强-大数据第八讲

基于Hadoop的WordCount源码示例：

 

一、WordCountMain.java

package demo;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCountMain {

public static void main(String[] args) throws Exception {
//创建一个job = map + reduce
Configuration conf = new Configuration();

//创建一个Job
Job job = Job.getInstance(conf);
//指定任务的入口
job.setJarByClass(WordCountMain.class);

//指定job的mapper
job.setMapperClass(WordCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);

//指定job的reducer
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

//指定任务的输入和输出
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));

//提交任务
job.waitForCompletion(true);
}

}

二、WordCountMapper.java

package demo;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
/*
* key: 输入的key
* value: 数据 I love Beijing
* context: Map上下文
*/
String data= value.toString();
//分词
String[] words = data.split(" ");

//输出每个单词
for(String w:words){
context.write(new Text(w), new LongWritable(1));
}
}

}

三、WordCountReducer.java

package demo;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable>{

@Override
protected void reduce(Text k3, Iterable<LongWritable> v3,Context context) throws IOException, InterruptedException {
//v3: 是一个集合，每个元素就是v2
long total = 0;
for(LongWritable l:v3){
total = total + l.get();
}

//输出
context.write(k3, new LongWritable(total));
}

}