问题
I am new to hadoop. I followed the maichel-noll tutorial to set up hadoop in single node.I tried running WordCount program. This is the code I used:
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 WordCount {
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class IntSumReducer
extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "WordCount");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
This is what I get when I try running it.
hduser@aswin-HP-Pavilion-15-Notebook-PC:/usr/local/hadoop$ bin/hadoop jar wc.jar WordCount /home/hduser/gutenberg /home/hduser/gutenberg-output/sample.txt
Exception in thread "main" java.lang.NoClassDefFoundError: WordCount (wrong name: org/myorg/WordCount)
at java.lang.ClassLoader.defineClass1(Native Method)
at java.lang.ClassLoader.defineClass(ClassLoader.java:788)
at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
at java.net.URLClassLoader.defineClass(URLClassLoader.java:447)
at java.net.URLClassLoader.access$100(URLClassLoader.java:71)
at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:411)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:270)
at org.apache.hadoop.util.RunJar.main(RunJar.java:205)
Can anyone please help me. My class path :
hduser@aswin-HP-Pavilion-15-Notebook-PC:/usr/local/hadoop$ hadoop classpath
/usr/local/hadoop/etc/hadoop:/usr/local/hadoop/share/hadoop/common/lib/*:/usr/local/hadoop/share/hadoop/common/*:/usr/local/hadoop/share/hadoop/hdfs:/usr/local/hadoop/share/hadoop/hdfs/lib/*:/usr/local/hadoop/share/hadoop/hdfs/*:/usr/local/hadoop/share/hadoop/yarn/lib/*:/usr/local/hadoop/share/hadoop/yarn/*:/usr/local/hadoop/share/hadoop/mapreduce/lib/*:/usr/local/hadoop/share/hadoop/mapreduce/*:/usr/lib/jvm/java-7-openjdk-i386/lib/tools.jar:/usr/local/hadoop/contrib/capacity-scheduler/*.jar
回答1:
try this,
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
public class WordCount {
public static class Map extends MapReduceBase implements
Mapper<LongWritable, Text, Text, IntWritable> {
@Override
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
value.set(tokenizer.nextToken());
output.collect(value, new IntWritable(1));
}
}
}
public static class Reduce extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable> {
@Override
public void reduce(Text key, Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
}
then run command
bin/hadoop jar WordCount.jar WordCount /hdfs_Input_filename /output_filename
if your code is in particular package then you have to mention package name with class name
bin/hadoop jar WordCount.jar PakageName.WordCount /hdfs_Input_filename /output_filename
回答2:
This may sound crazy. I added package org.myorg; to my code and compiled it again. I placed the class files in org/myorg folder and created the jar file using them. Then I ran using the jar wc.jar org.myorg.WordCount command and it got executed successfully. It would be nice if someone could explain me how it actually ran :D . Any way, thanks a lot for helping me guys.
回答3:
You are using package in your class. So your command should be
bin/hadoop jar wc.jar org.myorg.WordCount /home/hduser/gutenberg /home/hduser/gutenberg-output/sample.txt
回答4:
I think you made a mistake here :
/usr/local/hadoop$ bin/hadoop jar wc.jar WordCount /home/hduser/gutenberg /home/hduser/gutenberg-output/sample.txt
please change it to :
/usr/local/hadoop$ bin/hadoop jar wc.jar org.myorg.WordCount /home/hduser/gutenberg /home/hduser/gutenberg-output/sample.txt
that should work.
@Aswin Alagappan : Reason is a jar file cotains your path in it. JVM cannot find your class in the jar file becase it is in the "jar\org\myorg" path. Understand?
回答5:
try explicitly including the nested classes(i.e. TokenizerMapper and IntSumReducer) in you jar file. Here is how I did it:
jar cvf WordCount.jar WordCount.class WordCount\$TokenizerMapper.class WordCount\$IntSumReducer.class
回答6:
The answer of Kishore, allowed me to go in the right direction, if it’s possible i want to confirm this, reporting what I did about an experiiment with java code on moltiplication of sparse matrix :
1) Source code (downloaded from https://github.com/marufaytekin/MatrixMultiply/tree/master/src/main/java/com/lendap/hadoop), and saved in /home/hduser/playground/src/matrixMult
2) Downloaded datasets (matrix M and N from https://github.com/marufaytekin/MatrixMultiply/tree/master/input), and then saved in HDFS, with the following path : /user/hduser/inMatrix
3) Compilation with hadoop classes, with creation of java Classes in playground/classes5 : javac -classpath $HADOOP_HOME/share/hadoop/common/lib/activation-1.1.jar:$HADOOP_HOME/share/hadoop/common/hadoop-common-2.7.1.jar:/usr/hadoop/hadoop-2.7.1/share/hadoop/mapreduce/* -d playground/classes5 playground/src/matrixMult/*
4) Creation of jar file MatrixMultiply.jar with the following command : jar -cvf playground/MatrixMultiply.jar -C playground/classes5/ .
5) hadoop mapReduce command (from the $HADOOP_HOME path, that in my case is /usr/hadoop/hadoop-2.7.1$ hadoop jar /home/hduser/playground/MatrixMultiply.jar com.lendap.hadoop.MatrixMultiply /user/hduser/inMatrix/ outputMatrix
6) Correct execution of mapreduce job on my 4 nodes cluster. Here, part of the final output :
0,375,890.0 0,376,1005.0 0,377,1377.0 0,378,604.0 0,379,924.0 0,38,476.0 0,380,621.0 0,381,730.0
990,225,542.0 990,226,639.0 990,227,466.0 990,228,406.0 990,229,343.0 990,23,397.0 990,230,794.0
来源：https://stackoverflow.com/questions/26700910/hadoop-java-error-exception-in-thread-main-java-lang-noclassdeffounderror-w