From 406fb8bbeffda5b880d1b4a7a194f59e7a111e80 Mon Sep 17 00:00:00 2001
From: hniksic <devnull@localhost>
Date: Fri, 30 Nov 2001 13:33:31 -0800
Subject: [PATCH] [svn] Don't allow more than 20 successive redirections.

---
 NEWS          |  6 ++++++
 TODO          |  2 --
 src/ChangeLog |  4 ++++
 src/retr.c    | 38 ++++++++++++++++++++++++++++++--------
 4 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/NEWS b/NEWS
index 57141aa9..a1853afb 100644
--- a/NEWS
+++ b/NEWS
@@ -37,6 +37,10 @@ conversion now makes the BASE tags point to an empty string.
 same document (<a href="#anchorname">), which used to confuse Wget,
 are now converted correctly.
 
+*** When in page-requisites (-p) mode, no-parent (-np) is ignored when
+retrieving for inline images, stylesheets, and other documents needed
+to display the page.
+
 ** If a host has more than one IP address, Wget uses the other
 addresses when accessing the first one fails.
 
@@ -50,6 +54,8 @@ non-standard port.
 quoting.  Wget no longer dequotes reserved characters, e.g. `%3F' is
 no longer translated to `?', nor `%2B' to `+'.  Unsafe characters
 which are not reserved are still escaped, of course.
+
+** No more than 20 successive redirections are allowed.
 
 * Wget 1.7.1 is a bugfix release with no user-visible changes.
 
diff --git a/TODO b/TODO
index 84c796a3..8dea09d6 100644
--- a/TODO
+++ b/TODO
@@ -28,8 +28,6 @@ changes.
 * Try to devise a scheme so that, when password is unknown, Wget asks
   the user for one.
 
-* Limit the number of successive redirection to max. 20 or so.
-
 * If -c used with -N, check to make sure a file hasn't changed on the server
   before "continuing" to download it (preventing a bogus hybrid file).
 
diff --git a/src/ChangeLog b/src/ChangeLog
index f480009a..c2592d13 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,7 @@
+2001-11-30  Hrvoje Niksic  <hniksic@arsdigita.com>
+
+	* retr.c (retrieve_url): Don't allow more than 20 redirections.
+
 2001-11-30  Hrvoje Niksic  <hniksic@arsdigita.com>
 
 	* recur.c (retrieve_tree): Skip the non-inline entries when
diff --git a/src/retr.c b/src/retr.c
index 6c12462a..1f54cf0b 100644
--- a/src/retr.c
+++ b/src/retr.c
@@ -298,9 +298,16 @@ register_all_redirections (struct hash_table *redirections, const char *final)
 			&& no_proxy_match((u)->host,			\
 					  (const char **)opt.no_proxy))
 
-/* Retrieve the given URL.  Decides which loop to call -- HTTP(S), FTP,
-   or simply copy it with file:// (#### the latter not yet
-   implemented!).  */
+/* Maximum number of allowed redirections.  20 was chosen as a
+   "reasonable" value, which is low enough to not cause havoc, yet
+   high enough to guarantee that normal retrievals will not be hurt by
+   the check.  */
+
+#define MAX_REDIRECTIONS 20
+
+/* Retrieve the given URL.  Decides which loop to call -- HTTP, FTP,
+   FTP, proxy, etc.  */
+
 uerr_t
 retrieve_url (const char *origurl, char **file, char **newloc,
 	      const char *refurl, int *dt)
@@ -314,6 +321,7 @@ retrieve_url (const char *origurl, char **file, char **newloc,
   int up_error_code;		/* url parse error code */
   char *local_file;
   struct hash_table *redirections = NULL;
+  int redirection_count = 0;
 
   /* If dt is NULL, just ignore it.  */
   if (!dt)
@@ -402,18 +410,17 @@ retrieve_url (const char *origurl, char **file, char **newloc,
 	opt.recursive = 0;
       result = ftp_loop (u, dt);
       opt.recursive = oldrec;
-#if 0
+
       /* There is a possibility of having HTTP being redirected to
 	 FTP.  In these cases we must decide whether the text is HTML
 	 according to the suffix.  The HTML suffixes are `.html' and
 	 `.htm', case-insensitive.  */
-      if (redirections && u->local && (u->scheme == SCHEME_FTP))
+      if (redirections && local_file && u->scheme == SCHEME_FTP)
 	{
-	  char *suf = suffix (u->local);
+	  char *suf = suffix (local_file);
 	  if (suf && (!strcasecmp (suf, "html") || !strcasecmp (suf, "htm")))
 	    *dt |= TEXTHTML;
 	}
-#endif
     }
   location_changed = (result == NEWLOCATION);
   if (location_changed)
@@ -462,7 +469,22 @@ retrieve_url (const char *origurl, char **file, char **newloc,
 	  string_set_add (redirections, u->url);
 	}
 
-      /* The new location is OK.  Check for redirection cycle by
+      /* The new location is OK.  Check for max. number of
+	 redirections.  */
+      if (++redirection_count > MAX_REDIRECTIONS)
+	{
+	  logprintf (LOG_NOTQUIET, _("%d redirections exceeded.\n"),
+		     MAX_REDIRECTIONS);
+	  url_free (newloc_parsed);
+	  url_free (u);
+	  if (redirections)
+	    string_set_free (redirections);
+	  xfree (url);
+	  xfree (mynewloc);
+	  return WRONGCODE;
+	}
+
+      /*Check for redirection cycle by
          peeking through the history of redirections. */
       if (string_set_contains (redirections, newloc_parsed->url))
 	{