Index: modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java
===================================================================
--- modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java	(revision 1306969)
+++ modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java	(working copy)
@@ -20,12 +20,15 @@
 import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
+import java.io.BufferedReader;
+import java.io.InputStreamReader;
 import java.util.HashMap;
 import java.util.Map;
 
 import org.apache.lucene.benchmark.byTask.utils.Config;
 import org.apache.lucene.benchmark.byTask.utils.StreamUtils;
 import org.apache.lucene.util.ThreadInterruptedException;
+import org.apache.lucene.util.IOUtils;
 import org.xml.sax.Attributes;
 import org.xml.sax.InputSource;
 import org.xml.sax.SAXException;
@@ -172,7 +175,8 @@
         while(true){
           final InputStream localFileIS = is;
           try {
-            reader.parse(new InputSource(localFileIS));
+            // To work around a bug in XERCES, we assume the XML is always UTF8, so we simply provide reader.
+            reader.parse(new InputSource(new BufferedReader(new InputStreamReader(localFileIS, IOUtils.CHARSET_UTF_8))));
           } catch (IOException ioe) {
             synchronized(EnwikiContentSource.this) {
               if (localFileIS != is) {