<hibernate-configuration>
 <session-factory>
 	<property name="hibernate.search.analyzer">com.sobis.jaf.hibernate.search.JAFDefaultAnalyzer</property>
<property name="hibernate.search.default.directory_provider">org.hibernate.search.store.impl.FSSlaveDirectoryProvider</property>
	<property name="hibernate.search.default.indexBase">C:/Java-Dev/lucene/CMDB2/indexes</property>
	<property name="hibernate.search.default.sourceBase">C:/Java-Dev/lucene/CMDB/indexes</property>
	<property name="hibernate.search.default.refresh">120</property>
	<property name="hibernate.search.default.worker.backend">jms</property>
	<property name="hibernate.search.default.worker.jms.connection_factory">java:comp/env/jms/ConnectionFactory</property>
	<property name="hibernate.search.default.worker.jms.queue">java:comp/env/queue/hibernatesearch</property>
	<property name="hibernate.search.default.worker.jndi.java.naming.factory.initial">org.apache.activemq.jndi.ActiveMQInitialContextFactory</property>

import java.util.regex.Pattern;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.pattern.PatternTokenizer;

public final class JAFDefaultAnalyzer extends Analyzer {

	// regexp = search all whitespaces or special characters followed by a white space or at the end of the sentence
	private static final Pattern PATTERN = Pattern.compile("\\s+|[\\)\\}\\].,;:!?\"](\\s+|$)", Pattern.MULTILINE);

	public static Pattern getPattern() {
		return PATTERN;
	}

	@Override
	protected TokenStreamComponents createComponents(String fieldName) {
		Tokenizer tokenizer = new PatternTokenizer(PATTERN, -1);
		TokenStream stream = new LowerCaseFilter(tokenizer);
		return new TokenStreamComponents(tokenizer, stream);
	}

}