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
|
/* URL handling.
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
2005, 2006, 2007, 2008, 2009, 2010, 2011, 2015 Free Software
Foundation, Inc.
This file is part of GNU Wget.
GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or (at
your option) any later version.
GNU Wget is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Wget. If not, see <http://www.gnu.org/licenses/>.
Additional permission under GNU GPL version 3 section 7
If you modify this program, or any covered work, by linking or
combining it with the OpenSSL project's OpenSSL library (or a
modified version of that library), containing parts covered by the
terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
grants you additional permission to convey the resulting work.
Corresponding Source for a non-source form of such a combination
shall include the source code for the parts of OpenSSL used as well
as that of the covered work. */
#include "wget.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <assert.h>
#include "utils.h"
#include "url.h"
#include "host.h" /* for is_valid_ipv6_address */
#include "c-strcase.h"
#if HAVE_ICONV
#include <iconv.h>
#include <langinfo.h>
#endif
#ifdef __VMS
#include "vms.h"
#endif /* def __VMS */
#ifdef TESTING
#include "test.h"
#endif
enum {
scm_disabled = 1, /* for https when OpenSSL fails to init. */
scm_has_params = 2, /* whether scheme has ;params */
scm_has_query = 4, /* whether scheme has ?query */
scm_has_fragment = 8 /* whether scheme has #fragment */
};
struct scheme_data
{
/* Short name of the scheme, such as "http" or "ftp". */
const char *name;
/* Leading string that identifies the scheme, such as "https://". */
const char *leading_string;
/* Default port of the scheme when none is specified. */
int default_port;
/* Various flags. */
int flags;
};
/* Supported schemes: */
static struct scheme_data supported_schemes[] =
{
{ "http", "http://", DEFAULT_HTTP_PORT, scm_has_query|scm_has_fragment },
#ifdef HAVE_SSL
{ "https", "https://", DEFAULT_HTTPS_PORT, scm_has_query|scm_has_fragment },
#endif
{ "ftp", "ftp://", DEFAULT_FTP_PORT, scm_has_params|scm_has_fragment },
#ifdef HAVE_SSL
/*
* Explicit FTPS uses the same port as FTP.
* Implicit FTPS has its own port (990), but it is disabled by default.
*/
{ "ftps", "ftps://", DEFAULT_FTP_PORT, scm_has_params|scm_has_fragment },
#endif
/* SCHEME_INVALID */
{ NULL, NULL, -1, 0 }
};
/* Forward declarations: */
static bool path_simplify (enum url_scheme, char *);
/* Support for escaping and unescaping of URL strings. */
/* Table of "reserved" and "unsafe" characters. Those terms are
rfc1738-speak, as such largely obsoleted by rfc2396 and later
specs, but the general idea remains.
A reserved character is the one that you can't decode without
changing the meaning of the URL. For example, you can't decode
"/foo/%2f/bar" into "/foo///bar" because the number and contents of
path components is different. Non-reserved characters can be
changed, so "/foo/%78/bar" is safe to change to "/foo/x/bar". The
unsafe characters are loosely based on rfc1738, plus "$" and ",",
as recommended by rfc2396, and minus "~", which is very frequently
used (and sometimes unrecognized as %7E by broken servers).
An unsafe character is the one that should be encoded when URLs are
placed in foreign environments. E.g. space and newline are unsafe
in HTTP contexts because HTTP uses them as separator and line
terminator, so they must be encoded to %20 and %0A respectively.
"*" is unsafe in shell context, etc.
We determine whether a character is unsafe through static table
lookup. This code assumes ASCII character set and 8-bit chars. */
enum {
/* rfc1738 reserved chars + "$" and ",". */
urlchr_reserved = 1,
/* rfc1738 unsafe chars, plus non-printables. */
urlchr_unsafe = 2
};
#define urlchr_test(c, mask) (urlchr_table[(unsigned char)(c)] & (mask))
#define URL_RESERVED_CHAR(c) urlchr_test(c, urlchr_reserved)
#define URL_UNSAFE_CHAR(c) urlchr_test(c, urlchr_unsafe)
/* Shorthands for the table: */
#define R urlchr_reserved
#define U urlchr_unsafe
#define RU R|U
static const unsigned char urlchr_table[256] =
{
U, U, U, U, U, U, U, U, /* NUL SOH STX ETX EOT ENQ ACK BEL */
U, U, U, U, U, U, U, U, /* BS HT LF VT FF CR SO SI */
U, U, U, U, U, U, U, U, /* DLE DC1 DC2 DC3 DC4 NAK SYN ETB */
U, U, U, U, U, U, U, U, /* CAN EM SUB ESC FS GS RS US */
U, 0, U, RU, R, U, R, 0, /* SP ! " # $ % & ' */
0, 0, 0, R, R, 0, 0, R, /* ( ) * + , - . / */
0, 0, 0, 0, 0, 0, 0, 0, /* 0 1 2 3 4 5 6 7 */
0, 0, RU, R, U, R, U, R, /* 8 9 : ; < = > ? */
RU, 0, 0, 0, 0, 0, 0, 0, /* @ A B C D E F G */
0, 0, 0, 0, 0, 0, 0, 0, /* H I J K L M N O */
0, 0, 0, 0, 0, 0, 0, 0, /* P Q R S T U V W */
0, 0, 0, RU, U, RU, U, 0, /* X Y Z [ \ ] ^ _ */
U, 0, 0, 0, 0, 0, 0, 0, /* ` a b c d e f g */
0, 0, 0, 0, 0, 0, 0, 0, /* h i j k l m n o */
0, 0, 0, 0, 0, 0, 0, 0, /* p q r s t u v w */
0, 0, 0, U, U, U, 0, U, /* x y z { | } ~ DEL */
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
U, U, U, U, U, U, U, U, U, U, U, U, U, U, U, U,
};
#undef R
#undef U
#undef RU
static void
url_unescape_1 (char *s, unsigned char mask)
{
char *t = s; /* t - tortoise */
char *h = s; /* h - hare */
for (; *h; h++, t++)
{
if (*h != '%')
{
copychar:
*t = *h;
}
else
{
char c;
/* Do nothing if '%' is not followed by two hex digits. */
if (!h[1] || !h[2] || !(c_isxdigit (h[1]) && c_isxdigit (h[2])))
goto copychar;
c = X2DIGITS_TO_NUM (h[1], h[2]);
if (urlchr_test(c, mask))
goto copychar;
/* Don't unescape %00 because there is no way to insert it
into a C string without effectively truncating it. */
if (c == '\0')
goto copychar;
*t = c;
h += 2;
}
}
*t = '\0';
}
/* URL-unescape the string S.
This is done by transforming the sequences "%HH" to the character
represented by the hexadecimal digits HH. If % is not followed by
two hexadecimal digits, it is inserted literally.
The transformation is done in place. If you need the original
string intact, make a copy before calling this function. */
void
url_unescape (char *s)
{
url_unescape_1 (s, 0);
}
/* URL-unescape the string S.
This functions behaves identically as url_unescape(), but does not
convert characters from "reserved". In other words, it only converts
"unsafe" characters. */
void
url_unescape_except_reserved (char *s)
{
url_unescape_1 (s, urlchr_reserved);
}
/* The core of url_escape_* functions. Escapes the characters that
match the provided mask in urlchr_table.
If ALLOW_PASSTHROUGH is true, a string with no unsafe chars will be
returned unchanged. If ALLOW_PASSTHROUGH is false, a freshly
allocated string will be returned in all cases. */
static char *
url_escape_1 (const char *s, unsigned char mask, bool allow_passthrough)
{
const char *p1;
char *p2, *newstr;
int newlen;
int addition = 0;
for (p1 = s; *p1; p1++)
if (urlchr_test (*p1, mask))
addition += 2; /* Two more characters (hex digits) */
if (!addition)
return allow_passthrough ? (char *)s : xstrdup (s);
newlen = (p1 - s) + addition;
newstr = xmalloc (newlen + 1);
p1 = s;
p2 = newstr;
while (*p1)
{
/* Quote the characters that match the test mask. */
if (urlchr_test (*p1, mask))
{
unsigned char c = *p1++;
*p2++ = '%';
*p2++ = XNUM_TO_DIGIT (c >> 4);
*p2++ = XNUM_TO_DIGIT (c & 0xf);
}
else
*p2++ = *p1++;
}
assert (p2 - newstr == newlen);
*p2 = '\0';
return newstr;
}
/* URL-escape the unsafe characters (see urlchr_table) in a given
string, returning a freshly allocated string. */
char *
url_escape (const char *s)
{
return url_escape_1 (s, urlchr_unsafe, false);
}
/* URL-escape the unsafe and reserved characters (see urlchr_table) in
a given string, returning a freshly allocated string. */
char *
url_escape_unsafe_and_reserved (const char *s)
{
return url_escape_1 (s, urlchr_unsafe|urlchr_reserved, false);
}
/* URL-escape the unsafe characters (see urlchr_table) in a given
string. If no characters are unsafe, S is returned. */
static char *
url_escape_allow_passthrough (const char *s)
{
return url_escape_1 (s, urlchr_unsafe, true);
}
/* Decide whether the char at position P needs to be encoded. (It is
not enough to pass a single char *P because the function may need
to inspect the surrounding context.)
Return true if the char should be escaped as %XX, false otherwise. */
static inline bool
char_needs_escaping (const char *p)
{
if (*p == '%')
{
if (c_isxdigit (*(p + 1)) && c_isxdigit (*(p + 2)))
return false;
else
/* Garbled %.. sequence: encode `%'. */
return true;
}
else if (URL_UNSAFE_CHAR (*p) && !URL_RESERVED_CHAR (*p))
return true;
else
return false;
}
/* Translate a %-escaped (but possibly non-conformant) input string S
into a %-escaped (and conformant) output string. If no characters
are encoded or decoded, return the same string S; otherwise, return
a freshly allocated string with the new contents.
After a URL has been run through this function, the protocols that
use `%' as the quote character can use the resulting string as-is,
while those that don't can use url_unescape to get to the intended
data. This function is stable: once the input is transformed,
further transformations of the result yield the same output.
Let's discuss why this function is needed.
Imagine Wget is asked to retrieve `http://abc.xyz/abc def'. Since
a raw space character would mess up the HTTP request, it needs to
be quoted, like this:
GET /abc%20def HTTP/1.0
It would appear that the unsafe chars need to be quoted, for
example with url_escape. But what if we're requested to download
`abc%20def'? url_escape transforms "%" to "%25", which would leave
us with `abc%2520def'. This is incorrect -- since %-escapes are
part of URL syntax, "%20" is the correct way to denote a literal
space on the Wget command line. This leads to the conclusion that
in that case Wget should not call url_escape, but leave the `%20'
as is. This is clearly contradictory, but it only gets worse.
What if the requested URI is `abc%20 def'? If we call url_escape,
we end up with `/abc%2520%20def', which is almost certainly not
intended. If we don't call url_escape, we are left with the
embedded space and cannot complete the request. What the user
meant was for Wget to request `/abc%20%20def', and this is where
reencode_escapes kicks in.
Wget used to solve this by first decoding %-quotes, and then
encoding all the "unsafe" characters found in the resulting string.
This was wrong because it didn't preserve certain URL special
(reserved) characters. For instance, URI containing "a%2B+b" (0x2b
== '+') would get translated to "a%2B%2Bb" or "a++b" depending on
whether we considered `+' reserved (it is). One of these results
is inevitable because by the second step we would lose information
on whether the `+' was originally encoded or not. Both results
were wrong because in CGI parameters + means space, while %2B means
literal plus. reencode_escapes correctly translates the above to
"a%2B+b", i.e. returns the original string.
This function uses a modified version of the algorithm originally
proposed by Anon Sricharoenchai:
* Encode all "unsafe" characters, except those that are also
"reserved", to %XX. See urlchr_table for which characters are
unsafe and reserved.
* Encode the "%" characters not followed by two hex digits to
"%25".
* Pass through all other characters and %XX escapes as-is. (Up to
Wget 1.10 this decoded %XX escapes corresponding to "safe"
characters, but that was obtrusive and broke some servers.)
Anon's test case:
"http://abc.xyz/%20%3F%%36%31%25aa% a?a=%61+a%2Ba&b=b%26c%3Dc"
->
"http://abc.xyz/%20%3F%25%36%31%25aa%25%20a?a=%61+a%2Ba&b=b%26c%3Dc"
Simpler test cases:
"foo bar" -> "foo%20bar"
"foo%20bar" -> "foo%20bar"
"foo %20bar" -> "foo%20%20bar"
"foo%%20bar" -> "foo%25%20bar" (0x25 == '%')
"foo%25%20bar" -> "foo%25%20bar"
"foo%2%20bar" -> "foo%252%20bar"
"foo+bar" -> "foo+bar" (plus is reserved!)
"foo%2b+bar" -> "foo%2b+bar" */
static char *
reencode_escapes (const char *s)
{
const char *p1;
char *newstr, *p2;
int oldlen, newlen;
int encode_count = 0;
/* First pass: inspect the string to see if there's anything to do,
and to calculate the new length. */
for (p1 = s; *p1; p1++)
if (char_needs_escaping (p1))
++encode_count;
if (!encode_count)
/* The string is good as it is. */
return (char *) s; /* C const model sucks. */
oldlen = p1 - s;
/* Each encoding adds two characters (hex digits). */
newlen = oldlen + 2 * encode_count;
newstr = xmalloc (newlen + 1);
/* Second pass: copy the string to the destination address, encoding
chars when needed. */
p1 = s;
p2 = newstr;
while (*p1)
if (char_needs_escaping (p1))
{
unsigned char c = *p1++;
*p2++ = '%';
*p2++ = XNUM_TO_DIGIT (c >> 4);
*p2++ = XNUM_TO_DIGIT (c & 0xf);
}
else
*p2++ = *p1++;
*p2 = '\0';
assert (p2 - newstr == newlen);
return newstr;
}
/* Returns the scheme type if the scheme is supported, or
SCHEME_INVALID if not. */
enum url_scheme
url_scheme (const char *url)
{
int i;
for (i = 0; supported_schemes[i].leading_string; i++)
if (0 == strncasecmp (url, supported_schemes[i].leading_string,
strlen (supported_schemes[i].leading_string)))
{
if (!(supported_schemes[i].flags & scm_disabled))
return (enum url_scheme) i;
else
return SCHEME_INVALID;
}
return SCHEME_INVALID;
}
#define SCHEME_CHAR(ch) (c_isalnum (ch) || (ch) == '-' || (ch) == '+')
/* Return 1 if the URL begins with any "scheme", 0 otherwise. As
currently implemented, it returns true if URL begins with
[-+a-zA-Z0-9]+: . */
bool
url_has_scheme (const char *url)
{
const char *p = url;
/* The first char must be a scheme char. */
if (!*p || !SCHEME_CHAR (*p))
return false;
++p;
/* Followed by 0 or more scheme chars. */
while (*p && SCHEME_CHAR (*p))
++p;
/* Terminated by ':'. */
return *p == ':';
}
bool
url_valid_scheme (const char *url)
{
enum url_scheme scheme = url_scheme (url);
return scheme != SCHEME_INVALID;
}
int
scheme_default_port (enum url_scheme scheme)
{
return supported_schemes[scheme].default_port;
}
void
scheme_disable (enum url_scheme scheme)
{
supported_schemes[scheme].flags |= scm_disabled;
}
/* Skip the username and password, if present in the URL. The
function should *not* be called with the complete URL, but with the
portion after the scheme.
If no username and password are found, return URL. */
static const char *
url_skip_credentials (const char *url)
{
/* Look for '@' that comes before terminators, such as '/', '?',
'#', or ';'. */
const char *p = (const char *)strpbrk (url, "@/?#;");
if (!p || *p != '@')
return url;
return p + 1;
}
/* Parse credentials contained in [BEG, END). The region is expected
to have come from a URL and is unescaped. */
static bool
parse_credentials (const char *beg, const char *end, char **user, char **passwd)
{
char *colon;
const char *userend;
if (beg == end)
return false; /* empty user name */
colon = memchr (beg, ':', end - beg);
if (colon == beg)
return false; /* again empty user name */
if (colon)
{
*passwd = strdupdelim (colon + 1, end);
userend = colon;
url_unescape (*passwd);
}
else
{
*passwd = NULL;
userend = end;
}
*user = strdupdelim (beg, userend);
url_unescape (*user);
return true;
}
/* Used by main.c: detect URLs written using the "shorthand" URL forms
originally popularized by Netscape and NcFTP. HTTP shorthands look
like this:
www.foo.com[:port]/dir/file -> http://www.foo.com[:port]/dir/file
www.foo.com[:port] -> http://www.foo.com[:port]
FTP shorthands look like this:
foo.bar.com:dir/file -> ftp://foo.bar.com/dir/file
foo.bar.com:/absdir/file -> ftp://foo.bar.com//absdir/file
If the URL needs not or cannot be rewritten, return NULL. */
char *
rewrite_shorthand_url (const char *url)
{
const char *p;
char *ret;
if (url_scheme (url) != SCHEME_INVALID)
return NULL;
/* Look for a ':' or '/'. The former signifies NcFTP syntax, the
latter Netscape. */
p = strpbrk (url, ":/");
if (p == url)
return NULL;
/* If we're looking at "://", it means the URL uses a scheme we
don't support, which may include "https" when compiled without
SSL support. Don't bogusly rewrite such URLs. */
if (p && p[0] == ':' && p[1] == '/' && p[2] == '/')
return NULL;
if (p && *p == ':')
{
/* Colon indicates ftp, as in foo.bar.com:path. Check for
special case of http port number ("localhost:10000"). */
int digits = strspn (p + 1, "0123456789");
if (digits && (p[1 + digits] == '/' || p[1 + digits] == '\0'))
goto http;
/* Turn "foo.bar.com:path" to "ftp://foo.bar.com/path". */
if ((ret = aprintf ("ftp://%s", url)) != NULL)
ret[6 + (p - url)] = '/';
}
else
{
http:
/* Just prepend "http://" to URL. */
ret = aprintf ("http://%s", url);
}
return ret;
}
static void split_path (const char *, char **, char **);
/* Like strpbrk, with the exception that it returns the pointer to the
terminating zero (end-of-string aka "eos") if no matching character
is found. */
static inline char *
strpbrk_or_eos (const char *s, const char *accept)
{
char *p = strpbrk (s, accept);
if (!p)
p = strchr (s, '\0');
return p;
}
/* Turn STR into lowercase; return true if a character was actually
changed. */
static bool
lowercase_str (char *str)
{
bool changed = false;
for (; *str; str++)
if (c_isupper (*str))
{
changed = true;
*str = c_tolower (*str);
}
return changed;
}
static const char *
init_seps (enum url_scheme scheme)
{
static char seps[8] = ":/";
char *p = seps + 2;
int flags = supported_schemes[scheme].flags;
if (flags & scm_has_params)
*p++ = ';';
if (flags & scm_has_query)
*p++ = '?';
if (flags & scm_has_fragment)
*p++ = '#';
*p = '\0';
return seps;
}
static const char *parse_errors[] = {
#define PE_NO_ERROR 0
N_("No error"),
#define PE_UNSUPPORTED_SCHEME 1
N_("Unsupported scheme %s"), /* support for format token only here */
#define PE_MISSING_SCHEME 2
N_("Scheme missing"),
#define PE_INVALID_HOST_NAME 3
N_("Invalid host name"),
#define PE_BAD_PORT_NUMBER 4
N_("Bad port number"),
#define PE_INVALID_USER_NAME 5
N_("Invalid user name"),
#define PE_UNTERMINATED_IPV6_ADDRESS 6
N_("Unterminated IPv6 numeric address"),
#define PE_IPV6_NOT_SUPPORTED 7
N_("IPv6 addresses not supported"),
#define PE_INVALID_IPV6_ADDRESS 8
N_("Invalid IPv6 numeric address")
};
/* Parse a URL.
Return a new struct url if successful, NULL on error. In case of
error, and if ERROR is not NULL, also set *ERROR to the appropriate
error code. */
struct url *
url_parse (const char *url, int *error, struct iri *iri, bool percent_encode)
{
struct url *u;
const char *p;
bool path_modified, host_modified;
enum url_scheme scheme;
const char *seps;
const char *uname_b, *uname_e;
const char *host_b, *host_e;
const char *path_b, *path_e;
const char *params_b, *params_e;
const char *query_b, *query_e;
const char *fragment_b, *fragment_e;
int port;
char *user = NULL, *passwd = NULL;
const char *url_encoded = NULL;
int error_code;
scheme = url_scheme (url);
if (scheme == SCHEME_INVALID)
{
if (url_has_scheme (url))
error_code = PE_UNSUPPORTED_SCHEME;
else
error_code = PE_MISSING_SCHEME;
goto error;
}
url_encoded = url;
if (iri && iri->utf8_encode)
{
char *new_url = NULL;
iri->utf8_encode = remote_to_utf8 (iri, iri->orig_url ? iri->orig_url : url, &new_url);
if (!iri->utf8_encode)
new_url = NULL;
else
{
xfree (iri->orig_url);
iri->orig_url = xstrdup (url);
url_encoded = reencode_escapes (new_url);
if (url_encoded != new_url)
xfree (new_url);
percent_encode = false;
}
}
if (percent_encode)
url_encoded = reencode_escapes (url);
p = url_encoded;
p += strlen (supported_schemes[scheme].leading_string);
uname_b = p;
p = url_skip_credentials (p);
uname_e = p;
/* scheme://user:pass@host[:port]... */
/* ^ */
/* We attempt to break down the URL into the components path,
params, query, and fragment. They are ordered like this:
scheme://host[:port][/path][;params][?query][#fragment] */
path_b = path_e = NULL;
params_b = params_e = NULL;
query_b = query_e = NULL;
fragment_b = fragment_e = NULL;
/* Initialize separators for optional parts of URL, depending on the
scheme. For example, FTP has params, and HTTP and HTTPS have
query string and fragment. */
seps = init_seps (scheme);
host_b = p;
if (*p == '[')
{
/* Handle IPv6 address inside square brackets. Ideally we'd
just look for the terminating ']', but rfc2732 mandates
rejecting invalid IPv6 addresses. */
/* The address begins after '['. */
host_b = p + 1;
host_e = strchr (host_b, ']');
if (!host_e)
{
error_code = PE_UNTERMINATED_IPV6_ADDRESS;
goto error;
}
#ifdef ENABLE_IPV6
/* Check if the IPv6 address is valid. */
if (!is_valid_ipv6_address(host_b, host_e))
{
error_code = PE_INVALID_IPV6_ADDRESS;
goto error;
}
/* Continue parsing after the closing ']'. */
p = host_e + 1;
#else
error_code = PE_IPV6_NOT_SUPPORTED;
goto error;
#endif
/* The closing bracket must be followed by a separator or by the
null char. */
/* http://[::1]... */
/* ^ */
if (!strchr (seps, *p))
{
/* Trailing garbage after []-delimited IPv6 address. */
error_code = PE_INVALID_HOST_NAME;
goto error;
}
}
else
{
p = strpbrk_or_eos (p, seps);
host_e = p;
}
++seps; /* advance to '/' */
if (host_b == host_e)
{
error_code = PE_INVALID_HOST_NAME;
goto error;
}
port = scheme_default_port (scheme);
if (*p == ':')
{
const char *port_b, *port_e, *pp;
/* scheme://host:port/tralala */
/* ^ */
++p;
port_b = p;
p = strpbrk_or_eos (p, seps);
port_e = p;
/* Allow empty port, as per rfc2396. */
if (port_b != port_e)
for (port = 0, pp = port_b; pp < port_e; pp++)
{
if (!c_isdigit (*pp))
{
/* http://host:12randomgarbage/blah */
/* ^ */
error_code = PE_BAD_PORT_NUMBER;
goto error;
}
port = 10 * port + (*pp - '0');
/* Check for too large port numbers here, before we have
a chance to overflow on bogus port values. */
if (port > 0xffff)
{
error_code = PE_BAD_PORT_NUMBER;
goto error;
}
}
}
/* Advance to the first separator *after* '/' (either ';' or '?',
depending on the scheme). */
++seps;
/* Get the optional parts of URL, each part being delimited by
current location and the position of the next separator. */
#define GET_URL_PART(sepchar, var) do { \
if (*p == sepchar) \
var##_b = ++p, var##_e = p = strpbrk_or_eos (p, seps); \
++seps; \
} while (0)
GET_URL_PART ('/', path);
if (supported_schemes[scheme].flags & scm_has_params)
GET_URL_PART (';', params);
if (supported_schemes[scheme].flags & scm_has_query)
GET_URL_PART ('?', query);
if (supported_schemes[scheme].flags & scm_has_fragment)
GET_URL_PART ('#', fragment);
#undef GET_URL_PART
assert (*p == 0);
if (uname_b != uname_e)
{
/* http://user:pass@host */
/* ^ ^ */
/* uname_b uname_e */
if (!parse_credentials (uname_b, uname_e - 1, &user, &passwd))
{
error_code = PE_INVALID_USER_NAME;
goto error;
}
}
u = xnew0 (struct url);
u->scheme = scheme;
u->host = strdupdelim (host_b, host_e);
u->port = port;
u->user = user;
u->passwd = passwd;
u->path = strdupdelim (path_b, path_e);
path_modified = path_simplify (scheme, u->path);
split_path (u->path, &u->dir, &u->file);
host_modified = lowercase_str (u->host);
/* Decode %HH sequences in host name. This is important not so much
to support %HH sequences in host names (which other browser
don't), but to support binary characters (which will have been
converted to %HH by reencode_escapes). */
if (strchr (u->host, '%'))
{
url_unescape (u->host);
host_modified = true;
/* check for invalid control characters in host name */
for (p = u->host; *p; p++)
{
if (c_iscntrl(*p))
{
url_free(u);
error_code = PE_INVALID_HOST_NAME;
goto error;
}
}
/* Apply IDNA regardless of iri->utf8_encode status */
if (opt.enable_iri && iri)
{
char *new = idn_encode (iri, u->host);
if (new)
{
xfree (u->host);
u->host = new;
u->idn_allocated = true;
host_modified = true;
}
}
}
if (params_b)
u->params = strdupdelim (params_b, params_e);
if (query_b)
u->query = strdupdelim (query_b, query_e);
if (fragment_b)
u->fragment = strdupdelim (fragment_b, fragment_e);
if (opt.enable_iri || path_modified || u->fragment || host_modified || path_b == path_e)
{
/* If we suspect that a transformation has rendered what
url_string might return different from URL_ENCODED, rebuild
u->url using url_string. */
u->url = url_string (u, URL_AUTH_SHOW);
if (url_encoded != url)
xfree (url_encoded);
}
else
{
if (url_encoded == url)
u->url = xstrdup (url);
else
u->url = (char *) url_encoded;
}
return u;
error:
/* Cleanup in case of error: */
if (url_encoded && url_encoded != url)
xfree (url_encoded);
/* Transmit the error code to the caller, if the caller wants to
know. */
if (error)
*error = error_code;
return NULL;
}
/* Return the error message string from ERROR_CODE, which should have
been retrieved from url_parse. The error message is translated. */
char *
url_error (const char *url, int error_code)
{
assert (error_code >= 0 && ((size_t) error_code) < countof (parse_errors));
if (error_code == PE_UNSUPPORTED_SCHEME)
{
char *error, *p;
char *scheme = xstrdup (url);
assert (url_has_scheme (url));
if ((p = strchr (scheme, ':')))
*p = '\0';
if (!c_strcasecmp (scheme, "https"))
error = aprintf (_("HTTPS support not compiled in"));
else
error = aprintf (_(parse_errors[error_code]), quote (scheme));
xfree (scheme);
return error;
}
else
return xstrdup (_(parse_errors[error_code]));
}
/* Split PATH into DIR and FILE. PATH comes from the URL and is
expected to be URL-escaped.
The path is split into directory (the part up to the last slash)
and file (the part after the last slash), which are subsequently
unescaped. Examples:
PATH DIR FILE
"foo/bar/baz" "foo/bar" "baz"
"foo/bar/" "foo/bar" ""
"foo" "" "foo"
"foo/bar/baz%2fqux" "foo/bar" "baz/qux" (!)
DIR and FILE are freshly allocated. */
static void
split_path (const char *path, char **dir, char **file)
{
char *last_slash = strrchr (path, '/');
if (!last_slash)
{
*dir = xstrdup ("");
*file = xstrdup (path);
}
else
{
*dir = strdupdelim (path, last_slash);
*file = xstrdup (last_slash + 1);
}
url_unescape (*dir);
url_unescape (*file);
}
/* Note: URL's "full path" is the path with the query string and
params appended. The "fragment" (#foo) is intentionally ignored,
but that might be changed. For example, if the original URL was
"http://host:port/foo/bar/baz;bullshit?querystring#uselessfragment",
the full path will be "/foo/bar/baz;bullshit?querystring". */
/* Return the length of the full path, without the terminating
zero. */
static int
full_path_length (const struct url *url)
{
int len = 0;
#define FROB(el) if (url->el) len += 1 + strlen (url->el)
FROB (path);
FROB (params);
FROB (query);
#undef FROB
return len;
}
/* Write out the full path. */
static void
full_path_write (const struct url *url, char *where)
{
#define FROB(el, chr) do { \
char *f_el = url->el; \
if (f_el) { \
int l = strlen (f_el); \
*where++ = chr; \
memcpy (where, f_el, l); \
where += l; \
} \
} while (0)
FROB (path, '/');
FROB (params, ';');
FROB (query, '?');
#undef FROB
}
/* Public function for getting the "full path". E.g. if u->path is
"foo/bar" and u->query is "param=value", full_path will be
"/foo/bar?param=value". */
char *
url_full_path (const struct url *url)
{
int length = full_path_length (url);
char *full_path = xmalloc (length + 1);
full_path_write (url, full_path);
full_path[length] = '\0';
return full_path;
}
/* Unescape CHR in an otherwise escaped STR. Used to selectively
escaping of certain characters, such as "/" and ":". Returns a
count of unescaped chars. */
static void
unescape_single_char (char *str, char chr)
{
const char c1 = XNUM_TO_DIGIT (chr >> 4);
const char c2 = XNUM_TO_DIGIT (chr & 0xf);
char *h = str; /* hare */
char *t = str; /* tortoise */
for (; *h; h++, t++)
{
if (h[0] == '%' && h[1] == c1 && h[2] == c2)
{
*t = chr;
h += 2;
}
else
*t = *h;
}
*t = '\0';
}
/* Escape unsafe and reserved characters, except for the slash
characters. */
static char *
url_escape_dir (const char *dir)
{
char *newdir = url_escape_1 (dir, urlchr_unsafe | urlchr_reserved, 1);
if (newdir == dir)
return (char *)dir;
unescape_single_char (newdir, '/');
return newdir;
}
/* Sync u->path and u->url with u->dir and u->file. Called after
u->file or u->dir have been changed, typically by the FTP code. */
static void
sync_path (struct url *u)
{
char *newpath, *efile, *edir;
xfree (u->path);
/* u->dir and u->file are not escaped. URL-escape them before
reassembling them into u->path. That way, if they contain
separators like '?' or even if u->file contains slashes, the
path will be correctly assembled. (u->file can contain slashes
if the URL specifies it with %2f, or if an FTP server returns
it.) */
edir = url_escape_dir (u->dir);
efile = url_escape_1 (u->file, urlchr_unsafe | urlchr_reserved, 1);
if (!*edir)
newpath = xstrdup (efile);
else
{
int dirlen = strlen (edir);
int filelen = strlen (efile);
/* Copy "DIR/FILE" to newpath. */
char *p = newpath = xmalloc (dirlen + 1 + filelen + 1);
memcpy (p, edir, dirlen);
p += dirlen;
*p++ = '/';
memcpy (p, efile, filelen);
p += filelen;
*p = '\0';
}
u->path = newpath;
if (edir != u->dir)
xfree (edir);
if (efile != u->file)
xfree (efile);
/* Regenerate u->url as well. */
xfree (u->url);
u->url = url_string (u, URL_AUTH_SHOW);
}
/* Mutators. Code in ftp.c insists on changing u->dir and u->file.
This way we can sync u->path and u->url when they get changed. */
void
url_set_dir (struct url *url, const char *newdir)
{
xfree (url->dir);
url->dir = xstrdup (newdir);
sync_path (url);
}
void
url_set_file (struct url *url, const char *newfile)
{
xfree (url->file);
url->file = xstrdup (newfile);
sync_path (url);
}
void
url_free (struct url *url)
{
if (url)
{
if (url->idn_allocated) {
idn_free (url->host); /* A dummy if !defined(ENABLE_IRI) */
url->host = NULL;
}
else
xfree (url->host);
xfree (url->path);
xfree (url->url);
xfree (url->params);
xfree (url->query);
xfree (url->fragment);
xfree (url->user);
xfree (url->passwd);
xfree (url->dir);
xfree (url->file);
xfree (url);
}
}
/* Create all the necessary directories for PATH (a file). Calls
make_directory internally. */
int
mkalldirs (const char *path)
{
const char *p;
char *t;
struct_stat st;
int res;
p = path + strlen (path);
for (; *p != '/' && p != path; p--)
;
/* Don't create if it's just a file. */
if ((p == path) && (*p != '/'))
return 0;
t = strdupdelim (path, p);
/* Check whether the directory exists. */
if ((stat (t, &st) == 0))
{
if (S_ISDIR (st.st_mode))
{
xfree (t);
return 0;
}
else
{
/* If the dir exists as a file name, remove it first. This
is *only* for Wget to work with buggy old CERN http
servers. Here is the scenario: When Wget tries to
retrieve a directory without a slash, e.g.
http://foo/bar (bar being a directory), CERN server will
not redirect it too http://foo/bar/ -- it will generate a
directory listing containing links to bar/file1,
bar/file2, etc. Wget will lose because it saves this
HTML listing to a file `bar', so it cannot create the
directory. To work around this, if the file of the same
name exists, we just remove it and create the directory
anyway. */
DEBUGP (("Removing %s because of directory danger!\n", t));
unlink (t);
}
}
res = make_directory (t);
if (res != 0)
logprintf (LOG_NOTQUIET, "%s: %s", t, strerror (errno));
xfree (t);
return res;
}
/* Functions for constructing the file name out of URL components. */
/* A growable string structure, used by url_file_name and friends.
This should perhaps be moved to utils.c.
The idea is to have a convenient and efficient way to construct a
string by having various functions append data to it. Instead of
passing the obligatory BASEVAR, SIZEVAR and TAILPOS to all the
functions in questions, we pass the pointer to this struct.
Functions that write to the members in this struct must make sure
that base remains null terminated by calling append_null().
*/
struct growable {
char *base;
int size; /* memory allocated */
int tail; /* string length */
};
/* Ensure that the string can accept APPEND_COUNT more characters past
the current TAIL position. If necessary, this will grow the string
and update its allocated size. If the string is already large
enough to take TAIL+APPEND_COUNT characters, this does nothing. */
#define GROW(g, append_size) do { \
struct growable *G_ = g; \
DO_REALLOC (G_->base, G_->size, G_->tail + append_size, char); \
} while (0)
/* Return the tail position of the string. */
#define TAIL(r) ((r)->base + (r)->tail)
/* Move the tail position by APPEND_COUNT characters. */
#define TAIL_INCR(r, append_count) ((r)->tail += append_count)
/* Append NULL to DEST. */
static void
append_null (struct growable *dest)
{
GROW (dest, 1);
*TAIL (dest) = 0;
}
/* Append CH to DEST. */
static void
append_char (char ch, struct growable *dest)
{
if (ch)
{
GROW (dest, 1);
*TAIL (dest) = ch;
TAIL_INCR (dest, 1);
}
append_null (dest);
}
/* Append the string STR to DEST. */
static void
append_string (const char *str, struct growable *dest)
{
int l = strlen (str);
if (l)
{
GROW (dest, l);
memcpy (TAIL (dest), str, l);
TAIL_INCR (dest, l);
}
append_null (dest);
}
enum {
filechr_not_unix = 1, /* unusable on Unix, / and \0 */
filechr_not_vms = 2, /* unusable on VMS (ODS5), 0x00-0x1F * ? */
filechr_not_windows = 4, /* unusable on Windows, one of \|/<>?:*" */
filechr_control = 8 /* a control character, e.g. 0-31 */
};
#define FILE_CHAR_TEST(c, mask) \
((opt.restrict_files_nonascii && !c_isascii ((unsigned char)(c))) || \
(filechr_table[(unsigned char)(c)] & (mask)))
/* Shorthands for the table: */
#define U filechr_not_unix
#define V filechr_not_vms
#define W filechr_not_windows
#define C filechr_control
#define UVWC U|V|W|C
#define UW U|W
#define VC V|C
#define VW V|W
/* Table of characters unsafe under various conditions (see above).
Arguably we could also claim `%' to be unsafe, since we use it as
the escape character. If we ever want to be able to reliably
translate file name back to URL, this would become important
crucial. Right now, it's better to be minimal in escaping. */
static const unsigned char filechr_table[256] =
{
UVWC, VC, VC, VC, VC, VC, VC, VC, /* NUL SOH STX ETX EOT ENQ ACK BEL */
VC, VC, VC, VC, VC, VC, VC, VC, /* BS HT LF VT FF CR SO SI */
VC, VC, VC, VC, VC, VC, VC, VC, /* DLE DC1 DC2 DC3 DC4 NAK SYN ETB */
VC, VC, VC, VC, VC, VC, VC, VC, /* CAN EM SUB ESC FS GS RS US */
0, 0, W, 0, 0, 0, 0, 0, /* SP ! " # $ % & ' */
0, 0, VW, 0, 0, 0, 0, UW, /* ( ) * + , - . / */
0, 0, 0, 0, 0, 0, 0, 0, /* 0 1 2 3 4 5 6 7 */
0, 0, W, 0, W, 0, W, VW, /* 8 9 : ; < = > ? */
0, 0, 0, 0, 0, 0, 0, 0, /* @ A B C D E F G */
0, 0, 0, 0, 0, 0, 0, 0, /* H I J K L M N O */
0, 0, 0, 0, 0, 0, 0, 0, /* P Q R S T U V W */
0, 0, 0, 0, W, 0, 0, 0, /* X Y Z [ \ ] ^ _ */
0, 0, 0, 0, 0, 0, 0, 0, /* ` a b c d e f g */
0, 0, 0, 0, 0, 0, 0, 0, /* h i j k l m n o */
0, 0, 0, 0, 0, 0, 0, 0, /* p q r s t u v w */
0, 0, 0, 0, W, 0, 0, C, /* x y z { | } ~ DEL */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 128-143 */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 144-159 */
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
};
#undef U
#undef V
#undef W
#undef C
#undef UW
#undef UVWC
#undef VC
#undef VW
/* FN_PORT_SEP is the separator between host and port in file names
for non-standard port numbers. On Unix this is normally ':', as in
"www.xemacs.org:4001/index.html". Under Windows, we set it to +
because Windows can't handle ':' in file names. */
#define FN_PORT_SEP (opt.restrict_files_os != restrict_windows ? ':' : '+')
/* FN_QUERY_SEP is the separator between the file name and the URL
query, normally '?'. Because VMS and Windows cannot handle '?' in a
file name, we use '@' instead there. */
#define FN_QUERY_SEP \
(((opt.restrict_files_os != restrict_vms) && \
(opt.restrict_files_os != restrict_windows)) ? '?' : '@')
#define FN_QUERY_SEP_STR \
(((opt.restrict_files_os != restrict_vms) && \
(opt.restrict_files_os != restrict_windows)) ? "?" : "@")
/* Quote path element, characters in [b, e), as file name, and append
the quoted string to DEST. Each character is quoted as per
file_unsafe_char and the corresponding table.
If ESCAPED is true, the path element is considered to be
URL-escaped and will be unescaped prior to inspection. */
static void
append_uri_pathel (const char *b, const char *e, bool escaped,
struct growable *dest)
{
const char *p;
int quoted, outlen;
int mask;
if (opt.restrict_files_os == restrict_unix)
mask = filechr_not_unix;
else if (opt.restrict_files_os == restrict_vms)
mask = filechr_not_vms;
else
mask = filechr_not_windows;
if (opt.restrict_files_ctrl)
mask |= filechr_control;
/* Copy [b, e) to PATHEL and URL-unescape it. */
if (escaped)
{
char *unescaped;
BOUNDED_TO_ALLOCA (b, e, unescaped);
url_unescape (unescaped);
b = unescaped;
e = unescaped + strlen (unescaped);
}
/* Defang ".." when found as component of path. Remember that path
comes from the URL and might contain malicious input. */
if (e - b == 2 && b[0] == '.' && b[1] == '.')
{
b = "%2E%2E";
e = b + 6;
}
/* Walk the PATHEL string and check how many characters we'll need
to quote. */
quoted = 0;
for (p = b; p < e; p++)
if (FILE_CHAR_TEST (*p, mask))
++quoted;
/* Calculate the length of the output string. e-b is the input
string length. Each quoted char introduces two additional
characters in the string, hence 2*quoted. */
outlen = (e - b) + (2 * quoted);
GROW (dest, outlen);
if (!quoted)
{
/* If there's nothing to quote, we can simply append the string
without processing it again. */
memcpy (TAIL (dest), b, outlen);
}
else
{
char *q = TAIL (dest);
for (p = b; p < e; p++)
{
if (!FILE_CHAR_TEST (*p, mask))
*q++ = *p;
else
{
unsigned char ch = *p;
*q++ = '%';
*q++ = XNUM_TO_DIGIT (ch >> 4);
*q++ = XNUM_TO_DIGIT (ch & 0xf);
}
}
assert (q - TAIL (dest) == outlen);
}
/* Perform inline case transformation if required. */
if (opt.restrict_files_case == restrict_lowercase
|| opt.restrict_files_case == restrict_uppercase)
{
char *q;
for (q = TAIL (dest); q < TAIL (dest) + outlen; ++q)
{
if (opt.restrict_files_case == restrict_lowercase)
*q = c_tolower (*q);
else
*q = c_toupper (*q);
}
}
TAIL_INCR (dest, outlen);
append_null (dest);
}
static char *
convert_fname (char *fname)
{
char *converted_fname = fname;
#if HAVE_ICONV
const char *from_encoding = opt.encoding_remote;
const char *to_encoding = opt.locale;
iconv_t cd;
size_t len, done, inlen, outlen;
char *s;
const char *orig_fname = fname;
/* Defaults for remote and local encodings. */
if (!from_encoding)
from_encoding = "UTF-8";
if (!to_encoding)
to_encoding = nl_langinfo (CODESET);
cd = iconv_open (to_encoding, from_encoding);
if (cd == (iconv_t)(-1))
logprintf (LOG_VERBOSE, _("Conversion from %s to %s isn't supported\n"),
quote (from_encoding), quote (to_encoding));
else
{
inlen = strlen (fname);
len = outlen = inlen * 2;
converted_fname = s = xmalloc (outlen + 1);
done = 0;
for (;;)
{
if (iconv (cd, &fname, &inlen, &s, &outlen) != (size_t)(-1)
&& iconv (cd, NULL, NULL, &s, &outlen) != (size_t)(-1))
{
*(converted_fname + len - outlen - done) = '\0';
iconv_close(cd);
DEBUGP (("Converted file name '%s' (%s) -> '%s' (%s)\n",
orig_fname, from_encoding, converted_fname, to_encoding));
xfree (orig_fname);
return converted_fname;
}
/* Incomplete or invalid multibyte sequence */
if (errno == EINVAL || errno == EILSEQ)
{
logprintf (LOG_VERBOSE,
_("Incomplete or invalid multibyte sequence encountered\n"));
xfree (converted_fname);
converted_fname = (char *)orig_fname;
break;
}
else if (errno == E2BIG) /* Output buffer full */
{
done = len;
len = outlen = done + inlen * 2;
converted_fname = xrealloc (converted_fname, outlen + 1);
s = converted_fname + done;
}
else /* Weird, we got an unspecified error */
{
logprintf (LOG_VERBOSE, _("Unhandled errno %d\n"), errno);
xfree (converted_fname);
converted_fname = (char *)orig_fname;
break;
}
}
DEBUGP (("Failed to convert file name '%s' (%s) -> '?' (%s)\n",
orig_fname, from_encoding, to_encoding));
}
iconv_close(cd);
#endif
return converted_fname;
}
/* Append to DEST the directory structure that corresponds the
directory part of URL's path. For example, if the URL is
http://server/dir1/dir2/file, this appends "/dir1/dir2".
Each path element ("dir1" and "dir2" in the above example) is
examined, url-unescaped, and re-escaped as file name element.
Additionally, it cuts as many directories from the path as
specified by opt.cut_dirs. For example, if opt.cut_dirs is 1, it
will produce "bar" for the above example. For 2 or more, it will
produce "".
Each component of the path is quoted for use as file name. */
static void
append_dir_structure (const struct url *u, struct growable *dest)
{
char *pathel, *next;
int cut = opt.cut_dirs;
/* Go through the path components, de-URL-quote them, and quote them
(if necessary) as file names. */
pathel = u->path;
for (; (next = strchr (pathel, '/')) != NULL; pathel = next + 1)
{
if (cut-- > 0)
continue;
if (pathel == next)
/* Ignore empty pathels. */
continue;
if (dest->tail)
append_char ('/', dest);
append_uri_pathel (pathel, next, true, dest);
}
}
/* Return a unique file name that matches the given URL as well as
possible. Does not create directories on the file system. */
char *
url_file_name (const struct url *u, char *replaced_filename)
{
struct growable fnres; /* stands for "file name result" */
struct growable temp_fnres;
const char *u_file;
char *fname, *unique, *fname_len_check;
const char *index_filename = "index.html"; /* The default index file is index.html */
size_t max_length;
fnres.base = NULL;
fnres.size = 0;
fnres.tail = 0;
temp_fnres.base = NULL;
temp_fnres.size = 0;
temp_fnres.tail = 0;
/* If an alternative index file was defined, change index_filename */
if (opt.default_page)
index_filename = opt.default_page;
/* Start with the directory prefix, if specified. */
if (opt.dir_prefix)
append_string (opt.dir_prefix, &fnres);
/* If "dirstruct" is turned on (typically the case with -r), add
the host and port (unless those have been turned off) and
directory structure. */
if (opt.dirstruct)
{
if (opt.protocol_directories)
{
if (fnres.tail)
append_char ('/', &fnres);
append_string (supported_schemes[u->scheme].name, &fnres);
}
if (opt.add_hostdir)
{
if (fnres.tail)
append_char ('/', &fnres);
if (0 != strcmp (u->host, ".."))
append_string (u->host, &fnres);
else
/* Host name can come from the network; malicious DNS may
allow ".." to be resolved, causing us to write to
"../<file>". Defang such host names. */
append_string ("%2E%2E", &fnres);
if (u->port != scheme_default_port (u->scheme))
{
char portstr[24];
number_to_string (portstr, u->port);
append_char (FN_PORT_SEP, &fnres);
append_string (portstr, &fnres);
}
}
append_dir_structure (u, &fnres);
}
if (!replaced_filename)
{
/* Create the filename. */
u_file = *u->file ? u->file : index_filename;
/* Append "?query" to the file name, even if empty,
* and create fname_len_check. */
if (u->query)
fname_len_check = concat_strings (u_file, FN_QUERY_SEP_STR, u->query, NULL);
else
fname_len_check = strdupdelim (u_file, u_file + strlen (u_file));
}
else
{
u_file = replaced_filename;
fname_len_check = strdupdelim (u_file, u_file + strlen (u_file));
}
append_uri_pathel (fname_len_check,
fname_len_check + strlen (fname_len_check), false, &temp_fnres);
/* Zero-terminate the temporary file name. */
append_char ('\0', &temp_fnres);
/* Check that the length of the file name is acceptable. */
#ifdef WINDOWS
if (MAX_PATH > (fnres.tail + CHOMP_BUFFER + 2))
{
max_length = MAX_PATH - (fnres.tail + CHOMP_BUFFER + 2);
/* FIXME: In Windows a filename is usually limited to 255 characters.
To really be accurate you could call GetVolumeInformation() to get
lpMaximumComponentLength
*/
if (max_length > 255)
{
max_length = 255;
}
}
else
{
max_length = 0;
}
#else
max_length = get_max_length (fnres.base, fnres.tail, _PC_NAME_MAX) - CHOMP_BUFFER;
#endif
if (max_length > 0 && strlen (temp_fnres.base) > max_length)
{
logprintf (LOG_NOTQUIET, "The name is too long, %lu chars total.\n",
(unsigned long) strlen (temp_fnres.base));
logprintf (LOG_NOTQUIET, "Trying to shorten...\n");
/* Shorten the file name. */
temp_fnres.base[max_length] = '\0';
logprintf (LOG_NOTQUIET, "New name is %s.\n", temp_fnres.base);
}
xfree (fname_len_check);
/* The filename has already been 'cleaned' by append_uri_pathel() above. So,
* just append it. */
if (fnres.tail)
append_char ('/', &fnres);
append_string (temp_fnres.base, &fnres);
fname = fnres.base;
/* Make a final check that the path length is acceptable? */
/* TODO: check fnres.base for path length problem */
xfree (temp_fnres.base);
fname = convert_fname (fname);
/* Check the cases in which the unique extensions are not used:
1) Clobbering is turned off (-nc).
2) Retrieval with regetting.
3) Timestamping is used.
4) Hierarchy is built.
5) Backups are specified.
The exception is the case when file does exist and is a
directory (see `mkalldirs' for explanation). */
if (ALLOW_CLOBBER
&& !(file_exists_p (fname) && !file_non_directory_p (fname)))
{
unique = fname;
}
else
{
unique = unique_name (fname, true);
if (unique != fname)
xfree (fname);
}
/* On VMS, alter the name as required. */
#ifdef __VMS
{
char *unique2;
unique2 = ods_conform( unique);
if (unique2 != unique)
{
xfree (unique);
unique = unique2;
}
}
#endif /* def __VMS */
return unique;
}
/* Resolve "." and ".." elements of PATH by destructively modifying
PATH and return true if PATH has been modified, false otherwise.
The algorithm is in spirit similar to the one described in rfc1808,
although implemented differently, in one pass. To recap, path
elements containing only "." are removed, and ".." is taken to mean
"back up one element". Single leading and trailing slashes are
preserved.
For example, "a/b/c/./../d/.." will yield "a/b/". More exhaustive
test examples are provided below. If you change anything in this
function, run test_path_simplify to make sure you haven't broken a
test case. */
static bool
path_simplify (enum url_scheme scheme, char *path)
{
char *h = path; /* hare */
char *t = path; /* tortoise */
char *beg = path;
char *end = strchr (path, '\0');
while (h < end)
{
/* Hare should be at the beginning of a path element. */
if (h[0] == '.' && (h[1] == '/' || h[1] == '\0'))
{
/* Ignore "./". */
h += 2;
}
else if (h[0] == '.' && h[1] == '.' && (h[2] == '/' || h[2] == '\0'))
{
/* Handle "../" by retreating the tortoise by one path
element -- but not past beginning. */
if (t > beg)
{
/* Move backwards until T hits the beginning of the
previous path element or the beginning of path. */
for (--t; t > beg && t[-1] != '/'; t--)
;
}
else if (scheme == SCHEME_FTP
#ifdef HAVE_SSL
|| scheme == SCHEME_FTPS
#endif
)
{
/* If we're at the beginning, copy the "../" literally
and move the beginning so a later ".." doesn't remove
it. This violates RFC 3986; but we do it for FTP
anyway because there is otherwise no way to get at a
parent directory, when the FTP server drops us in a
non-root directory (which is not uncommon). */
beg = t + 3;
goto regular;
}
h += 3;
}
else
{
regular:
/* A regular path element. If H hasn't advanced past T,
simply skip to the next path element. Otherwise, copy
the path element until the next slash. */
if (t == h)
{
/* Skip the path element, including the slash. */
while (h < end && *h != '/')
t++, h++;
if (h < end)
t++, h++;
}
else
{
/* Copy the path element, including the final slash. */
while (h < end && *h != '/')
*t++ = *h++;
if (h < end)
*t++ = *h++;
}
}
}
if (t != h)
*t = '\0';
return t != h;
}
/* Return the length of URL's path. Path is considered to be
terminated by one or more of the ?query or ;params or #fragment,
depending on the scheme. */
static const char *
path_end (const char *url)
{
enum url_scheme scheme = url_scheme (url);
const char *seps;
if (scheme == SCHEME_INVALID)
scheme = SCHEME_HTTP; /* use http semantics for rel links */
/* +2 to ignore the first two separators ':' and '/' */
seps = init_seps (scheme) + 2;
return strpbrk_or_eos (url, seps);
}
/* Find the last occurrence of character C in the range [b, e), or
NULL, if none are present. */
#define find_last_char(b, e, c) memrchr ((b), (c), (e) - (b))
/* Merge BASE with LINK and return the resulting URI.
Either of the URIs may be absolute or relative, complete with the
host name, or path only. This tries to reasonably handle all
foreseeable cases. It only employs minimal URL parsing, without
knowledge of the specifics of schemes.
I briefly considered making this function call path_simplify after
the merging process, as rfc1738 seems to suggest. This is a bad
idea for several reasons: 1) it complexifies the code, and 2)
url_parse has to simplify path anyway, so it's wasteful to boot. */
char *
uri_merge (const char *base, const char *link)
{
int linklength;
const char *end;
char *merge;
if (url_has_scheme (link))
return xstrdup (link);
/* We may not examine BASE past END. */
end = path_end (base);
linklength = strlen (link);
if (!*link)
{
/* Empty LINK points back to BASE, query string and all. */
return xstrdup (base);
}
else if (*link == '?')
{
/* LINK points to the same location, but changes the query
string. Examples: */
/* uri_merge("path", "?new") -> "path?new" */
/* uri_merge("path?foo", "?new") -> "path?new" */
/* uri_merge("path?foo#bar", "?new") -> "path?new" */
/* uri_merge("path#foo", "?new") -> "path?new" */
int baselength = end - base;
merge = xmalloc (baselength + linklength + 1);
memcpy (merge, base, baselength);
memcpy (merge + baselength, link, linklength);
merge[baselength + linklength] = '\0';
}
else if (*link == '#')
{
/* uri_merge("path", "#new") -> "path#new" */
/* uri_merge("path#foo", "#new") -> "path#new" */
/* uri_merge("path?foo", "#new") -> "path?foo#new" */
/* uri_merge("path?foo#bar", "#new") -> "path?foo#new" */
int baselength;
const char *end1 = strchr (base, '#');
if (!end1)
end1 = base + strlen (base);
baselength = end1 - base;
merge = xmalloc (baselength + linklength + 1);
memcpy (merge, base, baselength);
memcpy (merge + baselength, link, linklength);
merge[baselength + linklength] = '\0';
}
else if (*link == '/' && *(link + 1) == '/')
{
/* LINK begins with "//" and so is a net path: we need to
replace everything after (and including) the double slash
with LINK. */
/* uri_merge("foo", "//new/bar") -> "//new/bar" */
/* uri_merge("//old/foo", "//new/bar") -> "//new/bar" */
/* uri_merge("http://old/foo", "//new/bar") -> "http://new/bar" */
int span;
const char *slash;
const char *start_insert;
/* Look for first slash. */
slash = memchr (base, '/', end - base);
/* If found slash and it is a double slash, then replace
from this point, else default to replacing from the
beginning. */
if (slash && *(slash + 1) == '/')
start_insert = slash;
else
start_insert = base;
span = start_insert - base;
merge = xmalloc (span + linklength + 1);
if (span)
memcpy (merge, base, span);
memcpy (merge + span, link, linklength);
merge[span + linklength] = '\0';
}
else if (*link == '/')
{
/* LINK is an absolute path: we need to replace everything
after (and including) the FIRST slash with LINK.
So, if BASE is "http://host/whatever/foo/bar", and LINK is
"/qux/xyzzy", our result should be
"http://host/qux/xyzzy". */
int span;
const char *slash;
const char *start_insert = NULL; /* for gcc to shut up. */
const char *pos = base;
bool seen_slash_slash = false;
/* We're looking for the first slash, but want to ignore
double slash. */
again:
slash = memchr (pos, '/', end - pos);
if (slash && !seen_slash_slash)
if (*(slash + 1) == '/')
{
pos = slash + 2;
seen_slash_slash = true;
goto again;
}
/* At this point, SLASH is the location of the first / after
"//", or the first slash altogether. START_INSERT is the
pointer to the location where LINK will be inserted. When
examining the last two examples, keep in mind that LINK
begins with '/'. */
if (!slash && !seen_slash_slash)
/* example: "foo" */
/* ^ */
start_insert = base;
else if (!slash && seen_slash_slash)
/* example: "http://foo" */
/* ^ */
start_insert = end;
else if (slash && !seen_slash_slash)
/* example: "foo/bar" */
/* ^ */
start_insert = base;
else if (slash && seen_slash_slash)
/* example: "http://something/" */
/* ^ */
start_insert = slash;
span = start_insert - base;
merge = xmalloc (span + linklength + 1);
if (span)
memcpy (merge, base, span);
memcpy (merge + span, link, linklength);
merge[span + linklength] = '\0';
}
else
{
/* LINK is a relative URL: we need to replace everything
after last slash (possibly empty) with LINK.
So, if BASE is "whatever/foo/bar", and LINK is "qux/xyzzy",
our result should be "whatever/foo/qux/xyzzy". */
bool need_explicit_slash = false;
int span;
const char *start_insert;
const char *last_slash = find_last_char (base, end, '/');
if (!last_slash)
{
/* No slash found at all. Replace what we have with LINK. */
start_insert = base;
}
else if (last_slash && last_slash >= base + 2
&& last_slash[-2] == ':' && last_slash[-1] == '/')
{
/* example: http://host" */
/* ^ */
start_insert = end + 1;
need_explicit_slash = true;
}
else
{
/* example: "whatever/foo/bar" */
/* ^ */
start_insert = last_slash + 1;
}
span = start_insert - base;
merge = xmalloc (span + linklength + 1);
if (span)
memcpy (merge, base, span);
if (need_explicit_slash)
merge[span - 1] = '/';
memcpy (merge + span, link, linklength);
merge[span + linklength] = '\0';
}
return merge;
}
#define APPEND(p, s) do { \
int len = strlen (s); \
memcpy (p, s, len); \
p += len; \
} while (0)
/* Use this instead of password when the actual password is supposed
to be hidden. We intentionally use a generic string without giving
away the number of characters in the password, like previous
versions did. */
#define HIDDEN_PASSWORD "*password*"
/* Recreate the URL string from the data in URL.
If HIDE is true (as it is when we're calling this on a URL we plan
to print, but not when calling it to canonicalize a URL for use
within the program), password will be hidden. Unsafe characters in
the URL will be quoted. */
char *
url_string (const struct url *url, enum url_auth_mode auth_mode)
{
int size;
char *result, *p;
char *quoted_host, *quoted_user = NULL, *quoted_passwd = NULL;
int scheme_port = supported_schemes[url->scheme].default_port;
const char *scheme_str = supported_schemes[url->scheme].leading_string;
int fplen = full_path_length (url);
bool brackets_around_host;
assert (scheme_str != NULL);
/* Make sure the user name and password are quoted. */
if (url->user)
{
if (auth_mode != URL_AUTH_HIDE)
{
quoted_user = url_escape_allow_passthrough (url->user);
if (url->passwd)
{
if (auth_mode == URL_AUTH_HIDE_PASSWD)
quoted_passwd = (char *) HIDDEN_PASSWORD;
else
quoted_passwd = url_escape_allow_passthrough (url->passwd);
}
}
}
/* In the unlikely event that the host name contains non-printable
characters, quote it for displaying to the user. */
quoted_host = url_escape_allow_passthrough (url->host);
/* Undo the quoting of colons that URL escaping performs. IPv6
addresses may legally contain colons, and in that case must be
placed in square brackets. */
if (quoted_host != url->host)
unescape_single_char (quoted_host, ':');
brackets_around_host = strchr (quoted_host, ':') != NULL;
size = (strlen (scheme_str)
+ strlen (quoted_host)
+ (brackets_around_host ? 2 : 0)
+ fplen
+ 1);
if (url->port != scheme_port)
size += 1 + numdigit (url->port);
if (quoted_user)
{
size += 1 + strlen (quoted_user);
if (quoted_passwd)
size += 1 + strlen (quoted_passwd);
}
p = result = xmalloc (size);
APPEND (p, scheme_str);
if (quoted_user)
{
APPEND (p, quoted_user);
if (quoted_passwd)
{
*p++ = ':';
APPEND (p, quoted_passwd);
}
*p++ = '@';
}
if (brackets_around_host)
*p++ = '[';
APPEND (p, quoted_host);
if (brackets_around_host)
*p++ = ']';
if (url->port != scheme_port)
{
*p++ = ':';
p = number_to_string (p, url->port);
}
full_path_write (url, p);
p += fplen;
*p++ = '\0';
assert (p - result == size);
if (quoted_user && quoted_user != url->user)
xfree (quoted_user);
if (quoted_passwd && auth_mode == URL_AUTH_SHOW
&& quoted_passwd != url->passwd)
xfree (quoted_passwd);
if (quoted_host != url->host)
xfree (quoted_host);
return result;
}
/* Return true if scheme a is similar to scheme b.
Schemes are similar if they are equal. If SSL is supported, schemes
are also similar if one is http (SCHEME_HTTP) and the other is https
(SCHEME_HTTPS). */
bool
schemes_are_similar_p (enum url_scheme a, enum url_scheme b)
{
if (a == b)
return true;
#ifdef HAVE_SSL
if ((a == SCHEME_HTTP && b == SCHEME_HTTPS)
|| (a == SCHEME_HTTPS && b == SCHEME_HTTP))
return true;
#endif
return false;
}
static int
getchar_from_escaped_string (const char *str, char *c)
{
const char *p = str;
assert (str && *str);
assert (c);
if (p[0] == '%')
{
if (!c_isxdigit(p[1]) || !c_isxdigit(p[2]))
{
*c = '%';
return 1;
}
else
{
if (p[2] == 0)
return 0; /* error: invalid string */
*c = X2DIGITS_TO_NUM (p[1], p[2]);
if (URL_RESERVED_CHAR(*c))
{
*c = '%';
return 1;
}
else
return 3;
}
}
else
{
*c = p[0];
}
return 1;
}
bool
are_urls_equal (const char *u1, const char *u2)
{
const char *p, *q;
int pp, qq;
char ch1, ch2;
assert(u1 && u2);
p = u1;
q = u2;
while (*p && *q
&& (pp = getchar_from_escaped_string (p, &ch1))
&& (qq = getchar_from_escaped_string (q, &ch2))
&& (c_tolower(ch1) == c_tolower(ch2)))
{
p += pp;
q += qq;
}
return (*p == 0 && *q == 0 ? true : false);
}
#ifdef TESTING
/* Debugging and testing support for path_simplify. */
#if 0
/* Debug: run path_simplify on PATH and return the result in a new
string. Useful for calling from the debugger. */
static char *
ps (char *path)
{
char *copy = xstrdup (path);
path_simplify (copy);
return copy;
}
#endif
static const char *
run_test (const char *test, const char *expected_result, enum url_scheme scheme,
bool expected_change)
{
char *test_copy = xstrdup (test);
bool modified = path_simplify (scheme, test_copy);
if (0 != strcmp (test_copy, expected_result))
{
printf ("Failed path_simplify(\"%s\"): expected \"%s\", got \"%s\".\n",
test, expected_result, test_copy);
mu_assert ("", 0);
}
if (modified != expected_change)
{
if (expected_change)
printf ("Expected modification with path_simplify(\"%s\").\n",
test);
else
printf ("Expected no modification with path_simplify(\"%s\").\n",
test);
}
xfree (test_copy);
mu_assert ("", modified == expected_change);
return NULL;
}
const char *
test_path_simplify (void)
{
static const struct {
const char *test, *result;
enum url_scheme scheme;
bool should_modify;
} tests[] = {
{ "", "", SCHEME_HTTP, false },
{ ".", "", SCHEME_HTTP, true },
{ "./", "", SCHEME_HTTP, true },
{ "..", "", SCHEME_HTTP, true },
{ "../", "", SCHEME_HTTP, true },
{ "..", "..", SCHEME_FTP, false },
{ "../", "../", SCHEME_FTP, false },
{ "foo", "foo", SCHEME_HTTP, false },
{ "foo/bar", "foo/bar", SCHEME_HTTP, false },
{ "foo///bar", "foo///bar", SCHEME_HTTP, false },
{ "foo/.", "foo/", SCHEME_HTTP, true },
{ "foo/./", "foo/", SCHEME_HTTP, true },
{ "foo./", "foo./", SCHEME_HTTP, false },
{ "foo/../bar", "bar", SCHEME_HTTP, true },
{ "foo/../bar/", "bar/", SCHEME_HTTP, true },
{ "foo/bar/..", "foo/", SCHEME_HTTP, true },
{ "foo/bar/../x", "foo/x", SCHEME_HTTP, true },
{ "foo/bar/../x/", "foo/x/", SCHEME_HTTP, true },
{ "foo/..", "", SCHEME_HTTP, true },
{ "foo/../..", "", SCHEME_HTTP, true },
{ "foo/../../..", "", SCHEME_HTTP, true },
{ "foo/../../bar/../../baz", "baz", SCHEME_HTTP, true },
{ "foo/../..", "..", SCHEME_FTP, true },
{ "foo/../../..", "../..", SCHEME_FTP, true },
{ "foo/../../bar/../../baz", "../../baz", SCHEME_FTP, true },
{ "a/b/../../c", "c", SCHEME_HTTP, true },
{ "./a/../b", "b", SCHEME_HTTP, true }
};
unsigned i;
for (i = 0; i < countof (tests); i++)
{
const char *message;
const char *test = tests[i].test;
const char *expected_result = tests[i].result;
enum url_scheme scheme = tests[i].scheme;
bool expected_change = tests[i].should_modify;
message = run_test (test, expected_result, scheme, expected_change);
if (message) return message;
}
return NULL;
}
const char *
test_append_uri_pathel(void)
{
unsigned i;
static const struct {
const char *original_url;
const char *input;
bool escaped;
const char *expected_result;
} test_array[] = {
{ "http://www.yoyodyne.com/path/", "somepage.html", false, "http://www.yoyodyne.com/path/somepage.html" },
};
for (i = 0; i < countof(test_array); ++i)
{
struct growable dest;
const char *p = test_array[i].input;
memset (&dest, 0, sizeof (dest));
append_string (test_array[i].original_url, &dest);
append_uri_pathel (p, p + strlen(p), test_array[i].escaped, &dest);
mu_assert ("test_append_uri_pathel: wrong result",
strcmp (dest.base, test_array[i].expected_result) == 0);
xfree (dest.base);
}
return NULL;
}
const char *
test_are_urls_equal(void)
{
unsigned i;
static const struct {
const char *url1;
const char *url2;
bool expected_result;
} test_array[] = {
{ "http://www.adomain.com/apath/", "http://www.adomain.com/apath/", true },
{ "http://www.adomain.com/apath/", "http://www.adomain.com/anotherpath/", false },
{ "http://www.adomain.com/apath/", "http://www.anotherdomain.com/path/", false },
{ "http://www.adomain.com/~path/", "http://www.adomain.com/%7epath/", true },
{ "http://www.adomain.com/longer-path/", "http://www.adomain.com/path/", false },
{ "http://www.adomain.com/path%2f", "http://www.adomain.com/path/", false },
};
for (i = 0; i < countof(test_array); ++i)
{
mu_assert ("test_are_urls_equal: wrong result",
are_urls_equal (test_array[i].url1, test_array[i].url2) == test_array[i].expected_result);
}
return NULL;
}
#endif /* TESTING */
/*
* vim: et ts=2 sw=2
*/
|