来学学Hive JDBC操作流程？

一：启动Hadoop

1. core-site.xml 配置代理用户属性

特别注意：hadoop.proxyuser.<服务器用户名>.hosts 和 hadoop.proxyuser.<服务器用户名>.groups这两个属性，服务器用户名是hadoop所在的机器的登录的名字，根据自己实际的登录名来配置。这里我的电脑用户名为mengday。

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
 <property>
  <name>hadoop.tmp.dir</name>
  <value>file:/usr/local/Cellar/hadoop/3.2.1/libexec/tmp</value>
 </property>
 <property>
     <name>fs.defaultFS</name>
     <value>hdfs://localhost:8020</value>
  </property>
  <property>
      <name>hadoop.proxyuser.mengday.hosts</name>
      <value>*</value>
  </property>
  <property>
      <name>hadoop.proxyuser.mengday.groups</name>
      <value>*</value>
  </property>    
</configuration>

2. 启动hadoop

> cd /usr/local/Cellar/hadoop/3.2.1/sbin
> ./start-all.sh
> jps

启动成功后注意查看DataNode节点是否启动起来, 经常遇到DataNode节点启动不成功。

二：配置hive-site.xml

Java是通过beeline来连接Hive的。启动beeline最重要的就是配置好hive-site.xml。

其中javax.jdo.option.ConnectionURL涉及到一个数据库，最好重新删掉原来的metastore数据库然后重新创建一个并初始化一下。

mysql> create database metastore;

> cd /usr/local/Cellar/hive/3.1.2/libexec/bin
> schematool -initSchema -dbType mysql

hive-site.xml

<configuration>
　　<property>
        <name>hive.metastore.local</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.metastore.uris</name>
        <value>thrift://localhost:9083</value>
        <description>Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore.</description>
      </property>
    <property>
        <name>javax.jdo.option.ConnectionURL</name>
        <value>jdbc:mysql://localhost:3306/metastore?characterEncoding=UTF-8&createDatabaseIfNotExist=true</value>
    </property>

    <property>
        <name>javax.jdo.option.ConnectionDriverName</name>
        <value>com.mysql.cj.jdbc.Driver</value>
    </property>
　　<!--mysql用户名-->
    <property>
        <name>javax.jdo.option.ConnectionUserName</name>
        <value>root</value>
    </property>
　　<!--mysql密码-->
　　<property>
        <name>javax.jdo.option.ConnectionPassword</name>
        <value>root123</value>
    </property>

 <!-- hive用来存储不同阶段的map/reduce的执行计划的目录，同时也存储中间输出结果
 ，默认是/tmp/<user.name>/hive,我们实际一般会按组区分，然后组内自建一个tmp目录存>储 -->

    <property>
        <name>hive.exec.local.scratchdir</name>
        <value>/tmp/hive</value>
    </property>

    <property>
        <name>hive.downloaded.resources.dir</name>
            <value>/tmp/hive</value>
    </property>

    <property>
        <name>hive.metastore.warehouse.dir</name>
        <value>/data/hive/warehouse</value>
    </property>

    <property>
        <name>hive.metastore.event.db.notification.api.auth</name>
        <value>false</value>
    </property>
    <property>
        <name>hive.server2.active.passive.ha.enable</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.server2.transport.mode</name>
        <value>binary</value>
        <description>
          Expects one of [binary, http].
          Transport mode of HiveServer2.
        </description>
    </property>
    <property>
        <name>hive.server2.logging.operation.log.location</name>
        <value>/tmp/hive</value>
    </property>
    <property>
        <name>hive.hwi.listen.host</name>
        <value>0.0.0.0</value>
        <description>This is the host address the Hive Web Interface will listen on</description>
    </property>

    <property>
        <name>hive.server2.webui.host</name>
        <value>0.0.0.0</value>
        <description>The host address the HiveServer2 WebUI will listen on</description>
    </property>

</configuration>

三：启动metastore

在启动beeline之前需要先启动hiveserver2，而在启动hiveserver2之前需要先启动metastore。metastore默认的端口为9083。

> cd /usr/local/Cellar/hive/3.1.2/bin
> hive --service metastore &

启动过一定确认一下启动是否成功。

四：启动hiveserver2

> cd /usr/local/Cellar/hive/3.1.2/bin
> hive --service hiveserver2 &

hiveserver2默认的端口为10000，启动之后一定要查看10000端口是否存在，配置有问题基本上10000端口都启动不成功。10000端口存在不存在是启动beeline的关键。

五：启动beeline

> cd /usr/local/Cellar/hive/3.1.2/bin
> beeline -u jdbc:hive2://localhost:10000/default -n mengday -p

• -u: 连接的url，jdbc:hive2://<主机名或IP>:<端口默认>/<数据库名>，端口号默认10000 可通过 ```hiveserver2 --hiveconf hive.server2.thrift.port=14000 修改端口号，default是自带的数据库
• -n: hive所在的那台服务器的登录账号名称, 这里是我Mac机器的登录用户名mengday, 这里的名字要和core-site.xml中的hadoop.proxyuser.mengday.hosts和hadoop.proxyuser.mengday.groups中mengday保持一致。
• -p: 密码，用户名对应的密码

看到0: jdbc:hive2://localhost:10000/default>就表示启动成功了。

六：Hive JDBC

1. 引入依赖

<dependency>
   <groupId>org.apache.hive</groupId>
   <artifactId>hive-jdbc</artifactId>
   <version>3.1.2</version>
</dependency>

2. 准备数据

/data/employee.txt

1,zhangsan,28,60.66,2020-02-01 10:00:00,true,eat#drink,k1:v1#k2:20,s1#c1#s1#1
2,lisi,29,60.66,2020-02-01 11:00:00,false,play#drink,k3:v3#k4:30,s2#c2#s1#2

3. Java

import java.sql.*;

public class HiveJdbcClient {
     
    private static String url = "jdbc:hive2://localhost:10000/default";
    private static String driverName = "org.apache.hive.jdbc.HiveDriver";
    private static String user = "mengday";
    private static String password = "user对应的密码";

    private static Connection conn = null;
    private static Statement stmt = null;
    private static ResultSet rs = null;

    static {
     
        try {
     
            Class.forName(driverName);
            conn = DriverManager.getConnection(url, user, password);
            stmt = conn.createStatement();
        } catch (Exception e) {
     
            e.printStackTrace();
        }
    }

    public static void init() throws Exception {
     
        stmt.execute("drop database if exists hive_test");
        stmt.execute("create database hive_test");
        rs = stmt.executeQuery("show databases");
        while (rs.next()) {
     
            System.out.println(rs.getString(1));
        }

        stmt.execute("drop table if exists employee");
        String sql = "create table if not exists employee(" +
                " id bigint, " +
                " username string, " +
                " age tinyint, " +
                " weight decimal(10, 2), " +
                " create_time timestamp, " +
                " is_test boolean, " +
                " tags array, " +
                " ext map, " +
                " address struct " +
                " ) " +
                " row format delimited " +
                " fields terminated by ',' " +
                " collection items terminated by '#' " +
                " map keys terminated by ':' " +
                " lines terminated by '\n'";
        stmt.execute(sql);

        rs = stmt.executeQuery("show tables");
        while (rs.next()) {
     
            System.out.println(rs.getString(1));
        }

        rs = stmt.executeQuery("desc employee");
        while (rs.next()) {
     
            System.out.println(rs.getString(1) + "\t" + rs.getString(2));
        }
    }

    private static void load() throws Exception {
     
        // 加载数据
        String filePath = "/data/employee.txt";
        stmt.execute("load data local inpath '" + filePath + "' overwrite into table employee");

        // 查询数据
        rs = stmt.executeQuery("select * from employee");
        while (rs.next()) {
     
            System.out.println(rs.getLong("id") + "\t"
                    + rs.getString("username") + "\t"
                    + rs.getObject("tags") + "\t"
                    + rs.getObject("ext") + "\t"
                    + rs.getObject("address")
            );
        }
    }

    private static void close() throws Exception {
     
        if ( rs != null) {
     
            rs.close();
        }
        if (stmt != null) {
     
            stmt.close();
        }
        if (conn != null) {
     
            conn.close();
        }
    }

    public static void main(String[] args) throws Exception {
     
        init();

        load();

        close();
    }
}