9.lucene入门-排序和高亮

 1 package com.home.utils;
 2 
 3 import java.util.ArrayList;
 4 import java.util.List;
 5 
 6 import org.apache.lucene.document.Document;
 7 import org.apache.lucene.queryParser.MultiFieldQueryParser;
 8 import org.apache.lucene.queryParser.QueryParser;
 9 import org.apache.lucene.search.IndexSearcher;
10 import org.apache.lucene.search.MultiPhraseQuery;
11 import org.apache.lucene.search.Query;
12 import org.apache.lucene.search.ScoreDoc;
13 import org.apache.lucene.search.TopDocs;
14 import org.apache.lucene.util.Version;
15 import org.junit.Test;
16 
17 public class SortTest {
18     /**
19      * 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
20      * 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
21      * 
22      * @throws Exception
23      */
24     @Test
25     public void testSearchIndex() throws Exception {
26         IndexSearcher indexSearcher = new IndexSearcher(LuceneUtils.directory);
27         QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_30,
28                 new String[] { "title", "content" }, LuceneUtils.analyzer);
29 
30         Query query = queryParser.parse("lucene");
31         TopDocs topDocs = indexSearcher.search(query, 26);
32 
33         ScoreDoc[] scoreDocs = topDocs.scoreDocs;
34         List<Article> articleList = new ArrayList<Article>();
35         for (ScoreDoc scoreDoc : scoreDocs) {
36             float score = scoreDoc.score;
37             System.out.println(score);
38             Document document = indexSearcher.doc(scoreDoc.doc);
39              Article article = DocumentUtils.document2Article(document);
40                articleList.add(article);
41             
42         }
43         
44          for(Article article:articleList){
45                System.out.println(article.getId());
46                System.out.println(article.getTitle());
47                System.out.println(article.getContent());
48               }
49              }
50     }
51

 1 package com.home.utils;
 2 
 3 import java.util.ArrayList;
 4 import java.util.List;
 5 
 6 import org.apache.lucene.document.Document;
 7 import org.apache.lucene.queryParser.MultiFieldQueryParser;
 8 import org.apache.lucene.queryParser.QueryParser;
 9 import org.apache.lucene.search.IndexSearcher;
10 import org.apache.lucene.search.Query;
11 import org.apache.lucene.search.ScoreDoc;
12 import org.apache.lucene.search.TopDocs;
13 import org.apache.lucene.search.highlight.Formatter;
14 import org.apache.lucene.search.highlight.Fragmenter;
15 import org.apache.lucene.search.highlight.Highlighter;
16 import org.apache.lucene.search.highlight.QueryScorer;
17 import org.apache.lucene.search.highlight.Scorer;
18 import org.apache.lucene.search.highlight.SimpleFragmenter;
19 import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
20 import org.apache.lucene.util.Version;
21 import org.junit.Test;
22 
23 /**
24  * 高亮 * 使关键字变色 * 设置 * 使用 * 控制摘要的大小
25  */
26 public class HighlighterTest {
27     @Test
28     public void testSearchIndex() throws Exception {
29         IndexSearcher indexSearcher = new IndexSearcher(LuceneUtils.directory);
30         QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_30,
31                 new String[] { "title", "content" }, LuceneUtils.analyzer);
32         Query query = queryParser.parse("Lucene");
33         TopDocs topDocs = indexSearcher.search(query, 25);
34         ScoreDoc[] scoreDocs = topDocs.scoreDocs;
35 
36         /***********************************************************************/
37         /**
38          * 给关键字加上前缀和后缀
39          */
40         Formatter formatter = new SimpleHTMLFormatter("<font color='red'>",
41                 "</font>");
42 
43         /**
44          * scorer封装了关键字
45          */
46         Scorer scorer = new QueryScorer(query);
47 
48         Highlighter highlighter = new Highlighter(formatter, scorer);
49 
50         /**
51          * 创建一个摘要
52          */
53         // //构建Fragmenter对象,用于文档切片
54         Fragmenter fragmenter = new SimpleFragmenter(10);
55         highlighter.setTextFragmenter(fragmenter);
56 
57         /***********************************************************************/
58         List<Article> articleList = new ArrayList<Article>();
59         for (ScoreDoc scoreDoc : scoreDocs) {
60             float score = scoreDoc.score;
61             System.out.println(score);// 相关的得分
62             Document document = indexSearcher.doc(scoreDoc.doc);
63             Article article = DocumentUtils.document2Article(document);
64 
65             /*
66              * 使用高亮器
67              */
68             /**
69              * 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
70              */
71             // 它实现了从指定的原始文件中，提取检索关键字出现频率最高的一段文字作为摘要
72             String titleText = highlighter.getBestFragment(
73                     LuceneUtils.analyzer, "title", document.get("title"));
74 
75             String contentText = highlighter.getBestFragment(
76                     LuceneUtils.analyzer, "content", document.get("content"));
77 
78             if (titleText != null) {
79                 article.setTitle(titleText);
80             }
81             if (contentText != null) {
82                 article.setContent(contentText);
83             }
84             articleList.add(article);
85 
86         }
87         
88           for(Article article:articleList){
89                System.out.println(article.getId());
90                System.out.println(article.getTitle());
91                System.out.println(article.getContent());
92               }
93     }
94 }

posted on 2016-10-24 13:45 Sharpest 阅读(270) 评论(0) 收藏举报