<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>practice.hadoop</groupId>
	<artifactId>simple-examples</artifactId>
	<version>0.0.1-SNAPSHOT</version>
	<packaging>jar</packaging>
 
	<name>simple-examples</name>
	<url>http://maven.apache.org</url>
 
	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
	</properties>
 
	<dependencies>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>4.12</version>
			<scope>test</scope>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-common</artifactId>
			<version>2.7.0</version>
		</dependency>
 
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-hdfs</artifactId>
			<version>2.7.0</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-client -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-client</artifactId>
			<version>2.7.0</version>
		</dependency>
 		
 		<dependency>
			<groupId>org.apache.mrunit</groupId>
			<artifactId>mrunit</artifactId>
			<version>1.1.0</version>
			<classifier>hadoop2</classifier>
			<scope>test</scope>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-core -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-mapreduce-client-core</artifactId>
			<version>2.7.0</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-yarn-api -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-yarn-api</artifactId>
			<version>2.7.0</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-auth -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-auth</artifactId>
			<version>2.7.0</version>
		</dependency>

		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-minicluster -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-minicluster</artifactId>
			<version>2.7.0</version>
			<scope>test</scope>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-jobclient -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-mapreduce-client-jobclient</artifactId>
			<version>2.7.0</version>
			<scope>provided</scope>
		</dependency>
 
	</dependencies>
</project>

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;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

	public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {

		/**
		 * LongWritable, IntWritable, Text 均是 Hadoop 中實現(xiàn)的用于封裝 Java
		 * 數(shù)據(jù)類型的類，這些類實現(xiàn)了WritableComparable接口，
		 * 都能夠被串行化從而便于在分布式環(huán)境中進行數(shù)據(jù)交換，你可以將它們分別視為long,int,String 的替代品。
		 */
		private final static IntWritable one = new IntWritable(1); // 值為1
		private Text word = new Text();

		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
			StringTokenizer itr = new StringTokenizer(value.toString()); // 對字符串進行切分
			while (itr.hasMoreTokens()) {
				word.set(itr.nextToken());
				context.write(word, one); 
			}
		}
	}

	public static class IntSumReducer extends 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();
    conf.addResource("classpath:/hadoop/core-site.xml");
    conf.addResource("classpath:/hadoop/hdfs-site.xml");
    conf.addResource("classpath:/hadoop/mapred-site.xml");
//		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		String[] otherArgs = {"/input", "/output"};
		if (otherArgs.length != 2) {
			System.err.println("Usage: wordcount <in> <out>");
			System.exit(2);
		}
		Job job = new Job(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.setInputDirRecursive(job, true);
		FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}

}