Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/11208#discussion_r56779046
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
---
@@ -369,28 +370,83 @@ class Analyzer(
}
/**
- * Replaces [[UnresolvedAttribute]]s with concrete
[[AttributeReference]]s from
- * a logical plan node's children.
+ * Expand [[UnresolvedStar]] or [[ResolvedStar]] to the matching
attributes in child's output.
*/
- object ResolveReferences extends Rule[LogicalPlan] {
+ object ResolveStar extends Rule[LogicalPlan] {
+
+ def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
+ case p: LogicalPlan if !p.childrenResolved => p
+
+ // If the projection list contains Stars, expand it.
+ case p: Project if containsStar(p.projectList) =>
+ val expanded = p.projectList.flatMap {
+ case s: Star => s.expand(p.child, resolver)
+ case ua @ UnresolvedAlias(_: UnresolvedFunction | _: CreateArray
| _: CreateStruct, _) =>
+ UnresolvedAlias(child = expandStarExpression(ua.child,
p.child)) :: Nil
+ case a @ Alias(_: UnresolvedFunction | _: CreateArray | _:
CreateStruct, _) =>
+ Alias(child = expandStarExpression(a.child, p.child), a.name)(
+ isGenerated = a.isGenerated) :: Nil
+ case o => o :: Nil
+ }
+ Project(projectList = expanded, p.child)
+ // If the aggregate function argument contains Stars, expand it.
+ case a: Aggregate if containsStar(a.aggregateExpressions) =>
+ val expanded = a.aggregateExpressions.flatMap {
+ case s: Star => s.expand(a.child, resolver)
+ case o if containsStar(o :: Nil) => expandStarExpression(o,
a.child) :: Nil
+ case o => o :: Nil
+ }.map(_.asInstanceOf[NamedExpression])
+ a.copy(aggregateExpressions = expanded)
+ // If the script transformation input contains Stars, expand it.
+ case t: ScriptTransformation if containsStar(t.input) =>
+ t.copy(
+ input = t.input.flatMap {
+ case s: Star => s.expand(t.child, resolver)
+ case o => o :: Nil
+ }
+ )
+ case g: Generate if containsStar(g.generator.children) =>
+ failAnalysis("Invalid usage of '*' in explode/json_tuple/UDTF")
+ }
+
+ /**
+ * Returns true if `exprs` contains a [[Star]].
+ */
+ def containsStar(exprs: Seq[Expression]): Boolean =
+ exprs.exists(_.collect { case _: Star => true }.nonEmpty)
+
/**
- * Foreach expression, expands the matching attribute.*'s in `child`'s
input for the subtree
- * rooted at each expression.
+ * Expands the matching attribute.*'s in `child`'s output.
*/
- def expandStarExpressions(exprs: Seq[Expression], child: LogicalPlan):
Seq[Expression] = {
- exprs.flatMap {
- case s: Star => s.expand(child, resolver)
- case e =>
- e.transformDown {
- case f1: UnresolvedFunction if containsStar(f1.children) =>
- f1.copy(children = f1.children.flatMap {
- case s: Star => s.expand(child, resolver)
- case o => o :: Nil
- })
- } :: Nil
+ def expandStarExpression(expr: Expression, child: LogicalPlan):
Expression = {
+ expr.transformUp {
+ case f1: UnresolvedFunction if containsStar(f1.children) =>
+ f1.copy(children = f1.children.flatMap {
+ case s: Star => s.expand(child, resolver)
+ case o => o :: Nil
+ })
+ case c: CreateStruct if containsStar(c.children) =>
+ c.copy(children = c.children.flatMap {
+ case s: Star => s.expand(child, resolver)
+ case o => o :: Nil
+ })
+ case c: CreateArray if containsStar(c.children) =>
+ c.copy(children = c.children.flatMap {
+ case s: Star => s.expand(child, resolver)
+ case o => o :: Nil
+ })
+ // count(*) has been replaced by count(1)
+ case o if containsStar(o.children) =>
--- End diff --
We can have a method:
```
private def mayContainsStar(expr: Expression): Boolean =
expr.isInstnaceOf[UnresolvedFunction] || expr.isInstnaceOf[CreateStruct]...
```
then we can simplify this to:
```
expr.transformUp {
case e if mayContainsStar(e) =>
e.copy(children = ...)
}
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
