Wordcount程序如下:
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> { private final static IntWritable one = new IntWritable(1); private Text word = new Text(); 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()) { word.set(tokenizer.nextToken()); output.collect(word, one); } } } public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> { 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.setCombinerClass(Reduce.class); conf.setReducerClass(Reduce.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); FileInputFormat.setInputPaths(conf, new Path("hdfs://192.168.1.181:9000/user/root/bbs_post2")); FileOutputFormat.setOutputPath(conf, new Path("hdfs://192.168.1.181:9000/data/test-out10")); // FileInputFormat.setInputPaths(conf, new Path(args[0])); // FileOutputFormat.setOutputPath(conf, new Path(args[1])); JobClient.runJob(conf); } }报错信息如下:
log4j:WARN No appenders could be found for logger (org.apache.hadoop.metrics2.lib.MutableMetricsFactory).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.
Exception in thread "main" java.lang.NullPointerException
at java.lang.ProcessBuilder.start(Unknown Source)
at org.apache.hadoop.util.Shell.runCommand(Shell.java:445)
at org.apache.hadoop.util.Shell.run(Shell.java:418)
at org.apache.hadoop.util.Shell$ShellCommandExecutor.execute(Shell.java:650)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:739)
at org.apache.hadoop.util.Shell.execCommand(Shell.java:722)
at org.apache.hadoop.fs.RawLocalFileSystem.setPermission(RawLocalFileSystem.java:631)
at org.apache.hadoop.fs.RawLocalFileSystem.mkdirs(RawLocalFileSystem.java:421)
at org.apache.hadoop.fs.FilterFileSystem.mkdirs(FilterFileSystem.java:277)
at org.apache.hadoop.mapreduce.JobSubmissionFiles.getStagingDir(JobSubmissionFiles.java:125)
at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:348)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1285)
at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1282)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Unknown Source)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
at org.apache.hadoop.mapreduce.Job.submit(Job.java:1282)
at org.apache.hadoop.mapred.JobClient$1.run(JobClient.java:562)
at org.apache.hadoop.mapred.JobClient$1.run(JobClient.java:557)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Unknown Source)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
at org.apache.hadoop.mapred.JobClient.submitJobInternal(JobClient.java:557)
at org.apache.hadoop.mapred.JobClient.submitJob(JobClient.java:548)
at org.apache.hadoop.mapred.JobClient.runJob(JobClient.java:833)
at WordCount.main(WordCount.java:71)
麻烦大家帮我看一下是怎么回事,谢谢!
1.classpath下面是否放置hadoopconf下面的*-site.xml文件
2.执行程序的主机是否配置了hadoop集群的hosts
3.是否把该程序打包放在Hadooplib下并且重启了集群,如果不想打包,可以设置conf.setJarClass( Map.class)该包会被分发到集群。
importjava.io.IOException;4importjava.util.*;56importorg.apache.hadoop.fs.Path;7importorg.apache.hadoop.conf.*;8importorg.apache.hadoop.io.*;9importorg.apache.hadoop.mapreduce.*;10importorg.apache.hadoop.mapreduce.lib.input.FileInputFormat;11importorg.apache.hadoop.mapreduce.lib.input.TextInputFormat;12importorg.apache.hadoop.mapreduce.lib.output.FileOutputFormat;13importorg.apache.hadoop.mapreduce.lib.output.TextOutputFormat;1415publicclassWordCount{1617publicstaticclassMapextendsMapper<LongWritable,Text,Text,IntWritable>{18privatefinalstaticIntWritableone=newIntWritable(1);19privateTextword=newText();2021publicvoidmap(LongWritablekey,Textvalue,Contextcontext)throwsIOException,InterruptedException{22Stringline=value.toString();23StringTokenizertokenizer=newStringTokenizer(line);24while(tokenizer.hasMoreTokens()){25word.set(tokenizer.nextToken());26context.write(word,one);27}28}29}3031publicstaticclassReduceextendsReducer<Text,IntWritable,Text,IntWritable>{3233publicvoidreduce(Textkey,Iterable<IntWritable>values,Contextcontext)34throwsIOException,InterruptedException{35intsum=0;36for(IntWritableval:values){37sum+=val.get();38}39context.write(key,newIntWritable(sum));40}41}4243publicstaticvoidmain(String[]args)throwsException{44Configurationconf=newConfiguration();4546Jobjob=newJob(conf,"wordcount");4748job.setOutputKeyClass(Text.class);49job.setOutputValueClass(IntWritable.class);5051job.setMapperClass(Map.class);52job.setReducerClass(Reduce.class);5354job.setInputFormatClass(TextInputFormat.class);55job.setOutputFormatClass(TextOutputFormat.class);5657FileInputFormat.addInputPath(job,newPath(args[0]));58FileOutputFormat.setOutputPath(job,newPath(args[1]));5960job.waitForCompletion(true);61}6263}
1.classpath下面是否放置hadoopconf下面的*-site.xml文件
2.执行程序的主机是否配置了hadoop集群的hosts
3.是否把该程序打包放在Hadooplib下并且重启了集群,如果不想打包,可以设置conf.setJarClass( Map.class)该包会被分发到集群。
版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。