/* 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.
You should have received a copy of the GNU General Public License
along with Wget. If not, see <http://www.gnu.org/licenses/>.
-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 <config.h>
+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 <errno.h>
#include <assert.h>
-#include "wget.h"
#include "utils.h"
#include "url.h"
#include "host.h" /* for is_valid_ipv6_address */
+#include "iri.h"
#ifdef TESTING
#include "test.h"
/* Forward declarations: */
-static bool path_simplify (char *);
+static bool path_simplify (enum url_scheme, char *);
\f
/* Support for escaping and unescaping of URL strings. */
{
char c;
/* Do nothing if '%' is not followed by two hex digits. */
- if (!h[1] || !h[2] || !(ISXDIGIT (h[1]) && ISXDIGIT (h[2])))
+ if (!h[1] || !h[2] || !(c_isxdigit (h[1]) && c_isxdigit (h[2])))
goto copychar;
c = X2DIGITS_TO_NUM (h[1], h[2]);
/* Don't unescape %00 because there is no way to insert it
{
if (*p == '%')
{
- if (ISXDIGIT (*(p + 1)) && ISXDIGIT (*(p + 2)))
+ if (c_isxdigit (*(p + 1)) && c_isxdigit (*(p + 2)))
return false;
else
/* Garbled %.. sequence: encode `%'. */
return SCHEME_INVALID;
}
-#define SCHEME_CHAR(ch) (ISALNUM (ch) || (ch) == '-' || (ch) == '+')
+#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
{
bool changed = false;
for (; *str; str++)
- if (ISUPPER (*str))
+ if (c_isupper (*str))
{
changed = true;
- *str = TOLOWER (*str);
+ *str = c_tolower (*str);
}
return changed;
}
goto error;
}
+ if (opt.enable_iri)
+ {
+ url_unescape ((char *) url);
+ url = locale_to_utf8(url);
+ }
+
url_encoded = reencode_escapes (url);
p = url_encoded;
if (port_b != port_e)
for (port = 0, pp = port_b; pp < port_e; pp++)
{
- if (!ISDIGIT (*pp))
+ if (!c_isdigit (*pp))
{
/* http://host:12randomgarbage/blah */
/* ^ */
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);
host_modified = true;
}
+ if (opt.enable_iri)
+ {
+ char *new = idn_encode (u->host);
+ if (new)
+ {
+ xfree (u->host);
+ u->host = new;
+ host_modified = true;
+ }
+ }
+
if (params_b)
u->params = strdupdelim (params_b, params_e);
if (query_b)
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
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]);
}
for (q = TAIL (dest); q < TAIL (dest) + outlen; ++q)
{
if (opt.restrict_files_case == restrict_lowercase)
- *q = TOLOWER (*q);
+ *q = c_tolower (*q);
else
- *q = TOUPPER (*q);
+ *q = c_toupper (*q);
}
}
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)
{
/* 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. */
if (p[0] == '%')
{
- if (!ISXDIGIT(p[1]) || !ISXDIGIT(p[2]))
+ if (!c_isxdigit(p[1]) || !c_isxdigit(p[2]))
{
*c = '%';
return 1;
while (*p && *q
&& (pp = getchar_from_escaped_string (p, &ch1))
&& (qq = getchar_from_escaped_string (q, &ch2))
- && (TOLOWER(ch1) == TOLOWER(ch2)))
+ && (c_tolower(ch1) == c_tolower(ch2)))
{
p += pp;
q += qq;
return (*p == 0 && *q == 0 ? true : false);
}
\f
-#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 *
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)
{
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
-\f
-#ifdef TESTING
const char *
test_append_uri_pathel()
projects / wget / blobdiff