Mapreduce之sort

正序排序：

mapreduce本身自带排序，在map阶段是局部有序，在reduce阶段是全局有序的。

现在我们测试单个文件使用map输出

package com.hnxy.mr.Sort;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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;

/**
 * 
 * @author 耀君 正序排序 1 北京 2 天津 8 黑龙江 3 河北 5 内蒙古 4 山西 7 吉林 6 辽宁
 */
public class SortMr extends Configured implements Tool {
	public static class SortMrMapper extends Mapper<LongWritable, Text, LongWritable, Text> {
		LongWritable outkey = new LongWritable();
		Text outval = new Text();
		String[] str = null;

		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, LongWritable, Text>.Context context)
				throws IOException, InterruptedException {
			str = value.toString().split("\t");
			if (str.length == 2 && null != str) {
				outkey.set(Long.parseLong(str[0]));
				outval.set(str[1]);
				context.write(outkey, outval);
			}
		}
	}

	@Override
	public int run(String[] args) throws Exception {
		Configuration conf = this.getConf();
		Job job = Job.getInstance(conf, "job1");
		job.setJarByClass(SortMr.class);
		job.setMapperClass(SortMrMapper.class);
		// job.setReducerClass(SortMrReducer.class);
		job.setOutputKeyClass(LongWritable.class);
		job.setOutputValueClass(Text.class);
		// 设置路径
		Path in = new Path(args[0]);
		Path out = new Path(args[1]);
		FileInputFormat.addInputPath(job, in);
		FileOutputFormat.setOutputPath(job, out);
		// 创建操作HDFS
		FileSystem fs = FileSystem.get(conf);
		if (fs.exists(out)) {
			fs.delete(out, true);
		}
		boolean con = job.waitForCompletion(true);
		if (con) {
			System.out.println("execution succeed");
		} else {
			System.out.println("Execution failed");
		}
		return 0;
		// 执行
	}

	public static void main(String[] args) throws Exception {
		System.exit(ToolRunner.run(new SortMr(), args));

	}

}

运行结果：

这是一个文件要是两个文件呢？

运行结果：