From 1e037fcf507b81c1e95a2622f02e7dec7ef0903a Mon Sep 17 00:00:00 2001
From: Ryan McKinley <ryan@apache.org>
Date: Tue, 3 Jul 2007 06:14:07 +0000
Subject: [PATCH] SOLR-225 -- adding pluggable highlighting formatters and
 fragmenters

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@552682 13f79535-47bb-0310-9956-ffa450edef68
---
 CHANGES.txt                                   |   4 +
 example/solr/conf/solrconfig.xml              |  25 +
 .../solr/common/params/HighlightParams.java   |  19 +-
 .../apache/solr/highlight/GapFragmenter.java  | 106 +++++
 .../highlight/HighlightingPluginBase.java     |  73 +++
 .../apache/solr/highlight/HtmlFormatter.java  |  65 +++
 .../apache/solr/highlight/SolrFormatter.java  |  44 ++
 .../apache/solr/highlight/SolrFragmenter.java |  44 ++
 .../solr/highlight/SolrHighlighter.java       | 435 ++++++++++++++++++
 .../solr/highlight/HighlighterTest.java       |  29 +-
 src/test/test-files/solr/conf/solrconfig.xml  |  24 +
 11 files changed, 857 insertions(+), 11 deletions(-)
 create mode 100644 src/java/org/apache/solr/highlight/GapFragmenter.java
 create mode 100644 src/java/org/apache/solr/highlight/HighlightingPluginBase.java
 create mode 100644 src/java/org/apache/solr/highlight/HtmlFormatter.java
 create mode 100644 src/java/org/apache/solr/highlight/SolrFormatter.java
 create mode 100644 src/java/org/apache/solr/highlight/SolrFragmenter.java
 create mode 100644 src/java/org/apache/solr/highlight/SolrHighlighter.java

diff --git a/CHANGES.txt b/CHANGES.txt
index d0e9181b57c..d0853332d02 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -87,6 +87,10 @@ New Features
     RequestHandlers, FieldTypes, and QueryResponseWriters to share the same
     base code for loading and initalizing plugins. (ryan)
 
+14. SOLR-225: Enable pluggable highlighting classes.  Allow configurable
+    highlighting formatters and Fragmenters.  (ryan)
+
+
 Changes in runtime behavior
 
 Optimizations
diff --git a/example/solr/conf/solrconfig.xml b/example/solr/conf/solrconfig.xml
index b6a8c8d962b..d32eafe5512 100755
--- a/example/solr/conf/solrconfig.xml
+++ b/example/solr/conf/solrconfig.xml
@@ -431,6 +431,31 @@
     </lst>
   </requestHandler>
   
+  <!-- This should mostlikely be commented out in the "default" case -->
+  <highlighting>
+   <!-- Configure the standard fragmenter -->
+   <fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
+    <lst name="defaults">
+     <int name="hl.fragsize">100</int>
+    </lst>
+   </fragmenter>
+   
+   <fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
+    <lst name="defaults">
+     <int name="hl.fragsize">70</int>
+    </lst>
+   </fragmenter>
+   
+   <!-- Configure the standard formatter -->
+   <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
+    <lst name="defaults">
+     <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+     <str name="hl.simple.post"><![CDATA[</em>]]></str>
+    </lst>
+   </formatter>
+  </highlighting>
+  
+  
   <!-- queryResponseWriter plugins... query responses will be written using the
     writer specified by the 'wt' request parameter matching the name of a registered
     writer.
diff --git a/src/java/org/apache/solr/common/params/HighlightParams.java b/src/java/org/apache/solr/common/params/HighlightParams.java
index 3bbd90efbd1..9d013a7061b 100644
--- a/src/java/org/apache/solr/common/params/HighlightParams.java
+++ b/src/java/org/apache/solr/common/params/HighlightParams.java
@@ -27,14 +27,17 @@ public interface HighlightParams {
   
   public static final String SIMPLE = "simple";
   
-  public static final String HIGHLIGHT = "hl";
-  public static final String PREFIX = "hl.";
-  public static final String FIELDS = PREFIX+"fl";
-  public static final String SNIPPETS = PREFIX+"snippets";
-  public static final String FRAGSIZE = PREFIX+"fragsize";
-  public static final String FORMATTER = PREFIX+"formatter";
-  public static final String SIMPLE_PRE = PREFIX+SIMPLE+".pre";
+  public static final String HIGHLIGHT   = "hl";
+  public static final String PREFIX      = "hl.";
+  public static final String FIELDS      = PREFIX+"fl";
+  public static final String SNIPPETS    = PREFIX+"snippets";
+  public static final String FRAGSIZE    = PREFIX+"fragsize";
+  public static final String INCREMENT   = PREFIX+"increment";
+  public static final String SLOP        = PREFIX+"slop";
+  public static final String MAX_CHARS   = PREFIX+"maxAnalyzedChars";
+  public static final String FORMATTER   = PREFIX+"formatter";
+  public static final String FRAGMENTER  = PREFIX+"fragmenter";
+  public static final String SIMPLE_PRE  = PREFIX+SIMPLE+".pre";
   public static final String SIMPLE_POST = PREFIX+SIMPLE+".post";
   public static final String FIELD_MATCH = PREFIX+"requireFieldMatch";
-
 }
diff --git a/src/java/org/apache/solr/highlight/GapFragmenter.java b/src/java/org/apache/solr/highlight/GapFragmenter.java
new file mode 100644
index 00000000000..6bd0a039206
--- /dev/null
+++ b/src/java/org/apache/solr/highlight/GapFragmenter.java
@@ -0,0 +1,106 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You 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.solr.highlight;
+
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.search.highlight.Fragmenter;
+import org.apache.lucene.search.highlight.NullFragmenter;
+import org.apache.lucene.search.highlight.SimpleFragmenter;
+import org.apache.solr.common.params.DefaultSolrParams;
+import org.apache.solr.common.params.HighlightParams;
+import org.apache.solr.common.params.SolrParams;
+
+public class GapFragmenter extends HighlightingPluginBase implements SolrFragmenter
+{
+  public Fragmenter getFragmenter(String fieldName, SolrParams params )
+  {
+    numRequests++;
+    if( defaults != null ) {
+      params = new DefaultSolrParams( params, defaults );
+    }
+    
+    int fragsize = params.getFieldInt( fieldName, HighlightParams.FRAGSIZE, 100 );
+    return (fragsize <= 0) ? new NullFragmenter() : new LuceneGapFragmenter(fragsize);
+  }
+  
+
+  ///////////////////////////////////////////////////////////////////////
+  //////////////////////// SolrInfoMBeans methods ///////////////////////
+  ///////////////////////////////////////////////////////////////////////
+
+  @Override
+  public String getDescription() {
+    return "GapFragmenter";
+  }
+
+  @Override
+  public String getVersion() {
+      return "$Revision$";
+  }
+
+  @Override
+  public String getSourceId() {
+    return "$Id$";
+  }
+
+  @Override
+  public String getSource() {
+    return "$URL$";
+  }
+}
+
+
+/**
+ * A simple modification of SimpleFragmenter which additionally creates new
+ * fragments when an unusually-large position increment is encountered
+ * (this behaves much better in the presence of multi-valued fields).
+ */
+class LuceneGapFragmenter extends SimpleFragmenter {
+  /** 
+   * When a gap in term positions is observed that is at least this big, treat
+   * the gap as a fragment delimiter.
+   */
+  public static final int INCREMENT_THRESHOLD = 50;
+  protected int fragOffsetAccum = 0;
+  
+  public LuceneGapFragmenter() {
+  }
+  
+  public LuceneGapFragmenter(int fragsize) {
+     super(fragsize);
+  }
+  
+  /* (non-Javadoc)
+   * @see org.apache.lucene.search.highlight.TextFragmenter#start(java.lang.String)
+   */
+  public void start(String originalText) {
+    fragOffsetAccum = 0;
+  }
+
+  /* (non-Javadoc)
+   * @see org.apache.lucene.search.highlight.TextFragmenter#isNewFragment(org.apache.lucene.analysis.Token)
+   */
+  public boolean isNewFragment(Token token) {
+    boolean isNewFrag = 
+      token.endOffset() >= fragOffsetAccum + getFragmentSize() ||
+      token.getPositionIncrement() > INCREMENT_THRESHOLD;
+    if(isNewFrag) {
+        fragOffsetAccum += token.endOffset() - fragOffsetAccum;
+    }
+    return isNewFrag;
+  }
+}
diff --git a/src/java/org/apache/solr/highlight/HighlightingPluginBase.java b/src/java/org/apache/solr/highlight/HighlightingPluginBase.java
new file mode 100644
index 00000000000..5661175b88f
--- /dev/null
+++ b/src/java/org/apache/solr/highlight/HighlightingPluginBase.java
@@ -0,0 +1,73 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You 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.solr.highlight;
+
+import java.net.URL;
+
+import org.apache.solr.common.params.SolrParams;
+import org.apache.solr.common.util.NamedList;
+import org.apache.solr.common.util.SimpleOrderedMap;
+import org.apache.solr.core.SolrInfoMBean;
+
+/**
+ * 
+ * @author ryan
+ * @since solr 1.3
+ */
+public abstract class HighlightingPluginBase implements SolrInfoMBean
+{
+  protected long numRequests;
+  protected SolrParams defaults;
+
+  public void init(NamedList args) {
+    if( args != null ) {
+      Object o = args.get("defaults");
+      if (o != null && o instanceof NamedList ) {
+        defaults = SolrParams.toSolrParams((NamedList)o);
+      }
+    }
+  }
+
+  //////////////////////// SolrInfoMBeans methods //////////////////////
+
+  public String getName() {
+    return this.getClass().getName();
+  }
+
+  public abstract String getDescription();
+  public abstract String getSourceId();
+  public abstract String getSource();
+  public abstract String getVersion();
+  
+  public Category getCategory()
+  {
+    return Category.HIGHLIGHTING;
+  }
+
+  public URL[] getDocs() {
+    return null;  // this can be overridden, but not required
+  }
+
+  public NamedList getStatistics() {
+    NamedList<Long> lst = new SimpleOrderedMap<Long>();
+    lst.add("requests", numRequests);
+    return lst;
+  }
+}
+
+
diff --git a/src/java/org/apache/solr/highlight/HtmlFormatter.java b/src/java/org/apache/solr/highlight/HtmlFormatter.java
new file mode 100644
index 00000000000..0aeb7aae93a
--- /dev/null
+++ b/src/java/org/apache/solr/highlight/HtmlFormatter.java
@@ -0,0 +1,65 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You 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.solr.highlight;
+
+import org.apache.lucene.search.highlight.Formatter;
+import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
+import org.apache.solr.common.params.DefaultSolrParams;
+import org.apache.solr.common.params.HighlightParams;
+import org.apache.solr.common.params.SolrParams;
+
+/**
+ * Use the SimpleHTMLFormatter
+ */
+public class HtmlFormatter extends HighlightingPluginBase implements SolrFormatter 
+{
+  public Formatter getFormatter(String fieldName, SolrParams params ) 
+  {
+    numRequests++;
+    if( defaults != null ) {
+      params = new DefaultSolrParams( params, defaults );
+    }
+    
+    return new SimpleHTMLFormatter(
+        params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
+        params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
+  }
+
+  ///////////////////////////////////////////////////////////////////////
+  //////////////////////// SolrInfoMBeans methods ///////////////////////
+  ///////////////////////////////////////////////////////////////////////
+
+  @Override
+  public String getDescription() {
+    return "GapFragmenter";
+  }
+
+  @Override
+  public String getVersion() {
+      return "$Revision$";
+  }
+
+  @Override
+  public String getSourceId() {
+    return "$Id$";
+  }
+
+  @Override
+  public String getSource() {
+    return "$URL$";
+  }
+}
diff --git a/src/java/org/apache/solr/highlight/SolrFormatter.java b/src/java/org/apache/solr/highlight/SolrFormatter.java
new file mode 100644
index 00000000000..f9c26aca931
--- /dev/null
+++ b/src/java/org/apache/solr/highlight/SolrFormatter.java
@@ -0,0 +1,44 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You 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.solr.highlight;
+
+import org.apache.lucene.search.highlight.Formatter;
+import org.apache.solr.common.params.SolrParams;
+import org.apache.solr.common.util.NamedList;
+import org.apache.solr.core.SolrInfoMBean;
+import org.apache.solr.util.plugin.NamedListInitializedPlugin;
+
+public interface SolrFormatter extends SolrInfoMBean, NamedListInitializedPlugin {
+
+  /** <code>init</code> will be called just once, immediately after creation.
+   * <p>The args are user-level initialization parameters that
+   * may be specified when declaring a request handler in
+   * solrconfig.xml
+   */
+  public void init(NamedList args);
+
+  /**
+   * Return a formatter appropriate for this field.
+   * 
+   * @param fieldName The name of the field
+   * @param request The current SolrQueryRequest
+   * @return An appropriate Formatter.
+   */
+  public Formatter getFormatter(String fieldName, SolrParams params );
+}
+
diff --git a/src/java/org/apache/solr/highlight/SolrFragmenter.java b/src/java/org/apache/solr/highlight/SolrFragmenter.java
new file mode 100644
index 00000000000..497a69fbe0c
--- /dev/null
+++ b/src/java/org/apache/solr/highlight/SolrFragmenter.java
@@ -0,0 +1,44 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You 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.solr.highlight;
+
+import org.apache.lucene.search.highlight.Fragmenter;
+import org.apache.solr.common.params.SolrParams;
+import org.apache.solr.common.util.NamedList;
+import org.apache.solr.core.SolrInfoMBean;
+import org.apache.solr.util.plugin.NamedListInitializedPlugin;
+
+public interface SolrFragmenter extends SolrInfoMBean, NamedListInitializedPlugin {
+
+  /** <code>init</code> will be called just once, immediately after creation.
+   * <p>The args are user-level initialization parameters that
+   * may be specified when declaring a request handler in
+   * solrconfig.xml
+   */
+  public void init(NamedList args);
+
+  /**
+   * Return a fragmenter appropriate for this field. 
+   * 
+   * @param fieldName The name of the field
+   * @param request The current SolrQueryRequest
+   * @return An appropriate Fragmenter.
+   */
+  public Fragmenter getFragmenter(String fieldName, SolrParams params);
+}
+
diff --git a/src/java/org/apache/solr/highlight/SolrHighlighter.java b/src/java/org/apache/solr/highlight/SolrHighlighter.java
new file mode 100644
index 00000000000..22dc95795f1
--- /dev/null
+++ b/src/java/org/apache/solr/highlight/SolrHighlighter.java
@@ -0,0 +1,435 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You 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.solr.highlight;
+
+import java.io.IOException;
+import java.io.StringReader;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.LinkedList;
+import java.util.ListIterator;
+import java.util.Map;
+import java.util.Set;
+import java.util.logging.Logger;
+
+import javax.xml.xpath.XPathConstants;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.search.Query;
+import org.apache.lucene.search.highlight.Formatter;
+import org.apache.lucene.search.highlight.Fragmenter;
+import org.apache.lucene.search.highlight.Highlighter;
+import org.apache.lucene.search.highlight.QueryScorer;
+import org.apache.lucene.search.highlight.TextFragment;
+import org.apache.lucene.search.highlight.TokenSources;
+import org.apache.solr.common.SolrException;
+import org.apache.solr.common.params.HighlightParams;
+import org.apache.solr.common.params.SolrParams;
+import org.apache.solr.common.util.NamedList;
+import org.apache.solr.common.util.SimpleOrderedMap;
+import org.apache.solr.core.Config;
+import org.apache.solr.request.SolrQueryRequest;
+import org.apache.solr.schema.IndexSchema;
+import org.apache.solr.schema.SchemaField;
+import org.apache.solr.search.DocIterator;
+import org.apache.solr.search.DocList;
+import org.apache.solr.search.SolrIndexSearcher;
+import org.apache.solr.util.SolrPluginUtils;
+import org.apache.solr.util.plugin.NamedListPluginLoader;
+import org.w3c.dom.NodeList;
+
+public class SolrHighlighter 
+{
+  public static Logger log = Logger.getLogger(SolrHighlighter.class.getName());
+  
+  // Thread safe registry
+  protected final Map<String,SolrFormatter> formatters = 
+    Collections.synchronizedMap( new HashMap<String, SolrFormatter>() );
+
+  // Thread safe registry
+  protected final Map<String,SolrFragmenter> fragmenters = 
+    Collections.synchronizedMap( new HashMap<String, SolrFragmenter>() );
+  
+  public void initalize( Config config )
+  {
+    formatters.clear();
+    fragmenters.clear();
+    
+    // Load the fragmenters
+    String xpath = "highlighting/fragmenter";
+    NamedListPluginLoader<SolrFragmenter> fragloader = new NamedListPluginLoader<SolrFragmenter>( xpath, fragmenters );
+    SolrFragmenter frag = fragloader.load( (NodeList)config.evaluate( xpath, XPathConstants.NODESET ) );
+    if( frag == null ) {
+      frag = new GapFragmenter();
+    }
+    fragmenters.put( "", frag );
+    fragmenters.put( null, frag );
+    
+    // Load the formatters
+    xpath = "highlighting/formatter";
+    NamedListPluginLoader<SolrFormatter> fmtloader = new NamedListPluginLoader<SolrFormatter>( xpath, formatters );
+    SolrFormatter fmt = fmtloader.load( (NodeList)config.evaluate( xpath, XPathConstants.NODESET ) );
+    if( fmt == null ) {
+      fmt = new HtmlFormatter();
+    }
+    formatters.put( "", fmt );
+    formatters.put( null, fmt );
+  }
+  
+  
+  /**
+   * Check whether Highlighting is enabled for this request.
+   * @param request The current SolrQueryRequest
+   * @return <code>true</code> if highlighting enabled, <code>false</code> if not.
+   */
+  public boolean isHighlightingEnabled(SolrParams params) {
+    return params.getBool(HighlightParams.HIGHLIGHT, false);
+  }
+  
+  /**
+   * Return a Highlighter appropriate for this field.
+   * @param query The current Query
+   * @param fieldName The name of the field
+   * @param request The current SolrQueryRequest
+   */
+  protected Highlighter getHighlighter(Query query, String fieldName, SolrQueryRequest request) {
+    SolrParams params = request.getParams(); 
+    Highlighter highlighter = new Highlighter(
+           getFormatter(fieldName, params), 
+           getQueryScorer(query, fieldName, request));
+     highlighter.setTextFragmenter(getFragmenter(fieldName, params));
+     return highlighter;
+  }
+  
+  /**
+   * Return a QueryScorer suitable for this Query and field.
+   * @param query The current query
+   * @param fieldName The name of the field
+   * @param request The SolrQueryRequest
+   */
+  protected QueryScorer getQueryScorer(Query query, String fieldName, SolrQueryRequest request) {
+     boolean reqFieldMatch = request.getParams().getFieldBool(fieldName, HighlightParams.FIELD_MATCH, false);
+     if (reqFieldMatch) {
+        return new QueryScorer(query, request.getSearcher().getReader(), fieldName);
+     }
+     else {
+        return new QueryScorer(query);
+     }
+  }
+  
+  /**
+   * Return a String array of the fields to be highlighted.
+   * Falls back to the programatic defaults, or the default search field if the list of fields
+   * is not specified in either the handler configuration or the request.
+   * @param query The current Query
+   * @param request The current SolrQueryRequest
+   * @param defaultFields Programmatic default highlight fields, used if nothing is specified in the handler config or the request.
+   */
+  public String[] getHighlightFields(Query query, SolrQueryRequest request, String[] defaultFields) {
+     String fields[] = request.getParams().getParams(HighlightParams.FIELDS);
+     
+     // if no fields specified in the request, or the handler, fall back to programmatic default, or default search field.
+     if(emptyArray(fields)) {
+        // use default search field if highlight fieldlist not specified.
+        if (emptyArray(defaultFields)) {
+           fields = new String[]{request.getSchema().getDefaultSearchFieldName()};
+        }  
+        else {
+           fields = defaultFields;
+        }
+     }
+     else if (fields.length == 1) {
+        // if there's a single request/handler value, it may be a space/comma separated list
+        fields = SolrPluginUtils.split(fields[0]);
+     }
+     
+     return fields;
+  }
+  
+  protected boolean emptyArray(String[] arr) {
+     return (arr == null || arr.length == 0 || arr[0] == null || arr[0].trim().length() == 0);
+  }
+  
+  /**
+   * Return the max number of snippets for this field. If this has not
+   * been configured for this field, fall back to the configured default
+   * or the solr default.
+   * @param fieldName The name of the field
+   * @param request The current SolrQueryRequest
+   */
+  protected int getMaxSnippets(String fieldName, SolrParams params) {
+     return params.getFieldInt(fieldName, HighlightParams.SNIPPETS,1);
+  }
+  
+  /**
+   * Return a formatter appropriate for this field. If a formatter
+   * has not been configured for this field, fall back to the configured
+   * default or the solr default (SimpleHTMLFormatter).
+   * 
+   * @param fieldName The name of the field
+   * @param request The current SolrQueryRequest
+   * @return An appropriate Formatter.
+   */
+  protected Formatter getFormatter(String fieldName, SolrParams params ) 
+  {
+    String str = params.getFieldParam( fieldName, HighlightParams.FORMATTER );
+    SolrFormatter formatter = formatters.get( str );
+    if( formatter == null ) {
+      throw new SolrException( SolrException.ErrorCode.BAD_REQUEST, "Unknown formatter: "+str );
+    }
+    return formatter.getFormatter( fieldName, params );
+  }
+  
+  /**
+   * Return a fragmenter appropriate for this field. If a fragmenter
+   * has not been configured for this field, fall back to the configured
+   * default or the solr default (GapFragmenter).
+   * 
+   * @param fieldName The name of the field
+   * @param request The current SolrQueryRequest
+   * @return An appropriate Fragmenter.
+   */
+  protected Fragmenter getFragmenter(String fieldName, SolrParams params) 
+  {
+    String fmt = params.getFieldParam( fieldName, HighlightParams.FRAGMENTER );
+    SolrFragmenter frag = fragmenters.get( fmt );
+    if( frag == null ) {
+      throw new SolrException( SolrException.ErrorCode.BAD_REQUEST, "Unknown fragmenter: "+fmt );
+    }
+    return frag.getFragmenter( fieldName, params );
+  }
+  
+  /**
+   * Generates a list of Highlighted query fragments for each item in a list
+   * of documents, or returns null if highlighting is disabled.
+   *
+   * @param docs query results
+   * @param query the query
+   * @param req the current request
+   * @param defaultFields default list of fields to summarize
+   *
+   * @return NamedList containing a NamedList for each document, which in 
+   * turns contains sets (field, summary) pairs.
+   */
+  @SuppressWarnings("unchecked")
+  public NamedList<Object> doHighlighting(DocList docs, Query query, SolrQueryRequest req, String[] defaultFields) throws IOException {
+    SolrParams params = req.getParams(); 
+    if (!isHighlightingEnabled(params))
+        return null;
+     
+     SolrIndexSearcher searcher = req.getSearcher();
+     IndexSchema schema = searcher.getSchema();
+     NamedList fragments = new SimpleOrderedMap();
+     String[] fieldNames = getHighlightFields(query, req, defaultFields);
+     Document[] readDocs = new Document[docs.size()];
+     {
+       // pre-fetch documents using the Searcher's doc cache
+       Set<String> fset = new HashSet<String>();
+       for(String f : fieldNames) { fset.add(f); }
+       // fetch unique key if one exists.
+       SchemaField keyField = schema.getUniqueKeyField();
+       if(null != keyField)
+         fset.add(keyField.getName());  
+       searcher.readDocs(readDocs, docs, fset);
+     }
+
+     // Highlight each document
+     DocIterator iterator = docs.iterator();
+     for (int i = 0; i < docs.size(); i++) {
+        int docId = iterator.nextDoc();
+        Document doc = readDocs[i];
+        NamedList docSummaries = new SimpleOrderedMap();
+        for (String fieldName : fieldNames) {
+           fieldName = fieldName.trim();
+           String[] docTexts = doc.getValues(fieldName);
+           if (docTexts == null) continue;
+
+           // get highlighter, and number of fragments for this field
+           Highlighter highlighter = getHighlighter(query, fieldName, req);
+           int numFragments = getMaxSnippets(fieldName, params);
+
+           String[] summaries;
+           TextFragment[] frag;
+           if (docTexts.length == 1) {
+              // single-valued field
+              TokenStream tstream;
+              try {
+                 // attempt term vectors
+                 tstream = TokenSources.getTokenStream(searcher.getReader(), docId, fieldName);
+              }
+              catch (IllegalArgumentException e) {
+                 // fall back to analyzer
+                 tstream = new TokenOrderingFilter(schema.getAnalyzer().tokenStream(fieldName, new StringReader(docTexts[0])), 10);
+              }
+              frag = highlighter.getBestTextFragments(tstream, docTexts[0], false, numFragments);
+           }
+           else {
+              // multi-valued field
+              MultiValueTokenStream tstream;
+              tstream = new MultiValueTokenStream(fieldName, docTexts, schema.getAnalyzer(), true);
+              frag = highlighter.getBestTextFragments(tstream, tstream.asSingleValue(), false, numFragments);
+           }
+           // convert fragments back into text
+           // TODO: we can include score and position information in output as snippet attributes
+           if (frag.length > 0) {
+              ArrayList<String> fragTexts = new ArrayList<String>();
+              for (int j = 0; j < frag.length; j++) {
+                 if ((frag[j] != null) && (frag[j].getScore() > 0)) {
+                    fragTexts.add(frag[j].toString());
+                 }
+              }
+              summaries = fragTexts.toArray(new String[0]);
+              if (summaries.length > 0) 
+                docSummaries.add(fieldName, summaries);
+           }
+        }
+        String printId = schema.printableUniqueKey(doc);
+        fragments.add(printId == null ? null : printId, docSummaries);
+     }
+     return fragments;
+  }
+}
+
+
+
+
+/** 
+ * Helper class which creates a single TokenStream out of values from a 
+ * multi-valued field.
+ */
+class MultiValueTokenStream extends TokenStream {
+  private String fieldName;
+  private String[] values;
+  private Analyzer analyzer;
+  private int curIndex;                  // next index into the values array
+  private int curOffset;                 // offset into concatenated string
+  private TokenStream currentStream;     // tokenStream currently being iterated
+  private boolean orderTokenOffsets;
+
+  /** Constructs a TokenStream for consecutively-analyzed field values
+   *
+   * @param fieldName name of the field
+   * @param values array of field data
+   * @param analyzer analyzer instance
+   */
+  public MultiValueTokenStream(String fieldName, String[] values, 
+                               Analyzer analyzer, boolean orderTokenOffsets) {
+    this.fieldName = fieldName;
+    this.values = values;
+    this.analyzer = analyzer;
+    curIndex = -1;
+    curOffset = 0;
+    currentStream = null;
+    this.orderTokenOffsets=orderTokenOffsets;
+  }
+
+  /** Returns the next token in the stream, or null at EOS. */
+  @Override
+  public Token next() throws IOException {
+    int extra = 0;
+    if(currentStream == null) {
+      curIndex++;        
+      if(curIndex < values.length) {
+        currentStream = analyzer.tokenStream(fieldName, 
+                                             new StringReader(values[curIndex]));
+        if (orderTokenOffsets) currentStream = new TokenOrderingFilter(currentStream,10);
+        // add extra space between multiple values
+        if(curIndex > 0) 
+          extra = analyzer.getPositionIncrementGap(fieldName);
+      } else {
+        return null;
+      }
+    }
+    Token nextToken = currentStream.next();
+    if(nextToken == null) {
+      curOffset += values[curIndex].length();
+      currentStream = null;
+      return next();
+    }
+    // create an modified token which is the offset into the concatenated
+    // string of all values
+    Token offsetToken = new Token(nextToken.termText(), 
+                                  nextToken.startOffset() + curOffset,
+                                  nextToken.endOffset() + curOffset);
+    offsetToken.setPositionIncrement(nextToken.getPositionIncrement() + extra*10);
+    return offsetToken;
+  }
+
+  /**
+   * Returns all values as a single String into which the Tokens index with
+   * their offsets.
+   */
+  public String asSingleValue() {
+    StringBuilder sb = new StringBuilder();
+    for(String str : values)
+      sb.append(str);
+    return sb.toString();
+  }
+
+}
+
+
+/** Orders Tokens in a window first by their startOffset ascending.
+ * endOffset is currently ignored.
+ * This is meant to work around fickleness in the highlighter only.  It
+ * can mess up token positions and should not be used for indexing or querying.
+ */
+class TokenOrderingFilter extends TokenFilter {
+  private final int windowSize;
+  private final LinkedList<Token> queue = new LinkedList<Token>();
+  private boolean done=false;
+
+  protected TokenOrderingFilter(TokenStream input, int windowSize) {
+    super(input);
+    this.windowSize = windowSize;
+  }
+
+  @Override
+  public Token next() throws IOException {
+    while (!done && queue.size() < windowSize) {
+      Token newTok = input.next();
+      if (newTok==null) {
+        done=true;
+        break;
+      }
+
+      // reverse iterating for better efficiency since we know the
+      // list is already sorted, and most token start offsets will be too.
+      ListIterator<Token> iter = queue.listIterator(queue.size());
+      while(iter.hasPrevious()) {
+        if (newTok.startOffset() >= iter.previous().startOffset()) {
+          // insertion will be before what next() would return (what
+          // we just compared against), so move back one so the insertion
+          // will be after.
+          iter.next();
+          break;
+        }
+      }
+      iter.add(newTok);
+    }
+
+    return queue.isEmpty() ? null : queue.removeFirst();
+  }
+}
+
+
diff --git a/src/test/org/apache/solr/highlight/HighlighterTest.java b/src/test/org/apache/solr/highlight/HighlighterTest.java
index f8251c4ce60..2367c3d6f48 100755
--- a/src/test/org/apache/solr/highlight/HighlighterTest.java
+++ b/src/test/org/apache/solr/highlight/HighlighterTest.java
@@ -17,10 +17,12 @@
 
 package org.apache.solr.highlight;
 
-import java.util.HashMap;
+import org.apache.solr.core.SolrCore;
+import org.apache.solr.request.*;
+import org.apache.solr.util.*;
+import org.apache.solr.schema.*;
 
-import org.apache.solr.util.AbstractSolrTestCase;
-import org.apache.solr.util.TestHarness;
+import java.util.HashMap;
 
 /**
  * Tests some basic functionality of Solr while demonstrating good
@@ -44,6 +46,27 @@ public class HighlighterTest extends AbstractSolrTestCase {
     // the super classes version
     super.tearDown();
   }
+  
+  public void testConfig()
+  {
+    SolrHighlighter highlighter = SolrCore.getSolrCore().getHighlighter();
+    System.out.println( "highlighter" );
+
+    // Make sure we loaded the one formatter
+    SolrFormatter fmt1 = highlighter.formatters.get( null );
+    SolrFormatter fmt2 = highlighter.formatters.get( "" );
+    assertSame( fmt1, fmt2 );
+    assertTrue( fmt1 instanceof HtmlFormatter );
+    
+    
+    // Make sure we loaded the one formatter
+    SolrFragmenter gap = highlighter.fragmenters.get( "gap" );
+    SolrFragmenter regex = highlighter.fragmenters.get( "regex" );
+    SolrFragmenter frag = highlighter.fragmenters.get( null );
+    assertSame( gap, frag );
+    assertTrue( gap instanceof GapFragmenter );
+    assertTrue( regex instanceof RegexFragmenter );
+  }
 
   public void testTermVecHighlight() {
 
diff --git a/src/test/test-files/solr/conf/solrconfig.xml b/src/test/test-files/solr/conf/solrconfig.xml
index ebd63fec17f..29d4ccece15 100644
--- a/src/test/test-files/solr/conf/solrconfig.xml
+++ b/src/test/test-files/solr/conf/solrconfig.xml
@@ -265,6 +265,30 @@
   <requestHandler name="/update"     class="solr.XmlUpdateRequestHandler"          />
   <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" />
 
+  <highlighting>
+   <!-- Configure the standard fragmenter -->
+   <fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
+    <lst name="defaults">
+     <int name="hl.fragsize">100</int>
+    </lst>
+   </fragmenter>
+   
+   <fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
+    <lst name="defaults">
+     <int name="hl.fragsize">70</int>
+    </lst>
+   </fragmenter>
+   
+   <!-- Configure the standard formatter -->
+   <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
+    <lst name="defaults">
+     <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+     <str name="hl.simple.post"><![CDATA[</em>]]></str>
+    </lst>
+   </formatter>
+  </highlighting>
+
+
   <!-- enable streaming for testing... -->
   <requestDispatcher handleSelect="true" >
     <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />