Github user mgaido91 commented on a diff in the pull request:
https://github.com/apache/spark/pull/19811#discussion_r156348687
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala
---
@@ -203,18 +267,35 @@ 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 $variableName;"
- }.mkString("\n")
+ }
+
+ val arrayStates = mutableStateArrayIdx.keys.map { case (javaType,
arrayName) =>
+ val length = mutableStateArrayIdx((javaType, arrayName)) + 1
+ if (javaType.matches("^.*\\[\\]$")) {
+ // initializer had an one-dimensional array variable
+ val baseType = javaType.substring(0, javaType.length - 2)
+ s"private $javaType[] $arrayName = new $baseType[$length][];"
+ } else {
+ // initializer had a scalar variable
+ s"private $javaType[] $arrayName = new $javaType[$length];"
+ }
+ }
+
+ (inlinedStates ++ arrayStates).mkString("\n")
}
def initMutableStates(): 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.
val initCodes = mutableStates.distinct.map(_._3 + "\n")
+ // statements for array element initialization
+ val arrayInitCodes = mutableStateArrayInitCodes.distinct.map(_ + "\n")
--- End diff --
as pointed out by @maropu above, here we can get rid of `.map(_ + "\n")`,
it will be added by `splitExpressions`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
