Lucene 自定義分詞器

package com.lucene.util;

import java.io.Reader;
import java.util.Set;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LetterTokenizer;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.util.Version;

//定義禁用詞分詞器
public class UserDefinedAnalyzer extends Analyzer {

    //定義禁用詞集合
    private Set stops;
    
    //無參構造器使用默認的禁用詞分詞器
    public UserDefinedAnalyzer(){
        stops=StopAnalyzer.ENGLISH_STOP_WORDS_SET;
    }
    
    /**
     * 傳一個禁用詞數組
     * @param sws
     */
    public UserDefinedAnalyzer(String[] sws){
        //使用stopFilter創建禁用詞集合
        stops=StopFilter.makeStopSet(Version.LUCENE_35,sws,true);
        //將默認的禁用詞添加進集合
        stops.addAll(StopAnalyzer.ENGLISH_STOP_WORDS_SET);
    }
    
    /**
     * 自定義分詞器
     */
    @Override
    public TokenStream tokenStream(String str, Reader reader) {
        
        return new StopFilter    
                (Version.LUCENE_35, 
                        new LowerCaseFilter    
                (Version.LUCENE_35, 
                        new LetterTokenizer(
                Version.LUCENE_35, reader)), stops);
    }

}

    @Test
    public void test04(){
        Analyzer a1=new UserDefinedAnalyzer(new String[]{"my","name"});
        //Analyzer a1=new UserDefinedAnalyzer();
        String str="my name is paul";
        AnalyzerUtil.displayToken(str, a1);
    }