基于idea操作hbase数据库并映射到hive表

2023-03-19 17:03:56 数据库操作映射

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

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

到此这篇关于用idea操作hbase数据库，并映射到hive的文章就介绍到这了,更多相关idea操作hbase数据库内容请搜索以前的文章或继续浏览下面的相关文章希望大家以后多多支持！