HIVE学习笔记：HiveServer2，调用HIVE的JavaAPI

首先修改配置文件hive-site.xml：

<property>
<name>hive.server2.thrift.bind.host</name>
<value>192.168.200.100</value>
<description>Bind host on which to run the HiveServer2 Thrift service.</description>
</property>
<property>

启动hiveserver2：

hive --service metastore &
hiveserver2 &

官方给出的示例代码：

package HIVEDemo;
import java.sql.SQLException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;
import java.sql.DriverManager;

public class HiveJdbcClient {
private static String driverName = "org.apache.hive.jdbc.HiveDriver";

/**
* @param args
* @throws SQLException
*/
public static void main(String[] args) throws SQLException {
try {
Class.forName(driverName);
} catch (ClassNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
System.exit(1);
}
//程序若在远程机器上执行则指定ip，本地执行可使用localhost，用户名与密码为Linux账户
Connection con = DriverManager.getConnection("jdbc:hive2://192.168.200.100:10000/default", "daya", "123456");
Statement stmt = con.createStatement();
//创建表
String tableName = "testHiveDriverTable";
stmt.execute("drop table if exists " + tableName);
stmt.execute("create table " + tableName + " (key int, value string)");
// show tables
String sql = "show tables '" + tableName + "'";
System.out.println("Running: " + sql);
ResultSet res = stmt.executeQuery(sql);
if (res.next()) {
System.out.println(res.getString(1));
}
// describe table
sql = "describe " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(res.getString(1) + "\t" + res.getString(2));
}

// load data into table
// NOTE: filepath has to be local to the hive server
// NOTE:本地文件每行应有两个条目
String filepath = "/home/daya/test/students.txt";
sql = "load data local inpath '" + filepath + "' into table " + tableName;
System.out.println("Running: " + sql);
stmt.execute(sql);

// select * query
sql = "select * from " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(String.valueOf(res.getInt(1)) + "\t" + res.getString(2));
}

// regular hive query
sql = "select count(1) from " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(res.getString(1));
}
}
}

官方给出的代码依赖包：

# To run the program using remote hiveserver in non-kerberos mode, we need the following jars in the classpath
# from hive/build/dist/lib
#     hive-jdbc*.jar
#     hive-service*.jar
#     libfb303-0.9.0.jar
#     libthrift-0.9.0.jar
#     log4j-1.2.16.jar
#     slf4j-api-1.6.1.jar
#     slf4j-log4j12-1.6.1.jar
#     commons-logging-1.0.4.jar
#
#
# To run the program using kerberos secure mode, we need the following jars in the classpath
#     hive-exec*.jar
#     commons-configuration-1.6.jar (This is not needed with Hadoop 2.6.x and later).
#  and from hadoop
#     hadoop-core*.jar (use hadoop-common*.jar for Hadoop 2.x)
#
# To run the program in embedded mode, we need the following additional jars in the classpath
# from hive/build/dist/lib
#     hive-exec*.jar
#     hive-metastore*.jar
#     antlr-runtime-3.0.1.jar
#     derby.jar
#     jdo2-api-2.1.jar
#     jpox-core-1.2.2.jar
#     jpox-rdbms-1.2.2.jar
# and from hadoop/build
#     hadoop-core*.jar
# as well as hive/build/dist/conf, any HIVE_AUX_JARS_PATH set,
# and hadoop jars necessary to run MR jobs (eg lzo codec)

我是在windows下的eclipse中执行，所以所需依赖包如下图所示：



本地测试文本内容为：



程序输出为：



不知为毛程序无法识别文本内容，原因暂时不明。