MapReduce之Reduce Join

一 介绍

Reduce Join其主要思想如下：
 在map阶段，map函数同时读取两个文件File1和File2，为了区分两种来源的key/value数据对，对每条数据打一个标签（tag）， 比如：tag=0表示来自文件File1，tag=2表示来自文件File2。即：map阶段的主要任务是对不同文件中的数据打标签。在reduce阶段，reduce函数获取key相同的来自File1和File2文件的value list， 然后对于同一个key，对File1和File2中的数据进行join（笛卡尔乘积)，即：reduce阶段进行实际的连接操作。

在这个例子中我们假设有两个数据文件如下：
存储客户信息的文件：customers.csv

1,stephaie leung,555-555-5555
2,edward kim,123-456-7890
3,jose madriz,281-330-8004
4,david storkk,408-55-0000

存储订单信息的文件：orders.csv

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

要求最终的输出结果为：

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,A,12.95,02-Jun-2008
3,Jose Madriz,281-330-8004,D,25.02,22-Jan-2009

二 代码部分

自定义数据类型：用于对不同文件数据打标签

package mapreduce.reducejoin;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;

public class DataJoinWritable implements Writable {

    // mark ,customer / order
    private String tag;

    // info
    private String data;

    public DataJoinWritable() {

    }

    public DataJoinWritable(String tag, String data) {
        this.set(tag, data);
    }

    public void set(String tag, String data) {
        this.setTag(tag);
        this.setData(data);
    }

    public String getTag() {
        return tag;
    }

    public void setTag(String tag) {
        this.tag = tag;
    }

    public String getData() {
        return data;
    }

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

    public void write(DataOutput out) throws IOException {
        out.writeUTF(this.getTag());
        out.writeUTF(this.getData());
    }

    public void readFields(DataInput in) throws IOException {
        this.setTag(in.readUTF());
        this.setData(in.readUTF());
    }

    @Override
    public int hashCode() {
        final int prime = 31;
        int result = 1;
        result = prime * result + ((data == null) ? 0 : data.hashCode());
        result = prime * result + ((tag == null) ? 0 : tag.hashCode());
        return result;
    }

    @Override
    public boolean equals(Object obj) {
        if (this == obj)
            return true;
        if (obj == null)
            return false;
        if (getClass() != obj.getClass())
            return false;
        DataJoinWritable other = (DataJoinWritable) obj;
        if (data == null) {
            if (other.data != null)
                return false;
        } else if (!data.equals(other.data))
            return false;
        if (tag == null) {
            if (other.tag != null)
                return false;
        } else if (!tag.equals(other.tag))
            return false;
        return true;
    }

    @Override
    public String toString() {
        return tag + "," + data;
    }
}

MapReduce代码部分

package mapreduce.reducejoin;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
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.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class DataJoinMapReduce extends Configured implements Tool {

    // step 1: Mapper
    public static class DataJoinMapper extends
            Mapper<LongWritable, Text, LongWritable, DataJoinWritable> {

        // map output key
        private LongWritable mapOutputKey = new LongWritable();

        // map output value
        private DataJoinWritable mapOutputValue = new DataJoinWritable();

        @Override
        public void setup(Context context) throws IOException,
                InterruptedException {
        }

        @Override
        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {

            // line value
            String lineValue = value.toString();

            // split
            String[] vals = lineValue.split(",");

            int length = vals.length;

            if ((3 != length) && (4 != length)) {
                return;
            }

            // get cid
            Long cid = Long.valueOf(vals[0]);

            // get name
            String name = vals[1];

            // set customer
            if (3 == length) {
                String phone = vals[2];

                // set
                mapOutputKey.set(cid);
                mapOutputValue.set("customer", name + "," + phone);
            }

            // set order
            if (4 == length) {
                String price = vals[2];
                String date = vals[3];

                // set
                mapOutputKey.set(cid);
                mapOutputValue.set("order", name + "," + price + "," + date);
            }

            // output
            context.write(mapOutputKey, mapOutputValue);

        }

        @Override
        public void cleanup(Context context) throws IOException,
                InterruptedException {
        }
    }

    // step 2: Reducer
    public static class DataJoinReducer extends
            Reducer<LongWritable, DataJoinWritable, NullWritable, Text> {

        private Text outputValue = new Text();

        @Override
        protected void setup(Context context) throws IOException,
                InterruptedException {
        }

        @Override
        protected void reduce(LongWritable key,
                Iterable<DataJoinWritable> values, Context context)
                throws IOException, InterruptedException {
            String customerInfo = null;
            List<String> orderList = new ArrayList<String>();

            for (DataJoinWritable value : values) {
                if ("customer".equals(value.getTag())) {
                    customerInfo = value.getData();
                } else if ("order".equals(value.getTag())) {
                    orderList.add(value.getData());
                }
            }

            // output
            for (String order : orderList) {

                // ser outout value
                outputValue.set(key.get() + "," + customerInfo + "," + order);

                // output
                context.write(NullWritable.get(), outputValue);
            }
        }

        @Override
        protected void cleanup(Context context) throws IOException,
                InterruptedException {
        }
    }

    /**
     * Execute the command with the given arguments.
     * 
     * @param args
     *            command specific arguments.
     * @return exit code.
     * @throws Exception
     */

    // step 3: Driver
    public int run(String[] args) throws Exception {

        Configuration configuration = this.getConf();
        
        // set job
        Job job = Job.getInstance(configuration, this.getClass().getSimpleName());
        job.setJarByClass(DataJoinMapReduce.class);
        
        // input
        Path inpath = new Path(args[0]);
        FileInputFormat.addInputPath(job, inpath);

        // output
        Path outPath = new Path(args[1]);
        FileOutputFormat.setOutputPath(job, outPath);

        // Mapper
        job.setMapperClass(DataJoinMapper.class);
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(DataJoinWritable.class);

        // Reducer
        job.setReducerClass(DataJoinReducer.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Text.class);

        // submit job -> YARN
        boolean isSuccess = job.waitForCompletion(true);
        return isSuccess ? 0 : 1;

    }

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

        Configuration configuration = new Configuration();

        args = new String[] {
                "hdfs://beifeng01:8020/user/beifeng01/mapreduce/input/reducejoin",
                "hdfs://beifeng01:8020/user/beifeng01/mapreduce/output" };

        // run job
        int status = ToolRunner.run(configuration, new DataJoinMapReduce(),
                args);

        // exit program
        System.exit(status);
    }
}

执行代码后查询结果

[hadoop@beifeng01 hadoop-2.5.0-cdh5.3.6]$ bin/hdfs dfs -text /user/beifeng01/mapreduce/output/p*
1,stephaie 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