From 26c490f404731d053a6205719b6246502c07b449 Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Sat, 14 Jun 2014 16:46:27 +0200
Subject: init

---
 hadoop/wordcount/WordCount.java | 57 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)
 create mode 100644 hadoop/wordcount/WordCount.java

(limited to 'hadoop/wordcount/WordCount.java')

diff --git a/hadoop/wordcount/WordCount.java b/hadoop/wordcount/WordCount.java
new file mode 100644
index 0000000..8917aee
--- /dev/null
+++ b/hadoop/wordcount/WordCount.java
@@ -0,0 +1,57 @@
+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 {
+
+   // Mapper
+   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(); // TextInputFormat
+       StringTokenizer tokenizer = new StringTokenizer(line);
+       while (tokenizer.hasMoreTokens()) {
+         word.set(tokenizer.nextToken());
+         output.collect(word, one);
+       }
+     }
+   }
+
+   // Reducer
+   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));
+     }
+   }
+
+   // Driver
+   public static void main(String[] args) throws Exception {
+     JobConf conf = new JobConf(WordCount.class);
+     conf.setJobName("wordcount");
+     conf.setNumReduceTasks(200);
+     conf.setOutputKeyClass(Text.class);
+     conf.setOutputValueClass(IntWritable.class);
+     conf.setMapperClass(Map.class);
+     conf.setCombinerClass(Reduce.class); // Combiner
+     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);
+   }
+
+}
+
-- 
cgit v1.2.3