Hbase-官方Hbase_MapReduce（一）【HbaseToHbase】

官方Hbase_MapReduce（一）【HbaseToHbase】

目标：实现Hbase数据库中，选取表city的数据到city_mr表。

分步实现：map+reduce

一、HbaseMapper类

package HbaseMr;

import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

/**
 * Author : ASUS and xinrong
 * Version : 2020/4/23 & 1.0
 * Mapper-查询city表，将name写到city_mr表中
 * 继承Hbase的TableMapper父类
 */
public class HbaseMpper extends TableMapper<ImmutableBytesWritable,Put> {
    @Override
    protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {
        //2.提取出city表的数据，封装成Put写到Reduce当中
        Put put = new Put(key.get());
        //1.遍历原来表里的column，获取到每一个列簇、列，捕捉到符合的列
        for(Cell cell : value.rawCells()){
            if("cf".equals(Bytes.toString(CellUtil.cloneFamily(cell)))){
                //put对象中添加countries
                if("countries".equals(Bytes.toString(CellUtil.cloneQualifier(cell)))){
                    put.add(cell);
                }
            }
        }
        context.write(key,put);
    }
}

二、HbaseReducer类

package HbaseMr;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.NullWritable;

import java.io.IOException;

/**
 * Author : ASUS and xinrong
 * Version : 2020/4/23 & 1.0
 */
public class HbaseReducer extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {
    @Override
    protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) throws IOException, InterruptedException {
        //将Mapper获取的数据写入到对应的city_mr表中
        for(Put put:values){
            context.write(NullWritable.get(),put);
        }
    }
}

三、CityToCity_mr类-测试类

package HbaseMr;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * Author : ASUS and xinrong
 * Version : 2020/4/23 & 1.0
 */
public class CityToCity_mr extends Configured implements Tool {

    @Override
    public int run(String[] strings) throws Exception {
        //1.获取配置文件
        Configuration conf = this.getConf();
        //2.创建一个job任务
        Job job = Job.getInstance(conf, getClass().getSimpleName());
        job.setJarByClass(CityToCity_mr.class);
        //3.创建一个扫描器
        Scan scan = new Scan();
        //4.配置map
        TableMapReduceUtil.initTableMapperJob(
                //1）读数据的表是哪张表
                "city",
                //2）扫描器
                scan,
                //3）设置map类
                HbaseMpper.class,
                //4）设置输出数据类型
                ImmutableBytesWritable.class,
                Put.class,
                //5）配置给job任务
                job
        );
        //5.配置reduce
        TableMapReduceUtil.initTableReducerJob(
                //1）将数据写到city_mr中
                "city_mr",
                //2）设置reduce表
                HbaseReducer.class,
                //3）输出put-这是默认的不用配置
                //4）配置给job任务
                job
        );
        //6.设置reduce个数
        job.setNumReduceTasks(1);
        //7.运行状态
        boolean status = job.waitForCompletion(true);
        //8.判断状态
        if(status){
            System.out.println("运行成功！");
            return 0;
        }else{
            System.out.println("运行失败！");
            return 1;
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = HBaseConfiguration.create();
        int status = ToolRunner.run(conf, new CityToCity_mr(), args);
        System.exit(status);
    }
}

四、执行

1.Maven打包：clean+package

2.新创建一个目录-myjob

/opt/module/hbase-1.3.1/myjob

3.上传刚打包好的jar包到此目录下

[root@bigdata111 myjob]# ll
total 16
-rw-r--r-- 1 root root 14849 Apr 25 14:51 hbase-1.0-SNAPSHOT.jar

4.执行命令：

/opt/module/hadoop-2.8.4/bin/yarn jar /opt/module/hbase-1.3.1/myjob/hbase-1.0-SNAPSHOT.jar HbaseMr.CityToCity_mr

HbaseMr.CityToCity_mr 这个是主类的全类名

尖叫提示：运行任务前，如果待数据导入的表不存在，则需要提前创建之。

五、结果

1.运行之前的city_mr表：

 

 2.运行日志

 

 3.查看city_mr表的数据