Github user mgaido91 commented on a diff in the pull request:
https://github.com/apache/spark/pull/19811#discussion_r156919894
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala
---
@@ -189,15 +255,37 @@ class CodegenContext {
def declareMutableStates(): String = {
// It's possible that we add same mutable state twice, e.g. the
`mergeExpressions` in
// `TypedAggregateExpression`, we should call `distinct` here to
remove the duplicated ones.
- mutableStates.distinct.map { case (javaType, variableName, _) =>
+ val inlinedStates = mutableStates.distinct.map { case (javaType,
variableName) =>
s"private $javaType $variableName;"
- }.mkString("\n")
+ }
+
+ val arrayStates = mutableStateArrayMap.flatMap { case (javaType,
mutableStateArrays) =>
+ val numArrays = mutableStateArrays.arrayNames.size
+ mutableStateArrays.arrayNames.zipWithIndex.map { case (arrayName,
index) =>
+ val length = if (index + 1 == numArrays) {
+ mutableStateArrays.getCurrentIndex
+ } else {
+ CodeGenerator.MUTABLESTATEARRAY_SIZE_LIMIT
--- End diff --
why can't we always use `mutableStateArrays.getCurrentIndex`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
