在Hadoop平台中运行MapReduce WordCount程序

一、实验名称

在Hadoop平台运行MapReduce程序

二、实验过程

1.设置环境变量

（1）编辑~/.bashrc文件，添加下列语句

export HADOOP_HOME=/usr/local/hadoop

export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar:$($HADOOP_HOME/bin/hadoopclasspath):$CLASSPATH

（2）source ~/.bashrc使环境变量生效

2.编译Java文件

 

3.将class文件打包生成jar文件

4.开启HDFS、YARN服务

5.5.上传文件计数文件至HDFS文件系统中

hdfs相关操作：

hdfs dfs -rm 删除HDFS文件系统中的文件或目录

hdfs dfs -mkdir 创建目录

hdfs dfs -ls 列出目录下所有文件

hdfs dfs -put 上传文件到HDFS

hdfs dfs -get 从HDFS下载文件到本地

6.在Hadoop平台中运行MapReduce Job

7.查看运行结果

8.具体程序

        
import java.io.IOException;
import java.util.*;
        
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
        
public class WordCount {
        
 public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
        
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        StringTokenizer tokenizer = new StringTokenizer(line);
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            context.write(word, one);
        }
    }
 } 
        
 public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {

    public void reduce(Text key, Iterable<IntWritable> values, Context context) 
      throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable val : values) {
            sum += val.get();
        }
        context.write(key, new IntWritable(sum));
    }
 }
        
 public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
        
    Job job = new Job(conf, "wordcount");
    
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
        
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);
        
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
        
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
    job.waitForCompletion(true);
 }
        
}