【Hadoop】WordCount案例详解

WordCount案例详解

---

需求：文件中存储的各种各样的单词，统计在这些文件中每个单词的出现次数

WordCount Map阶段

原理：针对每行数据应用map方法，按照分隔符拆分；Map阶段输出单词作为key，1作为value。

WordCount Reduce阶段

原理：从Map阶段拷贝对应的输出结果，统计每个单词出现的总词数

代码

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.FileOutputStream;
import java.io.IOException;

public class WC_MR {
    static class WCMapper extends Mapper<LongWritable,Text,Text,LongWritable>{
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] words = line.split("\t");
            for(String word : words){
                context.write(new Text(word),new LongWritable(1));
            }
        }
    }

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

        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        String input = args[0];
        String output = args[1];

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJobName("wordcount");
        
        job.setJarByClass(WC_MR.class);
        
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReducer.class);
        
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        FileInputFormat.setInputPaths(job,new Path(input));
        FileOutputFormat.setOutputPath(job,new Path(output));

        System.exit(job.waitForCompletion(true)?0:1);
    }
}