[SPARK-26168][SQL] Update the code comments in Expression and Aggregate

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

@@ -181,8 +181,9 @@ object TypeCoercion {
   }
 
   /**
-   * The method finds a common type for data types that differ only in nullable, containsNull
-   * and valueContainsNull flags. If the input types are too different, None is returned.
+   * The method finds a common type for data types that differ only in nullable flags, including
+   * `nullable`, `containsNull` of [[ArrayType]] and `valueContainsNull` of [[MapType]].
+   * If the input types are different besides nullable flags, None is returned.
    */
   def findCommonTypeDifferentOnlyInNullFlags(t1: DataType, t2: DataType): Option[DataType] = {
     if (t1 == t2) {

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

@@ -24,6 +24,7 @@ import org.apache.spark.sql.catalyst.analysis.{TypeCheckResult, TypeCoercion}
 import org.apache.spark.sql.catalyst.expressions.aggregate.DeclarativeAggregate
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.trees.TreeNode
 import org.apache.spark.sql.catalyst.util.truncatedString
 import org.apache.spark.sql.internal.SQLConf
@@ -40,12 +41,28 @@ import org.apache.spark.sql.types._
  * "name(arguments...)", the concrete implementation must be a case class whose constructor
  * arguments are all Expressions types. See [[Substring]] for an example.
  *
- * There are a few important traits:
+ * There are a few important traits or abstract classes:
  *
  * - [[Nondeterministic]]: an expression that is not deterministic.
+ * - [[Stateful]]: an expression that contains mutable state. For example, MonotonicallyIncreasingID
+ *                 and Rand. A stateful expression is always non-deterministic.
  * - [[Unevaluable]]: an expression that is not supposed to be evaluated.
  * - [[CodegenFallback]]: an expression that does not have code gen implemented and falls back to
  *                        interpreted mode.
+ * - [[NullIntolerant]]: an expression that is null intolerant (i.e. any null input will result in
+ *                       null output).
+ * - [[NonSQLExpression]]: a common base trait for the expressions that do not have SQL
+ *                         expressions like representation. For example, `ScalaUDF`, `ScalaUDAF`,
+ *                         and object `MapObjects` and `Invoke`.
+ * - [[UserDefinedExpression]]: a common base trait for user-defined functions, including
+ *                              UDF/UDAF/UDTF.
+ * - [[HigherOrderFunction]]: a common base trait for higher order functions that take one or more
+ *                            (lambda) functions and applies these to some objects. The function
+ *                            produces a number of variables which can be consumed by some lambda
+ *                            functions.
+ * - [[NamedExpression]]: An [[Expression]] that is named.
+ * - [[TimeZoneAwareExpression]]: A common base trait for time zone aware expressions.
+ * - [[SubqueryExpression]]: A base interface for expressions that contain a [[LogicalPlan]].
  *
  * - [[LeafExpression]]: an expression that has no child.
  * - [[UnaryExpression]]: an expression that has one child.
@@ -54,12 +71,20 @@ import org.apache.spark.sql.types._
  * - [[BinaryOperator]]: a special case of [[BinaryExpression]] that requires two children to have
  *                       the same output data type.
  *
+ * A few important traits used for type coercion rules:
+ * - [[ExpectsInputTypes]]: an expression that has the expected input types. This trait is typically
+ *                          used by operator expressions (e.g. [[Add]], [[Subtract]]) to define
+ *                          expected input types without any implicit casting.
+ * - [[ImplicitCastInputTypes]]: an expression that has the expected input types, which can be
+ *                               implicitly castable using [[TypeCoercion.ImplicitTypeCasts]].
+ * - [[ComplexTypeMergingExpression]]: to resolve output types of the complex expressions
+ *                                     (e.g., [[CaseWhen]]).
  */
 abstract class Expression extends TreeNode[Expression] {
 
   /**
    * Returns true when an expression is a candidate for static evaluation before the query is
-   * executed.
+   * executed. A typical use case: [[org.apache.spark.sql.catalyst.optimizer.ConstantFolding]]
    *
    * The following conditions are used to determine suitability for constant folding:
    *  - A [[Coalesce]] is foldable if all of its children are foldable
@@ -72,7 +97,8 @@ abstract class Expression extends TreeNode[Expression] {
 
   /**
    * Returns true when the current expression always return the same result for fixed inputs from
-   * children.
+   * children. The non-deterministic expressions should not change in number and order. They should
+   * not be evaluated during the query planning.
    *
    * Note that this means that an expression should be considered as non-deterministic if:
    * - it relies on some mutable internal state, or
@@ -252,8 +278,9 @@ abstract class Expression extends TreeNode[Expression] {
 
 
 /**
- * An expression that cannot be evaluated. Some expressions don't live past analysis or optimization
- * time (e.g. Star). This trait is used by those expressions.
+ * An expression that cannot be evaluated. These expressions don't live past analysis or
+ * optimization time (e.g. Star) and should not be evaluated during query planning and
+ * execution.
  */
 trait Unevaluable extends Expression {
 
@@ -724,9 +751,10 @@ abstract class TernaryExpression extends Expression {
 }
 
 /**
- * A trait resolving nullable, containsNull, valueContainsNull flags of the output date type.
- * This logic is usually utilized by expressions combining data from multiple child expressions
- * of non-primitive types (e.g. [[CaseWhen]]).
+ * A trait used for resolving nullable flags, including `nullable`, `containsNull` of [[ArrayType]]
+ * and `valueContainsNull` of [[MapType]], containsNull, valueContainsNull flags of the output date
+ * type. This is usually utilized by the expressions (e.g. [[CaseWhen]]) that combine data from
+ * multiple child expressions of non-primitive types.
  */
 trait ComplexTypeMergingExpression extends Expression {
 

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

@@ -130,6 +130,9 @@ abstract class Attribute extends LeafExpression with NamedExpression with NullIn
  * Note that exprId and qualifiers are in a separate parameter list because
  * we only pattern match on child and name.
  *
+ * Note that when creating a new Alias, all the [[AttributeReference]] that refer to
+ * the original alias should be updated to the new one.
+ *
  * @param child The computation being performed
  * @param name The name to be associated with the result of computing [[child]].
  * @param exprId A globally unique id used to check if an [[AttributeReference]] refers to this

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

@@ -17,11 +17,11 @@
 
 package org.apache.spark.sql.catalyst.plans.logical
 
-import org.apache.spark.sql.catalyst.{AliasIdentifier}
+import org.apache.spark.sql.catalyst.AliasIdentifier
 import org.apache.spark.sql.catalyst.analysis.{MultiInstanceRelation, NamedRelation}
 import org.apache.spark.sql.catalyst.catalog.{CatalogStorageFormat, CatalogTable}
 import org.apache.spark.sql.catalyst.expressions._
-import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression
+import org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression, AggregateFunction}
 import org.apache.spark.sql.catalyst.plans._
 import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, Partitioning, RangePartitioning, RoundRobinPartitioning}
 import org.apache.spark.sql.catalyst.util.truncatedString
@@ -575,6 +575,18 @@ case class Range(
   }
 }
 
+/**
+ * This is a Group by operator with the aggregate functions and projections.
+ *
+ * @param groupingExpressions expressions for grouping keys
+ * @param aggregateExpressions expressions for a project list, which could contain
+ *                             [[AggregateFunction]]s.
+ *
+ * Note: Currently, aggregateExpressions is the project list of this Group by operator. Before
+ * separating projection from grouping and aggregate, we should avoid expression-level optimization
+ * on aggregateExpressions, which could reference an expression in groupingExpressions.
+ * For example, see the rule [[org.apache.spark.sql.catalyst.optimizer.SimplifyExtractValueOps]]
+ */
 case class Aggregate(
     groupingExpressions: Seq[Expression],
     aggregateExpressions: Seq[NamedExpression],