Hadoop AWS Word Count 例子

在AWS里用Elastic Map Reduce 开一个Cluster
然后登陆master node并编译以下程序：

import java.io.IOException;
import java.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.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;

public class WordCount {

public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

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

@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while(tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}

}

public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for(IntWritable value : values) {
sum += value.get();
}
context.write(key, new IntWritable(sum));
}

}

public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = new Job(conf, "Word Count hadoop-0.20");

//setting the class names
job.setJarByClass(WordCount.class);
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);

//setting the output data type classes
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);

//to accept the hdfs input and outpur dir at run time
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));

System.exit(job.waitForCompletion(true) ? 0 : 1);
}

}


设置：
export CLASSPATH=$CLASSPATH:/home/hadoop/*:/home/hadoop/lib/*:'.'

javac WordCount.java
jar cvf WordCount.jar *.class
hadoop jar WordCount.jar WordCount s3://15-319-s13/book-dataset/pg_00 /output

运行成功后，因为output文件夹在Hadoop FS下，所以可以这样查看：
hadoop fs -cat /output/part-r-00000  | less

主要参考：
http://kickstarthadoop.blogspot.com/2011/04/word-count-hadoop-map-reduce-example.html

http://kickstarthadoop.blogspot.com/2011/05/word-count-example-with-hadoop-020.html