MapReduce练习:DataJoin联结练习

练习题如下：需要输出每个顾客的订单详情。

涉及到的文件：

Customers

1,Stephanie Leung,555-555-5555
2,Edward Kim,123-456-7890
3,Jose Madrize,281-330-8004
4,Davia Stork,408-555-0000

Orders

3,A,12.95,02-Jun-2008
1,B,88.25,20-May-2008
2,C,32.00,30-Nov-2007
3,D,25.02,22-Jan-2009

具体程序如下：

package Self;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.contrib.utils.join.DataJoinMapperBase;
import org.apache.hadoop.contrib.utils.join.DataJoinReducerBase;
import org.apache.hadoop.contrib.utils.join.TaggedMapOutput;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.OutputFormat;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class DataJoinTest extends Configured implements Tool {

	
	public static class MapperClass extends DataJoinMapperBase
	{

		@Override
		protected Text generateGroupKey(TaggedMapOutput value) {
			String[] lines=value.toString().split(",");
			return new Text(lines[0]);
		}

		@Override
		protected Text generateInputTag(String inputFile) {
			return new Text(inputFile);
		}

		@Override
		protected TaggedMapOutput generateTaggedMapOutput(Object object) {
			TaggedValue taggedValue=new  TaggedValue((Text) object);
			taggedValue.setTag(this.inputTag);
			return taggedValue;
		}
		
		
	}
	
	public  static class TaggedValue extends TaggedMapOutput
	{
		private Writable data;
		
		public TaggedValue(Writable data)
		{
			this.data=data;
			this.tag=new Text("");
		}

		public void readFields(DataInput dataInput) throws IOException {
			this.data.readFields(dataInput);
			this.tag.readFields(dataInput);
		}

		public void write(DataOutput out) throws IOException {
			this.data.write(out);
			this.tag.write(out);
		}

		@Override
		public Writable getData() {
			return this.data;
		}
		
	}
	
	public static class ReducerClass extends DataJoinReducerBase{

		@Override
		protected TaggedMapOutput combine(Object[] tags, Object[] values) {
			if(tags.length<2) return null;
			String joinStr="";
			for (int i=0;i<values.length;i++) {
				if(i>0) joinStr+=",";
				String[] lines=((TaggedMapOutput)values[i]).getData().toString().split(",",2);
				joinStr+=lines[1];
			}
			TaggedValue taggedValue=new TaggedValue(new Text(joinStr));
			taggedValue.setTag((Text)tags[0]);
			return taggedValue;
		}
		
	}
	public int run(String[] args) throws Exception {
		Configuration configuration=getConf();
		JobConf job=new JobConf(configuration, DataJoinTest.class);
		
		job.setJobName("DataJoinTest");
		Path in=new Path(args[0]);
		Path out=new Path(args[1]);
		
		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);
		
		job.setMapperClass(MapperClass.class);
		job.setReducerClass(ReducerClass.class);
		
		job.setInputFormat(TextInputFormat.class);
		job.setOutputFormat(TextOutputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(TaggedValue.class);
		job.set("mapred.textoutputformat.separator",",");
		
		JobClient.runJob(job);
		return 0;
	}

	public static void main(String[] args) throws Exception {
		int code=ToolRunner.run(new Configuration(), new DataJoinTest(),args);
		System.exit(code);
	}
}