uros-db commented on code in PR #45856:
URL: https://github.com/apache/spark/pull/45856#discussion_r1550949300
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala:
##########
@@ -543,25 +543,52 @@ case class RLike(left: Expression, right: Expression)
extends StringRegexExpress
case class StringSplit(str: Expression, regex: Expression, limit: Expression)
extends TernaryExpression with ImplicitCastInputTypes with NullIntolerant {
- override def dataType: DataType = ArrayType(StringType, containsNull = false)
- override def inputTypes: Seq[DataType] = Seq(StringType, StringType,
IntegerType)
+ override def dataType: DataType = ArrayType(str.dataType, containsNull =
false)
+ override def inputTypes: Seq[AbstractDataType] =
+ Seq(StringTypeAnyCollation, StringTypeAnyCollation, IntegerType)
+
+ override def checkInputDataTypes(): TypeCheckResult = str.dataType match {
+ case s: StringType =>
+ if (s.supportsBinaryEquality || s.isUTF8BinaryLcaseCollation) {
+ super.checkInputDataTypes()
+ } else {
+ TypeCheckFailure("Unsupported collation: " +
+ CollationFactory.fetchCollation(s.collationId).collationName)
+ }
+ case _ => super.checkInputDataTypes()
+ }
+
override def first: Expression = str
override def second: Expression = regex
override def third: Expression = limit
+ private def collationId = str.dataType.asInstanceOf[StringType].collationId
+ private def binarySplit =
CollationFactory.fetchCollation(collationId).supportsBinaryEquality
+
def this(exp: Expression, regex: Expression) = this(exp, regex, Literal(-1))
override def nullSafeEval(string: Any, regex: Any, limit: Any): Any = {
- val strings = string.asInstanceOf[UTF8String].split(
- regex.asInstanceOf[UTF8String], limit.asInstanceOf[Int])
+ val strings = if (binarySplit) {
+ string.asInstanceOf[UTF8String].split(
+ regex.asInstanceOf[UTF8String], limit.asInstanceOf[Int])
+ } else {
+ string.asInstanceOf[UTF8String].splitCaseInsensitive(
+ regex.asInstanceOf[UTF8String], limit.asInstanceOf[Int])
Review Comment:
I don't think branching here is a good idea, consider re-writing UTF8String
methods to accommodate this
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
