hadoop 源碼筆記

public interface Tool extends Configurable {
  /*
   實現Tool接口可以獲得hadoop命令行參數，通過run方法的args傳入
   */
  int run(String [] args) throws Exception;
}
/***************************MyApp實現了Tool接口的類************************************/
public class MyApp extends Configured implements Tool {
     
       public int run(String[] args) throws Exception {
  //返回父類Configured保存的conf實例(已經被ToolRunner改過了，加入了從命令行獲取的配置項)
         Configuration conf = getConf();
         
         // Create a JobConf using the processed conf
   //第一個參數爲配置項，第二個爲將來要分發的jobJar
         JobConf job = new JobConf(conf, MyApp.class);
         
         // Process custom command-line options
         Path in = new Path(args[1]);
         Path out = new Path(args[2]);
         
         // Specify various job-specific parameters     
         job.setJobName("my-app");
         job.setInputPath(in);
         job.setOutputPath(out);
         job.setMapperClass(MyApp.MyMapper.class);
         job.setReducerClass(MyApp.MyReducer.class);

         // Submit the job, then poll for progress until the job is complete
   //jobJobClient是我們的job 跟 JobTracker交互的接口
   JobClient.runJob(job);
       }
       
       public static void main(String[] args) throws Exception {
         // 調用ToolRunner的run方法（ToolRunner的run方法內部又調用了MyApp的run方法）
   //即ToolRunner只是轉換了參數，把參數的設置項加入到configuration裏，再運行
         int res = ToolRunner.run(new Configuration(), new MyApp(), args);
         
         System.exit(res);
       }
     }
/***************************ToolRunner運行實現了Tool接口的類************************************/
public class ToolRunner {
 /* 
 conf Configuration for the Tool.
 tool Tool to run.
 args command-line arguments to the tool.
 */
  public static int run(Configuration conf, Tool tool, String[] args) 
    throws Exception{
    if(conf == null) {
      conf = new Configuration();
    }
 //轉換命令行參數args爲配置項，並設置到conf裏面
    GenericOptionsParser parser = new GenericOptionsParser(conf, args);
    //重新設置conf到tool裏面，即改變了tool的設置
    tool.setConf(conf);
    
    //取得沒有轉換的參數 hadoop args
    String[] toolArgs = parser.getRemainingArgs();
    //調用tool的run方法
 return tool.run(toolArgs);
  }
  
  /*
 根據Tool自己的配置運行
   */
  public static int run(Tool tool, String[] args) 
    throws Exception{
    return run(tool.getConf(), tool, args);
  }
  
  public static void printGenericCommandUsage(PrintStream out) {
    GenericOptionsParser.printGenericCommandUsage(out);
  }
  
}
/********************Configured類實現了可配置接口，並保存了一個conf實例**************************/
public class Configured implements Configurable {

  //保存了一個conf實例
  private Configuration conf;

  /** Construct a Configured. */
  public Configured() {
    this(null);
  }

  public Configured(Configuration conf) {
    setConf(conf);
  }

  public void setConf(Configuration conf) {
    this.conf = conf;
  }
  //返回保存的conf實例
  public Configuration getConf() {
    return conf;
  }

}