MapReduce 入门程序----WordCount

最新推荐文章于 2023-09-06 11:06:46 发布

认知偏差

最新推荐文章于 2023-09-06 11:06:46 发布

阅读量94

点赞数 1

文章标签： hadoop mapreduce 大数据

本文链接：https://blog.csdn.net/m0_72324953/article/details/126923718

版权

WordCount 统计相同单词的个数

Driver驱动类

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;

public class WordCountDriver {

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

        // 1. 获取配置信息以及获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2. 关联本Driver程序的jar
        job.setJarByClass(WordCountDriver.class);

        // 3. 关联Mapper和Reducer的jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4. 设置Mapper输出的k,v类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5. 设置最终输出k,v类型  //最终输出不一定是Reducer的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        
        // 6. 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));  //文件位置
        FileOutputFormat.setOutputPath(job, new Path(args[1]));  //文件位置

        // 7. 提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

Mapper类

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
    
    Text k = new Text();
    IntWritable v = new IntWritable(1);
    
    @Override
    protected void map(LongWritable key, Text value, Context context)   throws IOException, InterruptedException {
        
        // 1 获取一行
        String line = value.toString();
        
        // 2 切割
        String[] words = line.split(" ");
        
        // 3 输出
        for (String word : words) {
            
            k.set(word);
            context.write(k, v);
        }
    }
}

Reducer类

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

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

int sum;
IntWritable v = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
        
        // 1 累加求和
        sum = 0;
        for (IntWritable count : values) {
            sum += count.get();
        }
        
        // 2 输出
         v.set(sum);
        context.write(key,v);
    }
}