Index: includes/path.inc
===================================================================
RCS file: /cvs/drupal/drupal/includes/path.inc,v
retrieving revision 1.13
diff -u -r1.13 path.inc
--- includes/path.inc	23 Dec 2006 22:04:52 -0000	1.13
+++ includes/path.inc	30 Sep 2008 05:17:50 -0000
@@ -46,42 +46,73 @@
 
   // Use $count to avoid looking up paths in subsequent calls if there simply are no aliases
   if (!isset($count)) {
-    $count = db_result(db_query('SELECT COUNT(pid) FROM {url_alias}'));
+    $count = (bool)db_result(db_query_range('SELECT pid FROM {url_alias}', 0, 1));
   }
-
-  if ($action == 'wipe') {
-    $map = array();
-    $no_src = array();
-  }
-  elseif ($count > 0 && $path != '') {
-    if ($action == 'alias') {
-      if (isset($map[$path])) {
-        return $map[$path];
+ // Load the whitelist
+ $whitelist = variable_get('alias_whitelist', array());
+  // And derive the top level component of the path
+  $pos = strpos($path, '/');
+  $top_level = ($pos) ? substr($path, 0, $pos) : $path;
+
+  switch($action) {
+    case 'wipe':
+      $map = array();
+      $no_src = array();
+      $count = 0;
+
+      // Rebuild a white list of top level paths, depending on what
+      // is stored in the url_alias table for this site.
+      $whitelist = array();
+
+      // For each alias in the database, get the top level (i.e. the portion before the first /).
+      // Using GROUP BY is faster than DISTINCT, at least for MyISAM.
+      $result = db_query("SELECT SUBSTRING_INDEX(src, '/', 1) AS path FROM {url_alias} GROUP BY path");
+      while ($row = db_fetch_object($result)) {
+        $whitelist[$row->path] = TRUE;  
       }
-      $alias = db_result(db_query("SELECT dst FROM {url_alias} WHERE src = '%s'", $path));
-      $map[$path] = $alias;
-      return $alias;
-    }
-    // Check $no_src for this $path in case we've already determined that there
-    // isn't a path that has this alias
-    elseif ($action == 'source' && !isset($no_src[$path])) {
-      // Look for the value $path within the cached $map
-      if (!$src = array_search($path, $map)) {
-        if ($src = db_result(db_query("SELECT src FROM {url_alias} WHERE dst = '%s'", $path))) {
-          $map[$src] = $path;
+      variable_set('alias_whitelist', $whitelist);
+      return;
+    case 'alias':
+      if ($count && $path != '') {
+        if (isset($map[$path])) {
+          return $map[$path];
         }
-        else {
-          // We can't record anything into $map because we do not have a valid
-          // index and there is no need because we have not learned anything
-          // about any Drupal path. Thus cache to $no_src.
-          $no_src[$path] = TRUE;
+        // Check the whitelist, if the top_level is not in it, then
+        // no need to do anything further, it is not in the database
+        if (!isset($whitelist[$top_level])) {
+          return FALSE;
         }
+        $alias = db_result(db_query("SELECT dst FROM {url_alias} WHERE src = '%s'", $path));  
+        return $alias;
       }
-      return $src;
-    }
-  }
-
-  return FALSE;
+      return;
+    case 'source':
+      if ($count && $path != '') {
+        // Check $no_src for this $path in case we've already determined that there
+        // isn't a path that has this alias
+        if (!isset($no_src[$path])) {
+          // Look for the value $path within the cached $map
+          if (!$src = array_search($path, $map)) {
+            if ($src = db_result(db_query("SELECT src FROM {url_alias} WHERE dst = '%s'", $path))) {
+              $map[$src] = $path;
+            }
+            else {
+              // We can't record anything into $map because we do not have a valid
+              // index and there is no need because we have not learned anything
+              // about any Drupal path. Thus cache to $no_src.
+              $no_src[$path] = TRUE;
+            }
+          }
+          return $src;
+         }
+       }
+      break;
+   } 
+   return FALSE;  
 }
 
 /**