1、自定义TokenFilter过滤器
package com.lkt.analyzer;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Stack;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.util.AttributeSource;
/**
* 定義同義詞過濾器
* @author lkt
*
*/
public class MyMmsegFilter extends TokenFilter {
//用來存儲同義詞集合
private Map<String, String[]> sameMap=new HashMap<String, String[]>();
//用來存儲當前詞的同義詞
private Stack<String> sameStack;
private int flag;
//存儲當前狀態
private AttributeSource.State currState;
private CharTermAttribute cta;
private PositionIncrementAttribute pia;
protected MyMmsegFilter(TokenStream input) {