derby 的配置及jdbc连接

hive-default.xml



javax.jdo.option.ConnectionURL
jdbc:derby:;databaseName=metastore_db;create=true 表示使用嵌入式的derby，create为true表示自动创建数据库，数据库名为metastore_db
表示使用客服模式的derby，hadoopor为数据库名，192.168.0.3为derby服务端的IP地址，而4567为服务端的端口号
JDBC connect string for a JDBC metastore



javax.jdo.option.ConnectionDriverName
org.apache.derby.jdbc.EmbeddedDriver 表示使用嵌入式的derby
表示使用客服模式的derby
Driver class name for a JDBC metastore



对于嵌入式的derby要求在hive的lib目录下有文件derby.jar，而对于客服模式的derby要求有derbyclient.jar文件
如果是derby坏了，就得把metastore_db删除就好了，不过以前的数据也没了，我觉得测试的时候用derby还行，如果正式上线的话就不要启动嵌入式的了，直接启动并连接线上服务器就ok了。不然metastore_db一加锁，启动了hive --service hiveserver就不能启动hive 启动了hive就不能启动hive --service hiveserver。

说明：
测试的时候使用嵌入式还可以，正式环境一定要用服务端模式，否则出了问题就没法恢复了。
可以选择任何你熟悉的语言类作为JDBC连接：
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.hadoop.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);

}

Connection con = DriverManager.getConnection("jdbc:hive://localhost:10000/default", "", "");

Statement stmt = con.createStatement();

String tableName = "testHiveDriverTable";

stmt.executeQuery("drop table " + tableName);

ResultSet res = stmt.executeQuery("create table " + tableName + " (key int, value string)");

// show tables

String sql = "show tables '" + tableName + "'";

System.out.println("Running: " + sql);

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: /tmp/a.txt is a ctrl-A separated file with two fields per line

String filepath = "/tmp/a.txt";

sql = "load data local inpath '" + filepath + "' into table " + tableName;

System.out.println("Running: " + sql);

res = stmt.executeQuery(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));

}

}

}

接下来做的工作即是运行了：
# Then on the command-line
$ javac HiveJdbcClient.java

# To run the program in standalone mode, we need the following jars in the classpath
# from hive/build/dist/lib
# hive_exec.jar
# hive_jdbc.jar
# hive_metastore.jar
# hive_service.jar
# libfb303.jar
# log4j-1.2.15.jar
#
# from hadoop/build
# hadoop-*-core.jar
#
# To run the program in embedded mode, we need the following additional jars in the classpath
# from hive/build/dist/lib
# 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
#
# as well as hive/build/dist/conf

$ java -cp $CLASSPATH HiveJdbcClient

# Alternatively, you can run the following bash script, which will seed the data file
# and build your classpath before invoking the client.

#!/bin/bash
HADOOP_HOME=/your/path/to/hadoop
HIVE_HOME=/your/path/to/hive

echo -e '1\x01foo' > /tmp/a.txt
echo -e '2\x01bar' >> /tmp/a.txt

HADOOP_CORE={{ls $HADOOP_HOME/hadoop-*-core.jar}}
CLASSPATH=.:$HADOOP_CORE:$HIVE_HOME/conf

for i in ${HIVE_HOME}/lib/*.jar ; do
CLASSPATH=$CLASSPATH:$i
done

java -cp $CLASSPATH HiveJdbcClient


http://www.iteye.com/topic/1113849