huiselele 发表于 2018-11-1 10:56:26

Hadoop基本流程与应用开发

public static void main(String[] args)  {
  try
  {
  run(args);
  } catch (Exception e)
  {
  e.printStackTrace();
  }
  }
  public static void run(String[] args) throws Exception
  {
  if (args == null || args.length = 0)
  shortin = shortin.substring(shortin.lastIndexOf(File.separator));
  if (shortout.indexOf(File.separator) >= 0)
  shortout = shortout.substring(shortout.lastIndexOf(File.separator));
  SimpleDateFormat formater = new SimpleDateFormat("yyyy.MM.dd");
  shortout = new StringBuffer(shortout).append("-")
  .append(formater.format(new Date())).toString();
  if (!shortin.startsWith("/"))
  shortin = "/" + shortin;
  if (!shortout.startsWith("/"))
  shortout = "/" + shortout;
  shortin = "/user/root" + shortin;
  shortout = "/user/root" + shortout;
  File inputdir = new File(inputpath);
  File outputdir = new File(outputpath);
  if (!inputdir.exists() || !inputdir.isDirectory())
  {
  System.out.println("inputpath not exist or isn't dir!");
  return;
  }
  if (!outputdir.exists())
  {
  new File(outputpath).mkdirs();
  }
  JobConf conf = new JobConf(new Configuration(),LogAnalysiser.class);//构建Config
  FileSystem fileSys = FileSystem.get(conf);
  fileSys.copyFromLocalFile(new Path(inputpath), new Path(shortin));//将本地文件系统的文件拷贝到HDFS中
  conf.setJobName("analysisjob");
  conf.setOutputKeyClass(Text.class);//输出的key类型,在OutputFormat会检查
  conf.setOutputValueClass(LongWritable.class); //输出的value类型,在OutputFormat会检查
  conf.setMapperClass(MapClass.class);
  conf.setCombinerClass(CombinerClass.class);
  conf.setReducerClass(ReduceClass.class);
  conf.setPartitionerClass(PartitionerClass.class);
  conf.set("mapred.reduce.tasks", "2");//强制需要有两个Reduce来分别处理流量和次数的统计
  FileInputFormat.setInputPaths(conf, shortin);//hdfs中的输入路径
  FileOutputFormat.setOutputPath(conf, new Path(shortout));//hdfs中输出路径
  Date startTime = new Date();
  System.out.println("Job started: " + startTime);
  JobClient.runJob(conf);
  Date end_time = new Date();
  System.out.println("Job ended: " + end_time);
  System.out.println("The job took " + (end_time.getTime() - startTime.getTime()) /1000 + " seconds.");
  //删除输入和输出的临时文件
  fileSys.copyToLocalFile(new Path(shortout),new Path(outputpath));
  fileSys.delete(new Path(shortin),true);
  fileSys.delete(new Path(shortout),true);
  }

页: [1]
查看完整版本: Hadoop基本流程与应用开发