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

hadoop上下文信息获取方法的更多相关文章

  1. spring上下文快速获取方法

    import org.springframework.beans.BeansException;import org.springframework.context.ApplicationContex ...

  2. JavaScript获取客户端计算机硬件及系统等信息的方法

    JavaScript获取客户端计算机硬件及系统等信息的方法 JavaScript 获取客户端计算机硬件及系统信息 通过WMI来实现获取客户端计算机硬件及系统信息: function getSysInf ...

  3. AspectJ获取方法注解的信息

    在使用Aspectj获取方法注解信息的时候,可以使用下面的代码片段: /** * Get value of annotated method parameter */ private <T ex ...

  4. PHP获取http头信息和CI中获取HTTP头信息的方法

    CI中获取HTTP头信息的方法: $this->input->request_headers() 在不支持apache_request_headers()的非Apache环境非常有用.返回 ...

  5. Request获取url各种信息的方法

    1.Request获取url各种信息的方法 测试的url地址:http://www.test.com/testweb/default.aspx, 结果如下: Request.ApplicationPa ...

  6. Oracle 和 SQLSERVER 重新获取统计信息的方法

    1. Oracle 重新获取统计信息的命令 exec dbms_stats.gather_schema_stats(ownname =>) # 需要修改 ownername options 指定 ...

  7. httpclient接口测试完整用例以及获取信息的方法

    原文地址https://blog.csdn.net/fhaohaizi/article/details/78088075 原文地址https://blog.csdn.net/fhaohaizi/art ...

  8. java反射子之获取方法信息(二)

    一.获取方法 1.方法作用. 2. 二.获取方法信息.(修饰符,返回值,方法名称,参数列表,抛出的异常). ############################################## ...

  9. laravel中单独获取一个错误信息的方法

    获取单独的错误信息的方法

随机推荐

  1. 将Eclipse中文注释字体变大方法

    今天下了最新的eclipse玩,结果发现注释变得灰常小,差点看瞎哥24K氪金狗眼 于是在网上找了找解决方法,结果都不对 最后自己试出来了... 方法:  Window --> Preferenc ...

  2. 深入python

    while循环知识: while是关键字 格式我们要怎么写:; while 条件 : 缩进    循环(代码块) 这里面有个死循环######条件如果一直为真,就形成了一个环,就成为了死循环 那我们如 ...

  3. HTML的基本结构和标签分类

    HTML:超文本标记语言 HTML基本结构 <!DOCTYPE html> <html> <head> <meta charset="utf-8&q ...

  4. 得到Access数据库中所有表名

    public static List<string> GetShemaTables(string db)        {                        string pa ...

  5. Python--day62--ORM的使用

    4.Django里ORM的使用 1,手动创建数据库 2,在settings.py里面,配置数据库的连接信息 3,在项目/__init__.py告诉Django用pymysql模块代替MySQLdb(不 ...

  6. Educational Codeforces Round 5(A,B题)

    虽然是水题但还是贴下代码把 A #include<cstring> #include<cstdio> using namespace std; ; char x[qq],y[q ...

  7. H3C ACL包过滤的局限性

  8. H3C OSPF协议工作过程概述

  9. java 利用Class获取类的属性信息

    package junereflect624; import java.lang.reflect.Modifier; class A { } interface B{ } interface C{ } ...

  10. H3C DHCP租约更新