大数据——MapReduce编程实现WordCount

a…txt文本

i wish to wish the wish you wish to wish,but
if you wish the wish the wish wishes,i won't
wish the wish you wish to wish

Mapper类

package cn.kgc.kb09.mr;

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;
//实现word count的mapper过程
public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
         //分行
        String line = value.toString();
        //根据空格分单词
        String[] words = line.split(" ");
        //遍历单词，并分别写出来
        for (String word : words) {
            context.write(new Text(word), new IntWritable(1));
        }
    }
}

Reducer类

package cn.kgc.kb09.mr;

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

import java.io.IOException;

public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //定义一个总和
        int total=0;
        //遍历value
        for (IntWritable value : values) {
        //把个数加起来
            total += value.get();
        }
        //写出总和
        context.write(key,new IntWritable(total));
    }
}

Partitioner类

package cn.kgc.kb09.mr;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
public class WCPartitioner extends Partitioner<Text, IntWritable> {
    @Override
    public int getPartition(Text text, IntWritable intWritable, int i) {
        //输出文档分成i份
        return Math.abs(text.hashCode())% i;
    }
}

Driver

package cn.kgc.kb09.mr;

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;

public class WCDriver {
    public static void main(String[] args)throws Exception {
        //1、建立连接
        Configuration cfg = new Configuration();
        Job job = Job.getInstance(cfg, "job_wc");
        job.setJarByClass(WCDriver.class);
        //2、指定mapper和reduce
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReducer.class);
        //3、指定mapper输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //4、指定paritioner
        job.setNumReduceTasks(4);
        job.setPartitionerClass(WCPartitioner.class);
        //5、指定reduce输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //6、指定输入输出路径
        FileInputFormat.setInputPaths(job, new Path("file:///D:/test/a.txt"));
        FileOutputFormat.setOutputPath(job, new Path("file:///D/test/testwc/"));
        //7、运行
        boolean result = job.waitForCompletion(true);
        System.out.println(result ? "成功" : "失败");
        System.exit(result ? 0 : 1);
    }
}

输出：