Tokenizer.java

/* 
 * Copyright (C) 2015 Adrien Guille <adrien.guille@univ-lyon2.fr>
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
package main.java.fr.ericlab.sondy.core.text.index;

import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

/**
 *
 *   @author Adrien GUILLE, ERIC Lab, University of Lyon 2
 *   @email adrien.guille@univ-lyon2.fr
 */
public class Tokenizer {
    
    public static List<String> tokenizeString(org.apache.lucene.analysis.Analyzer analyzer, String string) {
        List<String> result = new ArrayList<>(20);
        try {
            TokenStream stream  = analyzer.tokenStream(null, new StringReader(string));
            stream.reset();
            while (stream.incrementToken()) {
                result.add(stream.getAttribute(CharTermAttribute.class).toString());
            }
            stream.close();
        } catch (IOException e) {}
        return result;
    }
    
    public static List<String> tokenizeString(String string) {
        return tokenizeString(new StandardAnalyzer(), string);
    }
}