Automated merge.

[wget] / src / url.c

diff --git a/src/url.c b/src/url.c
index 5025e9377ce7cb18ea43ac1738ce11e347a651d4..48b23d6c649cb208e23933ef8aa08ee58d999815 100644 (file)
--- a/src/url.c
+++ b/src/url.c
@@ -1,11 +1,12 @@
 /* URL handling.
 /* URL handling.

-   Copyright (C) 1996-2005 Free Software Foundation, Inc.
+   Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006, 2007, 2008 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
 
 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 2 of the License, or (at
+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,
 your option) any later version.
 
 GNU Wget is distributed in the hope that it will be useful,


@@ -14,20 +15,20 @@ 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
 GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License

-along with Wget; if not, write to the Free Software Foundation, Inc.,
-51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+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 <stdio.h>
 #include <stdlib.h>


@@ -38,10 +39,10 @@ so, delete this exception statement from your version.  */
 #include <errno.h>
 #include <assert.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 "utils.h"
 #include "url.h"
 #include "host.h"  /* for is_valid_ipv6_address */

+#include "iri.h"

 
 #ifdef TESTING
 #include "test.h"
 
 #ifdef TESTING
 #include "test.h"


@@ -81,7 +82,7 @@ static struct scheme_data supported_schemes[] =
 
 /* Forward declarations: */
 
 
 /* Forward declarations: */
 

-static bool path_simplify (char *);
+static bool path_simplify (enum url_scheme, char *);

 \f
 /* Support for escaping and unescaping of URL strings.  */
 
 \f
 /* Support for escaping and unescaping of URL strings.  */
 


@@ -183,7 +184,7 @@ url_unescape (char *s)
         {
           char c;
           /* Do nothing if '%' is not followed by two hex digits. */
         {
           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
             goto copychar;
           c = X2DIGITS_TO_NUM (h[1], h[2]);
           /* Don't unescape %00 because there is no way to insert it


@@ -272,7 +273,7 @@ char_needs_escaping (const char *p)
 {
   if (*p == '%')
     {
 {
   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 false;
       else
         /* Garbled %.. sequence: encode `%'. */


@@ -428,7 +429,7 @@ url_scheme (const char *url)
   return SCHEME_INVALID;
 }
 
   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
 
 /* Return 1 if the URL begins with any "scheme", 0 otherwise.  As
    currently implemented, it returns true if URL begins with


@@ -590,10 +591,10 @@ lowercase_str (char *str)
 {
   bool changed = false;
   for (; *str; str++)
 {
   bool changed = false;
   for (; *str; str++)

-    if (ISUPPER (*str))
+    if (c_isupper (*str))

       {
         changed = true;
       {
         changed = true;

-        *str = TOLOWER (*str);
+        *str = c_tolower (*str);

       }
   return changed;
 }
       }
   return changed;
 }


@@ -670,6 +671,12 @@ url_parse (const char *url, int *error)
       goto error;
     }
 
       goto error;
     }
 

+  if (opt.enable_iri)
+    {
+      url_unescape ((char *) url);
+      url = locale_to_utf8(url);
+    }
+

   url_encoded = reencode_escapes (url);
   p = url_encoded;
 
   url_encoded = reencode_escapes (url);
   p = url_encoded;
 


@@ -769,7 +776,7 @@ url_parse (const char *url, int *error)
       if (port_b != port_e)
         for (port = 0, pp = port_b; pp < port_e; pp++)
           {
       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 */
                 /*               ^                  */
               {
                 /* http://host:12randomgarbage/blah */
                 /*               ^                  */


@@ -829,7 +836,7 @@ url_parse (const char *url, int *error)
   u->passwd = passwd;
 
   u->path = strdupdelim (path_b, path_e);
   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);
   split_path (u->path, &u->dir, &u->file);
 
   host_modified = lowercase_str (u->host);


@@ -844,6 +851,17 @@ url_parse (const char *url, int *error)
       host_modified = true;
     }
 
       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 (params_b)
     u->params = strdupdelim (params_b, params_e);
   if (query_b)


@@ -851,12 +869,12 @@ url_parse (const char *url, int *error)
   if (fragment_b)
     u->fragment = strdupdelim (fragment_b, fragment_e);
 
   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
          u->url using url_string.  */
     {
       /* 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, false);
+      u->url = url_string (u, URL_AUTH_SHOW);

 
       if (url_encoded != url)
         xfree ((char *) url_encoded);
 
       if (url_encoded != url)
         xfree ((char *) url_encoded);


@@ -889,7 +907,7 @@ url_parse (const char *url, int *error)
 const char *
 url_error (int error_code)
 {
 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]);
 }
 
   return _(parse_errors[error_code]);
 }
 


@@ -1072,7 +1090,7 @@ sync_path (struct url *u)
 
   /* Regenerate u->url as well.  */
   xfree (u->url);
 
   /* Regenerate u->url as well.  */
   xfree (u->url);

-  u->url = url_string (u, false);
+  u->url = url_string (u, URL_AUTH_SHOW);

 }
 
 /* Mutators.  Code in ftp.c insists on changing u->dir and u->file.
 }
 
 /* Mutators.  Code in ftp.c insists on changing u->dir and u->file.


@@ -1259,7 +1277,7 @@ UWC,  C,  C,  C,   C,  C,  C,  C,   /* NUL SOH STX ETX  EOT ENQ ACK BEL */
   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,   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,   0,  0,  0,  0,   /* x   y   z   {    |   }   ~   DEL */
+  0,  0,  0,  0,   W,  0,  0,  C,   /* x   y   z   {    |   }   ~   DEL */

 
   C, C, C, C,  C, C, C, C,  C, C, C, C,  C, C, C, C, /* 128-143 */
   C, C, C, C,  C, C, C, C,  C, C, C, C,  C, C, C, C, /* 144-159 */
 
   C, C, C, C,  C, C, C, C,  C, C, C, C,  C, C, C, C, /* 128-143 */
   C, C, C, C,  C, C, C, C,  C, C, C, C,  C, C, C, C, /* 144-159 */


@@ -1370,12 +1388,12 @@ append_uri_pathel (const char *b, const char *e, bool escaped,
       || opt.restrict_files_case == restrict_uppercase)
     {
       char *q;
       || opt.restrict_files_case == restrict_uppercase)
     {
       char *q;

-      for (q = TAIL (dest); *q; ++q)
+      for (q = TAIL (dest); q < TAIL (dest) + outlen; ++q)

         {
           if (opt.restrict_files_case == restrict_lowercase)
         {
           if (opt.restrict_files_case == restrict_lowercase)

-            *q = TOLOWER (*q);
+            *q = c_tolower (*q);

           else
           else

-            *q = TOUPPER (*q);
+            *q = c_toupper (*q);

         }
     }
           
         }
     }
           


@@ -1526,10 +1544,11 @@ url_file_name (const struct url *u)
    test case.  */
 
 static bool
    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 *h = path;               /* hare */
   char *t = path;               /* tortoise */

+  char *beg = path;

   char *end = strchr (path, '\0');
 
   while (h < end)
   char *end = strchr (path, '\0');
 
   while (h < end)


@@ -1545,17 +1564,29 @@ path_simplify (char *path)
         {
           /* Handle "../" by retreating the tortoise by one path
              element -- but not past beggining.  */
         {
           /* 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. */
             {
               /* 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
         {
           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.  */
           /* 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.  */


@@ -1815,7 +1846,7 @@ uri_merge (const char *base, const char *link)
    the URL will be quoted.  */
 
 char *
    the URL will be quoted.  */
 
 char *

-url_string (const struct url *url, bool hide_password)
+url_string (const struct url *url, enum url_auth_mode auth_mode)

 {
   int size;
   char *result, *p;
 {
   int size;
   char *result, *p;


@@ -1832,13 +1863,16 @@ url_string (const struct url *url, bool hide_password)
   /* Make sure the user name and password are quoted. */
   if (url->user)
     {
   /* Make sure the user name and password are quoted. */
   if (url->user)
     {

-      quoted_user = url_escape_allow_passthrough (url->user);
-      if (url->passwd)
+      if (auth_mode != URL_AUTH_HIDE)

         {
         {

-          if (hide_password)
-            quoted_passwd = HIDDEN_PASSWORD;
-          else
-            quoted_passwd = url_escape_allow_passthrough (url->passwd);
+          quoted_user = url_escape_allow_passthrough (url->user);
+          if (url->passwd)
+            {
+              if (auth_mode == URL_AUTH_HIDE_PASSWD)
+                quoted_passwd = HIDDEN_PASSWORD;
+              else
+                quoted_passwd = url_escape_allow_passthrough (url->passwd);
+            }

         }
     }
 
         }
     }
 


@@ -1900,7 +1934,8 @@ url_string (const struct url *url, bool hide_password)
 
   if (quoted_user && quoted_user != url->user)
     xfree (quoted_user);
 
   if (quoted_user && quoted_user != url->user)
     xfree (quoted_user);

-  if (quoted_passwd && !hide_password && quoted_passwd != url->passwd)
+  if (quoted_passwd && auth_mode == URL_AUTH_SHOW
+      && quoted_passwd != url->passwd)

     xfree (quoted_passwd);
   if (quoted_host != url->host)
     xfree (quoted_host);
     xfree (quoted_passwd);
   if (quoted_host != url->host)
     xfree (quoted_host);


@@ -1936,10 +1971,7 @@ getchar_from_escaped_string (const char *str, char *c)
   
   if (p[0] == '%')
     {
   
   if (p[0] == '%')
     {

-      if (p[1] == 0)
-        return 0; /* error: invalid string */
-
-      if (p[1] == '%')
+      if (!c_isxdigit(p[1]) || !c_isxdigit(p[2]))

         {
           *c = '%';
           return 1;
         {
           *c = '%';
           return 1;


@@ -1950,8 +1982,13 @@ getchar_from_escaped_string (const char *str, char *c)
             return 0; /* error: invalid string */
 
           *c = X2DIGITS_TO_NUM (p[1], p[2]);
             return 0; /* error: invalid string */
 
           *c = X2DIGITS_TO_NUM (p[1], p[2]);

-
-          return 3;
+          if (URL_RESERVED_CHAR(*c))
+            {
+              *c = '%';
+              return 1;
+            }
+          else
+            return 3;

         }
     }
   else
         }
     }
   else


@@ -1968,14 +2005,15 @@ are_urls_equal (const char *u1, const char *u2)
   const char *p, *q;
   int pp, qq;
   char ch1, ch2;
   const char *p, *q;
   int pp, qq;
   char ch1, ch2;

+  assert(u1 && u2);

 
   p = u1;
   q = u2;
 
 
   p = u1;
   q = u2;
 

-  while (*p 
+  while (*p && *q

          && (pp = getchar_from_escaped_string (p, &ch1))
          && (qq = getchar_from_escaped_string (q, &ch2))
          && (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;
     {
       p += pp;
       q += qq;


@@ -1984,9 +2022,10 @@ are_urls_equal (const char *u1, const char *u2)
   return (*p == 0 && *q == 0 ? true : false);
 }
 \f
   return (*p == 0 && *q == 0 ? true : false);
 }
 \f

-#if 0
+#ifdef TESTING

 /* Debugging and testing support for path_simplify. */
 
 /* 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 *
 /* Debug: run path_simplify on PATH and return the result in a new
    string.  Useful for calling from the debugger.  */
 static char *


@@ -1996,17 +2035,20 @@ ps (char *path)
   path_simplify (copy);
   return copy;
 }
   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);
 {
   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);
 
   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 (modified != expected_change)
     {


@@ -2018,51 +2060,60 @@ run_test (char *test, char *expected_result, bool expected_change)
                 test);
     }
   xfree (test_copy);
                 test);
     }
   xfree (test_copy);

+  mu_assert ("", modified == expected_change);
+  return NULL;

 }
 
 }
 

-static void
+const char *

 test_path_simplify (void)
 {
   static struct {
     char *test, *result;
 test_path_simplify (void)
 {
   static struct {
     char *test, *result;

+    enum url_scheme scheme;

     bool should_modify;
   } tests[] = {
     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++)
     {
   };
   int i;
 
   for (i = 0; i < countof (tests); i++)
     {

+      const char *message;

       char *test = tests[i].test;
       char *expected_result = tests[i].result;
       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;
       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()
 
 const char *
 test_append_uri_pathel()


@@ -2086,6 +2137,7 @@ test_append_uri_pathel()
       
       append_string (test_array[i].original_url, &dest);
       append_uri_pathel (p, p + strlen(p), test_array[i].escaped, &dest);
       
       append_string (test_array[i].original_url, &dest);
       append_uri_pathel (p, p + strlen(p), test_array[i].escaped, &dest);

+      append_char ('\0', &dest);

 
       mu_assert ("test_append_uri_pathel: wrong result", 
                  strcmp (dest.base, test_array[i].expected_result) == 0);
 
       mu_assert ("test_append_uri_pathel: wrong result", 
                  strcmp (dest.base, test_array[i].expected_result) == 0);


@@ -2107,6 +2159,8 @@ test_are_urls_equal()
     { "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/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 < sizeof(test_array)/sizeof(test_array[0]); ++i) 
   };
   
   for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i)