[SPARK-21164][SQL] Remove isTableSample from Sample and isGenerated from Alias and AttributeReference

## What changes were proposed in this pull request?
`isTableSample` and `isGenerated ` were introduced for SQL Generation respectively by #11148 and #11050

Since SQL Generation is removed, we do not need to keep `isTableSample`.

## How was this patch tested?
The existing test cases

Author: Xiao Li <[email protected]>

Closes #18379 from gatorsmile/CleanSample.

Author: gatorsmile

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala

@@ -874,7 +874,7 @@ class Analyzer(
 
     def newAliases(expressions: Seq[NamedExpression]): Seq[NamedExpression] = {
       expressions.map {
-        case a: Alias => Alias(a.child, a.name)(isGenerated = a.isGenerated)
+        case a: Alias => Alias(a.child, a.name)()
         case other => other
       }
     }
@@ -1368,7 +1368,7 @@ class Analyzer(
           val aggregatedCondition =
             Aggregate(
               grouping,
-              Alias(havingCondition, "havingCondition")(isGenerated = true) :: Nil,
+              Alias(havingCondition, "havingCondition")() :: Nil,
               child)
           val resolvedOperator = execute(aggregatedCondition)
           def resolvedAggregateFilter =
@@ -1424,7 +1424,7 @@ class Analyzer(
         try {
           val unresolvedSortOrders = sortOrder.filter(s => !s.resolved || containsAggregate(s))
           val aliasedOrdering =
-            unresolvedSortOrders.map(o => Alias(o.child, "aggOrder")(isGenerated = true))
+            unresolvedSortOrders.map(o => Alias(o.child, "aggOrder")())
           val aggregatedOrdering = aggregate.copy(aggregateExpressions = aliasedOrdering)
           val resolvedAggregate: Aggregate = execute(aggregatedOrdering).asInstanceOf[Aggregate]
           val resolvedAliasedOrdering: Seq[Alias] =
@@ -1935,7 +1935,7 @@ class Analyzer(
         leafNondeterministic.distinct.map { e =>
           val ne = e match {
             case n: NamedExpression => n
-            case _ => Alias(e, "_nondeterministic")(isGenerated = true)
+            case _ => Alias(e, "_nondeterministic")()
           }
           e -> ne
         }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala

@@ -81,9 +81,6 @@ trait NamedExpression extends Expression {
   /** Returns the metadata when an expression is a reference to another expression with metadata. */
   def metadata: Metadata = Metadata.empty
 
-  /** Returns true if the expression is generated by Catalyst */
-  def isGenerated: java.lang.Boolean = false
-
   /** Returns a copy of this expression with a new `exprId`. */
   def newInstance(): NamedExpression
 
@@ -128,13 +125,11 @@ abstract class Attribute extends LeafExpression with NamedExpression with NullIn
  *                   qualified way. Consider the examples tableName.name, subQueryAlias.name.
  *                   tableName and subQueryAlias are possible qualifiers.
  * @param explicitMetadata Explicit metadata associated with this alias that overwrites child's.
- * @param isGenerated A flag to indicate if this alias is generated by Catalyst
  */
 case class Alias(child: Expression, name: String)(
     val exprId: ExprId = NamedExpression.newExprId,
     val qualifier: Option[String] = None,
-    val explicitMetadata: Option[Metadata] = None,
-    override val isGenerated: java.lang.Boolean = false)
+    val explicitMetadata: Option[Metadata] = None)
   extends UnaryExpression with NamedExpression {
 
   // Alias(Generator, xx) need to be transformed into Generate(generator, ...)
@@ -159,13 +154,11 @@ case class Alias(child: Expression, name: String)(
   }
 
   def newInstance(): NamedExpression =
-    Alias(child, name)(
-      qualifier = qualifier, explicitMetadata = explicitMetadata, isGenerated = isGenerated)
+    Alias(child, name)(qualifier = qualifier, explicitMetadata = explicitMetadata)
 
   override def toAttribute: Attribute = {
     if (resolved) {
-      AttributeReference(name, child.dataType, child.nullable, metadata)(
-        exprId, qualifier, isGenerated)
+      AttributeReference(name, child.dataType, child.nullable, metadata)(exprId, qualifier)
     } else {
       UnresolvedAttribute(name)
     }
@@ -174,7 +167,7 @@ case class Alias(child: Expression, name: String)(
   override def toString: String = s"$child AS $name#${exprId.id}$typeSuffix"
 
   override protected final def otherCopyArgs: Seq[AnyRef] = {
-    exprId :: qualifier :: explicitMetadata :: isGenerated :: Nil
+    exprId :: qualifier :: explicitMetadata :: Nil
   }
 
   override def hashCode(): Int = {
@@ -207,16 +200,14 @@ case class Alias(child: Expression, name: String)(
  * @param qualifier An optional string that can be used to referred to this attribute in a fully
  *                  qualified way. Consider the examples tableName.name, subQueryAlias.name.
  *                  tableName and subQueryAlias are possible qualifiers.
- * @param isGenerated A flag to indicate if this reference is generated by Catalyst
  */
 case class AttributeReference(
     name: String,
     dataType: DataType,
     nullable: Boolean = true,
     override val metadata: Metadata = Metadata.empty)(
     val exprId: ExprId = NamedExpression.newExprId,
-    val qualifier: Option[String] = None,
-    override val isGenerated: java.lang.Boolean = false)
+    val qualifier: Option[String] = None)
   extends Attribute with Unevaluable {
 
   /**
@@ -253,8 +244,7 @@ case class AttributeReference(
   }
 
   override def newInstance(): AttributeReference =
-    AttributeReference(name, dataType, nullable, metadata)(
-      qualifier = qualifier, isGenerated = isGenerated)
+    AttributeReference(name, dataType, nullable, metadata)(qualifier = qualifier)
 
   /**
    * Returns a copy of this [[AttributeReference]] with changed nullability.
@@ -263,15 +253,15 @@ case class AttributeReference(
     if (nullable == newNullability) {
       this
     } else {
-      AttributeReference(name, dataType, newNullability, metadata)(exprId, qualifier, isGenerated)
+      AttributeReference(name, dataType, newNullability, metadata)(exprId, qualifier)
     }
   }
 
   override def withName(newName: String): AttributeReference = {
     if (name == newName) {
       this
     } else {
-      AttributeReference(newName, dataType, nullable, metadata)(exprId, qualifier, isGenerated)
+      AttributeReference(newName, dataType, nullable, metadata)(exprId, qualifier)
     }
   }
 
@@ -282,24 +272,24 @@ case class AttributeReference(
     if (newQualifier == qualifier) {
       this
     } else {
-      AttributeReference(name, dataType, nullable, metadata)(exprId, newQualifier, isGenerated)
+      AttributeReference(name, dataType, nullable, metadata)(exprId, newQualifier)
     }
   }
 
   def withExprId(newExprId: ExprId): AttributeReference = {
     if (exprId == newExprId) {
       this
     } else {
-      AttributeReference(name, dataType, nullable, metadata)(newExprId, qualifier, isGenerated)
+      AttributeReference(name, dataType, nullable, metadata)(newExprId, qualifier)
     }
   }
 
   override def withMetadata(newMetadata: Metadata): Attribute = {
-    AttributeReference(name, dataType, nullable, newMetadata)(exprId, qualifier, isGenerated)
+    AttributeReference(name, dataType, nullable, newMetadata)(exprId, qualifier)
   }
 
   override protected final def otherCopyArgs: Seq[AnyRef] = {
-    exprId :: qualifier :: isGenerated :: Nil
+    exprId :: qualifier :: Nil
   }
 
   /** Used to signal the column used to calculate an eventTime watermark (e.g. a#1-T{delayMs}) */

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala

@@ -134,7 +134,7 @@ object RewriteDistinctAggregates extends Rule[LogicalPlan] {
     // Aggregation strategy can handle queries with a single distinct group.
     if (distinctAggGroups.size > 1) {
       // Create the attributes for the grouping id and the group by clause.
-      val gid = AttributeReference("gid", IntegerType, nullable = false)(isGenerated = true)
+      val gid = AttributeReference("gid", IntegerType, nullable = false)()
       val groupByMap = a.groupingExpressions.collect {
         case ne: NamedExpression => ne -> ne.toAttribute
         case e => e -> AttributeReference(e.sql, e.dataType, e.nullable)()

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala

@@ -627,7 +627,7 @@ class AstBuilder(conf: SQLConf) extends SqlBaseBaseVisitor[AnyRef] with Logging
       validate(fraction >= 0.0 - eps && fraction <= 1.0 + eps,
         s"Sampling fraction ($fraction) must be on interval [0, 1]",
         ctx)
-      Sample(0.0, fraction, withReplacement = false, (math.random * 1000).toInt, query)(true)
+      Sample(0.0, fraction, withReplacement = false, (math.random * 1000).toInt, query)
     }
 
     ctx.sampleType.getType match {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala

@@ -80,12 +80,12 @@ object PhysicalOperation extends PredicateHelper {
     expr.transform {
       case a @ Alias(ref: AttributeReference, name) =>
         aliases.get(ref)
-          .map(Alias(_, name)(a.exprId, a.qualifier, isGenerated = a.isGenerated))
+          .map(Alias(_, name)(a.exprId, a.qualifier))
           .getOrElse(a)
 
       case a: AttributeReference =>
         aliases.get(a)
-          .map(Alias(_, a.name)(a.exprId, a.qualifier, isGenerated = a.isGenerated)).getOrElse(a)
+          .map(Alias(_, a.name)(a.exprId, a.qualifier)).getOrElse(a)
     }
   }
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala

@@ -200,7 +200,7 @@ abstract class QueryPlan[PlanType <: QueryPlan[PlanType]] extends TreeNode[PlanT
         // normalize that for equality testing, by assigning expr id from 0 incrementally. The
         // alias name doesn't matter and should be erased.
         val normalizedChild = QueryPlan.normalizeExprId(a.child, allAttributes)
-        Alias(normalizedChild, "")(ExprId(id), a.qualifier, isGenerated = a.isGenerated)
+        Alias(normalizedChild, "")(ExprId(id), a.qualifier)
 
       case ar: AttributeReference if allAttributes.indexOf(ar.exprId) == -1 =>
         // Top level `AttributeReference` may also be used for output like `Alias`, we should

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala

@@ -221,7 +221,7 @@ abstract class LogicalPlan extends QueryPlan[LogicalPlan] with QueryPlanConstrai
       nameParts: Seq[String],
       resolver: Resolver,
       attribute: Attribute): Option[(Attribute, List[String])] = {
-    if (!attribute.isGenerated && resolver(attribute.name, nameParts.head)) {
+    if (resolver(attribute.name, nameParts.head)) {
       Option((attribute.withName(nameParts.head), nameParts.tail.toList))
     } else {
       None

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala

@@ -807,15 +807,13 @@ case class SubqueryAlias(
  * @param withReplacement Whether to sample with replacement.
  * @param seed the random seed
  * @param child the LogicalPlan
- * @param isTableSample Is created from TABLESAMPLE in the parser.
  */
 case class Sample(
     lowerBound: Double,
     upperBound: Double,
     withReplacement: Boolean,
     seed: Long,
-    child: LogicalPlan)(
-    val isTableSample: java.lang.Boolean = false) extends UnaryNode {
+    child: LogicalPlan) extends UnaryNode {
 
   val eps = RandomSampler.roundingEpsilon
   val fraction = upperBound - lowerBound
@@ -842,8 +840,6 @@ case class Sample(
     // Don't propagate column stats, because we don't know the distribution after a sample operation
     Statistics(sizeInBytes, sampledRowCount, hints = childStats.hints)
   }
-
-  override protected def otherCopyArgs: Seq[AnyRef] = isTableSample :: Nil
 }
 
 /**

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala

@@ -573,7 +573,7 @@ class AnalysisErrorSuite extends AnalysisTest {
     val plan5 = Filter(
       Exists(
         Sample(0.0, 0.5, false, 1L,
-          Filter(EqualTo(UnresolvedAttribute("a"), b), LocalRelation(b)))().select('b)
+          Filter(EqualTo(UnresolvedAttribute("a"), b), LocalRelation(b))).select('b)
       ),
       LocalRelation(a))
     assertAnalysisError(plan5,

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala

@@ -491,7 +491,7 @@ class UnsupportedOperationsSuite extends SparkFunSuite {
 
   // Other unary operations
   testUnaryOperatorInStreamingPlan(
-    "sample", Sample(0.1, 1, true, 1L, _)(), expectedMsg = "sampling")
+    "sample", Sample(0.1, 1, true, 1L, _), expectedMsg = "sampling")
   testUnaryOperatorInStreamingPlan(
     "window", Window(Nil, Nil, Nil, _), expectedMsg = "non-time-based windows")