12.21熟悉常用的HBase操作1

1.实验目的

（1）理解HBase在Hadoop体系结构中的角色；

（2）熟练使用HBase操作常用的Shell命令；

（3）熟悉HBase操作常用的Java API。

2.实验平台

（1）操作系统：Linux（建议Ubuntu16.04或Ubuntu18.04）；

（2）Hadoop版本：3.1.3；

（3）HBase版本：2.2.2；

（4）JDK版本：1.8；

（5）Java IDE：Eclipse。

3. 实验步骤

（一）编程实现以下指定功能，并用Hadoop提供的HBase Shell命令完成相同任务：

（1） 列出HBase所有的表的相关信息，例如表名；

1.List

 

2.import org.apache.hadoop.hbase.HBaseConfiguration;

import org.apache.hadoop.hbase.client.Admin;

import org.apache.hadoop.hbase.client.Connection;

import org.apache.hadoop.hbase.client.ConnectionFactory;

 

public class ListTables {

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

        org.apache.hadoop.conf.Configuration config = HBaseConfiguration.create();

        try (Connection connection = ConnectionFactory.createConnection(config);

             Admin admin = connection.getAdmin()) {

            for (String tableName : admin.listTableNames()) {

                System.out.println("Table Name: " + tableName);

            }

        }

    }

}

（2） 在终端打印出指定的表的所有记录数据；

1.scan 'your_table_name'

2.import org.apache.hadoop.hbase.HBaseConfiguration;

import org.apache.hadoop.hbase.client.Connection;

import org.apache.hadoop.hbase.client.ConnectionFactory;

import org.apache.hadoop.hbase.client.Result;

import org.apache.hadoop.hbase.client.ResultScanner;

import org.apache.hadoop.hbase.client.Scan;

import org.apache.hadoop.hbase.client.Table;

 

public class ScanTable {

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

        org.apache.hadoop.conf.Configuration config = HBaseConfiguration.create();

        try (Connection connection = ConnectionFactory.createConnection(config);

             Table table = connection.getTable("your_table_name")) {

            Scan scan = new Scan();

            ResultScanner scanner = table.getScanner(scan);

            for (Result result : scanner) {

                System.out.println(result);

            }

        }

    }

}

 

（3） 向已经创建好的表添加和删除指定的列族或列；

1. 添加：alter 'your_table_name', {NAME => 'new_column_family'}

删除：alter 'your_table_name', {NAME => 'column_family_to_delete', METHOD => 'delete'}

2.import org.apache.hadoop.hbase.HBaseConfiguration;

import org.apache.hadoop.hbase.client.Admin;

import org.apache.hadoop.hbase.client.Connection;

import org.apache.hadoop.hbase.client.ConnectionFactory;

 

public class ModifyTable {

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

        org.apache.hadoop.conf.Configuration config = HBaseConfiguration.create();

        try (Connection connection = ConnectionFactory.createConnection(config);

             Admin admin = connection.getAdmin()) {

            // 添加列族

            admin.addColumnFamily("your_table_name", "new_column_family");

            // 删除列族

            admin.deleteColumn("your_table_name", "column_family_to_delete");

        }

    }

}

（4） 清空指定的表的所有记录数据；

1.truncate 'your_table_name'

2.import org.apache.hadoop.hbase.HBaseConfiguration;

import org.apache.hadoop.hbase.client.Admin;

import org.apache.hadoop.hbase.client.Connection;

import org.apache.hadoop.hbase.client.ConnectionFactory;

 

public class TruncateTable {

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

        org.apache.hadoop.conf.Configuration config = HBaseConfiguration.create();

        try (Connection connection = ConnectionFactory.createConnection(config);

             Admin admin = connection.getAdmin()) {

            admin.disableTable("your_table_name");

            admin.truncateTable("your_table_name", false);

        }

    }

}

 

（5） 统计表的行数。

1. count 'your_table_name'

2.import org.apache.hadoop.hbase.HBaseConfiguration;

import org.apache.hadoop.hbase.client.Connection;

import org.apache.hadoop.hbase.client.ConnectionFactory;

import org.apache.hadoop.hbase.client.ResultScanner;

import org.apache.hadoop.hbase.client.Scan;

import org.apache.hadoop.hbase.client.Table;

 

public class CountRows {

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

        org.apache.hadoop.conf.Configuration config = HBaseConfiguration.create();

        try (Connection connection = ConnectionFactory.createConnection(config);

             Table table = connection.getTable("your_table_name")) {

            Scan scan = new Scan();

            ResultScanner scanner = table.getScanner(scan);

            int rowCount = 0;

            for (Result result : scanner) {

                rowCount++;

            }

            System.out.println("Row count: " + rowCount);

        }

    }

}