LuciferYang commented on code in PR #41169:
URL: https://github.com/apache/spark/pull/41169#discussion_r1194845716
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala:
##########
@@ -2142,22 +2142,118 @@ case class OctetLength(child: Expression)
""",
since = "1.5.0",
group = "string_funcs")
-case class Levenshtein(left: Expression, right: Expression) extends
BinaryExpression
- with ImplicitCastInputTypes with NullIntolerant {
+case class Levenshtein(
+ left: Expression,
+ right: Expression,
+ threshold: Option[Expression] = None)
+ extends Expression
+ with ImplicitCastInputTypes
+ with NullIntolerant{
- override def inputTypes: Seq[AbstractDataType] = Seq(StringType, StringType)
+ def this(left: Expression, right: Expression, threshold: Expression) =
+ this(left, right, Option(threshold))
+
+ def this(left: Expression, right: Expression) = this(left, right, None)
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ if (children.length > 3 || children.length < 2) {
+ throw QueryCompilationErrors.wrongNumArgsError(
+ toSQLId(prettyName), Seq(2, 3), children.length)
+ } else {
+ super.checkInputDataTypes()
+ }
+ }
+
+ override def inputTypes: Seq[AbstractDataType] = if (threshold.isDefined) {
Review Comment:
case match maybe more robust？Otherwise, if `threshold` is `null`, NPE will
be thrown here?
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala:
##########
@@ -2142,22 +2142,118 @@ case class OctetLength(child: Expression)
""",
since = "1.5.0",
group = "string_funcs")
-case class Levenshtein(left: Expression, right: Expression) extends
BinaryExpression
- with ImplicitCastInputTypes with NullIntolerant {
+case class Levenshtein(
+ left: Expression,
+ right: Expression,
+ threshold: Option[Expression] = None)
+ extends Expression
+ with ImplicitCastInputTypes
+ with NullIntolerant{
- override def inputTypes: Seq[AbstractDataType] = Seq(StringType, StringType)
+ def this(left: Expression, right: Expression, threshold: Expression) =
+ this(left, right, Option(threshold))
+
+ def this(left: Expression, right: Expression) = this(left, right, None)
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ if (children.length > 3 || children.length < 2) {
+ throw QueryCompilationErrors.wrongNumArgsError(
+ toSQLId(prettyName), Seq(2, 3), children.length)
+ } else {
+ super.checkInputDataTypes()
+ }
+ }
+
+ override def inputTypes: Seq[AbstractDataType] = if (threshold.isDefined) {
+ Seq(StringType, StringType, IntegerType)
+ } else {
+ Seq(StringType, StringType)
+ }
+
+ override def children: Seq[Expression] = if (threshold.isDefined) {
Review Comment:
ditto
--
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]
