beliefer commented on a change in pull request #27507:
URL: https://github.com/apache/spark/pull/27507#discussion_r463047788
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala
##########
@@ -421,20 +423,59 @@ object RegExpExtract {
}
}
+abstract class RegExpExtractBase
+ extends TernaryExpression with ImplicitCastInputTypes with NullIntolerant {
+ def subject: Expression
+ def regexp: Expression
+ def idx: Expression
+
+ // last regex in string, we will update the pattern iff regexp value changed.
+ @transient private var lastRegex: UTF8String = _
+ // last regex pattern, we cache it for performance concern
+ @transient private var pattern: Pattern = _
+
+ override def inputTypes: Seq[AbstractDataType] = Seq(StringType, StringType,
IntegerType)
+ override def children: Seq[Expression] = subject :: regexp :: idx :: Nil
+
+ protected def getLastMatcher(s: Any, p: Any): Matcher = {
+ if (!p.equals(lastRegex)) {
Review comment:
OK
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
