cloud-fan commented on a change in pull request #25464: [SPARK-28746][SQL] Add
partitionby hint for sql queries
URL: https://github.com/apache/spark/pull/25464#discussion_r349543286
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveHints.scala
##########
@@ -137,31 +137,101 @@ object ResolveHints {
}
/**
- * COALESCE Hint accepts name "COALESCE" and "REPARTITION".
- * Its parameter includes a partition number.
+ * COALESCE Hint accepts names "COALESCE", "REPARTITION", and
"REPARTITION_BY_RANGE".
*/
- object ResolveCoalesceHints extends Rule[LogicalPlan] {
- private val COALESCE_HINT_NAMES = Set("COALESCE", "REPARTITION")
+ class ResolveCoalesceHints(conf: SQLConf) extends Rule[LogicalPlan] {
+
+ /**
+ * This function handles hints for "COALESCE" and "REPARTITION".
+ * The "COALESCE" hint only has a partition number as a parameter. The
"REPARTITION" hint
+ * has a partition number, columns, or both of them as parameters.
+ */
+ private def createRepartition(
+ shuffle: Boolean, hint: UnresolvedHint): LogicalPlan = {
+ val hintName = hint.name.toUpperCase(Locale.ROOT)
+
+ def createRepartitionByExpression(
+ numPartitions: Int, partitionExprs: Seq[Any]):
RepartitionByExpression = {
+ val sortOrders = partitionExprs.filter(_.isInstanceOf[SortOrder])
+ if (sortOrders.nonEmpty) throw new IllegalArgumentException(
+ s"""Invalid partitionExprs specified: $sortOrders
+ |For range partitioning use REPARTITION_BY_RANGE instead.
+ """.stripMargin)
+ val invalidParams =
partitionExprs.filter(!_.isInstanceOf[UnresolvedAttribute])
+ if (invalidParams.nonEmpty) {
+ throw new AnalysisException(s"$hintName Hint parameter should
include columns, but " +
+ s"${invalidParams.mkString(", ")} found")
+ }
+ RepartitionByExpression(
+ partitionExprs.map(_.asInstanceOf[Expression]), hint.child,
numPartitions)
+ }
- def apply(plan: LogicalPlan): LogicalPlan = plan.resolveOperators {
- case h: UnresolvedHint if
COALESCE_HINT_NAMES.contains(h.name.toUpperCase(Locale.ROOT)) =>
- val hintName = h.name.toUpperCase(Locale.ROOT)
- val shuffle = hintName match {
- case "REPARTITION" => true
- case "COALESCE" => false
+ hint.parameters match {
+ case Seq(IntegerLiteral(numPartitions)) =>
+ Repartition(numPartitions, shuffle, hint.child)
+ case Seq(numPartitions: Int) =>
+ Repartition(numPartitions, shuffle, hint.child)
+ // The "COALESCE" hint (shuffle = false) must have a partition number
only
+ case _ if !shuffle =>
+ throw new AnalysisException(s"$hintName Hint expects a partition
number as a parameter")
+
+ case param @ Seq(IntegerLiteral(numPartitions), _*) if shuffle =>
+ createRepartitionByExpression(numPartitions, param.tail)
+ case param @ Seq(numPartitions: Int, _*) if shuffle =>
+ createRepartitionByExpression(numPartitions, param.tail)
+ case param @ Seq(_*) if shuffle =>
+ createRepartitionByExpression(conf.numShufflePartitions, param)
+ }
+ }
+
+ /**
+ * This function handles hints for "REPARTITION_BY_RANGE".
+ * The "REPARTITION_BY_RANGE" hint must have column names and a partition
number is optional.
+ */
+ private def createRepartitionByRange(hint: UnresolvedHint):
RepartitionByExpression = {
+ val hintName = hint.name.toUpperCase(Locale.ROOT)
+
+ def createRepartitionByExpression(
+ numPartitions: Int, partitionExprs: Seq[Any]):
RepartitionByExpression = {
+ val invalidParams =
partitionExprs.filter(!_.isInstanceOf[UnresolvedAttribute])
+ if (invalidParams.nonEmpty) {
+ throw new AnalysisException(s"$hintName Hint parameter should
include columns, but " +
+ s"${invalidParams.mkString(", ")} found")
}
- val numPartitions = h.parameters match {
- case Seq(IntegerLiteral(numPartitions)) =>
- numPartitions
- case Seq(numPartitions: Int) =>
- numPartitions
- case _ =>
- throw new AnalysisException(s"$hintName Hint expects a partition
number as parameter")
+ val sortOrder = partitionExprs.map {
+ case expr: SortOrder => expr
+ case expr: Expression => SortOrder(expr, Ascending)
+ }
+ RepartitionByExpression(sortOrder, hint.child, numPartitions)
+ }
+
+ hint.parameters match {
+ case param @ Seq(IntegerLiteral(numPartitions), _*) =>
+ createRepartitionByExpression(numPartitions, param.tail)
+ case param @ Seq(numPartitions: Int, _*) =>
+ createRepartitionByExpression(numPartitions, param.tail)
+ case param @ Seq(_*) =>
+ createRepartitionByExpression(conf.numShufflePartitions, param)
+ }
+ }
+
+ def apply(plan: LogicalPlan): LogicalPlan = plan.resolveOperators {
+ case hint @ UnresolvedHint(hintName, _, _) =>
hintName.toUpperCase(Locale.ROOT) match {
+ case "REPARTITION" =>
+ createRepartition(shuffle = true, hint)
+ case "COALESCE" =>
+ createRepartition(shuffle = false, hint)
+ case "REPARTITION_BY_RANGE" =>
+ createRepartitionByRange(hint)
+ case _ => plan
Review comment:
shouldn't we return `hint` here? This will cause stack overflow once the
hint is not the root node.
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
