Introduce --trust-server-names. Close CVE-2010-2252.

diff --git a/NEWS b/NEWS
index 899807e470b804a9caf0bfb7abe53dbd96eddea8..d4a98037f9d4f64b316e72d58f0a54e07846da28 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -33,6 +33,9 @@ Please send GNU Wget bug reports to <bug-wget@gnu.org>.
 ** GNU TLS backend works again.
 
 ** Now --timestamping and --continue works well together.
+
+** By default, on server redirects, use the original URL to get the
+   local file name. Close CVE-2010-2252.
 \f
 * Changes in Wget 1.12
 

diff --git a/doc/wget.texi b/doc/wget.texi
index d5eaf4e5f460b968c59a008ba3baf9f04678697f..627e0059461a9dd9fb10e3087cda83c2a8a0b6b9 100644 (file)
--- a/doc/wget.texi
+++ b/doc/wget.texi
@@ -1498,6 +1498,13 @@ This option is useful for some file-downloading CGI programs that use
 @code{Content-Disposition} headers to describe what the name of a
 downloaded file should be.
 
+@cindex Trust server names
+@item --trust-server-names
+
+If this is set to on, on a redirect the last component of the
+redirection URL will be used as the local file name.  By default it is
+used the last component in the original URL.
+
 @cindex authentication
 @item --auth-no-challenge
 
@@ -2810,6 +2817,10 @@ Set the connect timeout---the same as @samp{--connect-timeout}.
 Turn on recognition of the (non-standard) @samp{Content-Disposition}
 HTTP header---if set to @samp{on}, the same as @samp{--content-disposition}.
 
+@item trust_server_names = on/off
+If set to on, use the last component of a redirection URL for the local
+file name.
+
 @item continue = on/off
 If set to on, force continuation of preexistent partially retrieved
 files.  See @samp{-c} before setting it.

diff --git a/src/ChangeLog b/src/ChangeLog
index 5c8dea7ad3b90fd2d3634ad626ff9cbdc6d69630..60e82d944cf7a8a23d307552b25f1576698757de 100644 (file)
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,18 @@
+2010-07-28  Giuseppe Scrivano  <gscrivano@gnu.org>
+
+       * http.h (http_loop): Add new argument `original_url'
+       * http.c (http_loop): Add new argument `original_url'.  Use
+       `original_url' to get a filename if `trustservernames' is false.
+
+       * init.c (commands): Add "trustservernames".
+
+       * options.h (library): Add variable `trustservernames'.
+
+       * main.c (option_data): Add trust-server-names.
+       (print_help): Describe --trust-server-names.
+
+       * retr.c (retrieve_url): Pass new argument to `http_loop'.
+
 2010-07-20  Alan Jenkins <alan-jenkins@tuffmail.co.uk> (tiny change)
 
        * http.c (gethttp): Check content-length was set before trying to

diff --git a/src/ftp.c b/src/ftp.c
index 42b0671e1c00510a5fbf426c46706ccffe0ceb73..9395369065f7a0f0e71105d2e915a8c531a38a59 100644 (file)
--- a/src/ftp.c
+++ b/src/ftp.c
@@ -2137,7 +2137,7 @@ ftp_retrieve_glob (struct url *u, ccon *con, int action)
    of URL.  Inherently, its capabilities are limited on what can be
    encoded into a URL.  */
 uerr_t
-ftp_loop (struct url *u, char **local_file, int *dt, struct url *proxy, 
+ftp_loop (struct url *u, char **local_file, int *dt, struct url *proxy,
           bool recursive, bool glob)
 {
   ccon con;                     /* FTP connection */

diff --git a/src/http.c b/src/http.c
index 1c1e165ceea0629e7f85aa7b379cd1663753bbf8..6795296706a8dae6b30e3f126fef5f0e8a5fa825 100644 (file)
--- a/src/http.c
+++ b/src/http.c
@@ -2593,8 +2593,9 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file));
 /* The genuine HTTP loop!  This is the part where the retrieval is
    retried, and retried, and retried, and...  */
 uerr_t
-http_loop (struct url *u, char **newloc, char **local_file, const char *referer,
-           int *dt, struct url *proxy, struct iri *iri)
+http_loop (struct url *u, struct url *original_url, char **newloc,
+           char **local_file, const char *referer, int *dt, struct url *proxy,
+           struct iri *iri)
 {
   int count;
   bool got_head = false;         /* used for time-stamping and filename detection */
@@ -2641,7 +2642,8 @@ http_loop (struct url *u, char **newloc, char **local_file, const char *referer,
     }
   else if (!opt.content_disposition)
     {
-      hstat.local_file = url_file_name (u);
+      hstat.local_file =
+        url_file_name (opt.trustservernames ? u : original_url);
       got_name = true;
     }
 
@@ -2679,7 +2681,7 @@ File %s already there; not retrieving.\n\n"),
 
   /* Send preliminary HEAD request if -N is given and we have an existing
    * destination file. */
-  file_name = url_file_name (u);
+  file_name = url_file_name (opt.trustservernames ? u : original_url);
   if (opt.timestamping && (file_exists_p (file_name)
                            || opt.content_disposition))
     send_head_first = true;
@@ -3039,9 +3041,9 @@ Remote file exists.\n\n"));
 
           /* Remember that we downloaded the file for later ".orig" code. */
           if (*dt & ADDED_HTML_EXTENSION)
-            downloaded_file(FILE_DOWNLOADED_AND_HTML_EXTENSION_ADDED, hstat.local_file);
+            downloaded_file (FILE_DOWNLOADED_AND_HTML_EXTENSION_ADDED, hstat.local_file);
           else
-            downloaded_file(FILE_DOWNLOADED_NORMALLY, hstat.local_file);
+            downloaded_file (FILE_DOWNLOADED_NORMALLY, hstat.local_file);
 
           ret = RETROK;
           goto exit;
@@ -3072,9 +3074,9 @@ Remote file exists.\n\n"));
 
               /* Remember that we downloaded the file for later ".orig" code. */
               if (*dt & ADDED_HTML_EXTENSION)
-                downloaded_file(FILE_DOWNLOADED_AND_HTML_EXTENSION_ADDED, hstat.local_file);
+                downloaded_file (FILE_DOWNLOADED_AND_HTML_EXTENSION_ADDED, hstat.local_file);
               else
-                downloaded_file(FILE_DOWNLOADED_NORMALLY, hstat.local_file);
+                downloaded_file (FILE_DOWNLOADED_NORMALLY, hstat.local_file);
 
               ret = RETROK;
               goto exit;

diff --git a/src/http.h b/src/http.h
index 293b82e448206fda89a3fd1c30d109cf6838e024..1b923ebb55020a405f04509c80e8b3d061bc1fdd 100644 (file)
--- a/src/http.h
+++ b/src/http.h
@@ -33,8 +33,8 @@ as that of the covered work.  */
 
 struct url;
 
-uerr_t http_loop (struct url *, char **, char **, const char *, int *,
-                 struct url *, struct iri *);
+uerr_t http_loop (struct url *, struct url *, char **, char **, const char *,
+                  int *, struct url *, struct iri *);
 void save_cookies (void);
 void http_cleanup (void);
 time_t http_atotm (const char *);

diff --git a/src/init.c b/src/init.c
index e3e7af21a95f596eaabbfba8f2224863dca10cd1..22394d11d1c16ab985354f917e6721d78926acd0 100644 (file)
--- a/src/init.c
+++ b/src/init.c
@@ -252,6 +252,7 @@ static const struct {
   { "timeout",          NULL,                   cmd_spec_timeout },
   { "timestamping",     &opt.timestamping,      cmd_boolean },
   { "tries",            &opt.ntry,              cmd_number_inf },
+  { "trustservernames", &opt.trustservernames,  cmd_boolean },
   { "useproxy",         &opt.use_proxy,         cmd_boolean },
   { "user",             &opt.user,              cmd_string },
   { "useragent",        NULL,                   cmd_spec_useragent },

diff --git a/src/main.c b/src/main.c
index 3a241fbbf3739e408d3677a098882a7b9d8decd9..5f40897a67d94ad91bd7bc079fc38b0cdf1f4172 100644 (file)
--- a/src/main.c
+++ b/src/main.c
@@ -266,6 +266,7 @@ static struct cmdline_option option_data[] =
     { "timeout", 'T', OPT_VALUE, "timeout", -1 },
     { "timestamping", 'N', OPT_BOOLEAN, "timestamping", -1 },
     { "tries", 't', OPT_VALUE, "tries", -1 },
+    { "trust-server-names", 0, OPT_BOOLEAN, "trustservernames", -1 },
     { "use-server-timestamps", 0, OPT_BOOLEAN, "useservertimestamps", -1 },
     { "user", 0, OPT_VALUE, "user", -1 },
     { "user-agent", 'U', OPT_VALUE, "useragent", -1 },
@@ -680,6 +681,8 @@ Recursive accept/reject:\n"),
     N_("\
   -I,  --include-directories=LIST  list of allowed directories.\n"),
     N_("\
+  --trust-server-names  use the name specified by the redirection url last component.\n"),
+    N_("\
   -X,  --exclude-directories=LIST  list of excluded directories.\n"),
     N_("\
   -np, --no-parent                 don't ascend to the parent directory.\n"),

diff --git a/src/options.h b/src/options.h
index 07872ec1bc063da2b1c9bd2e76b506ab3b74a7a6..9fbedb785f3fff7a6108b0fd8393aa8225c31735 100644 (file)
--- a/src/options.h
+++ b/src/options.h
@@ -242,6 +242,7 @@ struct options
   char *encoding_remote;
   char *locale;
 
+  bool trustservernames;
 #ifdef __VMS
   int ftp_stmlf;                /* Force Stream_LF format for binary FTP. */
 #endif /* def __VMS */

diff --git a/src/retr.c b/src/retr.c
index 911117b7309d85917959f21ea6a8f05446efa999..0604f6811dd676f904832a22080bbd8d15d70214 100644 (file)
--- a/src/retr.c
+++ b/src/retr.c
@@ -731,7 +731,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
 #endif
       || (proxy_url && proxy_url->scheme == SCHEME_HTTP))
     {
-      result = http_loop (u, &mynewloc, &local_file, refurl, dt, proxy_url, iri);
+      result = http_loop (u, orig_parsed, &mynewloc, &local_file, refurl, dt,
+                          proxy_url, iri);
     }
   else if (u->scheme == SCHEME_FTP)
     {