Hadoop-MapReduce-MapJoin

    MapJoin适用于一张表示十分小，一张表十分大的场景。在Map端缓存多张表，提前处理业务逻辑，这样增加Map端业务，减少Reduce端数据的压力，尽可能的减少数据倾斜。

1 京东
2 淘宝
3 亚马逊

---

3 shampoo 25
1 novel 70
2 phone 3999
1 desk 94
3 noodles 20
2 ipad 4988
1 notebook 20
2 computer 5999
3 clothes 111
1 pen 4
3 pizza 60

    第一张表是公司（id，名称），第二张表的商品（id，商品名称，价格）。将这两个表合并（join），形成一个如下的新表。

1	京东 pen 4
1	京东 notebook 20
1	京东 desk 94
1	京东 novel 70
2	淘宝 computer 5999
2	淘宝 ipad 4988
2	淘宝 phone 3999
3	亚马逊 pizza 60
3	亚马逊 clothes 111
3	亚马逊 noodles 20
3	亚马逊 shampoo 25

---

    驱动类设置要加载的缓存数据，job.addCacheFile(new URI(“file:///e:/brand.txt”));，注意URL的格式（file:///）。

public class MapJoinDriver {
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException, URISyntaxException {
		args = new String[] {"e:/order.txt", "e:/output"};
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);
		job.setJarByClass(MapJoinDriver.class);
		job.setMapperClass(MapJoinMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		//加载缓存数据
		job.addCacheFile(new URI("file:///e:/brand.txt"));
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		boolean result = job.waitForCompletion(true);
		System.exit(result ? 0 : 1);
	}
}

    setup的时候缓存一张小表，map的时候就可以使用这张表。

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URI;
import java.util.HashMap;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class MapJoinMapper extends Mapper<LongWritable, Text, Text, Text>{
	
	Text k = new Text();
	Text v = new Text();
	HashMap<String, String> map = new HashMap<>();
	
	@Override
	protected void setup(Mapper<LongWritable, Text, Text, Text>.Context context)
			throws IOException, InterruptedException {
		URI[] uri = context.getCacheFiles();
		String path = uri[0].getPath().toString();
		BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(path), "UTF-8"));
		String line;
		while(StringUtils.isNotEmpty(line = reader.readLine())) {
			String[] split = line.split(" ");
			map.put(split[0], split[1]);
		}
		IOUtils.closeStream(reader);
	}
	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
			throws IOException, InterruptedException {
		String[] split = value.toString().split(" ");
		k.set(split[0]);
		v.set(map.get(split[0]) + " " + split[1] + " " + split[2]);
		context.write(k, v);
	}
}