仅供参考 出自hadoop in action
import java.io.IOException;
import java.io.InterruptedIOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class MyJob extends Configured implements Tool{
public static class MapClass extends Mapper<LongWritable,Text,Text,Text>{
public void map(LongWritable key,Text value,Context context)throws IOException, InterruptedException{
String[] citation=value.toString().split(",");
context.write(new Text(citation[1]), new Text(citation[0]));
}//end map
}//end MapClass class
public static class Reduce extends Reducer<Text,Text,Text,Text>{
public void reduce(Text key,Iterator<Text> values,Context context) throws IOException, InterruptedException{
String csv="";
while(values.hasNext()){
if(csv.length()>0) csv+=",";
csv+=values.next().toString();
}//end while
context.write(key, new Text(csv));
}//end
}//end Reducer
public int run(String[] args)throws Exception{
Configuration conf =getConf();
Job job = new Job(conf,"MyJob");
job.setJarByClass(MyJob.class);
Path in = new Path(args[0]);
Path out = new Path(args[1]);
FileOutputFormat.setOutputPath(job, out);
job.setJobName("MyJob");
job.setMapperClass(MapClass.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
System.exit(job.waitForCompletion(true)?0:1);
return 0;
}//end run method
public static void main(String[] args) throws Exception{
int res = ToolRunner.run(new Configuration(), new MyJob(), args);
System.exit(res);
}//end main method
}//end class MyJob