Posted by
Akash R Nilugal (Jira) on
Aug 26, 2016; 3:54am
URL: http://apache-carbondata-dev-mailing-list-archive.168.s1.nabble.com/jira-Created-CARBONDATA-180-give-proper-error-message-when-dataloading-with-wrong-delimiter-value-tp472.html
QiangCai created CARBONDATA-180:
-----------------------------------
Summary: give proper error message when dataloading with wrong delimiter value
Key: CARBONDATA-180
URL:
https://issues.apache.org/jira/browse/CARBONDATA-180 Project: CarbonData
Issue Type: Bug
Reporter: QiangCai
Assignee: QiangCai
Priority: Minor
Reproduce:
CREATE TABLE IF NOT EXISTS t3
(ID Int, date Timestamp, country String, name String, phonetype String, serialname String, salary Int)
STORED BY 'carbondata'
LOAD DATA LOCAL INPATH 'data.csv' into table t3 options('DELIMITER'='#', 'FILEHEADER'='ID,date,country,name,phonetype,serialname,salary')
File name:data.csv
1,2015/7/23,china,aaa1,phone197,ASD69643,15000
2,2015/7/24,china,aaa2,phone756,ASD42892,15001
3,2015/7/25,china,aaa3,phone1904,ASD37014,15002
Exception:
ERROR 26-08 11:44:12,881 - generate global dictionary failed
java.lang.ArrayIndexOutOfBoundsException: 2
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$$anonfun$pruneDimensions$1$$anonfun$apply$1$$anonfun$apply$mcV$sp$1.apply(GlobalDictionaryUtil.scala:79)
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$$anonfun$pruneDimensions$1$$anonfun$apply$1$$anonfun$apply$mcV$sp$1.apply(GlobalDictionaryUtil.scala:76)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$$anonfun$pruneDimensions$1$$anonfun$apply$1.apply$mcV$sp(GlobalDictionaryUtil.scala:76)
at scala.util.control.Breaks.breakable(Breaks.scala:37)
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$$anonfun$pruneDimensions$1.apply(GlobalDictionaryUtil.scala:75)
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$$anonfun$pruneDimensions$1.apply(GlobalDictionaryUtil.scala:74)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.pruneDimensions(GlobalDictionaryUtil.scala:74)
at org.apache.carbondata.spark.util.GlobalDictionaryUtil$.generateGlobalDictionary(GlobalDictionaryUtil.scala:697)
at org.apache.spark.sql.execution.command.LoadTable.run(carbonTableSchema.scala:1159)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:933)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:933)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:144)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:129)
at org.apache.carbondata.spark.rdd.CarbonDataFrameRDD.<init>(CarbonDataFrameRDD.scala:23)
at org.apache.spark.sql.CarbonContext.sql(CarbonContext.scala:130)
at org.apache.carbondata.examples.CarbonExample$.main(CarbonExample.scala:42)
at org.apache.carbondata.examples.CarbonExample.main(CarbonExample.scala)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)