Linux CentOS 7下在Hadoop2.7.3全分布式环境编译运行WordCount.java

先上代码，详细步骤在后面。

源码WordCount.java

如果您的Linux系统下无法识别中文注释，那么请复制源码2（Hadoop来自官网）

源码1（带注释）：

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.commons.collections.map.StaticBucketMap;
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.io.WritableComparable;
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 org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        /**
         * LongWritable, IntWritable, Text 均是 Hadoop 中实现的用于封装 Java
         * 数据类型的类，这些类实现了WritableComparable接口，
         * 都能够被串行化从而便于在分布式环境中进行数据交换，你可以将它们分别视为long,int,String 的替代品。
         */
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        /**
         * Mapper接口中的map方法： void map(K1 key, V1 value, OutputCollector
         *  output, Reporter reporter) 映射一个单个的输入k/v对到一个中间的k/v对
         * 输出对不需要和输入对是相同的类型，输入对可以映射到0个或多个输出对。
         * OutputCollector接口：收集Mapper和Reducer输出的对。
         * OutputCollector接口的collect(k, v)方法:增加一个(k,v)对到output
         */
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString(); // 把文本字符串化
            StringTokenizer itr = new StringTokenizer(line);
            // Tokenizer是分词器的意思，将一个长的字符串根据空白字符进行分割成短字符串，返回一个字符串集合

            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());// 将每个单词封装成Text类，因为key的类型我们会设置成Text类
                context.write(word, one);// 放进结果集合里，context用于保存结果
            }
        }
    }

    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        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();

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        // validate the number of the args
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount  ");
            System.exit(2);
        }
        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(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

源码2(无注释)

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<Object, Text, Text, IntWritable>{

    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<Text,IntWritable,Text,IntWritable> {
    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);
  }
}

步骤：　　

1.创建WordCount.java文件，写入代码

2.临时设置CLASSPATH变量

执行下面命令，（当然也可以在etc/profile里面设置永久性的环境变量，但是这样会使其变得臃肿，而且不同的java文件依赖的CLASSPATH不同）

export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar

3.编译WordCount.java文件

执行命令：

hadoop com.sun.tools.javac.Main WordCount.java

4.打包编译生成的.class文件

jar -cvf WordCount.jar WordCount*.class

5.创建本地文件并上传到hdfs(如果hdfs上面已经存在测试数据文件可跳过创建步骤)

在本地创建一个input文件夹

mkdir input

在input文件夹下创建两个文本文件并输入数据

echo “Hello World Bye World” >> input/file1.txt
echo “Hello Hadoop Goodbye Hadoop” >> input/file2.txt

在hdfs上面根目录下创建一个InputData文件夹，存放测试文件

hdfs dfs -mkdir /InputData

把input文件夹下的所有文件上传到hdfs上面

hdfs dfs -put input/* /InputData

6.开始执行任务

hadoop jar WordCount.jar WordCount /InputData /OutputData

关于后面三个参数说明：
wordcount ：此项目（job）的名称，在WordCount.java中并未引用，但是不可少
/InputData：hdfs上的输入数据的目录
/OutputData：hdfs上的数据输出目录（不需提前创建，Hadoop会自动创建）

7.查看执行结果

hadoop fs -cat /OutputData/part-r-00000
正常的话应该会显示如下结果：

Bye 1
Goodbye 1
Hadoop 2
Hello 2
World 2

如有帮助，还望赏赞一个；如有疑问，欢迎私信，谢谢。