X-Git-Url: http://sjero.net/git/?a=blobdiff_plain;f=src%2Furl.c;h=e79cf8a2e0736688c0ce1495adc7d7b48286946c;hb=84395897ad2d1c107be470946daba744b2e7ebe8;hp=31dc09f654220847ae10836a520d8b13e9815023;hpb=da99855784988c6bf125799f47c57d888bbc25f1;p=wget diff --git a/src/url.c b/src/url.c index 31dc09f6..e79cf8a2 100644 --- a/src/url.c +++ b/src/url.c @@ -1,6 +1,6 @@ /* URL handling. Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, - 2004, 2005, 2006, 2007 Free Software Foundation, Inc. + 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc. This file is part of GNU Wget. @@ -17,17 +17,18 @@ 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 . -In addition, as a special exception, the Free Software Foundation -gives permission to link the code of its release of Wget with the -OpenSSL project's "OpenSSL" library (or with modified versions of it -that use the same license as the "OpenSSL" library), and distribute -the linked executables. You must obey the GNU General Public License -in all respects for all of the code used other than "OpenSSL". If you -modify this file, you may extend this exception to your version of the -file, but you are not obligated to do so. If you do not wish to do -so, delete this exception statement from your version. */ +Additional permission under GNU GPL version 3 section 7 -#include +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 #include @@ -38,7 +39,6 @@ so, delete this exception statement from your version. */ #include #include -#include "wget.h" #include "utils.h" #include "url.h" #include "host.h" /* for is_valid_ipv6_address */ @@ -81,7 +81,7 @@ static struct scheme_data supported_schemes[] = /* Forward declarations: */ -static bool path_simplify (char *); +static bool path_simplify (enum url_scheme, char *); /* Support for escaping and unescaping of URL strings. */ @@ -640,7 +640,7 @@ static const char *parse_errors[] = { error, and if ERROR is not NULL, also set *ERROR to the appropriate error code. */ struct url * -url_parse (const char *url, int *error) +url_parse (const char *url, int *error, struct iri *iri) { struct url *u; const char *p; @@ -659,7 +659,7 @@ url_parse (const char *url, int *error) int port; char *user = NULL, *passwd = NULL; - char *url_encoded = NULL; + char *url_encoded = NULL, *new_url = NULL; int error_code; @@ -670,9 +670,20 @@ url_parse (const char *url, int *error) goto error; } - url_encoded = reencode_escapes (url); + if (iri && iri->utf8_encode) + { + url_unescape ((char *) url); + iri->utf8_encode = remote_to_utf8 (iri, url, (const char **) &new_url); + if (!iri->utf8_encode) + new_url = NULL; + } + + url_encoded = reencode_escapes (new_url ? new_url : url); p = url_encoded; + if (new_url && url_encoded != new_url) + xfree (new_url); + p += strlen (supported_schemes[scheme].leading_string); uname_b = p; p = url_skip_credentials (p); @@ -829,7 +840,7 @@ url_parse (const char *url, int *error) u->passwd = passwd; u->path = strdupdelim (path_b, path_e); - path_modified = path_simplify (u->path); + path_modified = path_simplify (scheme, u->path); split_path (u->path, &u->dir, &u->file); host_modified = lowercase_str (u->host); @@ -842,6 +853,18 @@ url_parse (const char *url, int *error) { url_unescape (u->host); host_modified = true; + + /* 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; + host_modified = true; + } + } } if (params_b) @@ -851,7 +874,7 @@ url_parse (const char *url, int *error) if (fragment_b) u->fragment = strdupdelim (fragment_b, fragment_e); - if (path_modified || u->fragment || host_modified || path_b == path_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 @@ -889,7 +912,7 @@ url_parse (const char *url, int *error) const char * url_error (int error_code) { - assert (error_code >= 0 && error_code < countof (parse_errors)); + assert (error_code >= 0 && ((size_t) error_code) < countof (parse_errors)); return _(parse_errors[error_code]); } @@ -1526,10 +1549,11 @@ url_file_name (const struct url *u) test case. */ static bool -path_simplify (char *path) +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) @@ -1545,17 +1569,29 @@ path_simplify (char *path) { /* Handle "../" by retreating the tortoise by one path element -- but not past beggining. */ - if (t > path) + if (t > beg) { /* Move backwards until T hits the beginning of the previous path element or the beginning of path. */ - for (--t; t > path && t[-1] != '/'; t--) + for (--t; t > beg && t[-1] != '/'; t--) ; } + else if (scheme == SCHEME_FTP) + { + /* 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. */ @@ -1991,9 +2027,10 @@ are_urls_equal (const char *u1, const char *u2) return (*p == 0 && *q == 0 ? true : false); } -#if 0 +#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 * @@ -2003,17 +2040,20 @@ ps (char *path) path_simplify (copy); return copy; } +#endif -static void -run_test (char *test, char *expected_result, bool expected_change) +static const char * +run_test (char *test, char *expected_result, enum url_scheme scheme, + bool expected_change) { char *test_copy = xstrdup (test); - bool modified = path_simplify (test_copy); + 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) { @@ -2025,51 +2065,60 @@ run_test (char *test, char *expected_result, bool expected_change) test); } xfree (test_copy); + mu_assert ("", modified == expected_change); + return NULL; } -static void +const char * test_path_simplify (void) { static struct { char *test, *result; + enum url_scheme scheme; bool should_modify; } tests[] = { - { "", "", false }, - { ".", "", true }, - { "./", "", true }, - { "..", "", true }, - { "../", "", true }, - { "foo", "foo", false }, - { "foo/bar", "foo/bar", false }, - { "foo///bar", "foo///bar", false }, - { "foo/.", "foo/", true }, - { "foo/./", "foo/", true }, - { "foo./", "foo./", false }, - { "foo/../bar", "bar", true }, - { "foo/../bar/", "bar/", true }, - { "foo/bar/..", "foo/", true }, - { "foo/bar/../x", "foo/x", true }, - { "foo/bar/../x/", "foo/x/", true }, - { "foo/..", "", true }, - { "foo/../..", "", true }, - { "foo/../../..", "", true }, - { "foo/../../bar/../../baz", "baz", true }, - { "a/b/../../c", "c", true }, - { "./a/../b", "b", true } + { "", "", 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 } }; int i; for (i = 0; i < countof (tests); i++) { + const char *message; char *test = tests[i].test; char *expected_result = tests[i].result; + enum url_scheme scheme = tests[i].scheme; bool expected_change = tests[i].should_modify; - run_test (test, expected_result, expected_change); + message = run_test (test, expected_result, scheme, expected_change); + if (message) return message; } + return NULL; } -#endif - -#ifdef TESTING const char * test_append_uri_pathel()