我正在尝试运行puma benchmark中给出的单词计数程序
The WordCount.java file is as follows:
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
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 = new Job(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);
List<String> other_args = new ArrayList<String>();
for(int i=0; i < args.length; ++i) {
try {
if ("-r".equals(args[i])) {
job.setNumReduceTasks(Integer.parseInt(args[++i]));
} else {
other_args.add(args[i]);
}
} catch (NumberFormatException except) {
System.out.println("ERROR: Integer expected instead of " + args[i]);
System.err.println("Usage: wordcount <numReduces> <in> <out>");
System.exit(2);
} catch (ArrayIndexOutOfBoundsException except) {
System.out.println("ERROR: Required parameter missing from " +
args[i-1]);
System.err.println("Usage: wordcount <numReduces> <in> <out>");
System.exit(2);
}
}
// Make sure there are exactly 2 parameters left.
if (other_args.size() != 2) {
System.out.println("ERROR: Wrong number of parameters: " +
other_args.size() + " instead of 2.");
System.err.println("Usage: wordcount <numReduces> <in> <out>");
System.exit(2);
}
FileInputFormat.addInputPath(job, new Path(other_args.get(0)));
FileOutputFormat.setOutputPath(job, new Path(other_args.get(1)));
Date startIteration = new Date();
Boolean waitforCompletion = job.waitForCompletion(true) ;
Date endIteration = new Date();
System.out.println("The iteration took "
+ (endIteration.getTime() - startIteration.getTime()) / 1000
+ " seconds.");
System.exit(waitforCompletion ? 0 : 1);
}
}
我使用了以下命令并得到以下结果:
# javac -cp /opt/local/share/java/hadoop-1.2.1/hadoop-core-1.2.1.jar -d wordcount_classes WordCount.java
# jar -cvf wordcount.jar -C wordcount_classes/ .
我得到的结果是:
added manifest
adding: org/(in = 0) (out= 0)(stored 0%)
adding: org/apache/(in = 0) (out= 0)(stored 0%)
adding: org/apache/hadoop/(in = 0) (out= 0)(stored 0%)
adding: org/apache/hadoop/examples/(in = 0) (out= 0)(stored 0%)
adding: org/apache/hadoop/examples/WordCount$IntSumReducer.class(in = 1793) (out= 750)(deflated 58%)
adding: org/apache/hadoop/examples/WordCount$TokenizerMapper.class(in = 1790) (out= 764)(deflated 57%)
adding: org/apache/hadoop/examples/WordCount.class(in = 3131) (out= 1682)(deflated 46%)
adding: org/myorg/(in = 0) (out= 0)(stored 0%)
adding: org/myorg/WordCount$IntSumReducer.class(in = 1759) (out= 745)(deflated 57%)
adding: org/myorg/WordCount$TokenizerMapper.class(in = 1756) (out= 759)(deflated 56%)
adding: org/myorg/WordCount.class(in = 3080) (out= 1676)(deflated 45%)
# hadoop jar wordcount.jar WordCount ../input/file01.txt ../output/
我得到了以下输出:
Exception in thread "main" java.lang.NoClassDefFoundError: WordCount (wrong name: org/apache/hadoop/examples/WordCount)
at java.lang.ClassLoader.defineClass1(Native Method)
at java.lang.ClassLoader.defineClass(ClassLoader.java:800)
at java.security.SecureClassLoader.defineClass(SecureClassLoader.java:142)
at java.net.URLClassLoader.defineClass(URLClassLoader.java:449)
at java.net.URLClassLoader.access$100(URLClassLoader.java:71)
at java.net.URLClassLoader$1.run(URLClassLoader.java:361)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:412)
at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
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)
我应用了所有的程序描述之前在这个网站上,但没有什么是为我工作。如果有人告诉我如何解决这个问题,我将非常感激。
4条答案
按热度按时间4nkexdtk1#
jar有两个wordount类,用限定符指定要运行的类。
例如
hadoop jar wordcount.jar org.apache.hadoop.examples.WordCount ../input/file01.txt ../output/
或者hadoop jar wordcount.jar org.myorg.WordCount ../input/file01.txt ../output/
u5rb5r592#
你的
WordCount class
在其内部有两个嵌套类,即:TokenizerMapper
以及IntSumReducer
.您需要确保这些类包含在正在生成的jar文件中。试试这个:
0s7z1bwu3#
我认为问题是存在的,因为你没有使用完整的类名。
h6my8fg24#
将包语句更改为
并用完整的类名运行程序。
看看你的输出,你似乎包括
WordCount
在不同的路径(=包)中初始化两次,但在运行程序时,不指定任何包。