MR 练习 多表join

多表联查
      需求：从多文件输出factoryname    address
数据：

文本一：
      factoryname    id
       a    1
       b    2
       c    3
       d    4
       e    5
  文本二：          
       id    address
       1    A
       2    B
       3    C
       4    D
       5    E
            

输出效果：

factoryname    address
a    A
b    B
c    C
d    D
e    E

---

java code

package com.mxm.day26_1;

import java.io.IOException;

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.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 JoinTest2 extends Configured implements Tool {
	public static class MyMapper extends Mapper<LongWritable, Text, Text, Text> {
		boolean flag = false;

		@Override
		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			String line = value.toString();

			if (line.contains("factoryname")) {
				flag = true;
				return;
			} else if (line.contains("address")) {
				flag = false;
				return;
			}
			String[] split = line.split("\t");
			if (flag) {
				String id = split[1];
				String factoryname = split[0];
				context.write(new Text(id), new Text("1-" + factoryname));
			} else {
				String id = split[0];
				String address = split[1];
				context.write(new Text(id), new Text("2-" + address));
			}
		}

	}

	public static class MyReducer extends Reducer<Text, Text, Text, Text> {

		boolean flag = false;

		@Override
		protected void reduce(Text key, Iterable<Text> value, Context context)
				throws IOException, InterruptedException {
			if (!flag) {
				context.write(new Text("factoryname"), new Text("address"));

				flag = true;
			}
			String factoryname = "";
			String address = "";
			for (Text v : value) {
				String[] split = v.toString().split("-");
				if (split[0].equals("1")) {
					factoryname = split[1];
				} else if (split[0].equals("2")) {
					address = split[1];
				}
			}
			context.write(new Text(factoryname), new Text(address));

		}

	}

	@Override
	public int run(String[] args) throws Exception {
		Configuration conf = getConf();
		Job job = Job.getInstance(conf);
		job.setJarByClass(JoinTest2.class);

		job.setMapperClass(MyMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);

		job.setReducerClass(MyReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);

		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		int status = job.waitForCompletion(true) ? 0 : -1;
		return status;
	}

	public static void main(String[] args) throws Exception {
		int status = ToolRunner.run(new Configuration(), new JoinTest2(), args);
		System.exit(status);
	}

}