Hadoop MapReduce编程 API入门系列之wordcount版本3（七）

　　这篇博客，给大家，体会不一样的版本编程。

代码

package zhouls.bigdata.myMapReduce.wordcount3;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;

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

//该方法循环调用，从文件的split中读取每行调用一次，把该行所在的下标为key，该行的内容为value
protected void map(LongWritable key, Text value,
Context context)
throws IOException, InterruptedException {
String[] words = StringUtils.split(value.toString(), ' ');
for(String w :words){
context.write(new Text(w), new IntWritable(1));
}
}
}

package zhouls.bigdata.myMapReduce.wordcount3;

import java.io.IOException;

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

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

//每组调用一次，这一组数据特点：key相同，value可能有多个。
protected void reduce(Text arg0, Iterable<IntWritable> arg1,
Context arg2)
throws IOException, InterruptedException {
int sum =0;
for(IntWritable i: arg1){
sum=sum+i.get();
}
arg2.write(arg0, new IntWritable(sum));
}
}

package zhouls.bigdata.myMapReduce.wordcount3;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class RunJob {

public static void main(String[] args) {
Configuration config =new Configuration();

try {
FileSystem fs =FileSystem.get(config);

Job job =Job.getInstance(config);
job.setJarByClass(RunJob.class);

job.setJobName("wc");

job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);

job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);

FileInputFormat.addInputPath(job, new Path("./data/wc.txt"));

Path outpath =new Path("./out/WordCountout");
if(fs.exists(outpath)){
fs.delete(outpath, true);
}
FileOutputFormat.setOutputPath(job, outpath);

boolean f= job.waitForCompletion(true);
if(f){
System.out.println("job任务执行成功");
}
} catch (Exception e) {
e.printStackTrace();
}
}
}