lucene3.0 搜索结果排序+高亮展示

1.排序

package cn.xt.sort;

import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.util.Version;
import org.junit.Before;
import org.junit.Test;

import cn.xt.crud.LuncenUtil;
import cn.xt.pojo.Article;

public class SortTest {
	Article article = null;

	@Before
	public void setUp() throws Exception {
		article = new Article();
		article.setId(1);
		article.setTitle("lucene是一片文章");
		article.setContent("是一个非常好用的全文搜索技术，very good。");
	}

	/**
	 * 1、相同的结构，相同的关键词，得分一样
	 * 2、相同的结构，不同的关键词，得分不一样，一般来说中文比较高
	 * 3、不同的结构，关键词出现的次数越多，得分越高
	 * 4、利用document.setBoost(100)可以人为的提高相关度得分
	 * @throws Exception
	 */
	@Test
	public void testSearchIndex() throws Exception{
		IndexSearcher indexSearcher = new IndexSearcher(LuncenUtil.directory);
		QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_30, new String[]{"title","content"}, LuncenUtil.analyzer);
		Query query = queryParser.parse("lucene");
		TopDocs topDocs = indexSearcher.search(query, 26);
		ScoreDoc[] scoreDocs = topDocs.scoreDocs;
		List<Article> articleList = new ArrayList<Article>();
		for(ScoreDoc scoreDoc:scoreDocs){
			float score = scoreDoc.score;
			System.out.println(score);//相关的得分
			Document document =  indexSearcher.doc(scoreDoc.doc);
			articleList.add(article);
		}
		
		for(Article article:articleList){
			System.out.println(article.getId());
			System.out.println(article.getTitle());
			System.out.println(article.getContent());
		}
	}
}

2.高亮显示

package cn.xt.highlighter;

import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.util.Version;
import org.junit.Before;
import org.junit.Test;

import cn.xt.crud.LuncenUtil;
import cn.xt.pojo.Article;

/**
 * 高亮
 *    * 使关键字变色
 *       *  设置
 *       *  使用
 *    * 控制摘要的大小
 * @author Administrator
 */
public class HighlighterTest {
	Article article = null;

	@Before
	public void setUp() throws Exception {
		article = new Article();
		article.setId(1);
		article.setTitle("lucene是一片文章");
		article.setContent("是一个非常好用的全文搜索技术，very good。");
	}
	
	@Test
	public void testSearchIndex() throws Exception{
		IndexSearcher indexSearcher = new IndexSearcher(LuncenUtil.directory);
		QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_30, new String[]{"title","content"}, LuncenUtil.analyzer);
		Query query = queryParser.parse("Lucene");
		TopDocs topDocs = indexSearcher.search(query, 25);
		ScoreDoc[] scoreDocs = topDocs.scoreDocs;
		/***********************************************************************/
			/**
			 * 给关键字加上前缀和后缀
			 */
			Formatter formatter = new SimpleHTMLFormatter("<font color='red'>","</font>");
			/**
			 * scorer封装了关键字
			 */
			Scorer scorer = new QueryScorer(query);
			Highlighter highlighter = new Highlighter(formatter,scorer);
			/**
			 * 创建一个摘要
			 */
			Fragmenter fragmenter = new SimpleFragmenter(10);
			highlighter.setTextFragmenter(fragmenter);
		/***********************************************************************/
		List<Article> articleList = new ArrayList<Article>();
		for(ScoreDoc scoreDoc:scoreDocs){
			float score = scoreDoc.score;
			System.out.println(score);//相关的得分
			Document document =  indexSearcher.doc(scoreDoc.doc);
			/*
			 * 使用高亮器
			 */
			/**
			 * 1、分词器
			 *      查找关键词
			 * 2、字段
			 *      在哪个字段上进行高亮
			 * 3、字段的内容
			 *      把字段的内容提取出来
			 */
			String titleText = highlighter.getBestFragment(LuncenUtil.analyzer, "title", document.get("title"));
			String contentText = highlighter.getBestFragment(LuncenUtil.analyzer, "content", document.get("content"));
			if(titleText!=null){
				article.setTitle(titleText);
			}
			if(contentText!=null){
				article.setContent(contentText);
			}
			articleList.add(article);
		}
		
		for(Article article:articleList){
			System.out.println(article.getId());
			System.out.println(article.getTitle());
			System.out.println(article.getContent());
		}
	}
}