MapReduce编程:数字排序
问题描述
将乱序数字按照升序排序。
思路描述
按照mapreduce的默认排序,依次输出key值。
代码
package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
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;
public class sort {
public sort() {
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String fileAddress = "hdfs://localhost:9000/user/hadoop/";
//String[] otherArgs = (new GenericOptionsParser(conf, args)).getRemainingArgs();
String[] otherArgs = new String[]{fileAddress+"number.txt", fileAddress+"output"};
if(otherArgs.length < 2) {
System.err.println("Usage: sort [...] ");
System.exit(2);
}
Job job = Job.getInstance(conf, "sort");
job.setJarByClass(sort.class);
job.setMapperClass(sort.TokenizerMapper.class);
//job.setCombinerClass(sort.SortReducer.class);
job.setReducerClass(sort.SortReducer.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(IntWritable.class);
for(int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true)?0:1);
}
public static class TokenizerMapper extends Mapper
注:不能有combiner操作。
不然就会变成