X-Git-Url: http://sjero.net/git/?a=blobdiff_plain;f=src%2Frecur.c;h=72274fb52673c36f0924ccbfb1dbc306b5f12bfa;hb=b718128b4f3eb8473fb3b31c8397b49854e74ab7;hp=4e95e86915104d80fb018e2b636a5faab8dfd36e;hpb=18bca2706b4c5c1f3bdad7349e092d0675608a61;p=wget

diff --git a/src/recur.c b/src/recur.c
index 4e95e869..72274fb5 100644
--- a/src/recur.c
+++ b/src/recur.c
@@ -1,6 +1,7 @@
 /* Handling of recursive HTTP retrieving.
-   Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
-   2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc.
+   Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
+   2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
+   Inc.
 
 This file is part of GNU Wget.
 
@@ -33,9 +34,7 @@ as that of the covered work.  */
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#ifdef HAVE_UNISTD_H
-# include <unistd.h>
-#endif /* HAVE_UNISTD_H */
+#include <unistd.h>
 #include <errno.h>
 #include <assert.h>
 
@@ -200,7 +199,6 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
      the queue, but haven't been downloaded yet.  */
   struct hash_table *blacklist;
 
-  int up_error_code;
   struct iri *i = iri_new ();
 
 #define COPYSTR(x)  (x) ? xstrdup(x) : NULL;
@@ -283,7 +281,7 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
           struct url *url_parsed = url_parse (url, &url_err, i, true);
 
           status = retrieve_url (url_parsed, url, &file, &redirected, referer,
-                                 &dt, false, i);
+                                 &dt, false, i, true);
 
           if (html_allowed && file && status == RETROK
               && (dt & RETROKF) && (dt & TEXTHTML))
@@ -565,7 +563,8 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
   if (opt.no_parent
       && schemes_are_similar_p (u->scheme, start_url_parsed->scheme)
       && 0 == strcasecmp (u->host, start_url_parsed->host)
-      && u->port == start_url_parsed->port
+      && (u->scheme != start_url_parsed->scheme
+          || u->port == start_url_parsed->port)
       && !(opt.page_requisites && upos->link_inline_p))
     {
       if (!subdir_p (start_url_parsed->dir, u->dir))
@@ -587,6 +586,11 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
           goto out;
         }
     }
+  if (!accept_url (url))
+    {
+      DEBUGP (("%s is excluded/not-included through regex.\n", url));
+      goto out;
+    }
 
   /* 6. Check for acceptance/rejection rules.  We ignore these rules
      for directories (no file name to match) and for non-leaf HTMLs,