Hadoop 求单词count数

package com.yw.hadoop273;

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;

/**

 * @Auther: YW

 * @Date: 2019/9/18 20:58

 * @Description:

 */

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

    /*

    * Mapper 
　　*   把单词分割出来

    * */

    @Override

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

        Text keyOut = new Text();

        IntWritable valueOut = new IntWritable();

        String[] arr = value.toString().split("");

        for (String s : arr) {

            keyOut.set(s);

            valueOut.set();

            context.write(keyOut,valueOut);

        }

    }

}

package com.yw.hadoop273;

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

import java.io.IOException;

/**
 * @Auther: YW
 * @Date: 2019/9/18 21:20
 * @Description:
 */
public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    /***
     *  聚合
     */

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count=0;
        for (IntWritable value : values) {
            count = count + value.get();
        }
        context.write(key,new IntWritable(count));
    }

}

package com.yw.hadoop273;

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.input.TextInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**

 * @Auther: YW

 * @Date: 2019/9/16 21:20

 * @Description:

 */

public class WCApp {

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

        Configuration conf = new Configuration();

        // 删除已有的目录

        if (args.length>1){

            FileSystem.get(conf).delete(new Path(args[1]));

        }

        Job job = Job.getInstance(conf);

        //  设置job属性

        job.setJobName("WCApp");        // 设置作业名称

        job.setJarByClass(WCApp.class); // 设置搜索类

        job.setInputFormatClass(TextInputFormat.class);// 设置输入格式

        FileInputFormat.addInputPath(job,new Path(args[0])); // 输入路径

        FileOutputFormat.setOutputPath(job,new Path(args[1]));// 输出路径

        job.setMapperClass(WCWordCount.class);  // 设置mapper 类

        job.setReducerClass(WCReducer.class);   //  设置reducer类

        job.setNumReduceTasks(1);               // reducer个数

        job.setMapOutputKeyClass(Text.class);

        job.setMapOutputKeyClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputKeyClass(IntWritable.class);

    }

}

巴特西

Hadoop 求单词count数

最新文章

热门文章