MapReduce实现hive join操作

1. hive中join就是一条select语句，其核心也是用mapreduce来写的，下面就用mapreduce模拟一个简单的join操作

首先准备数据：

假设我们有2张表：

表A（左表）数据：

1	a
2	b
3	c
3	d
4	e
6	f

表B（右表）数据：

1	10
2	20
3	30
4	40
4	400
5	50

我们需要得到的结果是：

1	a	10

2	b	20

3	c	30
3	d	30

4	e	40
4	e	400

我们知道mr的特性可以将key相同的value组合成一个list写出到reduce端，

我们在map阶段给每行记录打个标签，表示是来自于左表还是右表，如：map输出<1, l#a>，其中key是我们需要join中on的那个字段，在reduce端就能得到<1, <l#a, r#10>>这样的数据，那么我们就可以做join操作了。

其实也不难，下面贴出代码：

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

import org.apache.hadoop.conf.Configuration;
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;

public class JoinJob {

	public static final String DELIMITER = "\u0009";

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		if (args.length < 2) {
			System.out.println("参数数量不对，至少两个以上参数：<数据文件输出路径>、<输入路径...>");
			System.exit(1);
		}
		String dataOutput = args[0];
		String[] inputs = new String[args.length - 1];
		System.arraycopy(args, 1, inputs, 0, inputs.length);

		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf, "join 测试");
		job.setJarByClass(JoinJob.class);
		job.setMapperClass(MyMapper.class);
		job.setReducerClass(MyReducer.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);

		Path[] inputPathes = new Path[inputs.length];
		for (int i = 0; i < inputs.length; i++) {
			inputPathes[i] = new Path(inputs[i]);
		}
		Path outputPath = new Path(dataOutput);
		FileInputFormat.setInputPaths(job, inputPathes);
		FileOutputFormat.setOutputPath(job, outputPath);
		job.waitForCompletion(true);
	}

	static class MyMapper extends Mapper<LongWritable, Text, Text, Text> {
		private String inputPath;
		private String fileCode = "";

		protected void setup(Context context) throws IOException, InterruptedException {
			// 文件中属性前缀
			FileSplit input = (FileSplit) context.getInputSplit();
			inputPath = input.getPath().getName();
			try {
				fileCode = inputPath.split("_")[0];
			} catch (Exception e) {
				e.printStackTrace();
			}
		}

		@Override
		public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			String[] values = value.toString().split(DELIMITER);
			StringBuffer sb = new StringBuffer();
			sb.append(fileCode + "#");
			boolean first = true;
			for (String v : values) {
				if (!first) {
					sb.append(v + DELIMITER);
				}
				first = false;
			}
			context.write(new Text(values[0]), new Text(sb.toString().substring(0, sb.toString().length() - 1)));
		}
	}

	static class MyReducer extends Reducer<Text, Text, Text, Text> {
		@Override
		public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
			List<String> left = new ArrayList<String>();
			List<String> right = new ArrayList<String>();
			for (Text value : values) {
				String[] vv = value.toString().split("#");
				String fileCode = vv[0];
				if (fileCode.equals("l")) {
					// 左表数据
					left.add(vv[1]);
				} else {
					// 右表数据
					right.add(vv[1]);
				}
			}

			for (String l : left) {
				for (String r : right) {
					context.write(new Text(key), new Text(l + DELIMITER + r));
				}
			}
		}
	}
}