Major Description
Got indexOutOfBound exception.
Here is the pig script:
register /grid/0/dev/hadoopqa/jars/zebra.jar;
--a1 = load '1.txt' as (a:int, b:float,c:long,d:double,e:chararray,f:bytearray,r1(f1:chararray,f2:chararray),m1:map[]);
--a2 = load 'empty.txt' as (a:int, b:float,c:long,d:double,e:chararray,f:bytearray,r1(f1:chararray,f2:chararray),m1:map[]);
--dump a1;
--a1order = order a1 by a;
--a2order = order a2 by a;
--store a1order into 'a1' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c];[d,e,f,r1,m1]');
--store a2order into 'empty' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c];[d,e,f,r1,m1]');
rec1 = load 'a1' using org.apache.hadoop.zebra.pig.TableLoader();
rec2 = load 'empty' using org.apache.hadoop.zebra.pig.TableLoader();
joina = join rec1 by a, rec2 by a using "merge" ;
dump joina;
======
please note that table "a1" and "empty" are created correctly.
Here is the stack trace:
Backend error message
---------------------
java.lang.ArrayIndexOutOfBoundsException: 0
at org.apache.hadoop.zebra.mapred.TableInputFormat.getTableRecordReader(TableInputFormat.java:478)
at org.apache.hadoop.zebra.pig.TableLoader.bindTo(TableLoader.java:166)
at org.apache.pig.backend.hadoop.executionengine.physicalLayer.relationalOperators.POMergeJoin.seekInRightStream(POMergeJoin.java:400)
at org.apache.pig.backend.hadoop.executionengine.physicalLayer.relationalOperators.POMergeJoin.getNext(POMergeJoin.java:181)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigMapBase.runPipeline(PigMapBase.java:247)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigMapBase.map(PigMapBase.java:238)
at org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigMapOnly$Map.map(PigMapOnly.java:65)
at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:50)
at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:358)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:307)
at org.apache.hadoop.mapred.Child.main(Child.java:159)
Pig Stack Trace
---------------
ERROR 6015: During execution, encountered a Hadoop error.
org.apache.pig.impl.logicalLayer.FrontendException: ERROR 1066: Unable to open iterator for alias joina
at org.apache.pig.PigServer.openIterator(PigServer.java:481)
at org.apache.pig.tools.grunt.GruntParser.processDump(GruntParser.java:539)
at org.apache.pig.tools.pigscript.parser.PigScriptParser.parse(PigScriptParser.java:241)
at org.apache.pig.tools.grunt.GruntParser.parseStopOnError(GruntParser.java:168)
at org.apache.pig.tools.grunt.GruntParser.parseStopOnError(GruntParser.java:144)
at org.apache.pig.tools.grunt.Grunt.exec(Grunt.java:89)
at org.apache.pig.Main.main(Main.java:386)
Caused by: org.apache.pig.backend.executionengine.ExecException: ERROR 6015: During execution, encountered a Hadoop error.
at .apache.hadoop.zebra.mapred.TableInputFormat.getTableRecordReader(TableInputFormat.java:478)
at .apache.hadoop.zebra.pig.TableLoader.bindTo(TableLoader.java:166)
at .apache.pig.backend.hadoop.executionengine.physicalLayer.relationalOperators.POMergeJoin.seekInRightStream(POMergeJoin.java:400)
at .apache.pig.backend.hadoop.executionengine.physicalLayer.relationalOperators.POMergeJoin.getNext(POMergeJoin.java:181)
at .apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigMapBase.runPipeline(PigMapBase.java:247)
at .apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigMapBase.map(PigMapBase.java:238)
at .apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigMapOnly$Map.map(PigMapOnly.java:65)
at .apache.hadoop.mapred.MapRunner.run(MapRunner.java:50)
at .apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:358)
at .apache.hadoop.mapred.MapTask.run(MapTask.java:307)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 0
... 10 more
================================================================================