Created
November 23, 2010 16:27
-
-
Save kzk/712029 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* WordCount.java - the very-first MapReduce Program | |
* | |
* <h1>How To Compile</h1> | |
* export HADOOP_HOME=/usr/lib/hadoop-0.20/ | |
* export DIR=wordcount_classes | |
* rm -fR $DIR | |
* mkdir $DIR | |
* javac -classpath ${HADOOP_HOME}/hadoop-core.jar -d $DIR WordCount.java | |
* jar -cvf wordcount.jar -C $DIR . | |
*/ | |
package net.kzk9; | |
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.input.TextInputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; | |
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; | |
public class WordCount { | |
public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> { | |
private final static 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 Reduce extends Reducer<Text, IntWritable, Text, IntWritable> { | |
private IntWritable value = new IntWritable(0); | |
@Override | |
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { | |
int sum = 0; | |
for (IntWritable value : values) | |
sum += value.get(); | |
value.set(sum); | |
context.write(key, value); | |
} | |
} | |
public static void main(String[] args) throws Exception { | |
Configuration conf = new Configuration(); | |
Job job = new Job(conf, "wordcount"); | |
job.setJarByClass(WordCount.class); | |
job.setOutputKeyClass(Text.class); | |
job.setOutputValueClass(IntWritable.class); | |
job.setMapperClass(Map.class); | |
job.setReducerClass(Reduce.class); | |
job.setInputFormatClass(TextInputFormat.class); | |
job.setOutputFormatClass(TextOutputFormat.class); | |
job.setNumReduceTasks(1); | |
FileInputFormat .setInputPaths(job, new Path(args[0])); | |
FileOutputFormat.setOutputPath(job, new Path(args[1])); | |
boolean success = job.waitForCompletion(true); | |
System.out.println(success); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Great