本文节选自《Netkiller Java 手札》

作者：netkiller 他的网站: http://www.netkiller.cn, QQ: 13721218

5.29. Spring boot with Apache Hive

5.29.1. Maven

<dependency><groupId>org.springframework.boot</groupId><artifactId>spring-boot-starter-jdbc</artifactId></dependency><dependency><groupId>org.springframework.data</groupId><artifactId>spring-data-hadoop</artifactId><version>2.5.0.RELEASE</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.hive/hive-jdbc --><dependency><groupId>org.apache.hive</groupId><artifactId>hive-jdbc</artifactId><version>2.3.0</version><exclusions><exclusion><groupId>org.eclipse.jetty.aggregate</groupId><artifactId>*</artifactId></exclusion></exclusions></dependency><dependency><groupId>org.apache.tomcat</groupId><artifactId>tomcat-jdbc</artifactId><version>8.5.20</version></dependency>

5.29.2. application.properties

hive 数据源配置项

hive.url=jdbc:hive2://172.16.0.10:10000/default
hive.driver-class-name=org.apache.hive.jdbc.HiveDriver
hive.username=hadoop
hive.password=

用户名是需要具有 hdfs 写入权限，密码可以不用写

如果使用 yaml 格式 application.yml 配置如下

hive:  url: jdbc:hive2://172.16.0.10:10000/defaultdriver-class-name: org.apache.hive.jdbc.HiveDriver type: com.alibaba.druid.pool.DruidDataSourceusername: hivepassword: hive

5.29.3. Configuration

package cn.netkiller.config;import org.apache.tomcat.jdbc.pool.DataSource;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Qualifier;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.core.env.Environment;
import org.springframework.jdbc.core.JdbcTemplate;@Configuration
public class HiveConfig {private static final Logger logger = LoggerFactory.getLogger(HiveConfig.class);@Autowiredprivate Environment env;@Bean(name = "hiveJdbcDataSource")@Qualifier("hiveJdbcDataSource")public DataSource dataSource() {DataSource dataSource = new DataSource();dataSource.setUrl(env.getProperty("hive.url"));dataSource.setDriverClassName(env.getProperty("hive.driver-class-name"));dataSource.setUsername(env.getProperty("hive.username"));dataSource.setPassword(env.getProperty("hive.password"));logger.debug("Hive DataSource");return dataSource;}@Bean(name = "hiveJdbcTemplate")public JdbcTemplate hiveJdbcTemplate(@Qualifier("hiveJdbcDataSource") DataSource dataSource) {return new JdbcTemplate(dataSource);}
}

你也可以使用 DruidDataSource

package cn.netkiller.api.config; @Configuration
public class HiveDataSource {  @Autowired  private Environment env;  @Bean(name = "hiveJdbcDataSource")@Qualifier("hiveJdbcDataSource")public DataSource dataSource() {DruidDataSource dataSource = new DruidDataSource();dataSource.setUrl(env.getProperty("hive.url"));dataSource.setDriverClassName(env.getProperty("hive.driver-class-name"));dataSource.setUsername(env.getProperty("hive.username"));dataSource.setPassword(env.getProperty("hive.password"));return dataSource;}@Bean(name = "hiveJdbcTemplate") public JdbcTemplate hiveJdbcTemplate(@Qualifier("hiveJdbcDataSource") DataSource dataSource) {return new JdbcTemplate(dataSource);}}

5.29.4. CURD 操作实例

Hive 数据库的增删插改操作与其他数据库没有什么不同。

package cn.netkiller.web;import java.util.Iterator;
import java.util.List;
import java.util.Map;import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Qualifier;
import org.springframework.jdbc.core.JdbcTemplate;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.servlet.ModelAndView;@Controller
@RequestMapping("/hive")
public class HiveController {private static final Logger logger = LoggerFactory.getLogger(HiveController.class);@Autowired@Qualifier("hiveJdbcTemplate")private JdbcTemplate hiveJdbcTemplate;@RequestMapping("/create")public ModelAndView create() {StringBuffer sql = new StringBuffer("create table IF NOT EXISTS ");sql.append("HIVE_TEST");sql.append("(KEY INT, VALUE STRING)");sql.append("PARTITIONED BY (CTIME DATE)"); // 分区存储sql.append("ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' "); // 定义分隔符sql.append("STORED AS TEXTFILE"); // 作为文本存储// drop table// StringBuffer sql = new StringBuffer("DROP TABLE IF EXISTS ");// sql.append("HIVE_TEST1");logger.info(sql.toString());hiveJdbcTemplate.execute(sql.toString());return new ModelAndView("index");}@RequestMapping("/insert")public String insert() {hiveJdbcTemplate.execute("insert into hive_test(key, value) values('Neo','Chen')");return "Done";}@RequestMapping("/select")public String select() {String sql = "select * from HIVE_TEST";List<Map<String, Object>> rows = hiveJdbcTemplate.queryForList(sql);Iterator<Map<String, Object>> it = rows.iterator();while (it.hasNext()) {Map<String, Object> row = it.next();System.out.println(String.format("%s\t%s", row.get("key"), row.get("value")));}return "Done";}@RequestMapping("/delete")public String delete() {StringBuffer sql = new StringBuffer("DROP TABLE IF EXISTS ");sql.append("HIVE_TEST");logger.info(sql.toString());hiveJdbcTemplate.execute(sql.toString());return "Done";}
}