Hadoop on Mac with IntelliJ IDEA - 8 单表关联NullPointerException

简化陆喜恒. Hadoop实战（第2版）5.4单表关联的代码时遇到空指向异常，经分析是逻辑问题，在此做个记录。

环境：Mac OS X 10.9.5, IntelliJ IDEA 13.1.5, Hadoop 1.2.1

改好的代码如下，在reduce阶段遇到了NullPointerException。

 public class STjoinEx {
     private static final String TIMES = "TIMES";

     public static void main(String[] args) throws Exception {
         Configuration configuration = new Configuration();
         configuration.setInt(TIMES, 1);
         String[] remainingArgs = new GenericOptionsParser(configuration, args).getRemainingArgs();
         if (remainingArgs.length != 2) {
             System.err.println("STjoinEx <input> <output>");
             System.exit(2);
         }

         Job job = new Job(configuration, STjoinEx.class.getSimpleName());
         job.setJarByClass(STjoinEx.class);
         job.setMapperClass(Map.class);
         job.setReducerClass(Reduce.class);
         job.setInputFormatClass(KeyValueTextInputFormat.class);
         job.setOutputFormatClass(TextOutputFormat.class);
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(Text.class);

         FileInputFormat.setInputPaths(job, new Path(remainingArgs[0]));
         FileOutputFormat.setOutputPath(job, new Path(remainingArgs[1]));

         System.exit(job.waitForCompletion(true) ? 0 : 1);

     }

     public static class Map extends Mapper<Text, Text, Text, Text> {
         final static Text LEFT_TABLE = new Text();
         final static Text RIGHT_TABLE = new Text();

         @Override
         protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
             // left table
             LEFT_TABLE.set("1 " + value);
             context.write(key, LEFT_TABLE);
             // right table
             RIGHT_TABLE.set("2 " + key);
             context.write(value, RIGHT_TABLE);
         }
     }

     public static class Reduce extends Reducer<Text, Text, Text, Text> {
         private static final int INDENT = 2;
         private static final Text GRAND_PARENT = new Text();
         private static final Text GRAND_CHILD = new Text();

         @Override
         protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
             // output header
             int times = context.getConfiguration().getInt(TIMES, 1);
             if (times == 1) {
                 context.write(new Text("grandChild"), new Text("grandParent"));
                 context.getConfiguration().setInt(TIMES, ++times);
             }

             // prepare matrix
             int headChar = 0;
             String[] grandChild = new String[10];
             String[] grandParent = new String[10];
             int grandChildNum = 0;
             int grandParentNum = 0;

             for (Text value : values) {
                 headChar = value.charAt(0);
                 if (headChar == '1') {
                     grandParent[grandParentNum] = value.toString().substring(2);
                     grandParentNum++;
                 } else {
                     grandChild[grandChildNum] = value.toString().substring(2);
                     grandChildNum++;
                 }
             }

             // multiply
             if (grandChildNum != 0 && grandChildNum != 0) {
                 for (int i = 0; i < grandChildNum; i++) {
                     GRAND_CHILD.set(grandChild[i]);
                     for (int j = 0; j < grandParentNum; j++) {
                         GRAND_PARENT.set(grandParent[j]);
                         context.write(GRAND_CHILD, GRAND_PARENT);
                     }
                 }
             }
         }
     }
 }

执行输出为

 14/10/07 11:12:51 INFO mapred.JobClient:  map 0% reduce 0%
 14/10/07 11:12:54 INFO mapred.JobClient:  map 100% reduce 0%
 14/10/07 11:13:01 INFO mapred.JobClient:  map 100% reduce 33%
 14/10/07 11:13:04 INFO mapred.JobClient: Task Id : attempt_201410021756_0048_r_000000_0, Status : FAILED
 java.lang.NullPointerException
     at org.apache.hadoop.io.Text.encode(Text.java:388)
     at org.apache.hadoop.io.Text.set(Text.java:178)
     at main.ch5.STjoinEx$Reduce.reduce(STjoinEx.java:96)
     at main.ch5.STjoinEx$Reduce.reduce(STjoinEx.java:61)
     at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:177)
     at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:649)
     at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:418)
     at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
     at java.security.AccessController.doPrivileged(Native Method)
     at javax.security.auth.Subject.doAs(Subject.java:396)
     at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1190)
     at org.apache.hadoop.mapred.Child.main(Child.java:249)

从输出信息可发现，源码96行if (grandChildNum != 0 && grandChildNum != 0)为出错行。两个判断条件重复了，将其中一个改成grandParentNum即可。

执行结果

 grandChild    grandParent
 Jone    Alice
 Jone    Jesse
 Tom    Alice
 Tom    Jesse
 Tom    Mary
 Tom    Ben
 Jone    Mary
 Jone    Ben
 Philip    Alice
 Philip    Jesse
 Mark    Alice
 Mark    Jesse