IDEA连接HBase
Posted curtime
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了IDEA连接HBase相关的知识,希望对你有一定的参考价值。
新建maven工程
打开pom.xml添加hbase需要的依赖
<dependency> <groupId>org.apache.hbase</groupId> <artifactId>hbase-client</artifactId> <version>2.3.5</version> </dependency> <dependency> <groupId>org.apache.hbase</groupId> <artifactId>hbase-server</artifactId> <version>2.3.5</version> </dependency>
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class HBase
public static void main(String[] args)
//配置HBase信息,连接HBase数据库
Configuration conf = HBaseConfiguration.create();
conf.set(HConstants.HBASE_DIR, "hdfs://192.168.153.146:9000/hbase");
//给配置类添加配置
conf.set(HConstants.ZOOKEEPER_QUORUM, "192.168.153.146");
conf.set(HConstants.CLIENT_PORT_STR, "2181");
try
//获取连接
Connection conn = ConnectionFactory.createConnection(conf);
System.out.println(conn);
Table stuTB = conn.getTable(TableName.valueOf("bigdata:student"));
Put put = new Put(Bytes.toBytes("rowkey11"));
put.addColumn("baseinfo".getBytes(), "name".getBytes(), "guo".getBytes());
put.addColumn("baseinfo".getBytes(), "age".getBytes(), "18".getBytes());
put.addColumn("baseinfo".getBytes(), "birthday".getBytes(), "1994-10-06".getBytes());
put.addColumn("schoolinfo".getBytes(), "name".getBytes(), "西华一高".getBytes());
put.addColumn("schoolinfo".getBytes(), "address".getBytes(), "西华".getBytes());
stuTB.put(put);
catch (IOException e)
e.printStackTrace();
import static org.junit.Assert.assertTrue;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
/**
* Unit test for simple App.
*/
public class AppTest
static Configuration config = null;
private Connection conn = null;
private Admin admin;
@Before//测试之前先加载
public void init() throws IOException
System.out.println("执行init()");
config = HBaseConfiguration.create();
config.set(HConstants.HBASE_DIR, "hdfs://192.168.153.147:9000/hbase");
config.set(HConstants.ZOOKEEPER_QUORUM, "192.168.153.147");
config.set(HConstants.CLIENT_PORT_STR, "2181");
conn = ConnectionFactory.createConnection(config);
admin = conn.getAdmin();
@Test
public void test1()
System.out.println(conn);
System.out.println("执行test1()");
/**
* 创建命名空间
*/
@Test
public void createNameSpace() throws IOException
NamespaceDescriptor kb21 = NamespaceDescriptor.create("kb21").build();
try
admin.createNamespace(kb21);
catch (IOException e)
e.printStackTrace();
/**
* 创建表
*/
@Test
public void createTable() throws IOException
//创建表的描述类
TableName tableName = TableName.valueOf("bigdata:car2");
HTableDescriptor desc = new HTableDescriptor(tableName);
//创建列族的描述
HColumnDescriptor family1 = new HColumnDescriptor("info");
desc.addFamily(family1);
admin.createTable(desc);
/**
* 删除表
*
* @throws IOException
*/
@Test
public void createTable2() throws IOException
admin.disableTable(TableName.valueOf("bigdata:car"));
admin.deleteTable(TableName.valueOf("bigdata:car"));
@Test
public void getAllNamespace() throws IOException
String[] nps = admin.listNamespaces();
String s = Arrays.toString(nps);
System.out.println(s);
/**
*
*/
@Test
public void getAllNamespace2() throws IOException
List<TableDescriptor> tableDesc = admin.listTableDescriptorsByNamespace("kb21".getBytes());
System.out.println(tableDesc.toString());
@After
public void close() throws IOException
System.out.println("执行close()");
if (admin != null)
admin.close();
if (conn != null)
conn.close();
@Test
public void insertData() throws IOException
Table table = conn.getTable(TableName.valueOf("bigdata:car2"));
Put put2 = new Put(Bytes.toBytes("model3"));
put2.addColumn("info".getBytes(), "brand".getBytes(), "TSLA".getBytes());
put2.addColumn("info".getBytes(), "country".getBytes(), "美国".getBytes());
put2.addColumn("info".getBytes(), "model".getBytes(), "轿车".getBytes());
put2.addColumn("info".getBytes(), "price".getBytes(), "23万".getBytes());
put2.addColumn("info".getBytes(), "data".getBytes(), "1994-10-01".getBytes());
Put put3 = new Put(Bytes.toBytes("modely"));
put3.addColumn("info".getBytes(), "brand".getBytes(), "TSLA".getBytes());
put3.addColumn("info".getBytes(), "country".getBytes(), "美国".getBytes());
put3.addColumn("info".getBytes(), "model".getBytes(), "suv".getBytes());
put3.addColumn("info".getBytes(), "price".getBytes(), "40万".getBytes());
put3.addColumn("info".getBytes(), "data".getBytes(), "1998-10-01".getBytes());
ArrayList<Put> list = new ArrayList<>();
list.add(put2);
list.add(put3);
table.put(list);
/**
* get查询
*/
@Test
public void queryData() throws IOException
Table table = conn.getTable(TableName.valueOf("kb21:student"));
Get get = new Get(Bytes.toBytes("student1"));
Result result = table.get(get);
byte[] value = result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name"));
System.out.println("姓名:" + Bytes.toString(value));
value = result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("school"));
System.out.println("学校:" + Bytes.toString(value));
@Test
public void scanData() throws IOException
Table table = conn.getTable(TableName.valueOf("kb21:student"));
Scan scan = new Scan();
ResultScanner scanner = table.getScanner(scan);
for (Result result : scanner)
byte[] value = result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name"));
System.out.println("姓名:" + Bytes.toString(value));
value = result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("school"));
System.out.println("学校:" + Bytes.toString(value));
System.out.println(Bytes.toString(result.getRow()));
Hive连接Hbase
修改 /opt/soft/hive312/conf 下的 hive-site.xml
<property>
<name>hive.zookeeper.quorum</name>
<value>192.168.153.147</value>
</property><property>
<name>hbase.zookeeper.quorum</name>
<value>192.168.153.147</value>
</property><property>
<name>hive.aux.jars.path</name>
<value>file:///opt/soft/hive312/lib/hive-hbase-handler-3.1.2.jar,file:///opt/soft/hive312/lib/zookeeper-3.4.6.jar,file:///opt/soft/hive312/lib/hbase-client-2.3.5.jar,file:///opt/soft/hive312/lib/hbase-common-2.3.5-tests.jar,file:///opt/soft/hive312/lib/hbase-server-2.3.5.jar,file:///opt/soft/hive312/lib/hbase-common-2.3.5.jar,file:///opt/soft/hive312/lib/hbase-protocol-2.3.5.jar,file:///opt/soft/hive312/lib/htrace-core-3.2.0-incubating.jar</value>
</property>
把hbase jar包拷贝到hive
[root@guo147 conf]# cp /opt/soft/hbase235/lib/* /opt/soft/hive312/lib/
(会有重复的选 n 不覆盖)
删除hive guava-11.0.2.jar
[root@guo147 conf]# find ../lib/guava*
../lib/guava-11.0.2.jar
../lib/guava-27.0-jre.jar
[root@guo147 conf]# rm -rf ../lib/guava-11.0.2.jar
删除hbase guava-11.0.2.jar
[root@guo147 lib]# pwd
/opt/soft/hbase235/lib[root@guo147 lib]# rm -rf guava-11.0.2.jar
//拷贝
[root@guo147 lib]# cp /opt/soft/hive312/lib/guava-27.0-jre.jar ./
用idea操作hbase数据库,并映射到hive
依赖条件:需要有Hadoop,hive,zookeeper,hbase环境
映射:每一个在 Hive 表中的域都存在于 HBase 中,而在 Hive 表中不需要包含所有HBase 中的列。HBase 中的 RowKey 对应到 Hive 中为选择一个域使用 :key 来对应,列族(cf:)映射到 Hive 中的其它所有域,列为(cf:cq)
配置映射环境
一:先关闭所有服务
[root@siwen ~]# stop-hbase.sh -----关闭hbase
[root@siwen ~]# zkServer.sh stop -----关闭zookeeper
[root@siwen ~]# stop-alll.sh -----关闭hadoop
二:配置文件
1,修改host文件:
C:\\Windows\\System32\\drivers\\etc在此目录下的hosts文件把此机器的ip和hostname加入进去
2,修改hive-site.xml
[root@siwen ~]# cd /opt/soft/hive312/conf/
[root@siwen conf]# vim ./hive-site.xml
加入下面几行
<property>
<name>hive.zookeeper.quorum</name>
<value>192.168.255.159</value>
</property>
<property>
<name>hbase.zookeeper.quorum</name>
<value>192.168.255.159</value>
</property>
<property>
<name>hive.aux.jars.path</name>
<value>file:///opt/soft/hive312/lib/hive-hbase-handler-3.1.2.jar,file:///opt/soft/hive312/lib/zookeeper-3.4.6.jar,file:///opt/soft/hive312/lib/hbase-client-2.3.5.jar,file:///opt/soft/hive312/lib/hbase-common-2.3.5-tests.jar,file:///opt/soft/hive312/lib/hbase-server-2.3.5.jar,file:///opt/soft/hive312/lib/hbase-common-2.3.5.jar,file:///opt/soft/hive312/lib/hbase-protocol-2.3.5.jar,file:///opt/soft/hive312/lib/htrace-core-3.2.0-incubating.jar</value>
</property>
3,拷贝jar包
①将hbase235/lib目录下所有的jar包都拷贝到hive下面
[root@siwen conf]# cp /opt/soft/hbase235/lib/* /opt/soft/hive312/lib/
是否覆盖内容的时候,可以输入n,不覆盖;或者覆盖了也没问题
②统一guava文件
[root@siwen lib]# find ../lib/guava* -------查看所有的guava文件
[root@siwen lib]# rm -rf ../lib/guava-11.0.2.jar -------删除11版本的
[root@siwen conf]# cd /opt/soft/hbase235/lib/
[root@siwen lib]# pwd
/opt/soft/hbase235/lib
[root@siwen lib]# cp /opt/soft/hive312/lib/guava-27.0-jre.jar ./ -----把hive的guava文件拷贝给hbase
三:启动服务
#启动hadoop
[root@siwen lib]# start-all.sh
#启动zookeeper
[root@siwen lib]# zkServer.sh start
#启动hbase
[root@siwen lib]# start-hbase.sh
#启动hive
[root@siwen lib]# nohup hive --service metastore &
[root@siwen lib]# nohup hive --service hiveserver2 &
开始使用idea创建maven工程
在pom.xml 里面添加依赖
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>2.3.5</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>2.3.5</version>
</dependency>
1,编写初始化方法:配置hbase信息,连接数据库
//定义一个config,用于获取配置对象
static Configuration config = null;
//获取连接
private Connection conn = null;
Admin admin = null;
@Before
public void init() throws IOException
//配置hbase信息,连接hbase数据库
config = HBaseConfiguration.create();
config.set(HConstants.HBASE_DIR, "hdfs://192.168.255.159:9000/hbase");
config.set(HConstants.ZOOKEEPER_QUORUM, "192.168.255.159");
config.set(HConstants.CLIENT_PORT_STR, "2181");
//hbase连接工厂
conn = ConnectionFactory.createConnection(config);
//拿到admin
admin = conn.getAdmin();
2,编写关闭方法
@After
public void close() throws IOException
System.out.println("执行close()方法");
if (admin!=null)
admin.close();
if (conn!=null)
conn.close();
3,编写创建命名空间方法
@Test
public void createNameSpace() throws IOException
NamespaceDescriptor bigdata = NamespaceDescriptor.create("bigdata").build();
#执行创建对象
admin.createNamespace(bigdata);
4,编写创建表的方法
@Test
public void createTable() throws IOException
//创建表的描述类
TableName tableName = TableName.valueOf("bigdata:student");
//获取表格描述器
HTableDescriptor desc = new HTableDescriptor(tableName);
//创建列族的描述,添加列族
HColumnDescriptor family1 = new HColumnDescriptor("info1");
HColumnDescriptor family2 = new HColumnDescriptor("info2");
desc.addFamily(family1);
desc.addFamily(family2);
admin.createTable(desc);*/
5,编写查看表结构的方法
@Test
public void getAllNamespace() throws IOException
List<TableDescriptor> tableDesc = admin.listTableDescriptorsByNamespace("bigdata".getBytes());
System.out.println(tableDesc.toString());
6,编写插入数据方法
@Test
public void insertData() throws IOException
//获取表的信息
Table table = conn.getTable(TableName.valueOf("bigdata:student"));
//设置行键
Put put = new Put(Bytes.toBytes("student1"));
//设置列的标识以及列值
put.addColumn("info1".getBytes(), "name".getBytes(), "zs".getBytes());
put.addColumn("info2".getBytes(), "school".getBytes(), "xwxx".getBytes());
//执行添加
table.put(put);
//使用集合添加数据
Put put2 = new Put(Bytes.toBytes("student2"));
put2.addColumn("info1".getBytes(), "name".getBytes(), "zss".getBytes());
put2.addColumn("info2".getBytes(), "school".getBytes(), "xwxx".getBytes());
Put put3 = new Put(Bytes.toBytes("student3"));
put3.addColumn("info1".getBytes(), "name".getBytes(), "zsr".getBytes());
put3.addColumn("info2".getBytes(), "school".getBytes(), "xwxx".getBytes());
List<Put> list = new ArrayList<>();
list.add(put2);
list.add(put3);
table.put(list);
7,编写查询指定数据的方法
#查询student1的信息
@Test
public void queryData() throws IOException
Table table = conn.getTable(TableName.valueOf("bigdata:student"));
Get get = new Get(Bytes.toBytes("student1"));
Result result = table.get(get);
byte[] value = result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name"));
System.out.println("姓名:"+Bytes.toString(value));
value = result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("school"));
System.out.println("学校:"+Bytes.toString(value));
8,编写扫描数据的方法(所有数据)
@Test
public void scanData() throws IOException
Table table = conn.getTable(TableName.valueOf("kb21:student"));
Scan scan = new Scan();
ResultScanner scanner = table.getScanner(scan);
for (Result result : scanner)
byte[] value = result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name"));
System.out.println("姓名:"+Bytes.toString(value));
value = result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("school"));
System.out.println("学校:"+Bytes.toString(value));
System.out.println(Bytes.toString(result.getRow()));
9,编写删除表的方法
@Test
public void deleteTable() throws IOException
//先禁用
admin.disableTable(TableName.valueOf("bigdata:student"));
//再删除
admin.deleteTable(TableName.valueOf("bigdata:student"));
创建外部表
---------主要外部表的字段需要和Hbase中的列形成映射
create external table student(
id string,
name string,
school string
)
stored by 'org.apache.hadoop.hive.hbase.HBaseStorageHandler' with
serdeproperties ("hbase.columns.mapping"=":key,info1:name,info2:school")
tblproperties ("hbase.table.name"="bigdata:student");
select * from student
以上是关于IDEA连接HBase的主要内容,如果未能解决你的问题,请参考以下文章
IntelliJ IDEA+Mysql connecter/j JDBC驱动连接