Lucene-排序+高亮

最新推荐文章于 2023-09-01 19:32:45 发布

南栀_倾寒

最新推荐文章于 2023-09-01 19:32:45 发布

阅读量627

点赞数

分类专栏： lucene

本文链接：https://blog.csdn.net/xinxinqiu/article/details/21339201

版权

lucene 专栏收录该内容

11 篇文章 0 订阅

订阅专栏

public class SortTest {
	/**
	 * 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(LuceneUtils.directory);
		QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_30, new String[]{"title","content"}, LuceneUtils.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);
			Article article = DocumentUtils.document2Article(document);
			articleList.add(article);
		}
		
		for(Article article:articleList){
			System.out.println(article.getId());
			System.out.println(article.getTitle());
			System.out.println(article.getContent());
		}
	}
}

/**
 * 高亮
 *    * 使关键字变色
 *       *  设置
 *       *  使用
 *    * 控制摘要的大小
 */
public class HighlighterTest {
	@Test
	public void testSearchIndex() throws Exception{
		IndexSearcher indexSearcher = new IndexSearcher(LuceneUtils.directory);
		QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_30, new String[]{"title","content"}, LuceneUtils.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);
			Article article = DocumentUtils.document2Article(document);
			/*
			 * 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(LuceneUtils.analyzer, "title", document.get("title"));
			String contentText = highlighter.getBestFragment(LuceneUtils.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());
		}
	}
}