使用eclipse的快捷键自动生成的map或者reduce函数的参数中:“org.apache.hadoop.mapreduce.Reducer.Context context”

时间:2022-06-15 18:46:32

今天在测试mapreduce的程序时,就是简单的去重,对照课本上的程序和自己的程序,唯一不同的就是“org.apache.hadoop.mapreduce.Reducer.Context context”,我写的程序如下:

package com.pro.bq;

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 Dedup {
public static class Map extends Mapper<Object,Text, Text, Text>{
private Text line=new Text(); @Override
protected void map(Object key, Text value,
Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
line=value;
context.write(line, new Text("")); } }
public static class Reduce extends Reducer<Text, Text, Text, Text>
{ @SuppressWarnings("unchecked")
protected void reduce(Text key, Iterable<Text> value,
org.apache.hadoop.mapreduce.Reducer.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
context.write(key, new Text("")); }
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf=new Configuration();
// conf.set("mapred.job.tracker", "localhost:9001");
String hdfs=new String("hdfs://localhost:9000/user/haduser/");
String[] ioStr=new String[]{hdfs+"input",hdfs+"output/outDedup"}; //自己在代码中定义路径,否则的话就要就要在程序的输入参数中设置了
String[] otherStr=new GenericOptionsParser(conf, ioStr).getRemainingArgs(); if(otherStr.length!=2)
{
System.err.println("Usage: Data deduplication <in> <out>");
System.exit(2);
} Job job=new Job(conf, "Data deduplication");
job.setJarByClass(Dedup.class); job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherStr[0]));
FileOutputFormat.setOutputPath(job, new Path(otherStr[1]));
System.exit(job.waitForCompletion(true) ? 0:1); } }

课本上给出的程序如下:

package com.pro.bq;

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 Dedup {
public static class Map extends Mapper<Object,Text, Text, Text>{
private Text line=new Text(); protected void map(Object key, Text value,
Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
line=value;
context.write(line, new Text("")); } }
public static class Reduce extends Reducer<Text, Text, Text, Text>
{ protected void reduce(Text key, Iterable<Text> value,
Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
context.write(key, new Text("")); }
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf=new Configuration();
// conf.set("mapred.job.tracker", "localhost:9001");
String hdfs=new String("hdfs://localhost:9000/user/haduser/");
String[] ioStr=new String[]{hdfs+"input",hdfs+"output/outDedup"}; //自己在代码中定义路径,否则的话就要就要在程序的输入参数中设置了
String[] otherStr=new GenericOptionsParser(conf, ioStr).getRemainingArgs(); if(otherStr.length!=2)
{
System.err.println("Usage: Data deduplication <in> <out>");
System.exit(2);
} Job job=new Job(conf, "Data deduplication");
job.setJarByClass(Dedup.class); job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherStr[0]));
FileOutputFormat.setOutputPath(job, new Path(otherStr[1]));
System.exit(job.waitForCompletion(true) ? 0:1); } }

测试的文件file1.txt是:

2012-3-1 a
2012-3-2 b
2012-3-3 c
2012-3-4 d
2012-3-5 a
2012-3-6 b
2012-3-7 c
2012-3-3 c

file2.txt:

2012-3-1 b
2012-3-2 a
2012-3-3 b
2012-3-4 d
2012-3-5 a
2012-3-6 c
2012-3-7 d
2012-3-3 c

按照我写的运行的结果是:

2012-3-1 a
2012-3-1 b
2012-3-2 a
2012-3-2 b
2012-3-3 b
2012-3-3 c
2012-3-3 c
2012-3-3 c
2012-3-4 d
2012-3-4 d
2012-3-5 a
2012-3-5 a
2012-3-6 b
2012-3-6 c
2012-3-7 c
2012-3-7 d

想要的结果是:

2012-3-1 a
2012-3-1 b
2012-3-2 a
2012-3-2 b
2012-3-3 b
2012-3-3 c
2012-3-4 d
2012-3-5 a
2012-3-6 b
2012-3-6 c
2012-3-7 c
2012-3-7 d

不知道为什么?暂且记下,有懂的希望不吝赐教,我是菜鸟...