hbase与mapreduce集成

一：运行给定的案例

1.获取jar包里的方法

　　

2.运行hbase自带的mapreduce程序

　　lib/hbase-server-0.98.6-hadoop2.jar　

　

3.具体运行

　　注意命令：mapredcp。

　　HADOOP_CLASSPATH是当前运行时需要的环境。

　　

4.运行一个小方法

　　$HADOOP_HOME/bin/yarn jar lib/hbase-server-0.98.6-hadoop2.jar rowcounter nstest1:tb1

　　

二：自定义hbase的数据拷贝

1.需求

　　将nstest1:tb1的数据info：name列拷贝到nstest1:tb2

2.新建tb2表

　　

3.书写mapreduce程序

　　输入：rowkey，result。

 package com.beifeng.bigdat;

 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.conf.Configured;
 import org.apache.hadoop.hbase.Cell;
 import org.apache.hadoop.hbase.CellUtil;
 import org.apache.hadoop.hbase.HBaseConfiguration;
 import org.apache.hadoop.hbase.client.Put;
 import org.apache.hadoop.hbase.client.Result;
 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.hbase.mapreduce.TableMapper;
 import org.apache.hadoop.hbase.mapreduce.TableReducer;
 import org.apache.hadoop.hbase.util.Bytes;
 import org.apache.hadoop.mapreduce.Job;
 import org.apache.hadoop.mapreduce.Mapper.Context;
 import org.apache.hadoop.util.Tool;
 import org.apache.hadoop.util.ToolRunner;

 public class HBaseMRTest extends Configured implements Tool{
     /**
      * map
      * @author      *
      */
     public static class tbMap extends TableMapper<ImmutableBytesWritable, Put>{

         @Override
         protected void map(ImmutableBytesWritable key, Result value,Context context) throws IOException, InterruptedException {
             Put put=new Put(key.get());
             for(Cell cell:value.rawCells()){
                 if("info".equals(Bytes.toString(CellUtil.cloneFamily(cell)))){
                     if("name".equals(Bytes.toString(CellUtil.cloneQualifier(cell)))){
                         put.add(cell);
                         context.write(key, put);
                     }
                 }
             }
         }

     }
     /**
      * reduce
      * @author      *
      */
     public static class tbReduce extends TableReducer<ImmutableBytesWritable, Put, ImmutableBytesWritable>{

         @Override
         protected void reduce(ImmutableBytesWritable key, Iterable<Put> values,Context context)throws IOException, InterruptedException {
             for(Put put:values){
                 context.write(key, put);
             }
         }

     }

     public int run(String[] args) throws Exception {
         Configuration conf=super.getConf();
         Job job =Job.getInstance(conf, "hbasemr");
         job.setJarByClass(HBaseMRTest.class);
         Scan scan=new Scan();
         TableMapReduceUtil.initTableMapperJob(
                 "nstest1:tb1",
                 scan,
                 tbMap.class,
                 ImmutableBytesWritable.class,
                 Put.class,
                 job);
         TableMapReduceUtil.initTableReducerJob(
                 "nstest1:tb2",
                 tbReduce.class,
                 job);
         boolean issucess=job.waitForCompletion(true);
         return issucess?0:1;
     }
     public static void main(String[] args) throws Exception{
         Configuration conf=HBaseConfiguration.create();
         int status=ToolRunner.run(conf, new HBaseMRTest(), args);
         System.exit(status);
     }

 }

4.打成jar包

5.运行语句

　　加上需要的export前提。

　　$HADOOP_HOME/bin/yarn jar /etc/opt/datas/HBaseMR.jar com.beifeng.bigdat.HBaseMRTest

6.效果