1.lucene入門-準備Lucene的開發環境

1.1        準備lucene的開發環境
 

搭建lucene的開發環境，要準備lucene的jar包，要加入的jar包至少有：
 
1)    lucene-core-3.1.0.jar    (核心包)
 
2)    lucene-analyzers-3.1.0.jar    (分詞器)
 
3)    lucene-highlighter-3.1.0.jar    (高亮器)
 
4)    lucene-memory-3.1.0.jar      (高亮器)
 

 

1.

 1 package com.home.utils;
 2 
 3 public class Article {
 4     private Long id;
 5     private String title;
 6     private String content;
 7 
 8     public Long getId() {
 9         return id;
10     }
11 
12     public void setId(Long id) {
13         this.id = id;
14     }
15 
16     public String getTitle() {
17         return title;
18     }
19 
20     public void setTitle(String title) {
21         this.title = title;
22     }
23 
24     public String getContent() {
25         return content;
26     }
27 
28     public void setContent(String content) {
29         this.content = content;
30 
31     }
32 }

 

2.

  1 package com.home.utils;
  2 
  3 import java.io.File;
  4 import java.util.ArrayList;
  5 import java.util.List;
  6 
  7 import org.apache.lucene.analysis.Analyzer;
  8 import org.apache.lucene.analysis.standard.StandardAnalyzer;
  9 import org.apache.lucene.document.Document;
 10 import org.apache.lucene.document.Field;
 11 import org.apache.lucene.document.Field.Index;
 12 import org.apache.lucene.document.Field.Store;
 13 import org.apache.lucene.index.IndexWriter;
 14 import org.apache.lucene.index.IndexWriter.MaxFieldLength;
 15 import org.apache.lucene.queryParser.QueryParser;
 16 import org.apache.lucene.search.IndexSearcher;
 17 import org.apache.lucene.search.Query;
 18 import org.apache.lucene.search.ScoreDoc;
 19 import org.apache.lucene.search.TopDocs;
 20 import org.apache.lucene.store.Directory;
 21 import org.apache.lucene.store.FSDirectory;
 22 import org.apache.lucene.util.Version;
 23 import org.junit.Test;
 24 
 25 public class HelloWorld {
 26 
 27     @Test
 28     public void testCreateIndex() throws Exception {
 29         /**
 30          * 一、建立一個article對象，而且把信息存放進去 二、調用indexWriter的API把數據存放在索引庫中
 31          * 三、關閉indexWriter
 32          */
 33 
 34         // 建立一個article對象，而且把信息存放進去
 35         Article article = new Article();
 36         article.setId(1L);
 37         article.setTitle("lucene能夠作搜索引擎");
 38         article.setContent("baidu,google都是很好的搜索引擎");
 39         // 調用indexWriter的API把數據存放在索引庫中
 40         /**
 41          * 建立一個IndexWriter 參數三個 一、索引庫 指向索引庫的位置 二、分詞器
 42          */
 43 
 44         // 建立索引庫
 45         Directory directory = FSDirectory.open(new File("E:\\s"));
 46         // 建立分詞器
 47         Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
 48         IndexWriter indexWriter = new IndexWriter(directory, analyzer,
 49                 MaxFieldLength.LIMITED);
 50         // 把一個article對象轉化成document
 51         Document document = new Document();
 52         Field idField = new Field("id", article.getId().toString(), Store.YES,
 53                 Index.NOT_ANALYZED);
 54         Field titleField = new Field("title", article.getTitle(), Store.YES,
 55                 Index.ANALYZED);
 56         Field contentField = new Field("content", article.getContent(),
 57                 Store.YES, Index.ANALYZED);
 58         document.add(idField);
 59         document.add(titleField);
 60         document.add(contentField);
 61 
 62         indexWriter.addDocument(document);
 63         // 關閉indexWriter
 64         indexWriter.close();
 65     }
 66 
 67     @Test
 68     public void testSearchIndex() throws Exception {
 69 
 70         /**
 71          * 一、建立一個 IndexSearch對象 二、調用search方法進行檢索 三、輸出內容
 72          */
 73         // 建立索引庫
 74         Directory directory = FSDirectory.open(new File("E:\\s"));
 75 
 76         IndexSearcher indexSearcher = new IndexSearcher(directory);
 77         // 調用search方法進行檢索
 78 
 79         Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30);
 80         // 爲查詢分析器QueryParser 指定查詢字段和分詞器
 81         QueryParser queryParser = new QueryParser(Version.LUCENE_30, "content",
 82                 analyzer);
 83         // 查詢
 84         Query query = queryParser.parse("baidu");// 關鍵詞
 85         // 指向相匹配的搜索條件的前N個搜索結果
 86         TopDocs topDocs = indexSearcher.search(query, 2);
 87         // 根據關鍵詞查詢出來的總的記錄數
 88         int count = topDocs.totalHits;
 89         // 。ScoreDoc是表明一個結果的相關度得分與文檔編號等信息的對象。
 90         ScoreDoc[] scoreDocs = topDocs.scoreDocs;
 91         List<Article> articleList = new ArrayList<Article>();
 92 
 93         for (ScoreDoc scoreDoc : scoreDocs) {
 94             float score = scoreDoc.score;// 關鍵詞得分
 95             int index = scoreDoc.doc;// 索引的下標
 96             // 查詢文檔
 97             Document document = indexSearcher.doc(index);
 98             // 把document轉化成article
 99             Article article = new Article();
100             article.setId(Long.parseLong(document.get("id")));// document.getField("id").stringValue()
101             article.setTitle(document.get("title"));
102             article.setContent(document.get("content"));
103             articleList.add(article);
104 
105         }
106 
107         for (Article article : articleList) {
108             System.out.println(article.getId());
109             System.out.println(article.getTitle());
110             System.out.println(article.getContent());
111         }
112     }
113 }

 

如何把一個信息寫到索引庫中

讀取信息的過程