Left join --案例2

参考xx 订单数据：

package com.testMr;

import java.io.IOException;
import java.util.ArrayList;
import java.util.LinkedList;
import java.util.List;

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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

public class LeftJoinDemo {

	public static class LeftJoinMap extends Mapper<LongWritable, Text, Text, Text> {
		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
				throws IOException, InterruptedException {
			String[] arr = value.toString().split(" ");
			FileSplit file = (FileSplit) context.getInputSplit();
			String path = file.getPath().toString();
			String ID;
			if (path.contains("trade.txt")) {
				ID = arr[0];
				context.write(new Text(ID), new Text(value.toString() + " " + "a"));
			} else {
				ID = arr[0];
				context.write(new Text(ID), new Text(value.toString() + " " + "b"));
			}
		}
	}

	public static class LeftJoinReduce extends Reducer<Text, Text, Text, Text> {
		@Override
		protected void reduce(Text arg0, Iterable<Text> arg1, Reducer<Text, Text, Text, Text>.Context arg2)
				throws IOException, InterruptedException {

			String a = null;
			List<String> b = new ArrayList<String>();
			String[] arr;
			for (Text line : arg1) {
				arr = line.toString().split(" ");
				if (arr[arr.length - 1].equals("a")) {
					a = line.toString();
				} else {
					b.add(line.toString());
				}
			}
			if (a != null) {
				String ID = a.split(" ")[0];
				String buyer = a.split(" ")[2];
				String city = a.split(" ")[3];
				String productName;
				String price;
				if (b.size() != 0) {
					for (String str : b) {
						productName = str.split(" ")[1];
						price = str.split(" ")[2];
						arg2.write(new Text(ID), new Text(buyer + " " + productName + " " + price + " " + city));
					}
				}
			}
		}

	}

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		System.out.println(args.length);
		for (String str : args) {
			System.out.println(str);
		}
		String input1 = args[0];
		String input2 = args[1];
		String outputPath = args[2];

		Job job = Job.getInstance();

		job.setJobName("test");
		job.setJarByClass(LeftJoinDemo.class);

		FileInputFormat.addInputPath(job, new Path(input1));
		FileInputFormat.addInputPath(job, new Path(input2));
		FileOutputFormat.setOutputPath(job, new Path(outputPath));

		job.setMapperClass(LeftJoinMap.class);
		job.setReducerClass(LeftJoinReduce.class);
		job.setPartitionerClass(HashPartitioner.class);
		job.setNumReduceTasks(1);

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

		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}

}