Index: apachesolr.index.inc
===================================================================
RCS file: /cvs/drupal-contrib/contributions/modules/apachesolr/apachesolr.index.inc,v
retrieving revision 1.1.2.5
diff -u -p -r1.1.2.5 apachesolr.index.inc
--- apachesolr.index.inc	19 May 2009 19:58:23 -0000	1.1.2.5
+++ apachesolr.index.inc	1 Jul 2009 00:59:04 -0000
@@ -21,6 +21,7 @@ function apachesolr_add_node_document(&$
 function apachesolr_strip_ctl_chars($text) {
   // See:  http://w3.org/International/questions/qa-forms-utf-8.html
   // Printable utf-8 does not include any of these chars below x7F
+  $text = iconv("UTF-8", "UTF-8//IGNORE", $text);
   return preg_replace('@[\x00-\x08\x0B\x0C\x0E-\x1F]@', ' ', $text);
 }
 
@@ -28,7 +29,8 @@ function apachesolr_strip_ctl_chars($tex
  * Strip html tags and also control characters that cause Jetty/Solr to fail.
  */
 function apachesolr_clean_text($text) {
-  return _apachesolr_strip_decode(preg_replace('@[\x00-\x08\x0B\x0C\x0E-\x1F]@', ' ', $text));
+  $text = apachesolr_strip_ctl_chars($text);
+  return _apachesolr_strip_decode($text);
 }
 
 function _apachesolr_strip_decode($text) {