Hadoop: Contoh Program Sederhana
Sumber:
- http://www.drdobbs.com/database/hadoop-writing-and-running-your-first-pr/240153197
- https://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html
Source Code
Contoh source code WordCount.java untuk menghitung jumlah masing-masing kata dari sebuah input set.
cd ~ vi WordCount.java
package org.myorg;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;
public class WordCount {
public static class Map extends MapReduceBase implements 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, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}
public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
}
Compile
Asumsinya HADOOP_HOME adalah root instalasi dan HADOOP_VERSION adalah versi Hadoop yang di install, compile WordCount.java dan buat jar:
mkdir wordcount_classes
javac -classpath ${HADOOP_HOME}/hadoop-${HADOOP_VERSION}-core.jar -d wordcount_classes WordCount.java
jar -cvf /usr/joe/wordcount.jar -C wordcount_classes/ .
Penggunaan
Asumsi
/usr/joe/wordcount/input - input directory di HDFS /usr/joe/wordcount/output - output directory di HDFS
Sample text-files as input:
bin/hadoop dfs -ls /usr/joe/wordcount/input/ /usr/joe/wordcount/input/file01 /usr/joe/wordcount/input/file02
bin/hadoop dfs -cat /usr/joe/wordcount/input/file01 Hello World Bye World
bin/hadoop dfs -cat /usr/joe/wordcount/input/file02 Hello Hadoop Goodbye Hadoop
Jalankan aplikasi
bin/hadoop jar /usr/joe/wordcount.jar org.myorg.WordCount /usr/joe/wordcount/input /usr/joe/wordcount/output
Output:
bin/hadoop dfs -cat /usr/joe/wordcount/output/part-00000 Bye 1 Goodbye 1 Hadoop 2 Hello 2 World 2