1.添加MapReduce的相关jar包
2.实现map()方法
package com.mapreduce;
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;
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private Text outK=new Text();
private IntWritable outV= new IntWritable(1);
protected void map(LongWritable key, Text value,Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
super.map(key, value, context);
String data=value.toString();
String[] words=data.split("[,\\.\\s]+");
for(String word : words){
outK.set(word);
context.write(outK,outV);
}
}
}
3.实现reduce()方法
package com.mapreduce;
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> {
private IntWritable outV=new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
super.reduce(key, values, context);
int sum=0;
for (IntWritable value : values) {
sum += value.get();
}
outV.set(sum);
context.write(key, outV);
}
}
4.drive部分:
package com.mapreduce;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.IntWritable;
public class WordCountDriver {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job =Job.getInstance(conf);
job.setJarByClass(WordCountDriver.class);
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path(c:****)); //设置文件input的输入路径
FileOutputFormat.setOutputPath(job,new Path(c:****)); //设置输出路径output,注意输出路径文件必须是新建的,如果已经存在则无法运行
boolean result=job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
将需要统计的文件放入 input文件夹,本地运行程序。output中即可查看结果
用命令行参数指定输入路径和输出路径
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
之后即可在集群中上传需要执行的文件,集群中运行程序