rednaxelafx commented on a change in pull request #28463:
URL: https://github.com/apache/spark/pull/28463#discussion_r426999033
##########
File path: core/src/main/scala/org/apache/spark/util/ClosureCleaner.scala
##########
@@ -414,6 +434,312 @@ private[spark] object ClosureCleaner extends Logging {
}
}
+private[spark] object IndylambdaScalaClosures extends Logging {
+ // internal name of java.lang.invoke.LambdaMetafactory
+ val LambdaMetafactoryClassName = "java/lang/invoke/LambdaMetafactory"
+ // the method that Scala indylambda use for bootstrap method
+ val LambdaMetafactoryMethodName = "altMetafactory"
+ val LambdaMetafactoryMethodDesc = "(Ljava/lang/invoke/MethodHandles$Lookup;"
+
+ "Ljava/lang/String;Ljava/lang/invoke/MethodType;[Ljava/lang/Object;)" +
+ "Ljava/lang/invoke/CallSite;"
+
+ /**
+ * Check if the given reference is a indylambda style Scala closure.
+ * If so (e.g. for Scala 2.12+ closures), return a non-empty serialization
proxy
+ * (SerializedLambda) of the closure;
+ * otherwise (e.g. for Scala 2.11 closures) return None.
+ *
+ * @param maybeClosure the closure to check.
+ */
+ def getSerializationProxy(maybeClosure: AnyRef): Option[SerializedLambda] = {
+ def isClosureCandidate(cls: Class[_]): Boolean = {
+ // TODO: maybe lift this restriction to support other functional
interfaces in the future
+ val implementedInterfaces = ClassUtils.getAllInterfaces(cls).asScala
+ implementedInterfaces.exists(_.getName.startsWith("scala.Function"))
+ }
+
+ maybeClosure.getClass match {
+ // shortcut the fast check:
+ // 1. indylambda closure classes are generated by Java's
LambdaMetafactory, and they're
+ // always synthetic.
+ // 2. We only care about Serializable closures, so let's check that as
well
+ case c if !c.isSynthetic || !maybeClosure.isInstanceOf[Serializable] =>
None
+
+ case c if isClosureCandidate(c) =>
+ try {
+ Option(inspect(maybeClosure)).filter(isIndylambdaScalaClosure)
+ } catch {
+ case e: Exception =>
+ logDebug("The given reference is not an indylambda Scala
closure.", e)
+ None
+ }
+
+ case _ => None
+ }
+ }
+
+ def isIndylambdaScalaClosure(lambdaProxy: SerializedLambda): Boolean = {
+ lambdaProxy.getImplMethodKind == MethodHandleInfo.REF_invokeStatic &&
+ lambdaProxy.getImplMethodName.contains("$anonfun$")
+ }
+
+ def inspect(closure: AnyRef): SerializedLambda = {
+ val writeReplace = closure.getClass.getDeclaredMethod("writeReplace")
+ writeReplace.setAccessible(true)
+ writeReplace.invoke(closure).asInstanceOf[SerializedLambda]
+ }
+
+ /**
+ * Check if the handle represents the LambdaMetafactory that indylambda
Scala closures
+ * use for creating the lambda class and getting a closure instance.
+ */
+ def isLambdaMetafactory(bsmHandle: Handle): Boolean = {
+ bsmHandle.getOwner == LambdaMetafactoryClassName &&
+ bsmHandle.getName == LambdaMetafactoryMethodName &&
+ bsmHandle.getDesc == LambdaMetafactoryMethodDesc
+ }
+
+ /**
+ * Check if the handle represents a target method that is:
+ * - a STATIC method that implements a Scala lambda body in the indylambda
style
+ * - captures the enclosing `this`, i.e. the first argument is a reference
to the same type as
+ * the owning class.
+ * Returns true if both criteria above are met.
+ */
+ def isLambdaBodyCapturingOuter(handle: Handle, ownerInternalName: String):
Boolean = {
+ handle.getTag == H_INVOKESTATIC &&
+ handle.getName.contains("$anonfun$") &&
+ handle.getOwner == ownerInternalName &&
+ handle.getDesc.startsWith(s"(L$ownerInternalName;")
+ }
+
+ /**
+ * Check if the callee of a call site is a inner class constructor.
+ * - A constructor has to be invoked via INVOKESPECIAL
+ * - A constructor's internal name is "<init>" and the return type is
"V" (void)
+ * - An inner class' first argument in the signature has to be a reference
to the
+ * enclosing "this", aka `$outer` in Scala.
+ */
+ def isInnerClassCtorCapturingOuter(
+ op: Int, owner: String, name: String, desc: String, callerInternalName:
String): Boolean = {
Review comment:
Good point! Thanks for the suggestion, I'll remove the unused parameter
when I gather enough changes for a follow-up change.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
