MapReduce Join拼接数据

读取两个数据，一个数据存放用户的id,性别和年龄,一个数据存放的电影的uid，id等信息但缺少用户信息，将二者拼接起来

本次采用的是在reduce阶段拼接，也可以在map阶段拼接

1.JoinBean

今天碰到一个很尴尬的问题，read和write中的读写数据顺序必须一直，否则数据会混乱。检查了很久才发现，需要注意

package nuc.edu.ls.extend;

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

import org.apache.hadoop.io.Writable;

public class JoinBean implements Writable{
    private String uid;
    private String age;
    private String gender;
    private String movieId;
    private String rating;
    private String table;
	public String getUid() {
		return uid;
	}
	public void setUid(String uid) {
		this.uid = uid;
	}
	public String getAge() {
		return age;
	}
	public void setAge(String age) {
		this.age = age;
	}
	public String getGender() {
		return gender;
	}
	public void setGender(String gender) {
		this.gender = gender;
	}
	public String getMovieId() {
		return movieId;
	}
	public void setMovieId(String movieId) {
		this.movieId = movieId;
	}
	public String getRating() {
		return rating;
	}
	public void setRating(String rating) {
		this.rating = rating;
	}
	public String getTable() {
		return table;
	}
	public void setTable(String table) {
		this.table = table;
	}
	@Override
	public String toString() {
		return "JoinBean [uid=" + uid + ", age=" + age + ", gender=" + gender + ", movieId=" + movieId + ", rating="
				+ rating + ", table=" + table + "]";
	}
	@Override
	public void readFields(DataInput arg0) throws IOException {
		uid=arg0.readUTF();
		age=arg0.readUTF();
		gender=arg0.readUTF();
		movieId=arg0.readUTF();
		rating=arg0.readUTF();
		table=arg0.readUTF();
		
	}
	@Override
	public void write(DataOutput arg0) throws IOException {
		// TODO Auto-generated method stub
		arg0.writeUTF(uid);
		arg0.writeUTF(age);
		arg0.writeUTF(gender);
		arg0.writeUTF(movieId);
		arg0.writeUTF(rating);
		arg0.writeUTF(table);
		
	}
	public void set(String uid, String age, String gender, String movieId, String rating, String table) {
		this.uid = uid;
		this.age = age;
		this.gender = gender;
		this.movieId = movieId;
		this.rating = rating;
		this.table = table;
	}
	
    
}

2.任务

map将相同用d户id的数据汇集到一起，两数据的唯一联系就是uid

setup方法中获得了写入的文件名信息，写入setup中的好处在于只需要获取一次即可，提高效率

reduce阶段  随便取到一个用户信息（根据table即写入的文件名)，就可以对集合中所有电影信息进行拼接了

package nuc.edu.ls.extend;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;

import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.Configuration;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


public class JoinMR {
	public static class MapTask extends Mapper<LongWritable, Text, Text, JoinBean> {
		String table;

		@Override
		protected void setup(Mapper<LongWritable, Text, Text, JoinBean>.Context context)
				throws IOException, InterruptedException {
			// TODO Auto-generated method stub
			FileSplit fileSplit = (FileSplit) context.getInputSplit();
			table = fileSplit.getPath().getName();
		}

		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, JoinBean>.Context context)
				throws IOException, InterruptedException {
			// TODO Auto-generated method stub
			String[] split = value.toString().split("::");
			JoinBean jb = new JoinBean();
			if (table.startsWith("users")) {
				jb.set(split[0], split[2], split[1], "null", "null", "user");
			} else {
				jb.set(split[0], "null", "null", split[1], split[2], "rating");
			}
//			System.out.print(jb.getUid()+"\\");
//			System.out.println(jb);
			context.write(new Text(jb.getUid()), jb);
		}
	}

	public static class ReduceTask extends Reducer<Text, JoinBean, JoinBean, NullWritable> {
		@Override
		protected void reduce(Text key, Iterable<JoinBean> values,
				Reducer<Text, JoinBean, JoinBean, NullWritable>.Context context)
				throws IOException, InterruptedException {
			// TODO Auto-generated method stub
			JoinBean user = new JoinBean();
			ArrayList<JoinBean> list = new ArrayList<>();
			for (JoinBean joinBean2 : values) {
				String table = joinBean2.getTable();
				if ("user".equals(table)) {
					user.set(joinBean2.getUid(), joinBean2.getAge(), joinBean2.getGender(), joinBean2.getMovieId(), joinBean2.getRating(), joinBean2.getTable());

				} else {
					JoinBean joinBean3 = new JoinBean();
					joinBean3.set(joinBean2.getUid(), joinBean2.getAge(), joinBean2.getGender(), joinBean2.getMovieId(), joinBean2.getRating(), joinBean2.getTable());
					list.add(joinBean3);
				}
			}
			System.out.print(key.toString()+"\\\\\\");
			System.out.println(user+"\\\\\\");
			// 拼接数据
			for (JoinBean join : list) {
				join.setAge(user.getAge());
				join.setGender(user.getGender());
				context.write(join, NullWritable.get());
			}

		}
	}
	public static void main(String[] args) throws Exception {
		System.setProperty("HADOOP_USER_NAME", "root");

		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf, "eclipseToCluster");

		job.setMapperClass(MapTask.class);
		job.setReducerClass(ReduceTask.class);
		job.setJarByClass(JoinMR.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(JoinBean.class);
		job.setOutputKeyClass(JoinBean.class);
		job.setOutputValueClass(NullWritable.class);
       // job.setCombinerClass(ReduceTask.class);
		FileInputFormat.addInputPath(job, new Path("d:/indata/"));
		FileOutputFormat.setOutputPath(job, new Path("d:/outdata/movie"));
		File file = new File("d:/outdata/movie");
        if(file.exists()) {
        	FileUtils.deleteDirectory(file);
        }
		boolean completion = job.waitForCompletion(true);
		System.out.println(completion ? 0 : 1);

	}

}

3.结果：

想结果好看可以修改JavaBean里面的toString方法