Created
January 7, 2016 21:35
-
-
Save miholeus/f93e8790a75e221d98c8 to your computer and use it in GitHub Desktop.
Hadoop WordCount example
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
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.mapreduce.*; | |
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; | |
/** | |
* Hadoop WordCount first program | |
*/ | |
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(); | |
public 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> { | |
public void reduce(Text key, Iterable<IntWritable> values, Context context) | |
throws IOException, InterruptedException { | |
int sum = 0; | |
for (IntWritable val : values) { | |
sum += val.get(); | |
} | |
context.write(key, new IntWritable(sum)); | |
} | |
} | |
public static void main(String[] args) throws Exception { | |
Configuration conf = new Configuration(); | |
Job job = new Job(conf, "wordcount"); | |
job.setOutputKeyClass(Text.class); | |
job.setOutputValueClass(IntWritable.class); | |
job.setMapperClass(Map.class); | |
job.setReducerClass(Reduce.class); | |
job.setInputFormatClass(TextInputFormat.class); | |
job.setOutputFormatClass(TextOutputFormat.class); | |
FileInputFormat.addInputPath(job, new Path(args[0])); | |
FileOutputFormat.setOutputPath(job, new Path(args[1])); | |
job.waitForCompletion(true); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment