LuciferYang commented on code in PR #41169:
URL: https://github.com/apache/spark/pull/41169#discussion_r1194847178
##########
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) {
+ Seq(left, right, threshold.get)
+ } else {
+ Seq(left, right)
+ }
override def dataType: DataType = IntegerType
- protected override def nullSafeEval(leftValue: Any, rightValue: Any): Any =
-
leftValue.asInstanceOf[UTF8String].levenshteinDistance(rightValue.asInstanceOf[UTF8String])
- override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
- nullSafeCodeGen(ctx, ev, (left, right) =>
- s"${ev.value} = $left.levenshteinDistance($right);")
+ override protected def withNewChildrenInternal(newChildren:
IndexedSeq[Expression]): 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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
