[
https://issues.apache.org/jira/browse/CARBONDATA-904?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15967456#comment-15967456
]
Rahul Kumar commented on CARBONDATA-904:
----------------------------------------
[~swati.rao] there is a blank-space in value *' 2019-07-05 13:07:30'* . this
behaviour is not supported in Spark-1.6 .
You can try same query without blank-space.
> ArrayIndexOutOfBoundsException
> -------------------------------
>
> Key: CARBONDATA-904
> URL: https://issues.apache.org/jira/browse/CARBONDATA-904
> Project: CarbonData
> Issue Type: Bug
> Environment: Spark1.6
> Reporter: SWATI RAO
> Assignee: Rahul Kumar
> Fix For: 1.1.0-incubating
>
> Attachments: Test_Data1_h1.csv, Test_Data1_h1.csv
>
>
> Or operator is not working properly.
> When we execute these query in hive it is working fine but when we execute
> the same in carbondata it throws an exception:
> java.lang.ArrayIndexOutOfBoundsException
> HIVE:
> 0: jdbc:hive2://hadoop-master:10000> create table Test_Boundary_h1 (c1_int
> int,c2_Bigint Bigint,c3_Decimal Decimal(38,30),c4_double double,c5_string
> string,c6_Timestamp Timestamp,c7_Datatype_Desc string) ROW FORMAT DELIMITED
> FIELDS TERMINATED BY ',' ;
> +---------+--+
> | result |
> +---------+--+
> +---------+--+
> No rows selected (1.177 seconds)
> 0: jdbc:hive2://hadoop-master:10000> load data local inpath
> '/opt/Carbon/CarbonData/TestData/Data/Test_Data1_h1.csv' OVERWRITE INTO TABLE
> Test_Boundary_h1 ;
> +---------+--+
> | Result |
> +---------+--+
> +---------+--+
> No rows selected (0.437 seconds)
> 0: jdbc:hive2://hadoop-master:10000> select c6_Timestamp,max(c6_Timestamp)
> from Test_Boundary_h1 where c6_Timestamp ='2017-07-01 12:07:28' or
> c6_Timestamp ='2019-07-05 13:07:30' or c6_Timestamp = '1999-01-06 10:05:29'
> group by c6_Timestamp ;
> +------------------------+------------------------+--+
> | c6_Timestamp | _c1 |
> +------------------------+------------------------+--+
> | 2017-07-01 12:07:28.0 | 2017-07-01 12:07:28.0 |
> +------------------------+------------------------+--+
> 1 row selected (1.637 seconds)
> CARBONDATA:
> 0: jdbc:hive2://hadoop-master:10000> create table Test_Boundary (c1_int
> int,c2_Bigint Bigint,c3_Decimal Decimal(38,30),c4_double double,c5_string
> string,c6_Timestamp Timestamp,c7_Datatype_Desc string) STORED BY
> 'org.apache.carbondata.format' ;
> +---------+--+
> | Result |
> +---------+--+
> +---------+--+
> No rows selected (4.48 seconds)
> 0: jdbc:hive2://hadoop-master:10000> LOAD DATA INPATH
> 'hdfs://192.168.2.145:54310/BabuStore/Data/Test_Data1.csv' INTO table
> Test_Boundary
> OPTIONS('DELIMITER'=',','QUOTECHAR'='','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='')
> ;
> +---------+--+
> | Result |
> +---------+--+
> +---------+--+
> No rows selected (4.445 seconds)
> 0: jdbc:hive2://hadoop-master:10000> select c6_Timestamp,max(c6_Timestamp)
> from Test_Boundary where c6_Timestamp ='2017-07-01 12:07:28' or c6_Timestamp
> =' 2019-07-05 13:07:30' or c6_Timestamp = '1999-01-06 10:05:29' group by
> c6_Timestamp ;
> Error: org.apache.spark.SparkException: Job aborted due to stage failure:
> Task 0 in stage 5.0 failed 4 times, most recent failure: Lost task 0.3 in
> stage 5.0 (TID 8, hadoop-master): java.lang.RuntimeException:
> java.util.concurrent.ExecutionException:
> java.lang.ArrayIndexOutOfBoundsException: 0
> at
> org.apache.carbondata.core.scan.processor.AbstractDataBlockIterator.updateScanner(AbstractDataBlockIterator.java:136)
> at
> org.apache.carbondata.core.scan.processor.impl.DataBlockIteratorImpl.next(DataBlockIteratorImpl.java:50)
> at
> org.apache.carbondata.core.scan.processor.impl.DataBlockIteratorImpl.next(DataBlockIteratorImpl.java:32)
> at
> org.apache.carbondata.core.scan.result.iterator.DetailQueryResultIterator.getBatchResult(DetailQueryResultIterator.java:50)
> at
> org.apache.carbondata.core.scan.result.iterator.DetailQueryResultIterator.next(DetailQueryResultIterator.java:41)
> at
> org.apache.carbondata.core.scan.result.iterator.DetailQueryResultIterator.next(DetailQueryResultIterator.java:31)
> at
> org.apache.carbondata.core.scan.result.iterator.ChunkRowIterator.<init>(ChunkRowIterator.java:41)
> at
> org.apache.carbondata.hadoop.CarbonRecordReader.initialize(CarbonRecordReader.java:79)
> at
> org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:204)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.util.concurrent.ExecutionException:
> java.lang.ArrayIndexOutOfBoundsException: 0
> at java.util.concurrent.FutureTask.report(FutureTask.java:122)
> at java.util.concurrent.FutureTask.get(FutureTask.java:192)
> at
> org.apache.carbondata.core.scan.processor.AbstractDataBlockIterator.getNextScannedResult(AbstractDataBlockIterator.java:146)
> at
> org.apache.carbondata.core.scan.processor.AbstractDataBlockIterator.updateScanner(AbstractDataBlockIterator.java:124)
> ... 26 more
> Caused by: java.lang.ArrayIndexOutOfBoundsException: 0
> at
> org.apache.carbondata.core.util.BitSetGroup.getBitSet(BitSetGroup.java:40)
> at org.apache.carbondata.core.util.BitSetGroup.or(BitSetGroup.java:68)
> at
> org.apache.carbondata.core.scan.filter.executer.OrFilterExecuterImpl.applyFilter(OrFilterExecuterImpl.java:40)
> at
> org.apache.carbondata.core.scan.filter.executer.OrFilterExecuterImpl.applyFilter(OrFilterExecuterImpl.java:38)
> at
> org.apache.carbondata.core.scan.scanner.impl.FilterScanner.fillScannedResult(FilterScanner.java:147)
> at
> org.apache.carbondata.core.scan.scanner.impl.FilterScanner.scanBlocklet(FilterScanner.java:92)
> at
> org.apache.carbondata.core.scan.processor.AbstractDataBlockIterator$1.call(AbstractDataBlockIterator.java:189)
> at
> org.apache.carbondata.core.scan.processor.AbstractDataBlockIterator$1.call(AbstractDataBlockIterator.java:176)
> at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> ... 3 more
> Driver stacktrace: (state=,code=0)
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
