基于hadoop0.20.2mapreducer的实例

package com.founder.hadoop.mapreduce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class TestMapReduce2 extends Configured implements Tool {
enum Counter {
LINESKIP
}

public static class Map extends
Mapper<LongWritable, Text, Text, Text> {
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
try{
String line = value.toString();
String[] lines = line.split(" ");
String anum = lines[0];
String bnum = lines[1];

Text outa = new Text(anum);
Text outb = new Text(bnum);
context.write(outb, outa) ;
}catch(java.lang.ArrayIndexOutOfBoundsException e){
context.getCounter(Counter.LINESKIP).increment(1);
return ;
}
}
}

public static class Reduce extends Reducer<Text, Text, Text, Text> {

protected void reduce(Text key, Iterable<Text> values,Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
  String valueString;
  String out="";
  for(Text value : values){
  valueString = value.toString();
  out += valueString + "|" ;
  }
  context.write(key, new Text(out)) ;
}
}


@Override
public int run(String[] arg) throws Exception {
// TODO Auto-generated method stub
Configuration conf = getConf();
Job job = new Job(conf, "TestMapReduce2");// 任务名称
job.setJarByClass(TestMapReduce2.class);// 指定class
FileInputFormat.addInputPath(job, new Path(arg[0]));// 输入路径
FileOutputFormat.setOutputPath(job, new Path(arg[1]));// 输出路径
job.setMapperClass(Map.class);//调用上面Map类作为作为map任务代码
job.setReducerClass(Reduce.class);
job.setOutputFormatClass(TextOutputFormat.class);//
job.setOutputKeyClass(Text.class);//指定输出key的格式
job.setOutputValueClass(Text.class);//指定输出value的格式
job.waitForCompletion(true);

return job.isSuccessful() ? 0 : 1;
}

public static void main(String args[]) throws Exception {
int res = ToolRunner.run(new Configuration(), new TestMapReduce2(),
args);
System.exit(res);
}
}