Hadoop中的Context使用

秒速五厘米 2022-06-11 09:54 171阅读 0赞

简要截取：

![这里写图片描述][20161021083829067]

本篇博客以经典的wordcount程序为例来说明context的用法：  
直接上代码：

package MapReduce;
    
    import java.io.IOException;
    
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.FSDataInputStream;
    import org.apache.hadoop.fs.FileSystem;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.LongWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Counter;
    import org.apache.hadoop.mapreduce.Job;
    import org.apache.hadoop.mapreduce.JobID;
    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.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.mapreduce.lib.partition.HashPartitioner;
    import org.apache.zookeeper.common.IOUtils;
    
    
    
    public class WordCount  
    {
        public static String path1 = "file:///C:\\word.txt"; 
        public static String path2 = "file:///C:\\dirout\\";
        public static void main(String[] args) throws Exception
         {
    
             Configuration conf = new Configuration();
    
             FileSystem fileSystem = FileSystem.get(conf);//获取本地文件系统中的一个fileSystem实例
    
             if(fileSystem.exists(new Path(path2)))
             {
                 fileSystem.delete(new Path(path2), true);
             }
    
             Job job = Job.getInstance(conf,"wordcount");
    
             //job.setJarByClass(WordCount.class);
    
             FileInputFormat.setInputPaths(job, new Path(path1));
             job.setInputFormatClass(TextInputFormat.class);
             job.setMapperClass(MyMapper.class);
             job.setMapOutputKeyClass(Text.class);
             job.setMapOutputValueClass(LongWritable.class);
    
             job.setNumReduceTasks(1);
             job.setPartitionerClass(HashPartitioner.class);
    
    
             job.setReducerClass(MyReducer.class);
             job.setOutputKeyClass(Text.class);
             job.setOutputValueClass(LongWritable.class);
             job.setOutputFormatClass(TextOutputFormat.class);
             FileOutputFormat.setOutputPath(job, new Path(path2));
             job.waitForCompletion(true);
             //查看运行结果：
             FSDataInputStream fr = fileSystem.open(new Path("file:///C:\\dirout\\part-r-00000"));
             IOUtils.copyBytes(fr, System.out, 1024, true);
         }    
         public  static  class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable>
         {
    
                protected void map(LongWritable k1, Text v1,Context context)throws IOException, InterruptedException
                {
                     //在这里我们利用context获取日志中的相关数据:键值对信息
                     LongWritable key = context.getCurrentKey();
                     System.out.println(v1.toString()+"对应的起始偏移量是："+key.get());
                     Text value = context.getCurrentValue();
                     System.out.println("当前文本行是："+value.toString());
                     //获取当前行文本所对应的文件的信息
                     FileSplit inputSplit = (FileSplit) context.getInputSplit();
                     Path path = inputSplit.getPath();
                     System.out.println(v1.toString()+"对应的文本路径是："+path);
                     String filename = path.getName();
                     System.out.println(v1.toString()+"对应的文件名是："+filename);
                     System.out.println("----------------------------------------------------------");
    
    
    
                     //利用context获取计数器,对敏感词汇进行计数
                     Counter counter = context.getCounter("Sensitive Word", "sensitiveword");
                     if(v1.toString().contains("fenlie"))
                     {
                         counter.increment(1L);  //如果日志当中包含dalai这个敏感词,自定义计数器加1       
                     }
                     String[] splited = v1.toString().split("\t");
    
    
                     for (String string : splited)
                     {
                           context.write(new Text(string),new LongWritable(1L));
                     }
                }   
                protected void cleanup(Context context)throws IOException, InterruptedException
                {
                      String jobName = context.getJobName();
                      System.out.println("当前运行的jobname是："+jobName);
                      JobID jobID = context.getJobID();
                      System.out.println("当前运行的jobId是："+jobID);
                      Configuration conf = context.getConfiguration();
                      System.out.println("运行中读取的配置文件是："+conf);
                      String user = context.getUser();
                      System.out.println("当前操作用户是："+user);
    
                }
         }
         public  static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>
         {
            protected void reduce(Text k2, Iterable<LongWritable> v2s,Context context)throws IOException, InterruptedException
            {
                     long sum = 0L;
                     for (LongWritable v2 : v2s)
                    {
                        sum += v2.get();
                    }
                    context.write(k2,new LongWritable(sum));
            }
         }
    }

运行结果

2016-07-10 13:29:56,715 INFO  [main] Configuration.deprecation (Configuration.java:warnOnceIfDeprecated(1009)) - session.id is deprecated. Instead, use dfs.metrics.session-id
    2016-07-10 13:29:56,719 INFO  [main] jvm.JvmMetrics (JvmMetrics.java:init(76)) - Initializing JVM Metrics with processName=JobTracker, sessionId=
    2016-07-10 13:29:57,138 WARN  [main] mapreduce.JobSubmitter (JobSubmitter.java:copyAndConfigureFiles(150)) - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
    2016-07-10 13:29:57,142 WARN  [main] mapreduce.JobSubmitter (JobSubmitter.java:copyAndConfigureFiles(259)) - No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
    2016-07-10 13:29:57,151 INFO  [main] input.FileInputFormat (FileInputFormat.java:listStatus(280)) - Total input paths to process : 1
    2016-07-10 13:29:57,202 INFO  [main] mapreduce.JobSubmitter (JobSubmitter.java:submitJobInternal(396)) - number of splits:1
    2016-07-10 13:29:57,350 INFO  [main] mapreduce.JobSubmitter (JobSubmitter.java:printTokens(479)) - Submitting tokens for job: job_local492959629_0001
    2016-07-10 13:29:57,426 WARN  [main] conf.Configuration (Configuration.java:loadProperty(2358)) - file:/tmp/hadoop-Administrator/mapred/staging/Administrator492959629/.staging/job_local492959629_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval;  Ignoring.
    2016-07-10 13:29:57,436 WARN  [main] conf.Configuration (Configuration.java:loadProperty(2358)) - file:/tmp/hadoop-Administrator/mapred/staging/Administrator492959629/.staging/job_local492959629_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts;  Ignoring.
    2016-07-10 13:29:57,648 WARN  [main] conf.Configuration (Configuration.java:loadProperty(2358)) - file:/tmp/hadoop-Administrator/mapred/local/localRunner/Administrator/job_local492959629_0001/job_local492959629_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval;  Ignoring.
    2016-07-10 13:29:57,656 WARN  [main] conf.Configuration (Configuration.java:loadProperty(2358)) - file:/tmp/hadoop-Administrator/mapred/local/localRunner/Administrator/job_local492959629_0001/job_local492959629_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts;  Ignoring.
    2016-07-10 13:29:57,663 INFO  [main] mapreduce.Job (Job.java:submit(1289)) - The url to track the job: http://localhost:8080/
    2016-07-10 13:29:57,664 INFO  [main] mapreduce.Job (Job.java:monitorAndPrintJob(1334)) - Running job: job_local492959629_0001
    2016-07-10 13:29:57,667 INFO  [Thread-3] mapred.LocalJobRunner (LocalJobRunner.java:createOutputCommitter(471)) - OutputCommitter set in config null
    2016-07-10 13:29:57,673 INFO  [Thread-3] mapred.LocalJobRunner (LocalJobRunner.java:createOutputCommitter(489)) - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
    2016-07-10 13:29:57,753 INFO  [Thread-3] mapred.LocalJobRunner (LocalJobRunner.java:runTasks(448)) - Waiting for map tasks
    2016-07-10 13:29:57,754 INFO  [LocalJobRunner Map Task Executor #0] mapred.LocalJobRunner (LocalJobRunner.java:run(224)) - Starting task: attempt_local492959629_0001_m_000000_0
    2016-07-10 13:29:57,788 INFO  [LocalJobRunner Map Task Executor #0] util.ProcfsBasedProcessTree (ProcfsBasedProcessTree.java:isAvailable(182)) - ProcfsBasedProcessTree currently is supported only on Linux.
    2016-07-10 13:29:58,098 INFO  [LocalJobRunner Map Task Executor #0] mapred.Task (Task.java:initialize(581)) -  Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@3030ff48
    2016-07-10 13:29:58,103 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:runNewMapper(733)) - Processing split: file:/C:/word.txt:0+64
    2016-07-10 13:29:58,115 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:createSortingCollector(388)) - Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
    2016-07-10 13:29:58,162 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:setEquator(1182)) - (EQUATOR) 0 kvi 26214396(104857584)
    2016-07-10 13:29:58,162 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:init(975)) - mapreduce.task.io.sort.mb: 100
    2016-07-10 13:29:58,162 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:init(976)) - soft limit at 83886080
    2016-07-10 13:29:58,163 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:init(977)) - bufstart = 0; bufvoid = 104857600
    2016-07-10 13:29:58,163 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:init(978)) - kvstart = 26214396; length = 6553600
    hello   you对应的起始偏移量是：0
    当前文本行是：hello    you
    hello   you对应的文本路径是：file:/C:/word.txt
    hello   you对应的文件名是：word.txt
    ----------------------------------------------------------
    hello   me对应的起始偏移量是：11
    当前文本行是：hello    me
    hello   me对应的文本路径是：file:/C:/word.txt
    hello   me对应的文件名是：word.txt
    ----------------------------------------------------------
    hello   she对应的起始偏移量是：21
    当前文本行是：hello    she
    hello   she对应的文本路径是：file:/C:/word.txt
    hello   she对应的文件名是：word.txt
    ----------------------------------------------------------
    hello   he对应的起始偏移量是：32
    当前文本行是：hello    he
    hello   he对应的文本路径是：file:/C:/word.txt
    hello   he对应的文件名是：word.txt
    ----------------------------------------------------------
    hello   he对应的起始偏移量是：42
    当前文本行是：hello    he
    hello   he对应的文本路径是：file:/C:/word.txt
    hello   he对应的文件名是：word.txt
    ----------------------------------------------------------
    fenlie  hello对应的起始偏移量是：52
    当前文本行是：fenlie   hello
    fenlie  hello对应的文本路径是：file:/C:/word.txt
    fenlie  hello对应的文件名是：word.txt
    ----------------------------------------------------------
    当前运行的jobname是：wordcount
    当前运行的jobId是：job_local492959629_0001
    运行中读取的配置文件是：Configuration: core-default.xml, core-site.xml, mapred-default.xml, mapred-site.xml, yarn-default.xml, yarn-site.xml, hdfs-default.xml, hdfs-site.xml, file:/tmp/hadoop-Administrator/mapred/local/localRunner/Administrator/job_local492959629_0001/job_local492959629_0001.xml
    当前操作用户是：Administrator
    2016-07-10 13:29:58,177 INFO  [LocalJobRunner Map Task Executor #0] mapred.LocalJobRunner (LocalJobRunner.java:statusUpdate(591)) - 
    2016-07-10 13:29:58,177 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:flush(1437)) - Starting flush of map output
    2016-07-10 13:29:58,178 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:flush(1455)) - Spilling map output
    2016-07-10 13:29:58,178 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:flush(1456)) - bufstart = 0; bufend = 156; bufvoid = 104857600
    2016-07-10 13:29:58,178 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:flush(1458)) - kvstart = 26214396(104857584); kvend = 26214352(104857408); length = 45/6553600
    2016-07-10 13:29:58,202 INFO  [LocalJobRunner Map Task Executor #0] mapred.MapTask (MapTask.java:sortAndSpill(1641)) - Finished spill 0
    2016-07-10 13:29:58,212 INFO  [LocalJobRunner Map Task Executor #0] mapred.Task (Task.java:done(995)) - Task:attempt_local492959629_0001_m_000000_0 is done. And is in the process of committing
    2016-07-10 13:29:58,224 INFO  [LocalJobRunner Map Task Executor #0] mapred.LocalJobRunner (LocalJobRunner.java:statusUpdate(591)) - map
    2016-07-10 13:29:58,224 INFO  [LocalJobRunner Map Task Executor #0] mapred.Task (Task.java:sendDone(1115)) - Task 'attempt_local492959629_0001_m_000000_0' done.
    2016-07-10 13:29:58,224 INFO  [LocalJobRunner Map Task Executor #0] mapred.LocalJobRunner (LocalJobRunner.java:run(249)) - Finishing task: attempt_local492959629_0001_m_000000_0
    2016-07-10 13:29:58,225 INFO  [Thread-3] mapred.LocalJobRunner (LocalJobRunner.java:runTasks(456)) - map task executor complete.
    2016-07-10 13:29:58,229 INFO  [Thread-3] mapred.LocalJobRunner (LocalJobRunner.java:runTasks(448)) - Waiting for reduce tasks
    2016-07-10 13:29:58,229 INFO  [pool-3-thread-1] mapred.LocalJobRunner (LocalJobRunner.java:run(302)) - Starting task: attempt_local492959629_0001_r_000000_0
    2016-07-10 13:29:58,247 INFO  [pool-3-thread-1] util.ProcfsBasedProcessTree (ProcfsBasedProcessTree.java:isAvailable(182)) - ProcfsBasedProcessTree currently is supported only on Linux.
    2016-07-10 13:29:58,334 INFO  [pool-3-thread-1] mapred.Task (Task.java:initialize(581)) -  Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@c8a80d8
    2016-07-10 13:29:58,338 INFO  [pool-3-thread-1] mapred.ReduceTask (ReduceTask.java:run(362)) - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@50d379e8
    2016-07-10 13:29:58,351 INFO  [pool-3-thread-1] reduce.MergeManagerImpl (MergeManagerImpl.java:<init>(193)) - MergerManager: memoryLimit=1331114752, maxSingleShuffleLimit=332778688, mergeThreshold=878535744, ioSortFactor=10, memToMemMergeOutputsThreshold=10
    2016-07-10 13:29:58,354 INFO  [EventFetcher for fetching Map Completion Events] reduce.EventFetcher (EventFetcher.java:run(61)) - attempt_local492959629_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
    2016-07-10 13:29:58,381 INFO  [localfetcher#1] reduce.LocalFetcher (LocalFetcher.java:copyMapOutput(140)) - localfetcher#1 about to shuffle output of map attempt_local492959629_0001_m_000000_0 decomp: 182 len: 186 to MEMORY
    2016-07-10 13:29:58,390 INFO  [localfetcher#1] reduce.InMemoryMapOutput (InMemoryMapOutput.java:shuffle(100)) - Read 182 bytes from map-output for attempt_local492959629_0001_m_000000_0
    2016-07-10 13:29:58,419 INFO  [localfetcher#1] reduce.MergeManagerImpl (MergeManagerImpl.java:closeInMemoryFile(307)) - closeInMemoryFile -> map-output of size: 182, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->182
    2016-07-10 13:29:58,420 INFO  [EventFetcher for fetching Map Completion Events] reduce.EventFetcher (EventFetcher.java:run(76)) - EventFetcher is interrupted.. Returning
    2016-07-10 13:29:58,421 INFO  [pool-3-thread-1] mapred.LocalJobRunner (LocalJobRunner.java:statusUpdate(591)) - 1 / 1 copied.
    2016-07-10 13:29:58,422 INFO  [pool-3-thread-1] reduce.MergeManagerImpl (MergeManagerImpl.java:finalMerge(667)) - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
    2016-07-10 13:29:58,445 INFO  [pool-3-thread-1] mapred.Merger (Merger.java:merge(591)) - Merging 1 sorted segments
    2016-07-10 13:29:58,445 INFO  [pool-3-thread-1] mapred.Merger (Merger.java:merge(690)) - Down to the last merge-pass, with 1 segments left of total size: 173 bytes
    2016-07-10 13:29:58,450 INFO  [pool-3-thread-1] reduce.MergeManagerImpl (MergeManagerImpl.java:finalMerge(742)) - Merged 1 segments, 182 bytes to disk to satisfy reduce memory limit
    2016-07-10 13:29:58,451 INFO  [pool-3-thread-1] reduce.MergeManagerImpl (MergeManagerImpl.java:finalMerge(772)) - Merging 1 files, 186 bytes from disk
    2016-07-10 13:29:58,452 INFO  [pool-3-thread-1] reduce.MergeManagerImpl (MergeManagerImpl.java:finalMerge(787)) - Merging 0 segments, 0 bytes from memory into reduce
    2016-07-10 13:29:58,452 INFO  [pool-3-thread-1] mapred.Merger (Merger.java:merge(591)) - Merging 1 sorted segments
    2016-07-10 13:29:58,453 INFO  [pool-3-thread-1] mapred.Merger (Merger.java:merge(690)) - Down to the last merge-pass, with 1 segments left of total size: 173 bytes
    2016-07-10 13:29:58,453 INFO  [pool-3-thread-1] mapred.LocalJobRunner (LocalJobRunner.java:statusUpdate(591)) - 1 / 1 copied.
    2016-07-10 13:29:58,467 INFO  [pool-3-thread-1] Configuration.deprecation (Configuration.java:warnOnceIfDeprecated(1009)) - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
    2016-07-10 13:29:58,474 INFO  [pool-3-thread-1] mapred.Task (Task.java:done(995)) - Task:attempt_local492959629_0001_r_000000_0 is done. And is in the process of committing
    2016-07-10 13:29:58,476 INFO  [pool-3-thread-1] mapred.LocalJobRunner (LocalJobRunner.java:statusUpdate(591)) - 1 / 1 copied.
    2016-07-10 13:29:58,476 INFO  [pool-3-thread-1] mapred.Task (Task.java:commit(1156)) - Task attempt_local492959629_0001_r_000000_0 is allowed to commit now
    2016-07-10 13:29:58,483 INFO  [pool-3-thread-1] output.FileOutputCommitter (FileOutputCommitter.java:commitTask(439)) - Saved output of task 'attempt_local492959629_0001_r_000000_0' to file:/C:/dirout/_temporary/0/task_local492959629_0001_r_000000
    2016-07-10 13:29:58,484 INFO  [pool-3-thread-1] mapred.LocalJobRunner (LocalJobRunner.java:statusUpdate(591)) - reduce > reduce
    2016-07-10 13:29:58,484 INFO  [pool-3-thread-1] mapred.Task (Task.java:sendDone(1115)) - Task 'attempt_local492959629_0001_r_000000_0' done.
    2016-07-10 13:29:58,484 INFO  [pool-3-thread-1] mapred.LocalJobRunner (LocalJobRunner.java:run(325)) - Finishing task: attempt_local492959629_0001_r_000000_0
    2016-07-10 13:29:58,484 INFO  [Thread-3] mapred.LocalJobRunner (LocalJobRunner.java:runTasks(456)) - reduce task executor complete.
    2016-07-10 13:29:58,666 INFO  [main] mapreduce.Job (Job.java:monitorAndPrintJob(1355)) - Job job_local492959629_0001 running in uber mode : false
    2016-07-10 13:29:58,667 INFO  [main] mapreduce.Job (Job.java:monitorAndPrintJob(1362)) -  map 100% reduce 100%
    2016-07-10 13:29:58,668 INFO  [main] mapreduce.Job (Job.java:monitorAndPrintJob(1373)) - Job job_local492959629_0001 completed successfully
    2016-07-10 13:29:58,679 INFO  [main] mapreduce.Job (Job.java:monitorAndPrintJob(1380)) - Counters: 34
        File System Counters
            FILE: Number of bytes read=804
            FILE: Number of bytes written=462717
            FILE: Number of read operations=0
            FILE: Number of large read operations=0
            FILE: Number of write operations=0
        Map-Reduce Framework
            Map input records=6
            Map output records=12
            Map output bytes=156
            Map output materialized bytes=186
            Input split bytes=82
            Combine input records=0
            Combine output records=0
            Reduce input groups=6
            Reduce shuffle bytes=186
            Reduce input records=12
            Reduce output records=6
            Spilled Records=24
            Shuffled Maps =1
            Failed Shuffles=0
            Merged Map outputs=1
            GC time elapsed (ms)=7
            CPU time spent (ms)=0
            Physical memory (bytes) snapshot=0
            Virtual memory (bytes) snapshot=0
            Total committed heap usage (bytes)=467664896
        Sensitive Word
            sensitiveword=1
        Shuffle Errors
            BAD_ID=0
            CONNECTION=0
            IO_ERROR=0
            WRONG_LENGTH=0
            WRONG_MAP=0
            WRONG_REDUCE=0
        File Input Format Counters 
            Bytes Read=64
        File Output Format Counters 
            Bytes Written=51
    fenlie  1
    he  2
    hello   6
    me  1
    she 1
    you 1

特别说明：  
1、计数器counter是全局的。 换言之，MapReduce框架将跨所有map和reduce聚集这些计数器，并在作业结束 时产生一个最终结果。  
2、Configuration: core-site.xml, mapred-site.xml, yarn-site.xml, hdfs-site.xml这四个配置文件读取的方式分为3种：  
第一：用 [Hadoop][]的集群模式运行程序，将会读取 [hadoop][Hadoop]中这几个配置文件的内容。  
第二：将这个xxx-site.xml加载到eclipse的工程src中  
第三：在代码中用 conf.set(name, value)的方式进行指定

[20161021083829067]: /images/20220611/4c761423457346589ef05cfb32aa4d2c.png
[Hadoop]: http://lib.csdn.net/base/hadoop