map reduce文件输出计数器为零

tzdcorbm  于 2021-06-02  发布在  Hadoop
关注(0)|答案(0)|浏览(232)

我正在为一个文件的反向索引编写map reduce代码，该文件的每一行都包含“doc\ id title document contents”。我不明白为什么文件输出格式计数器为零，尽管map reduce作业毫无例外地成功完成。

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
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.output.FileOutputFormat;

public class InvertedIndex {

 public static class TokenizerMapper             
     extends Mapper<Object, Text, Text, Text> {

    private Text word = new Text();
    private Text docID_Title = new Text();

    //RemoveStopWords is a different class
    static RemoveStopWords rmvStpWrd = new RemoveStopWords(); 

    //Stemmer is a different class
    Stemmer stemmer = new Stemmer();

    public void map(Object key, Text value, Context context)
                  throws IOException, InterruptedException {

        rmvStpWrd.makeStopWordList();
        StringTokenizer itr = new StringTokenizer(value.toString().replaceAll(" [^\\p{L}]", " "));

 //fetching id of the document
        String id = null;
        String title = null;

     if(itr.hasMoreTokens()) 
            id = itr.nextToken();

     //fetching title of the document
        if(itr.hasMoreTokens())
              title = itr.nextToken();

     String ID_TITLE = id + title;

       if(id!=null)
           docID_Title.set(ID_TITLE);

        while (itr.hasMoreTokens()) {

            /*manipulation of tokens:
             * First we remove stop words
             * Then Stem the words 
            */
            String temp = itr.nextToken().toLowerCase();
            if(RemoveStopWords.isStopWord(temp)) {

                continue;
            }    
            else {

                //now the word is not a stop word
                //we will stem it

                  char[] a;
                  stemmer.add((a = temp.toCharArray()), a.length);
                  stemmer.stem();                     
                  temp = stemmer.toString();
                  word.set(temp);
                  context.write(word, docID_Title); 
            }

        }//end while
    }//end map
}//end mapper

public static class IntSumReducer
       extends Reducer<Text,Text,Text, Text> {

    public void reduce(Text key, Iterable<Text> values, Context context)
           throws IOException, InterruptedException {

        //to iterate over the values
        Iterator<Text>  itr = values.iterator();
        String old = itr.next().toString();

        int freq = 1;
        String next = null;
        boolean isThere = true;
        StringBuilder stringBuilder = new StringBuilder();

        while(itr.hasNext()) {

             //freq counts number of times a word comes in a document
             freq = 1;

            while((isThere = itr.hasNext())) {

                next = itr.next().toString();
                if(old == next)
                       freq++;
                else {
                       //the loop break when we get different docID_Title for the word(key)
                       break;
                }
            //if more data is there
        if(isThere) {
                    old = old +"_"+ freq;
                    stringBuilder.append(old);
                    stringBuilder.append(" | ");
                    old = next;
                    context.write(key, new Text(stringBuilder.toString()));
                    stringBuilder.setLength(0);
       }
       else   {
               //for the last key
                freq++;
                old = old +"_"+ freq;
                stringBuilder.append(old);
                stringBuilder.append(" | ");
                old = next;

                context.write(key, new Text(stringBuilder.toString()));
       }//end else
    }//end while

     }//end while

   }//end reduce    
 }//end reducer

  public static void main(String[] args) throws Exception {

      Configuration conf = new Configuration();

      Job job = Job.getInstance(conf, "InvertedIndex");
      job.setJarByClass(InvertedIndex.class);
      job.setMapperClass(TokenizerMapper.class);
      job.setCombinerClass(IntSumReducer.class);
      job.setReducerClass(IntSumReducer.class);
      job.setOutputKeyClass(Text.class);
      job.setOutputValueClass(Text.class);

      FileInputFormat.addInputPath(job, new Path(args[0]));
      FileOutputFormat.setOutputPath(job, new Path(args[1]));

      System.exit(job.waitForCompletion(true) ? 0 : 1);
  }//end main

}//end InvertexIndex

这是我得到的结果：

16/10/03 15:34:21 INFO Configuration.deprecation: session.id is    deprecated. Instead, use dfs.metrics.session-id
16/10/03 15:34:21 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
16/10/03 15:34:21 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
16/10/03 15:34:22 INFO input.FileInputFormat: Total input paths to process : 1
16/10/03 15:34:22 INFO mapreduce.JobSubmitter: number of splits:1
16/10/03 15:34:22 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local507694567_0001
16/10/03 15:34:22 INFO mapreduce.Job: The url to track the job: http://localhost:8080/
16/10/03 15:34:22 INFO mapreduce.Job: Running job: job_local507694567_0001
16/10/03 15:34:22 INFO mapred.LocalJobRunner: OutputCommitter set in config null
16/10/03 15:34:22 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
16/10/03 15:34:22 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
16/10/03 15:34:22 INFO mapred.LocalJobRunner: Waiting for map tasks
16/10/03 15:34:22 INFO mapred.LocalJobRunner: Starting task: attempt_local507694567_0001_m_000000_0
16/10/03 15:34:22 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
16/10/03 15:34:22 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
16/10/03 15:34:22 INFO mapred.MapTask: Processing split: hdfs://localhost:9000/user/sonu/ss.txt:0+1002072
16/10/03 15:34:23 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584)
16/10/03 15:34:23 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100
16/10/03 15:34:23 INFO mapred.MapTask: soft limit at 83886080
16/10/03 15:34:23 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600
16/10/03 15:34:23 INFO mapred.MapTask: kvstart = 26214396; length = 6553600
16/10/03 15:34:23 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
16/10/03 15:34:23 INFO mapreduce.Job: Job job_local507694567_0001 running in uber mode : false
16/10/03 15:34:23 INFO mapreduce.Job:  map 0% reduce 0%
16/10/03 15:34:24 INFO mapred.LocalJobRunner: 
16/10/03 15:34:24 INFO mapred.MapTask: Starting flush of map output
16/10/03 15:34:24 INFO mapred.MapTask: Spilling map output
16/10/03 15:34:24 INFO mapred.MapTask: bufstart = 0; bufend = 2206696; bufvoid = 104857600
16/10/03 15:34:24 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 25789248(103156992); length = 425149/6553600
16/10/03 15:34:24 INFO mapred.MapTask: Finished spill 0
16/10/03 15:34:24 INFO mapred.Task: Task:attempt_local507694567_0001_m_000000_0 is done. And is in the process of committing
16/10/03 15:34:24 INFO mapred.LocalJobRunner: map
16/10/03 15:34:24 INFO mapred.Task: Task 'attempt_local507694567_0001_m_000000_0' done.
16/10/03 15:34:24 INFO mapred.LocalJobRunner: Finishing task: attempt_local507694567_0001_m_000000_0
16/10/03 15:34:24 INFO mapred.LocalJobRunner: map task executor complete.
16/10/03 15:34:25 INFO mapred.LocalJobRunner: Waiting for reduce tasks
16/10/03 15:34:25 INFO mapred.LocalJobRunner: Starting task: attempt_local507694567_0001_r_000000_0
16/10/03 15:34:25 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
16/10/03 15:34:25 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
16/10/03 15:34:25 INFO mapred.ReduceTask: Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@5d0e7307
16/10/03 15:34:25 INFO reduce.MergeManagerImpl: MergerManager: memoryLimit=333971456, maxSingleShuffleLimit=83492864, mergeThreshold=220421168, ioSortFactor=10, memToMemMergeOutputsThreshold=10
16/10/03 15:34:25 INFO reduce.EventFetcher: attempt_local507694567_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
16/10/03 15:34:25 INFO reduce.LocalFetcher: localfetcher#1 about to shuffle output of map attempt_local507694567_0001_m_000000_0 decomp: 2 len: 6 to MEMORY
16/10/03 15:34:25 INFO reduce.InMemoryMapOutput: Read 2 bytes from map-output for attempt_local507694567_0001_m_000000_0
16/10/03 15:34:25 INFO reduce.MergeManagerImpl: closeInMemoryFile -> map-output of size: 2, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->2
16/10/03 15:34:25 INFO reduce.EventFetcher: EventFetcher is interrupted.. Returning
16/10/03 15:34:25 INFO mapred.LocalJobRunner: 1 / 1 copied.
16/10/03 15:34:25 INFO reduce.MergeManagerImpl: finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
16/10/03 15:34:25 INFO mapred.Merger: Merging 1 sorted segments
16/10/03 15:34:25 INFO mapred.Merger: Down to the last merge-pass, with 0 segments left of total size: 0 bytes
16/10/03 15:34:25 INFO reduce.MergeManagerImpl: Merged 1 segments, 2 bytes to disk to satisfy reduce memory limit
16/10/03 15:34:25 INFO reduce.MergeManagerImpl: Merging 1 files, 6 bytes from disk
16/10/03 15:34:25 INFO reduce.MergeManagerImpl: Merging 0 segments, 0 bytes from memory into reduce
16/10/03 15:34:25 INFO mapred.Merger: Merging 1 sorted segments
16/10/03 15:34:25 INFO mapred.Merger: Down to the last merge-pass, with 0 segments left of total size: 0 bytes
16/10/03 15:34:25 INFO mapred.LocalJobRunner: 1 / 1 copied.
16/10/03 15:34:25 INFO Configuration.deprecation: mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
16/10/03 15:34:25 INFO mapred.Task: Task:attempt_local507694567_0001_r_000000_0 is done. And is in the process of committing
16/10/03 15:34:25 INFO mapred.LocalJobRunner: 1 / 1 copied.
16/10/03 15:34:25 INFO mapred.Task: Task attempt_local507694567_0001_r_000000_0 is allowed to commit now
16/10/03 15:34:25 INFO output.FileOutputCommitter: Saved output of task 'attempt_local507694567_0001_r_000000_0' to hdfs://localhost:9000/user/sonu/output/_temporary/0/task_local507694567_0001_r_000000
16/10/03 15:34:25 INFO mapred.LocalJobRunner: reduce > reduce
16/10/03 15:34:25 INFO mapred.Task: Task 'attempt_local507694567_0001_r_000000_0' done.
16/10/03 15:34:25 INFO mapred.LocalJobRunner: Finishing task: attempt_local507694567_0001_r_000000_0
16/10/03 15:34:25 INFO mapred.LocalJobRunner: reduce task executor complete.
16/10/03 15:34:25 INFO mapreduce.Job:  map 100% reduce 100%
16/10/03 15:34:25 INFO mapreduce.Job: Job job_local507694567_0001 completed successfully
16/10/03 15:34:25 INFO mapreduce.Job: Counters: 35
File System Counters
    FILE: Number of bytes read=17342
    FILE: Number of bytes written=571556
    FILE: Number of read operations=0
    FILE: Number of large read operations=0
    FILE: Number of write operations=0
    HDFS: Number of bytes read=2004144
    HDFS: Number of bytes written=0
    HDFS: Number of read operations=13
    HDFS: Number of large read operations=0
    HDFS: Number of write operations=4
Map-Reduce Framework
    Map input records=53
    Map output records=106288
    Map output bytes=2206696
    Map output materialized bytes=6
    Input split bytes=103
    Combine input records=106288
    Combine output records=0
    Reduce input groups=0
    Reduce shuffle bytes=6
    Reduce input records=0
    Reduce output records=0
    Spilled Records=0
    Shuffled Maps =1
    Failed Shuffles=0
    Merged Map outputs=1
    GC time elapsed (ms)=12
    Total committed heap usage (bytes)=562036736
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=1002072
File Output Format Counters 
    Bytes Written=0
hadoopmapreduceinverted-index

暂无答案！

目前还没有任何答案，快来回答吧！

我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com