yaooqinn commented on code in PR #55422:
URL: https://github.com/apache/spark/pull/55422#discussion_r3192759338
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowEvaluatorFactoryBase.scala:
##########
@@ -295,4 +342,59 @@ trait WindowEvaluatorFactoryBase {
}
}
+ /**
+ * Segment-tree path eligibility. The tree relies on
+ * `DeclarativeAggregate.mergeExpressions`, which
[[AggregateWindowFunction]]s
+ * (NthValue, NTile, Rank, RowNumber, NullIndex) refuse via
+ * `mergeUnsupportedByWindowFunctionError`: they extend DeclarativeAggregate
+ * but are NOT merge-capable. Normal aggregate window expressions reach this
+ * code as the inner DeclarativeAggregate unwrapped from
+ * [[AggregateExpression]] (see `windowFrameExpressionFactoryPairs.collect`).
+ *
+ * DISTINCT aggregate window expressions are already rejected earlier in
+ * analysis by `WindowResolution.checkWindowFunction`
+ * (error class `DISTINCT_WINDOW_FUNCTION_UNSUPPORTED`), so no explicit
+ * `isDistinct` gate is needed here.
+ */
+ private def eligibleForSegTree(
+ functions: Array[Expression],
+ filters: Array[Option[Expression]],
+ frameType: FrameType): Boolean = {
+ // RANGE accepted only for single-column order specs. Multi-column RANGE
+ // with non-zero offset is already rejected by `createBoundOrdering`, so
+ // gating here on `orderSpec.size == 1` matches the Sliding-path invariant.
+ val frameTypeOk = frameType match {
+ case RowFrame => true
+ case RangeFrame => orderSpec.size == 1
+ }
+ SQLConf.get.windowSegmentTreeEnabled &&
Review Comment:
Addressed in `eb31df11e5f` (thread-conf-param). Thank you for the advice!
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/window/AggregateProcessor.scala:
##########
@@ -181,7 +181,26 @@ private[window] final class AggregateProcessor(
}
/** Evaluate buffer. */
- def evaluate(target: InternalRow): Unit = {
- evaluateProjection.target(target)(buffer)
+ def evaluate(target: InternalRow): Unit = evaluate(buffer, target)
+
+ /**
+ * Evaluate using an arbitrary `source` buffer (e.g. a segment-tree query
+ * result) instead of the internal one.
+ *
+ * '''Contract''': `source` must share this processor's internal
+ * `aggBufferAttributes` layout -- same field count, same dataTypes, in the
+ * same order. The segment-tree path enforces this upstream in
+ * `WindowEvaluatorFactoryBase.eligibleForSegTree` (rejects
+ * `SizeBasedWindowFunction`; the same `functions:
Array[DeclarativeAggregate]`
Review Comment:
Addressed in `eb31df11e5f` (allowlist-comment). Thank you for the advice!
--
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]
