MapJoin的简单实现

MapJoin 适用于有一份数据较小的连接情况。做法是直接把该小份数据直接全部加载到内存当中，按链接关键字建立索引。然后大份数据就作为 MapTask 的输入，对 map()方法的每次输入都去内存当中直接去匹配连接。然后把连接结果按 key 输出，这种方法要使用 hadoop中的 DistributedCache 把小份数据分布到各个计算节点，每个 maptask 执行任务的节点都需要加载该数据到内存，并且按连接关键字建立索引：

封装 MovieRate,方便数据的排序和序列化：

package mapreduce.join.mapJoin;

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

import org.apache.hadoop.io.WritableComparable;

public class MovieRate implements WritableComparable<MovieRate>{
//	new MovieRate(userid, movieid, rate, ts, movieName, movieType);

	private String userid;
	private String movieid;
	private int rate;
	private Long ts;
	private String movieName;
	private String movieType;
	public String getUserid() {
		return userid;
	}
	public void setUserid(String userid) {
		this.userid = userid;
	}
	public String getMovieid() {
		return movieid;
	}
	public void setMovieid(String movieid) {
		this.movieid = movieid;
	}
	public int getRate() {
		return rate;
	}
	public void setRate(int rate) {
		this.rate = rate;
	}
	public Long getTs() {
		return ts;
	}
	public void setTs(Long ts) {
		this.ts = ts;
	}
	public String getMovieName() {
		return movieName;
	}
	public void setMovieName(String movieName) {
		this.movieName = movieName;
	}
	public String getMovieType() {
		return movieType;
	}
	public void setMovieType(String movieType) {
		this.movieType = movieType;
	}
	public MovieRate(String userid, String movieid, int rate, Long ts, String movieName, String movieType) {
		super();
		this.userid = userid;
		this.movieid = movieid;
		this.rate = rate;
		this.ts = ts;
		this.movieName = movieName;
		this.movieType = movieType;
	}
	public MovieRate() {
		super();
	}
	@Override
	public String toString() {
		return  userid + "\t" + movieid + "\t" + rate + "\t" + ts + "\t" + movieName + "\t" + movieType ;
	}
	
	@Override
	public void write(DataOutput out) throws IOException {

		out.writeUTF(userid);
		out.writeUTF(movieid);
		out.writeInt(rate);
		out.writeLong(ts);
		out.writeUTF(movieName);
		out.writeUTF(movieType);
		
	}
	
	@Override
	public void readFields(DataInput in) throws IOException {

		this.userid = in.readUTF();
		this.movieid = in.readUTF();
		this.rate = in.readInt();
		this.ts = in.readLong();
		this.movieName = in.readUTF();
		this.movieType = in.readUTF();
	
	}
	
	@Override
	public int compareTo(MovieRate mr) {
		int it = mr.getMovieid().compareTo(this.movieid);
		if(it == 0){
			return mr.getUserid().compareTo(this.userid);
			
		}else{
			return it;
		}
	
	}

}

编写 MapReduce 程序：

package mapreduce.join.mapJoin;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.HashMap;
import java.util.Map;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.filecache.DistributedCache;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.zookeeper.common.IOUtils;

public class MovieRateMapJoinMR {
	public static void main(String[] args) throws Exception {
		
		Configuration conf = new Configuration();
		
		conf.set("fs.defaultFS", "hdfs://hadoop01:9000");
		System.setProperty("HADOOP_USER_NAME", "hadoop");
		
//		conf.set("mapreduce.framework.name", "yarn");
		
		Job job = Job.getInstance(conf);
		
		job.setJarByClass(MovieRateMapJoinMR.class);
		
		job.setMapperClass(MovieRateMapJoinMRMapper.class);
		job.setMapOutputKeyClass(MovieRate.class);
		job.setMapOutputValueClass(NullWritable.class);
		
		job.setNumReduceTasks(0);
		
		Path minPath = new Path(args[0]);
		
//		Path maxPath = new Path(args[0]);
//		Path outPath = new Path(args[1]);
		
		Path maxPath = new Path(args[1]);
//		URI uri = new URI("C:/Users/Administrator/Desktop/mapjoin/minpath");
//		DistributedCache.addCacheFile(uri, conf);
		Path outPath = new Path(args[2]);
		URI uri = minPath.toUri();
		job.addCacheFile(uri);
		
		FileSystem fs  = FileSystem.get(conf);
		if(fs.exists(outPath)){
			fs.delete(outPath, true);
		}
		
		FileInputFormat.setInputPaths(job, maxPath);
		FileOutputFormat.setOutputPath(job, outPath);
		
		boolean status = job.waitForCompletion(true);
		System.exit(status ? 0 : 1);
		
	}

	private static class MovieRateMapJoinMRMapper extends Mapper<LongWritable, Text, Text, NullWritable>{

		private static Map<String, String> movieMap = new HashMap<>();
		
		@Override
		protected void setup(Context context)
				throws IOException, InterruptedException {

			URI[] cacheFiles = context.getCacheFiles();
//			String path = cacheFiles[0].getPath();
			
//			Path[] localCacheFiles = DistributedCache.getLocalCacheFiles(context.getConfiguration());
			//通过context获取所有的缓存文件，并且获取缓存文件的路径等信息
//			Path[] localCacheFiles = context.getLocalCacheFiles();
//			String strPath = localCacheFiles[0].toUri().toString();
			
			Path cacheFile = new Path(cacheFiles[0]);
			
			String strPath = cacheFile.toUri().toString();
			
			
//			自定义读取逻辑去读这个文件，然后进行相关的业务处理
			BufferedReader br = new BufferedReader(new FileReader(strPath));
			String readLine = null;
			
			while(null != (readLine = br.readLine())){
				System.out.println(readLine);
				String[] movieFileds = readLine.split("::");
				String movieid = movieFileds[0];
				String moviename = movieFileds[1];
				String movieType = movieFileds[2];
				
				movieMap.put(movieid,moviename + "::" + movieType);
			
			}
			
			IOUtils.closeStream(br);
			
		}
		
		@Override
		protected void map(LongWritable key, Text value, Context context)
				throws IOException, InterruptedException {
			
			String[] splits = value.toString().split("::");
			String movieid  = splits[1];
			int rate = Integer.parseInt(splits[2]);
			long ts = Long.parseLong(splits[3]);
			String userid = splits[0];
			
//			map根据key到movieMap中去匹配小表数据
			String movieNameAndType = movieMap.get(movieid);
			String movieName = movieNameAndType.split("::")[0];
			String movieType = movieNameAndType.split("::")[1];
			
			MovieRate mr = new MovieRate(userid, movieid, rate, ts, movieName, movieType);
			
			context.write(new Text(mr.toString()), NullWritable.get());			
			
		}
	
	}
}