新版MapReduce的API编程简单模板

新版MapReduce的API编程简单模板import java.io.IOException;
import java.util.*;import org.apache.Hadoop.conf.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;
import org.apache.hadoop.util.*;public class MyJob extends Configured implements Tool{
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable（1）;
private Text word = new Text（）;
public void map（LongWritable key, Text value, Context context） throws IOException, InterruptedException {
String line = value.toString（）;
StringTokenizer tokenizer = new StringTokenizer（line," f,.:？！[]"`;"）;
while （tokenizer.hasMoreTokens（）） {
word.set（tokenizer.nextToken（））;
context.write（word, one）;
}
}
} public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce（Text key, Iterable<IntWritable> values, Context context） throws IOException, InterruptedException {
int sum = 0;
while （values.iterator（）.hasNext（）） {
sum += values.iterator（）.next（）.get（）;
}
context.write（key, new IntWritable（sum））;
}
}

public int run（String[] args） throws Exception {
Configuration conf=getConf（）;

Job job= new Job（conf,"WordCount"）;
job.setJarByClass（MyJob.class）;

FileInputFormat.setInputPaths（job, new Path（args[0]））;
FileOutputFormat.setOutputPath（job, new Path（args[1]））;

job.setJobName（"WordCount"）;
job.setMapperClass（Map.class）;
job.setCombinerClass（Reduce.class）;
job.setReducerClass（Reduce.class）;

job.setInputFormatClass（TextInputFormat.class）;
job.setOutputFormatClass（TextOutputFormat.class）;
job.setOutputKeyClass（Text.class）;
job.setOutputValueClass（IntWritable.class）;
System.exit（job.waitForCompletion（true）？0:1） ;
return 1;
}

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