这是连接两个关系的作业，
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.contrib.utils.join.*;
import java.io.*;
public class TwoByTwo extends Configured implements Tool
{
public static class MapClass extends DataJoinMapperBase
{
protected Text generateInputTag( String inputFile)
{
String datasource = inputFile.split( "\\.")[ 0];
return new Text( datasource);
}//end generateInputTag
protected Text generateGroupKey( TaggedMapOutput aRecord)
{
String line = ( ( Text) aRecord.getData()).toString();
//between two relations there may be more than one common attributes
//so group key has to include all these common attributes. Common
//attributes begin with an '_'( underscore).
String[] tokens = line.split(",");
String groupKey = "";
for( String s : tokens)
{
if( s.charAt( 0) == '_')
{
groupKey = groupKey + s;
}
}
return new Text( groupKey);
}//end generateGroupKey
protected TaggedMapOutput generateTaggedMapOutput( Object value)
{
TaggedWritable retv = new TaggedWritable( ( Text) value);
retv.setTag( this.inputTag);
return retv;
}//end TaggedMapOutput
}//end MapClass
public static class Reduce extends DataJoinReducerBase
{
protected TaggedMapOutput combine( Object[] tags, Object[] values)
{
if( tags.length < 2)
{
return null;
}
String joinedStr = "";
for( int i = 0; i < values.length; i++)
{
if( i > 0)
{
joinedStr += ",";
}
TaggedWritable tw = ( TaggedWritable) values[ i];
String line = ( ( Text) tw.getData()).toString();
String[] tokens = line.split( ",", 2);
joinedStr += tokens[ 1];
}
TaggedWritable retv = new TaggedWritable( new Text( joinedStr));
retv.setTag( ( Text) tags[ 0]);
return retv;
}//end TaggedMapOutput
}//end Reduce
public static class TaggedWritable extends TaggedMapOutput
{
private Writable data;
public TaggedWritable( Writable data)
{
this.tag = new Text( "");
this.data = data;
}//end TaggedWritable
public Writable getData()
{
return data;
}//end getData
public void write( DataOutput out) throws IOException
{
this.tag.write( out);
this.data.write( out);
}//end write
public void readFields( DataInput in) throws IOException
{
this.tag.readFields( in);
this.data.readFields( in);
}//end readFields
}//end TaggedWritable
public int run( String[] args) throws Exception
{
Configuration conf = getConf();
JobConf job = new JobConf( conf, TwoByTwo.class);
Path in = new Path( "relations/");
Path out = new Path( "relout/");
FileInputFormat.setInputPaths( job, in);
FileOutputFormat.setOutputPath( job, out);
job.setJobName( "TwoByTwo");
job.setMapperClass( MapClass.class);
job.setReducerClass( Reduce.class);
job.setInputFormat( TextInputFormat.class);
job.setOutputFormat( TextOutputFormat.class);
job.setOutputKeyClass( Text.class);
job.setOutputValueClass( TaggedWritable.class);
job.set("mapred.textoutputformat.separator", ",");
JobClient.runJob( job);
return 0;
}//end run
public static void main( String[] args) throws Exception
{
int res = ToolRunner.run( new Configuration(), new TwoByTwo(), args);
System.exit( res);
}//end main
}
当我运行这个作业时，
bin/hadoop jar /home/hduser/TwoByTwo.jar TwoByTwo -libjars /usr/local/hadoop/contrib/datajoin/hadoop-datajoin-1.0.3.jar
MapClass 正常运行。当 Reduce 在运行一段时间后运行时，我得到这个 NoSuchMethodException
12/10/18 16:38:17 INFO mapred.JobClient: map 100% reduce 27%
12/10/18 16:38:19 INFO mapred.JobClient: Task Id : attempt_201210181416_0013_r_000000_0, Status : FAILED
java.lang.RuntimeException: java.lang.NoSuchMethodException: TwoByTwo$TaggedWritable.<init>()
at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:115)
at org.apache.hadoop.io.serializer.WritableSerialization$WritableDeserializer.deserialize(WritableSerialization.java:62)
at org.apache.hadoop.io.serializer.WritableSerialization$WritableDeserializer.deserialize(WritableSerialization.java:40)
at org.apache.hadoop.mapred.Task$ValuesIterator.readNextValue(Task.java:1271)
at org.apache.hadoop.mapred.Task$ValuesIterator.next(Task.java:1211)
at org.apache.hadoop.mapred.ReduceTask$ReduceValuesIterator.moveToNext(ReduceTask.java:249)
at org.apache.hadoop.mapred.ReduceTask$ReduceValuesIterator.next(ReduceTask.java:245)
at org.apache.hadoop.contrib.utils.join.DataJoinReducerBase.regroup(DataJoinReducerBase.java:106)
at org.apache.hadoop.contrib.utils.join.DataJoinReducerBase.reduce(DataJoinReducerBase.java:129)
at org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:519)
at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:420)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1121)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
Caused by: java.lang.NoSuchMethodException: TwoByTwo$TaggedWritable.<init>()
at java.lang.Class.getConstructor0(Class.java:2721)
at java.lang.Class.getDeclaredConstructor(Class.java:2002)
at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:109)
... 15 more
我对嵌套类 TaggedWritable 有疑问。为什么我在 reduce 端而不是 map 端遇到此类问题？我该如何解决这个错误？两个关系的约束对错误有什么影响？感谢您的帮助。
最佳答案
类 TaggedWritable 没有空构造函数，因此在应该读取序列化数据的 reduce 阶段应用程序失败，因为无法创建 TaggedWritable 类型的键通过反射。您应该添加一个空的构造函数。
您的映射阶段成功完成，因为在映射阶段您的映射器创建了 TaggedWritable 类型的键本身。
关于Hadoop : NoSuchMethodException，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/12956488/