hadoop-mapreduce-wordcount-api

 

/**
 * 
 */
package com.lxl.hadoop.mr;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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.output.FileOutputFormat;

/**
 * Description:
 * 
 * @author LXL
 * @date 2019年5月23日
 */
public class MyWC {

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

        Configuration conf = new Configuration(true);

        Job job = Job.getInstance(conf);

        // Create a new Job
        // Job job = Job.getInstance();
        job.setJarByClass(MyWC.class);

        // Specify various job-specific parameters
        job.setJobName("ooxx");

        
        
        //输入
        // job.setInputPath(new Path("in"));
        // job.setOutputPath(new Path("out"));
        
        Path input = new Path("/user/root/test.txt");
        FileInputFormat.addInputPath(job, input );
        
        
        //输出
        Path output = new Path("/data/wc/output");
        
        if(output.getFileSystem(conf).exists(output)){
            output.getFileSystem(conf).delete(output, true);
        }
        
        FileOutputFormat.setOutputPath(job, output);
        
        

        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(MyReducer.class);

        // Submit the job, then poll for progress until the job is complete
        job.waitForCompletion(true);

    }

}

/**
 * 
 */
package com.lxl.hadoop.mr;

import java.io.IOException;
import java.util.StringTokenizer;

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

/**
 * Description:
 * 
 * @author LXL
 * @date 2019年5月24日
 */
public class MyMapper extends Mapper<Object, Text, Text, IntWritable> {

    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

        // hello sxt 102
        StringTokenizer itr = new StringTokenizer(value.toString());
        while (itr.hasMoreTokens()) {
            word.set(itr.nextToken());
            context.write(word, one);

        }
    }

}

/**
 * 
 */
package com.lxl.hadoop.mr;

import java.io.IOException;

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

/**
 * Description:
 * 
 * @author LXL
 * @date 2019年5月24日
 */
public class MyReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    // 相同的key为一组。。调用一次reduce方法，在方法内迭代这一组数据，进行计算：sum count max min.....

    private IntWritable result = new IntWritable();

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

        
        //hello 1
        //hello 1
        //.....
        
        //key: hello
        //values:(1,1,...)
        
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        result.set(sum);
        context.write(key, result);
    }

}

导出JAR包：

 

需要计算文件的目录位置：

执行jar包：

修改自己写的代码。重新上传jar包

重新执行：