--- src.orig/conf/regex-normalize.xml	2006-05-21 17:05:23.000000000 +0200
+++ src.new/conf/regex-normalize.xml	2006-05-22 15:04:17.000000000 +0200
@@ -19,4 +19,27 @@
   <pattern>(\?|\&amp;|\&amp;amp;)PHPSESSID=[a-zA-Z0-9]{32}(\&amp;|\&amp;amp;)(.*)</pattern>
   <substitution>$1$3</substitution>
 </regex>
+
+<!-- Java-sessionIDs, e.g.:
+     http://www.somesite.com/;jsessionid=A8D7D812B5EFD3099F099A760F779E3B?query=string
+-->
+<regex>
+  <pattern>(;jsessionid=[a-zA-Z0-9]{32})</pattern>
+  <substitution></substitution>
+</regex>
+
+
+<!-- other (unknown) sessionIDs, e.g.:
+     http://www.example.com/oxid.php/sid/7d675533331837a16ed42ce2004396e0/cl/alist/cnid/72142a71185d5feb1.33707404
+     http://www.example.com/-S:PtVOZ9:eURFQ9,NsQ8-a9NNNNxM/overview.shtml
+-->
+<regex>
+  <pattern>(\/sid\/[a-z0-9]{32}\/)</pattern>
+  <substitution>/</substitution>
+</regex>
+<regex>
+  <pattern>(\/-S:[a-zA-Z0-9]{6}:[\-\.\,a-zA-Z0-9]{20}\/)</pattern>
+  <substitution>/</substitution>
+</regex>
+
 </regex-normalize>
diff -u -r -N src.orig/java/org/apache/nutch/net/RegexUrlNormalizerChecker.java src.new/java/org/apache/nutch/net/RegexUrlNormalizerChecker.java
--- src.orig/java/org/apache/nutch/net/RegexUrlNormalizerChecker.java	1970-01-01 01:00:00.000000000 +0100
+++ src.new/java/org/apache/nutch/net/RegexUrlNormalizerChecker.java	2006-05-22 15:03:52.000000000 +0200
@@ -0,0 +1,75 @@
+/**
+ * Copyright 2005 The Apache Software Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nutch.net;
+
+import java.io.IOException;
+import org.apache.oro.text.regex.*;
+
+import org.apache.nutch.plugin.Extension;
+import org.apache.nutch.plugin.ExtensionPoint;
+import org.apache.nutch.plugin.PluginRepository;
+
+import org.apache.hadoop.util.LogFormatter;
+import org.apache.hadoop.conf.Configuration;
+
+import org.apache.nutch.util.NutchConfiguration;
+
+import java.util.logging.Logger;
+
+import java.io.BufferedReader;
+import java.io.InputStreamReader;
+
+/**
+ * Check RegexUrlNormalizer
+ *
+ * Based on URLFilterChecker by John Xing
+ * 
+ * @author Stefan Neufeind
+ */
+
+public class RegexUrlNormalizerChecker {
+
+  public static final Logger LOG =
+    LogFormatter.getLogger(RegexUrlNormalizerChecker.class.getName());
+  private Configuration conf;
+
+  public RegexUrlNormalizerChecker(Configuration conf) {
+      this.conf = conf;
+  }
+
+  private void normalize()
+    throws MalformedPatternException, IOException {
+    LOG.info("Normalizing with regex-url-normalizer");
+
+    BufferedReader in = new BufferedReader(new InputStreamReader(System.in));
+    String line;
+    while((line=in.readLine())!=null) {
+      RegexUrlNormalizer normalizer = new RegexUrlNormalizer();
+      normalizer.setConf(this.conf);
+      String out = normalizer.normalize(line);
+      System.out.println(out);
+    }
+  }
+
+  public static void main(String args[])
+    throws MalformedPatternException, IOException {
+    RegexUrlNormalizerChecker checker = new RegexUrlNormalizerChecker(NutchConfiguration.create());
+    checker.normalize();
+
+    System.exit(0);
+  }
+}