hbase自定义mr-1

1.目标：将fruit表中的一部分数据，通过mr迁入到fruit1表中
从hbase读数据，经过mr，最终写入hbase中

//数据样式
1001 apple red
1002 pear yellow
1003 pineapple yellow

/opt/hadoop/bin/yarn jar /opt/hbase/lib/hbase-server-1.4.3.jar importtsv
-Dimporttsv.columns=HBASE_ROW_KEY,info:name,info:color fruit
hdfs://192.168.8.10:9000/fruit.tsv

1.创建fruit.tsv,导入数据，上传到hdfs / 下
2.hbase 中 创建 fruit 表
3.把下面自定义 mr打包 上传到集群中 // 例如： /opt 下
4.运行命令：
/opt/hadoop/bin/yarn jar /opt/mr.jar mr1(主类名)
5.hbase中 scan ‘fruit’ ,查看数据是否写入

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class mr1 {

public static class MyMapper extends TableMapper<ImmutableBytesWritable, Put>{

@Override
protected void map(ImmutableBytesWritable key, Result value, Context context)
		throws IOException, InterruptedException {
	
	//构建put数组
	Put put = new Put(key.get());      // key.get()  把  序列化的key  转成  byte数组
	
	//遍历一个rowkey下的数据
	Cell[] cells = value.rawCells();
	for (Cell cell : cells) {
		if("name".equals(Bytes.toString(CellUtil.cloneQualifier(cell)))) {
			put.add(cell);
		}
	}
	//将数据写出去
	context.write(key, put);	
}		

}

public static class MyReduce extends TableReducer<ImmutableBytesWritable, Put, NullWritable>{

@Override
protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context)
		throws IOException, InterruptedException {
	
	//遍历写出     （可以作 + - / * 等等）
	for (Put value : values) {
		context.write(NullWritable.get(), value);			
	}	
}	

}

public static class Driver extends Configuration implements Tool{

private Configuration configuration = null;


public void setConf(Configuration conf) {
	this.configuration = conf;
}

public Configuration getConf() {
	return configuration;
}

public int run(String[] args) throws Exception {
	
	//获取任务对象
	Job job = Job.getInstance(configuration);
	
	//设置主类
	job.setJarByClass(Driver.class);	
	
	//指定Mapper   fruit:表名   Scan:扫描器   Mapper.class:Mapper的类  
	TableMapReduceUtil.initTableMapperJob("fruit",
			new Scan(),
			MyMapper.class,
			ImmutableBytesWritable.class,
			Put.class,
			job
			);
	
	//指定Reducer  fruit111:向哪个表写  MyReduce.class:redece类型
	TableMapReduceUtil.initTableReducerJob("q",
			MyReduce.class,
			job
			);
	
	//提交
	boolean b = job.waitForCompletion(true);
	
	return b ? 0 : 1;
}

}

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

Configuration configuration = HBaseConfiguration.create();

int i = ToolRunner.run(configuration, new Driver(),args);

}

}