Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/22630#discussion_r223025094
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala ---
@@ -66,27 +75,22 @@ trait BaseLimitExec extends UnaryExecNode with
CodegenSupport {
// to the parent operator.
override def usedInputs: AttributeSet = AttributeSet.empty
+ private lazy val countTerm = BaseLimitExec.newLimitCountTerm()
+
+ override lazy val limitNotReachedChecks: Seq[String] = {
+ s"$countTerm < $limit" +: super.limitNotReachedChecks
+ }
+
protected override def doProduce(ctx: CodegenContext): String = {
child.asInstanceOf[CodegenSupport].produce(ctx, this)
}
override def doConsume(ctx: CodegenContext, input: Seq[ExprCode], row:
ExprCode): String = {
- val stopEarly =
- ctx.addMutableState(CodeGenerator.JAVA_BOOLEAN, "stopEarly") // init
as stopEarly = false
-
- ctx.addNewFunction("stopEarly", s"""
- @Override
- protected boolean stopEarly() {
- return $stopEarly;
- }
- """, inlineToOuterClass = true)
- val countTerm = ctx.addMutableState(CodeGenerator.JAVA_INT, "count")
// init as count = 0
+ ctx.addMutableState(CodeGenerator.JAVA_INT, countTerm, forceInline =
true, useFreshName = false)
--- End diff --
because the counter variable name is decided before we obtain the
`CodegenContext`. If we don't inline here, we need a way to notify the upstream
operators about the counter name, which is hard to do.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
