java - Hadoop - 线程 "main"java.lang.NullPointerException 中的异常

Question

我正尝试通过本教程在 Windows 平台上使用 Apache Hadoop:http://www.codeproject.com/Articles/757934/Apache-Hadoop-for-Windows-Platform?fid=1858035 ， eclipse 部分。一切顺利，直到最后一步。运行程序时我得到:log4j:WARN 找不到记录器 (org.apache.hadoop.metrics2.lib.MutableMetricsFactory) 的附加程序。

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.mapreduce.Job.waitForCompletion(Job.java:1303)
    at Recipe.main(Recipe.java:82)

代码是:

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;
import org.apache.hadoop.util.GenericOptionsParser;

import com.google.gson.Gson;
public class Recipe {

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

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        Gson gson = new Gson();
        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);
            } 

            Roo roo=gson.fromJson(value.toString(),Roo.class);
            if(roo.cookTime!=null)
            {
            word.set(roo.cookTime);
            }
            else
            {
                word.set("none");
            }
            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();
        @SuppressWarnings("deprecation")
        Job job = new Job(conf, "Recipe");
        job.setJarByClass(Recipe.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(otherArgs[0]));
        //FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

       FileInputFormat.addInputPath(job, new Path("hdfs://127.0.0.1:9000/in"));
       FileOutputFormat.setOutputPath(job, new Path("hdfs://127.0.0.1:9000/output"));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
       // job.submit();
    }
}

 class Id
{

    public String oid;
}


 class Ts
{

    public long date ;
}

class Roo
{
    public Id _id ;
    public String name ;
    public String ingredients ;
    public String url ;
    public String image ;
    public Ts ts ;
    public String cookTime;
    public String source ;
    public String recipeYield ;
    public String datePublished;
    public String prepTime ;
    public String description;
}

只有当我尝试通过 Eclipse 运行它时才会发生这种情况。通过 CMD 一切顺利:

javac -classpath C:\hadoop-2.3\share\hadoop\common\hadoop-common-2.3.0.jar;C:\hadoop-2.3\share\hadoop\common\lib\gson-2.2.4.jar;C:\hadoop-2.3\share\hadoop\common\lib\commons-cli-1.2.jar;C:\hadoop-2.3\share\hadoop\mapreduce\hadoop-mapreduce-client-core-2.3.0.jar;Recipe.java
jar -cvf Recipe.jar *.class
hadoop jar c:\Hwork\Recipe.jar Recipe /in /out

知道如何解决这个问题吗？

Answer 1

我从这里遇到了同样的问题和解决方法 http://qnalist.com/questions/4994960/run-spark-unit-test-on-windows-7修复它。

解决方法是:

1. 从以下位置下载已编译的 winutils.exe https://codeload.github.com/srccodes/hadoop-common-2.2.0-bin/zip/master
2. 将此存档直接提取到 d:\winutil 中，应该创建 d:\winutil\bin
3. 在实例化 Job 之前将 System.setProperty("hadoop.home.dir", "d:\\winutil\\"); 添加到您的代码中(对于例如作为 main 方法的第一行)