Lucene入门案例
1. 新建maven工程导入lucene相关依赖
<properties> <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> <!-- mysql版本 --> <mysql.version>5.1.10</mysql.version> <!-- lucene版本 --> <lucene.version>4.10.3</lucene.version> </properties> <dependencies> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <version>1.18.6</version> <scope>provided</scope> </dependency> <!-- mysql数据库依赖 --> <dependency> <groupId>mysql</groupId> <artifactId>mysql-connector-java</artifactId> <version>${mysql.version}</version> </dependency> <!--lucene依赖包 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-core</artifactId> <version>${lucene.version}</version> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers-common</artifactId> <version>${lucene.version}</version> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-queryparser</artifactId> <version>${lucene.version}</version> </dependency> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <version>4.12</version> </dependency> <!-- ik分词器 --> <dependency> <groupId>com.janeluo</groupId> <artifactId>ikanalyzer</artifactId> <version>2012_u6</version> </dependency> </dependencies>
2.准备索引数据
package com.pomelo.dao.impl; import com.pomelo.dao.BookDao; import com.pomelo.domain.Book; import org.junit.Test; import java.sql.Connection; import java.sql.DriverManager; import java.sql.PreparedStatement; import java.sql.ResultSet; import java.util.ArrayList; import java.util.List; //准备文档数据 public class BookDaoImpl implements BookDao { @Override public List<Book> findAll() { List<Book> bookList = new ArrayList<>(); Connection connection = null; PreparedStatement statement = null; ResultSet resultSet = null; try { //1.加载驱动 Class.forName("com.mysql.jdbc.Driver"); //2. 创建连接 connection = DriverManager.getConnection("jdbc:mysql://localhost:3306/ssm", "root", "root"); //3. 创建预编译对象 statement = connection.prepareStatement("SELECT * from book"); //4. 执行查询,得到结果集 resultSet = statement.executeQuery(); //5. 循环遍历，放入list容器 while (resultSet.next()) { Book book = new Book(); book.setId(resultSet.getInt("id")); book.setBookName(resultSet.getString("bookname")); book.setPrice(resultSet.getFloat("price")); book.setPic(resultSet.getString("pic")); book.setBookDesc(resultSet.getString("bookdesc")); bookList.add(book); } } catch (Exception e) { e.printStackTrace(); } finally { //6. 释放资源 try { if (connection != null) { connection.close(); } } catch (Exception e) { e.printStackTrace(); } try { if (statement != null) { statement.close(); } } catch (Exception e) { e.printStackTrace(); } try { if (resultSet != null) { resultSet.close(); } } catch (Exception e) { e.printStackTrace(); } } return bookList; } //测试 @Test public void findAllTest() { List<Book> bookList = findAll(); System.out.println(bookList); } }
3.创建索引库
package com.pomelo.search; import com.pomelo.dao.BookDao; import com.pomelo.dao.impl.BookDaoImpl; import com.pomelo.domain.Book; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field.Store; import org.apache.lucene.document.TextField; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; import org.junit.Test; import org.wltea.analyzer.lucene.IKAnalyzer; import java.io.File; import java.io.IOException; import java.util.ArrayList; import java.util.List; //2. 创建索引 public class IndexManagerDemo { @Test public void createIndex() throws IOException { //1. 采集文档数据 BookDao bookDao = new BookDaoImpl(); List<Book> bookList = bookDao.findAll(); //2. 创建文档对象 List<Document> documentList = new ArrayList<>(); for (Book book : bookList) { Document document = new Document(); /** * IntField整型类型域，TextField文本类型域，FloatField浮点型类型域 * 参数1：域名--对应数据库中字段名 * 参数2：域值 * 参数3：是否存储--是否需要将该域对应的值存储到文档中 */ document.add(new TextField("bookId", book.getId() + "", Store.YES)); document.add(new TextField("bookName", book.getBookName(), Store.YES)); document.add(new TextField("bookPrice", book.getPrice() + "", Store.YES)); document.add(new TextField("bookPic", book.getPic(), Store.YES)); document.add(new TextField("bookDesc", book.getBookDesc(), Store.YES)); documentList.add(document); } //3. 创建分词器 Analyzer analyzer = new IKAnalyzer(); //4、创建文档索引配置对象 IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer); //5、创建存放索引目录Directory，指定索引存放路径 File file = new File("C:\\tmp\\lucene\\book1"); Directory directory = FSDirectory.open(file); //6、创建索引编写器 IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); //7、利用索引编写器写入文档到索引目录 for (Document document : documentList) { //把文档对象写入到索引库中 indexWriter.addDocument(document); } //8. 释放资源 indexWriter.close(); } }
4.检索索引
package com.pomelo.search; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.document.Document; import org.apache.lucene.index.DirectoryReader; import org.apache.lucene.index.IndexReader; import org.apache.lucene.queryparser.classic.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.store.Directory; import org.apache.lucene.store.FSDirectory; import org.junit.Test; import org.wltea.analyzer.lucene.IKAnalyzer; import java.io.File; //3. 检索索引 public class SearchManagerDemo { @Test public void searchIndex() throws Exception { //1. 创建分词器 Analyzer analyzer = new IKAnalyzer(); //2、创建查询对象Query //2.1、创建查询分析器；参数1：默认查询的域，参数2：分词器 QueryParser queryParser = new QueryParser("bookName", analyzer); //2.2、创建Query对象 Query query = queryParser.parse("java"); //3、创建存放索引目录Directory，指定索引存放路径 Directory directory = FSDirectory.open(new File("C:\\tmp\\lucene\\book1")); //4、创建索引读对象IndexReader IndexReader indexReader = DirectoryReader.open(directory); //5、创建索引搜索对象IndexSearcher，执行搜索，返回结果 IndexSearcher indexSearcher = new IndexSearcher(indexReader); /** * 参数1：查询对象 * 参数2：查询前n个文档 * 返回结果：得分文档（包含文档数组，总的命中数） */ TopDocs topDocs = indexSearcher.search(query, 10); System.out.println("符合本次查询的总命中文档数为：" + topDocs.totalHits); //6、处理搜索结果 ScoreDoc[] scoreDocs = topDocs.scoreDocs; for (ScoreDoc scoreDoc : scoreDocs) { System.out.println("文档在Lucene中的id为：" + scoreDoc.doc + "；文档分值为：" + scoreDoc.score); //根据lucene中的文档id查询到文档 Document document = indexSearcher.doc(scoreDoc.doc); System.out.println("文档id为：" + document.get("bookId")); System.out.println("名称为：" + document.get("bookName")); System.out.println("价格为：" + document.get("bookPrice")); System.out.println("图片为：" + document.get("bookPic")); System.out.println("描述为：" + document.get("bookDesc")); System.out.println("---------------------------------------"); } //7、释放资源 indexReader.close(); } }
