设计思路:
使用mapreduce的默认排序,按照key值进行排序的,如果key为封装int的IntWritable类型,那么MapReduce按照数字大小对key排序,如果key为封装为String的Text类型,那么MapReduce按照字典顺序对字符串排序。
首先map阶段将输入的数字作为key, 并记录相同key出现的次数,在reduce阶段将输入的key作为输出的value,如果相同值存在多个,循环便利输出。
源数据:file1
2
32
654
32
15
756
65223
file2
5956
22
650
92
file3
26
54
6
2
15
源代码
package com.duking.hadoop;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class DataSort {
public static class Map extends
Mapper<Object, Text, IntWritable, IntWritable> {
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(); // 将输入的每一行数据转换为String类型
data.set(Integer.parseInt(line)); // 将String 转换为Integer
context.write(data, new IntWritable(1)); // 将 date->key
// 统计key出现的次数自增为value
}
}
// reduce将输入中的key复制到输出数据的key上,并直接输出 这是数据区重的思想
public static class Reduce extends
Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {
private static IntWritable linenum = new IntWritable(1);
private IntWritable result = new IntWritable();
// 实现reduce函数
public void reduce(IntWritable key, Iterable<IntWritable> values, //Iterable转为List
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", "192.168.60.129:9000");
// 指定带运行参数的目录为输入输出目录
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
/*
* 指定工程下的input2为文件输入目录 output2为文件输出目录 String[] ioArgs = new String[] {
* "input2", "output2" };
*
* String[] otherArgs = new GenericOptionsParser(conf, ioArgs)
* .getRemainingArgs();
*/
if (otherArgs.length != 2) { // 判断路径参数是否为2个
System.err.println("Usage: Data Deduplication <in> <out>");
System.exit(2);
}
// set maprduce job name
Job job = new Job(conf, "Data sort");
job.setJarByClass(DataSort.class);
// 设置Map、Combine和Reduce处理类
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.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);
}
}
结果
1 2
2 2
3 6
4 15
5 15
6 22
7 26
8 32
9 32
10 54
11 92
12 650
13 654
14 756
15 5956
16 65223