wiki:waue/helloHadoop
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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 HelloHadoop {

  static public class HelloMapper extends
      Mapper<LongWritable, Text, LongWritable, Text> {

    public void map(LongWritable key, Text value, Context context)
        throws IOException, InterruptedException {
      // 將出入資料 原封不動的寫入 輸出
      context.write((LongWritable) key, (Text) value);
    }

  }

  static public class HelloReducer extends
      Reducer<LongWritable, Text, LongWritable, Text> {
    public void reduce(LongWritable key, Iterable<Text> values,
        Context context) throws IOException, InterruptedException {
      Text val = new Text();
      // 取回 val 的資料
      for (Text str : values) {
        val.set(str.toString());
      }
      // 將取回的資料引入輸出
      context.write(key, val);
    }
  }

  public static void main(String[] args) throws IOException,
      InterruptedException, ClassNotFoundException {
    // 引入 $HADOOP_HOME/conf 內控制檔內的資料
    Configuration conf = new Configuration();
    // 宣告job 取得conf 並設定名稱 Hadoop Hello World
    Job job = new Job(conf, "Hadoop Hello World");
    // 設定此運算的主程式
    job.setJarByClass(HelloHadoop.class);
    // 設定輸入路徑
    FileInputFormat.setInputPaths(job, "/user/hadoop/input");
    // 設定輸出路徑
    FileOutputFormat.setOutputPath(job, new Path("/user/hadoop/output-hh1"));
    // 指定定map class
    job.setMapperClass(HelloMapper.class);
    // 指定reduce class
    job.setReducerClass(HelloReducer.class);
    // 開使運算
    job.waitForCompletion(true);

  }
}

Last modified 13 years ago Last modified on Dec 17, 2011, 12:37:32 PM