mapReduce 的join

mapreduce join分为两种：

1、map的join     2、reduce的join

思路：

1、map的join是将一个数据集的数据放入Map集合中，将集合在setup放入到缓存中，所以涉及DistributedCache，因为涉及在内存，所以放入缓存的数据集样本要小，否则不适用，所以这个业务场景比较少

setup中代码实现如下：（官网有源码）

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

            Configuration configuration = context.getConfiguration();
            URI[] uri = Job.getInstance(configuration).getCacheFiles();
            Path path = new Path(uri[0]);
            FileSystem fileSystem = FileSystem.get(configuration);
            InputStream inputStream = fileSystem.open(path);
            InputStreamReader inputStreamReader = new InputStreamReader(inputStream);
            BufferedReader bufferedReader = new BufferedReader(inputStreamReader);

            String line = null;
            while ((line=bufferedReader.readLine())!=null){
                if (line.trim().length()>0){
                    customer.put(line.split(",")[0],line);
                }
            }
            bufferedReader.close();
            inputStreamReader.close();
            inputStream.close();
        }

在主函数中要调用job.addCache方法，将URI写入进去

 

2、reduce的join

将需要join的数据集都作为map的输入，在map的逻辑中对数据进行标记，reduce中对数据进行合并,需要自定义数据类型

自定义数据类型

package com.kfk.hadoop.mr.join;

import org.apache.hadoop.io.Writable;

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

public class DataJoinWritable implements Writable {

    private int id;
    private String data;

    public DataJoinWritable() {
    }

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

    public void set(int id, String data) {
        this.id = id;
        this.data = data;
    }

    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeInt(this.id);
        dataOutput.writeUTF(this.data);
    }

    public void readFields(DataInput dataInput) throws IOException {
        this.id = dataInput.readInt();
        this.data = dataInput.readUTF();
    }

    public int getId() {
        return id;
    }

    public void setId(int id) {
        this.id = id;
    }

    public String getData() {
        return data;
    }

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

    @Override
    public String toString() {
        return "DataJoinWritable{" +
                "id=" + id +
                ", data='" + data + '\'' +
                '}';
    }

    @Override
    public boolean equals(Object o) {
        if (this == o) return true;
        if (o == null || getClass() != o.getClass()) return false;

        DataJoinWritable that = (DataJoinWritable) o;

        if (id != that.id) return false;
        return data != null ? data.equals(that.data) : that.data == null;
    }

    @Override
    public int hashCode() {
        int result = id;
        result = 31 * result + (data != null ? data.hashCode() : 0);
        return result;
    }
}

标记类

package com.kfk.hadoop.mr.join;

public class DataCommon {
    public static final int CUSTOMER = 1;
    public static final int ORDER = 2;
}

map代码

public static class ReduceJoinMapper extends Mapper<LongWritable, Text,Text, DataJoinWritable>{

        Text outKey = new Text();
        DataJoinWritable outValue = new DataJoinWritable();

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

            String[] line = value.toString().split(",");
            if (line.length==3){
                outKey.set(line[0]);
                outValue.set(DataCommon.CUSTOMER,line[1]+","+line[2]);
            }else {
                outKey.set(line[1]);
                outValue.set(DataCommon.ORDER,line[0]+","+line[2]+","+line[3]);
            }
            context.write(outKey,outValue);

        }


    }

 

reduce代码

    public static class ReduceJoinReducer extends Reducer<Text,DataJoinWritable, Text,Text>{

        private String customer = null;
        private List<String> order = new ArrayList<String>();

        @Override
        public void reduce(Text key, Iterable<DataJoinWritable> values, Context context) throws IOException, InterruptedException {
            for (DataJoinWritable dataJoinWritable:values){
                if (dataJoinWritable.getId()==DataCommon.CUSTOMER){
                    customer = dataJoinWritable.getData();
                }else if (dataJoinWritable.getId()==DataCommon.ORDER){
                    order.add(dataJoinWritable.getData());
                }
            }
            for (String o:order) {
                context.write(key,new Text(customer+","+o));
            }
        }
}
}