搭建好Hadoop集群环境或者单机环境，并运行，MapReduce进程要起来

1. 假设已经配置了下列环境变量

export JAVA_HOME=/usr/java/defaultexport PATH=$JAVA_HOME/bin:$PATHexport HADOOP_CLASSPATH=$JAVA_HOME/lib/tools.jar

2.创建2个测试文件，并上传到Hadoop HDFS中

[hadoop@centos-one temp]$ cat file01Hello World Bye World[hadoop@centos-one temp]$ cat file02 Hello Hadoop Goodbye Hadoop [hadoop@centos-one temp]$ ../hadoop-2.6.0/bin/hdfs dfs -mkdir /wordcount [hadoop@centos-one temp]$ ../hadoop-2.6.0/bin/hdfs dfs -mkdir /wordcount/input ../hadoop-2.6.0/bin/hdfs dfs -put file* /wordcount/input 这个是删除HDFS文件夹的命令: ../hadoop-2.6.0/bin/hdfs dfs -rm -r /temp

3.编写WordCount类

import java.io.IOException;import java.util.StringTokenizer;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.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;public class WordCount {  public static class TokenizerMapper       extends Mapper
     
      {    private final static IntWritable one = new IntWritable(1);    private Text word = new Text();    public void map(Object key, Text value, Context context                    ) throws IOException, InterruptedException {      StringTokenizer itr = new StringTokenizer(value.toString());      while (itr.hasMoreTokens()) {        word.set(itr.nextToken());        context.write(word, one);      }    }  }  public static class IntSumReducer       extends Reducer
      
        {    private IntWritable result = new IntWritable();    public void reduce(Text key, Iterable
       
         values,                       Context context                       ) throws IOException, InterruptedException {      int sum = 0;      for (IntWritable val : values) {        sum += val.get();      }      result.set(sum);      context.write(key, result);    }  }  public static void main(String[] args) throws Exception {    Configuration conf = new Configuration();    Job job = Job.getInstance(conf, "word count");    job.setJarByClass(WordCount.class);    job.setMapperClass(TokenizerMapper.class);    job.setCombinerClass(IntSumReducer.class);    job.setReducerClass(IntSumReducer.class);    job.setOutputKeyClass(Text.class);    job.setOutputValueClass(IntWritable.class);    FileInputFormat.addInputPath(job, new Path(args[0]));    FileOutputFormat.setOutputPath(job, new Path(args[1]));    System.exit(job.waitForCompletion(true) ? 0 : 1);  }}
       
      
     

4. 编译WordCount.java 并 打包为jar

$ bin/hadoop com.sun.tools.javac.Main WordCount.java$ jar cf wc.jar WordCount*.class

5.运行MapReduce程序

[hadoop@centos-one temp]$ ../hadoop-2.6.0/bin/hadoop  jar wc.jar WordCount /wordcount/input /wordcount/output

查看结果

../hadoop-2.6.0/bin/hadoop  dfs -cat /wordcount/output/part-r-00000 Bye    1 Goodbye    1 Hadoop    2 Hello    2 World    2