HBase综合测试

最新推荐文章于 2024-05-04 09:38:05 发布

咖啡不提神

最新推荐文章于 2024-05-04 09:38:05 发布

阅读量229

点赞数 1

文章标签： hbase 数据库大数据

本文链接：https://blog.csdn.net/m0_52680439/article/details/134365759

版权

第1关：HBase-shell命令

任务描述

使用HBase shell命令创建表：exam_tb1，向表中添加数据，表的数据与结构如下：

#启动HBAse
start-hbase.sh
hbase shell
#创建表
create 'exam_tb1',  {NAME=>'user_info'},{NAME=>'class_info'}
#添加数据
put 'exam_tb1','row-1','user_info:name','jack'
put 'exam_tb1','row-1','user_info:age','32'
put 'exam_tb1','row-1','class_info:class_name','software'
put 'exam_tb1','row-1','class_info:class_id','201801'

put 'exam_tb1','row-2','user_info:name','rose'
put 'exam_tb1','row-2','user_info:age','28'
put 'exam_tb1','row-2','class_info:class_name','hardware'
put 'exam_tb1','row-2','class_info:class_id','201802'

第2关：Hbase Java API

任务描述

在右侧编写代码，禁用表step2_tb0，删除表step2_tb1，创建表emp_tb1，emp_tb1表结构与数据如下图：

package step2;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.io.compress.Compression;
import org.apache.hadoop.hbase.util.*;

public class Task {

	public void operatorTables()throws Exception{
		/********* Begin *********/

        Configuration conf = HBaseConfiguration.create(); //使用create()静态方法就可以得到Configuration对象
        Connection conn = ConnectionFactory.createConnection(conf); //config为前文的配置对象
        Admin admin = conn.getAdmin(); //使用连接对象获取Admin对象
        TableName tableName = TableName.valueOf("emp_tb1");//定义表名
        HTableDescriptor htd = new HTableDescriptor(tableName);//定义表对象
        HColumnDescriptor hcd1 = new HColumnDescriptor("emp_info");//定义列族对象
        HColumnDescriptor hcd2 = new HColumnDescriptor("dept_info");//定义列族对象
        htd.addFamily(hcd1); //添加
        htd.addFamily(hcd2); //添加
        admin.createTable(htd);//创建表
        
        // 停用表
        admin.disableTable(TableName.valueOf("step2_tb0"));
        // 停用表
        admin.disableTable(TableName.valueOf("step2_tb1"));
        // 删除表
        admin.deleteTable(TableName.valueOf("step2_tb1"));

        // 获取一个操作指定表的table对象,进行DML操作
        Table table = conn.getTable(TableName.valueOf("emp_tb1"));
        
        // 构造要插入的数据为一个Put类型(一个put对象只能对应一个rowkey)的对象
        Put put = new Put(Bytes.toBytes("201101"));
        put.addColumn(Bytes.toBytes("emp_info"), Bytes.toBytes("emp_name"), Bytes.toBytes("lucy"));
        put.addColumn(Bytes.toBytes("emp_info"), Bytes.toBytes("emp_id"), Bytes.toBytes("1"));
        put.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("gender"), Bytes.toBytes("man"));
        put.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("dept_id"), Bytes.toBytes("2001"));
        put.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("dept_name"), Bytes.toBytes("finance"));

        Put put2 = new Put(Bytes.toBytes("201102"));
        put2.addColumn(Bytes.toBytes("emp_info"), Bytes.toBytes("emp_name"), Bytes.toBytes("alpha"));
        put2.addColumn(Bytes.toBytes("emp_info"), Bytes.toBytes("emp_id"), Bytes.toBytes("2"));
        put2.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("gender"), Bytes.toBytes("woman"));
        put2.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("dept_id"), Bytes.toBytes("2003"));
        put2.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("dept_name"), Bytes.toBytes("techenology"));		


        Put put3 = new Put(Bytes.toBytes("201103"));
        put3.addColumn(Bytes.toBytes("emp_info"), Bytes.toBytes("emp_name"), Bytes.toBytes("linus"));
        put3.addColumn(Bytes.toBytes("emp_info"), Bytes.toBytes("emp_id"), Bytes.toBytes("3"));
        put3.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("gender"), Bytes.toBytes("man"));
        put3.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("dept_id"), Bytes.toBytes("3002"));
        put3.addColumn(Bytes.toBytes("dept_info"), Bytes.toBytes("dept_name"), Bytes.toBytes("logistics"));
        
        ArrayList<Put> puts = new ArrayList<>();
        puts.add(put);
        puts.add(put2);
        puts.add(put3);
        
        // 插进去
        table.put(puts);
        
        table.close();
        conn.close();

		/********* End *********/
	}
	
	
}

第3关：HBase扫描

任务描述

在右侧sanTable(String tablename) 方法中扫描表中的数据并输出（tablename为要扫描的表名），扫描起止行要求从row-10开始至row-50，且只扫描info:name列。

package step3;

import java.io.IOException;

import org.apache.hadoop.conf.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.*;

public class Task {

	public void scanTable(String tableName)throws Exception{
		/********* Begin *********/
		Configuration config = HBaseConfiguration.create();
        Connection conn = ConnectionFactory.createConnection(config);
        Admin admin = conn.getAdmin();
        TableName tablename=TableName.valueOf(tableName);
        Table table=conn.getTable(tablename);

        Scan scan = new Scan();
        scan.addColumn(Bytes.toBytes("info"),Bytes.toBytes("name"));
        scan.setStartRow(Bytes.toBytes("row-10"));
        scan.setStopRow(Bytes.toBytes("row-50"));

        ResultScanner scanner = table.getScanner(scan);
        for(Result result:scanner){
            System.out.println(Bytes.toString(result.getRow()));
            for(Cell cell:result.listCells()){
                String family = Bytes.toString(CellUtil.cloneFamily(cell));
                String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
                String value = Bytes.toString(CellUtil.cloneValue(cell));
                System.out.println("\t"+family+ ":" + qualifier + " " + value);

            }
        }
	
		/********* End *********/
	}
}

第4关：HBase过滤器

任务描述

在右侧query(String tName)中编写代码，使用过滤器查询出如下数据：

查询行健大于等于row20且data:phone列的值是正确的手机号码的数据并输出该行的所有数据；

手机号的规则为：1开头，第二位是[3,4,5,7,8]中的任意一位，第三位到十一位都为0-9的数字。

package step4;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.cli.util.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.util.*;

public class Task {

	public void query(String tName) throws Exception {
		/********* Begin *********/
		Configuration conf = HBaseConfiguration.create();
	    Connection connection = ConnectionFactory.createConnection(conf);
        Admin admin = connection.getAdmin();
        TableName tablename = TableName.valueOf(tName);
	    Table table = connection.getTable(tablename);

        //行键大于20
       Filter equalFilter1 = new RowFilter(CompareOperator.GREATER_OR_EQUAL,
       new BinaryComparator(Bytes.toBytes("row20")));
   
       //单列值过滤器 电话号码
       SingleColumnValueFilter valueFilter =new      SingleColumnValueFilter(Bytes.toBytes("data"),Bytes.toBytes("phone"),CompareOperator.EQUAL,new RegexStringComparator("^1[3|4|5|7|8][0-9]{9}$"));
   
        List<Filter> list =new ArrayList<>();
	    list.add(valueFilter);
	    list.add(equalFilter1);

	    FilterList filterList1 =new FilterList(FilterList.Operator.MUST_PASS_ALL,list);

	    Scan scan1 = new Scan();
	    scan1.setFilter(filterList1);

	    ResultScanner scanner1 = table.getScanner(scan1);
	    for (Result result : scanner1) {
		 System.out.println(Bytes.toString(result.getRow()));
          for(Cell cell : result.listCells()){
                 String family = Bytes.toString(CellUtil.cloneFamily(cell));
                 String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
                 String value = Bytes.toString(CellUtil.cloneValue(cell));
                 System.out.println("\t" + family + ":" + qualifier + " " + value);
                  }
            }
        scanner1.close();

	    connection.close();

		/********* End *********/
	}

}