joobisb created CARBONDATA-967:
----------------------------------
Summary: select * with order by and limit for join not working
Key: CARBONDATA-967
URL:
https://issues.apache.org/jira/browse/CARBONDATA-967 Project: CarbonData
Issue Type: Bug
Components: spark-integration
Reporter: joobisb
Priority: Minor
Attachments: carbon1.csv, carbon2.csv
CREATE TABLE carbon1 (imei string,age int,task bigint,sale decimal(10,3),productdate timestamp,score double)STORED BY 'org.apache.carbondata.format';
LOAD DATA INPATH 'hdfs://hacluster/data/carbon1.csv' INTO TABLE carbon1 options ('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_LOGGER_ENABLE'='false','BAD_RECORDS_ACTION'='FORCE', 'FILEHEADER'= '');
CREATE TABLE carbon2 (imei string,age int,task bigint,sale decimal(10,3),productdate timestamp,score double)STORED BY 'org.apache.carbondata.format';
LOAD DATA INPATH 'hdfs://hacluster/data/carbon2.csv' INTO TABLE carbon2 options ('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_LOGGER_ENABLE'='false','BAD_RECORDS_ACTION'='FORCE', 'FILEHEADER'= '');
CREATE TABLE carbon3 (imei string,age int,task bigint,sale decimal(10,3),productdate timestamp,score double)STORED BY 'org.apache.carbondata.format';
LOAD DATA INPATH 'hdfs://hacluster/data/carbon1.csv' INTO TABLE carbon3 options ('DELIMITER'=',', 'QUOTECHAR'='"','BAD_RECORDS_LOGGER_ENABLE'='false','BAD_RECORDS_ACTION'='FORCE', 'FILEHEADER'= '');
select * from carbon1 a full outer join carbon2 b on substr(a.productdate,1,10)=substr(b.productdate,1,10) order by a.imei limit 100;
it is throwing below exception
ERROR TaskSetManager: Task 0 in stage 12.0 failed 1 times; aborting job
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 12.0 failed 1 times, most recent failure: Lost task 0.0 in stage 12.0 (TID 211, localhost, executor driver): java.lang.ClassCastException: org.apache.spark.unsafe.types.UTF8String cannot be cast to java.lang.Integer
at scala.runtime.BoxesRunTime.unboxToInt(BoxesRunTime.java:101)
at org.apache.spark.sql.CarbonDictionaryDecoder$$anonfun$doExecute$1$$anonfun$3$$anon$1$$anonfun$next$1.apply$mcVI$sp(CarbonDictionaryDecoder.scala:112)
at org.apache.spark.sql.CarbonDictionaryDecoder$$anonfun$doExecute$1$$anonfun$3$$anon$1$$anonfun$next$1.apply(CarbonDictionaryDecoder.scala:109)
at org.apache.spark.sql.CarbonDictionaryDecoder$$anonfun$doExecute$1$$anonfun$3$$anon$1$$anonfun$next$1.apply(CarbonDictionaryDecoder.scala:109)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.sql.CarbonDictionaryDecoder$$anonfun$doExecute$1$$anonfun$3$$anon$1.next(CarbonDictionaryDecoder.scala:109)
at org.apache.spark.sql.CarbonDictionaryDecoder$$anonfun$doExecute$1$$anonfun$3$$anon$1.next(CarbonDictionaryDecoder.scala:99)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:232)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
at
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
Locked
