Github user gvramana commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1032#discussion_r124548518
--- Diff:
integration/spark-common/src/main/scala/org/apache/carbondata/spark/util/CommonUtil.scala
---
@@ -288,6 +297,69 @@ object CommonUtil {
result
}
+ def validateForOverLappingRangeValues(desType: Option[String],
+ rangeInfoArray: Array[String]): Boolean = {
+ val rangeInfoValuesValid = desType match {
+ case Some("IntegerType") | Some("int") =>
+ val intRangeInfoArray = rangeInfoArray.map(_.toInt)
+ val sortedRangeInfoArray = intRangeInfoArray.sorted
+ intRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("StringType") | Some("string") =>
+ val sortedRangeInfoArray = rangeInfoArray.sorted
+ rangeInfoArray.sameElements(sortedRangeInfoArray)
+ case a if (desType.get.startsWith("varchar") ||
desType.get.startsWith("char")) =>
+ val sortedRangeInfoArray = rangeInfoArray.sorted
+ rangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("LongType") | Some("long") | Some("bigint") =>
+ val longRangeInfoArray = rangeInfoArray.map(_.toLong)
+ val sortedRangeInfoArray = longRangeInfoArray.sorted
+ longRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("FloatType") | Some("float") =>
+ val floatRangeInfoArray = rangeInfoArray.map(_.toFloat)
+ val sortedRangeInfoArray = floatRangeInfoArray.sorted
+ floatRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("DoubleType") | Some("double") =>
+ val doubleRangeInfoArray = rangeInfoArray.map(_.toDouble)
+ val sortedRangeInfoArray = doubleRangeInfoArray.sorted
+ doubleRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("ByteType") | Some("tinyint") =>
+ val byteRangeInfoArray = rangeInfoArray.map(_.toByte)
+ val sortedRangeInfoArray = byteRangeInfoArray.sorted
+ byteRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("ShortType") | Some("smallint") =>
+ val shortRangeInfoArray = rangeInfoArray.map(_.toShort)
+ val sortedRangeInfoArray = shortRangeInfoArray.sorted
+ shortRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("BooleanType") | Some("boolean") =>
+ true
+ case a if (desType.get.startsWith("DecimalType") ||
desType.get.startsWith("decimal")) =>
+ val decimalRangeInfoArray = rangeInfoArray.map(value =>
BigDecimal(value))
+ val sortedRangeInfoArray = decimalRangeInfoArray.sorted
+ decimalRangeInfoArray.sameElements(sortedRangeInfoArray)
+ case Some("DateType") | Some("date") =>
+ val dateRangeInfoArray = rangeInfoArray.map { value =>
--- End diff --
Dictionary generation can bring duplicate values. duplicate value check
required.
Same is the case with timesamp case also.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---