hadoop 数据排序

1、输入

file1.txt

23
8
24
34
234234
3
5
6
5
5

file2.txt

123
2
4
45678
56
78
102
56
23
99999
99
999

2、问题、思路

问题:

将上面两个文件,排序,结果要求:每行两个数 第一个是序号,第二个是数值

思路:

map阶段进行取词,reduce接受到的数据已经是有序的(hadoop已排好),那么reduce需要计数

3、代码

package smiple;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.GenericOptionsParser;

public class Sort {
	
	// map将输入中的value化成IntWritable类型,作为输出的key
	public static class MyMap extends Mapper {
		private static IntWritable data = new IntWritable();

		// 实现map函数
		public void map(Object key, Text value, Context context)
				throws IOException, InterruptedException {
			String line = value.toString();
			data.set(Integer.parseInt(line));
			context.write(data, new IntWritable(1));
		}
	}

	/**
	 * reduce将输入中的key复制到输出数据的key上,
	 * 然后根据输入的value-list中元素的个数决定key的输出次数
	 * 用全局linenum来代表key的位次
	 * @author allen
	 *
	 */
	public static class MyReduce extends Reducer {
		private static IntWritable linenum = new IntWritable(1);

		// 实现reduce函数
		public void reduce(IntWritable key, Iterable values,
				Context context) throws IOException, InterruptedException {
			for (IntWritable val : values) {
				context.write(linenum, key);
				linenum = new IntWritable(linenum.get() + 1);
			}
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
//		conf.set("mapred.job.tracker", "ip:端口");
		String[] ioArgs = new String[] { "hdfs://ip:端口/mr/sort/sort_in", "hdfs://ip:端口/mr/sort/sort_out" };
		String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();

		if (otherArgs.length != 2) {
			System.err.println("Usage: Data Sort  ");
			System.exit(2);
		}
		Job job = new Job(conf, "Data Sort");
		
		job.setJarByClass(Sort.class);
		
		// 设置Map和Reduce处理类
		job.setMapperClass(MyMap.class);
		job.setReducerClass(MyReduce.class);
		
		// 设置输出类型
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(IntWritable.class);

		// 设置输入和输出目录
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

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

	}

}


4、结果

1 2
2 3
3 4
4 5
5 5
6 5
7 6
8 8
9 23
10 23
11 24
12 34
13 56
14 56
15 78
16 99
17 102
18 123
19 999
20 45678
21 99999
22 234234


声明: 参考 http://www.cnblogs.com/xia520pi/archive/2012/06/04/2534533.html


你可能感兴趣的:(Hadoop学习与使用)