1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769
|
import errno
import sys
import os
import io
from hashlib import sha256
from contextlib import contextmanager, ExitStack
from random import Random
import pathlib
import shutil
import re
import warnings
import stat
import unittest
import unittest.mock
import tarfile
from test import archiver_tests
from test import support
from test.support import os_helper
from test.support import script_helper
from test.support import warnings_helper
# Check for our compression modules.
try:
import gzip
except ImportError:
gzip = None
try:
import zlib
except ImportError:
zlib = None
try:
import bz2
except ImportError:
bz2 = None
try:
import lzma
except ImportError:
lzma = None
def sha256sum(data):
return sha256(data).hexdigest()
TEMPDIR = os.path.abspath(os_helper.TESTFN) + "-tardir"
tarextdir = TEMPDIR + '-extract-test'
tarname = support.findfile("testtar.tar", subdir="archivetestdata")
gzipname = os.path.join(TEMPDIR, "testtar.tar.gz")
bz2name = os.path.join(TEMPDIR, "testtar.tar.bz2")
xzname = os.path.join(TEMPDIR, "testtar.tar.xz")
tmpname = os.path.join(TEMPDIR, "tmp.tar")
dotlessname = os.path.join(TEMPDIR, "testtar")
SPACE = b" "
sha256_regtype = (
"e09e4bc8b3c9d9177e77256353b36c159f5f040531bbd4b024a8f9b9196c71ce"
)
sha256_sparse = (
"4f05a776071146756345ceee937b33fc5644f5a96b9780d1c7d6a32cdf164d7b"
)
class TarTest:
tarname = tarname
suffix = ''
open = io.FileIO
taropen = tarfile.TarFile.taropen
@property
def mode(self):
return self.prefix + self.suffix
@support.requires_gzip()
class GzipTest:
tarname = gzipname
suffix = 'gz'
open = gzip.GzipFile if gzip else None
taropen = tarfile.TarFile.gzopen
@support.requires_bz2()
class Bz2Test:
tarname = bz2name
suffix = 'bz2'
open = bz2.BZ2File if bz2 else None
taropen = tarfile.TarFile.bz2open
@support.requires_lzma()
class LzmaTest:
tarname = xzname
suffix = 'xz'
open = lzma.LZMAFile if lzma else None
taropen = tarfile.TarFile.xzopen
class ReadTest(TarTest):
prefix = "r:"
def setUp(self):
self.tar = tarfile.open(self.tarname, mode=self.mode,
encoding="iso8859-1")
def tearDown(self):
self.tar.close()
class StreamModeTest(ReadTest):
# Only needs to change how the tarfile is opened to set
# stream mode
def setUp(self):
self.tar = tarfile.open(self.tarname, mode=self.mode,
encoding="iso8859-1",
stream=True)
class UstarReadTest(ReadTest, unittest.TestCase):
def test_fileobj_regular_file(self):
tarinfo = self.tar.getmember("ustar/regtype")
with self.tar.extractfile(tarinfo) as fobj:
data = fobj.read()
self.assertEqual(len(data), tarinfo.size,
"regular file extraction failed")
self.assertEqual(sha256sum(data), sha256_regtype,
"regular file extraction failed")
def test_fileobj_readlines(self):
self.tar.extract("ustar/regtype", TEMPDIR, filter='data')
tarinfo = self.tar.getmember("ustar/regtype")
with open(os.path.join(TEMPDIR, "ustar/regtype"), "r") as fobj1:
lines1 = fobj1.readlines()
with self.tar.extractfile(tarinfo) as fobj:
fobj2 = io.TextIOWrapper(fobj)
lines2 = fobj2.readlines()
self.assertEqual(lines1, lines2,
"fileobj.readlines() failed")
self.assertEqual(len(lines2), 114,
"fileobj.readlines() failed")
self.assertEqual(lines2[83],
"I will gladly admit that Python is not the fastest "
"running scripting language.\n",
"fileobj.readlines() failed")
def test_fileobj_iter(self):
self.tar.extract("ustar/regtype", TEMPDIR, filter='data')
tarinfo = self.tar.getmember("ustar/regtype")
with open(os.path.join(TEMPDIR, "ustar/regtype"), "r") as fobj1:
lines1 = fobj1.readlines()
with self.tar.extractfile(tarinfo) as fobj2:
lines2 = list(io.TextIOWrapper(fobj2))
self.assertEqual(lines1, lines2,
"fileobj.__iter__() failed")
def test_fileobj_seek(self):
self.tar.extract("ustar/regtype", TEMPDIR,
filter='data')
with open(os.path.join(TEMPDIR, "ustar/regtype"), "rb") as fobj:
data = fobj.read()
tarinfo = self.tar.getmember("ustar/regtype")
with self.tar.extractfile(tarinfo) as fobj:
text = fobj.read()
fobj.seek(0)
self.assertEqual(0, fobj.tell(),
"seek() to file's start failed")
fobj.seek(2048, 0)
self.assertEqual(2048, fobj.tell(),
"seek() to absolute position failed")
fobj.seek(-1024, 1)
self.assertEqual(1024, fobj.tell(),
"seek() to negative relative position failed")
fobj.seek(1024, 1)
self.assertEqual(2048, fobj.tell(),
"seek() to positive relative position failed")
s = fobj.read(10)
self.assertEqual(s, data[2048:2058],
"read() after seek failed")
fobj.seek(0, 2)
self.assertEqual(tarinfo.size, fobj.tell(),
"seek() to file's end failed")
self.assertEqual(fobj.read(), b"",
"read() at file's end did not return empty string")
fobj.seek(-tarinfo.size, 2)
self.assertEqual(0, fobj.tell(),
"relative seek() to file's end failed")
fobj.seek(512)
s1 = fobj.readlines()
fobj.seek(512)
s2 = fobj.readlines()
self.assertEqual(s1, s2,
"readlines() after seek failed")
fobj.seek(0)
self.assertEqual(len(fobj.readline()), fobj.tell(),
"tell() after readline() failed")
fobj.seek(512)
self.assertEqual(len(fobj.readline()) + 512, fobj.tell(),
"tell() after seek() and readline() failed")
fobj.seek(0)
line = fobj.readline()
self.assertEqual(fobj.read(), data[len(line):],
"read() after readline() failed")
def test_fileobj_text(self):
with self.tar.extractfile("ustar/regtype") as fobj:
fobj = io.TextIOWrapper(fobj)
data = fobj.read().encode("iso8859-1")
self.assertEqual(sha256sum(data), sha256_regtype)
try:
fobj.seek(100)
except AttributeError:
# Issue #13815: seek() complained about a missing
# flush() method.
self.fail("seeking failed in text mode")
# Test if symbolic and hard links are resolved by extractfile(). The
# test link members each point to a regular member whose data is
# supposed to be exported.
def _test_fileobj_link(self, lnktype, regtype):
with self.tar.extractfile(lnktype) as a, \
self.tar.extractfile(regtype) as b:
self.assertEqual(a.name, b.name)
def test_fileobj_link1(self):
self._test_fileobj_link("ustar/lnktype", "ustar/regtype")
def test_fileobj_link2(self):
self._test_fileobj_link("./ustar/linktest2/lnktype",
"ustar/linktest1/regtype")
def test_fileobj_symlink1(self):
self._test_fileobj_link("ustar/symtype", "ustar/regtype")
def test_fileobj_symlink2(self):
self._test_fileobj_link("./ustar/linktest2/symtype",
"ustar/linktest1/regtype")
def test_issue14160(self):
self._test_fileobj_link("symtype2", "ustar/regtype")
def test_add_dir_getmember(self):
# bpo-21987
self.add_dir_and_getmember('bar')
self.add_dir_and_getmember('a'*101)
@unittest.skipUnless(hasattr(os, "getuid") and hasattr(os, "getgid"),
"Missing getuid or getgid implementation")
def add_dir_and_getmember(self, name):
def filter(tarinfo):
tarinfo.uid = tarinfo.gid = 100
return tarinfo
with os_helper.temp_cwd():
with tarfile.open(tmpname, 'w') as tar:
tar.format = tarfile.USTAR_FORMAT
try:
os.mkdir(name)
tar.add(name, filter=filter)
finally:
os.rmdir(name)
with tarfile.open(tmpname) as tar:
self.assertEqual(
tar.getmember(name),
tar.getmember(name + '/')
)
class GzipUstarReadTest(GzipTest, UstarReadTest):
pass
class Bz2UstarReadTest(Bz2Test, UstarReadTest):
pass
class LzmaUstarReadTest(LzmaTest, UstarReadTest):
pass
class ListTest(ReadTest, unittest.TestCase):
# Override setUp to use default encoding (UTF-8)
def setUp(self):
self.tar = tarfile.open(self.tarname, mode=self.mode)
def test_list(self):
tio = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n')
with support.swap_attr(sys, 'stdout', tio):
self.tar.list(verbose=False)
out = tio.detach().getvalue()
self.assertIn(b'ustar/conttype', out)
self.assertIn(b'ustar/regtype', out)
self.assertIn(b'ustar/lnktype', out)
self.assertIn(b'ustar' + (b'/12345' * 40) + b'67/longname', out)
self.assertIn(b'./ustar/linktest2/symtype', out)
self.assertIn(b'./ustar/linktest2/lnktype', out)
# Make sure it puts trailing slash for directory
self.assertIn(b'ustar/dirtype/', out)
self.assertIn(b'ustar/dirtype-with-size/', out)
# Make sure it is able to print unencodable characters
def conv(b):
s = b.decode(self.tar.encoding, 'surrogateescape')
return s.encode('ascii', 'backslashreplace')
self.assertIn(conv(b'ustar/umlauts-\xc4\xd6\xdc\xe4\xf6\xfc\xdf'), out)
self.assertIn(conv(b'misc/regtype-hpux-signed-chksum-'
b'\xc4\xd6\xdc\xe4\xf6\xfc\xdf'), out)
self.assertIn(conv(b'misc/regtype-old-v7-signed-chksum-'
b'\xc4\xd6\xdc\xe4\xf6\xfc\xdf'), out)
self.assertIn(conv(b'pax/bad-pax-\xe4\xf6\xfc'), out)
self.assertIn(conv(b'pax/hdrcharset-\xe4\xf6\xfc'), out)
# Make sure it prints files separated by one newline without any
# 'ls -l'-like accessories if verbose flag is not being used
# ...
# ustar/conttype
# ustar/regtype
# ...
self.assertRegex(out, br'ustar/conttype ?\r?\n'
br'ustar/regtype ?\r?\n')
# Make sure it does not print the source of link without verbose flag
self.assertNotIn(b'link to', out)
self.assertNotIn(b'->', out)
def test_list_verbose(self):
tio = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n')
with support.swap_attr(sys, 'stdout', tio):
self.tar.list(verbose=True)
out = tio.detach().getvalue()
# Make sure it prints files separated by one newline with 'ls -l'-like
# accessories if verbose flag is being used
# ...
# ?rw-r--r-- tarfile/tarfile 7011 2003-01-06 07:19:43 ustar/conttype
# -rw-r--r-- tarfile/tarfile 7011 2003-01-06 07:19:43 ustar/regtype
# drwxr-xr-x tarfile/tarfile 0 2003-01-05 15:19:43 ustar/dirtype/
# ...
#
# Array of values to modify the regex below:
# ((file_type, file_permissions, file_length), ...)
type_perm_lengths = (
(br'\?', b'rw-r--r--', b'7011'), (b'-', b'rw-r--r--', b'7011'),
(b'd', b'rwxr-xr-x', b'0'), (b'd', b'rwxr-xr-x', b'255'),
(br'\?', b'rw-r--r--', b'0'), (b'l', b'rwxrwxrwx', b'0'),
(b'b', b'rw-rw----', b'3,0'), (b'c', b'rw-rw-rw-', b'1,3'),
(b'p', b'rw-r--r--', b'0'))
self.assertRegex(out, b''.join(
[(tp + (br'%s tarfile/tarfile\s+%s ' % (perm, ln) +
br'\d{4}-\d\d-\d\d\s+\d\d:\d\d:\d\d '
br'ustar/\w+type[/>\sa-z-]*\n')) for tp, perm, ln
in type_perm_lengths]))
# Make sure it prints the source of link with verbose flag
self.assertIn(b'ustar/symtype -> regtype', out)
self.assertIn(b'./ustar/linktest2/symtype -> ../linktest1/regtype', out)
self.assertIn(b'./ustar/linktest2/lnktype link to '
b'./ustar/linktest1/regtype', out)
self.assertIn(b'gnu' + (b'/123' * 125) + b'/longlink link to gnu' +
(b'/123' * 125) + b'/longname', out)
self.assertIn(b'pax' + (b'/123' * 125) + b'/longlink link to pax' +
(b'/123' * 125) + b'/longname', out)
def test_list_members(self):
tio = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n')
def members(tar):
for tarinfo in tar.getmembers():
if 'reg' in tarinfo.name:
yield tarinfo
with support.swap_attr(sys, 'stdout', tio):
self.tar.list(verbose=False, members=members(self.tar))
out = tio.detach().getvalue()
self.assertIn(b'ustar/regtype', out)
self.assertNotIn(b'ustar/conttype', out)
class GzipListTest(GzipTest, ListTest):
pass
class Bz2ListTest(Bz2Test, ListTest):
pass
class LzmaListTest(LzmaTest, ListTest):
pass
class CommonReadTest(ReadTest):
def test_is_tarfile_erroneous(self):
with open(tmpname, "wb"):
pass
# is_tarfile works on filenames
self.assertFalse(tarfile.is_tarfile(tmpname))
# is_tarfile works on path-like objects
self.assertFalse(tarfile.is_tarfile(os_helper.FakePath(tmpname)))
# is_tarfile works on file objects
with open(tmpname, "rb") as fobj:
self.assertFalse(tarfile.is_tarfile(fobj))
# is_tarfile works on file-like objects
self.assertFalse(tarfile.is_tarfile(io.BytesIO(b"invalid")))
def test_is_tarfile_valid(self):
# is_tarfile works on filenames
self.assertTrue(tarfile.is_tarfile(self.tarname))
# is_tarfile works on path-like objects
self.assertTrue(tarfile.is_tarfile(os_helper.FakePath(self.tarname)))
# is_tarfile works on file objects
with open(self.tarname, "rb") as fobj:
self.assertTrue(tarfile.is_tarfile(fobj))
# is_tarfile works on file-like objects
with open(self.tarname, "rb") as fobj:
self.assertTrue(tarfile.is_tarfile(io.BytesIO(fobj.read())))
def test_is_tarfile_keeps_position(self):
# Test for issue44289: tarfile.is_tarfile() modifies
# file object's current position
with open(self.tarname, "rb") as fobj:
tarfile.is_tarfile(fobj)
self.assertEqual(fobj.tell(), 0)
with open(self.tarname, "rb") as fobj:
file_like = io.BytesIO(fobj.read())
tarfile.is_tarfile(file_like)
self.assertEqual(file_like.tell(), 0)
def test_empty_tarfile(self):
# Test for issue6123: Allow opening empty archives.
# This test checks if tarfile.open() is able to open an empty tar
# archive successfully. Note that an empty tar archive is not the
# same as an empty file!
with tarfile.open(tmpname, self.mode.replace("r", "w")):
pass
try:
tar = tarfile.open(tmpname, self.mode)
tar.getnames()
except tarfile.ReadError:
self.fail("tarfile.open() failed on empty archive")
else:
self.assertListEqual(tar.getmembers(), [])
finally:
tar.close()
def test_non_existent_tarfile(self):
# Test for issue11513: prevent non-existent gzipped tarfiles raising
# multiple exceptions.
with self.assertRaisesRegex(FileNotFoundError, "xxx"):
tarfile.open("xxx", self.mode)
def test_null_tarfile(self):
# Test for issue6123: Allow opening empty archives.
# This test guarantees that tarfile.open() does not treat an empty
# file as an empty tar archive.
with open(tmpname, "wb"):
pass
self.assertRaises(tarfile.ReadError, tarfile.open, tmpname, self.mode)
self.assertRaises(tarfile.ReadError, tarfile.open, tmpname)
def test_ignore_zeros(self):
# Test TarFile's ignore_zeros option.
# generate 512 pseudorandom bytes
data = Random(0).randbytes(512)
for char in (b'\0', b'a'):
# Test if EOFHeaderError ('\0') and InvalidHeaderError ('a')
# are ignored correctly.
with self.open(tmpname, "w") as fobj:
fobj.write(char * 1024)
tarinfo = tarfile.TarInfo("foo")
tarinfo.size = len(data)
fobj.write(tarinfo.tobuf())
fobj.write(data)
tar = tarfile.open(tmpname, mode="r", ignore_zeros=True)
try:
self.assertListEqual(tar.getnames(), ["foo"],
"ignore_zeros=True should have skipped the %r-blocks" %
char)
finally:
tar.close()
def test_premature_end_of_archive(self):
for size in (512, 600, 1024, 1200):
with tarfile.open(tmpname, "w:") as tar:
t = tarfile.TarInfo("foo")
t.size = 1024
tar.addfile(t, io.BytesIO(b"a" * 1024))
with open(tmpname, "r+b") as fobj:
fobj.truncate(size)
with tarfile.open(tmpname) as tar:
with self.assertRaisesRegex(tarfile.ReadError, "unexpected end of data"):
for t in tar:
pass
with tarfile.open(tmpname) as tar:
t = tar.next()
with self.assertRaisesRegex(tarfile.ReadError, "unexpected end of data"):
tar.extract(t, TEMPDIR, filter='data')
with self.assertRaisesRegex(tarfile.ReadError, "unexpected end of data"):
tar.extractfile(t).read()
def test_length_zero_header(self):
# bpo-39017 (CVE-2019-20907): reading a zero-length header should fail
# with an exception
with self.assertRaisesRegex(tarfile.ReadError, "file could not be opened successfully"):
with tarfile.open(support.findfile('recursion.tar', subdir='archivetestdata')):
pass
def test_extractfile_attrs(self):
# gh-74468: TarFile.name must name a file, not a parent archive.
file = self.tar.getmember('ustar/regtype')
with self.tar.extractfile(file) as fobj:
self.assertEqual(fobj.name, 'ustar/regtype')
self.assertRaises(AttributeError, fobj.fileno)
self.assertEqual(fobj.mode, 'rb')
self.assertIs(fobj.readable(), True)
self.assertIs(fobj.writable(), False)
if self.is_stream:
self.assertRaises(AttributeError, fobj.seekable)
else:
self.assertIs(fobj.seekable(), True)
self.assertIs(fobj.closed, False)
self.assertIs(fobj.closed, True)
self.assertEqual(fobj.name, 'ustar/regtype')
self.assertRaises(AttributeError, fobj.fileno)
self.assertEqual(fobj.mode, 'rb')
self.assertIs(fobj.readable(), True)
self.assertIs(fobj.writable(), False)
if self.is_stream:
self.assertRaises(AttributeError, fobj.seekable)
else:
self.assertIs(fobj.seekable(), True)
class MiscReadTestBase(CommonReadTest):
is_stream = False
def test_no_name_argument(self):
with open(self.tarname, "rb") as fobj:
self.assertIsInstance(fobj.name, str)
with tarfile.open(fileobj=fobj, mode=self.mode) as tar:
self.assertIsInstance(tar.name, str)
self.assertEqual(tar.name, os.path.abspath(fobj.name))
def test_no_name_attribute(self):
with open(self.tarname, "rb") as fobj:
data = fobj.read()
fobj = io.BytesIO(data)
self.assertRaises(AttributeError, getattr, fobj, "name")
tar = tarfile.open(fileobj=fobj, mode=self.mode)
self.assertIsNone(tar.name)
def test_empty_name_attribute(self):
with open(self.tarname, "rb") as fobj:
data = fobj.read()
fobj = io.BytesIO(data)
fobj.name = ""
with tarfile.open(fileobj=fobj, mode=self.mode) as tar:
self.assertIsNone(tar.name)
def test_int_name_attribute(self):
# Issue 21044: tarfile.open() should handle fileobj with an integer
# 'name' attribute.
fd = os.open(self.tarname, os.O_RDONLY)
with open(fd, 'rb') as fobj:
self.assertIsInstance(fobj.name, int)
with tarfile.open(fileobj=fobj, mode=self.mode) as tar:
self.assertIsNone(tar.name)
def test_bytes_name_attribute(self):
tarname = os.fsencode(self.tarname)
with open(tarname, 'rb') as fobj:
self.assertIsInstance(fobj.name, bytes)
with tarfile.open(fileobj=fobj, mode=self.mode) as tar:
self.assertIsInstance(tar.name, bytes)
self.assertEqual(tar.name, os.path.abspath(fobj.name))
def test_pathlike_name(self, tarname=None):
if tarname is None:
tarname = self.tarname
expected = os.path.abspath(tarname)
tarname = os_helper.FakePath(tarname)
with tarfile.open(tarname, mode=self.mode) as tar:
self.assertEqual(tar.name, expected)
with self.taropen(tarname) as tar:
self.assertEqual(tar.name, expected)
with tarfile.TarFile.open(tarname, mode=self.mode) as tar:
self.assertEqual(tar.name, expected)
if self.suffix == '':
with tarfile.TarFile(tarname, mode='r') as tar:
self.assertEqual(tar.name, expected)
def test_pathlike_bytes_name(self):
self.test_pathlike_name(os.fsencode(self.tarname))
def test_illegal_mode_arg(self):
with open(tmpname, 'wb'):
pass
with self.assertRaisesRegex(ValueError, 'mode must be '):
tar = self.taropen(tmpname, 'q')
with self.assertRaisesRegex(ValueError, 'mode must be '):
tar = self.taropen(tmpname, 'rw')
with self.assertRaisesRegex(ValueError, 'mode must be '):
tar = self.taropen(tmpname, '')
def test_fileobj_with_offset(self):
# Skip the first member and store values from the second member
# of the testtar.
tar = tarfile.open(self.tarname, mode=self.mode)
try:
tar.next()
t = tar.next()
name = t.name
offset = t.offset
with tar.extractfile(t) as f:
data = f.read()
finally:
tar.close()
# Open the testtar and seek to the offset of the second member.
with self.open(self.tarname) as fobj:
fobj.seek(offset)
# Test if the tarfile starts with the second member.
with tar.open(self.tarname, mode="r:", fileobj=fobj) as tar:
t = tar.next()
self.assertEqual(t.name, name)
# Read to the end of fileobj and test if seeking back to the
# beginning works.
tar.getmembers()
self.assertEqual(tar.extractfile(t).read(), data,
"seek back did not work")
def test_fail_comp(self):
# For Gzip and Bz2 Tests: fail with a ReadError on an uncompressed file.
self.assertRaises(tarfile.ReadError, tarfile.open, tarname, self.mode)
with open(tarname, "rb") as fobj:
self.assertRaises(tarfile.ReadError, tarfile.open,
fileobj=fobj, mode=self.mode)
def test_v7_dirtype(self):
# Test old style dirtype member (bug #1336623):
# Old V7 tars create directory members using an AREGTYPE
# header with a "/" appended to the filename field.
tarinfo = self.tar.getmember("misc/dirtype-old-v7")
self.assertEqual(tarinfo.type, tarfile.DIRTYPE,
"v7 dirtype failed")
def test_xstar_type(self):
# The xstar format stores extra atime and ctime fields inside the
# space reserved for the prefix field. The prefix field must be
# ignored in this case, otherwise it will mess up the name.
try:
self.tar.getmember("misc/regtype-xstar")
except KeyError:
self.fail("failed to find misc/regtype-xstar (mangled prefix?)")
def test_check_members(self):
for tarinfo in self.tar:
self.assertEqual(int(tarinfo.mtime), 0o7606136617,
"wrong mtime for %s" % tarinfo.name)
if not tarinfo.name.startswith("ustar/"):
continue
self.assertEqual(tarinfo.uname, "tarfile",
"wrong uname for %s" % tarinfo.name)
def test_find_members(self):
self.assertEqual(self.tar.getmembers()[-1].name, "misc/eof",
"could not find all members")
@unittest.skipUnless(hasattr(os, "link"),
"Missing hardlink implementation")
@os_helper.skip_unless_symlink
def test_extract_hardlink(self):
# Test hardlink extraction (e.g. bug #857297).
with tarfile.open(tarname, errorlevel=1, encoding="iso8859-1") as tar:
tar.extract("ustar/regtype", TEMPDIR, filter='data')
self.addCleanup(os_helper.unlink, os.path.join(TEMPDIR, "ustar/regtype"))
tar.extract("ustar/lnktype", TEMPDIR, filter='data')
self.addCleanup(os_helper.unlink, os.path.join(TEMPDIR, "ustar/lnktype"))
with open(os.path.join(TEMPDIR, "ustar/lnktype"), "rb") as f:
data = f.read()
self.assertEqual(sha256sum(data), sha256_regtype)
tar.extract("ustar/symtype", TEMPDIR, filter='data')
self.addCleanup(os_helper.unlink, os.path.join(TEMPDIR, "ustar/symtype"))
with open(os.path.join(TEMPDIR, "ustar/symtype"), "rb") as f:
data = f.read()
self.assertEqual(sha256sum(data), sha256_regtype)
@os_helper.skip_unless_working_chmod
def test_extractall(self):
# Test if extractall() correctly restores directory permissions
# and times (see issue1735).
tar = tarfile.open(tarname, encoding="iso8859-1")
DIR = os.path.join(TEMPDIR, "extractall")
os.mkdir(DIR)
try:
directories = [t for t in tar if t.isdir()]
tar.extractall(DIR, directories, filter='fully_trusted')
for tarinfo in directories:
path = os.path.join(DIR, tarinfo.name)
if sys.platform != "win32":
# Win32 has no support for fine grained permissions.
self.assertEqual(tarinfo.mode & 0o777,
os.stat(path).st_mode & 0o777,
tarinfo.name)
def format_mtime(mtime):
if isinstance(mtime, float):
return "{} ({})".format(mtime, mtime.hex())
else:
return "{!r} (int)".format(mtime)
file_mtime = os.path.getmtime(path)
errmsg = "tar mtime {0} != file time {1} of path {2!a}".format(
format_mtime(tarinfo.mtime),
format_mtime(file_mtime),
path)
self.assertEqual(tarinfo.mtime, file_mtime, errmsg)
finally:
tar.close()
os_helper.rmtree(DIR)
@os_helper.skip_unless_working_chmod
def test_extract_directory(self):
dirtype = "ustar/dirtype"
DIR = os.path.join(TEMPDIR, "extractdir")
os.mkdir(DIR)
try:
with tarfile.open(tarname, encoding="iso8859-1") as tar:
tarinfo = tar.getmember(dirtype)
tar.extract(tarinfo, path=DIR, filter='fully_trusted')
extracted = os.path.join(DIR, dirtype)
self.assertEqual(os.path.getmtime(extracted), tarinfo.mtime)
if sys.platform != "win32":
self.assertEqual(os.stat(extracted).st_mode & 0o777, 0o755)
finally:
os_helper.rmtree(DIR)
def test_deprecation_if_no_filter_passed_to_extractall(self):
DIR = pathlib.Path(TEMPDIR) / "extractall"
with (
os_helper.temp_dir(DIR),
tarfile.open(tarname, encoding="iso8859-1") as tar
):
directories = [t for t in tar if t.isdir()]
with self.assertWarnsRegex(DeprecationWarning, "Use the filter argument") as cm:
tar.extractall(DIR, directories)
# check that the stacklevel of the deprecation warning is correct:
self.assertEqual(cm.filename, __file__)
def test_deprecation_if_no_filter_passed_to_extract(self):
dirtype = "ustar/dirtype"
DIR = pathlib.Path(TEMPDIR) / "extractall"
with (
os_helper.temp_dir(DIR),
tarfile.open(tarname, encoding="iso8859-1") as tar
):
tarinfo = tar.getmember(dirtype)
with self.assertWarnsRegex(DeprecationWarning, "Use the filter argument") as cm:
tar.extract(tarinfo, path=DIR)
# check that the stacklevel of the deprecation warning is correct:
self.assertEqual(cm.filename, __file__)
def test_extractall_pathlike_dir(self):
DIR = os.path.join(TEMPDIR, "extractall")
with os_helper.temp_dir(DIR), \
tarfile.open(tarname, encoding="iso8859-1") as tar:
directories = [t for t in tar if t.isdir()]
tar.extractall(os_helper.FakePath(DIR), directories, filter='fully_trusted')
for tarinfo in directories:
path = os.path.join(DIR, tarinfo.name)
self.assertEqual(os.path.getmtime(path), tarinfo.mtime)
def test_extract_pathlike_dir(self):
dirtype = "ustar/dirtype"
DIR = os.path.join(TEMPDIR, "extractall")
with os_helper.temp_dir(DIR), \
tarfile.open(tarname, encoding="iso8859-1") as tar:
tarinfo = tar.getmember(dirtype)
tar.extract(tarinfo, path=os_helper.FakePath(DIR), filter='fully_trusted')
extracted = os.path.join(DIR, dirtype)
self.assertEqual(os.path.getmtime(extracted), tarinfo.mtime)
def test_init_close_fobj(self):
# Issue #7341: Close the internal file object in the TarFile
# constructor in case of an error. For the test we rely on
# the fact that opening an empty file raises a ReadError.
empty = os.path.join(TEMPDIR, "empty")
with open(empty, "wb") as fobj:
fobj.write(b"")
try:
tar = object.__new__(tarfile.TarFile)
try:
tar.__init__(empty)
except tarfile.ReadError:
self.assertTrue(tar.fileobj.closed)
else:
self.fail("ReadError not raised")
finally:
os_helper.unlink(empty)
def test_parallel_iteration(self):
# Issue #16601: Restarting iteration over tarfile continued
# from where it left off.
with tarfile.open(self.tarname) as tar:
for m1, m2 in zip(tar, tar):
self.assertEqual(m1.offset, m2.offset)
self.assertEqual(m1.get_info(), m2.get_info())
@unittest.skipIf(zlib is None, "requires zlib")
def test_zlib_error_does_not_leak(self):
# bpo-39039: tarfile.open allowed zlib exceptions to bubble up when
# parsing certain types of invalid data
with unittest.mock.patch("tarfile.TarInfo.fromtarfile") as mock:
mock.side_effect = zlib.error
with self.assertRaises(tarfile.ReadError):
tarfile.open(self.tarname)
def test_next_on_empty_tarfile(self):
fd = io.BytesIO()
tf = tarfile.open(fileobj=fd, mode="w")
tf.close()
fd.seek(0)
with tarfile.open(fileobj=fd, mode="r|") as tf:
self.assertEqual(tf.next(), None)
fd.seek(0)
with tarfile.open(fileobj=fd, mode="r") as tf:
self.assertEqual(tf.next(), None)
class MiscReadTest(MiscReadTestBase, unittest.TestCase):
test_fail_comp = None
class GzipMiscReadTest(GzipTest, MiscReadTestBase, unittest.TestCase):
pass
class Bz2MiscReadTest(Bz2Test, MiscReadTestBase, unittest.TestCase):
pass
class LzmaMiscReadTest(LzmaTest, MiscReadTestBase, unittest.TestCase):
pass
class StreamReadTest(CommonReadTest, unittest.TestCase):
prefix="r|"
is_stream = True
def test_read_through(self):
# Issue #11224: A poorly designed _FileInFile.read() method
# caused seeking errors with stream tar files.
for tarinfo in self.tar:
if not tarinfo.isreg():
continue
with self.tar.extractfile(tarinfo) as fobj:
while True:
try:
buf = fobj.read(512)
except tarfile.StreamError:
self.fail("simple read-through using "
"TarFile.extractfile() failed")
if not buf:
break
def test_fileobj_regular_file(self):
tarinfo = self.tar.next() # get "regtype" (can't use getmember)
with self.tar.extractfile(tarinfo) as fobj:
data = fobj.read()
self.assertEqual(len(data), tarinfo.size,
"regular file extraction failed")
self.assertEqual(sha256sum(data), sha256_regtype,
"regular file extraction failed")
def test_provoke_stream_error(self):
tarinfos = self.tar.getmembers()
with self.tar.extractfile(tarinfos[0]) as f: # read the first member
self.assertRaises(tarfile.StreamError, f.read)
def test_compare_members(self):
tar1 = tarfile.open(tarname, encoding="iso8859-1")
try:
tar2 = self.tar
while True:
t1 = tar1.next()
t2 = tar2.next()
if t1 is None:
break
self.assertIsNotNone(t2, "stream.next() failed.")
if t2.islnk() or t2.issym():
with self.assertRaises(tarfile.StreamError):
tar2.extractfile(t2)
continue
v1 = tar1.extractfile(t1)
v2 = tar2.extractfile(t2)
if v1 is None:
continue
self.assertIsNotNone(v2, "stream.extractfile() failed")
self.assertEqual(v1.read(), v2.read(),
"stream extraction failed")
finally:
tar1.close()
class GzipStreamReadTest(GzipTest, StreamReadTest):
pass
class Bz2StreamReadTest(Bz2Test, StreamReadTest):
pass
class LzmaStreamReadTest(LzmaTest, StreamReadTest):
pass
class TarStreamModeReadTest(StreamModeTest, unittest.TestCase):
def test_stream_mode_no_cache(self):
for _ in self.tar:
pass
self.assertEqual(self.tar.members, [])
class GzipStreamModeReadTest(GzipTest, TarStreamModeReadTest):
pass
class Bz2StreamModeReadTest(Bz2Test, TarStreamModeReadTest):
pass
class LzmaStreamModeReadTest(LzmaTest, TarStreamModeReadTest):
pass
class DetectReadTest(TarTest, unittest.TestCase):
def _testfunc_file(self, name, mode):
try:
tar = tarfile.open(name, mode)
except tarfile.ReadError as e:
self.fail()
else:
tar.close()
def _testfunc_fileobj(self, name, mode):
try:
with open(name, "rb") as f:
tar = tarfile.open(name, mode, fileobj=f)
except tarfile.ReadError as e:
self.fail()
else:
tar.close()
def _test_modes(self, testfunc):
if self.suffix:
with self.assertRaises(tarfile.ReadError):
tarfile.open(tarname, mode="r:" + self.suffix)
with self.assertRaises(tarfile.ReadError):
tarfile.open(tarname, mode="r|" + self.suffix)
with self.assertRaises(tarfile.ReadError):
tarfile.open(self.tarname, mode="r:")
with self.assertRaises(tarfile.ReadError):
tarfile.open(self.tarname, mode="r|")
testfunc(self.tarname, "r")
testfunc(self.tarname, "r:" + self.suffix)
testfunc(self.tarname, "r:*")
testfunc(self.tarname, "r|" + self.suffix)
testfunc(self.tarname, "r|*")
def test_detect_file(self):
self._test_modes(self._testfunc_file)
def test_detect_fileobj(self):
self._test_modes(self._testfunc_fileobj)
class GzipDetectReadTest(GzipTest, DetectReadTest):
pass
class Bz2DetectReadTest(Bz2Test, DetectReadTest):
def test_detect_stream_bz2(self):
# Originally, tarfile's stream detection looked for the string
# "BZh91" at the start of the file. This is incorrect because
# the '9' represents the blocksize (900,000 bytes). If the file was
# compressed using another blocksize autodetection fails.
with open(tarname, "rb") as fobj:
data = fobj.read()
# Compress with blocksize 100,000 bytes, the file starts with "BZh11".
with bz2.BZ2File(tmpname, "wb", compresslevel=1) as fobj:
fobj.write(data)
self._testfunc_file(tmpname, "r|*")
class LzmaDetectReadTest(LzmaTest, DetectReadTest):
pass
class GzipBrokenHeaderCorrectException(GzipTest, unittest.TestCase):
"""
See: https://github.com/python/cpython/issues/107396
"""
def runTest(self):
f = io.BytesIO(
b'\x1f\x8b' # header
b'\x08' # compression method
b'\x04' # flags
b'\0\0\0\0\0\0' # timestamp, compression data, OS ID
b'\0\x01' # size
b'\0\0\0\0\0' # corrupt data (zeros)
)
with self.assertRaises(tarfile.ReadError):
tarfile.open(fileobj=f, mode='r|gz')
class MemberReadTest(ReadTest, unittest.TestCase):
def _test_member(self, tarinfo, chksum=None, **kwargs):
if chksum is not None:
with self.tar.extractfile(tarinfo) as f:
self.assertEqual(sha256sum(f.read()), chksum,
"wrong sha256sum for %s" % tarinfo.name)
kwargs["mtime"] = 0o7606136617
kwargs["uid"] = 1000
kwargs["gid"] = 100
if "old-v7" not in tarinfo.name:
# V7 tar can't handle alphabetic owners.
kwargs["uname"] = "tarfile"
kwargs["gname"] = "tarfile"
for k, v in kwargs.items():
self.assertEqual(getattr(tarinfo, k), v,
"wrong value in %s field of %s" % (k, tarinfo.name))
def test_find_regtype(self):
tarinfo = self.tar.getmember("ustar/regtype")
self._test_member(tarinfo, size=7011, chksum=sha256_regtype)
def test_find_conttype(self):
tarinfo = self.tar.getmember("ustar/conttype")
self._test_member(tarinfo, size=7011, chksum=sha256_regtype)
def test_find_dirtype(self):
tarinfo = self.tar.getmember("ustar/dirtype")
self._test_member(tarinfo, size=0)
def test_find_dirtype_with_size(self):
tarinfo = self.tar.getmember("ustar/dirtype-with-size")
self._test_member(tarinfo, size=255)
def test_find_lnktype(self):
tarinfo = self.tar.getmember("ustar/lnktype")
self._test_member(tarinfo, size=0, linkname="ustar/regtype")
def test_find_symtype(self):
tarinfo = self.tar.getmember("ustar/symtype")
self._test_member(tarinfo, size=0, linkname="regtype")
def test_find_blktype(self):
tarinfo = self.tar.getmember("ustar/blktype")
self._test_member(tarinfo, size=0, devmajor=3, devminor=0)
def test_find_chrtype(self):
tarinfo = self.tar.getmember("ustar/chrtype")
self._test_member(tarinfo, size=0, devmajor=1, devminor=3)
def test_find_fifotype(self):
tarinfo = self.tar.getmember("ustar/fifotype")
self._test_member(tarinfo, size=0)
def test_find_sparse(self):
tarinfo = self.tar.getmember("ustar/sparse")
self._test_member(tarinfo, size=86016, chksum=sha256_sparse)
def test_find_gnusparse(self):
tarinfo = self.tar.getmember("gnu/sparse")
self._test_member(tarinfo, size=86016, chksum=sha256_sparse)
def test_find_gnusparse_00(self):
tarinfo = self.tar.getmember("gnu/sparse-0.0")
self._test_member(tarinfo, size=86016, chksum=sha256_sparse)
def test_find_gnusparse_01(self):
tarinfo = self.tar.getmember("gnu/sparse-0.1")
self._test_member(tarinfo, size=86016, chksum=sha256_sparse)
def test_find_gnusparse_10(self):
tarinfo = self.tar.getmember("gnu/sparse-1.0")
self._test_member(tarinfo, size=86016, chksum=sha256_sparse)
def test_find_umlauts(self):
tarinfo = self.tar.getmember("ustar/umlauts-"
"\xc4\xd6\xdc\xe4\xf6\xfc\xdf")
self._test_member(tarinfo, size=7011, chksum=sha256_regtype)
def test_find_ustar_longname(self):
name = "ustar/" + "12345/" * 39 + "1234567/longname"
self.assertIn(name, self.tar.getnames())
def test_find_regtype_oldv7(self):
tarinfo = self.tar.getmember("misc/regtype-old-v7")
self._test_member(tarinfo, size=7011, chksum=sha256_regtype)
def test_find_pax_umlauts(self):
self.tar.close()
self.tar = tarfile.open(self.tarname, mode=self.mode,
encoding="iso8859-1")
tarinfo = self.tar.getmember("pax/umlauts-"
"\xc4\xd6\xdc\xe4\xf6\xfc\xdf")
self._test_member(tarinfo, size=7011, chksum=sha256_regtype)
class LongnameTest:
def test_read_longname(self):
# Test reading of longname (bug #1471427).
longname = self.subdir + "/" + "123/" * 125 + "longname"
try:
tarinfo = self.tar.getmember(longname)
except KeyError:
self.fail("longname not found")
self.assertNotEqual(tarinfo.type, tarfile.DIRTYPE,
"read longname as dirtype")
def test_read_longlink(self):
longname = self.subdir + "/" + "123/" * 125 + "longname"
longlink = self.subdir + "/" + "123/" * 125 + "longlink"
try:
tarinfo = self.tar.getmember(longlink)
except KeyError:
self.fail("longlink not found")
self.assertEqual(tarinfo.linkname, longname, "linkname wrong")
def test_truncated_longname(self):
longname = self.subdir + "/" + "123/" * 125 + "longname"
tarinfo = self.tar.getmember(longname)
offset = tarinfo.offset
self.tar.fileobj.seek(offset)
fobj = io.BytesIO(self.tar.fileobj.read(3 * 512))
with self.assertRaises(tarfile.ReadError):
tarfile.open(name="foo.tar", fileobj=fobj)
def test_header_offset(self):
# Test if the start offset of the TarInfo object includes
# the preceding extended header.
longname = self.subdir + "/" + "123/" * 125 + "longname"
offset = self.tar.getmember(longname).offset
with open(tarname, "rb") as fobj:
fobj.seek(offset)
tarinfo = tarfile.TarInfo.frombuf(fobj.read(512),
"iso8859-1", "strict")
self.assertEqual(tarinfo.type, self.longnametype)
def test_longname_directory(self):
# Test reading a longlink directory. Issue #47231.
longdir = ('a' * 101) + '/'
with os_helper.temp_cwd():
with tarfile.open(tmpname, 'w') as tar:
tar.format = self.format
try:
os.mkdir(longdir)
tar.add(longdir)
finally:
os.rmdir(longdir.rstrip("/"))
with tarfile.open(tmpname) as tar:
self.assertIsNotNone(tar.getmember(longdir))
self.assertIsNotNone(tar.getmember(longdir.removesuffix('/')))
class GNUReadTest(LongnameTest, ReadTest, unittest.TestCase):
subdir = "gnu"
longnametype = tarfile.GNUTYPE_LONGNAME
format = tarfile.GNU_FORMAT
# Since 3.2 tarfile is supposed to accurately restore sparse members and
# produce files with holes. This is what we actually want to test here.
# Unfortunately, not all platforms/filesystems support sparse files, and
# even on platforms that do it is non-trivial to make reliable assertions
# about holes in files. Therefore, we first do one basic test which works
# an all platforms, and after that a test that will work only on
# platforms/filesystems that prove to support sparse files.
def _test_sparse_file(self, name):
self.tar.extract(name, TEMPDIR, filter='data')
filename = os.path.join(TEMPDIR, name)
with open(filename, "rb") as fobj:
data = fobj.read()
self.assertEqual(sha256sum(data), sha256_sparse,
"wrong sha256sum for %s" % name)
if self._fs_supports_holes():
s = os.stat(filename)
self.assertLess(s.st_blocks * 512, s.st_size)
def test_sparse_file_old(self):
self._test_sparse_file("gnu/sparse")
def test_sparse_file_00(self):
self._test_sparse_file("gnu/sparse-0.0")
def test_sparse_file_01(self):
self._test_sparse_file("gnu/sparse-0.1")
def test_sparse_file_10(self):
self._test_sparse_file("gnu/sparse-1.0")
@staticmethod
def _fs_supports_holes():
# Return True if the platform knows the st_blocks stat attribute and
# uses st_blocks units of 512 bytes, and if the filesystem is able to
# store holes of 4 KiB in files.
#
# The function returns False if page size is larger than 4 KiB.
# For example, ppc64 uses pages of 64 KiB.
if sys.platform.startswith(("linux", "android")):
# Linux evidentially has 512 byte st_blocks units.
name = os.path.join(TEMPDIR, "sparse-test")
with open(name, "wb") as fobj:
# Seek to "punch a hole" of 4 KiB
fobj.seek(4096)
fobj.write(b'x' * 4096)
fobj.truncate()
s = os.stat(name)
os_helper.unlink(name)
return (s.st_blocks * 512 < s.st_size)
else:
return False
class PaxReadTest(LongnameTest, ReadTest, unittest.TestCase):
subdir = "pax"
longnametype = tarfile.XHDTYPE
format = tarfile.PAX_FORMAT
def test_pax_global_headers(self):
tar = tarfile.open(tarname, encoding="iso8859-1")
try:
tarinfo = tar.getmember("pax/regtype1")
self.assertEqual(tarinfo.uname, "foo")
self.assertEqual(tarinfo.gname, "bar")
self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"),
"\xc4\xd6\xdc\xe4\xf6\xfc\xdf")
tarinfo = tar.getmember("pax/regtype2")
self.assertEqual(tarinfo.uname, "")
self.assertEqual(tarinfo.gname, "bar")
self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"),
"\xc4\xd6\xdc\xe4\xf6\xfc\xdf")
tarinfo = tar.getmember("pax/regtype3")
self.assertEqual(tarinfo.uname, "tarfile")
self.assertEqual(tarinfo.gname, "tarfile")
self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"),
"\xc4\xd6\xdc\xe4\xf6\xfc\xdf")
finally:
tar.close()
def test_pax_number_fields(self):
# All following number fields are read from the pax header.
tar = tarfile.open(tarname, encoding="iso8859-1")
try:
tarinfo = tar.getmember("pax/regtype4")
self.assertEqual(tarinfo.size, 7011)
self.assertEqual(tarinfo.uid, 123)
self.assertEqual(tarinfo.gid, 123)
self.assertEqual(tarinfo.mtime, 1041808783.0)
self.assertEqual(type(tarinfo.mtime), float)
self.assertEqual(float(tarinfo.pax_headers["atime"]), 1041808783.0)
self.assertEqual(float(tarinfo.pax_headers["ctime"]), 1041808783.0)
finally:
tar.close()
def test_pax_header_bad_formats(self):
# The fields from the pax header have priority over the
# TarInfo.
pax_header_replacements = (
b" foo=bar\n",
b"0 \n",
b"1 \n",
b"2 \n",
b"3 =\n",
b"4 =a\n",
b"1000000 foo=bar\n",
b"0 foo=bar\n",
b"-12 foo=bar\n",
b"000000000000000000000000036 foo=bar\n",
)
pax_headers = {"foo": "bar"}
for replacement in pax_header_replacements:
with self.subTest(header=replacement):
tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT,
encoding="iso8859-1")
try:
t = tarfile.TarInfo()
t.name = "pax" # non-ASCII
t.uid = 1
t.pax_headers = pax_headers
tar.addfile(t)
finally:
tar.close()
with open(tmpname, "rb") as f:
data = f.read()
self.assertIn(b"11 foo=bar\n", data)
data = data.replace(b"11 foo=bar\n", replacement)
with open(tmpname, "wb") as f:
f.truncate()
f.write(data)
with self.assertRaisesRegex(tarfile.ReadError, r"method tar: ReadError\('invalid header'\)"):
tarfile.open(tmpname, encoding="iso8859-1")
class WriteTestBase(TarTest):
# Put all write tests in here that are supposed to be tested
# in all possible mode combinations.
def test_fileobj_no_close(self):
fobj = io.BytesIO()
with tarfile.open(fileobj=fobj, mode=self.mode) as tar:
tar.addfile(tarfile.TarInfo("foo"))
self.assertFalse(fobj.closed, "external fileobjs must never closed")
# Issue #20238: Incomplete gzip output with mode="w:gz"
data = fobj.getvalue()
del tar
support.gc_collect()
self.assertFalse(fobj.closed)
self.assertEqual(data, fobj.getvalue())
def test_eof_marker(self):
# Make sure an end of archive marker is written (two zero blocks).
# tarfile insists on aligning archives to a 20 * 512 byte recordsize.
# So, we create an archive that has exactly 10240 bytes without the
# marker, and has 20480 bytes once the marker is written.
with tarfile.open(tmpname, self.mode) as tar:
t = tarfile.TarInfo("foo")
t.size = tarfile.RECORDSIZE - tarfile.BLOCKSIZE
tar.addfile(t, io.BytesIO(b"a" * t.size))
with self.open(tmpname, "rb") as fobj:
self.assertEqual(len(fobj.read()), tarfile.RECORDSIZE * 2)
class WriteTest(WriteTestBase, unittest.TestCase):
prefix = "w:"
def test_100_char_name(self):
# The name field in a tar header stores strings of at most 100 chars.
# If a string is shorter than 100 chars it has to be padded with '\0',
# which implies that a string of exactly 100 chars is stored without
# a trailing '\0'.
name = "0123456789" * 10
tar = tarfile.open(tmpname, self.mode)
try:
t = tarfile.TarInfo(name)
tar.addfile(t)
finally:
tar.close()
tar = tarfile.open(tmpname)
try:
self.assertEqual(tar.getnames()[0], name,
"failed to store 100 char filename")
finally:
tar.close()
def test_tar_size(self):
# Test for bug #1013882.
tar = tarfile.open(tmpname, self.mode)
try:
path = os.path.join(TEMPDIR, "file")
with open(path, "wb") as fobj:
fobj.write(b"aaa")
tar.add(path)
finally:
tar.close()
self.assertGreater(os.path.getsize(tmpname), 0,
"tarfile is empty")
# The test_*_size tests test for bug #1167128.
def test_file_size(self):
tar = tarfile.open(tmpname, self.mode)
try:
path = os.path.join(TEMPDIR, "file")
with open(path, "wb"):
pass
tarinfo = tar.gettarinfo(path)
self.assertEqual(tarinfo.size, 0)
with open(path, "wb") as fobj:
fobj.write(b"aaa")
tarinfo = tar.gettarinfo(path)
self.assertEqual(tarinfo.size, 3)
finally:
tar.close()
def test_directory_size(self):
path = os.path.join(TEMPDIR, "directory")
os.mkdir(path)
try:
tar = tarfile.open(tmpname, self.mode)
try:
tarinfo = tar.gettarinfo(path)
self.assertEqual(tarinfo.size, 0)
finally:
tar.close()
finally:
os_helper.rmdir(path)
# mock the following:
# os.listdir: so we know that files are in the wrong order
def test_ordered_recursion(self):
path = os.path.join(TEMPDIR, "directory")
os.mkdir(path)
open(os.path.join(path, "1"), "a").close()
open(os.path.join(path, "2"), "a").close()
try:
tar = tarfile.open(tmpname, self.mode)
try:
with unittest.mock.patch('os.listdir') as mock_listdir:
mock_listdir.return_value = ["2", "1"]
tar.add(path)
paths = []
for m in tar.getmembers():
paths.append(os.path.split(m.name)[-1])
self.assertEqual(paths, ["directory", "1", "2"]);
finally:
tar.close()
finally:
os_helper.unlink(os.path.join(path, "1"))
os_helper.unlink(os.path.join(path, "2"))
os_helper.rmdir(path)
def test_gettarinfo_pathlike_name(self):
with tarfile.open(tmpname, self.mode) as tar:
path = os.path.join(TEMPDIR, "file")
with open(path, "wb") as fobj:
fobj.write(b"aaa")
tarinfo = tar.gettarinfo(os_helper.FakePath(path))
tarinfo2 = tar.gettarinfo(path)
self.assertIsInstance(tarinfo.name, str)
self.assertEqual(tarinfo.name, tarinfo2.name)
self.assertEqual(tarinfo.size, 3)
@unittest.skipUnless(hasattr(os, "link"),
"Missing hardlink implementation")
def test_link_size(self):
link = os.path.join(TEMPDIR, "link")
target = os.path.join(TEMPDIR, "link_target")
with open(target, "wb") as fobj:
fobj.write(b"aaa")
try:
os.link(target, link)
except PermissionError as e:
self.skipTest('os.link(): %s' % e)
try:
tar = tarfile.open(tmpname, self.mode)
try:
# Record the link target in the inodes list.
tar.gettarinfo(target)
tarinfo = tar.gettarinfo(link)
self.assertEqual(tarinfo.size, 0)
finally:
tar.close()
finally:
os_helper.unlink(target)
os_helper.unlink(link)
@os_helper.skip_unless_symlink
def test_symlink_size(self):
path = os.path.join(TEMPDIR, "symlink")
os.symlink("link_target", path)
try:
tar = tarfile.open(tmpname, self.mode)
try:
tarinfo = tar.gettarinfo(path)
self.assertEqual(tarinfo.size, 0)
finally:
tar.close()
finally:
os_helper.unlink(path)
def test_add_self(self):
# Test for #1257255.
dstname = os.path.abspath(tmpname)
tar = tarfile.open(tmpname, self.mode)
try:
self.assertEqual(tar.name, dstname,
"archive name must be absolute")
tar.add(dstname)
self.assertEqual(tar.getnames(), [],
"added the archive to itself")
with os_helper.change_cwd(TEMPDIR):
tar.add(dstname)
self.assertEqual(tar.getnames(), [],
"added the archive to itself")
finally:
tar.close()
def test_filter(self):
tempdir = os.path.join(TEMPDIR, "filter")
os.mkdir(tempdir)
try:
for name in ("foo", "bar", "baz"):
name = os.path.join(tempdir, name)
os_helper.create_empty_file(name)
def filter(tarinfo):
if os.path.basename(tarinfo.name) == "bar":
return
tarinfo.uid = 123
tarinfo.uname = "foo"
return tarinfo
tar = tarfile.open(tmpname, self.mode, encoding="iso8859-1")
try:
tar.add(tempdir, arcname="empty_dir", filter=filter)
finally:
tar.close()
# Verify that filter is a keyword-only argument
with self.assertRaises(TypeError):
tar.add(tempdir, "empty_dir", True, None, filter)
tar = tarfile.open(tmpname, "r")
try:
for tarinfo in tar:
self.assertEqual(tarinfo.uid, 123)
self.assertEqual(tarinfo.uname, "foo")
self.assertEqual(len(tar.getmembers()), 3)
finally:
tar.close()
finally:
os_helper.rmtree(tempdir)
# Guarantee that stored pathnames are not modified. Don't
# remove ./ or ../ or double slashes. Still make absolute
# pathnames relative.
# For details see bug #6054.
def _test_pathname(self, path, cmp_path=None, dir=False):
# Create a tarfile with an empty member named path
# and compare the stored name with the original.
foo = os.path.join(TEMPDIR, "foo")
if not dir:
os_helper.create_empty_file(foo)
else:
os.mkdir(foo)
tar = tarfile.open(tmpname, self.mode)
try:
tar.add(foo, arcname=path)
finally:
tar.close()
tar = tarfile.open(tmpname, "r")
try:
t = tar.next()
finally:
tar.close()
if not dir:
os_helper.unlink(foo)
else:
os_helper.rmdir(foo)
self.assertEqual(t.name, cmp_path or path.replace(os.sep, "/"))
@os_helper.skip_unless_symlink
def test_extractall_symlinks(self):
# Test if extractall works properly when tarfile contains symlinks
tempdir = os.path.join(TEMPDIR, "testsymlinks")
temparchive = os.path.join(TEMPDIR, "testsymlinks.tar")
os.mkdir(tempdir)
try:
source_file = os.path.join(tempdir,'source')
target_file = os.path.join(tempdir,'symlink')
with open(source_file,'w') as f:
f.write('something\n')
os.symlink(source_file, target_file)
with tarfile.open(temparchive, 'w') as tar:
tar.add(source_file, arcname="source")
tar.add(target_file, arcname="symlink")
# Let's extract it to the location which contains the symlink
with tarfile.open(temparchive, errorlevel=2) as tar:
# this should not raise OSError: [Errno 17] File exists
try:
tar.extractall(path=tempdir,
filter='fully_trusted')
except OSError:
self.fail("extractall failed with symlinked files")
finally:
os_helper.unlink(temparchive)
os_helper.rmtree(tempdir)
def test_pathnames(self):
self._test_pathname("foo")
self._test_pathname(os.path.join("foo", ".", "bar"))
self._test_pathname(os.path.join("foo", "..", "bar"))
self._test_pathname(os.path.join(".", "foo"))
self._test_pathname(os.path.join(".", "foo", "."))
self._test_pathname(os.path.join(".", "foo", ".", "bar"))
self._test_pathname(os.path.join(".", "foo", "..", "bar"))
self._test_pathname(os.path.join(".", "foo", "..", "bar"))
self._test_pathname(os.path.join("..", "foo"))
self._test_pathname(os.path.join("..", "foo", ".."))
self._test_pathname(os.path.join("..", "foo", ".", "bar"))
self._test_pathname(os.path.join("..", "foo", "..", "bar"))
self._test_pathname("foo" + os.sep + os.sep + "bar")
self._test_pathname("foo" + os.sep + os.sep, "foo", dir=True)
def test_abs_pathnames(self):
if sys.platform == "win32":
self._test_pathname("C:\\foo", "foo")
else:
self._test_pathname("/foo", "foo")
self._test_pathname("///foo", "foo")
def test_cwd(self):
# Test adding the current working directory.
with os_helper.change_cwd(TEMPDIR):
tar = tarfile.open(tmpname, self.mode)
try:
tar.add(".")
finally:
tar.close()
tar = tarfile.open(tmpname, "r")
try:
for t in tar:
if t.name != ".":
self.assertTrue(t.name.startswith("./"), t.name)
finally:
tar.close()
def test_open_nonwritable_fileobj(self):
for exctype in OSError, EOFError, RuntimeError:
class BadFile(io.BytesIO):
first = True
def write(self, data):
if self.first:
self.first = False
raise exctype
f = BadFile()
with (
warnings_helper.check_no_resource_warning(self),
self.assertRaises(exctype),
):
tarfile.open(tmpname, self.mode, fileobj=f,
format=tarfile.PAX_FORMAT,
pax_headers={'non': 'empty'})
self.assertFalse(f.closed)
def test_missing_fileobj(self):
with tarfile.open(tmpname, self.mode) as tar:
tarinfo = tar.gettarinfo(tarname)
with self.assertRaises(ValueError):
tar.addfile(tarinfo)
class GzipWriteTest(GzipTest, WriteTest):
pass
class Bz2WriteTest(Bz2Test, WriteTest):
pass
class LzmaWriteTest(LzmaTest, WriteTest):
pass
class StreamWriteTest(WriteTestBase, unittest.TestCase):
prefix = "w|"
decompressor = None
def test_stream_padding(self):
# Test for bug #1543303.
tar = tarfile.open(tmpname, self.mode)
tar.close()
if self.decompressor:
dec = self.decompressor()
with open(tmpname, "rb") as fobj:
data = fobj.read()
data = dec.decompress(data)
self.assertFalse(dec.unused_data, "found trailing data")
else:
with self.open(tmpname) as fobj:
data = fobj.read()
self.assertEqual(data.count(b"\0"), tarfile.RECORDSIZE,
"incorrect zero padding")
@unittest.skipUnless(sys.platform != "win32" and hasattr(os, "umask"),
"Missing umask implementation")
@unittest.skipIf(
support.is_emscripten or support.is_wasi,
"Emscripten's/WASI's umask is a stub."
)
def test_file_mode(self):
# Test for issue #8464: Create files with correct
# permissions.
if os.path.exists(tmpname):
os_helper.unlink(tmpname)
original_umask = os.umask(0o022)
try:
tar = tarfile.open(tmpname, self.mode)
tar.close()
mode = os.stat(tmpname).st_mode & 0o777
self.assertEqual(mode, 0o644, "wrong file permissions")
finally:
os.umask(original_umask)
def test_pathlike_name(self):
expected_name = os.path.abspath(tmpname)
tarpath = os_helper.FakePath(tmpname)
for func in (tarfile.open, tarfile.TarFile.open):
with self.subTest():
with func(tarpath, self.mode) as tar:
self.assertEqual(tar.name, expected_name)
os_helper.unlink(tmpname)
class GzipStreamWriteTest(GzipTest, StreamWriteTest):
def test_source_directory_not_leaked(self):
"""
Ensure the source directory is not included in the tar header
per bpo-41316.
"""
tarfile.open(tmpname, self.mode).close()
payload = pathlib.Path(tmpname).read_text(encoding='latin-1')
assert os.path.dirname(tmpname) not in payload
class Bz2StreamWriteTest(Bz2Test, StreamWriteTest):
decompressor = bz2.BZ2Decompressor if bz2 else None
class LzmaStreamWriteTest(LzmaTest, StreamWriteTest):
decompressor = lzma.LZMADecompressor if lzma else None
class _CompressedWriteTest(TarTest):
# This is not actually a standalone test.
# It does not inherit WriteTest because it only makes sense with gz,bz2
source = (b"And we move to Bristol where they have a special, " +
b"Very Silly candidate")
def _compressed_tar(self, compresslevel):
fobj = io.BytesIO()
with tarfile.open(tmpname, self.mode, fobj,
compresslevel=compresslevel) as tarfl:
tarfl.addfile(tarfile.TarInfo("foo"), io.BytesIO(self.source))
return fobj
def _test_bz2_header(self, compresslevel):
fobj = self._compressed_tar(compresslevel)
self.assertEqual(fobj.getvalue()[0:10],
b"BZh%d1AY&SY" % compresslevel)
def _test_gz_header(self, compresslevel):
fobj = self._compressed_tar(compresslevel)
self.assertEqual(fobj.getvalue()[:3], b"\x1f\x8b\x08")
class Bz2CompressWriteTest(Bz2Test, _CompressedWriteTest, unittest.TestCase):
prefix = "w:"
def test_compression_levels(self):
self._test_bz2_header(1)
self._test_bz2_header(5)
self._test_bz2_header(9)
class Bz2CompressStreamWriteTest(Bz2Test, _CompressedWriteTest,
unittest.TestCase):
prefix = "w|"
def test_compression_levels(self):
self._test_bz2_header(1)
self._test_bz2_header(5)
self._test_bz2_header(9)
class GzCompressWriteTest(GzipTest, _CompressedWriteTest, unittest.TestCase):
prefix = "w:"
def test_compression_levels(self):
self._test_gz_header(1)
self._test_gz_header(5)
self._test_gz_header(9)
class GzCompressStreamWriteTest(GzipTest, _CompressedWriteTest,
unittest.TestCase):
prefix = "w|"
def test_compression_levels(self):
self._test_gz_header(1)
self._test_gz_header(5)
self._test_gz_header(9)
class CompressLevelRaises(unittest.TestCase):
def test_compresslevel_wrong_modes(self):
compresslevel = 5
fobj = io.BytesIO()
with self.assertRaises(TypeError):
tarfile.open(tmpname, "w:", fobj, compresslevel=compresslevel)
@support.requires_bz2()
def test_wrong_compresslevels(self):
# BZ2 checks that the compresslevel is in [1,9]. gz does not
fobj = io.BytesIO()
with self.assertRaises(ValueError):
tarfile.open(tmpname, "w:bz2", fobj, compresslevel=0)
with self.assertRaises(ValueError):
tarfile.open(tmpname, "w:bz2", fobj, compresslevel=10)
with self.assertRaises(ValueError):
tarfile.open(tmpname, "w|bz2", fobj, compresslevel=10)
class GNUWriteTest(unittest.TestCase):
# This testcase checks for correct creation of GNU Longname
# and Longlink extended headers (cp. bug #812325).
def _length(self, s):
blocks = len(s) // 512 + 1
return blocks * 512
def _calc_size(self, name, link=None):
# Initial tar header
count = 512
if len(name) > tarfile.LENGTH_NAME:
# GNU longname extended header + longname
count += 512
count += self._length(name)
if link is not None and len(link) > tarfile.LENGTH_LINK:
# GNU longlink extended header + longlink
count += 512
count += self._length(link)
return count
def _test(self, name, link=None):
tarinfo = tarfile.TarInfo(name)
if link:
tarinfo.linkname = link
tarinfo.type = tarfile.LNKTYPE
tar = tarfile.open(tmpname, "w")
try:
tar.format = tarfile.GNU_FORMAT
tar.addfile(tarinfo)
v1 = self._calc_size(name, link)
v2 = tar.offset
self.assertEqual(v1, v2, "GNU longname/longlink creation failed")
finally:
tar.close()
tar = tarfile.open(tmpname)
try:
member = tar.next()
self.assertIsNotNone(member,
"unable to read longname member")
self.assertEqual(tarinfo.name, member.name,
"unable to read longname member")
self.assertEqual(tarinfo.linkname, member.linkname,
"unable to read longname member")
finally:
tar.close()
def test_longname_1023(self):
self._test(("longnam/" * 127) + "longnam")
def test_longname_1024(self):
self._test(("longnam/" * 127) + "longname")
def test_longname_1025(self):
self._test(("longnam/" * 127) + "longname_")
def test_longlink_1023(self):
self._test("name", ("longlnk/" * 127) + "longlnk")
def test_longlink_1024(self):
self._test("name", ("longlnk/" * 127) + "longlink")
def test_longlink_1025(self):
self._test("name", ("longlnk/" * 127) + "longlink_")
def test_longnamelink_1023(self):
self._test(("longnam/" * 127) + "longnam",
("longlnk/" * 127) + "longlnk")
def test_longnamelink_1024(self):
self._test(("longnam/" * 127) + "longname",
("longlnk/" * 127) + "longlink")
def test_longnamelink_1025(self):
self._test(("longnam/" * 127) + "longname_",
("longlnk/" * 127) + "longlink_")
class DeviceHeaderTest(WriteTestBase, unittest.TestCase):
prefix = "w:"
def test_headers_written_only_for_device_files(self):
# Regression test for bpo-18819.
tempdir = os.path.join(TEMPDIR, "device_header_test")
os.mkdir(tempdir)
try:
tar = tarfile.open(tmpname, self.mode)
try:
input_blk = tarfile.TarInfo(name="my_block_device")
input_reg = tarfile.TarInfo(name="my_regular_file")
input_blk.type = tarfile.BLKTYPE
input_reg.type = tarfile.REGTYPE
tar.addfile(input_blk)
tar.addfile(input_reg)
finally:
tar.close()
# devmajor and devminor should be *interpreted* as 0 in both...
tar = tarfile.open(tmpname, "r")
try:
output_blk = tar.getmember("my_block_device")
output_reg = tar.getmember("my_regular_file")
finally:
tar.close()
self.assertEqual(output_blk.devmajor, 0)
self.assertEqual(output_blk.devminor, 0)
self.assertEqual(output_reg.devmajor, 0)
self.assertEqual(output_reg.devminor, 0)
# ...but the fields should not actually be set on regular files:
with open(tmpname, "rb") as infile:
buf = infile.read()
buf_blk = buf[output_blk.offset:output_blk.offset_data]
buf_reg = buf[output_reg.offset:output_reg.offset_data]
# See `struct posixheader` in GNU docs for byte offsets:
# <https://www.gnu.org/software/tar/manual/html_node/Standard.html>
device_headers = slice(329, 329 + 16)
self.assertEqual(buf_blk[device_headers], b"0000000\0" * 2)
self.assertEqual(buf_reg[device_headers], b"\0" * 16)
finally:
os_helper.rmtree(tempdir)
class CreateTest(WriteTestBase, unittest.TestCase):
prefix = "x:"
file_path = os.path.join(TEMPDIR, "spameggs42")
def setUp(self):
os_helper.unlink(tmpname)
@classmethod
def setUpClass(cls):
with open(cls.file_path, "wb") as fobj:
fobj.write(b"aaa")
@classmethod
def tearDownClass(cls):
os_helper.unlink(cls.file_path)
def test_create(self):
with tarfile.open(tmpname, self.mode) as tobj:
tobj.add(self.file_path)
with self.taropen(tmpname) as tobj:
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
def test_create_existing(self):
with tarfile.open(tmpname, self.mode) as tobj:
tobj.add(self.file_path)
with self.assertRaises(FileExistsError):
tobj = tarfile.open(tmpname, self.mode)
with self.taropen(tmpname) as tobj:
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
def test_create_taropen(self):
with self.taropen(tmpname, "x") as tobj:
tobj.add(self.file_path)
with self.taropen(tmpname) as tobj:
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
def test_create_existing_taropen(self):
with self.taropen(tmpname, "x") as tobj:
tobj.add(self.file_path)
with self.assertRaises(FileExistsError):
with self.taropen(tmpname, "x"):
pass
with self.taropen(tmpname) as tobj:
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn("spameggs42", names[0])
def test_create_pathlike_name(self):
with tarfile.open(os_helper.FakePath(tmpname), self.mode) as tobj:
self.assertIsInstance(tobj.name, str)
self.assertEqual(tobj.name, os.path.abspath(tmpname))
tobj.add(os_helper.FakePath(self.file_path))
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
with self.taropen(tmpname) as tobj:
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
def test_create_taropen_pathlike_name(self):
with self.taropen(os_helper.FakePath(tmpname), "x") as tobj:
self.assertIsInstance(tobj.name, str)
self.assertEqual(tobj.name, os.path.abspath(tmpname))
tobj.add(os_helper.FakePath(self.file_path))
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
with self.taropen(tmpname) as tobj:
names = tobj.getnames()
self.assertEqual(len(names), 1)
self.assertIn('spameggs42', names[0])
class GzipCreateTest(GzipTest, CreateTest):
def test_create_with_compresslevel(self):
with tarfile.open(tmpname, self.mode, compresslevel=1) as tobj:
tobj.add(self.file_path)
with tarfile.open(tmpname, 'r:gz', compresslevel=1) as tobj:
pass
class Bz2CreateTest(Bz2Test, CreateTest):
def test_create_with_compresslevel(self):
with tarfile.open(tmpname, self.mode, compresslevel=1) as tobj:
tobj.add(self.file_path)
with tarfile.open(tmpname, 'r:bz2', compresslevel=1) as tobj:
pass
class LzmaCreateTest(LzmaTest, CreateTest):
# Unlike gz and bz2, xz uses the preset keyword instead of compresslevel.
# It does not allow for preset to be specified when reading.
def test_create_with_preset(self):
with tarfile.open(tmpname, self.mode, preset=1) as tobj:
tobj.add(self.file_path)
class CreateWithXModeTest(CreateTest):
prefix = "x"
test_create_taropen = None
test_create_existing_taropen = None
@unittest.skipUnless(hasattr(os, "link"), "Missing hardlink implementation")
class HardlinkTest(unittest.TestCase):
# Test the creation of LNKTYPE (hardlink) members in an archive.
def setUp(self):
self.foo = os.path.join(TEMPDIR, "foo")
self.bar = os.path.join(TEMPDIR, "bar")
with open(self.foo, "wb") as fobj:
fobj.write(b"foo")
try:
os.link(self.foo, self.bar)
except PermissionError as e:
self.skipTest('os.link(): %s' % e)
self.tar = tarfile.open(tmpname, "w")
self.tar.add(self.foo)
def tearDown(self):
self.tar.close()
os_helper.unlink(self.foo)
os_helper.unlink(self.bar)
def test_add_twice(self):
# The same name will be added as a REGTYPE every
# time regardless of st_nlink.
tarinfo = self.tar.gettarinfo(self.foo)
self.assertEqual(tarinfo.type, tarfile.REGTYPE,
"add file as regular failed")
def test_add_hardlink(self):
tarinfo = self.tar.gettarinfo(self.bar)
self.assertEqual(tarinfo.type, tarfile.LNKTYPE,
"add file as hardlink failed")
def test_dereference_hardlink(self):
self.tar.dereference = True
tarinfo = self.tar.gettarinfo(self.bar)
self.assertEqual(tarinfo.type, tarfile.REGTYPE,
"dereferencing hardlink failed")
class PaxWriteTest(GNUWriteTest):
def _test(self, name, link=None):
# See GNUWriteTest.
tarinfo = tarfile.TarInfo(name)
if link:
tarinfo.linkname = link
tarinfo.type = tarfile.LNKTYPE
tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT)
try:
tar.addfile(tarinfo)
finally:
tar.close()
tar = tarfile.open(tmpname)
try:
if link:
l = tar.getmembers()[0].linkname
self.assertEqual(link, l, "PAX longlink creation failed")
else:
n = tar.getmembers()[0].name
self.assertEqual(name, n, "PAX longname creation failed")
finally:
tar.close()
def test_pax_global_header(self):
pax_headers = {
"foo": "bar",
"uid": "0",
"mtime": "1.23",
"test": "\xe4\xf6\xfc",
"\xe4\xf6\xfc": "test"}
tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT,
pax_headers=pax_headers)
try:
tar.addfile(tarfile.TarInfo("test"))
finally:
tar.close()
# Test if the global header was written correctly.
tar = tarfile.open(tmpname, encoding="iso8859-1")
try:
self.assertEqual(tar.pax_headers, pax_headers)
self.assertEqual(tar.getmembers()[0].pax_headers, pax_headers)
# Test if all the fields are strings.
for key, val in tar.pax_headers.items():
self.assertIsNot(type(key), bytes)
self.assertIsNot(type(val), bytes)
if key in tarfile.PAX_NUMBER_FIELDS:
try:
tarfile.PAX_NUMBER_FIELDS[key](val)
except (TypeError, ValueError):
self.fail("unable to convert pax header field")
finally:
tar.close()
def test_pax_extended_header(self):
# The fields from the pax header have priority over the
# TarInfo.
pax_headers = {"path": "foo", "uid": "123"}
tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT,
encoding="iso8859-1")
try:
t = tarfile.TarInfo()
t.name = "\xe4\xf6\xfc" # non-ASCII
t.uid = 8**8 # too large
t.pax_headers = pax_headers
tar.addfile(t)
finally:
tar.close()
tar = tarfile.open(tmpname, encoding="iso8859-1")
try:
t = tar.getmembers()[0]
self.assertEqual(t.pax_headers, pax_headers)
self.assertEqual(t.name, "foo")
self.assertEqual(t.uid, 123)
finally:
tar.close()
def test_create_pax_header(self):
# The ustar header should contain values that can be
# represented reasonably, even if a better (e.g. higher
# precision) version is set in the pax header.
# Issue #45863
# values that should be kept
t = tarfile.TarInfo()
t.name = "foo"
t.mtime = 1000.1
t.size = 100
t.uid = 123
t.gid = 124
info = t.get_info()
header = t.create_pax_header(info, encoding="iso8859-1")
self.assertEqual(info['name'], "foo")
# mtime should be rounded to nearest second
self.assertIsInstance(info['mtime'], int)
self.assertEqual(info['mtime'], 1000)
self.assertEqual(info['size'], 100)
self.assertEqual(info['uid'], 123)
self.assertEqual(info['gid'], 124)
self.assertEqual(header,
b'././@PaxHeader' + bytes(86) \
+ b'0000000\x000000000\x000000000\x0000000000020\x0000000000000\x00010205\x00 x' \
+ bytes(100) + b'ustar\x0000'+ bytes(247) \
+ b'16 mtime=1000.1\n' + bytes(496) + b'foo' + bytes(97) \
+ b'0000644\x000000173\x000000174\x0000000000144\x0000000001750\x00006516\x00 0' \
+ bytes(100) + b'ustar\x0000' + bytes(247))
# values that should be changed
t = tarfile.TarInfo()
t.name = "foo\u3374" # can't be represented in ascii
t.mtime = 10**10 # too big
t.size = 10**10 # too big
t.uid = 8**8 # too big
t.gid = 8**8+1 # too big
info = t.get_info()
header = t.create_pax_header(info, encoding="iso8859-1")
# name is kept as-is in info but should be added to pax header
self.assertEqual(info['name'], "foo\u3374")
self.assertEqual(info['mtime'], 0)
self.assertEqual(info['size'], 0)
self.assertEqual(info['uid'], 0)
self.assertEqual(info['gid'], 0)
self.assertEqual(header,
b'././@PaxHeader' + bytes(86) \
+ b'0000000\x000000000\x000000000\x0000000000130\x0000000000000\x00010207\x00 x' \
+ bytes(100) + b'ustar\x0000' + bytes(247) \
+ b'15 path=foo\xe3\x8d\xb4\n16 uid=16777216\n' \
+ b'16 gid=16777217\n20 size=10000000000\n' \
+ b'21 mtime=10000000000\n'+ bytes(424) + b'foo?' + bytes(96) \
+ b'0000644\x000000000\x000000000\x0000000000000\x0000000000000\x00006540\x00 0' \
+ bytes(100) + b'ustar\x0000' + bytes(247))
class UnicodeTest:
def test_iso8859_1_filename(self):
self._test_unicode_filename("iso8859-1")
def test_utf7_filename(self):
self._test_unicode_filename("utf7")
def test_utf8_filename(self):
self._test_unicode_filename("utf-8")
def _test_unicode_filename(self, encoding):
tar = tarfile.open(tmpname, "w", format=self.format,
encoding=encoding, errors="strict")
try:
name = "\xe4\xf6\xfc"
tar.addfile(tarfile.TarInfo(name))
finally:
tar.close()
tar = tarfile.open(tmpname, encoding=encoding)
try:
self.assertEqual(tar.getmembers()[0].name, name)
finally:
tar.close()
def test_unicode_filename_error(self):
tar = tarfile.open(tmpname, "w", format=self.format,
encoding="ascii", errors="strict")
try:
tarinfo = tarfile.TarInfo()
tarinfo.name = "\xe4\xf6\xfc"
self.assertRaises(UnicodeError, tar.addfile, tarinfo)
tarinfo.name = "foo"
tarinfo.uname = "\xe4\xf6\xfc"
self.assertRaises(UnicodeError, tar.addfile, tarinfo)
finally:
tar.close()
def test_unicode_argument(self):
tar = tarfile.open(tarname, "r",
encoding="iso8859-1", errors="strict")
try:
for t in tar:
self.assertIs(type(t.name), str)
self.assertIs(type(t.linkname), str)
self.assertIs(type(t.uname), str)
self.assertIs(type(t.gname), str)
finally:
tar.close()
def test_uname_unicode(self):
t = tarfile.TarInfo("foo")
t.uname = "\xe4\xf6\xfc"
t.gname = "\xe4\xf6\xfc"
tar = tarfile.open(tmpname, mode="w", format=self.format,
encoding="iso8859-1")
try:
tar.addfile(t)
finally:
tar.close()
tar = tarfile.open(tmpname, encoding="iso8859-1")
try:
t = tar.getmember("foo")
self.assertEqual(t.uname, "\xe4\xf6\xfc")
self.assertEqual(t.gname, "\xe4\xf6\xfc")
if self.format != tarfile.PAX_FORMAT:
tar.close()
tar = tarfile.open(tmpname, encoding="ascii")
t = tar.getmember("foo")
self.assertEqual(t.uname, "\udce4\udcf6\udcfc")
self.assertEqual(t.gname, "\udce4\udcf6\udcfc")
finally:
tar.close()
class UstarUnicodeTest(UnicodeTest, unittest.TestCase):
format = tarfile.USTAR_FORMAT
# Test whether the utf-8 encoded version of a filename exceeds the 100
# bytes name field limit (every occurrence of '\xff' will be expanded to 2
# bytes).
def test_unicode_name1(self):
self._test_ustar_name("0123456789" * 10)
self._test_ustar_name("0123456789" * 10 + "0", ValueError)
self._test_ustar_name("0123456789" * 9 + "01234567\xff")
self._test_ustar_name("0123456789" * 9 + "012345678\xff", ValueError)
def test_unicode_name2(self):
self._test_ustar_name("0123456789" * 9 + "012345\xff\xff")
self._test_ustar_name("0123456789" * 9 + "0123456\xff\xff", ValueError)
# Test whether the utf-8 encoded version of a filename exceeds the 155
# bytes prefix + '/' + 100 bytes name limit.
def test_unicode_longname1(self):
self._test_ustar_name("0123456789" * 15 + "01234/" + "0123456789" * 10)
self._test_ustar_name("0123456789" * 15 + "0123/4" + "0123456789" * 10, ValueError)
self._test_ustar_name("0123456789" * 15 + "012\xff/" + "0123456789" * 10)
self._test_ustar_name("0123456789" * 15 + "0123\xff/" + "0123456789" * 10, ValueError)
def test_unicode_longname2(self):
self._test_ustar_name("0123456789" * 15 + "01\xff/2" + "0123456789" * 10, ValueError)
self._test_ustar_name("0123456789" * 15 + "01\xff\xff/" + "0123456789" * 10, ValueError)
def test_unicode_longname3(self):
self._test_ustar_name("0123456789" * 15 + "01\xff\xff/2" + "0123456789" * 10, ValueError)
self._test_ustar_name("0123456789" * 15 + "01234/" + "0123456789" * 9 + "01234567\xff")
self._test_ustar_name("0123456789" * 15 + "01234/" + "0123456789" * 9 + "012345678\xff", ValueError)
def test_unicode_longname4(self):
self._test_ustar_name("0123456789" * 15 + "01234/" + "0123456789" * 9 + "012345\xff\xff")
self._test_ustar_name("0123456789" * 15 + "01234/" + "0123456789" * 9 + "0123456\xff\xff", ValueError)
def _test_ustar_name(self, name, exc=None):
with tarfile.open(tmpname, "w", format=self.format, encoding="utf-8") as tar:
t = tarfile.TarInfo(name)
if exc is None:
tar.addfile(t)
else:
self.assertRaises(exc, tar.addfile, t)
if exc is None:
with tarfile.open(tmpname, "r", encoding="utf-8") as tar:
for t in tar:
self.assertEqual(name, t.name)
break
# Test the same as above for the 100 bytes link field.
def test_unicode_link1(self):
self._test_ustar_link("0123456789" * 10)
self._test_ustar_link("0123456789" * 10 + "0", ValueError)
self._test_ustar_link("0123456789" * 9 + "01234567\xff")
self._test_ustar_link("0123456789" * 9 + "012345678\xff", ValueError)
def test_unicode_link2(self):
self._test_ustar_link("0123456789" * 9 + "012345\xff\xff")
self._test_ustar_link("0123456789" * 9 + "0123456\xff\xff", ValueError)
def _test_ustar_link(self, name, exc=None):
with tarfile.open(tmpname, "w", format=self.format, encoding="utf-8") as tar:
t = tarfile.TarInfo("foo")
t.linkname = name
if exc is None:
tar.addfile(t)
else:
self.assertRaises(exc, tar.addfile, t)
if exc is None:
with tarfile.open(tmpname, "r", encoding="utf-8") as tar:
for t in tar:
self.assertEqual(name, t.linkname)
break
class GNUUnicodeTest(UnicodeTest, unittest.TestCase):
format = tarfile.GNU_FORMAT
def test_bad_pax_header(self):
# Test for issue #8633. GNU tar <= 1.23 creates raw binary fields
# without a hdrcharset=BINARY header.
for encoding, name in (
("utf-8", "pax/bad-pax-\udce4\udcf6\udcfc"),
("iso8859-1", "pax/bad-pax-\xe4\xf6\xfc"),):
with tarfile.open(tarname, encoding=encoding,
errors="surrogateescape") as tar:
try:
t = tar.getmember(name)
except KeyError:
self.fail("unable to read bad GNU tar pax header")
class PAXUnicodeTest(UnicodeTest, unittest.TestCase):
format = tarfile.PAX_FORMAT
# PAX_FORMAT ignores encoding in write mode.
test_unicode_filename_error = None
def test_binary_header(self):
# Test a POSIX.1-2008 compatible header with a hdrcharset=BINARY field.
for encoding, name in (
("utf-8", "pax/hdrcharset-\udce4\udcf6\udcfc"),
("iso8859-1", "pax/hdrcharset-\xe4\xf6\xfc"),):
with tarfile.open(tarname, encoding=encoding,
errors="surrogateescape") as tar:
try:
t = tar.getmember(name)
except KeyError:
self.fail("unable to read POSIX.1-2008 binary header")
class AppendTestBase:
# Test append mode (cp. patch #1652681).
def setUp(self):
self.tarname = tmpname
if os.path.exists(self.tarname):
os_helper.unlink(self.tarname)
def _create_testtar(self, mode="w:"):
with tarfile.open(tarname, encoding="iso8859-1") as src:
t = src.getmember("ustar/regtype")
t.name = "foo"
with src.extractfile(t) as f:
with tarfile.open(self.tarname, mode) as tar:
tar.addfile(t, f)
def test_append_compressed(self):
self._create_testtar("w:" + self.suffix)
self.assertRaises(tarfile.ReadError, tarfile.open, tmpname, "a")
class AppendTest(AppendTestBase, unittest.TestCase):
test_append_compressed = None
def _add_testfile(self, fileobj=None):
with tarfile.open(self.tarname, "a", fileobj=fileobj) as tar:
tar.addfile(tarfile.TarInfo("bar"))
def _test(self, names=["bar"], fileobj=None):
with tarfile.open(self.tarname, fileobj=fileobj) as tar:
self.assertEqual(tar.getnames(), names)
def test_non_existing(self):
self._add_testfile()
self._test()
def test_empty(self):
tarfile.open(self.tarname, "w:").close()
self._add_testfile()
self._test()
def test_empty_fileobj(self):
fobj = io.BytesIO(b"\0" * 1024)
self._add_testfile(fobj)
fobj.seek(0)
self._test(fileobj=fobj)
def test_fileobj(self):
self._create_testtar()
with open(self.tarname, "rb") as fobj:
data = fobj.read()
fobj = io.BytesIO(data)
self._add_testfile(fobj)
fobj.seek(0)
self._test(names=["foo", "bar"], fileobj=fobj)
def test_existing(self):
self._create_testtar()
self._add_testfile()
self._test(names=["foo", "bar"])
# Append mode is supposed to fail if the tarfile to append to
# does not end with a zero block.
def _test_error(self, data):
with open(self.tarname, "wb") as fobj:
fobj.write(data)
self.assertRaises(tarfile.ReadError, self._add_testfile)
def test_null(self):
self._test_error(b"")
def test_incomplete(self):
self._test_error(b"\0" * 13)
def test_premature_eof(self):
data = tarfile.TarInfo("foo").tobuf()
self._test_error(data)
def test_trailing_garbage(self):
data = tarfile.TarInfo("foo").tobuf()
self._test_error(data + b"\0" * 13)
def test_invalid(self):
self._test_error(b"a" * 512)
class GzipAppendTest(GzipTest, AppendTestBase, unittest.TestCase):
pass
class Bz2AppendTest(Bz2Test, AppendTestBase, unittest.TestCase):
pass
class LzmaAppendTest(LzmaTest, AppendTestBase, unittest.TestCase):
pass
class LimitsTest(unittest.TestCase):
def test_ustar_limits(self):
# 100 char name
tarinfo = tarfile.TarInfo("0123456789" * 10)
tarinfo.tobuf(tarfile.USTAR_FORMAT)
# 101 char name that cannot be stored
tarinfo = tarfile.TarInfo("0123456789" * 10 + "0")
self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# 256 char name with a slash at pos 156
tarinfo = tarfile.TarInfo("123/" * 62 + "longname")
tarinfo.tobuf(tarfile.USTAR_FORMAT)
# 256 char name that cannot be stored
tarinfo = tarfile.TarInfo("1234567/" * 31 + "longname")
self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# 512 char name
tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# 512 char linkname
tarinfo = tarfile.TarInfo("longlink")
tarinfo.linkname = "123/" * 126 + "longname"
self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# uid > 8 digits
tarinfo = tarfile.TarInfo("name")
tarinfo.uid = 0o10000000
self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
def test_gnu_limits(self):
tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
tarinfo.tobuf(tarfile.GNU_FORMAT)
tarinfo = tarfile.TarInfo("longlink")
tarinfo.linkname = "123/" * 126 + "longname"
tarinfo.tobuf(tarfile.GNU_FORMAT)
# uid >= 256 ** 7
tarinfo = tarfile.TarInfo("name")
tarinfo.uid = 0o4000000000000000000
self.assertRaises(ValueError, tarinfo.tobuf, tarfile.GNU_FORMAT)
def test_pax_limits(self):
tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
tarinfo.tobuf(tarfile.PAX_FORMAT)
tarinfo = tarfile.TarInfo("longlink")
tarinfo.linkname = "123/" * 126 + "longname"
tarinfo.tobuf(tarfile.PAX_FORMAT)
tarinfo = tarfile.TarInfo("name")
tarinfo.uid = 0o4000000000000000000
tarinfo.tobuf(tarfile.PAX_FORMAT)
class MiscTest(unittest.TestCase):
def test_char_fields(self):
self.assertEqual(tarfile.stn("foo", 8, "ascii", "strict"),
b"foo\0\0\0\0\0")
self.assertEqual(tarfile.stn("foobar", 3, "ascii", "strict"),
b"foo")
self.assertEqual(tarfile.nts(b"foo\0\0\0\0\0", "ascii", "strict"),
"foo")
self.assertEqual(tarfile.nts(b"foo\0bar\0", "ascii", "strict"),
"foo")
def test_read_number_fields(self):
# Issue 13158: Test if GNU tar specific base-256 number fields
# are decoded correctly.
self.assertEqual(tarfile.nti(b"0000001\x00"), 1)
self.assertEqual(tarfile.nti(b"7777777\x00"), 0o7777777)
self.assertEqual(tarfile.nti(b"\x80\x00\x00\x00\x00\x20\x00\x00"),
0o10000000)
self.assertEqual(tarfile.nti(b"\x80\x00\x00\x00\xff\xff\xff\xff"),
0xffffffff)
self.assertEqual(tarfile.nti(b"\xff\xff\xff\xff\xff\xff\xff\xff"),
-1)
self.assertEqual(tarfile.nti(b"\xff\xff\xff\xff\xff\xff\xff\x9c"),
-100)
self.assertEqual(tarfile.nti(b"\xff\x00\x00\x00\x00\x00\x00\x00"),
-0x100000000000000)
# Issue 24514: Test if empty number fields are converted to zero.
self.assertEqual(tarfile.nti(b"\0"), 0)
self.assertEqual(tarfile.nti(b" \0"), 0)
def test_write_number_fields(self):
self.assertEqual(tarfile.itn(1), b"0000001\x00")
self.assertEqual(tarfile.itn(0o7777777), b"7777777\x00")
self.assertEqual(tarfile.itn(0o10000000, format=tarfile.GNU_FORMAT),
b"\x80\x00\x00\x00\x00\x20\x00\x00")
self.assertEqual(tarfile.itn(0xffffffff, format=tarfile.GNU_FORMAT),
b"\x80\x00\x00\x00\xff\xff\xff\xff")
self.assertEqual(tarfile.itn(-1, format=tarfile.GNU_FORMAT),
b"\xff\xff\xff\xff\xff\xff\xff\xff")
self.assertEqual(tarfile.itn(-100, format=tarfile.GNU_FORMAT),
b"\xff\xff\xff\xff\xff\xff\xff\x9c")
self.assertEqual(tarfile.itn(-0x100000000000000,
format=tarfile.GNU_FORMAT),
b"\xff\x00\x00\x00\x00\x00\x00\x00")
# Issue 32713: Test if itn() supports float values outside the
# non-GNU format range
self.assertEqual(tarfile.itn(-100.0, format=tarfile.GNU_FORMAT),
b"\xff\xff\xff\xff\xff\xff\xff\x9c")
self.assertEqual(tarfile.itn(8 ** 12 + 0.0, format=tarfile.GNU_FORMAT),
b"\x80\x00\x00\x10\x00\x00\x00\x00")
self.assertEqual(tarfile.nti(tarfile.itn(-0.1, format=tarfile.GNU_FORMAT)), 0)
def test_number_field_limits(self):
with self.assertRaises(ValueError):
tarfile.itn(-1, 8, tarfile.USTAR_FORMAT)
with self.assertRaises(ValueError):
tarfile.itn(0o10000000, 8, tarfile.USTAR_FORMAT)
with self.assertRaises(ValueError):
tarfile.itn(-0x10000000001, 6, tarfile.GNU_FORMAT)
with self.assertRaises(ValueError):
tarfile.itn(0x10000000000, 6, tarfile.GNU_FORMAT)
def test__all__(self):
not_exported = {
'version', 'grp', 'pwd', 'symlink_exception', 'NUL', 'BLOCKSIZE',
'RECORDSIZE', 'GNU_MAGIC', 'POSIX_MAGIC', 'LENGTH_NAME',
'LENGTH_LINK', 'LENGTH_PREFIX', 'REGTYPE', 'AREGTYPE', 'LNKTYPE',
'SYMTYPE', 'CHRTYPE', 'BLKTYPE', 'DIRTYPE', 'FIFOTYPE', 'CONTTYPE',
'GNUTYPE_LONGNAME', 'GNUTYPE_LONGLINK', 'GNUTYPE_SPARSE',
'XHDTYPE', 'XGLTYPE', 'SOLARIS_XHDTYPE', 'SUPPORTED_TYPES',
'REGULAR_TYPES', 'GNU_TYPES', 'PAX_FIELDS', 'PAX_NAME_FIELDS',
'PAX_NUMBER_FIELDS', 'stn', 'nts', 'nti', 'itn', 'calc_chksums',
'copyfileobj', 'filemode', 'EmptyHeaderError',
'TruncatedHeaderError', 'EOFHeaderError', 'InvalidHeaderError',
'SubsequentHeaderError', 'ExFileObject', 'main'}
support.check__all__(self, tarfile, not_exported=not_exported)
def test_useful_error_message_when_modules_missing(self):
fname = os.path.join(os.path.dirname(__file__), 'archivetestdata', 'testtar.tar.xz')
with self.assertRaises(tarfile.ReadError) as excinfo:
error = tarfile.CompressionError('lzma module is not available'),
with unittest.mock.patch.object(tarfile.TarFile, 'xzopen', side_effect=error):
tarfile.open(fname)
self.assertIn(
"\n- method xz: CompressionError('lzma module is not available')\n",
str(excinfo.exception),
)
@unittest.skipUnless(os_helper.can_symlink(), 'requires symlink support')
@unittest.skipUnless(hasattr(os, 'chmod'), "missing os.chmod")
@unittest.mock.patch('os.chmod')
def test_deferred_directory_attributes_update(self, mock_chmod):
# Regression test for gh-127987: setting attributes on arbitrary files
tempdir = os.path.join(TEMPDIR, 'test127987')
def mock_chmod_side_effect(path, mode, **kwargs):
target_path = os.path.realpath(path)
if os.path.commonpath([target_path, tempdir]) != tempdir:
raise Exception("should not try to chmod anything outside the destination", target_path)
mock_chmod.side_effect = mock_chmod_side_effect
outside_tree_dir = os.path.join(TEMPDIR, 'outside_tree_dir')
with ArchiveMaker() as arc:
arc.add('x', symlink_to='.')
arc.add('x', type=tarfile.DIRTYPE, mode='?rwsrwsrwt')
arc.add('x', symlink_to=outside_tree_dir)
os.makedirs(outside_tree_dir)
try:
arc.open().extractall(path=tempdir, filter='tar')
finally:
os_helper.rmtree(outside_tree_dir)
os_helper.rmtree(tempdir)
class CommandLineTest(unittest.TestCase):
def tarfilecmd(self, *args, **kwargs):
rc, out, err = script_helper.assert_python_ok('-m', 'tarfile', *args,
**kwargs)
return out.replace(os.linesep.encode(), b'\n')
def tarfilecmd_failure(self, *args):
return script_helper.assert_python_failure('-m', 'tarfile', *args)
def make_simple_tarfile(self, tar_name):
files = [support.findfile('tokenize_tests.txt',
subdir='tokenizedata'),
support.findfile('tokenize_tests-no-coding-cookie-'
'and-utf8-bom-sig-only.txt',
subdir='tokenizedata')]
self.addCleanup(os_helper.unlink, tar_name)
with tarfile.open(tar_name, 'w') as tf:
for tardata in files:
tf.add(tardata, arcname=os.path.basename(tardata))
def make_evil_tarfile(self, tar_name):
self.addCleanup(os_helper.unlink, tar_name)
with tarfile.open(tar_name, 'w') as tf:
benign = tarfile.TarInfo('benign')
tf.addfile(benign, fileobj=io.BytesIO(b''))
evil = tarfile.TarInfo('../evil')
tf.addfile(evil, fileobj=io.BytesIO(b''))
def test_bad_use(self):
rc, out, err = self.tarfilecmd_failure()
self.assertEqual(out, b'')
self.assertIn(b'usage', err.lower())
self.assertIn(b'error', err.lower())
self.assertIn(b'required', err.lower())
rc, out, err = self.tarfilecmd_failure('-l', '')
self.assertEqual(out, b'')
self.assertNotEqual(err.strip(), b'')
def test_test_command(self):
for tar_name in testtarnames:
for opt in '-t', '--test':
out = self.tarfilecmd(opt, tar_name)
self.assertEqual(out, b'')
def test_test_command_verbose(self):
for tar_name in testtarnames:
for opt in '-v', '--verbose':
out = self.tarfilecmd(opt, '-t', tar_name,
PYTHONIOENCODING='utf-8')
self.assertIn(b'is a tar archive.\n', out)
def test_test_command_invalid_file(self):
zipname = support.findfile('zipdir.zip', subdir='archivetestdata')
rc, out, err = self.tarfilecmd_failure('-t', zipname)
self.assertIn(b' is not a tar archive.', err)
self.assertEqual(out, b'')
self.assertEqual(rc, 1)
for tar_name in testtarnames:
with self.subTest(tar_name=tar_name):
with open(tar_name, 'rb') as f:
data = f.read()
try:
with open(tmpname, 'wb') as f:
f.write(data[:511])
rc, out, err = self.tarfilecmd_failure('-t', tmpname)
self.assertEqual(out, b'')
self.assertEqual(rc, 1)
finally:
os_helper.unlink(tmpname)
def test_list_command(self):
for tar_name in testtarnames:
with support.captured_stdout() as t:
with tarfile.open(tar_name, 'r') as tf:
tf.list(verbose=False)
expected = t.getvalue().encode('ascii', 'backslashreplace')
for opt in '-l', '--list':
out = self.tarfilecmd(opt, tar_name,
PYTHONIOENCODING='ascii')
self.assertEqual(out, expected)
def test_list_command_verbose(self):
for tar_name in testtarnames:
with support.captured_stdout() as t:
with tarfile.open(tar_name, 'r') as tf:
tf.list(verbose=True)
expected = t.getvalue().encode('ascii', 'backslashreplace')
for opt in '-v', '--verbose':
out = self.tarfilecmd(opt, '-l', tar_name,
PYTHONIOENCODING='ascii')
self.assertEqual(out, expected)
def test_list_command_invalid_file(self):
zipname = support.findfile('zipdir.zip', subdir='archivetestdata')
rc, out, err = self.tarfilecmd_failure('-l', zipname)
self.assertIn(b' is not a tar archive.', err)
self.assertEqual(out, b'')
self.assertEqual(rc, 1)
def test_create_command(self):
files = [support.findfile('tokenize_tests.txt',
subdir='tokenizedata'),
support.findfile('tokenize_tests-no-coding-cookie-'
'and-utf8-bom-sig-only.txt',
subdir='tokenizedata')]
for opt in '-c', '--create':
try:
out = self.tarfilecmd(opt, tmpname, *files)
self.assertEqual(out, b'')
with tarfile.open(tmpname) as tar:
tar.getmembers()
finally:
os_helper.unlink(tmpname)
def test_create_command_verbose(self):
files = [support.findfile('tokenize_tests.txt',
subdir='tokenizedata'),
support.findfile('tokenize_tests-no-coding-cookie-'
'and-utf8-bom-sig-only.txt',
subdir='tokenizedata')]
for opt in '-v', '--verbose':
try:
out = self.tarfilecmd(opt, '-c', tmpname, *files,
PYTHONIOENCODING='utf-8')
self.assertIn(b' file created.', out)
with tarfile.open(tmpname) as tar:
tar.getmembers()
finally:
os_helper.unlink(tmpname)
def test_create_command_dotless_filename(self):
files = [support.findfile('tokenize_tests.txt', subdir='tokenizedata')]
try:
out = self.tarfilecmd('-c', dotlessname, *files)
self.assertEqual(out, b'')
with tarfile.open(dotlessname) as tar:
tar.getmembers()
finally:
os_helper.unlink(dotlessname)
def test_create_command_dot_started_filename(self):
tar_name = os.path.join(TEMPDIR, ".testtar")
files = [support.findfile('tokenize_tests.txt', subdir='tokenizedata')]
try:
out = self.tarfilecmd('-c', tar_name, *files)
self.assertEqual(out, b'')
with tarfile.open(tar_name) as tar:
tar.getmembers()
finally:
os_helper.unlink(tar_name)
def test_create_command_compressed(self):
files = [support.findfile('tokenize_tests.txt',
subdir='tokenizedata'),
support.findfile('tokenize_tests-no-coding-cookie-'
'and-utf8-bom-sig-only.txt',
subdir='tokenizedata')]
for filetype in (GzipTest, Bz2Test, LzmaTest):
if not filetype.open:
continue
try:
tar_name = tmpname + '.' + filetype.suffix
out = self.tarfilecmd('-c', tar_name, *files)
with filetype.taropen(tar_name) as tar:
tar.getmembers()
finally:
os_helper.unlink(tar_name)
def test_extract_command(self):
self.make_simple_tarfile(tmpname)
for opt in '-e', '--extract':
try:
with os_helper.temp_cwd(tarextdir):
out = self.tarfilecmd(opt, tmpname)
self.assertEqual(out, b'')
finally:
os_helper.rmtree(tarextdir)
def test_extract_command_verbose(self):
self.make_simple_tarfile(tmpname)
for opt in '-v', '--verbose':
try:
with os_helper.temp_cwd(tarextdir):
out = self.tarfilecmd(opt, '-e', tmpname,
PYTHONIOENCODING='utf-8')
self.assertIn(b' file is extracted.', out)
finally:
os_helper.rmtree(tarextdir)
def test_extract_command_filter(self):
self.make_evil_tarfile(tmpname)
# Make an inner directory, so the member named '../evil'
# is still extracted into `tarextdir`
destdir = os.path.join(tarextdir, 'dest')
os.mkdir(tarextdir)
try:
with os_helper.temp_cwd(destdir):
self.tarfilecmd_failure('-e', tmpname,
'-v',
'--filter', 'data')
out = self.tarfilecmd('-e', tmpname,
'-v',
'--filter', 'fully_trusted',
PYTHONIOENCODING='utf-8')
self.assertIn(b' file is extracted.', out)
finally:
os_helper.rmtree(tarextdir)
def test_extract_command_different_directory(self):
self.make_simple_tarfile(tmpname)
try:
with os_helper.temp_cwd(tarextdir):
out = self.tarfilecmd('-e', tmpname, 'spamdir')
self.assertEqual(out, b'')
finally:
os_helper.rmtree(tarextdir)
def test_extract_command_invalid_file(self):
zipname = support.findfile('zipdir.zip', subdir='archivetestdata')
with os_helper.temp_cwd(tarextdir):
rc, out, err = self.tarfilecmd_failure('-e', zipname)
self.assertIn(b' is not a tar archive.', err)
self.assertEqual(out, b'')
self.assertEqual(rc, 1)
class ContextManagerTest(unittest.TestCase):
def test_basic(self):
with tarfile.open(tarname) as tar:
self.assertFalse(tar.closed, "closed inside runtime context")
self.assertTrue(tar.closed, "context manager failed")
def test_closed(self):
# The __enter__() method is supposed to raise OSError
# if the TarFile object is already closed.
tar = tarfile.open(tarname)
tar.close()
with self.assertRaises(OSError):
with tar:
pass
def test_exception(self):
# Test if the OSError exception is passed through properly.
with self.assertRaises(Exception) as exc:
with tarfile.open(tarname) as tar:
raise OSError
self.assertIsInstance(exc.exception, OSError,
"wrong exception raised in context manager")
self.assertTrue(tar.closed, "context manager failed")
def test_no_eof(self):
# __exit__() must not write end-of-archive blocks if an
# exception was raised.
try:
with tarfile.open(tmpname, "w") as tar:
raise Exception
except:
pass
self.assertEqual(os.path.getsize(tmpname), 0,
"context manager wrote an end-of-archive block")
self.assertTrue(tar.closed, "context manager failed")
def test_eof(self):
# __exit__() must write end-of-archive blocks, i.e. call
# TarFile.close() if there was no error.
with tarfile.open(tmpname, "w"):
pass
self.assertNotEqual(os.path.getsize(tmpname), 0,
"context manager wrote no end-of-archive block")
def test_fileobj(self):
# Test that __exit__() did not close the external file
# object.
with open(tmpname, "wb") as fobj:
try:
with tarfile.open(fileobj=fobj, mode="w") as tar:
raise Exception
except:
pass
self.assertFalse(fobj.closed, "external file object was closed")
self.assertTrue(tar.closed, "context manager failed")
@unittest.skipIf(hasattr(os, "link"), "requires os.link to be missing")
class LinkEmulationTest(ReadTest, unittest.TestCase):
# Test for issue #8741 regression. On platforms that do not support
# symbolic or hard links tarfile tries to extract these types of members
# as the regular files they point to.
def _test_link_extraction(self, name):
self.tar.extract(name, TEMPDIR, filter='fully_trusted')
with open(os.path.join(TEMPDIR, name), "rb") as f:
data = f.read()
self.assertEqual(sha256sum(data), sha256_regtype)
# See issues #1578269, #8879, and #17689 for some history on these skips
@unittest.skipIf(hasattr(os.path, "islink"),
"Skip emulation - has os.path.islink but not os.link")
def test_hardlink_extraction1(self):
self._test_link_extraction("ustar/lnktype")
@unittest.skipIf(hasattr(os.path, "islink"),
"Skip emulation - has os.path.islink but not os.link")
def test_hardlink_extraction2(self):
self._test_link_extraction("./ustar/linktest2/lnktype")
@unittest.skipIf(hasattr(os, "symlink"),
"Skip emulation if symlink exists")
def test_symlink_extraction1(self):
self._test_link_extraction("ustar/symtype")
@unittest.skipIf(hasattr(os, "symlink"),
"Skip emulation if symlink exists")
def test_symlink_extraction2(self):
self._test_link_extraction("./ustar/linktest2/symtype")
class Bz2PartialReadTest(Bz2Test, unittest.TestCase):
# Issue5068: The _BZ2Proxy.read() method loops forever
# on an empty or partial bzipped file.
def _test_partial_input(self, mode):
class MyBytesIO(io.BytesIO):
hit_eof = False
def read(self, n):
if self.hit_eof:
raise AssertionError("infinite loop detected in "
"tarfile.open()")
self.hit_eof = self.tell() == len(self.getvalue())
return super(MyBytesIO, self).read(n)
def seek(self, *args):
self.hit_eof = False
return super(MyBytesIO, self).seek(*args)
data = bz2.compress(tarfile.TarInfo("foo").tobuf())
for x in range(len(data) + 1):
try:
tarfile.open(fileobj=MyBytesIO(data[:x]), mode=mode)
except tarfile.ReadError:
pass # we have no interest in ReadErrors
def test_partial_input(self):
self._test_partial_input("r")
def test_partial_input_bz2(self):
self._test_partial_input("r:bz2")
def root_is_uid_gid_0():
try:
import pwd, grp
except ImportError:
return False
if pwd.getpwuid(0)[0] != 'root':
return False
if grp.getgrgid(0)[0] != 'root':
return False
return True
@unittest.skipUnless(hasattr(os, 'chown'), "missing os.chown")
@unittest.skipUnless(hasattr(os, 'geteuid'), "missing os.geteuid")
class NumericOwnerTest(unittest.TestCase):
# mock the following:
# os.chown: so we can test what's being called
# os.chmod: so the modes are not actually changed. if they are, we can't
# delete the files/directories
# os.geteuid: so we can lie and say we're root (uid = 0)
@staticmethod
def _make_test_archive(filename_1, dirname_1, filename_2):
# the file contents to write
fobj = io.BytesIO(b"content")
# create a tar file with a file, a directory, and a file within that
# directory. Assign various .uid/.gid values to them
items = [(filename_1, 99, 98, tarfile.REGTYPE, fobj),
(dirname_1, 77, 76, tarfile.DIRTYPE, None),
(filename_2, 88, 87, tarfile.REGTYPE, fobj),
]
with tarfile.open(tmpname, 'w') as tarfl:
for name, uid, gid, typ, contents in items:
t = tarfile.TarInfo(name)
t.uid = uid
t.gid = gid
t.uname = 'root'
t.gname = 'root'
t.type = typ
tarfl.addfile(t, contents)
# return the full pathname to the tar file
return tmpname
@staticmethod
@contextmanager
def _setup_test(mock_geteuid):
mock_geteuid.return_value = 0 # lie and say we're root
fname = 'numeric-owner-testfile'
dirname = 'dir'
# the names we want stored in the tarfile
filename_1 = fname
dirname_1 = dirname
filename_2 = os.path.join(dirname, fname)
# create the tarfile with the contents we're after
tar_filename = NumericOwnerTest._make_test_archive(filename_1,
dirname_1,
filename_2)
# open the tarfile for reading. yield it and the names of the items
# we stored into the file
with tarfile.open(tar_filename) as tarfl:
yield tarfl, filename_1, dirname_1, filename_2
@unittest.mock.patch('os.chown')
@unittest.mock.patch('os.chmod')
@unittest.mock.patch('os.geteuid')
def test_extract_with_numeric_owner(self, mock_geteuid, mock_chmod,
mock_chown):
with self._setup_test(mock_geteuid) as (tarfl, filename_1, _,
filename_2):
tarfl.extract(filename_1, TEMPDIR, numeric_owner=True,
filter='fully_trusted')
tarfl.extract(filename_2 , TEMPDIR, numeric_owner=True,
filter='fully_trusted')
# convert to filesystem paths
f_filename_1 = os.path.join(TEMPDIR, filename_1)
f_filename_2 = os.path.join(TEMPDIR, filename_2)
mock_chown.assert_has_calls([unittest.mock.call(f_filename_1, 99, 98),
unittest.mock.call(f_filename_2, 88, 87),
],
any_order=True)
@unittest.mock.patch('os.chown')
@unittest.mock.patch('os.chmod')
@unittest.mock.patch('os.geteuid')
def test_extractall_with_numeric_owner(self, mock_geteuid, mock_chmod,
mock_chown):
with self._setup_test(mock_geteuid) as (tarfl, filename_1, dirname_1,
filename_2):
tarfl.extractall(TEMPDIR, numeric_owner=True,
filter='fully_trusted')
# convert to filesystem paths
f_filename_1 = os.path.join(TEMPDIR, filename_1)
f_dirname_1 = os.path.join(TEMPDIR, dirname_1)
f_filename_2 = os.path.join(TEMPDIR, filename_2)
mock_chown.assert_has_calls([unittest.mock.call(f_filename_1, 99, 98),
unittest.mock.call(f_dirname_1, 77, 76),
unittest.mock.call(f_filename_2, 88, 87),
],
any_order=True)
# this test requires that uid=0 and gid=0 really be named 'root'. that's
# because the uname and gname in the test file are 'root', and extract()
# will look them up using pwd and grp to find their uid and gid, which we
# test here to be 0.
@unittest.skipUnless(root_is_uid_gid_0(),
'uid=0,gid=0 must be named "root"')
@unittest.mock.patch('os.chown')
@unittest.mock.patch('os.chmod')
@unittest.mock.patch('os.geteuid')
def test_extract_without_numeric_owner(self, mock_geteuid, mock_chmod,
mock_chown):
with self._setup_test(mock_geteuid) as (tarfl, filename_1, _, _):
tarfl.extract(filename_1, TEMPDIR, numeric_owner=False,
filter='fully_trusted')
# convert to filesystem paths
f_filename_1 = os.path.join(TEMPDIR, filename_1)
mock_chown.assert_called_with(f_filename_1, 0, 0)
@unittest.mock.patch('os.geteuid')
def test_keyword_only(self, mock_geteuid):
with self._setup_test(mock_geteuid) as (tarfl, filename_1, _, _):
self.assertRaises(TypeError,
tarfl.extract, filename_1, TEMPDIR, False, True)
class ReplaceTests(ReadTest, unittest.TestCase):
def test_replace_name(self):
member = self.tar.getmember('ustar/regtype')
replaced = member.replace(name='misc/other')
self.assertEqual(replaced.name, 'misc/other')
self.assertEqual(member.name, 'ustar/regtype')
self.assertEqual(self.tar.getmember('ustar/regtype').name,
'ustar/regtype')
def test_replace_deep(self):
member = self.tar.getmember('pax/regtype1')
replaced = member.replace()
replaced.pax_headers['gname'] = 'not-bar'
self.assertEqual(member.pax_headers['gname'], 'bar')
self.assertEqual(
self.tar.getmember('pax/regtype1').pax_headers['gname'], 'bar')
def test_replace_shallow(self):
member = self.tar.getmember('pax/regtype1')
replaced = member.replace(deep=False)
replaced.pax_headers['gname'] = 'not-bar'
self.assertEqual(member.pax_headers['gname'], 'not-bar')
self.assertEqual(
self.tar.getmember('pax/regtype1').pax_headers['gname'], 'not-bar')
def test_replace_all(self):
member = self.tar.getmember('ustar/regtype')
for attr_name in ('name', 'mtime', 'mode', 'linkname',
'uid', 'gid', 'uname', 'gname'):
with self.subTest(attr_name=attr_name):
replaced = member.replace(**{attr_name: None})
self.assertEqual(getattr(replaced, attr_name), None)
self.assertNotEqual(getattr(member, attr_name), None)
def test_replace_internal(self):
member = self.tar.getmember('ustar/regtype')
with self.assertRaises(TypeError):
member.replace(offset=123456789)
class NoneInfoExtractTests(ReadTest):
# These mainly check that all kinds of members are extracted successfully
# if some metadata is None.
# Some of the methods do additional spot checks.
# We also test that the default filters can deal with None.
extraction_filter = None
@classmethod
def setUpClass(cls):
tar = tarfile.open(tarname, mode='r', encoding="iso8859-1")
cls.control_dir = pathlib.Path(TEMPDIR) / "extractall_ctrl"
tar.errorlevel = 0
with ExitStack() as cm:
if cls.extraction_filter is None:
cm.enter_context(warnings.catch_warnings(
action="ignore", category=DeprecationWarning))
tar.extractall(cls.control_dir, filter=cls.extraction_filter)
tar.close()
cls.control_paths = set(
p.relative_to(cls.control_dir)
for p in pathlib.Path(cls.control_dir).glob('**/*'))
@classmethod
def tearDownClass(cls):
shutil.rmtree(cls.control_dir)
def check_files_present(self, directory):
got_paths = set(
p.relative_to(directory)
for p in pathlib.Path(directory).glob('**/*'))
if self.extraction_filter == 'data':
# The 'data' filter is expected to reject special files
for path in 'ustar/fifotype', 'ustar/blktype', 'ustar/chrtype':
got_paths.discard(pathlib.Path(path))
self.assertEqual(self.control_paths, got_paths)
@contextmanager
def extract_with_none(self, *attr_names):
DIR = pathlib.Path(TEMPDIR) / "extractall_none"
self.tar.errorlevel = 0
for member in self.tar.getmembers():
for attr_name in attr_names:
setattr(member, attr_name, None)
with os_helper.temp_dir(DIR):
self.tar.extractall(DIR, filter='fully_trusted')
self.check_files_present(DIR)
yield DIR
def test_extractall_none_mtime(self):
# mtimes of extracted files should be later than 'now' -- the mtime
# of a previously created directory.
now = pathlib.Path(TEMPDIR).stat().st_mtime
with self.extract_with_none('mtime') as DIR:
for path in pathlib.Path(DIR).glob('**/*'):
with self.subTest(path=path):
try:
mtime = path.stat().st_mtime
except OSError:
# Some systems can't stat symlinks, ignore those
if not path.is_symlink():
raise
else:
self.assertGreaterEqual(path.stat().st_mtime, now)
def test_extractall_none_mode(self):
# modes of directories and regular files should match the mode
# of a "normally" created directory or regular file
dir_mode = pathlib.Path(TEMPDIR).stat().st_mode
regular_file = pathlib.Path(TEMPDIR) / 'regular_file'
regular_file.write_text('')
regular_file_mode = regular_file.stat().st_mode
with self.extract_with_none('mode') as DIR:
for path in pathlib.Path(DIR).glob('**/*'):
with self.subTest(path=path):
if path.is_dir():
self.assertEqual(path.stat().st_mode, dir_mode)
elif path.is_file():
self.assertEqual(path.stat().st_mode,
regular_file_mode)
def test_extractall_none_uid(self):
with self.extract_with_none('uid'):
pass
def test_extractall_none_gid(self):
with self.extract_with_none('gid'):
pass
def test_extractall_none_uname(self):
with self.extract_with_none('uname'):
pass
def test_extractall_none_gname(self):
with self.extract_with_none('gname'):
pass
def test_extractall_none_ownership(self):
with self.extract_with_none('uid', 'gid', 'uname', 'gname'):
pass
class NoneInfoExtractTests_Data(NoneInfoExtractTests, unittest.TestCase):
extraction_filter = 'data'
class NoneInfoExtractTests_FullyTrusted(NoneInfoExtractTests,
unittest.TestCase):
extraction_filter = 'fully_trusted'
class NoneInfoExtractTests_Tar(NoneInfoExtractTests, unittest.TestCase):
extraction_filter = 'tar'
class NoneInfoExtractTests_Default(NoneInfoExtractTests,
unittest.TestCase):
extraction_filter = None
class NoneInfoTests_Misc(unittest.TestCase):
def test_add(self):
# When addfile() encounters None metadata, it raises a ValueError
bio = io.BytesIO()
for tarformat in (tarfile.USTAR_FORMAT, tarfile.GNU_FORMAT,
tarfile.PAX_FORMAT):
with self.subTest(tarformat=tarformat):
tar = tarfile.open(fileobj=bio, mode='w', format=tarformat)
tarinfo = tar.gettarinfo(tarname)
try:
with open(tarname, 'rb') as f:
tar.addfile(tarinfo, f)
except Exception:
if tarformat == tarfile.USTAR_FORMAT:
# In the old, limited format, adding might fail for
# reasons like the UID being too large
pass
else:
raise
else:
for attr_name in ('mtime', 'mode', 'uid', 'gid',
'uname', 'gname'):
with self.subTest(attr_name=attr_name):
replaced = tarinfo.replace(**{attr_name: None})
with self.assertRaisesRegex(ValueError,
f"{attr_name}"):
with open(tarname, 'rb') as f:
tar.addfile(replaced, f)
def test_list(self):
# Change some metadata to None, then compare list() output
# word-for-word. We want list() to not raise, and to only change
# printout for the affected piece of metadata.
# (n.b.: some contents of the test archive are hardcoded.)
for attr_names in ({'mtime'}, {'mode'}, {'uid'}, {'gid'},
{'uname'}, {'gname'},
{'uid', 'uname'}, {'gid', 'gname'}):
with (self.subTest(attr_names=attr_names),
tarfile.open(tarname, encoding="iso8859-1") as tar):
tio_prev = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n')
with support.swap_attr(sys, 'stdout', tio_prev):
tar.list()
for member in tar.getmembers():
for attr_name in attr_names:
setattr(member, attr_name, None)
tio_new = io.TextIOWrapper(io.BytesIO(), 'ascii', newline='\n')
with support.swap_attr(sys, 'stdout', tio_new):
tar.list()
for expected, got in zip(tio_prev.detach().getvalue().split(),
tio_new.detach().getvalue().split()):
if attr_names == {'mtime'} and re.match(rb'2003-01-\d\d', expected):
self.assertEqual(got, b'????-??-??')
elif attr_names == {'mtime'} and re.match(rb'\d\d:\d\d:\d\d', expected):
self.assertEqual(got, b'??:??:??')
elif attr_names == {'mode'} and re.match(
rb'.([r-][w-][x-]){3}', expected):
self.assertEqual(got, b'??????????')
elif attr_names == {'uname'} and expected.startswith(
(b'tarfile/', b'lars/', b'foo/')):
exp_user, exp_group = expected.split(b'/')
got_user, got_group = got.split(b'/')
self.assertEqual(got_group, exp_group)
self.assertRegex(got_user, b'[0-9]+')
elif attr_names == {'gname'} and expected.endswith(
(b'/tarfile', b'/users', b'/bar')):
exp_user, exp_group = expected.split(b'/')
got_user, got_group = got.split(b'/')
self.assertEqual(got_user, exp_user)
self.assertRegex(got_group, b'[0-9]+')
elif attr_names == {'uid'} and expected.startswith(
(b'1000/')):
exp_user, exp_group = expected.split(b'/')
got_user, got_group = got.split(b'/')
self.assertEqual(got_group, exp_group)
self.assertEqual(got_user, b'None')
elif attr_names == {'gid'} and expected.endswith((b'/100')):
exp_user, exp_group = expected.split(b'/')
got_user, got_group = got.split(b'/')
self.assertEqual(got_user, exp_user)
self.assertEqual(got_group, b'None')
elif attr_names == {'uid', 'uname'} and expected.startswith(
(b'tarfile/', b'lars/', b'foo/', b'1000/')):
exp_user, exp_group = expected.split(b'/')
got_user, got_group = got.split(b'/')
self.assertEqual(got_group, exp_group)
self.assertEqual(got_user, b'None')
elif attr_names == {'gname', 'gid'} and expected.endswith(
(b'/tarfile', b'/users', b'/bar', b'/100')):
exp_user, exp_group = expected.split(b'/')
got_user, got_group = got.split(b'/')
self.assertEqual(got_user, exp_user)
self.assertEqual(got_group, b'None')
else:
# In other cases the output should be the same
self.assertEqual(expected, got)
def _filemode_to_int(mode):
"""Inverse of `stat.filemode` (for permission bits)
Using mode strings rather than numbers makes the later tests more readable.
"""
str_mode = mode[1:]
result = (
{'r': stat.S_IRUSR, '-': 0}[str_mode[0]]
| {'w': stat.S_IWUSR, '-': 0}[str_mode[1]]
| {'x': stat.S_IXUSR, '-': 0,
's': stat.S_IXUSR | stat.S_ISUID,
'S': stat.S_ISUID}[str_mode[2]]
| {'r': stat.S_IRGRP, '-': 0}[str_mode[3]]
| {'w': stat.S_IWGRP, '-': 0}[str_mode[4]]
| {'x': stat.S_IXGRP, '-': 0,
's': stat.S_IXGRP | stat.S_ISGID,
'S': stat.S_ISGID}[str_mode[5]]
| {'r': stat.S_IROTH, '-': 0}[str_mode[6]]
| {'w': stat.S_IWOTH, '-': 0}[str_mode[7]]
| {'x': stat.S_IXOTH, '-': 0,
't': stat.S_IXOTH | stat.S_ISVTX,
'T': stat.S_ISVTX}[str_mode[8]]
)
# check we did this right
assert stat.filemode(result)[1:] == mode[1:]
return result
class ArchiveMaker:
"""Helper to create a tar file with specific contents
Usage:
with ArchiveMaker() as t:
t.add('filename', ...)
with t.open() as tar:
... # `tar` is now a TarFile with 'filename' in it!
"""
def __init__(self, **kwargs):
self.bio = io.BytesIO()
self.tar_kwargs = dict(kwargs)
def __enter__(self):
self.tar_w = tarfile.TarFile(mode='w', fileobj=self.bio, **self.tar_kwargs)
return self
def __exit__(self, *exc):
self.tar_w.close()
self.contents = self.bio.getvalue()
self.bio = None
def add(self, name, *, type=None, symlink_to=None, hardlink_to=None,
mode=None, size=None, content=None, **kwargs):
"""Add a member to the test archive. Call within `with`.
Provides many shortcuts:
- default `type` is based on symlink_to, hardlink_to, and trailing `/`
in name (which is stripped)
- size & content defaults are based on each other
- content can be str or bytes
- mode should be textual ('-rwxrwxrwx')
(add more! this is unstable internal test-only API)
"""
name = str(name)
tarinfo = tarfile.TarInfo(name).replace(**kwargs)
if content is not None:
if isinstance(content, str):
content = content.encode()
size = len(content)
if size is not None:
tarinfo.size = size
if content is None:
content = bytes(tarinfo.size)
if mode:
tarinfo.mode = _filemode_to_int(mode)
if symlink_to is not None:
type = tarfile.SYMTYPE
tarinfo.linkname = str(symlink_to)
if hardlink_to is not None:
type = tarfile.LNKTYPE
tarinfo.linkname = str(hardlink_to)
if name.endswith('/') and type is None:
type = tarfile.DIRTYPE
if type is not None:
tarinfo.type = type
if tarinfo.isreg():
fileobj = io.BytesIO(content)
else:
fileobj = None
self.tar_w.addfile(tarinfo, fileobj)
def open(self, **kwargs):
"""Open the resulting archive as TarFile. Call after `with`."""
bio = io.BytesIO(self.contents)
return tarfile.open(fileobj=bio, **kwargs)
# Under WASI, `os_helper.can_symlink` is False to make
# `skip_unless_symlink` skip symlink tests. "
# But in the following tests we use can_symlink to *determine* which
# behavior is expected.
# Like other symlink tests, skip these on WASI for now.
if support.is_wasi:
def symlink_test(f):
return unittest.skip("WASI: Skip symlink test for now")(f)
else:
def symlink_test(f):
return f
class TestExtractionFilters(unittest.TestCase):
# A temporary directory for the extraction results.
# All files that "escape" the destination path should still end
# up in this directory.
outerdir = pathlib.Path(TEMPDIR) / 'outerdir'
# The destination for the extraction, within `outerdir`
destdir = outerdir / 'dest'
@contextmanager
def check_context(self, tar, filter, *, check_flag=True):
"""Extracts `tar` to `self.destdir` and allows checking the result
If an error occurs, it must be checked using `expect_exception`
Otherwise, all resulting files must be checked using `expect_file`,
except the destination directory itself and parent directories of
other files.
When checking directories, do so before their contents.
A file called 'flag' is made in outerdir (i.e. outside destdir)
before extraction; it should not be altered nor should its contents
be read/copied.
"""
with os_helper.temp_dir(self.outerdir):
flag_path = self.outerdir / 'flag'
flag_path.write_text('capture me')
try:
tar.extractall(self.destdir, filter=filter)
except Exception as exc:
self.raised_exception = exc
self.reraise_exception = True
self.expected_paths = set()
else:
self.raised_exception = None
self.reraise_exception = False
self.expected_paths = set(self.outerdir.glob('**/*'))
self.expected_paths.discard(self.destdir)
self.expected_paths.discard(flag_path)
try:
yield self
finally:
tar.close()
if self.reraise_exception:
raise self.raised_exception
self.assertEqual(self.expected_paths, set())
if check_flag:
self.assertEqual(flag_path.read_text(), 'capture me')
else:
assert filter == 'fully_trusted'
def expect_file(self, name, type=None, symlink_to=None, mode=None,
size=None, content=None):
"""Check a single file. See check_context."""
if self.raised_exception:
raise self.raised_exception
# use normpath() rather than resolve() so we don't follow symlinks
path = pathlib.Path(os.path.normpath(self.destdir / name))
self.assertIn(path, self.expected_paths)
self.expected_paths.remove(path)
if mode is not None and os_helper.can_chmod() and os.name != 'nt':
got = stat.filemode(stat.S_IMODE(path.stat().st_mode))
self.assertEqual(got, mode)
if type is None and isinstance(name, str) and name.endswith('/'):
type = tarfile.DIRTYPE
if symlink_to is not None:
got = (self.destdir / name).readlink()
expected = pathlib.Path(symlink_to)
# The symlink might be the same (textually) as what we expect,
# but some systems change the link to an equivalent path, so
# we fall back to samefile().
try:
if expected != got:
self.assertTrue(got.samefile(expected))
except Exception as e:
# attach a note, so it's shown even if `samefile` fails
e.add_note(f'{expected=}, {got=}')
raise
elif type == tarfile.REGTYPE or type is None:
self.assertTrue(path.is_file())
elif type == tarfile.DIRTYPE:
self.assertTrue(path.is_dir())
elif type == tarfile.FIFOTYPE:
self.assertTrue(path.is_fifo())
elif type == tarfile.SYMTYPE:
self.assertTrue(path.is_symlink())
else:
raise NotImplementedError(type)
if size is not None:
self.assertEqual(path.stat().st_size, size)
if content is not None:
self.assertEqual(path.read_text(), content)
for parent in path.parents:
self.expected_paths.discard(parent)
def expect_any_tree(self, name):
"""Check a directory; forget about its contents."""
tree_path = (self.destdir / name).resolve()
self.expect_file(tree_path, type=tarfile.DIRTYPE)
self.expected_paths = {
p for p in self.expected_paths
if tree_path not in p.parents
}
def expect_exception(self, exc_type, message_re='.'):
with self.assertRaisesRegex(exc_type, message_re):
if self.raised_exception is not None:
raise self.raised_exception
self.reraise_exception = False
return self.raised_exception
def test_benign_file(self):
with ArchiveMaker() as arc:
arc.add('benign.txt')
for filter in 'fully_trusted', 'tar', 'data':
with self.check_context(arc.open(), filter):
self.expect_file('benign.txt')
def test_absolute(self):
# Test handling a member with an absolute path
# Inspired by 'absolute1' in https://github.com/jwilk/traversal-archives
with ArchiveMaker() as arc:
arc.add(self.outerdir / 'escaped.evil')
with self.check_context(arc.open(), 'fully_trusted'):
self.expect_file('../escaped.evil')
for filter in 'tar', 'data':
with self.check_context(arc.open(), filter):
if str(self.outerdir).startswith('/'):
# We strip leading slashes, as e.g. GNU tar does
# (without --absolute-filenames).
outerdir_stripped = str(self.outerdir).lstrip('/')
self.expect_file(f'{outerdir_stripped}/escaped.evil')
else:
# On this system, absolute paths don't have leading
# slashes.
# So, there's nothing to strip. We refuse to unpack
# to an absolute path, nonetheless.
self.expect_exception(
tarfile.AbsolutePathError,
"""['"].*escaped.evil['"] has an absolute path""")
@symlink_test
def test_parent_symlink(self):
# Test interplaying symlinks
# Inspired by 'dirsymlink2a' in jwilk/traversal-archives
with ArchiveMaker() as arc:
# `current` links to `.` which is both:
# - the destination directory
# - `current` itself
arc.add('current', symlink_to='.')
# effectively points to ./../
arc.add('parent', symlink_to='current/..')
arc.add('parent/evil')
if os_helper.can_symlink():
with self.check_context(arc.open(), 'fully_trusted'):
if self.raised_exception is not None:
# Windows will refuse to create a file that's a symlink to itself
# (and tarfile doesn't swallow that exception)
self.expect_exception(FileExistsError)
# The other cases will fail with this error too.
# Skip the rest of this test.
return
else:
self.expect_file('current', symlink_to='.')
self.expect_file('parent', symlink_to='current/..')
self.expect_file('../evil')
with self.check_context(arc.open(), 'tar'):
self.expect_exception(
tarfile.OutsideDestinationError,
"""'parent/evil' would be extracted to ['"].*evil['"], """
+ "which is outside the destination")
with self.check_context(arc.open(), 'data'):
self.expect_exception(
tarfile.LinkOutsideDestinationError,
"""'parent' would link to ['"].*outerdir['"], """
+ "which is outside the destination")
else:
# No symlink support. The symlinks are ignored.
with self.check_context(arc.open(), 'fully_trusted'):
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'tar'):
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'data'):
self.expect_file('parent/evil')
@symlink_test
@os_helper.skip_unless_symlink
def test_realpath_limit_attack(self):
# (CVE-2025-4517)
with ArchiveMaker() as arc:
# populate the symlinks and dirs that expand in os.path.realpath()
# The component length is chosen so that in common cases, the unexpanded
# path fits in PATH_MAX, but it overflows when the final symlink
# is expanded
steps = "abcdefghijklmnop"
if sys.platform == 'win32':
component = 'd' * 25
elif 'PC_PATH_MAX' in os.pathconf_names:
max_path_len = os.pathconf(self.outerdir.parent, "PC_PATH_MAX")
path_sep_len = 1
dest_len = len(str(self.destdir)) + path_sep_len
component_len = (max_path_len - dest_len) // (len(steps) + path_sep_len)
component = 'd' * component_len
else:
raise NotImplementedError("Need to guess component length for {sys.platform}")
path = ""
step_path = ""
for i in steps:
arc.add(os.path.join(path, component), type=tarfile.DIRTYPE,
mode='drwxrwxrwx')
arc.add(os.path.join(path, i), symlink_to=component)
path = os.path.join(path, component)
step_path = os.path.join(step_path, i)
# create the final symlink that exceeds PATH_MAX and simply points
# to the top dir.
# this link will never be expanded by
# os.path.realpath(strict=False), nor anything after it.
linkpath = os.path.join(*steps, "l"*254)
parent_segments = [".."] * len(steps)
arc.add(linkpath, symlink_to=os.path.join(*parent_segments))
# make a symlink outside to keep the tar command happy
arc.add("escape", symlink_to=os.path.join(linkpath, ".."))
# use the symlinks above, that are not checked, to create a hardlink
# to a file outside of the destination path
arc.add("flaglink", hardlink_to=os.path.join("escape", "flag"))
# now that we have the hardlink we can overwrite the file
arc.add("flaglink", content='overwrite')
# we can also create new files as well!
arc.add("escape/newfile", content='new')
with (self.subTest('fully_trusted'),
self.check_context(arc.open(), filter='fully_trusted',
check_flag=False)):
if sys.platform == 'win32':
self.expect_exception((FileNotFoundError, FileExistsError))
elif self.raised_exception:
# Cannot symlink/hardlink: tarfile falls back to getmember()
self.expect_exception(KeyError)
# Otherwise, this block should never enter.
else:
self.expect_any_tree(component)
self.expect_file('flaglink', content='overwrite')
self.expect_file('../newfile', content='new')
self.expect_file('escape', type=tarfile.SYMTYPE)
self.expect_file('a', symlink_to=component)
for filter in 'tar', 'data':
with self.subTest(filter), self.check_context(arc.open(), filter=filter):
exc = self.expect_exception((OSError, KeyError))
if isinstance(exc, OSError):
if sys.platform == 'win32':
# 3: ERROR_PATH_NOT_FOUND
# 5: ERROR_ACCESS_DENIED
# 206: ERROR_FILENAME_EXCED_RANGE
self.assertIn(exc.winerror, (3, 5, 206))
else:
self.assertEqual(exc.errno, errno.ENAMETOOLONG)
@symlink_test
def test_parent_symlink2(self):
# Test interplaying symlinks
# Inspired by 'dirsymlink2b' in jwilk/traversal-archives
# Posix and Windows have different pathname resolution:
# either symlink or a '..' component resolve first.
# Let's see which we are on.
if os_helper.can_symlink():
testpath = os.path.join(TEMPDIR, 'resolution_test')
os.mkdir(testpath)
# testpath/current links to `.` which is all of:
# - `testpath`
# - `testpath/current`
# - `testpath/current/current`
# - etc.
os.symlink('.', os.path.join(testpath, 'current'))
# we'll test where `testpath/current/../file` ends up
with open(os.path.join(testpath, 'current', '..', 'file'), 'w'):
pass
if os.path.exists(os.path.join(testpath, 'file')):
# Windows collapses 'current\..' to '.' first, leaving
# 'testpath\file'
dotdot_resolves_early = True
elif os.path.exists(os.path.join(testpath, '..', 'file')):
# Posix resolves 'current' to '.' first, leaving
# 'testpath/../file'
dotdot_resolves_early = False
else:
raise AssertionError('Could not determine link resolution')
with ArchiveMaker() as arc:
# `current` links to `.` which is both the destination directory
# and `current` itself
arc.add('current', symlink_to='.')
# `current/parent` is also available as `./parent`,
# and effectively points to `./../`
arc.add('current/parent', symlink_to='..')
arc.add('parent/evil')
with self.check_context(arc.open(), 'fully_trusted'):
if os_helper.can_symlink():
self.expect_file('current', symlink_to='.')
self.expect_file('parent', symlink_to='..')
self.expect_file('../evil')
else:
self.expect_file('current/')
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'tar'):
if os_helper.can_symlink():
# Fail when extracting a file outside destination
self.expect_exception(
tarfile.OutsideDestinationError,
"'parent/evil' would be extracted to "
+ """['"].*evil['"], which is outside """
+ "the destination")
else:
self.expect_file('current/')
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'data'):
if os_helper.can_symlink():
if dotdot_resolves_early:
# Fail when extracting a file outside destination
self.expect_exception(
tarfile.OutsideDestinationError,
"'parent/evil' would be extracted to "
+ """['"].*evil['"], which is outside """
+ "the destination")
else:
# Fail as soon as we have a symlink outside the destination
self.expect_exception(
tarfile.LinkOutsideDestinationError,
"'current/parent' would link to "
+ """['"].*outerdir['"], which is outside """
+ "the destination")
else:
self.expect_file('current/')
self.expect_file('parent/evil')
@symlink_test
def test_absolute_symlink(self):
# Test symlink to an absolute path
# Inspired by 'dirsymlink' in jwilk/traversal-archives
with ArchiveMaker() as arc:
arc.add('parent', symlink_to=self.outerdir)
arc.add('parent/evil')
with self.check_context(arc.open(), 'fully_trusted'):
if os_helper.can_symlink():
self.expect_file('parent', symlink_to=self.outerdir)
self.expect_file('../evil')
else:
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'tar'):
if os_helper.can_symlink():
self.expect_exception(
tarfile.OutsideDestinationError,
"'parent/evil' would be extracted to "
+ """['"].*evil['"], which is outside """
+ "the destination")
else:
self.expect_file('parent/evil')
with self.check_context(arc.open(), 'data'):
self.expect_exception(
tarfile.AbsoluteLinkError,
"'parent' is a link to an absolute path")
def test_absolute_hardlink(self):
# Test hardlink to an absolute path
# Inspired by 'dirsymlink' in https://github.com/jwilk/traversal-archives
with ArchiveMaker() as arc:
arc.add('parent', hardlink_to=self.outerdir / 'foo')
with self.check_context(arc.open(), 'fully_trusted'):
self.expect_exception(KeyError, ".*foo. not found")
with self.check_context(arc.open(), 'tar'):
self.expect_exception(KeyError, ".*foo. not found")
with self.check_context(arc.open(), 'data'):
self.expect_exception(
tarfile.AbsoluteLinkError,
"'parent' is a link to an absolute path")
@symlink_test
def test_sly_relative0(self):
# Inspired by 'relative0' in jwilk/traversal-archives
with ArchiveMaker() as arc:
# points to `../../tmp/moo`
arc.add('../moo', symlink_to='..//tmp/moo')
try:
with self.check_context(arc.open(), filter='fully_trusted'):
if os_helper.can_symlink():
if isinstance(self.raised_exception, FileExistsError):
# XXX TarFile happens to fail creating a parent
# directory.
# This might be a bug, but fixing it would hurt
# security.
# Note that e.g. GNU `tar` rejects '..' components,
# so you could argue this is an invalid archive and we
# just raise an bad type of exception.
self.expect_exception(FileExistsError)
else:
self.expect_file('../moo', symlink_to='..//tmp/moo')
else:
# The symlink can't be extracted and is ignored
pass
except FileExistsError:
pass
for filter in 'tar', 'data':
with self.check_context(arc.open(), filter):
self.expect_exception(
tarfile.OutsideDestinationError,
"'../moo' would be extracted to "
+ "'.*moo', which is outside "
+ "the destination")
@symlink_test
def test_sly_relative2(self):
# Inspired by 'relative2' in jwilk/traversal-archives
with ArchiveMaker() as arc:
arc.add('tmp/')
arc.add('tmp/../../moo', symlink_to='tmp/../..//tmp/moo')
with self.check_context(arc.open(), 'fully_trusted'):
self.expect_file('tmp', type=tarfile.DIRTYPE)
if os_helper.can_symlink():
self.expect_file('../moo', symlink_to='tmp/../../tmp/moo')
for filter in 'tar', 'data':
with self.check_context(arc.open(), filter):
self.expect_exception(
tarfile.OutsideDestinationError,
"'tmp/../../moo' would be extracted to "
+ """['"].*moo['"], which is outside the """
+ "destination")
@symlink_test
def test_deep_symlink(self):
# Test that symlinks and hardlinks inside a directory
# point to the correct file (`target` of size 3).
# If links aren't supported we get a copy of the file.
with ArchiveMaker() as arc:
arc.add('targetdir/target', size=3)
# a hardlink's linkname is relative to the archive
arc.add('linkdir/hardlink', hardlink_to=os.path.join(
'targetdir', 'target'))
# a symlink's linkname is relative to the link's directory
arc.add('linkdir/symlink', symlink_to=os.path.join(
'..', 'targetdir', 'target'))
for filter in 'tar', 'data', 'fully_trusted':
with self.check_context(arc.open(), filter):
self.expect_file('targetdir/target', size=3)
self.expect_file('linkdir/hardlink', size=3)
if os_helper.can_symlink():
self.expect_file('linkdir/symlink', size=3,
symlink_to='../targetdir/target')
else:
self.expect_file('linkdir/symlink', size=3)
@symlink_test
def test_chains(self):
# Test chaining of symlinks/hardlinks.
# Symlinks are created before the files they point to.
with ArchiveMaker() as arc:
arc.add('linkdir/symlink', symlink_to='hardlink')
arc.add('symlink2', symlink_to=os.path.join(
'linkdir', 'hardlink2'))
arc.add('targetdir/target', size=3)
arc.add('linkdir/hardlink', hardlink_to=os.path.join('targetdir', 'target'))
arc.add('linkdir/hardlink2', hardlink_to=os.path.join('linkdir', 'symlink'))
for filter in 'tar', 'data', 'fully_trusted':
with self.check_context(arc.open(), filter):
self.expect_file('targetdir/target', size=3)
self.expect_file('linkdir/hardlink', size=3)
self.expect_file('linkdir/hardlink2', size=3)
if os_helper.can_symlink():
self.expect_file('linkdir/symlink', size=3,
symlink_to='hardlink')
self.expect_file('symlink2', size=3,
symlink_to='linkdir/hardlink2')
else:
self.expect_file('linkdir/symlink', size=3)
self.expect_file('symlink2', size=3)
@symlink_test
def test_sneaky_hardlink_fallback(self):
# (CVE-2025-4330)
# Test that when hardlink extraction falls back to extracting members
# from the archive, the extracted member is (re-)filtered.
with ArchiveMaker() as arc:
# Create a directory structure so the c/escape symlink stays
# inside the path
arc.add("a/t/dummy")
# Create b/ directory
arc.add("b/")
# Point "c" to the bottom of the tree in "a"
arc.add("c", symlink_to=os.path.join("a", "t"))
# link to non-existant location under "a"
arc.add("c/escape", symlink_to=os.path.join("..", "..",
"link_here"))
# Move "c" to point to "b" ("c/escape" no longer exists)
arc.add("c", symlink_to="b")
# Attempt to create a hard link to "c/escape". Since it doesn't
# exist it will attempt to extract "cescape" but at "boom".
arc.add("boom", hardlink_to=os.path.join("c", "escape"))
with self.check_context(arc.open(), 'data'):
if not os_helper.can_symlink():
# When 'c/escape' is extracted, 'c' is a regular
# directory, and 'c/escape' *would* point outside
# the destination if symlinks were allowed.
self.expect_exception(
tarfile.LinkOutsideDestinationError)
elif sys.platform == "win32":
# On Windows, 'c/escape' points outside the destination
self.expect_exception(tarfile.LinkOutsideDestinationError)
else:
e = self.expect_exception(
tarfile.LinkFallbackError,
"link 'boom' would be extracted as a copy of "
+ "'c/escape', which was rejected")
self.assertIsInstance(e.__cause__,
tarfile.LinkOutsideDestinationError)
for filter in 'tar', 'fully_trusted':
with self.subTest(filter), self.check_context(arc.open(), filter):
if not os_helper.can_symlink():
self.expect_file("a/t/dummy")
self.expect_file("b/")
self.expect_file("c/")
else:
self.expect_file("a/t/dummy")
self.expect_file("b/")
self.expect_file("a/t/escape", symlink_to='../../link_here')
self.expect_file("boom", symlink_to='../../link_here')
self.expect_file("c", symlink_to='b')
@symlink_test
def test_exfiltration_via_symlink(self):
# (CVE-2025-4138)
# Test changing symlinks that result in a symlink pointing outside
# the extraction directory, unless prevented by 'data' filter's
# normalization.
with ArchiveMaker() as arc:
arc.add("escape", symlink_to=os.path.join('link', 'link', '..', '..', 'link-here'))
arc.add("link", symlink_to='./')
for filter in 'tar', 'data', 'fully_trusted':
with self.check_context(arc.open(), filter):
if os_helper.can_symlink():
self.expect_file("link", symlink_to='./')
if filter == 'data':
self.expect_file("escape", symlink_to='link-here')
else:
self.expect_file("escape",
symlink_to='link/link/../../link-here')
else:
# Nothing is extracted.
pass
@symlink_test
def test_chmod_outside_dir(self):
# (CVE-2024-12718)
# Test that members used for delayed updates of directory metadata
# are (re-)filtered.
with ArchiveMaker() as arc:
# "pwn" is a veeeery innocent symlink:
arc.add("a/pwn", symlink_to='.')
# But now "pwn" is also a directory, so it's scheduled to have its
# metadata updated later:
arc.add("a/pwn/", mode='drwxrwxrwx')
# Oops, "pwn" is not so innocent any more:
arc.add("a/pwn", symlink_to='x/../')
# Newly created symlink points to the dest dir,
# so it's OK for the "data" filter.
arc.add('a/x', symlink_to=('../'))
# But now "pwn" points outside the dest dir
for filter in 'tar', 'data', 'fully_trusted':
with self.check_context(arc.open(), filter) as cc:
if not os_helper.can_symlink():
self.expect_file("a/pwn/")
elif filter == 'data':
self.expect_file("a/x", symlink_to='../')
self.expect_file("a/pwn", symlink_to='.')
else:
self.expect_file("a/x", symlink_to='../')
self.expect_file("a/pwn", symlink_to='x/../')
if sys.platform != "win32":
st_mode = cc.outerdir.stat().st_mode
self.assertNotEqual(st_mode & 0o777, 0o777)
def test_link_fallback_normalizes(self):
# Make sure hardlink fallbacks work for non-normalized paths for all
# filters
with ArchiveMaker() as arc:
arc.add("dir/")
arc.add("dir/../afile")
arc.add("link1", hardlink_to='dir/../afile')
arc.add("link2", hardlink_to='dir/../dir/../afile')
for filter in 'tar', 'data', 'fully_trusted':
with self.check_context(arc.open(), filter) as cc:
self.expect_file("dir/")
self.expect_file("afile")
self.expect_file("link1")
self.expect_file("link2")
def test_modes(self):
# Test how file modes are extracted
# (Note that the modes are ignored on platforms without working chmod)
with ArchiveMaker() as arc:
arc.add('all_bits', mode='?rwsrwsrwt')
arc.add('perm_bits', mode='?rwxrwxrwx')
arc.add('exec_group_other', mode='?rw-rwxrwx')
arc.add('read_group_only', mode='?---r-----')
arc.add('no_bits', mode='?---------')
arc.add('dir/', mode='?---rwsrwt')
arc.add('dir_all_bits/', mode='?rwsrwsrwt')
# On some systems, setting the uid, gid, and/or sticky bit is a no-ops.
# Check which bits we can set, so we can compare tarfile machinery to
# a simple chmod.
tmp_filename = os.path.join(TEMPDIR, "tmp.file")
with open(tmp_filename, 'w'):
pass
try:
new_mode = (os.stat(tmp_filename).st_mode
| stat.S_ISVTX | stat.S_ISGID | stat.S_ISUID)
try:
os.chmod(tmp_filename, new_mode)
except OSError as exc:
if exc.errno == getattr(errno, "EFTYPE", 0):
# gh-108948: On FreeBSD, regular users cannot set
# the sticky bit.
self.skipTest("chmod() failed with EFTYPE: "
"regular users cannot set sticky bit")
else:
raise
got_mode = os.stat(tmp_filename).st_mode
_t_file = 't' if (got_mode & stat.S_ISVTX) else 'x'
_suid_file = 's' if (got_mode & stat.S_ISUID) else 'x'
_sgid_file = 's' if (got_mode & stat.S_ISGID) else 'x'
finally:
os.unlink(tmp_filename)
os.mkdir(tmp_filename)
new_mode = (os.stat(tmp_filename).st_mode
| stat.S_ISVTX | stat.S_ISGID | stat.S_ISUID)
os.chmod(tmp_filename, new_mode)
got_mode = os.stat(tmp_filename).st_mode
_t_dir = 't' if (got_mode & stat.S_ISVTX) else 'x'
_suid_dir = 's' if (got_mode & stat.S_ISUID) else 'x'
_sgid_dir = 's' if (got_mode & stat.S_ISGID) else 'x'
os.rmdir(tmp_filename)
with self.check_context(arc.open(), 'fully_trusted'):
self.expect_file('all_bits',
mode=f'?rw{_suid_file}rw{_sgid_file}rw{_t_file}')
self.expect_file('perm_bits', mode='?rwxrwxrwx')
self.expect_file('exec_group_other', mode='?rw-rwxrwx')
self.expect_file('read_group_only', mode='?---r-----')
self.expect_file('no_bits', mode='?---------')
self.expect_file('dir/', mode=f'?---rw{_sgid_dir}rw{_t_dir}')
self.expect_file('dir_all_bits/',
mode=f'?rw{_suid_dir}rw{_sgid_dir}rw{_t_dir}')
with self.check_context(arc.open(), 'tar'):
self.expect_file('all_bits', mode='?rwxr-xr-x')
self.expect_file('perm_bits', mode='?rwxr-xr-x')
self.expect_file('exec_group_other', mode='?rw-r-xr-x')
self.expect_file('read_group_only', mode='?---r-----')
self.expect_file('no_bits', mode='?---------')
self.expect_file('dir/', mode='?---r-xr-x')
self.expect_file('dir_all_bits/', mode='?rwxr-xr-x')
with self.check_context(arc.open(), 'data'):
normal_dir_mode = stat.filemode(stat.S_IMODE(
self.outerdir.stat().st_mode))
self.expect_file('all_bits', mode='?rwxr-xr-x')
self.expect_file('perm_bits', mode='?rwxr-xr-x')
self.expect_file('exec_group_other', mode='?rw-r--r--')
self.expect_file('read_group_only', mode='?rw-r-----')
self.expect_file('no_bits', mode='?rw-------')
self.expect_file('dir/', mode=normal_dir_mode)
self.expect_file('dir_all_bits/', mode=normal_dir_mode)
def test_pipe(self):
# Test handling of a special file
with ArchiveMaker() as arc:
arc.add('foo', type=tarfile.FIFOTYPE)
for filter in 'fully_trusted', 'tar':
with self.check_context(arc.open(), filter):
if hasattr(os, 'mkfifo'):
self.expect_file('foo', type=tarfile.FIFOTYPE)
else:
# The pipe can't be extracted and is skipped.
pass
with self.check_context(arc.open(), 'data'):
self.expect_exception(
tarfile.SpecialFileError,
"'foo' is a special file")
def test_special_files(self):
# Creating device files is tricky. Instead of attempting that let's
# only check the filter result.
for special_type in tarfile.FIFOTYPE, tarfile.CHRTYPE, tarfile.BLKTYPE:
tarinfo = tarfile.TarInfo('foo')
tarinfo.type = special_type
trusted = tarfile.fully_trusted_filter(tarinfo, '')
self.assertIs(trusted, tarinfo)
tar = tarfile.tar_filter(tarinfo, '')
self.assertEqual(tar.type, special_type)
with self.assertRaises(tarfile.SpecialFileError) as cm:
tarfile.data_filter(tarinfo, '')
self.assertIsInstance(cm.exception.tarinfo, tarfile.TarInfo)
self.assertEqual(cm.exception.tarinfo.name, 'foo')
def test_fully_trusted_filter(self):
# The 'fully_trusted' filter returns the original TarInfo objects.
with tarfile.TarFile.open(tarname) as tar:
for tarinfo in tar.getmembers():
filtered = tarfile.fully_trusted_filter(tarinfo, '')
self.assertIs(filtered, tarinfo)
def test_tar_filter(self):
# The 'tar' filter returns TarInfo objects with the same name/type.
# (It can also fail for particularly "evil" input, but we don't have
# that in the test archive.)
with tarfile.TarFile.open(tarname, encoding="iso8859-1") as tar:
for tarinfo in tar.getmembers():
try:
filtered = tarfile.tar_filter(tarinfo, '')
except UnicodeEncodeError:
continue
self.assertIs(filtered.name, tarinfo.name)
self.assertIs(filtered.type, tarinfo.type)
def test_data_filter(self):
# The 'data' filter either raises, or returns TarInfo with the same
# name/type.
with tarfile.TarFile.open(tarname, encoding="iso8859-1") as tar:
for tarinfo in tar.getmembers():
try:
filtered = tarfile.data_filter(tarinfo, '')
except (tarfile.FilterError, UnicodeEncodeError):
continue
self.assertIs(filtered.name, tarinfo.name)
self.assertIs(filtered.type, tarinfo.type)
@unittest.skipIf(sys.platform == 'win32', 'requires native bytes paths')
def test_filter_unencodable(self):
# Sanity check using a valid path.
tarinfo = tarfile.TarInfo(os_helper.TESTFN)
filtered = tarfile.tar_filter(tarinfo, '')
self.assertIs(filtered.name, tarinfo.name)
filtered = tarfile.data_filter(tarinfo, '')
self.assertIs(filtered.name, tarinfo.name)
tarinfo = tarfile.TarInfo('test\x00')
self.assertRaises(ValueError, tarfile.tar_filter, tarinfo, '')
self.assertRaises(ValueError, tarfile.data_filter, tarinfo, '')
tarinfo = tarfile.TarInfo('\ud800')
self.assertRaises(UnicodeEncodeError, tarfile.tar_filter, tarinfo, '')
self.assertRaises(UnicodeEncodeError, tarfile.data_filter, tarinfo, '')
@unittest.skipIf(sys.platform == 'win32', 'requires native bytes paths')
def test_extract_unencodable(self):
# Create a member with name \xed\xa0\x80 which is UTF-8 encoded
# lone surrogate \ud800.
with ArchiveMaker(encoding='ascii', errors='surrogateescape') as arc:
arc.add('\udced\udca0\udc80')
with os_helper.temp_cwd() as tmp:
tar = arc.open(encoding='utf-8', errors='surrogatepass',
errorlevel=1)
self.assertEqual(tar.getnames(), ['\ud800'])
with self.assertRaises(UnicodeEncodeError):
tar.extractall(filter=tarfile.tar_filter)
self.assertEqual(os.listdir(), [])
tar = arc.open(encoding='utf-8', errors='surrogatepass',
errorlevel=0, debug=1)
with support.captured_stderr() as stderr:
tar.extractall(filter=tarfile.tar_filter)
self.assertEqual(os.listdir(), [])
self.assertIn('tarfile: UnicodeEncodeError ', stderr.getvalue())
def test_default_filter_warns(self):
"""Ensure the default filter warns"""
with ArchiveMaker() as arc:
arc.add('foo')
with warnings_helper.check_warnings(
('Python 3.14', DeprecationWarning)):
with self.check_context(arc.open(), None):
self.expect_file('foo')
def test_change_default_filter_on_instance(self):
tar = tarfile.TarFile(tarname, 'r')
def strict_filter(tarinfo, path):
if tarinfo.name == 'ustar/regtype':
return tarinfo
else:
return None
tar.extraction_filter = strict_filter
with self.check_context(tar, None):
self.expect_file('ustar/regtype')
def test_change_default_filter_on_class(self):
def strict_filter(tarinfo, path):
if tarinfo.name == 'ustar/regtype':
return tarinfo
else:
return None
tar = tarfile.TarFile(tarname, 'r')
with support.swap_attr(tarfile.TarFile, 'extraction_filter',
staticmethod(strict_filter)):
with self.check_context(tar, None):
self.expect_file('ustar/regtype')
def test_change_default_filter_on_subclass(self):
class TarSubclass(tarfile.TarFile):
def extraction_filter(self, tarinfo, path):
if tarinfo.name == 'ustar/regtype':
return tarinfo
else:
return None
tar = TarSubclass(tarname, 'r')
with self.check_context(tar, None):
self.expect_file('ustar/regtype')
def test_change_default_filter_to_string(self):
tar = tarfile.TarFile(tarname, 'r')
tar.extraction_filter = 'data'
with self.check_context(tar, None):
self.expect_exception(TypeError)
def test_custom_filter(self):
def custom_filter(tarinfo, path):
self.assertIs(path, self.destdir)
if tarinfo.name == 'move_this':
return tarinfo.replace(name='moved')
if tarinfo.name == 'ignore_this':
return None
return tarinfo
with ArchiveMaker() as arc:
arc.add('move_this')
arc.add('ignore_this')
arc.add('keep')
with self.check_context(arc.open(), custom_filter):
self.expect_file('moved')
self.expect_file('keep')
def test_bad_filter_name(self):
with ArchiveMaker() as arc:
arc.add('foo')
with self.check_context(arc.open(), 'bad filter name'):
self.expect_exception(ValueError)
def test_stateful_filter(self):
# Stateful filters should be possible.
# (This doesn't really test tarfile. Rather, it demonstrates
# that third parties can implement a stateful filter.)
class StatefulFilter:
def __enter__(self):
self.num_files_processed = 0
return self
def __call__(self, tarinfo, path):
try:
tarinfo = tarfile.data_filter(tarinfo, path)
except tarfile.FilterError:
return None
self.num_files_processed += 1
return tarinfo
def __exit__(self, *exc_info):
self.done = True
with ArchiveMaker() as arc:
arc.add('good')
arc.add('bad', symlink_to='/')
arc.add('good')
with StatefulFilter() as custom_filter:
with self.check_context(arc.open(), custom_filter):
self.expect_file('good')
self.assertEqual(custom_filter.num_files_processed, 2)
self.assertEqual(custom_filter.done, True)
def test_errorlevel(self):
def extracterror_filter(tarinfo, path):
raise tarfile.ExtractError('failed with ExtractError')
def filtererror_filter(tarinfo, path):
raise tarfile.FilterError('failed with FilterError')
def oserror_filter(tarinfo, path):
raise OSError('failed with OSError')
def tarerror_filter(tarinfo, path):
raise tarfile.TarError('failed with base TarError')
def valueerror_filter(tarinfo, path):
raise ValueError('failed with ValueError')
with ArchiveMaker() as arc:
arc.add('file')
# If errorlevel is 0, errors affected by errorlevel are ignored
with self.check_context(arc.open(errorlevel=0), extracterror_filter):
pass
with self.check_context(arc.open(errorlevel=0), filtererror_filter):
pass
with self.check_context(arc.open(errorlevel=0), oserror_filter):
pass
with self.check_context(arc.open(errorlevel=0), tarerror_filter):
self.expect_exception(tarfile.TarError)
with self.check_context(arc.open(errorlevel=0), valueerror_filter):
self.expect_exception(ValueError)
# If 1, all fatal errors are raised
with self.check_context(arc.open(errorlevel=1), extracterror_filter):
pass
with self.check_context(arc.open(errorlevel=1), filtererror_filter):
self.expect_exception(tarfile.FilterError)
with self.check_context(arc.open(errorlevel=1), oserror_filter):
self.expect_exception(OSError)
with self.check_context(arc.open(errorlevel=1), tarerror_filter):
self.expect_exception(tarfile.TarError)
with self.check_context(arc.open(errorlevel=1), valueerror_filter):
self.expect_exception(ValueError)
# If 2, all non-fatal errors are raised as well.
with self.check_context(arc.open(errorlevel=2), extracterror_filter):
self.expect_exception(tarfile.ExtractError)
with self.check_context(arc.open(errorlevel=2), filtererror_filter):
self.expect_exception(tarfile.FilterError)
with self.check_context(arc.open(errorlevel=2), oserror_filter):
self.expect_exception(OSError)
with self.check_context(arc.open(errorlevel=2), tarerror_filter):
self.expect_exception(tarfile.TarError)
with self.check_context(arc.open(errorlevel=2), valueerror_filter):
self.expect_exception(ValueError)
# We only handle ExtractionError, FilterError & OSError specially.
with self.check_context(arc.open(errorlevel='boo!'), filtererror_filter):
self.expect_exception(TypeError) # errorlevel is not int
class OverwriteTests(archiver_tests.OverwriteTests, unittest.TestCase):
testdir = os.path.join(TEMPDIR, "testoverwrite")
@classmethod
def setUpClass(cls):
p = cls.ar_with_file = os.path.join(TEMPDIR, 'tar-with-file.tar')
cls.addClassCleanup(os_helper.unlink, p)
with tarfile.open(p, 'w') as tar:
t = tarfile.TarInfo('test')
t.size = 10
tar.addfile(t, io.BytesIO(b'newcontent'))
p = cls.ar_with_dir = os.path.join(TEMPDIR, 'tar-with-dir.tar')
cls.addClassCleanup(os_helper.unlink, p)
with tarfile.open(p, 'w') as tar:
tar.addfile(tar.gettarinfo(os.curdir, 'test'))
p = os.path.join(TEMPDIR, 'tar-with-implicit-dir.tar')
cls.ar_with_implicit_dir = p
cls.addClassCleanup(os_helper.unlink, p)
with tarfile.open(p, 'w') as tar:
t = tarfile.TarInfo('test/file')
t.size = 10
tar.addfile(t, io.BytesIO(b'newcontent'))
def open(self, path):
return tarfile.open(path, 'r')
def extractall(self, ar):
ar.extractall(self.testdir, filter='fully_trusted')
class OffsetValidationTests(unittest.TestCase):
tarname = tmpname
invalid_posix_header = (
# name: 100 bytes
tarfile.NUL * tarfile.LENGTH_NAME
# mode, space, null terminator: 8 bytes
+ b"000755" + SPACE + tarfile.NUL
# uid, space, null terminator: 8 bytes
+ b"000001" + SPACE + tarfile.NUL
# gid, space, null terminator: 8 bytes
+ b"000001" + SPACE + tarfile.NUL
# size, space: 12 bytes
+ b"\xff" * 11 + SPACE
# mtime, space: 12 bytes
+ tarfile.NUL * 11 + SPACE
# chksum: 8 bytes
+ b"0011407" + tarfile.NUL
# type: 1 byte
+ tarfile.REGTYPE
# linkname: 100 bytes
+ tarfile.NUL * tarfile.LENGTH_LINK
# magic: 6 bytes, version: 2 bytes
+ tarfile.POSIX_MAGIC
# uname: 32 bytes
+ tarfile.NUL * 32
# gname: 32 bytes
+ tarfile.NUL * 32
# devmajor, space, null terminator: 8 bytes
+ tarfile.NUL * 6 + SPACE + tarfile.NUL
# devminor, space, null terminator: 8 bytes
+ tarfile.NUL * 6 + SPACE + tarfile.NUL
# prefix: 155 bytes
+ tarfile.NUL * tarfile.LENGTH_PREFIX
# padding: 12 bytes
+ tarfile.NUL * 12
)
invalid_gnu_header = (
# name: 100 bytes
tarfile.NUL * tarfile.LENGTH_NAME
# mode, null terminator: 8 bytes
+ b"0000755" + tarfile.NUL
# uid, null terminator: 8 bytes
+ b"0000001" + tarfile.NUL
# gid, space, null terminator: 8 bytes
+ b"0000001" + tarfile.NUL
# size, space: 12 bytes
+ b"\xff" * 11 + SPACE
# mtime, space: 12 bytes
+ tarfile.NUL * 11 + SPACE
# chksum: 8 bytes
+ b"0011327" + tarfile.NUL
# type: 1 byte
+ tarfile.REGTYPE
# linkname: 100 bytes
+ tarfile.NUL * tarfile.LENGTH_LINK
# magic: 8 bytes
+ tarfile.GNU_MAGIC
# uname: 32 bytes
+ tarfile.NUL * 32
# gname: 32 bytes
+ tarfile.NUL * 32
# devmajor, null terminator: 8 bytes
+ tarfile.NUL * 8
# devminor, null terminator: 8 bytes
+ tarfile.NUL * 8
# padding: 167 bytes
+ tarfile.NUL * 167
)
invalid_v7_header = (
# name: 100 bytes
tarfile.NUL * tarfile.LENGTH_NAME
# mode, space, null terminator: 8 bytes
+ b"000755" + SPACE + tarfile.NUL
# uid, space, null terminator: 8 bytes
+ b"000001" + SPACE + tarfile.NUL
# gid, space, null terminator: 8 bytes
+ b"000001" + SPACE + tarfile.NUL
# size, space: 12 bytes
+ b"\xff" * 11 + SPACE
# mtime, space: 12 bytes
+ tarfile.NUL * 11 + SPACE
# chksum: 8 bytes
+ b"0010070" + tarfile.NUL
# type: 1 byte
+ tarfile.REGTYPE
# linkname: 100 bytes
+ tarfile.NUL * tarfile.LENGTH_LINK
# padding: 255 bytes
+ tarfile.NUL * 255
)
valid_gnu_header = tarfile.TarInfo("filename").tobuf(tarfile.GNU_FORMAT)
data_block = b"\xff" * tarfile.BLOCKSIZE
def _write_buffer(self, buffer):
with open(self.tarname, "wb") as f:
f.write(buffer)
def _get_members(self, ignore_zeros=None):
with open(self.tarname, "rb") as f:
with tarfile.open(
mode="r", fileobj=f, ignore_zeros=ignore_zeros
) as tar:
return tar.getmembers()
def _assert_raises_read_error_exception(self):
with self.assertRaisesRegex(
tarfile.ReadError, "file could not be opened successfully"
):
self._get_members()
def test_invalid_offset_header_validations(self):
for tar_format, invalid_header in (
("posix", self.invalid_posix_header),
("gnu", self.invalid_gnu_header),
("v7", self.invalid_v7_header),
):
with self.subTest(format=tar_format):
self._write_buffer(invalid_header)
self._assert_raises_read_error_exception()
def test_early_stop_at_invalid_offset_header(self):
buffer = self.valid_gnu_header + self.invalid_gnu_header + self.valid_gnu_header
self._write_buffer(buffer)
members = self._get_members()
self.assertEqual(len(members), 1)
self.assertEqual(members[0].name, "filename")
self.assertEqual(members[0].offset, 0)
def test_ignore_invalid_archive(self):
# 3 invalid headers with their respective data
buffer = (self.invalid_gnu_header + self.data_block) * 3
self._write_buffer(buffer)
members = self._get_members(ignore_zeros=True)
self.assertEqual(len(members), 0)
def test_ignore_invalid_offset_headers(self):
for first_block, second_block, expected_offset in (
(
(self.valid_gnu_header),
(self.invalid_gnu_header + self.data_block),
0,
),
(
(self.invalid_gnu_header + self.data_block),
(self.valid_gnu_header),
1024,
),
):
self._write_buffer(first_block + second_block)
members = self._get_members(ignore_zeros=True)
self.assertEqual(len(members), 1)
self.assertEqual(members[0].name, "filename")
self.assertEqual(members[0].offset, expected_offset)
def setUpModule():
os_helper.unlink(TEMPDIR)
os.makedirs(TEMPDIR)
global testtarnames
testtarnames = [tarname]
with open(tarname, "rb") as fobj:
data = fobj.read()
# Create compressed tarfiles.
for c in GzipTest, Bz2Test, LzmaTest:
if c.open:
os_helper.unlink(c.tarname)
testtarnames.append(c.tarname)
with c.open(c.tarname, "wb") as tar:
tar.write(data)
def tearDownModule():
if os.path.exists(TEMPDIR):
os_helper.rmtree(TEMPDIR)
if __name__ == "__main__":
unittest.main()
|