MapReduce编程实践之自定义数据类型

package mrTest;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class zidingyishujuleixing {
	
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		// TODO Auto-generated method stub
		
		Job job = new Job(new Configuration(),"自定义数据类型");
		job.setJarByClass(zidingyishujuleixing.class);
		//一：文件输入路径
		FileInputFormat.addInputPath(job, new Path(args[0]));
		
		//二：指定自定义Map类
		job.setMapperClass(Map.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(WlanString.class);
		
		//三：分区，指定reduce个数
		job.setNumReduceTasks(1);
		
		//四：TODO 排序  分组
		
		//五：规约处理
		
		//六：指定自定义的reduce类
		job.setReducerClass(Reduce.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(WlanString.class);
		
		//七：指定文件输出位置
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//八：提交运行
		System.exit(job.waitForCompletion(true)? 0 : 1);
	}
	
	public static class Map extends Mapper<Object, Text, Text, WlanString>{
		public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
			String[] split = value.toString().split("\t");
			String keyNum = split[1];
			WlanString ws = new WlanString(split[6],split[7],split[8],split[9]);
			System.out.println(split[6] + "| " + split[7] + "|" + split[8] + "|" + split[9]);
			context.write(new Text(keyNum), ws);
		}
	}
	
	public static class Reduce extends Reducer<Text, WlanString, Text, WlanString>{
		public void reduce(Text key, Iterable<WlanString> values, Context context) throws IOException, InterruptedException{
			long upData = 0;
			long downData = 0;
			long upFlow = 0;
			long downFlow = 0;
			for (WlanString w : values) {
				upData += w.upData;
				downData += w.downData;
				upFlow += w.upFlow;
				downFlow += w.downFlow;
			}
			WlanString newWs = new WlanString(String.valueOf(upData),String.valueOf(downData),String.valueOf(upFlow),String.valueOf(downFlow)); 
			context.write(key, newWs);
		}
	}
	
	public static class WlanString implements Writable{

		long upData;
		long downData;
		long upFlow;
		long downFlow;
		
		public WlanString(){	}
		
		public WlanString(String  upData1, String downData1, String upFlow1, String downFlow1) {
			// TODO Auto-generated constructor stub
			this.upData =  Long.parseLong(upData1);
			this.upData = Long.parseLong(downData1);
			this.upFlow =  Long.parseLong(upFlow1);
			this.downFlow = Long.parseLong(downFlow1);
		}

		@Override
		public void readFields(DataInput in) throws IOException {
			// TODO Auto-generated method stub
			this.upData = in.readLong();
			this.downData = in.readLong();
			this.upFlow = in.readLong();
			this.downFlow = in.readLong();
			System.out.println("upData:" + upData + "downData:" + downData + "upFlow:" + upFlow + "downFlow:" + downFlow);
		}

		@Override
		public void write(DataOutput out) throws IOException {
			// TODO Auto-generated method stub
			out.writeLong(upData);
			out.writeLong(downData);
			out.writeLong(upFlow);
			out.writeLong(upFlow);
			System.out.println("upData:" + upData + "downData:" + downData + "upFlow:" + upFlow + "downFlow:" + downFlow);
		}	

		 @Override  
	     public String toString() {  
	            return upData + "\t" + downData + "\t" + upFlow +"\t" + downFlow;  
	     }  
	}
}