Mapreduce概述和WordCount程序

/**
 * @author: PrincessHug
 * @date: 2019/3/24, 0:52
 * @Blog: https://www.cnblogs.com/HelloBigTable/
 */
public class WordCountMapper extends Mapper {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //读取数据
        String line = value.toString();

        //切分数据
        String[] fields = line.split(" ");

        //传输数据
        for (String f:fields){
            context.write(new Text(f),new IntWritable(1));
        }
    }
}

public class WordCountReducer extends Reducer {
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
        //累加
        int sum = 0;
        for (IntWritable i:values){
            sum += i.get();
        }
        //输出
        context.write(key,new IntWritable(sum));
    }
}

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //配置，job对象
        Configuration cOnf= new Configuration();
        Job job = Job.getInstance();

        //设置运行类
        job.setJarByClass(WordCountDriver.class);

        //设置Mapper，Reducer类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //设置Mapper输出数据类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置Reducer输出数据类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置输入输出流
        FileInputFormat.setInputPaths(job,new Path("G:\\mapreduce\\wordcount\\in"));
        FileOutputFormat.setOutputPath(job,new Path("G:\\mapreduce\\wordcount\\out"));

        //提交任务
        if (job.waitForCompletion(true)){
            System.out.println("运行完成！");
        }else {
            System.out.println("运行失败！");
        }

    }

}