dbatomic commented on code in PR #45643:
URL: https://github.com/apache/spark/pull/45643#discussion_r1537454075
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala:
##########
@@ -1377,17 +1394,34 @@ case class StringInstr(str: Expression, substr:
Expression)
override def left: Expression = str
override def right: Expression = substr
override def dataType: DataType = IntegerType
- override def inputTypes: Seq[DataType] = Seq(StringType, StringType)
+ override def inputTypes: Seq[AbstractDataType] =
+ Seq(StringTypeAnyCollation, StringTypeAnyCollation)
override def nullSafeEval(string: Any, sub: Any): Any = {
- string.asInstanceOf[UTF8String].indexOf(sub.asInstanceOf[UTF8String], 0) +
1
+ val collationId = left.dataType.asInstanceOf[StringType].collationId
+ string.asInstanceOf[UTF8String].indexOf(sub.asInstanceOf[UTF8String], 0,
collationId) + 1
+ }
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ val defaultCheck = super.checkInputDataTypes()
+ if (defaultCheck.isFailure) {
+ return defaultCheck
+ }
+
+ val collationId = left.dataType.asInstanceOf[StringType].collationId
+ CollationTypeConstraints.checkCollationCompatibility(collationId,
children.map(_.dataType))
Review Comment:
Btw, let's wait for implicit casting before merging this PR. Implicit
casting should change things both in constraints space and also how we write
tests.
--
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]
