Lucene高亮功能

package it.heima.luceneInde;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.*;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;

import java.io.File;
import java.io.IOException;

public class HighlighterToLusene {
    @Test
    public void HighlighterToLucene1() throws IOException, InvalidTokenOffsetsException {
        //创建查询对象
        IndexSearcher indexSearcher = new IndexSearcher(DirectoryReader.open(FSDirectory.open(new File("f:\\test"))));
        //执行查询,此处用词条查询
        TermQuery termQuery = new TermQuery(new Term("content","格力"));//分词中有"格力"两个字,如果格力在title不能分词的中就查询不到了
        //--------------------高亮开始---------------------------------------------------------
        SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color='red'>", "</font>");//格式,高亮红色
        QueryScorer queryScorer = new QueryScorer(termQuery);//中间内容
        Highlighter highlighter = new Highlighter(simpleHTMLFormatter, queryScorer);//组合格式和中间内容
        //--------------------高亮结束----------------------------------------------------------
        TopDocs topDocs = indexSearcher.search(termQuery, 20);
        //获取结果集总数
        int totalHits = topDocs.totalHits;
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;//获取结果集分数数组;
        for (ScoreDoc scoreDoc : scoreDocs) {
            float score = scoreDoc.score;//获取分数
            int id = scoreDoc.doc;//获取分数对应的id(此id是lusene系统自定义的,从0开始)
            Document doc = indexSearcher.doc(id);
            System.out.println(doc);
            String content = doc.get("content");
            //---------------高亮获取-----------------------------------
            content = highlighter.getBestFragment(new IKAnalyzer(), "content", content);

            System.out.println("共获取到:"+totalHits+"条结果.--结果为:"+content);


        }


    }
}

结果:

猜你喜欢

转载自blog.csdn.net/weixin_42333583/article/details/82026964
今日推荐