Hadoop: Data Join

Reduce-side joining / repartitioned sort-merge join

 

Note:DataJoinReducerBase, on the other hand, is the workhorse of the datajoin package, and it simplifies our programming by performing a full outer join for us. Our reducer subclass only has to implement the combine() method to filter out unwanted combinations to get the desired join operation (inner join, left outer join, etc.). It’s also in the combine() method that we format the combination into the appropriate
output format.

When run the sample code in <<hadoop in action>> chapter 5. There will some errors coming up. see

http://stackoverflow.com/questions/10201500/hadoop-reduce-side-join-using-datajoin

The correct code after modified  likes

package com.test.datamine.topic;

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.FileSystem;
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.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class DataJoin extends Configured implements Tool {

	public static class MapClass extends DataJoinMapperBase {

		protected Text generateInputTag(String inputFile) {
			String datasource = inputFile.split("-")[0];
			return new Text(datasource);
		}

		protected Text generateGroupKey(TaggedMapOutput aRecord) {
			String line = ((Text) aRecord.getData()).toString();
			String[] tokens = line.split(",");
			String groupKey = tokens[0];
			return new Text(groupKey);
		}

		protected TaggedMapOutput generateTaggedMapOutput(Object value) {
			TaggedWritable retv = new TaggedWritable((Text) value);
			retv.setTag(this.inputTag);
			return retv;
		}
	}

	public static class Reduce extends DataJoinReducerBase {

		protected TaggedMapOutput combine(Object[] tags, Object[] values) {
			if (tags.length < 2)
				return null;
			String joinedStr = "";
			for (int i = 0; i < values.length; i++) {
				if (i > 0)
					joinedStr += ",";
				TaggedWritable tw = (TaggedWritable) values[i];
				String line = ((Text) tw.getData()).toString();
				String[] tokens = line.split(",", 2);
				joinedStr += tokens[1];
			}
			TaggedWritable retv = new TaggedWritable(new Text(joinedStr));
			retv.setTag((Text) tags[0]);
			return retv;
		}
	}

	public static class TaggedWritable extends TaggedMapOutput {

		private Writable data;

		public TaggedWritable() {
			this.tag = new Text();
		}

		public TaggedWritable(Writable data) {
			this.tag = new Text("");
			this.data = data;
		}

		public Writable getData() {
			return data;
		}

		public void setData(Writable data) {
			this.data = data;
		}

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

		public void readFields(DataInput in) throws IOException {
			// this.tag.readFields(in);
			// this.data.readFields(in);
			this.tag.readFields(in);
			String dataClz = in.readUTF();
			if (this.data == null
					|| !this.data.getClass().getName().equals(dataClz)) {
				try {
					this.data = (Writable) ReflectionUtils.newInstance(
							Class.forName(dataClz), null);
				} catch (ClassNotFoundException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				}
			}
			this.data.readFields(in);
		}
	}

	public int run(String[] args) throws Exception {
		Configuration conf = getConf();

		JobConf job = new JobConf(conf, DataJoin.class);

		Path in = new Path(args[0]);
		Path out = new Path(args[1]);
		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);

		job.setJobName("DataJoin");
		job.setMapperClass(MapClass.class);
		job.setReducerClass(Reduce.class);

		job.setInputFormat(TextInputFormat.class);
		job.setOutputFormat(TextOutputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(TaggedWritable.class);
		job.set("mapred.textoutputformat.separator", ",");

		FileSystem fs = in.getFileSystem(conf);
		fs.delete(out);

		JobClient.runJob(job);
		return 0;
	}

	public static void main(String[] args) throws Exception {
		int res = ToolRunner.run(new Configuration(), new DataJoin(), args);

		System.exit(res);
	}
}

 The test data is consist of two files

customers

1,Stephanie Leung,555-555-5555
2,Edward Kim,123-456-7890
3,Jose Madriz,281-330-8004
4,David 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

the joined result is

1,Stephanie Leung,555-555-5555,B,88.25,20-May-2008
2,Edward Kim,123-456-7890,C,32.00,30-Nov-2007
3,Jose Madriz,281-330-8004,D,25.02,22-Jan-2009
3,Jose Madriz,281-330-8004,A,12.95,02-Jun-2008