MapReduce API

ReduceJoin

ReduceJoin
package a.b.c;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapreduce.InputSplit;
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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;



/*
订单表
detail
order_id    item_id            amount    
12,sp001,2
12,sp002,4
12,sp003,3
13,sp001,2
13,sp002,4


商品信息表  iteminfo
item_id         item_type     
sp001,type001
sp002,type002
sp003,type002

*/

//对商品表和订单表进行连接，通过item_id进行连接
//对文件夹数据进行识别，并且打flag的形式放入JoinBean类型

class Joinbean implements WritableComparable<Joinbean>{
	
	
	
	private String order_id;
	private String item_id;
	private String amount;
	private String item_type;
	private String flag;
	
	public Joinbean() {
	}
	
	public Joinbean(String order_id,String item_id,String amount,String item_type,String flag) {
		this.order_id=order_id;
		this.item_id=item_id;
		this.amount=amount;
		this.item_type=item_type;
		this.flag=flag;
	}
	
	public String getOrder_id() {
		return order_id;
	}

	public void setOrder_id(String order_id) {
		this.order_id = order_id;
	}

	public String getItem_id() {
		return item_id;
	}

	public void setItem_id(String item_id) {
		this.item_id = item_id;
	}

	public String getAmount() {
		return amount;
	}

	public void setAmount(String amount) {
		this.amount = amount;
	}

	public String getItem_type() {
		return item_type;
	}

	public void setItem_type(String item_type) {
		this.item_type = item_type;
	}
	
	public String getFlag() {
		return flag;
	}

	public void setFlag(String flag) {
		this.flag = flag;
	}

	@Override
	public void write(DataOutput arg0) throws IOException {
		arg0.writeUTF(order_id);
		arg0.writeUTF(item_id);
		arg0.writeUTF(amount);
		arg0.writeUTF(item_type);
		arg0.writeUTF(flag);
		
	}
	
	@Override
	public void readFields(DataInput arg0) throws IOException {
		this.order_id=arg0.readUTF();
		this.item_id=arg0.readUTF();
		this.amount=arg0.readUTF();
		this.item_type=arg0.readUTF();
		this.flag=arg0.readUTF();
		
	}
	
	@Override
	public String toString() {
		String aaaString=this.order_id+"\t"+item_id+"\t"+amount+"\t"+item_type+"\t"+flag;
		return aaaString;
	}

	@Override
	public int compareTo(Joinbean arg0) {
	     int thisValue = Integer.parseInt(this.order_id);
         int thatValue = Integer.parseInt(arg0.order_id);
         return (thisValue < thatValue ? -1 : (thisValue==thatValue ? 0 : 1));
	}
}


class ReduceJoinMapper extends Mapper<LongWritable, Text, Text,Joinbean >{
	@Override
	protected void map(LongWritable key, Text value,Context context)
			throws IOException, InterruptedException {
		//初始化数据，默认flag为0
		String order_id="";
		String item_id="";
		String amount="";
		String item_type="";
		String flag="0";
		
		String[] wordsStrings=value.toString().split(",");
		//获取文件夹地址，获取地址后，对文件进行操作
		FileSplit inpuSplit=(FileSplit)context.getInputSplit();
		String fileNameString=inpuSplit.getPath().getName();
		//判断表如果是detail，放入JoinBean，并且flag设置为0
		if("detail".equals(fileNameString)){
			order_id=wordsStrings[0];
			item_id=wordsStrings[1];
			amount=wordsStrings[2];
		//判断表如果是iteminfo，放入JoinBean，并且flag设置为1
		}else{
			item_id=wordsStrings[0];
			item_type=wordsStrings[1];
			flag="1";
		}
		//对每个表的数据，进行输出，并且通过flag来标记数据来自那个表
		Joinbean bean=new Joinbean(order_id,item_id,amount,item_type,flag);
		System.out.println(item_id+"-----"+bean);
		context.write(new Text(item_id),bean);
		
	}
}


class ReduceJoinReducer  extends Reducer<Text, Joinbean, NullWritable, Joinbean>{
	@Override
	protected void reduce(Text key, Iterable<Joinbean> values,Context context)
			throws IOException, InterruptedException {
		String type=null;
		//设置arralist
		ArrayList<Joinbean> detailBeans= new ArrayList<Joinbean>();
		for (Joinbean joinbean:values){
			System.out.println(joinbean.toString());
			//如果获取flag为1，则是iteminfo表，直接获取Item_type
			if("1".equals(joinbean.getFlag())){
				type=joinbean.getItem_type();
			}else{
				//如果不是1，则为0detail订单详情，因为reduce获取的都是具有相同的key，即相同的item_id，这就是匹配到的符合join条件的两表的数据
				detailBeans.add(new Joinbean(joinbean.getOrder_id(),joinbean.getItem_id(),joinbean.getAmount(), joinbean.getItem_type(), joinbean.getFlag()));	
			}
		}
		//对Item_type写入到
			for (Joinbean bean:detailBeans){
				bean.setItem_type(type);
				context.write(NullWritable.get(),bean);
		}
	}
}


public class ReduceJoin {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
	Configuration conf = new Configuration();
	Job job = Job.getInstance(conf);
	job.setJarByClass(ReduceJoin.class);
	
	
	job.setMapperClass(ReduceJoinMapper.class);
	job.setReducerClass(ReduceJoinReducer.class);
	
	job.setMapOutputKeyClass(Text.class);
	job.setMapOutputValueClass(Joinbean.class);

	job.setOutputKeyClass(NullWritable.class);
	job.setOutputValueClass(Joinbean.class);
	
	
	FileInputFormat.addInputPath(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));

	Path path = new Path(args [1]);
	FileSystem fileSystem = path.getFileSystem(conf);
	if (fileSystem.exists(path)) {
		fileSystem.delete((path),true);}
	
	

	boolean res = job.waitForCompletion(true);

	System.exit(res ? 0 : 1);
	
	
}
}