Follow RFC 2616 and httpbis specifications when handling redirects

[wget] / src / html-url.c

diff --git a/src/html-url.c b/src/html-url.c
index 0a8afc5ef4fb3510877ff8ad7bced52133e18c00..f02982173cec0302e0295e68aaecac5abad5942d 100644 (file)
--- a/src/html-url.c
+++ b/src/html-url.c
@@ -1,6 +1,6 @@
 /* Collect URLs from HTML source.
    Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
-   2007, 2008, 2009, 2010 Free Software Foundation, Inc.
+   2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
 
 This file is part of GNU Wget.
 
@@ -36,6 +36,7 @@ as that of the covered work.  */
 #include <errno.h>
 #include <assert.h>
 
+#include "exits.h"
 #include "html-parse.h"
 #include "url.h"
 #include "utils.h"
@@ -674,8 +675,9 @@ collect_tags_mapper (struct taginfo *tag, void *arg)
 
   check_style_attr (tag, ctx);
 
-  if (tag->end_tag_p && (0 == strcasecmp (tag->name, "style")) &&
-      tag->contents_begin && tag->contents_end)
+  if (tag->end_tag_p && (0 == strcasecmp (tag->name, "style"))
+      && tag->contents_begin && tag->contents_end
+      && tag->contents_begin <= tag->contents_end)
   {
     /* parse contents */
     get_urls_css (ctx, tag->contents_begin - ctx->text,
@@ -802,6 +804,13 @@ get_urls_file (const char *file)
           url_text = merged;
         }
 
+      char *new_url = rewrite_shorthand_url (url_text);
+      if (new_url)
+        {
+          xfree (url_text);
+          url_text = new_url;
+        }
+
       url = url_parse (url_text, &up_error_code, NULL, false);
       if (!url)
         {
@@ -810,6 +819,7 @@ get_urls_file (const char *file)
                      file, url_text, error);
           xfree (url_text);
           xfree (error);
+          inform_exit_status (URLERROR);
           continue;
         }
       xfree (url_text);