理解Hadoop源码 --- WordCount

Gradle:

group 'yqg'
version '1.0-SNAPSHOT'

apply plugin: 'java'

sourceCompatibility = 1.8

repositories {
mavenCentral()

}

dependencies {
testCompile group: 'junit', name: 'junit', version: '4.12'
// https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common compile group: 'org.apache.hadoop', name: 'hadoop-common', version: '2.8.1'
// https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-core compile group: 'org.apache.hadoop', name: 'hadoop-core', version: '2.6.0-mr1-cdh5.12.1', ext: 'pom'
// https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-hdfs compile group: 'org.apache.hadoop', name: 'hadoop-hdfs', version: '2.8.1'
// https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-core compile group: 'org.apache.hadoop', name: 'hadoop-mapreduce-client-core', version: '2.8.1'
// https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-yarn-api compile group: 'org.apache.hadoop', name: 'hadoop-yarn-api', version: '2.8.1'
// https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-client-jobclient provided group: 'org.apache.hadoop', name: 'hadoop-mapreduce-client-jobclient', version: '2.8.1'

compile group: 'org.apache.hadoop', name: 'hadoop-mapreduce', version: '2.8.1', ext: 'pom'
}

package wordcount;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
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;
import java.io.IOException;
import java.util.StringTokenizer;

/**
* @author Ryan
*/

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.hasMoreElements()){
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);
}

}