trunk/src/webapp/WEB-INF/xconf/lucene2.xconf

<?xml version="1.0"?>
<!--
  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.
-->

<components>
  <!-- Include dependencies -->
  <include src="context://WEB-INF/xconf/cocoon-xsp.xconf"/>

  <!-- Include roles -->
  <include src="resource://org/apache/cocoon/components/search/lucene2.roles"/>

  <!-- Search:
    These are the components that handle the search. 
    
   -->
	<analyzer_manager logger="core.search.analyzer_manager">
		<analyzer id="standard" class="org.apache.lucene.analysis.standard.StandardAnalyzer"/>
		<analyzer id="stopword_en" class="org.apache.cocoon.components.search.analyzer.ConfigurableStopwordAnalyzer" configfile="context://WEB-INF/analyzer/stopword/English_en.xml" checkupdate="true"/>
		<analyzer id="stopword_fr" class="org.apache.cocoon.components.search.analyzer.ConfigurableStopwordAnalyzer" configfile="context://WEB-INF/analyzer/stopword/French_fr.xml" checkupdate="true"/>
		<analyzer id="analyzer_research" class="org.apache.cocoon.components.search.analyzer.ConfigurablePerFieldAnalyzer" configfile="context://WEB-INF/analyzer/perfieldconf.xml" checkupdate="false"/>
	</analyzer_manager>
	
	<index_manager logger="core.search.index_manager">
		
		<indexer role="org.apache.cocoon.components.search.components.Indexer/default" />
		
		<!-- ALL indexes (BE CAREFUL: 	Change the directory attribute) 		-->
		<indexes>
		
			<!--
			id attribute : the index id 
			defaultAnalyzer: the id of the default analyzer (registered in AnalyzerManager)
			directory: the location of the physical index 
			-->
			<index id="research" analyzer="analyzer_research" directory="d:\\index">
				<structure>
					<!--
					type text:  tokenized , indexed   (with the additional attribute "storeText"  : stored/ unstored)
					type keyword:  no tokenized , indexed, stored
					type date = type keyword  but for specific date type
					-->
					<field id="title" type="text" storetext="true"/>
					<field id="author" type="text"/>
					<field id="description_fr" type="text" storetext="true"/>
					<field id="description_en" type="text" storetext="true"/>
					<field id="date" type="date" dateformat="yyyy-MM-dd"/> 
					<field id="subject" type="keyword"/>
					<field id="level" type="keyword"/> 
					<field id="type" type="keyword" />
					<field id="format" type="keyword" />
					<field id="topic" type="keyword" />
				</structure>
			</index>
			
			<!-- STANDARD HTML INDEX  -->
			<index id="HTML" analyzer="stopword_en" directory="d:\\index2" >
				<structure>
					<field id="url" type="keyword" />
					<field id="title" type="text" storetext="true"/>
					<field id="body" type="text" storetext="false"/>
				</structure>
			</index>
		</indexes>
	</index_manager>

<!-- default indexer component -->	
	<default_indexer logger="core.search.default_indexer">
		<!-- number of lucene documents in the buffer -->
		<buffersize>200</buffersize>
	</default_indexer>
	
<!-- parallel indexer component -->		
	<parallel_indexer logger="core.search.parallel_indexer">
		<!-- number of thread (normaly = number of CPUs) -->
		<numthread>2</numthread>
	</parallel_indexer>
	
	
</components>