X-Git-Url: http://sjero.net/git/?p=wget;a=blobdiff_plain;f=src%2Frecur.c;h=b6ba1d9558cb3b163eda8b33e3ac6f11046e553e;hp=b0042dff1a2ec077710e8ead0ae8748624595794;hb=c9c0e4c6418350d913638d73e0a50bebdb5fd983;hpb=a00b834bb39fd2982ebb247d52e576208d4934ab

diff --git a/src/recur.c b/src/recur.c
index b0042dff..b6ba1d95 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, 2012 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>
 
@@ -111,7 +110,8 @@ url_enqueue (struct url_queue *queue, struct iri *i,
   if (queue->count > queue->maxcount)
     queue->maxcount = queue->count;
 
-  DEBUGP (("Enqueuing %s at depth %d\n", url, depth));
+  DEBUGP (("Enqueuing %s at depth %d\n",
+           quotearg_n_style (0, escape_quoting_style, url), depth));
   DEBUGP (("Queue count %d, maxcount %d.\n", queue->count, queue->maxcount));
 
   if (i)
@@ -152,7 +152,8 @@ url_dequeue (struct url_queue *queue, struct iri **i,
 
   --queue->count;
 
-  DEBUGP (("Dequeuing %s at depth %d\n", qel->url, qel->depth));
+  DEBUGP (("Dequeuing %s at depth %d\n",
+           quotearg_n_style (0, escape_quoting_style, qel->url), qel->depth));
   DEBUGP (("Queue count %d, maxcount %d.\n", queue->count, queue->maxcount));
 
   xfree (qel);
@@ -198,7 +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;
@@ -253,26 +253,23 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
          the second time.  */
       if (dl_url_file_map && hash_table_contains (dl_url_file_map, url))
         {
+	  bool is_css_bool;
+
           file = xstrdup (hash_table_get (dl_url_file_map, url));
 
           DEBUGP (("Already downloaded \"%s\", reusing it from \"%s\".\n",
                    url, file));
 
-          /* this sucks, needs to be combined! */
-          if (html_allowed
-              && downloaded_html_set
-              && string_set_contains (downloaded_html_set, file))
-            {
-              descend = true;
-              is_css = false;
-            }
-          if (css_allowed
-              && downloaded_css_set
-              && string_set_contains (downloaded_css_set, file))
-            {
-              descend = true;
-              is_css = true;
-            }
+	  if ((is_css_bool = (css_allowed
+			      && downloaded_css_set
+			      && string_set_contains (downloaded_css_set, file)))
+	      || (html_allowed
+		  && downloaded_html_set
+		  && string_set_contains (downloaded_html_set, file)))
+	    {
+	      descend = true;
+	      is_css = is_css_bool;
+	    }
         }
       else
         {
@@ -281,7 +278,7 @@ 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))
@@ -563,7 +560,8 @@ 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))
@@ -585,6 +583,11 @@ 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,
@@ -635,7 +638,7 @@ download_child_p (const struct urlpos *upos, struct url *parent, int depth,
                  files after downloading or we're just running a spider. */
               if (opt.delete_after || opt.spider)
                 {
-                  logprintf (LOG_VERBOSE, "Removing %s.\n", rfile);
+                  logprintf (LOG_VERBOSE, _("Removing %s.\n"), rfile);
                   if (unlink (rfile))
                       logprintf (LOG_NOTQUIET, "unlink: %s\n",
                                  strerror (errno));