gengliangwang commented on code in PR #51505:
URL: https://github.com/apache/spark/pull/51505#discussion_r2417592705
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproxTopKAggregates.scala:
##########
@@ -435,3 +507,203 @@ case class ApproxTopKAccumulate(
override def prettyName: String =
getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("approx_top_k_accumulate")
}
+
+class CombineInternal[T](
+ sketch: ItemsSketch[T],
+ var itemDataType: DataType,
+ var maxItemsTracked: Int) {
+ def getSketch: ItemsSketch[T] = sketch
+
+ def getItemDataType: DataType = itemDataType
+
+ def setItemDataType(dataType: DataType): Unit = {
+ if (this.itemDataType == null) {
+ this.itemDataType = dataType
+ } else if (this.itemDataType != dataType) {
+ throw
QueryExecutionErrors.approxTopKSketchTypeNotMatch(this.itemDataType, dataType)
+ }
+ }
+
+ def getMaxItemsTracked: Int = maxItemsTracked
+
+ def setMaxItemsTracked(maxItemsTracked: Int): Unit = this.maxItemsTracked =
maxItemsTracked
+}
+
+/**
+ * An aggregate function that combines multiple sketches into a single sketch.
+ *
+ * @param state the expression containing the sketches to
combine
+ * @param maxItemsTracked the maximum number of items to track in the
sketch
+ * @param mutableAggBufferOffset the offset for mutable aggregation buffer
+ * @param inputAggBufferOffset the offset for input aggregation buffer
+ */
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = """
+ _FUNC_(state, maxItemsTracked) - Combines multiple sketches into a single
sketch.
+ `maxItemsTracked` An optional positive INTEGER literal with upper limit
of 1000000. If maxItemsTracked is not specified, it defaults to 10000.
Review Comment:
let's add comment about the syntax when maxItemsTracked is not provided
--
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]
