Index: src/test/org/apache/nutch/metadata/TestMetadata.java
===================================================================
--- src/test/org/apache/nutch/metadata/TestMetadata.java	(revision 467333)
+++ src/test/org/apache/nutch/metadata/TestMetadata.java	(working copy)
@@ -1,267 +0,0 @@
-/**
- * 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.metadata;
-
-// JDK imports
-import java.io.ByteArrayInputStream;
-import java.io.ByteArrayOutputStream;
-import java.io.DataInputStream;
-import java.io.DataOutputStream;
-import java.io.IOException;
-import java.util.Properties;
-import junit.framework.Test;
-
-// JUnit imports
-import junit.framework.TestCase;
-import junit.framework.TestSuite;
-import junit.textui.TestRunner;
-
-// Nutch imports
-import org.apache.nutch.metadata.Metadata;
-
-
-/**
- * JUnit based tests of class {@link org.apache.nutch.metadata.Metadata}.
- *
- * @author Chris Mattmann
- * @author Jérôme Charron
- */
-public class TestMetadata extends TestCase {
-
-  
-  public TestMetadata(String testName) {
-    super(testName);
-  }
-  
-  public static Test suite() {
-    return new TestSuite(TestMetadata.class);
-  }
-  
-  public static void main(String[] args) {
-    TestRunner.run(suite());
-  }
-  
-
-  /** Test for the <code>getNormalizedName(String)</code> method. */
-  public void testGetNormalizedName() {
-    assertEquals("Content-Type", Metadata.getNormalizedName("Content-Type"));
-    assertEquals("Content-Type", Metadata.getNormalizedName("ContentType"));
-    assertEquals("Content-Type", Metadata.getNormalizedName("Content-type"));
-    assertEquals("Content-Type", Metadata.getNormalizedName("contenttype"));
-    assertEquals("Content-Type", Metadata.getNormalizedName("contentype"));
-    assertEquals("Content-Type", Metadata.getNormalizedName("contntype"));
-  }
-
-  /** Test for the <code>add(String, String)</code> method. */
-  public void testAdd() {
-    String[] values = null;
-    Metadata meta = new Metadata();
-
-    values = meta.getValues("contentype");
-    assertEquals(0, values.length);
-
-    meta.add("contentype", "value1");
-    values = meta.getValues("contentype");
-    assertEquals(1, values.length);
-    assertEquals("value1", values[0]);
-    
-    meta.add("Content-Type", "value2");
-    values = meta.getValues("contentype");
-    assertEquals(2, values.length);
-    assertEquals("value1", values[0]);
-    assertEquals("value2", values[1]);
-
-    // NOTE : For now, the same value can be added many times.
-    //        Should it be changed?
-    meta.add("ContentType", "value1");
-    values = meta.getValues("Content-Type");
-    assertEquals(3, values.length);
-    assertEquals("value1", values[0]);
-    assertEquals("value2", values[1]);
-    assertEquals("value1", values[2]);
-  }
-
-  /** Test for the <code>set(String, String)</code> method. */
-  public void testSet() {
-    String[] values = null;
-    Metadata meta = new Metadata();
-
-    values = meta.getValues("contentype");
-    assertEquals(0, values.length);
-
-    meta.set("contentype", "value1");
-    values = meta.getValues("contentype");
-    assertEquals(1, values.length);
-    assertEquals("value1", values[0]);
-    
-    meta.set("Content-Type", "value2");
-    values = meta.getValues("contentype");
-    assertEquals(1, values.length);
-    assertEquals("value2", values[0]);
-    
-    meta.set("contenttype", "new value 1");
-    meta.add("contenttype", "new value 2");
-    values = meta.getValues("contentype");
-    assertEquals(2, values.length);
-    assertEquals("new value 1", values[0]);
-    assertEquals("new value 2", values[1]);
-  }
-  
-  /** Test for <code>setAll(Properties)</code> method */
-  public void testSetProperties() {
-    String[] values = null;
-    Metadata meta = new Metadata();
-    Properties props = new Properties();
-    
-    meta.setAll(props);
-    assertEquals(0, meta.size());
-    
-    props.setProperty("name-one", "value1.1");
-    meta.setAll(props);
-    assertEquals(1, meta.size());
-    values = meta.getValues("name-one");
-    assertEquals(1, values.length);
-    assertEquals("value1.1", values[0]);
-    
-    props.setProperty("name-two", "value2.1");
-    meta.setAll(props);
-    assertEquals(2, meta.size());
-    values = meta.getValues("name-one");
-    assertEquals(1, values.length);
-    assertEquals("value1.1", values[0]);
-    values = meta.getValues("name-two");
-    assertEquals(1, values.length);
-    assertEquals("value2.1", values[0]);
-  }
-    
-  /** Test for <code>get(String)</code> method */
-  public void testGet() {
-    Metadata meta = new Metadata();
-    assertNull(meta.get("a-name"));
-    
-    meta.add("a-name", "value-1");
-    assertEquals("value-1", meta.get("a-name"));
-    meta.add("a-name", "value-2");
-    assertEquals("value-1", meta.get("a-name"));
-  }
-    
-  /** Test for <code>isMultiValued()</code> method */
-  public void testIsMultiValued() {
-    Metadata meta = new Metadata();
-    assertFalse(meta.isMultiValued("key"));
-    meta.add("key", "value1");
-    assertFalse(meta.isMultiValued("key"));
-    meta.add("key", "value2");
-    assertTrue(meta.isMultiValued("key"));
-  }
-
-  /** Test for <code>names</code> method */
-  public void testNames() {
-    String[] names = null;
-    Metadata meta = new Metadata();
-    names = meta.names();
-    assertEquals(0, names.length);
-    
-    meta.add("name-one", "value");
-    names = meta.names();
-    assertEquals(1, names.length);
-    assertEquals("name-one", names[0]);
-    meta.add("name-two", "value");
-    names = meta.names();
-    assertEquals(2, names.length);
-  }
-  
-  /** Test for <code>remove(String)</code> method */
-  public void testRemove() {
-    Metadata meta = new Metadata();
-    meta.remove("name-one");
-    assertEquals(0, meta.size());
-    meta.add("name-one", "value-1.1");
-    meta.add("name-one", "value-1.2");
-    meta.add("name-two", "value-2.2");
-    assertEquals(2, meta.size());
-    assertNotNull(meta.get("name-one"));
-    assertNotNull(meta.get("name-two"));
-    meta.remove("name-one");
-    assertEquals(1, meta.size());
-    assertNull(meta.get("name-one"));
-    assertNotNull(meta.get("name-two"));
-    meta.remove("name-two");
-    assertEquals(0, meta.size());
-    assertNull(meta.get("name-one"));
-    assertNull(meta.get("name-two"));
-  }
-
-  /** Test for <code>equals(Object)</code> method */
-  public void testObject() {
-    Metadata meta1 = new Metadata();
-    Metadata meta2 = new Metadata();
-    assertFalse(meta1.equals(null));
-    assertFalse(meta1.equals("String"));
-    assertTrue(meta1.equals(meta2));
-    meta1.add("name-one", "value-1.1");
-    assertFalse(meta1.equals(meta2));
-    meta2.add("name-one", "value-1.1");
-    assertTrue(meta1.equals(meta2));
-    meta1.add("name-one", "value-1.2");
-    assertFalse(meta1.equals(meta2));
-    meta2.add("name-one", "value-1.2");
-    assertTrue(meta1.equals(meta2));
-    meta1.add("name-two", "value-2.1");
-    assertFalse(meta1.equals(meta2));
-    meta2.add("name-two", "value-2.1");
-    assertTrue(meta1.equals(meta2));
-    meta1.add("name-two", "value-2.2");
-    assertFalse(meta1.equals(meta2));
-    meta2.add("name-two", "value-2.x");
-    assertFalse(meta1.equals(meta2));
-  }
-  
-  /** Test for <code>Writable</code> implementation */
-  public void testWritable() {
-    Metadata result = null;
-    Metadata meta = new Metadata();
-    result = writeRead(meta);
-    assertEquals(0, result.size());
-    meta.add("name-one", "value-1.1");
-    result = writeRead(meta);
-    assertEquals(1, result.size());
-    assertEquals(1, result.getValues("name-one").length);
-    assertEquals("value-1.1", result.get("name-one"));
-    meta.add("name-two", "value-2.1");
-    meta.add("name-two", "value-2.2");
-    result = writeRead(meta);
-    assertEquals(2, result.size());
-    assertEquals(1, result.getValues("name-one").length);
-    assertEquals("value-1.1", result.getValues("name-one")[0]);
-    assertEquals(2, result.getValues("name-two").length);
-    assertEquals("value-2.1", result.getValues("name-two")[0]);
-    assertEquals("value-2.2", result.getValues("name-two")[1]);
-  }
-  
-  private Metadata writeRead(Metadata meta) {
-    Metadata readed = new Metadata();
-    try {
-      ByteArrayOutputStream out = new ByteArrayOutputStream();
-      meta.write(new DataOutputStream(out));
-      readed.readFields(new DataInputStream(new ByteArrayInputStream(out.toByteArray())));
-    } catch (IOException ioe) {
-      fail(ioe.toString());
-    }
-    return readed;
-  }
-  	
-}
Index: src/test/org/apache/nutch/protocol/TestContent.java
===================================================================
--- src/test/org/apache/nutch/protocol/TestContent.java	(revision 467333)
+++ src/test/org/apache/nutch/protocol/TestContent.java	(working copy)
@@ -16,7 +16,7 @@
 
 package org.apache.nutch.protocol;
 
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.nutch.util.NutchConfiguration;
 import org.apache.nutch.util.WritableTestUtils;
@@ -38,7 +38,7 @@
 
     String url = "http://www.foo.com/";
 
-    Metadata metaData = new Metadata();
+    PlainMetadata metaData = new PlainMetadata();
     metaData.add("Host", "www.foo.com");
     metaData.add("Content-Type", "text/html");
 
@@ -54,7 +54,7 @@
   /** Unit tests for getContentType(String, String, byte[]) method. */
   public void testGetContentType() throws Exception {
     Content c = null;
-    Metadata p = new Metadata();
+    PlainMetadata p = new PlainMetadata();
 
     c = new Content("http://www.foo.com/",
                     "http://www.foo.com/",
Index: src/test/org/apache/nutch/parse/TestParseData.java
===================================================================
--- src/test/org/apache/nutch/parse/TestParseData.java	(revision 467333)
+++ src/test/org/apache/nutch/parse/TestParseData.java	(working copy)
@@ -16,11 +16,22 @@
 
 package org.apache.nutch.parse;
 
+import java.io.DataInputStream;
+import java.io.DataOutputStream;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.net.MalformedURLException;
+
 import org.apache.hadoop.conf.Configuration;
 import org.apache.nutch.util.NutchConfiguration;
 
 import org.apache.nutch.util.WritableTestUtils;
 import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
+import org.apache.nutch.protocol.Content;
 
 import junit.framework.TestCase;
 
@@ -28,6 +39,7 @@
 
 public class TestParseData extends TestCase {
     
+  private static final int ITERATIONS = 1000;
   private Configuration conf = NutchConfiguration.create();
   
   public TestParseData(String name) { super(name); }
@@ -41,7 +53,7 @@
       new Outlink("http://bar.com/", "Bar", conf)
     };
 
-    Metadata metaData = new Metadata();
+    PlainMetadata metaData = new PlainMetadata();
     metaData.add("Language", "en/us");
     metaData.add("Charset", "UTF-8");
 
@@ -59,7 +71,7 @@
     ParseData original = new ParseData(ParseStatus.STATUS_SUCCESS,
                                        "Max Outlinks Title",
                                        outlinks,
-                                       new Metadata());
+                                       new PlainMetadata());
     Configuration conf = NutchConfiguration.create();
     // No Outlinks
     conf.setInt("db.max.outlinks.per.page", 0);
@@ -78,4 +90,69 @@
     data = (ParseData) WritableTestUtils.writeRead(original, conf);
     assertEquals(outlinks.length, data.getOutlinks().length);
   }
+  
+    
+  public void testIOPerformance() throws FileNotFoundException, MalformedURLException{
+    Configuration conf=NutchConfiguration.create();
+    String url="http://www.apache.org/";
+    String base="http://www.apache.org/";
+    String contentType="text/html";
+
+    
+    File f=new File("build/test/parsedataio");
+    FileOutputStream fos=new FileOutputStream(f);
+    DataOutputStream dos=new DataOutputStream(fos);
+    
+    long time=System.currentTimeMillis();
+    
+    Outlink [] links=new Outlink[30];
+    
+    for(int i=0;i<links.length;i++){
+      links[i]=new Outlink("http://www-apache.org/","apache software foundation", conf);
+    }
+    
+    try {
+      for(int i=0;i<ITERATIONS;i++){
+        
+        ParseStatus p=new ParseStatus(ParseStatus.SUCCESS);
+        PlainMetadata contentMetadata=new PlainMetadata();
+        contentMetadata.add("Content-Length", "13972");
+        contentMetadata.add("Connection", "close");
+        contentMetadata.add("ETag", "b207b4-3694-41e7366772800");
+        contentMetadata.add("nutch.segment.name", "20060101000000");
+        contentMetadata.add("nutch.crawl.score","1.0");
+        contentMetadata.add("nutch.content.digest", "4edc6c719de415f6dd6a0aa99f702762");
+        contentMetadata.add("Accept-Ranges","bytes");
+        contentMetadata.add("Server","Apache/2.2.3 (Unix) mod_ssl/2.2.3 OpenSSL/0.9.7g");
+        contentMetadata.add("Content-Type","text/html");
+        contentMetadata.add("date","Sat, 28 Oct 2006 09:54:24 GMT");
+        contentMetadata.add("Last-Modified","Wed, 27 Sep 2006 18:14:56 GMT");
+        
+        Content c=new Content(url,base,"content".getBytes(),contentType, contentMetadata, conf);
+        ParseData pd=new ParseData(p,"title",links,contentMetadata, contentMetadata);
+
+        pd.write(dos);
+      }
+      fos.flush();
+      fos.close();
+    
+      System.out.println("Write:" + ITERATIONS + " iterations " + (System.currentTimeMillis()-time) + "ms.");
+      System.out.println("Size:" + f.length() + " bytes");
+
+      FileInputStream fis=new FileInputStream(f);
+      DataInputStream dis=new DataInputStream(fis);
+
+      time=System.currentTimeMillis();
+      
+      for(int i=0;i<ITERATIONS;i++){
+        ParseData pd=new ParseData();
+        pd.setConf(conf);
+        pd.readFields(dis);
+      }
+      System.out.println("Read:" + ITERATIONS + " iterations " + (System.currentTimeMillis()-time) + "ms.");
+      
+    } catch (IOException ioe) {
+      fail(ioe.toString());
+    }
+  }
 }
Index: src/java/org/apache/nutch/metadata/Metadata.java
===================================================================
--- src/java/org/apache/nutch/metadata/Metadata.java	(revision 468695)
+++ src/java/org/apache/nutch/metadata/Metadata.java	(working copy)
@@ -46,6 +46,9 @@
  *
  * @author Chris Mattmann
  * @author J&eacute;r&ocirc;me Charron
+ * @deprecated use {@link PlainMetadata} instead, If you need
+ * spell checking capabilities use {@link MetadataSpellChecker} which basically 
+ * decorates PlainMetadata with spell checking capabilities
  */
 public class Metadata implements CreativeCommons,
                                  DublinCore,
@@ -330,5 +333,17 @@
   /* -------------------------- *
    * </implementation:Writable> *
    * -------------------------- */
-   
+  
+  public static PlainMetadata convert(Metadata s){
+    String[] names=s.names();
+    PlainMetadata dest=new PlainMetadata();
+    for(int i=0;i<names.length;i++){
+      String[] values=s.getValues(names[i]);
+      for(int j=0;j<values.length;j++){
+        dest.add(names[i],values[j]);
+      }
+    }
+    return dest;
+  }
+  
 }
Index: src/java/org/apache/nutch/metadata/PlainMetadata.java
===================================================================
--- src/java/org/apache/nutch/metadata/PlainMetadata.java	(revision 0)
+++ src/java/org/apache/nutch/metadata/PlainMetadata.java	(revision 0)
@@ -0,0 +1,221 @@
+/**
+ * Copyright 2006 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.metadata;
+
+import java.io.DataInput;
+import java.io.DataOutput;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Enumeration;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Properties;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.WritableUtils;
+
+/**
+ * Multi-valued metadata container.
+ * 
+ * @author nutch-dev@lucene.apache.org
+ */
+public class PlainMetadata implements Writable {
+
+  /** A map of all metadata attributes */
+  private Map metadata = null;
+
+  /** Constructs a new, empty metadata. */
+  public PlainMetadata() {
+    metadata = new HashMap();
+  }
+
+  /**
+   */
+  public boolean isMultiValued(String name) {
+    return getValues(name).length > 1;
+  }
+
+  /**
+   * Returns an array of the names contained in the metadata.
+   */
+  public String[] names() {
+    return (String[]) metadata.keySet().toArray(new String[metadata.size()]);
+  }
+
+  /**
+   * Get the value associated to a metadata name. If many values are assiociated
+   * to the specified name, then the first one is returned.
+   * 
+   * @param name
+   *          of the metadata.
+   * @return the value associated to the specified metadata name.
+   */
+  public String get(String name) {
+    Object values = metadata.get(name);
+    if ((values != null) && (values instanceof List)) {
+      return (String) ((List) values).get(0);
+    } else {
+      return (String) values;
+    }
+  }
+
+  /**
+   * Get the values associated to a metadata name.
+   * 
+   * @param name
+   *          of the metadata.
+   * @return the values associated to a metadata name.
+   */
+  public String[] getValues(String name) {
+    Object values = metadata.get(name);
+    if (values != null) {
+      if (values instanceof List) {
+        List list = (List) values;
+        return (String[]) list.toArray(new String[list.size()]);
+      } else {
+        return new String[] { (String) values };
+      }
+    }
+    return new String[0];
+  }
+
+  /**
+   * Add a metadata name/value mapping. Add the specified value to the list of
+   * values associated to the specified metadata name.
+   * 
+   * @param name
+   *          the metadata name.
+   * @param value
+   *          the metadata value.
+   */
+  public void add(String name, String value) {
+    Object values = metadata.get(name);
+    if (values != null) {
+      if (values instanceof String) {
+        List list = new ArrayList();
+        list.add(values);
+        list.add(value);
+        metadata.put(name, list);
+      } else if (values instanceof List) {
+        ((List) values).add(value);
+      }
+    } else {
+      metadata.put(name, value);
+    }
+  }
+
+  public void setAll(Properties properties) {
+    Enumeration names = properties.propertyNames();
+    while (names.hasMoreElements()) {
+      String name = (String) names.nextElement();
+      set(name, properties.getProperty(name));
+    }
+  }
+
+  /**
+   * Set metadata name/value. Associate the specified value to the specified
+   * metadata name. If some previous values were associated to this name, they
+   * are removed.
+   * 
+   * @param name
+   *          the metadata name.
+   * @param value
+   *          the metadata value.
+   */
+  public void set(String name, String value) {
+    remove(name);
+    add(name, value);
+  }
+
+  /**
+   * Remove a metadata and all its associated values.
+   */
+  public void remove(String name) {
+    metadata.remove(name);
+  }
+
+  /**
+   * Returns the number of metadata names in this metadata.
+   */
+  public int size() {
+    return metadata.size();
+  }
+
+  public boolean equals(Object o) {
+
+    if (o == null) {
+      return false;
+    }
+
+    PlainMetadata other = null;
+    try {
+      other = (PlainMetadata) o;
+    } catch (ClassCastException cce) {
+      return false;
+    }
+
+    if (other.size() != size()) {
+      return false;
+    }
+
+    String[] names = names();
+    for (int i = 0; i < names.length; i++) {
+      String[] otherValues = other.getValues(names[i]);
+      String[] thisValues = getValues(names[i]);
+      if (otherValues.length != thisValues.length) {
+        return false;
+      }
+      for (int j = 0; j < otherValues.length; j++) {
+        if (!otherValues[j].equals(thisValues[j])) {
+          return false;
+        }
+      }
+    }
+    return true;
+  }
+
+  public String toString() {
+    StringBuffer buf = new StringBuffer();
+    String[] names = names();
+    for (int i = 0; i < names.length; i++) {
+      String[] values = getValues(names[i]);
+      for (int j = 0; j < values.length; j++) {
+        buf.append(names[i]).append("=").append(values[j]).append(" ");
+      }
+    }
+    return buf.toString();
+  }
+
+  public final void write(DataOutput out) throws IOException {
+    String[] values = null;
+    String[] names = names();
+    WritableUtils.writeStringArray(out, names);
+    for (int i = 0; i < names.length; i++) {
+      values = getValues(names[i]);
+      WritableUtils.writeStringArray(out, values);
+    }
+  }
+
+  public final void readFields(DataInput in) throws IOException {
+    String keys[] = WritableUtils.readStringArray(in);
+    for (int i = 0; i < keys.length; i++) {
+      String values[] = WritableUtils.readStringArray(in);
+      for (int j = 0; j < values.length; j++) {
+        add(keys[i], values[j]);
+      }
+    }
+  }
+}
Index: src/java/org/apache/nutch/metadata/MetadataSpellChecker.java
===================================================================
--- src/java/org/apache/nutch/metadata/MetadataSpellChecker.java	(revision 0)
+++ src/java/org/apache/nutch/metadata/MetadataSpellChecker.java	(revision 0)
@@ -0,0 +1,112 @@
+package org.apache.nutch.metadata;
+
+import java.lang.reflect.Field;
+import java.lang.reflect.Modifier;
+import java.util.HashMap;
+import java.util.Map;
+
+import org.apache.commons.lang.StringUtils;
+
+/**
+ * This decorator brings spell checking capabilities to metadata, if
+ * none is required use {Metadata} instead
+ * 
+ * All the static String fields declared by this class are used as reference
+ * names for syntax correction on meta-data naming.
+ */
+public class MetadataSpellChecker extends PlainMetadata implements CreativeCommons,
+    DublinCore, HttpHeaders, Nutch, Office {
+
+  private final static Map NAMES_IDX = new HashMap();
+
+  private static String[] normalized = null;
+
+  // Uses self introspection to fill the metanames index and the
+  // metanames list.
+  static {
+    Field[] fields = PlainMetadata.class.getFields();
+    for (int i=0; i<fields.length; i++) {
+      int mods = fields[i].getModifiers();
+      if (Modifier.isFinal(mods) &&
+          Modifier.isPublic(mods) &&
+          Modifier.isStatic(mods) &&
+          fields[i].getType().equals(String.class)) {
+        try {
+          String val = (String) fields[i].get(null);
+          NAMES_IDX.put(normalize(val), val);
+        } catch (Exception e) {
+          // Simply ignore...
+        }
+      }
+    }
+    normalized = (String[]) NAMES_IDX.keySet().toArray(new String[NAMES_IDX.size()]);
+  }
+  
+  private final static String normalize(String str) {
+    char c;
+    StringBuffer buf = new StringBuffer();
+    for (int i=0; i<str.length(); i++) {
+      c = str.charAt(i);
+      if (Character.isLetter(c)) {
+        buf.append(Character.toLowerCase(c));
+      }
+    }
+    return buf.toString();
+  }
+  
+  public void remove(String name) {
+    super.remove(getNormalizedName(name));
+  }
+
+  public String get(String name) {
+    return super.get(getNormalizedName(name));
+  }
+  
+  public void add(String name, String value) {
+    super.add(getNormalizedName(name),value);
+  }
+  
+  public String[] getValues(String name) {
+    return super.getValues(getNormalizedName(name));
+  }
+  
+  /**
+   * Get the normalized name of metadata attribute name.
+   * This method tries to find a well-known metadata name (one of the
+   * metadata names defined in this class) that matches the specified name.
+   * The matching is error tolerent. For instance,
+   * <ul>
+   *  <li>content-type gives Content-Type</li>
+   *  <li>CoNtEntType  gives Content-Type</li>
+   *  <li>ConTnTtYpe   gives Content-Type</li>
+   * </ul>
+   * If no matching with a well-known metadata name is found, then the original
+   * name is returned.
+   */
+  public static String getNormalizedName(String name) {
+    String searched = normalize(name);
+    String value = (String) NAMES_IDX.get(searched);
+
+    if ((value == null) && (normalized != null)) {
+      int threshold = searched.length() / 3;
+      for (int i=0; i<normalized.length && value == null; i++) {
+        if (StringUtils.getLevenshteinDistance(searched, normalized[i]) < threshold) {
+          value = (String) NAMES_IDX.get(normalized[i]);
+        }
+      }
+    }
+    return (value != null) ? value : name;
+  }
+  
+  public String[] names() {
+    String[] names = super.names();
+    
+    for(int i=0;i<names.length;i++){
+      names[i]=getNormalizedName(names[i]);
+    }
+    return names;
+  }
+
+
+
+}
Index: src/java/org/apache/nutch/fetcher/Fetcher.java
===================================================================
--- src/java/org/apache/nutch/fetcher/Fetcher.java	(revision 467333)
+++ src/java/org/apache/nutch/fetcher/Fetcher.java	(working copy)
@@ -17,6 +17,7 @@
 package org.apache.nutch.fetcher;
 
 import java.io.IOException;
+import java.util.Iterator;
 
 // Commons Logging imports
 import org.apache.commons.logging.Log;
@@ -29,7 +30,7 @@
 
 import org.apache.nutch.crawl.CrawlDatum;
 import org.apache.nutch.crawl.SignatureFactory;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.*;
 import org.apache.nutch.protocol.*;
 import org.apache.nutch.parse.*;
@@ -40,6 +41,30 @@
 /** The fetcher. Most of the work is done by plugins. */
 public class Fetcher extends Configured implements MapRunnable { 
 
+  public static class VoidReducer implements Reducer {
+
+    public void reduce(WritableComparable key, Iterator values, OutputCollector collector, Reporter reporter) throws IOException {
+      
+//      LOG.info("reduce: K:" + key);
+      while (values.hasNext()){
+        Writable w=(Writable)values.next();
+//        LOG.info("  val:" + w.getClass().toString());
+        collector.collect(key,w);
+      }
+    }
+
+    public void configure(JobConf arg0) {
+      // TODO Auto-generated method stub
+      
+    }
+
+    public void close() throws IOException {
+      // TODO Auto-generated method stub
+      
+    }
+    
+  }
+  
   public static final Log LOG = LogFactory.getLog(Fetcher.class);
   
   public static final String SIGNATURE_KEY = "nutch.content.digest";
@@ -261,9 +286,9 @@
 
       if (content == null) {
         String url = key.toString();
-        content = new Content(url, url, new byte[0], "", new Metadata(), this.conf);
+        content = new Content(url, url, new byte[0], "", new PlainMetadata(), this.conf);
       }
-      Metadata metadata = content.getMetadata();
+      PlainMetadata metadata = content.getMetadata();
       // add segment to metadata
       metadata.set(SEGMENT_NAME_KEY, segmentName);
       // add score to content metadata so that ParseSegment can pick it up.
@@ -332,17 +357,19 @@
 
   public Fetcher(Configuration conf) { super(conf); }
 
-  private synchronized void updateStatus(int bytesInPage) throws IOException {
+  private void updateStatus(int bytesInPage) throws IOException {
     pages++;
     bytes += bytesInPage;
   }
 
   private void reportStatus() throws IOException {
     String status;
+    long elapsed = (System.currentTimeMillis() - start)/1000;
+    
+    
     synchronized (this) {
-      long elapsed = (System.currentTimeMillis() - start)/1000;
       status = 
-        pages+" pages, "+errors+" errors, "
+        pages + " pages, " + errors + " errors, "
         + Math.round(((float)pages*10)/elapsed)/10.0+" pages/s, "
         + Math.round(((((float)bytes)*8)/1024)/elapsed)+" kb/s, ";
     }
@@ -439,6 +466,7 @@
     job.setOutputFormat(FetcherOutputFormat.class);
     job.setOutputKeyClass(UTF8.class);
     job.setOutputValueClass(FetcherOutput.class);
+    job.setReducerClass(VoidReducer.class);
 
     JobClient.runJob(job);
     if (LOG.isInfoEnabled()) { LOG.info("Fetcher: done"); }
Index: src/java/org/apache/nutch/fetcher/FetcherOutput.java
===================================================================
--- src/java/org/apache/nutch/fetcher/FetcherOutput.java	(revision 467333)
+++ src/java/org/apache/nutch/fetcher/FetcherOutput.java	(working copy)
@@ -18,6 +18,8 @@
 
 import java.io.*;
 
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.io.*;
 import org.apache.nutch.crawl.CrawlDatum;
 import org.apache.nutch.protocol.Content;
@@ -27,6 +29,11 @@
 
 /* An entry in the fetcher's output. */
 public final class FetcherOutput implements Writable, Configurable {
+  
+  private static Log LOG = LogFactory.getLog(FetcherOutput.class);
+  
+  private static final byte MASK_CONTENT = 1;
+  private static final byte MASK_PARSE = 2;
   private CrawlDatum crawlDatum;
   private Content content;
   private ParseImpl parse;
@@ -36,26 +43,38 @@
 
   public FetcherOutput(CrawlDatum crawlDatum, Content content,
                        ParseImpl parse) {
+
+    this.content=content;
+    this.parse=parse;
     this.crawlDatum = crawlDatum;
-    this.content = content;
-    this.parse = parse;
+    
   }
-
+  
   public final void readFields(DataInput in) throws IOException {
     this.crawlDatum = CrawlDatum.read(in);
-    this.content = in.readBoolean() ? Content.read(in) : null;
-    this.parse = in.readBoolean() ? ParseImpl.read(in, this.conf) : null;
+    int composition=in.readByte();
+    
+    boolean hasContent=(composition | MASK_CONTENT)!=0;
+    boolean hasParse=(composition | MASK_PARSE)!=0;
+
+    if (hasContent) {
+      content=Content.read(in);
+    }
+    if(hasParse){
+      parse=ParseImpl.read(in, conf);
+    }
   }
 
   public final void write(DataOutput out) throws IOException {
     crawlDatum.write(out);
 
-    out.writeBoolean(content != null);
+    int composition=((content!=null)?MASK_CONTENT:(byte)0) + ((content!=null)?MASK_PARSE:(byte)0);  
+
+    out.writeByte((byte)composition);
     if (content != null) {
       content.write(out);
     }
 
-    out.writeBoolean(parse != null);
     if (parse != null) {
       parse.write(out);
     }
Index: src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java
===================================================================
--- src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java	(revision 467333)
+++ src/java/org/apache/nutch/fetcher/FetcherOutputFormat.java	(working copy)
@@ -98,9 +98,7 @@
             parseOut.close(reporter);
           }
         }
-
       };
-
   }      
 }
 
Index: src/java/org/apache/nutch/servlet/Cached.java
===================================================================
--- src/java/org/apache/nutch/servlet/Cached.java	(revision 467333)
+++ src/java/org/apache/nutch/servlet/Cached.java	(working copy)
@@ -16,7 +16,7 @@
 
 package org.apache.nutch.servlet;
 
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.protocols.Response;
 import org.apache.nutch.searcher.NutchBean;
 import org.apache.nutch.searcher.Hit;
@@ -82,7 +82,7 @@
     byte[] bytes = bean.getContent(details);
 
     // pass all original headers? only these for now.
-    Metadata metadata = bean.getParseData(details).getContentMeta();
+    PlainMetadata metadata = bean.getParseData(details).getContentMeta();
     String contentType = metadata.get(Response.CONTENT_TYPE);
     //String lastModified = metadata.get(Metadata.LAST_MODIFIED);
     //String contentLength = metadata.get(Metadata.CONTENT_LENGTH);
Index: src/java/org/apache/nutch/net/protocols/Response.java
===================================================================
--- src/java/org/apache/nutch/net/protocols/Response.java	(revision 467333)
+++ src/java/org/apache/nutch/net/protocols/Response.java	(working copy)
@@ -20,7 +20,7 @@
 
 // Nutch imports
 import org.apache.nutch.metadata.HttpHeaders;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 
 
 /**
@@ -38,7 +38,7 @@
   public String getHeader(String name);
 
   /** Returns all the headers. */
-  public Metadata getHeaders();
+  public PlainMetadata getHeaders();
   
   /** Returns the full content of the response. */
   public byte[] getContent();
Index: src/java/org/apache/nutch/indexer/Indexer.java
===================================================================
--- src/java/org/apache/nutch/indexer/Indexer.java	(revision 467333)
+++ src/java/org/apache/nutch/indexer/Indexer.java	(working copy)
@@ -43,7 +43,7 @@
 
 import org.apache.lucene.index.*;
 import org.apache.lucene.document.*;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 
 /** Create indexes for segments. */
 public class Indexer extends Configured implements Reducer {
@@ -210,7 +210,7 @@
     }
 
     Document doc = new Document();
-    Metadata metadata = parseData.getContentMeta();
+    PlainMetadata metadata = parseData.getContentMeta();
 
     // add segment, used to map from merged index back to segment files
     doc.add(new Field("segment", metadata.get(Fetcher.SEGMENT_NAME_KEY),
Index: src/java/org/apache/nutch/protocol/Content.java
===================================================================
--- src/java/org/apache/nutch/protocol/Content.java	(revision 468658)
+++ src/java/org/apache/nutch/protocol/Content.java	(working copy)
@@ -23,6 +23,7 @@
 import org.apache.hadoop.fs.*;
 import org.apache.hadoop.conf.*;
 import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.util.mime.MimeType;
 import org.apache.nutch.util.mime.MimeTypes;
 import org.apache.nutch.util.mime.MimeTypeException;
@@ -32,30 +33,68 @@
 
   public static final String DIR_NAME = "content";
 
-  private final static byte VERSION = 1;
+  private final static byte VERSION = 2;
 
   private byte version;
+
   private String url;
+
   private String base;
+
   private byte[] content;
+
   private String contentType;
-  private Metadata metadata;
+
+  private PlainMetadata metadata;
+
   private boolean mimeTypeMagic;
+
   private MimeTypes mimeTypes;
 
-  public Content() {}
-    
+  public Content() {
+  }
+
+  /**
+   * @deprecated use
+   *             {@link #Content(String, String, byte[], String, PlainMetadata, Configuration)}
+   *             instead
+   */
   public Content(String url, String base, byte[] content, String contentType,
-                 Metadata metadata, Configuration conf) {
+      Metadata metadata, Configuration conf) {
 
-    if (url == null) throw new IllegalArgumentException("null url");
-    if (base == null) throw new IllegalArgumentException("null base");
-    if (content == null) throw new IllegalArgumentException("null content");
-    if (metadata == null) throw new IllegalArgumentException("null metadata");
+    if (url == null)
+      throw new IllegalArgumentException("null url");
+    if (base == null)
+      throw new IllegalArgumentException("null base");
+    if (content == null)
+      throw new IllegalArgumentException("null content");
+    if (metadata == null)
+      throw new IllegalArgumentException("null metadata");
 
     this.url = url;
     this.base = base;
     this.content = content;
+    this.metadata = Metadata.convert(metadata);
+    this.mimeTypeMagic = conf.getBoolean("mime.type.magic", true);
+    this.mimeTypes = MimeTypes.get(conf.get("mime.types.file"));
+    this.contentType = getContentType(contentType, url, content);
+  }
+
+  public Content(String url, String base, byte[] content, String contentType,
+      PlainMetadata metadata, Configuration conf) {
+
+    if (url == null)
+      throw new IllegalArgumentException("null url");
+    if (base == null)
+      throw new IllegalArgumentException("null base");
+    if (content == null)
+      throw new IllegalArgumentException("null content");
+    if (metadata == null)
+      throw new IllegalArgumentException("null metadata");
+
+    this.url = url;
+    this.base = base;
+    this.content = content;
     this.metadata = metadata;
     this.mimeTypeMagic = conf.getBoolean("mime.type.magic", true);
     this.mimeTypes = MimeTypes.get(conf.get("mime.types.file"));
@@ -67,30 +106,49 @@
     if (version > VERSION)
       throw new VersionMismatchException(VERSION, version);
 
-    url = UTF8.readString(in);                    // read url
-    base = UTF8.readString(in);                   // read base
+    if (version == 2) {
+      //handle version 2 format
+      String sData[]=WritableUtils.readStringArray(in);
+      url = sData[0]; 
+      base = sData[1];
+      contentType = sData[2];
 
-    content = new byte[in.readInt()];             // read content
-    in.readFully(content);
+      metadata = new PlainMetadata();
+      metadata.readFields(in);
 
-    contentType = UTF8.readString(in);            // read contentType
+      content = new byte[in.readInt()]; // read content
+      in.readFully(content);
+    } else if (version == 1) {
+      //handle verion 1 format
 
-    metadata = new Metadata();
-    metadata.readFields(in);                    // read meta data
+      url = UTF8.readString(in); // read url
+      base = UTF8.readString(in); // read base
+
+      content = new byte[in.readInt()]; // read content
+      in.readFully(content);
+
+      contentType = UTF8.readString(in); // read contentType
+
+      Metadata metadata = new Metadata();
+      metadata.readFields(in); // read meta data
+      this.metadata = Metadata.convert(metadata);
+    }
   }
 
   protected final void writeCompressed(DataOutput out) throws IOException {
     out.writeByte(version);
 
-    UTF8.writeString(out, url);                   // write url
-    UTF8.writeString(out, base);                  // write base
-
-    out.writeInt(content.length);                 // write content
+    //collect all strings to array
+    String sData[]=new String[]{
+      url,base,contentType  
+    };
+    
+    WritableUtils.writeStringArray(out,sData); //write Strings
+    
+    metadata.write(out); // write metadata
+    
+    out.writeInt(content.length); // write content
     out.write(content);
-
-    UTF8.writeString(out, contentType);           // write contentType
-    
-    metadata.write(out);                           // write metadata
   }
 
   public static Content read(DataInput in) throws IOException {
@@ -99,18 +157,15 @@
     return content;
   }
 
-  //
-  // Accessor methods
-  //
-
   /** The url fetched. */
   public String getUrl() {
     ensureInflated();
     return url;
   }
 
-  /** The base url for relative links contained in the content.
-   * Maybe be different from url if the request redirected.
+  /**
+   * The base url for relative links contained in the content. Maybe be
+   * different from url if the request redirected.
    */
   public String getBaseUrl() {
     ensureInflated();
@@ -122,12 +177,15 @@
     ensureInflated();
     return content;
   }
+
   public void setContent(byte[] content) {
     ensureInflated();
     this.content = content;
   }
 
-  /** The media type of the retrieved content.
+  /**
+   * The media type of the retrieved content.
+   * 
    * @see <a href="http://www.iana.org/assignments/media-types/">
    *      http://www.iana.org/assignments/media-types/</a>
    */
@@ -135,48 +193,47 @@
     ensureInflated();
     return contentType;
   }
+
   public void setContentType(String contentType) {
     ensureInflated();
     this.contentType = contentType;
   }
 
   /** Other protocol-specific data. */
-  public Metadata getMetadata() {
+  public PlainMetadata getMetadata() {
     ensureInflated();
     return metadata;
   }
 
   /** Other protocol-specific data. */
-  public void setMetadata(Metadata metadata) {
+  public void setMetadata(PlainMetadata metadata) {
     ensureInflated();
     this.metadata = metadata;
   }
 
   public boolean equals(Object o) {
     ensureInflated();
-    if (!(o instanceof Content)){
+    if (!(o instanceof Content)) {
       return false;
     }
-    Content that = (Content)o;
+    Content that = (Content) o;
     that.ensureInflated();
-    return
-      this.url.equals(that.url) &&
-      this.base.equals(that.base) &&
-      Arrays.equals(this.getContent(), that.getContent()) &&
-      this.contentType.equals(that.contentType) &&
-      this.metadata.equals(that.metadata);
+    return this.url.equals(that.url) && this.base.equals(that.base)
+        && Arrays.equals(this.getContent(), that.getContent())
+        && this.contentType.equals(that.contentType)
+        && this.metadata.equals(that.metadata);
   }
 
   public String toString() {
     ensureInflated();
     StringBuffer buffer = new StringBuffer();
 
-    buffer.append("url: " + url + "\n" );
-    buffer.append("base: " + base + "\n" );
-    buffer.append("contentType: " + contentType + "\n" );
-    buffer.append("metadata: " + metadata + "\n" );
+    buffer.append("url: " + url + "\n");
+    buffer.append("base: " + base + "\n");
+    buffer.append("contentType: " + contentType + "\n");
+    buffer.append("metadata: " + metadata + "\n");
     buffer.append("Content:\n");
-    buffer.append(new String(content));           // try default encoding
+    buffer.append(new String(content)); // try default encoding
 
     return buffer.toString();
 
@@ -185,7 +242,7 @@
   public static void main(String argv[]) throws Exception {
 
     String usage = "Content (-local | -dfs <namenode:port>) recno segment";
-    
+
     if (argv.length < 3) {
       System.out.println("usage:" + usage);
       return;
@@ -199,7 +256,8 @@
       Path file = new Path(segment, DIR_NAME);
       System.out.println("Reading from file: " + file);
 
-      ArrayFile.Reader contents = new ArrayFile.Reader(fs, file.toString(), conf);
+      ArrayFile.Reader contents = new ArrayFile.Reader(fs, file.toString(),
+          conf);
 
       Content content = new Content();
       contents.get(recno, content);
@@ -216,10 +274,10 @@
   private String getContentType(String typeName, String url, byte[] data) {
     MimeType type = null;
     try {
-        typeName = MimeType.clean(typeName);
-        type = typeName == null ? null : this.mimeTypes.forName(typeName);
+      typeName = MimeType.clean(typeName);
+      type = typeName == null ? null : this.mimeTypes.forName(typeName);
     } catch (MimeTypeException mte) {
-        // Seems to be a malformed mime type name...
+      // Seems to be a malformed mime type name...
     }
 
     if (typeName == null || type == null || !type.matches(url)) {
@@ -229,8 +287,8 @@
       type = this.mimeTypes.getMimeType(url);
       typeName = type == null ? typeName : type.getName();
     }
-    if (typeName == null || type == null ||
-        (this.mimeTypeMagic && type.hasMagic() && !type.matches(data))) {
+    if (typeName == null || type == null
+        || (this.mimeTypeMagic && type.hasMagic() && !type.matches(data))) {
       // If no mime-type already found, or the one found doesn't match
       // the magic bytes it should be, then, guess a mime-type from the
       // document content (magic bytes)
Index: src/java/org/apache/nutch/segment/SegmentMerger.java
===================================================================
--- src/java/org/apache/nutch/segment/SegmentMerger.java	(revision 467333)
+++ src/java/org/apache/nutch/segment/SegmentMerger.java	(working copy)
@@ -32,7 +32,7 @@
 import org.apache.nutch.crawl.CrawlDatum;
 import org.apache.nutch.crawl.Generator;
 import org.apache.nutch.fetcher.Fetcher;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.URLFilters;
 import org.apache.nutch.parse.ParseData;
 import org.apache.nutch.parse.ParseText;
@@ -144,12 +144,12 @@
             ((CrawlDatum)o).getMetaData().put(SEGMENT_NAME_KEY, new UTF8(segment));
           } else if (o instanceof Content) {
             if (((Content)o).getMetadata() == null) {
-              ((Content)o).setMetadata(new Metadata());
+              ((Content)o).setMetadata(new PlainMetadata());
             }
             ((Content)o).getMetadata().set(SEGMENT_NAME_KEY.toString(), segment);
           } else if (o instanceof ParseData) {
             if (((ParseData)o).getParseMeta() == null) {
-              ((ParseData)o).setParseMeta(new Metadata());
+              ((ParseData)o).setParseMeta(new PlainMetadata());
             }
             ((ParseData)o).getParseMeta().set(SEGMENT_NAME_KEY.toString(), segment);
           } else if (o instanceof ParseText) {
Index: src/java/org/apache/nutch/crawl/CrawlDbMerger.java
===================================================================
--- src/java/org/apache/nutch/crawl/CrawlDbMerger.java	(revision 467333)
+++ src/java/org/apache/nutch/crawl/CrawlDbMerger.java	(working copy)
@@ -28,6 +28,7 @@
 import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.io.UTF8;
+import org.apache.hadoop.io.Writable;
 import org.apache.hadoop.io.WritableComparable;
 import org.apache.hadoop.mapred.*;
 import org.apache.nutch.net.URLFilters;
@@ -51,30 +52,104 @@
  */
 public class CrawlDbMerger extends Configured {
   private static final Log LOG = LogFactory.getLog(CrawlDbMerger.class);
+  
+  
+  public static class TimeoutWatchDog implements Runnable{
 
-  public static class Merger extends MapReduceBase implements Reducer {
+    Thread toNotify=null; 
+    int timeout;
+    long lastPing=0;
+    
+    public TimeoutWatchDog(int timeoutInSeconds){
+      this.timeout=timeoutInSeconds;
+    }
+
+    public void on(){
+      if(toNotify==null){
+        toNotify=Thread.currentThread();
+      }
+      lastPing=System.currentTimeMillis();
+    }
+
+    public void off(){
+      toNotify=null;
+    }
+    
+    public void run(){
+      try{
+        Thread.sleep(1000);
+      } catch (InterruptedException e){
+        if(toNotify!=null && System.currentTimeMillis()-lastPing>1000*timeout){
+          LOG.info("seems like thread is in trouble!");
+          if(toNotify!=null){
+            toNotify.interrupt();
+          }
+        }
+      }
+    }
+  }
+  
+
+  public static class MyMapper extends org.apache.hadoop.mapred.lib.IdentityMapper {
+
     private URLFilters filters = null;
-    MapWritable meta = new MapWritable();
+    int index=0;
+    private Thread watchDogThread;
+    private TimeoutWatchDog watchDog;
 
-    public void close() throws IOException {}
-
-    public void configure(JobConf conf) {
-      if (conf.getBoolean("crawldb.merger.urlfilters", false))
+   public void configure(JobConf conf) {
+     watchDog=new TimeoutWatchDog(10);
+     watchDogThread=new Thread(watchDog);
+     watchDogThread.start();
+     
+     super.configure(conf);
+      if (conf.getBoolean("crawldb.merger.urlfilters", false)) {
+        LOG.info("Filtering urls");
         filters = new URLFilters(conf);
+      }
     }
 
-    public void reduce(WritableComparable key, Iterator values, OutputCollector output, Reporter reporter)
-            throws IOException {
+    public void map(WritableComparable key, Writable val, OutputCollector output, Reporter reporter) throws IOException {
+      if(index++%10000==0){
+        if(LOG.isInfoEnabled()){
+          LOG.info("Processing entry #" + index);
+        }
+      }
       if (filters != null) {
         try {
-          if (filters.filter(((UTF8) key).toString()) == null)
+          watchDog.on();
+          if (filters.filter(((UTF8) key).toString()) == null) {
+            if(LOG.isDebugEnabled()) {
+              LOG.debug("Filtering out: " + key.toString());
+            }
             return;
+          }
+          watchDog.off();
         } catch (Exception e) {
+          watchDog.off();
           if (LOG.isDebugEnabled()) {
             LOG.debug("Can't filter " + key + ": " + e);
           }
         }
+        super.map(key, val, output, reporter);
       }
+    }
+  }
+  
+  public static class Merger extends MapReduceBase implements Reducer {
+    MapWritable meta = new MapWritable();
+    int index=0;
+
+    public void close() throws IOException {}
+
+    public void reduce(WritableComparable key, Iterator values, OutputCollector output, Reporter reporter)
+            throws IOException {
+      if(index++%10000==0){
+        if(LOG.isInfoEnabled()){
+          LOG.info("Processing entry #" + index);
+        }
+      }
+      
       CrawlDatum res = null;
       long resTime = 0L;
       meta.clear();
@@ -130,6 +205,7 @@
     job.setInputKeyClass(UTF8.class);
     job.setInputValueClass(CrawlDatum.class);
 
+    job.setMapperClass(MyMapper.class);
     job.setReducerClass(Merger.class);
 
     job.setOutputPath(newCrawlDb);
@@ -165,4 +241,5 @@
     CrawlDbMerger merger = new CrawlDbMerger(conf);
     merger.merge(output, (Path[]) dbs.toArray(new Path[dbs.size()]), filter);
   }
+
 }
Index: src/java/org/apache/nutch/parse/ParseOutputFormat.java
===================================================================
--- src/java/org/apache/nutch/parse/ParseOutputFormat.java	(revision 467333)
+++ src/java/org/apache/nutch/parse/ParseOutputFormat.java	(working copy)
@@ -23,10 +23,12 @@
 import org.apache.hadoop.io.*;
 import org.apache.nutch.crawl.CrawlDatum;
 import org.apache.nutch.fetcher.Fetcher;
+import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.*;
 import org.apache.hadoop.mapred.*;
 import org.apache.nutch.scoring.ScoringFilterException;
 import org.apache.nutch.scoring.ScoringFilters;
+import org.apache.nutch.util.NutchConfiguration;
 import org.apache.nutch.util.StringUtil;
 import org.apache.nutch.net.*;
 
@@ -38,6 +40,9 @@
 
 /* Parse content in a segment. */
 public class ParseOutputFormat implements OutputFormat {
+  
+  static Configuration conf=NutchConfiguration.create();
+
   private static final Log LOG = LogFactory.getLog(ParseOutputFormat.class);
 
   private UrlNormalizer urlNormalizer;
@@ -80,10 +85,12 @@
         public void write(WritableComparable key, Writable value)
           throws IOException {
           
-          Parse parse = (Parse)value;
+          ParseImpl parse=(ParseImpl) value;
+
           String fromUrl = key.toString();
           String fromHost = null; 
-          String toHost = null;          
+          String toHost = null;
+          //LOG.info("to: appending text");
           textOut.append(key, new ParseText(parse.getText()));
           
           ParseData parseData = parse.getData();
@@ -95,6 +102,7 @@
               // append a CrawlDatum with a signature
               CrawlDatum d = new CrawlDatum(CrawlDatum.STATUS_SIGNATURE, 0.0f);
               d.setSignature(signature);
+          //    LOG.info("co: appending signature");
               crawlOut.append(key, d);
             }
           }
@@ -153,9 +161,14 @@
               }
               continue;
             }
+            //LOG.info("co: appending target");
             crawlOut.append(targetUrl, target);
-            if (adjust != null) crawlOut.append(key, adjust);
+            if (adjust != null) {
+              //LOG.info("co: appending adjust");
+              crawlOut.append(key, adjust);
+            }
           }
+          //LOG.info("appending parseData");
           dataOut.append(key, parseData);
         }
         
Index: src/java/org/apache/nutch/parse/ParseData.java
===================================================================
--- src/java/org/apache/nutch/parse/ParseData.java	(revision 467333)
+++ src/java/org/apache/nutch/parse/ParseData.java	(working copy)
@@ -25,76 +25,111 @@
 import org.apache.hadoop.conf.Configurable;
 
 import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.util.NutchConfiguration;
 
-
-/** Data extracted from a page's content.
+/**
+ * Data extracted from a page's content.
+ * 
  * @see Parse#getData()
  */
 public final class ParseData extends VersionedWritable implements Configurable {
   public static final String DIR_NAME = "parse_data";
 
-  private final static byte VERSION = 4;
+  private final static byte VERSION = 5;
+  private int maxOutlinks = Integer.MAX_VALUE;
 
   private String title;
+
   private Outlink[] outlinks;
-  private Metadata contentMeta;
-  private Metadata parseMeta;
+
+  private PlainMetadata contentMeta;
+
+  private PlainMetadata parseMeta;
+
   private ParseStatus status;
+
   private Configuration conf;
-  
-  // TODO mb@media-style.com: should we really implement Configurable or should we add the
-  // parameter Configuration to the default-constructor. NOTE: The test
-  // TestWriteable instantiates ParseData with Class.newInstance() -> the default
-  // constructor is called -> conf is null. The programmer which use this object may not forget to set the conf.
-  public ParseData() {}
 
+  public ParseData() {
+  }
+
+  /**
+   * @deprecated use {@link #ParseData(ParseStatus, String, Outlink[], PlainMetadata)}
+   * instead
+   */
   public ParseData(ParseStatus status, String title, Outlink[] outlinks,
-                   Metadata contentMeta) {
+      Metadata contentMeta) {
     this(status, title, outlinks, contentMeta, new Metadata());
   }
+
+  public ParseData(ParseStatus status, String title, Outlink[] outlinks,
+      PlainMetadata contentMeta) {
+    this(status, title, outlinks, contentMeta, new PlainMetadata());
+  }
+    
+  /**
+   * @deprecated use {@link #ParseData(ParseStatus, String, Outlink[], PlainMetadata, PlainMetadata)}
+   * instead
+   */
+  public ParseData(ParseStatus status, String title, Outlink[] outlinks,
+      Metadata contentMeta, Metadata parseMeta) {
+    this.status = status;
+    this.title = title;
+    this.outlinks = outlinks;
+    //convert metadata
+    this.contentMeta = Metadata.convert(contentMeta);
+    this.parseMeta = Metadata.convert(parseMeta);
+  }
   
   public ParseData(ParseStatus status, String title, Outlink[] outlinks,
-                   Metadata contentMeta, Metadata parseMeta) {
+      PlainMetadata contentMeta, PlainMetadata parseMeta) {
     this.status = status;
     this.title = title;
     this.outlinks = outlinks;
+    //convert metadata
     this.contentMeta = contentMeta;
     this.parseMeta = parseMeta;
   }
 
-  //
-  // Accessor methods
-  //
+  /** The status of parsing the page. */
+  public ParseStatus getStatus() {
+    return status;
+  }
 
-  /** The status of parsing the page. */
-  public ParseStatus getStatus() { return status; }
-  
   /** The title of the page. */
-  public String getTitle() { return title; }
+  public String getTitle() {
+    return title;
+  }
 
   /** The outlinks of the page. */
-  public Outlink[] getOutlinks() { return outlinks; }
+  public Outlink[] getOutlinks() {
+    return outlinks;
+  }
 
   /** The original Metadata retrieved from content */
-  public Metadata getContentMeta() { return contentMeta; }
+  public PlainMetadata getContentMeta() {
+    return contentMeta;
+  }
 
   /**
-   * Other content properties.
-   * This is the place to find format-specific properties.
-   * Different parser implementations for different content types will populate
-   * this differently.
+   * Other content properties. This is the place to find format-specific
+   * properties. Different parser implementations for different content types
+   * will populate this differently.
    */
-  public Metadata getParseMeta() { return parseMeta; }
-  
-  public void setParseMeta(Metadata parseMeta) {
+  public PlainMetadata getParseMeta() {
+    return parseMeta;
+  }
+
+  public void setParseMeta(PlainMetadata parseMeta) {
     this.parseMeta = parseMeta;
   }
-  
+
   /**
-   * Get a metadata single value.
-   * This method first looks for the metadata value in the parse metadata. If no
-   * value is found it the looks for the metadata in the content metadata.
+   * Get a metadata single value. This method first looks for the metadata value
+   * in the parse metadata. If no value is found it the looks for the metadata
+   * in the content metadata.
+   * 
    * @see #getContentMeta()
    * @see #getParseMeta()
    */
@@ -105,62 +140,92 @@
     }
     return value;
   }
-  
-  //
-  // Writable methods
-  //
 
-  public byte getVersion() { return VERSION; }
+  public byte getVersion() {
+    return VERSION;
+  }
 
   public final void readFields(DataInput in) throws IOException {
 
     byte version = in.readByte();
-    if (version > 1)
+
+    if (version == 5) {
+      //handle version 5 here
       status = ParseStatus.read(in);
-    else
-      status = ParseStatus.STATUS_SUCCESS;
-    title = UTF8.readString(in);                   // read title
+      title = UTF8.readString(in); // read title
+      parseMeta=new PlainMetadata();
+      
+      String[] anchors=WritableUtils.readStringArray(in);
+      String[] urls=WritableUtils.readStringArray(in);
+      
+      outlinks=new Outlink[anchors.length];
+      for(int i=0;i<outlinks.length;i++){
+        outlinks[i]=new Outlink(urls[i],anchors[i]);
+      }
 
-    int totalOutlinks = in.readInt();             // read outlinks
-    int maxOutlinksPerPage = this.conf.getInt("db.max.outlinks.per.page", 100);
-    int outlinksToRead = totalOutlinks;
-    if (maxOutlinksPerPage >= 0) {
-      outlinksToRead = Math.min(maxOutlinksPerPage, totalOutlinks);
-    }
-    outlinks = new Outlink[outlinksToRead];
-    for (int i = 0; i < outlinksToRead; i++) {
-      outlinks[i] = Outlink.read(in);
-    }
-    for (int i = outlinksToRead; i < totalOutlinks; i++) {
-      Outlink.skip(in);
-    }
-    
-    if (version < 3) {
-      int propertyCount = in.readInt();             // read metadata
-      contentMeta = new Metadata();
-      for (int i = 0; i < propertyCount; i++) {
-        contentMeta.add(UTF8.readString(in), UTF8.readString(in));
-      }
-    } else {
-      contentMeta = new Metadata();
+      contentMeta = new PlainMetadata();
       contentMeta.readFields(in);
-    }
-    if (version > 3) {
-      parseMeta = new Metadata();
+      parseMeta = new PlainMetadata();
       parseMeta.readFields(in);
+    } else {
+      //handle other versions here
+      if (version > 1)
+        status = ParseStatus.read(in);
+      else
+        status = ParseStatus.STATUS_SUCCESS;
+      title = UTF8.readString(in); // read title
+
+      int totalOutlinks = in.readInt(); // read outlinks
+      int maxOutlinksPerPage = this.conf
+          .getInt("db.max.outlinks.per.page", 100);
+      int outlinksToRead = totalOutlinks;
+      if (maxOutlinksPerPage >= 0) {
+        outlinksToRead = Math.min(maxOutlinksPerPage, totalOutlinks);
+      }
+      outlinks = new Outlink[outlinksToRead];
+      for (int i = 0; i < outlinksToRead; i++) {
+        outlinks[i] = Outlink.read(in);
+      }
+      for (int i = outlinksToRead; i < totalOutlinks; i++) {
+        Outlink.skip(in);
+      }
+
+      if (version < 3) {
+        int propertyCount = in.readInt(); // read metadata
+        contentMeta = new PlainMetadata();
+        for (int i = 0; i < propertyCount; i++) {
+          contentMeta.add(UTF8.readString(in), UTF8.readString(in));
+        }
+      } else {
+        contentMeta = new PlainMetadata();
+        contentMeta.readFields(in);
+      }
+      if (version > 3) {
+        parseMeta = new PlainMetadata();
+        parseMeta.readFields(in);
+      }
     }
   }
 
   public final void write(DataOutput out) throws IOException {
-    out.writeByte(VERSION);                       // write version
-    status.write(out);                            // write status
-    UTF8.writeString(out, title);                 // write title
+    out.writeByte(VERSION); // write version
+    status.write(out); // write status
+    UTF8.writeString(out, title); // write title
 
-    out.writeInt(outlinks.length);                // write outlinks
-    for (int i = 0; i < outlinks.length; i++) {
-      outlinks[i].write(out);
+    String[] anchors=new String[outlinks.length];
+    String[] urls=new String[outlinks.length];
+    
+    for(int i=0;i<outlinks.length && i < maxOutlinks;i++){
+      anchors[i]=outlinks[i].getAnchor();
+      urls[i]=outlinks[i].getToUrl();
     }
-    contentMeta.write(out);                      // write content metadata
+    
+    // write outlinks
+    WritableUtils.writeStringArray(out,anchors);
+    WritableUtils.writeStringArray(out,urls);
+    
+    //write metadata
+    contentMeta.write(out);
     parseMeta.write(out);
   }
 
@@ -170,44 +235,38 @@
     return parseText;
   }
 
-  //
-  // other methods
-  //
-
   public boolean equals(Object o) {
     if (!(o instanceof ParseData))
       return false;
-    ParseData other = (ParseData)o;
-    return
-      this.status.equals(other.status) &&
-      this.title.equals(other.title) &&
-      Arrays.equals(this.outlinks, other.outlinks) &&
-      this.contentMeta.equals(other.contentMeta) &&
-      this.parseMeta.equals(other.parseMeta);
+    ParseData other = (ParseData) o;
+    return this.status.equals(other.status) && this.title.equals(other.title)
+        && Arrays.equals(this.outlinks, other.outlinks)
+        && this.contentMeta.equals(other.contentMeta)
+        && this.parseMeta.equals(other.parseMeta);
   }
 
   public String toString() {
     StringBuffer buffer = new StringBuffer();
 
-    buffer.append("Status: " + status + "\n" );
-    buffer.append("Title: " + title + "\n" );
+    buffer.append("Status: " + status + "\n");
+    buffer.append("Title: " + title + "\n");
 
     if (outlinks != null) {
-      buffer.append("Outlinks: " + outlinks.length + "\n" );
+      buffer.append("Outlinks: " + outlinks.length + "\n");
       for (int i = 0; i < outlinks.length; i++) {
         buffer.append("  outlink: " + outlinks[i] + "\n");
       }
     }
 
-    buffer.append("Content Metadata: " + contentMeta + "\n" );
-    buffer.append("Parse Metadata: " + parseMeta + "\n" );
+    buffer.append("Content Metadata: " + contentMeta + "\n");
+    buffer.append("Parse Metadata: " + parseMeta + "\n");
 
     return buffer.toString();
   }
 
   public static void main(String argv[]) throws Exception {
     String usage = "ParseData (-local | -dfs <namenode:port>) recno segment";
-    
+
     if (argv.length < 3) {
       System.out.println("usage:" + usage);
       return;
@@ -238,6 +297,7 @@
 
   public void setConf(Configuration conf) {
     this.conf = conf;
+    maxOutlinks=conf.getInt("db.max.outlinks.per.page", 100);
   }
 
   public Configuration getConf() {
Index: src/java/org/apache/nutch/parse/ParseStatus.java
===================================================================
--- src/java/org/apache/nutch/parse/ParseStatus.java	(revision 467333)
+++ src/java/org/apache/nutch/parse/ParseStatus.java	(working copy)
@@ -13,7 +13,7 @@
 import org.apache.hadoop.io.WritableUtils;
 import org.apache.hadoop.conf.Configuration;
 
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 
 
 /**
@@ -234,7 +234,7 @@
     
     public EmptyParseImpl(ParseStatus status, Configuration conf) {
       data = new ParseData(status, "", new Outlink[0],
-                           new Metadata(), new Metadata());
+                           new PlainMetadata(), new PlainMetadata());
       data.setConf(conf);
     }
     
Index: src/java/org/apache/nutch/parse/Outlink.java
===================================================================
--- src/java/org/apache/nutch/parse/Outlink.java	(revision 467333)
+++ src/java/org/apache/nutch/parse/Outlink.java	(working copy)
@@ -35,6 +35,11 @@
     this.toUrl = new UrlNormalizerFactory(conf).getNormalizer().normalize(toUrl);
     this.anchor = anchor;
   }
+  
+  public Outlink(String toUrl, String anchor){
+    this.toUrl = toUrl;
+    this.anchor = anchor;
+  }
 
   public void readFields(DataInput in) throws IOException {
     toUrl = UTF8.readString(in);
Index: src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java
===================================================================
--- src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java	(revision 467333)
+++ src/plugin/microformats-reltag/src/java/org/apache/nutch/microformats/reltag/RelTagParser.java	(working copy)
@@ -31,7 +31,7 @@
 import org.apache.commons.logging.LogFactory;
 
 // Nutch imports
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.parse.HTMLMetaTags;
 import org.apache.nutch.parse.Parse;
 import org.apache.nutch.parse.HtmlParseFilter;
@@ -68,7 +68,7 @@
     Parser parser = new Parser(doc);
     Set tags = parser.getRelTags();
     Iterator iter = tags.iterator();
-    Metadata metadata = parse.getData().getParseMeta();
+    PlainMetadata metadata = parse.getData().getParseMeta();
     while (iter.hasNext()) {
       metadata.add(REL_TAG, (String) iter.next());
     }
Index: src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java
===================================================================
--- src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java	(revision 467333)
+++ src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java	(working copy)
@@ -31,6 +31,8 @@
 
 import org.apache.nutch.protocol.Content;
 import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.MetadataSpellChecker;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.protocols.Response;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.nutch.parse.ParseStatus;
@@ -72,7 +74,7 @@
 
     String text = null;
     String title = null;
-    Metadata metadata = new Metadata();
+    PlainMetadata metadata = new PlainMetadata();
 
     try {
 
@@ -105,12 +107,12 @@
       PDDocumentInformation info = pdf.getDocumentInformation();
       title = info.getTitle();
       // more useful info, currently not used. please keep them for future use.
-      metadata.add(Metadata.PAGE_COUNT, String.valueOf(pdf.getPageCount()));
-      metadata.add(Metadata.AUTHOR, info.getAuthor());
-      metadata.add(Metadata.SUBJECT, info.getSubject());
-      metadata.add(Metadata.KEYWORDS, info.getKeywords());
-      metadata.add(Metadata.CREATOR, info.getCreator());
-      metadata.add(Metadata.PUBLISHER, info.getProducer());
+      metadata.add(MetadataSpellChecker.PAGE_COUNT, String.valueOf(pdf.getPageCount()));
+      metadata.add(MetadataSpellChecker.AUTHOR, info.getAuthor());
+      metadata.add(MetadataSpellChecker.SUBJECT, info.getSubject());
+      metadata.add(MetadataSpellChecker.KEYWORDS, info.getKeywords());
+      metadata.add(MetadataSpellChecker.CREATOR, info.getCreator());
+      metadata.add(MetadataSpellChecker.PUBLISHER, info.getProducer());
       
       //TODO: Figure out why we get a java.io.IOException: Error converting date:1-Jan-3 18:15PM
       //error here
Index: src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCIndexingFilter.java
===================================================================
--- src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCIndexingFilter.java	(revision 467333)
+++ src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCIndexingFilter.java	(working copy)
@@ -29,7 +29,7 @@
 import org.apache.nutch.crawl.CrawlDatum;
 import org.apache.nutch.crawl.Inlinks;
 import org.apache.nutch.metadata.Metadata;
-import org.apache.nutch.metadata.CreativeCommons;
+import org.apache.nutch.metadata.PlainMetadata;
 
 import org.apache.hadoop.conf.Configuration;
 
@@ -52,7 +52,7 @@
   public Document filter(Document doc, Parse parse, UTF8 url, CrawlDatum datum, Inlinks inlinks)
     throws IndexingException {
     
-    Metadata metadata = parse.getData().getParseMeta();
+    PlainMetadata metadata = parse.getData().getParseMeta();
     // index the license
     String licenseUrl = metadata.get(CreativeCommons.LICENSE_URL);
     if (licenseUrl != null) {
Index: src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java
===================================================================
--- src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java	(revision 467333)
+++ src/plugin/creativecommons/src/java/org/creativecommons/nutch/CCParseFilter.java	(working copy)
@@ -17,9 +17,9 @@
 package org.creativecommons.nutch;
 
 import org.apache.nutch.metadata.CreativeCommons;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.parse.*;
 import org.apache.nutch.protocol.Content;
-import org.apache.nutch.metadata.Metadata;
 import org.apache.hadoop.conf.Configuration;
 
 import org.apache.commons.logging.Log;
@@ -51,7 +51,7 @@
     }
 
     /** Scan the document adding attributes to metadata.*/
-    public static void walk(Node doc, URL base, Metadata metadata, Configuration conf)
+    public static void walk(Node doc, URL base, PlainMetadata metadata, Configuration conf)
       throws ParseException {
 
       // walk the DOM tree, scanning for license data
Index: src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java
===================================================================
--- src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java	(revision 467333)
+++ src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java	(working copy)
@@ -31,7 +31,8 @@
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
 
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.MetadataSpellChecker;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.protocols.Response;
 import org.apache.nutch.protocol.Content;
 import org.apache.hadoop.conf.*;
@@ -113,7 +114,7 @@
     String text = "";
     String title = "";
     Outlink[] outlinks = new Outlink[0];
-    Metadata metadata = new Metadata();
+    PlainMetadata metadata = new PlainMetadata();
 
     // parse the content
     DocumentFragment root;
@@ -123,9 +124,9 @@
       String contentType = content.getMetadata().get(Response.CONTENT_TYPE);
       String encoding = StringUtil.parseCharacterEncoding(contentType);
       if ((encoding != null) && !("".equals(encoding))) {
-        metadata.set(Metadata.ORIGINAL_CHAR_ENCODING, encoding);
+        metadata.set(MetadataSpellChecker.ORIGINAL_CHAR_ENCODING, encoding);
         if ((encoding = StringUtil.resolveEncodingAlias(encoding)) != null) {
-          metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, encoding);
+          metadata.set(MetadataSpellChecker.CHAR_ENCODING_FOR_CONVERSION, encoding);
           if (LOG.isTraceEnabled()) {
             LOG.trace(base + ": setting encoding to " + encoding);
           }
@@ -136,9 +137,9 @@
       if ((encoding == null) || ("".equals(encoding))) {
         encoding = sniffCharacterEncoding(contentInOctets);
         if (encoding!=null) {
-          metadata.set(Metadata.ORIGINAL_CHAR_ENCODING, encoding);
+          metadata.set(MetadataSpellChecker.ORIGINAL_CHAR_ENCODING, encoding);
           if ((encoding = StringUtil.resolveEncodingAlias(encoding)) != null) {
-            metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, encoding);
+            metadata.set(MetadataSpellChecker.CHAR_ENCODING_FOR_CONVERSION, encoding);
             if (LOG.isTraceEnabled()) {
               LOG.trace(base + ": setting encoding to " + encoding);
             }
@@ -154,7 +155,7 @@
         // doesn't work for jp because euc-jp and shift_jis have about the
         // same share)
         encoding = defaultCharEncoding;
-        metadata.set(Metadata.CHAR_ENCODING_FOR_CONVERSION, defaultCharEncoding);
+        metadata.set(MetadataSpellChecker.CHAR_ENCODING_FOR_CONVERSION, defaultCharEncoding);
         if (LOG.isTraceEnabled()) {
           LOG.trace(base + ": falling back to " + defaultCharEncoding);
         }
@@ -287,11 +288,9 @@
     HtmlParser parser = new HtmlParser();
     parser.setConf(conf);
     Parse parse = parser.getParse(
-            new Content(url, url, bytes, "text/html", new Metadata(), conf));
+            new Content(url, url, bytes, "text/html", new PlainMetadata(), conf));
     System.out.println("data: "+parse.getData());
-
     System.out.println("text: "+parse.getText());
-    
   }
 
   public void setConf(Configuration conf) {
Index: src/plugin/protocol-httpclient/src/java/org/apache/nutch/protocol/httpclient/HttpResponse.java
===================================================================
--- src/plugin/protocol-httpclient/src/java/org/apache/nutch/protocol/httpclient/HttpResponse.java	(revision 467333)
+++ src/plugin/protocol-httpclient/src/java/org/apache/nutch/protocol/httpclient/HttpResponse.java	(working copy)
@@ -20,7 +20,6 @@
 import java.io.IOException;
 import java.io.InputStream;
 import java.net.URL;
-import java.util.Date;
 
 // Commons Logging imports
 import org.apache.commons.logging.Log;
@@ -35,7 +34,7 @@
 
 // Nutch imports
 import org.apache.nutch.crawl.CrawlDatum;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.protocols.Response;
 import org.apache.nutch.protocol.http.api.HttpBase;
 import org.apache.nutch.util.LogUtil;
@@ -52,7 +51,6 @@
   
   private String orig;
 
-  private String base;
 
   private byte[] content;
 
@@ -60,7 +58,7 @@
 
   private int code;
 
-  private Metadata headers = new Metadata();
+  private PlainMetadata headers = new PlainMetadata();
 
   
   public HttpResponse(HttpBase http, URL url, CrawlDatum datum) throws IOException {
@@ -71,7 +69,6 @@
   HttpResponse(HttpBase http, URL url, CrawlDatum datum, boolean followRedirects) throws IOException {
     this.http = http;
     this.url = url;
-    this.base = url.toString();
     this.orig = url.toString();
     GetMethod get = new GetMethod(this.orig);
     get.setFollowRedirects(followRedirects);
@@ -153,7 +150,7 @@
     return headers.get(name);
   }
   
-  public Metadata getHeaders() {
+  public PlainMetadata getHeaders() {
     return headers;
   }
 
Index: src/plugin/lib-parsems/src/java/org/apache/nutch/parse/ms/MSBaseParser.java
===================================================================
--- src/plugin/lib-parsems/src/java/org/apache/nutch/parse/ms/MSBaseParser.java	(revision 467333)
+++ src/plugin/lib-parsems/src/java/org/apache/nutch/parse/ms/MSBaseParser.java	(working copy)
@@ -30,7 +30,8 @@
 
 // Nutch imports
 import org.apache.nutch.metadata.DublinCore;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.MetadataSpellChecker;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.protocols.Response;
 import org.apache.nutch.parse.Outlink;
 import org.apache.nutch.parse.OutlinkExtractor;
@@ -69,7 +70,7 @@
     
     try {
       byte[] raw = content.getContent();
-      String contentLength = content.getMetadata().get(Metadata.CONTENT_LENGTH);
+      String contentLength = content.getMetadata().get(MetadataSpellChecker.CONTENT_LENGTH);
       if ((contentLength != null) &&
           (raw.length != Integer.parseInt(contentLength))) {
         return new ParseStatus(ParseStatus.FAILED,
@@ -90,7 +91,7 @@
     }
     
     // collect meta data
-    Metadata metadata = new Metadata();
+    PlainMetadata metadata = new PlainMetadata();
     if (properties != null) {
       title = properties.getProperty(DublinCore.TITLE);
       properties.remove(DublinCore.TITLE);
@@ -121,7 +122,7 @@
     String file = args[0];
     byte[] raw = getRawBytes(new File(file));
 
-    Metadata meta = new Metadata();
+    PlainMetadata meta = new PlainMetadata();
     meta.set(Response.CONTENT_LENGTH, "" + raw.length);
     Content content = new Content(file, file, raw, mime, meta,
                                   NutchConfiguration.create());
Index: src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java
===================================================================
--- src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java	(revision 467333)
+++ src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java	(working copy)
@@ -29,7 +29,7 @@
 
 // Nutch imports
 import org.apache.nutch.crawl.CrawlDatum;
-import org.apache.nutch.metadata.Metadata;
+import org.apache.nutch.metadata.PlainMetadata;
 import org.apache.nutch.net.protocols.Response;
 import org.apache.nutch.protocol.ProtocolException;
 import org.apache.nutch.protocol.http.api.HttpBase;
@@ -46,7 +46,7 @@
   private String base;
   private byte[] content;
   private int code;
-  private Metadata headers = new Metadata();
+  private PlainMetadata headers = new PlainMetadata();
 
 
   public HttpResponse(HttpBase http, URL url, CrawlDatum datum)
@@ -178,7 +178,7 @@
     return headers.get(name);
   }
   
-  public Metadata getHeaders() {
+  public PlainMetadata getHeaders() {
     return headers;
   }