mapreduce编程实例——wordcount

package com.leokadia.mapreduce.wordcount; 
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;

/**
 * KEYIN, map阶段输入的key的类型：LongWritable
 * VALUEIN,map阶段输入value类型：Text
 * KEYOUT,map阶段输出的Key类型：Text
 * VALUEOUT,map阶段输出的value类型：IntWritable
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);  //map阶段不进行聚合
 
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 1 获取一行 
        String line = value.toString();

        // 2 切割(取决于原始数据的中间分隔符) 
        String[] words = line.split(" ");

        // 3 循环写出
        for (String word : words) {
            // 封装outk
            outK.set(word);

            // 写出
            context.write(outK, outV);
        }
    }
}

package com.leokadia.mapreduce.wordcount;

/**
 * @author sa
 * @create 2021-05-05 10:47
 */
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * KEYIN, reduce阶段输入的key的类型：Text
 * VALUEIN,reduce阶段输入value类型：IntWritable
 * KEYOUT,reduce阶段输出的Key类型：Text
 * VALUEOUT,reduce阶段输出的value类型：IntWritable
 */
public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    private IntWritable outV = new IntWritable(); 
    
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        int sum = 0;
        // xxxxxxx xxxxxxx ->(xxxxxxx,1),(xxxxxxx,1)
        // xxxxxxx, (1,1)
        // 将values进行累加
        for (IntWritable value : values) {
            sum += value.get();
        } 
        outV.set(sum);

        // 写出
        context.write(key,outV);
    }
}

package com.leokadia.mapreduce.wordcount; 

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; 
import java.io.IOException;

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

        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        // 3 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出的kV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\input\\inputword"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\hadoop\\output888"));

        // 7 提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }
}