID(seek), "ii", 0, 2);
Py_CLEAR(cookieObj);
if (res == NULL)
goto fail;
if (self->encoder) {
/* If seek() == 0, we are at the start of stream, otherwise not */
cmp = PyObject_RichCompareBool(res, zero, Py_EQ);
if (cmp < 0 || _textiowrapper_encoder_reset(self, cmp)) {
Py_DECREF(res);
goto fail;
}
}
return res;
case SEEK_SET:
break;
default:
PyErr_Format(PyExc_ValueError,
"invalid whence (%d, should be %d, %d or %d)", whence,
SEEK_SET, SEEK_CUR, SEEK_END);
goto fail;
}
cmp = PyObject_RichCompareBool(cookieObj, zero, Py_LT);
if (cmp < 0)
goto fail;
if (cmp == 1) {
PyErr_Format(PyExc_ValueError,
"negative seek position %R", cookieObj);
goto fail;
}
if (_PyFile_Flush((PyObject *)self) < 0) {
goto fail;
}
/* The strategy of seek() is to go back to the safe start point
* and replay the effect of read(chars_to_skip) from there.
*/
if (textiowrapper_parse_cookie(&cookie, cookieObj) < 0)
goto fail;
/* Seek back to the safe start point. */
posobj = PyLong_FromOff_t(cookie.start_pos);
if (posobj == NULL)
goto fail;
res = PyObject_CallMethodOneArg(self->buffer, &_Py_ID(seek), posobj);
Py_DECREF(posobj);
if (res == NULL)
goto fail;
Py_DECREF(res);
textiowrapper_set_decoded_chars(self, NULL);
Py_CLEAR(self->snapshot);
/* Restore the decoder to its state from the safe start point. */
if (self->decoder) {
if (_textiowrapper_decoder_setstate(self, &cookie) < 0)
goto fail;
}
if (cookie.chars_to_skip) {
/* Just like _read_chunk, feed the decoder and save a snapshot. */
PyObject *input_chunk = _PyObject_CallMethod(self->buffer, &_Py_ID(read),
"i", cookie.bytes_to_feed);
PyObject *decoded;
if (input_chunk == NULL)
goto fail;
if (!PyBytes_Check(input_chunk)) {
PyErr_Format(PyExc_TypeError,
"underlying read() should have returned a bytes "
"object, not '%.200s'",
Py_TYPE(input_chunk)->tp_name);
Py_DECREF(input_chunk);
goto fail;
}
snapshot = Py_BuildValue("iN", cookie.dec_flags, input_chunk);
if (snapshot == NULL) {
goto fail;
}
Py_XSETREF(self->snapshot, snapshot);
decoded = PyObject_CallMethodObjArgs(self->decoder, &_Py_ID(decode),
input_chunk, cookie.need_eof ? Py_True : Py_False, NULL);
if (check_decoded(decoded) < 0)
goto fail;
textiowrapper_set_decoded_chars(self, decoded);
/* Skip chars_to_skip of the decoded characters. */
if (PyUnicode_GetLength(self->decoded_chars) < cookie.chars_to_skip) {
PyErr_SetString(PyExc_OSError, "can't restore logical file position");
goto fail;
}
self->decoded_chars_used = cookie.chars_to_skip;
}
else {
snapshot = Py_BuildValue("iy", cookie.dec_flags, "");
if (snapshot == NULL)
goto fail;
Py_XSETREF(self->snapshot, snapshot);
}
/* Finally, reset the encoder (merely useful for proper BOM handling) */
if (self->encoder) {
if (_textiowrapper_encoder_setstate(self, &cookie) < 0)
goto fail;
}
return cookieObj;
fail:
Py_XDECREF(cookieObj);
return NULL;
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.tell
Return the stream position as an opaque number.
The return value of tell() can be given as input to seek(), to restore a
previous stream position.
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_tell_impl(textio *self)
/*[clinic end generated code: output=4f168c08bf34ad5f input=415d6b4e4f8e6e8c]*/
{
PyObject *res;
PyObject *posobj = NULL;
cookie_type cookie = {0,0,0,0,0};
PyObject *next_input;
Py_ssize_t chars_to_skip, chars_decoded;
Py_ssize_t skip_bytes, skip_back;
PyObject *saved_state = NULL;
const char *input, *input_end;
Py_ssize_t dec_buffer_len;
int dec_flags;
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
if (!self->seekable) {
_unsupported(self->state, "underlying stream is not seekable");
goto fail;
}
if (!self->telling) {
PyErr_SetString(PyExc_OSError,
"telling position disabled by next() call");
goto fail;
}
if (_textiowrapper_writeflush(self) < 0)
return NULL;
if (_PyFile_Flush((PyObject *)self) < 0) {
goto fail;
}
posobj = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(tell));
if (posobj == NULL)
goto fail;
if (self->decoder == NULL || self->snapshot == NULL) {
assert (self->decoded_chars == NULL || PyUnicode_GetLength(self->decoded_chars) == 0);
return posobj;
}
#if defined(HAVE_LARGEFILE_SUPPORT)
cookie.start_pos = PyLong_AsLongLong(posobj);
#else
cookie.start_pos = PyLong_AsLong(posobj);
#endif
Py_DECREF(posobj);
if (PyErr_Occurred())
goto fail;
/* Skip backward to the snapshot point (see _read_chunk). */
assert(PyTuple_Check(self->snapshot));
if (!PyArg_ParseTuple(self->snapshot, "iO", &cookie.dec_flags, &next_input))
goto fail;
assert (PyBytes_Check(next_input));
cookie.start_pos -= PyBytes_GET_SIZE(next_input);
/* How many decoded characters have been used up since the snapshot? */
if (self->decoded_chars_used == 0) {
/* We haven't moved from the snapshot point. */
return textiowrapper_build_cookie(&cookie);
}
chars_to_skip = self->decoded_chars_used;
/* Decoder state will be restored at the end */
saved_state = PyObject_CallMethodNoArgs(self->decoder,
&_Py_ID(getstate));
if (saved_state == NULL)
goto fail;
#define DECODER_GETSTATE() do { \
PyObject *dec_buffer; \
PyObject *_state = PyObject_CallMethodNoArgs(self->decoder, \
&_Py_ID(getstate)); \
if (_state == NULL) \
goto fail; \
if (!PyTuple_Check(_state)) { \
PyErr_SetString(PyExc_TypeError, \
"illegal decoder state"); \
Py_DECREF(_state); \
goto fail; \
} \
if (!PyArg_ParseTuple(_state, "Oi;illegal decoder state", \
&dec_buffer, &dec_flags)) \
{ \
Py_DECREF(_state); \
goto fail; \
} \
if (!PyBytes_Check(dec_buffer)) { \
PyErr_Format(PyExc_TypeError, \
"illegal decoder state: the first item should be a " \
"bytes object, not '%.200s'", \
Py_TYPE(dec_buffer)->tp_name); \
Py_DECREF(_state); \
goto fail; \
} \
dec_buffer_len = PyBytes_GET_SIZE(dec_buffer); \
Py_DECREF(_state); \
} while (0)
#define DECODER_DECODE(start, len, res) do { \
PyObject *_decoded = _PyObject_CallMethod( \
self->decoder, &_Py_ID(decode), "y#", start, len); \
if (check_decoded(_decoded) < 0) \
goto fail; \
res = PyUnicode_GET_LENGTH(_decoded); \
Py_DECREF(_decoded); \
} while (0)
/* Fast search for an acceptable start point, close to our
current pos */
skip_bytes = (Py_ssize_t) (self->b2cratio * chars_to_skip);
skip_back = 1;
assert(skip_back <= PyBytes_GET_SIZE(next_input));
input = PyBytes_AS_STRING(next_input);
while (skip_bytes > 0) {
/* Decode up to temptative start point */
if (_textiowrapper_decoder_setstate(self, &cookie) < 0)
goto fail;
DECODER_DECODE(input, skip_bytes, chars_decoded);
if (chars_decoded <= chars_to_skip) {
DECODER_GETSTATE();
if (dec_buffer_len == 0) {
/* Before pos and no bytes buffered in decoder => OK */
cookie.dec_flags = dec_flags;
chars_to_skip -= chars_decoded;
break;
}
/* Skip back by buffered amount and reset heuristic */
skip_bytes -= dec_buffer_len;
skip_back = 1;
}
else {
/* We're too far ahead, skip back a bit */
skip_bytes -= skip_back;
skip_back *= 2;
}
}
if (skip_bytes <= 0) {
skip_bytes = 0;
if (_textiowrapper_decoder_setstate(self, &cookie) < 0)
goto fail;
}
/* Note our initial start point. */
cookie.start_pos += skip_bytes;
cookie.chars_to_skip = Py_SAFE_DOWNCAST(chars_to_skip, Py_ssize_t, int);
if (chars_to_skip == 0)
goto finally;
/* We should be close to the desired position. Now feed the decoder one
* byte at a time until we reach the `chars_to_skip` target.
* As we go, note the nearest "safe start point" before the current
* location (a point where the decoder has nothing buffered, so seek()
* can safely start from there and advance to this location).
*/
chars_decoded = 0;
input = PyBytes_AS_STRING(next_input);
input_end = input + PyBytes_GET_SIZE(next_input);
input += skip_bytes;
while (input < input_end) {
Py_ssize_t n;
DECODER_DECODE(input, (Py_ssize_t)1, n);
/* We got n chars for 1 byte */
chars_decoded += n;
cookie.bytes_to_feed += 1;
DECODER_GETSTATE();
if (dec_buffer_len == 0 && chars_decoded <= chars_to_skip) {
/* Decoder buffer is empty, so this is a safe start point. */
cookie.start_pos += cookie.bytes_to_feed;
chars_to_skip -= chars_decoded;
cookie.dec_flags = dec_flags;
cookie.bytes_to_feed = 0;
chars_decoded = 0;
}
if (chars_decoded >= chars_to_skip)
break;
input++;
}
if (input == input_end) {
/* We didn't get enough decoded data; signal EOF to get more. */
PyObject *decoded = _PyObject_CallMethod(
self->decoder, &_Py_ID(decode), "yO", "", /* final = */ Py_True);
if (check_decoded(decoded) < 0)
goto fail;
chars_decoded += PyUnicode_GET_LENGTH(decoded);
Py_DECREF(decoded);
cookie.need_eof = 1;
if (chars_decoded < chars_to_skip) {
PyErr_SetString(PyExc_OSError,
"can't reconstruct logical file position");
goto fail;
}
}
finally:
res = PyObject_CallMethodOneArg(
self->decoder, &_Py_ID(setstate), saved_state);
Py_DECREF(saved_state);
if (res == NULL)
return NULL;
Py_DECREF(res);
/* The returned cookie corresponds to the last safe start point. */
cookie.chars_to_skip = Py_SAFE_DOWNCAST(chars_to_skip, Py_ssize_t, int);
return textiowrapper_build_cookie(&cookie);
fail:
if (saved_state) {
PyObject *exc = PyErr_GetRaisedException();
res = PyObject_CallMethodOneArg(
self->decoder, &_Py_ID(setstate), saved_state);
_PyErr_ChainExceptions1(exc);
Py_DECREF(saved_state);
Py_XDECREF(res);
}
return NULL;
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.truncate
pos: object = None
/
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_truncate_impl(textio *self, PyObject *pos)
/*[clinic end generated code: output=90ec2afb9bb7745f input=8bddb320834c93ee]*/
{
CHECK_ATTACHED(self)
if (_PyFile_Flush((PyObject *)self) < 0) {
return NULL;
}
return PyObject_CallMethodOneArg(self->buffer, &_Py_ID(truncate), pos);
}
static PyObject *
textiowrapper_repr(textio *self)
{
PyObject *nameobj, *modeobj, *res, *s;
int status;
const char *type_name = Py_TYPE(self)->tp_name;
CHECK_INITIALIZED(self);
res = PyUnicode_FromFormat("<%.100s", type_name);
if (res == NULL)
return NULL;
status = Py_ReprEnter((PyObject *)self);
if (status != 0) {
if (status > 0) {
PyErr_Format(PyExc_RuntimeError,
"reentrant call inside %.100s.__repr__",
type_name);
}
goto error;
}
if (PyObject_GetOptionalAttr((PyObject *) self, &_Py_ID(name), &nameobj) < 0) {
if (!PyErr_ExceptionMatches(PyExc_ValueError)) {
goto error;
}
/* Ignore ValueError raised if the underlying stream was detached */
PyErr_Clear();
}
if (nameobj != NULL) {
s = PyUnicode_FromFormat(" name=%R", nameobj);
Py_DECREF(nameobj);
if (s == NULL)
goto error;
PyUnicode_AppendAndDel(&res, s);
if (res == NULL)
goto error;
}
if (PyObject_GetOptionalAttr((PyObject *) self, &_Py_ID(mode), &modeobj) < 0) {
goto error;
}
if (modeobj != NULL) {
s = PyUnicode_FromFormat(" mode=%R", modeobj);
Py_DECREF(modeobj);
if (s == NULL)
goto error;
PyUnicode_AppendAndDel(&res, s);
if (res == NULL)
goto error;
}
s = PyUnicode_FromFormat("%U encoding=%R>",
res, self->encoding);
Py_DECREF(res);
if (status == 0) {
Py_ReprLeave((PyObject *)self);
}
return s;
error:
Py_XDECREF(res);
if (status == 0) {
Py_ReprLeave((PyObject *)self);
}
return NULL;
}
/* Inquiries */
/*[clinic input]
@critical_section
_io.TextIOWrapper.fileno
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_fileno_impl(textio *self)
/*[clinic end generated code: output=21490a4c3da13e6c input=515e1196aceb97ab]*/
{
CHECK_ATTACHED(self);
return PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(fileno));
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.seekable
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_seekable_impl(textio *self)
/*[clinic end generated code: output=ab223dbbcffc0f00 input=71c4c092736c549b]*/
{
CHECK_ATTACHED(self);
return PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(seekable));
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.readable
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_readable_impl(textio *self)
/*[clinic end generated code: output=72ff7ba289a8a91b input=80438d1f01b0a89b]*/
{
CHECK_ATTACHED(self);
return PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(readable));
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.writable
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_writable_impl(textio *self)
/*[clinic end generated code: output=a728c71790d03200 input=9d6c22befb0c340a]*/
{
CHECK_ATTACHED(self);
return PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(writable));
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.isatty
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_isatty_impl(textio *self)
/*[clinic end generated code: output=12be1a35bace882e input=7f83ff04d4d1733d]*/
{
CHECK_ATTACHED(self);
return PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(isatty));
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.flush
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_flush_impl(textio *self)
/*[clinic end generated code: output=59de9165f9c2e4d2 input=3ac3bf521bfed59d]*/
{
CHECK_ATTACHED(self);
CHECK_CLOSED(self);
self->telling = self->seekable;
if (_textiowrapper_writeflush(self) < 0)
return NULL;
return PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(flush));
}
/*[clinic input]
@critical_section
_io.TextIOWrapper.close
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_close_impl(textio *self)
/*[clinic end generated code: output=056ccf8b4876e4f4 input=8e12d7079d5ac5c1]*/
{
PyObject *res;
int r;
CHECK_ATTACHED(self);
res = _io_TextIOWrapper_closed_get_impl(self);
if (res == NULL)
return NULL;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r < 0)
return NULL;
if (r > 0) {
Py_RETURN_NONE; /* stream already closed */
}
else {
PyObject *exc = NULL;
if (self->finalizing) {
res = PyObject_CallMethodOneArg(self->buffer, &_Py_ID(_dealloc_warn),
(PyObject *)self);
if (res) {
Py_DECREF(res);
}
else {
PyErr_Clear();
}
}
if (_PyFile_Flush((PyObject *)self) < 0) {
exc = PyErr_GetRaisedException();
}
res = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(close));
if (exc != NULL) {
_PyErr_ChainExceptions1(exc);
Py_CLEAR(res);
}
return res;
}
}
static PyObject *
textiowrapper_iternext_lock_held(PyObject *op)
{
_Py_CRITICAL_SECTION_ASSERT_OBJECT_LOCKED(op);
PyObject *line;
textio *self = (textio *)op;
CHECK_ATTACHED(self);
self->telling = 0;
if (Py_IS_TYPE(self, self->state->PyTextIOWrapper_Type)) {
/* Skip method call overhead for speed */
line = _textiowrapper_readline(self, -1);
}
else {
line = PyObject_CallMethodNoArgs((PyObject *)self,
&_Py_ID(readline));
if (line && !PyUnicode_Check(line)) {
PyErr_Format(PyExc_OSError,
"readline() should have returned a str object, "
"not '%.200s'", Py_TYPE(line)->tp_name);
Py_DECREF(line);
return NULL;
}
}
if (line == NULL)
return NULL;
if (PyUnicode_GET_LENGTH(line) == 0) {
/* Reached EOF or would have blocked */
Py_DECREF(line);
Py_CLEAR(self->snapshot);
self->telling = self->seekable;
return NULL;
}
return line;
}
static PyObject *
textiowrapper_iternext(PyObject *op)
{
PyObject *result;
Py_BEGIN_CRITICAL_SECTION(op);
result = textiowrapper_iternext_lock_held(op);
Py_END_CRITICAL_SECTION();
return result;
}
/*[clinic input]
@critical_section
@getter
_io.TextIOWrapper.name
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_name_get_impl(textio *self)
/*[clinic end generated code: output=8c2f1d6d8756af40 input=26ecec9b39e30e07]*/
{
CHECK_ATTACHED(self);
return PyObject_GetAttr(self->buffer, &_Py_ID(name));
}
/*[clinic input]
@critical_section
@getter
_io.TextIOWrapper.closed
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_closed_get_impl(textio *self)
/*[clinic end generated code: output=b49b68f443a85e3c input=7dfcf43f63c7003d]*/
{
CHECK_ATTACHED(self);
return PyObject_GetAttr(self->buffer, &_Py_ID(closed));
}
/*[clinic input]
@critical_section
@getter
_io.TextIOWrapper.newlines
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_newlines_get_impl(textio *self)
/*[clinic end generated code: output=53aa03ac35573180 input=610df647e514b3e8]*/
{
PyObject *res;
CHECK_ATTACHED(self);
if (self->decoder == NULL ||
PyObject_GetOptionalAttr(self->decoder, &_Py_ID(newlines), &res) == 0)
{
Py_RETURN_NONE;
}
return res;
}
/*[clinic input]
@critical_section
@getter
_io.TextIOWrapper.errors
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper_errors_get_impl(textio *self)
/*[clinic end generated code: output=dca3a3ef21b09484 input=b45f983e6d43c4d8]*/
{
CHECK_INITIALIZED(self);
return Py_NewRef(self->errors);
}
/*[clinic input]
@critical_section
@getter
_io.TextIOWrapper._CHUNK_SIZE
[clinic start generated code]*/
static PyObject *
_io_TextIOWrapper__CHUNK_SIZE_get_impl(textio *self)
/*[clinic end generated code: output=039925cd2df375bc input=e9715b0e06ff0fa6]*/
{
CHECK_ATTACHED(self);
return PyLong_FromSsize_t(self->chunk_size);
}
/*[clinic input]
@critical_section
@setter
_io.TextIOWrapper._CHUNK_SIZE
[clinic start generated code]*/
static int
_io_TextIOWrapper__CHUNK_SIZE_set_impl(textio *self, PyObject *value)
/*[clinic end generated code: output=edb86d2db660a5ab input=32fc99861db02a0a]*/
{
Py_ssize_t n;
CHECK_ATTACHED_INT(self);
if (value == NULL) {
PyErr_SetString(PyExc_AttributeError, "cannot delete attribute");
return -1;
}
n = PyNumber_AsSsize_t(value, PyExc_ValueError);
if (n == -1 && PyErr_Occurred())
return -1;
if (n <= 0) {
PyErr_SetString(PyExc_ValueError,
"a strictly positive integer is required");
return -1;
}
self->chunk_size = n;
return 0;
}
static PyMethodDef incrementalnewlinedecoder_methods[] = {
_IO_INCREMENTALNEWLINEDECODER_DECODE_METHODDEF
_IO_INCREMENTALNEWLINEDECODER_GETSTATE_METHODDEF
_IO_INCREMENTALNEWLINEDECODER_SETSTATE_METHODDEF
_IO_INCREMENTALNEWLINEDECODER_RESET_METHODDEF
{NULL}
};
static PyGetSetDef incrementalnewlinedecoder_getset[] = {
{"newlines", (getter)incrementalnewlinedecoder_newlines_get, NULL, NULL},
{NULL}
};
static PyType_Slot nldecoder_slots[] = {
{Py_tp_dealloc, incrementalnewlinedecoder_dealloc},
{Py_tp_doc, (void *)_io_IncrementalNewlineDecoder___init____doc__},
{Py_tp_methods, incrementalnewlinedecoder_methods},
{Py_tp_getset, incrementalnewlinedecoder_getset},
{Py_tp_traverse, incrementalnewlinedecoder_traverse},
{Py_tp_clear, incrementalnewlinedecoder_clear},
{Py_tp_init, _io_IncrementalNewlineDecoder___init__},
{0, NULL},
};
PyType_Spec nldecoder_spec = {
.name = "_io.IncrementalNewlineDecoder",
.basicsize = sizeof(nldecoder_object),
.flags = (Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE | Py_TPFLAGS_HAVE_GC |
Py_TPFLAGS_IMMUTABLETYPE),
.slots = nldecoder_slots,
};
static PyMethodDef textiowrapper_methods[] = {
_IO_TEXTIOWRAPPER_DETACH_METHODDEF
_IO_TEXTIOWRAPPER_RECONFIGURE_METHODDEF
_IO_TEXTIOWRAPPER_WRITE_METHODDEF
_IO_TEXTIOWRAPPER_READ_METHODDEF
_IO_TEXTIOWRAPPER_READLINE_METHODDEF
_IO_TEXTIOWRAPPER_FLUSH_METHODDEF
_IO_TEXTIOWRAPPER_CLOSE_METHODDEF
_IO_TEXTIOWRAPPER_FILENO_METHODDEF
_IO_TEXTIOWRAPPER_SEEKABLE_METHODDEF
_IO_TEXTIOWRAPPER_READABLE_METHODDEF
_IO_TEXTIOWRAPPER_WRITABLE_METHODDEF
_IO_TEXTIOWRAPPER_ISATTY_METHODDEF
_IO_TEXTIOWRAPPER_SEEK_METHODDEF
_IO_TEXTIOWRAPPER_TELL_METHODDEF
_IO_TEXTIOWRAPPER_TRUNCATE_METHODDEF
{"__getstate__", _PyIOBase_cannot_pickle, METH_NOARGS},
{NULL, NULL}
};
static PyMemberDef textiowrapper_members[] = {
{"encoding", _Py_T_OBJECT, offsetof(textio, encoding), Py_READONLY},
{"buffer", _Py_T_OBJECT, offsetof(textio, buffer), Py_READONLY},
{"line_buffering", Py_T_BOOL, offsetof(textio, line_buffering), Py_READONLY},
{"write_through", Py_T_BOOL, offsetof(textio, write_through), Py_READONLY},
{"_finalizing", Py_T_BOOL, offsetof(textio, finalizing), 0},
{"__weaklistoffset__", Py_T_PYSSIZET, offsetof(textio, weakreflist), Py_READONLY},
{"__dictoffset__", Py_T_PYSSIZET, offsetof(textio, dict), Py_READONLY},
{NULL}
};
static PyGetSetDef textiowrapper_getset[] = {
_IO_TEXTIOWRAPPER_NAME_GETSETDEF
_IO_TEXTIOWRAPPER_CLOSED_GETSETDEF
/* {"mode", (getter)TextIOWrapper_mode_get, NULL, NULL},
*/
_IO_TEXTIOWRAPPER_NEWLINES_GETSETDEF
_IO_TEXTIOWRAPPER_ERRORS_GETSETDEF
_IO_TEXTIOWRAPPER__CHUNK_SIZE_GETSETDEF
{NULL}
};
PyType_Slot textiowrapper_slots[] = {
{Py_tp_dealloc, textiowrapper_dealloc},
{Py_tp_repr, textiowrapper_repr},
{Py_tp_doc, (void *)_io_TextIOWrapper___init____doc__},
{Py_tp_traverse, textiowrapper_traverse},
{Py_tp_clear, textiowrapper_clear},
{Py_tp_iternext, textiowrapper_iternext},
{Py_tp_methods, textiowrapper_methods},
{Py_tp_members, textiowrapper_members},
{Py_tp_getset, textiowrapper_getset},
{Py_tp_init, _io_TextIOWrapper___init__},
{0, NULL},
};
PyType_Spec textiowrapper_spec = {
.name = "_io.TextIOWrapper",
.basicsize = sizeof(textio),
.flags = (Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE | Py_TPFLAGS_HAVE_GC |
Py_TPFLAGS_IMMUTABLETYPE),
.slots = textiowrapper_slots,
};
|