Hadoop之Mapreduce------>入门级程序WordCount代码编写

一 、Mapper编写

继承Mapper类------>重写map方法------>实现具体业务逻辑------>将新的key,value输出

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

    @Override

    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        //接收数据V1

        String line = value.toString();

//按照空格切分成单词

        String[] words = line.split(" ");

        for (String w : words) {

            //出现一次记1

            context.write(new Text(w), new LongWritable(1));

        }

    }

}

一 、Reducer编写

继承Reducer类------>重写reduce方法------>实现具体业务逻辑------>将新的key,value输出

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

    @Override

    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

        //接受数据

//        Text k3 = key;

        //定义一个计数器
        long counter = 0;

       //遍历values集合，并求和

        for(LongWritable i:values){

            counter += i.get();

        }

       //将新的key,value输出

        context.write(key,new LongWritable(counter));

    }

}

三 、主函数编写

public class WordCount {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //构建job类

        Job job = Job.getInstance(new Configuration());

        //注意main方法所在的类，别忘记设置setJarByClass

        job.setJarByClass(WordCount.class);

        //设置mapper相关属性

        job.setMapperClass(WCMapper.class);

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputValueClass(LongWritable.class);

//设置源文件

        FileInputFormat.setInputPaths(job,new Path("/wordcount"));

        //设置Rueduce相关属性

        job.setReducerClass(WCReducer.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(LongWritable.class);

//设置输出文件

        FileOutputFormat.setOutputPath(job,new Path("/wcout126"));

        //提交任务

        job.waitForCompletion(true);

    }

}