extras/indexing/src/main/java/org/apache/rya/indexing/accumulo/freetext/LuceneTokenizer.java

package org.apache.rya.indexing.accumulo.freetext;

/*
 * 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.
 */

import java.io.IOException;
import java.io.StringReader;
import java.util.SortedSet;
import java.util.TreeSet;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

/**
 * A {@link Tokenizer} that delegates to Lucene functions
 */
public class LuceneTokenizer implements Tokenizer {
	private static final Analyzer ANALYZER = new StandardAnalyzer();

	@Override
	public SortedSet<String> tokenize(String string) {
		SortedSet<String> set = new TreeSet<String>();
		try (final TokenStream stream = ANALYZER.tokenStream(null, new StringReader(string))) {
			stream.reset();
			while (stream.incrementToken()) {
				set.add(stream.getAttribute(CharTermAttribute.class).toString());
			}
		} catch (IOException e) {
			// not thrown b/c we're using a string reader...
			throw new RuntimeException(e);
		}

		return set;
	}
}