大数据MapReduce原理之WordCount程序

Map Reduce

WordCount

用IDEA创建一个maven工程wordcountmr(单词计数程序）
在pom.xml中引入Hadoop依赖包

    <dependencies>
       <dependency>
           <groupId>org.apache.hadoop</groupId>
           <artifactId>hadoop-client</artifactId>
           <version>2.9.1</version>
       </dependency>
   </dependencies>

新建WordCountMR.Class

package com.cniao5;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
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.FileOutputCommitter;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class WordCountMR{
    public static class WordCountMapper 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));
            }
        }
    }
    public static class WordCountReducer 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(WordCountMR.class);
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.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);
    }
}

打包jar包，View-Tool Windows-Maven Projects- 双击package完成打包，在target文件夹下wordcountmr-1.0-SNAPSHOT.jar
将此jar包拷贝到Linux机器上执行
在hdfs上新建一个input文件夹，下面放一个要计数的文件（自己写若干的单词，空格隔开）
hadoop jar ./wordcountmr-1.0-SNAPSHOT.jar mr.WordCountMR /input /output
等待程序结束，输出在output下