[
https://issues.apache.org/jira/browse/CARBONDATA-1758?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Chetan Bhat updated CARBONDATA-1758:
Description:
Steps :
In Beeline user executes the queries in sequence.
CREATE TABLE uniqdata_DI_int (CUST_ID int,CUST_NAME String,ACTIVE_EMUI_VERSION
string, DOB timestamp, DOJ timestamp, BIGINT_COLUMN1 bigint,BIGINT_COLUMN2
bigint,DECIMAL_COLUMN1 decimal(30,10), DECIMAL_COLUMN2
decimal(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1
int) STORED BY 'org.apache.carbondata.format'
TBLPROPERTIES('DICTIONARY_INCLUDE'='cust_id','NO_INVERTED_INDEX'='cust_id');
LOAD DATA INPATH 'hdfs://hacluster/chetan/3000_UniqData.csv' into table
uniqdata_DI_int OPTIONS('DELIMITER'=',',
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');
Select count(CUST_ID) from uniqdata_DI_int;
Select count(CUST_ID)*10 as multiple from uniqdata_DI_int;
Select avg(CUST_ID) as average from uniqdata_DI_int;
Select floor(CUST_ID) as average from uniqdata_DI_int;
Select ceil(CUST_ID) as average from uniqdata_DI_int;
Select ceiling(CUST_ID) as average from uniqdata_DI_int;
Select CUST_ID*integer_column1 as multiple from uniqdata_DI_int;
Select CUST_ID from uniqdata_DI_int where CUST_ID is null;
*Issue : Select column with is null for no_inverted_index column throws
java.lang.ArrayIndexOutOfBoundsException*
0: jdbc:hive2://10.18.98.34:23040> Select CUST_ID from uniqdata_DI_int where
CUST_ID is null;
Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task
0 in stage 79.0 failed 4 times, most recent failure: Lost task 0.3 in stage
79.0 (TID 123, BLR114278, executor 18):
org.apache.spark.util.TaskCompletionListenerException:
java.util.concurrent.ExecutionException:
java.lang.ArrayIndexOutOfBoundsException: 0
at
org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
at org.apache.spark.scheduler.Task.run(Task.scala:112)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace: (state=,code=0)
Expected : Select column with is null for no_inverted_index column should be
successful displaying the correct result set.
was:
Steps :
In Beeline user executes the queries in sequence.
CREATE TABLE uniqdata_DI_int (CUST_ID int,CUST_NAME String,ACTIVE_EMUI_VERSION
string, DOB timestamp, DOJ timestamp, BIGINT_COLUMN1 bigint,BIGINT_COLUMN2
bigint,DECIMAL_COLUMN1 decimal(30,10), DECIMAL_COLUMN2
decimal(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1
int) STORED BY 'org.apache.carbondata.format'
TBLPROPERTIES('DICTIONARY_INCLUDE'='cust_id','NO_INVERTED_INDEX'='cust_id');
LOAD DATA INPATH 'hdfs://hacluster/chetan/3000_UniqData.csv' into table
uniqdata_DI_int OPTIONS('DELIMITER'=',',
'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');
Select count(CUST_ID) from uniqdata_DI_int;
Select count(CUST_ID)*10 as multiple from uniqdata_DI_int;
Select avg(CUST_ID) as average from uniqdata_DI_int;
Select floor(CUST_ID) as average from uniqdata_DI_int;
Select ceil(CUST_ID) as average from uniqdata_DI_int;
Select ceiling(CUST_ID) as average from uniqdata_DI_int;
Select CUST_ID*integer_column1 as multiple from uniqdata_DI_int;
Select CUST_ID from uniqdata_DI_int where CUST_ID is null;
Issue : Select column with is null for no_inverted_index column throws
java.lang.ArrayIndexOutOfBoundsException
0: jdbc:hive2://10.18.98.34:23040> Select CUST_ID from uniqdata_DI_int where
CUST_ID is null;
Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task
0 in stage 79.0 failed 4 times, most recent failure: Lost task 0.3 in stage
79.0 (TID 123, BLR114278, executor 18):
org.apache.spark.util.TaskCompletionListenerException:
java.util.concurrent.ExecutionException:
java.lang.ArrayIndexOutOfBoundsException: 0
at
org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:105)
at org.apache.spark.scheduler.Task.run(Task.scala:112)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace: (state=,code=0)
Expected : Select column