java ikanalyzer 动态扩展分词

若要使 自定义分词全部生效,请使用 细粒度分词

 

package com.thinkgem.jeesite.common.utils;

import java.io.StringReader;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

import org.apache.lucene.analysis.Analyzer;
import org.wltea.analyzer.cfg.Configuration;
import org.wltea.analyzer.cfg.DefaultConfig;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;
import org.wltea.analyzer.dic.Dictionary;

public class LuceneHelper {
	static Analyzer analyzer = new IKAnalyzer5x(true);
	
	static Dictionary dictionary = null;
	
	
	public static void init(){
		Configuration cfg = DefaultConfig.getInstance();  //加载词库
		cfg.setUseSmart(false); //true　用智能分词　，false细粒度可以根根据可扩展词切词
		Dictionary.initial(cfg);
		dictionary = Dictionary.getSingleton();
}
	
	/**
	 * 添加自定义词
	 * @param words
	 */
	public static void addCustomWords(Set<String>words){
			dictionary.addWords(words);  
			
		}
	/**
	 * 删除自定义词
	 * @param words
	 */
	public static void disableCustomWords(Set<String>words){
		dictionary.disableWords(words);  
		
	}
	public static List<String> queryWords(String query) {
    List<String> list = new ArrayList<String>();
    try {
    StringReader input = new StringReader(query.trim());
    IKSegmenter ikSeg = new IKSegmenter(input, false);// true　用智能分词　，false细粒度可以根根据可扩展词切词
    for (Lexeme lexeme = ikSeg.next(); lexeme != null; lexeme = ikSeg.next()){
        list.add(lexeme.getLexemeText());
    	}
	} catch (Exception e) {
		e.printStackTrace();
	}
    return list;
}

	public static void main(String[] args) {
		init();
		System.out.println(queryWords("养老证"));
		Set<String> words = new HashSet<String>();
    words.add("养老证");
    //words.add("老保");
    addCustomWords(words);
    disableCustomWords(words);
		System.out.println(queryWords("养老证"));
		
	}

}