MapReduce的简单入门级代码

1. 需求：统计以下ip出现的次数

        IP              应用             网站
192.168.0.1		 QQ 	    com.baidu.com
192.168.0.4		 QQ 	   	com.baidu.com
192.168.0.2 	 QQ 	 	com.baidu.com
192.168.0.3 	 QQ 		com.baidu.com
192.168.0.1 	 QQ		    com.baidu.com

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 java.io.IOException;

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

    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] str= value.toString().split(" ");
        String ip = str[1];
        context.write(new Text(ip),new IntWritable(1));
    }
}

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

    /**
     *
     * @param key 行字节偏移量
     * @param values 一行文本数据
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int total = 0;
        for(IntWritable intWritab:values){
            total+=intWritab.get();
        }
        context.write(key,new IntWritable(total));
    }
}

public class CustomJobSubmitter extends Configured implements Tool {

    public int run(String[] strings) throws Exception {
        //1.封装job
        Configuration conf=getConf();
        Job job= Job.getInstance(conf);

        job.setJarByClass(CustomJobSubmitter.class);
        //2.设置分析|输出数据格式类型
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        //3.设置数据读入和写出路径
        Path src = new Path("/demo/access");
        TextInputFormat.addInputPath(job,src);
        Path dst = new Path("/demo/res");//必须为null（目录必须不存在）
        TextOutputFormat.setOutputPath(job,dst);

        //4.设置Mapper和Reducer逻辑
        job.setMapperClass(AccessMapper.class);
        job.setReducerClass(AccessReducer.class);

        //5.设置Mapper和Reducer的输出k/v类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //6.提交任务
        job.waitForCompletion(true);//表示看执行的结果
        return 0;
    }

    public static void main(String[] args) throws Exception {
        ToolRunner.run(new CustomJobSubmitter(),args);
    }

}

5.package
6.上传到linux系统 运行即可