hadoop平台运行WordCount程序 - JAVA

1. 经典的WordCound程序（WordCount.java）
[java] view plaincopyprint
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool {

public static class MapClass extends MapReduceBase implements
Mapper {

private final static IntWritable one = new IntWritable(1);
private Text word = new Text();

public void map(LongWritable key, Text value,
OutputCollector output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
output.collect(word, one);
}
}
}

/**
* A reducer class that just emits the sum of the input values.

*/
public static class Reduce extends MapReduceBase implements
Reducer {

public void reduce(Text key, Iterator values,
OutputCollector output, Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}

static int printUsage() {
System.out.println("wordcount [-m ] [-r ] ");
ToolRunner.printGenericCommandUsage(System.out);
return -1;
}

/**
* The main driver for word count map/reduce program. Invoke this method to
* submit the map/reduce job.
*
* @throws IOException
* When there is communication problems with the job tracker.
*/
public int run(String[] args) throws Exception {
JobConf conf = new JobConf(getConf(), WordCount.class);
conf.setJobName("wordcount");

// the keys are words (strings)
conf.setOutputKeyClass(Text.class);
// the values are counts (ints)
conf.setOutputValueClass(IntWritable.class);

conf.setMapperClass(MapClass.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);

List other_args = new ArrayList();
for (int i = 0; i < args.length; ++i) {
try {
if ("-m".equals(args[i])) {
conf.setNumMapTasks(Integer.parseInt(args[++i]));
} else if ("-r".equals(args[i])) {

hadoop平台运行WordCount程序(一)