WordCount类
package org.apache.hadoop.examples;
import java.io.IOException;
import jvaa.util.StringTokenizer;
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.FileInputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount{
public static class TokenizerMapper //Map
extends Mapper<Object, Text, Text, IntWritable>
{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedExeption{
StringTokenizer itr = new StringTokenizer(value.toString)
while(itr.hasMoreTokens()){
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer //Reduce
extends Reducer<Object, Text, Text, IntWritable>
{
private IntWritable result = new IntWritable();
public void reduce (Text key, Iterable<IntWritable> values, context context)
throws IOException, InterruptedException{
int sum = 0;
for (IntWritable val: values){
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
}
public static void main (String [] args) throws Exception{
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if(otherArgs.length!=2){
System.err.println("Usage arg err!");
System(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper);
job.setCombinerClass(IntSumReducer);
job.setReducerClass(IntSumReducer);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0));
FileOutPutFormat.addOuputtPath(job, new path(otherArgs[1])
System.exit(job.waitForCompletion(true?1:0);
}
本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系:hwhale#tublm.com(使用前将#替换为@)