12、自定义Analyzer实现扩展停用词

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseTokenizer;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;import java.util.ArrayList;
import java.util.List;/*** Created by kangz on 2016/12/16.* 自定义Analyzer实现扩展停用词*/
public class MyAnalzer extends Analyzer {public MyAnalzer() {super();setStopWordSet(StopAnalyzer.ENGLISH_STOP_WORDS_SET);}private CharArraySet stopWordSet;//停止词词典public MyAnalzer(List<String> stops) {this();//stopWordSet = getStopWordSet();  //如果直接这么调用的话，则并没有什么效果stopWordSet = CharArraySet.copy(getStopWordSet());//执行过滤分析stopWordSet.addAll(StopFilter.makeStopSet(stops));}public CharArraySet getStopWordSet() {return stopWordSet;}public void setStopWordSet(CharArraySet stopWordSet) {this.stopWordSet = stopWordSet;}@Overrideprotected TokenStreamComponents createComponents(String s) {Tokenizer source = new LowerCaseTokenizer();return new TokenStreamComponents(source, new StopFilter(source, stopWordSet));}public static void main(String[] args) throws Exception {// 将所要过滤的词 通过List进行赋值ArrayList<String> strings = new ArrayList<String>() {{add("小鬼子");add("美国佬");add("红毛鬼");}};Analyzer analyzer = new MyAnalzer(strings);String content = "小鬼子 and 美国佬 and 红毛鬼 are Playing Together!";TokenStream tokenStream = analyzer.tokenStream("myfield", content);tokenStream.reset();CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);while (tokenStream.incrementToken()) {// 已经过滤掉自定义停用词// 输出：playing   togetherSystem.out.println(charTermAttribute.toString());}tokenStream.end();tokenStream.close();}
}