import java.io.IOException;
import java.net.URI; import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.JobID;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.TaskAttemptID;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser; public class GetIDMapReduce {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
// String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if(args.length!=2){
System.err.println("Usage databaseV1 <inputpath> <outputpath>");
} Job job = Job.getInstance(conf, GetIDMapReduce.class.getSimpleName() + "1");
job.setJarByClass(GetIDMapReduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
job.setMapperClass(MyMapper1.class);
job.setNumReduceTasks(0);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
public static class MyMapper1 extends Mapper<LongWritable, Text, Text, NullWritable>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, NullWritable>.Context context)
throws IOException, InterruptedException { FileSplit fileSplit=(FileSplit) context.getInputSplit();
String pathname=fileSplit.getPath().getName();
JobID jobid=context.getJobID(); //获取jobid
LongWritable keyout=context.getCurrentKey(); //获取key偏移量
Text valueout=context.getCurrentValue(); //获取一行的值
String jobname=context.getJobName(); //获得job名字
TaskAttemptID taskid=context.getTaskAttemptID(); //获得taskid
float progress=context.getProgress(); //获取任务执行进度
String jar = context.getJar(); //作业运行之前,往集群拷贝的作业资源jar
//String status = context.getStatus();
String user = context.getUser(); //获取当前用户
//String[] fileTimestamps = context.getFileTimestamps();
int numReduceTasks = context.getNumReduceTasks(); //获得reduce的数量
//Path[] fileClassPaths = context.getFileClassPaths();
Configuration configuration = context.getConfiguration(); //获得作业配置文件
//RawComparator<?> groupingComparator = context.getGroupingComparator();
boolean jobSetupCleanupNeeded = context.getJobSetupCleanupNeeded(); //Get whether job-setup and job-cleanup is needed for the job
int maxMapAttempts = context.getMaxMapAttempts(); //the max number of attempts per map task
int maxReduceAttempts = context.getMaxReduceAttempts(); //he max number of attempts per reduce task.
//@SuppressWarnings("deprecation")
//Path[] localCacheFiles = context.getLocalCacheFiles();
//OutputCommitter outputCommitter = context.getOutputCommitter();
Path workingDirectory = context.getWorkingDirectory(); //工作目录
boolean nextKeyValue = context.nextKeyValue(); //下一个键值对
//URI[] cacheFiles = context.getCacheFiles();
URI[] cacheArchives = context.getCacheArchives(); //Get cache archives set in the Configuration
Path[] archiveClassPaths = context.getArchiveClassPaths();//Get the archive entries in classpath as an array of Path
boolean profileEnabled = context.getProfileEnabled();//Get whether the task profiling is enabled.
//String profileParams = context.getProfileParams();
@SuppressWarnings("deprecation")
boolean symlink = context.getSymlink();// Originally intended to check if symlinks should be used, but currently symlinks cannot be disabled
//RawComparator<?> sortComparator = context.getSortComparator();
//int hashCode = context.hashCode();
context.write(new Text("===================================================================================="), NullWritable.get());
context.write(new Text("pathname--"+pathname), NullWritable.get());
context.write(new Text("jobid--"+jobid.toString()), NullWritable.get());
context.write(new Text("keyout--"+keyout.toString()), NullWritable.get());
context.write(new Text("keyout--"+valueout), NullWritable.get());
context.write(new Text("jobname--"+jobname), NullWritable.get());
context.write(new Text("taskid--"+taskid.toString()), NullWritable.get());
context.write(new Text("progress--"+progress), NullWritable.get());
context.write(new Text("jar--"+jar.toString()), NullWritable.get());
//context.write(new Text("status--"+status), NullWritable.get());
context.write(new Text("user--"+user), NullWritable.get());
//context.write(new Text("fileTimestamps--"+fileTimestamps), NullWritable.get());
context.write(new Text("numReduceTasks--"+numReduceTasks), NullWritable.get());
//context.write(new Text("fileClassPaths--"+fileClassPaths), NullWritable.get());
context.write(new Text("configuration--"+configuration), NullWritable.get());
//context.write(new Text("groupingComparator--"+groupingComparator), NullWritable.get());
context.write(new Text("jobSetupCleanupNeeded--"+jobSetupCleanupNeeded), NullWritable.get());
context.write(new Text("maxMapAttempts--"+maxMapAttempts), NullWritable.get());
context.write(new Text("maxReduceAttempts--"+maxReduceAttempts), NullWritable.get());
//context.write(new Text("localCacheFiles--"+localCacheFiles), NullWritable.get());
//context.write(new Text("outputCommitter--"+outputCommitter), NullWritable.get());
context.write(new Text("workingDirectory--"+workingDirectory), NullWritable.get());
context.write(new Text("nextKeyValue--"+nextKeyValue), NullWritable.get());
//context.write(new Text("cacheFiles--"+cacheFiles), NullWritable.get());
context.write(new Text("cacheArchives--"+cacheArchives), NullWritable.get());
context.write(new Text("archiveClassPaths--"+archiveClassPaths), NullWritable.get());
context.write(new Text("profileEnabled--"+profileEnabled), NullWritable.get());
//context.write(new Text("profileParams--"+profileParams), NullWritable.get());
context.write(new Text("symlink--"+symlink), NullWritable.get());
//context.write(new Text("sortComparator--"+sortComparator), NullWritable.get());
//context.write(new Text("hashCode--"+hashCode), NullWritable.get());
}
}
}

注:并非原著,备注下来方便后面自己查看

最新文章

  1. pdfbox加载pdf时遇到wrappedioexception报错处理方式
  2. Android 高级面试题及答案
  3. asp.net core获取HttpContext相关操作
  4. android 动态设置Framelayout,view,imageView,Layout高度
  5. [GO编程]GO编程环境
  6. Google搜索命令语法大全
  7. ping: unknown host www.baidu.com
  8. STL之iterator(迭代器)
  9. 【转】Django中的request与response对象
  10. 【easy】438.Find All Anagrams in a String 找出字符串中所有的变位词
  11. Python内置函数(19)——eval
  12. CUDA 计算线程索引的一般公式
  13. 浏览器报XMLHttpRequest cannot loadxxxxxx
  14. PHP下载远程图片的3个方法
  15. node:express:error---填坑之路
  16. vnode的挂载和更新流程 -- 简介.
  17. for循环中的 break和continue的区别
  18. spring框架学习(三)spring与junit整合测试
  19. 向OSG视图Viewer发送消息
  20. Java名称由来

热门文章

  1. 基于LIVE555的RTSP QoS实现
  2. angular select框 option空行
  3. ifram子页面与父页面的方法相互调用
  4. js面向对象(对象/类/工厂模式/构造函数/公有和原型)
  5. Python--day69--ORM正反向查找(外键)
  6. hdu 1016 Prime Ring Problem(dfs)
  7. 买房的贷款时间是否是越长越好?https://www.zhihu.com/question/20842791
  8. H3C OSPF协议工作过程概述
  9. 【p083】传球游戏
  10. es6 let和const的用法