<repositories><repository><id>apache</id><url>http://maven.apache.org</url></repository>
</repositories>

<dependencies><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-core</artifactId><version>1.2.1</version></dependency><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-common</artifactId><version>2.7.2</version></dependency>
</dependencies>

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"><modelVersion>4.0.0</modelVersion><groupId>com.fun</groupId><artifactId>hadoop</artifactId><version>1.0-SNAPSHOT</version><repositories><repository><id>apache</id><url>http://maven.apache.org</url></repository></repositories><dependencies><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-core</artifactId><version>1.2.1</version></dependency><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-common</artifactId><version>2.7.2</version></dependency></dependencies><build><plugins><plugin><artifactId>maven-dependency-plugin</artifactId><configuration><excludeTransitive>false</excludeTransitive><stripVersion>true</stripVersion><outputDirectory>./lib</outputDirectory></configuration></plugin></plugins></build>
</project>

/*** Created by jinshilin on 16/12/7.*/
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.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 TokenizerMapperextends Mapper<Object, Text, Text, IntWritable> {private final static IntWritable one = new IntWritable(1);private Text word = new Text();public void map(Object key, Text value, Context context) throws IOException, InterruptedException {StringTokenizer itr = new StringTokenizer(value.toString());while (itr.hasMoreTokens()) {word.set(itr.nextToken());context.write(word, one);}}}public static class IntSumReducerextends Reducer<Text, IntWritable, Text, IntWritable> {private IntWritable result = new IntWritable();public void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {int sum = 0;for (IntWritable val : values) {sum += val.get();}result.set(sum);context.write(key, result);}}public static void main(String[] args) throws Exception {Configuration conf = new Configuration();Job job = Job.getInstance(conf, "word count");job.setJarByClass(WordCount.class);job.setMapperClass(TokenizerMapper.class);job.setCombinerClass(IntSumReducer.class);job.setReducerClass(IntSumReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);FileInputFormat.addInputPath(job, new Path(args[0]));FileOutputFormat.setOutputPath(job, new Path(args[1]));System.exit(job.waitForCompletion(true) ? 0 : 1);}
}