hadoop从wordCount开始

最近一段时间大数据很火，我有稍微有点java基础，自然选择了由java编写的hadoop框架，wordCount是hadoop中类似于java中helloWorld的存在，自然不能错过。

package hadoop.wordcount.com;
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 {

  /**
   * Hadoop mapreduce中的map，用来把数据转化为map
   * @author admin
   *
   */
  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{

    // IntWritable是hadoop中定义的类型，相当于java中的int，这行代码相当于 int one=1;
	private final static IntWritable one = new IntWritable(1);
	// Text是hadoop中定义的类型，相当于java中的String,这行代码相当于 String text="";
    private Text word = new Text();
    
    /**
     * hadoop中继承Mapper需要实现map()方法
     * key 转化为map时输入的key，类型与Mapper第一个参数一致
     * value 转化为map时输入的value，类型与Mapper第二个参数一致
     */
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      // 遍历输入的value，并将它们写入上下文
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }

  /**
   * hadoop mapreduce中的Reducer，对数据的具体操作写在这里面
   * @author admin
   *
   */
  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();
    
    /**
     * 在这里添加对数据的操作
     * key为输入类型
     * values为输出类型
     * 
     */
    public void reduce(Text key, Iterable<IntWritable> 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();// 读取配置文件
    Job job = Job.getInstance(conf, "word count");// 新建一个任务
    job.setJarByClass(WordCount.class);// 主类
    job.setMapperClass(TokenizerMapper.class);// mapper
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);//  reducer
    job.setOutputKeyClass(Text.class);// 输出结果的key类型
    job.setOutputValueClass(IntWritable.class);// 输出结果的value类型
    // 要读取的数据，此处内容根据你hadoop实际配置而定
    FileInputFormat.addInputPath(job, new Path("hdfs://dtj007:9000/dtj007/djt.txt"));
    //  要输出数据的路径，此处内容根据你hadoop实际配置而定
    FileOutputFormat.setOutputPath(job, new Path("hdfs://dtj007:9000/dtj007/wordcount-out"));
    System.exit(job.waitForCompletion(true) ? 0 : 1);// 提交任务
  }
}

　　运行完毕以后可以在你linux配置的hadoop目录下使用:

　　　　 bin/hadoop fs -text /你在wordCount中配置的输出路径/part-r-00000

命令进行查看