[SPARK-22520][SQL] Support code generation for large CaseWhen

Author: mgaido91

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

@@ -87,8 +87,7 @@ class EquivalentExpressions {
     def childrenToRecurse: Seq[Expression] = expr match {
       case _: CodegenFallback => Nil
       case i: If => i.predicate :: Nil
-      // `CaseWhen` implements `CodegenFallback`, we only need to handle `CaseWhenCodegen` here.
-      case c: CaseWhenCodegen => c.children.head :: Nil
+      case c: CaseWhen => c.children.head :: Nil
       case c: Coalesce => c.children.head :: Nil
       case other => other.children
     }

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

@@ -141,14 +141,34 @@ case class If(predicate: Expression, trueValue: Expression, falseValue: Expressi
 }
 
 /**
- * Abstract parent class for common logic in CaseWhen and CaseWhenCodegen.
+ * Case statements of the form "CASE WHEN a THEN b [WHEN c THEN d]* [ELSE e] END".
+ * When a = true, returns b; when c = true, returns d; else returns e.
  *
  * @param branches seq of (branch condition, branch value)
  * @param elseValue optional value for the else branch
  */
-abstract class CaseWhenBase(
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+  usage = "CASE WHEN expr1 THEN expr2 [WHEN expr3 THEN expr4]* [ELSE expr5] END - When `expr1` = true, returns `expr2`; else when `expr3` = true, returns `expr4`; else returns `expr5`.",
+  arguments = """
+    Arguments:
+      * expr1, expr3 - the branch condition expressions should all be boolean type.
+      * expr2, expr4, expr5 - the branch value expressions and else value expression should all be
+          same type or coercible to a common type.
+  """,
+  examples = """
+    Examples:
+      > SELECT CASE WHEN 1 > 0 THEN 1 WHEN 2 > 0 THEN 2.0 ELSE 1.2 END;
+       1
+      > SELECT CASE WHEN 1 < 0 THEN 1 WHEN 2 > 0 THEN 2.0 ELSE 1.2 END;
+       2
+      > SELECT CASE WHEN 1 < 0 THEN 1 WHEN 2 < 0 THEN 2.0 ELSE null END;
+       NULL
+  """)
+// scalastyle:on line.size.limit
+case class CaseWhen(
     branches: Seq[(Expression, Expression)],
-    elseValue: Option[Expression])
+    elseValue: Option[Expression] = None)
   extends Expression with Serializable {
 
   override def children: Seq[Expression] = branches.flatMap(b => b._1 :: b._2 :: Nil) ++ elseValue
@@ -211,111 +231,61 @@ abstract class CaseWhenBase(
     val elseCase = elseValue.map(" ELSE " + _.sql).getOrElse("")
     "CASE" + cases + elseCase + " END"
   }
-}
-
-
-/**
- * Case statements of the form "CASE WHEN a THEN b [WHEN c THEN d]* [ELSE e] END".
- * When a = true, returns b; when c = true, returns d; else returns e.
- *
- * @param branches seq of (branch condition, branch value)
- * @param elseValue optional value for the else branch
- */
-// scalastyle:off line.size.limit
-@ExpressionDescription(
-  usage = "CASE WHEN expr1 THEN expr2 [WHEN expr3 THEN expr4]* [ELSE expr5] END - When `expr1` = true, returns `expr2`; else when `expr3` = true, returns `expr4`; else returns `expr5`.",
-  arguments = """
-    Arguments:
-      * expr1, expr3 - the branch condition expressions should all be boolean type.
-      * expr2, expr4, expr5 - the branch value expressions and else value expression should all be
-          same type or coercible to a common type.
-  """,
-  examples = """
-    Examples:
-      > SELECT CASE WHEN 1 > 0 THEN 1 WHEN 2 > 0 THEN 2.0 ELSE 1.2 END;
-       1
-      > SELECT CASE WHEN 1 < 0 THEN 1 WHEN 2 > 0 THEN 2.0 ELSE 1.2 END;
-       2
-      > SELECT CASE WHEN 1 < 0 THEN 1 WHEN 2 < 0 THEN 2.0 ELSE null END;
-       NULL
-  """)
-// scalastyle:on line.size.limit
-case class CaseWhen(
-    val branches: Seq[(Expression, Expression)],
-    val elseValue: Option[Expression] = None)
-  extends CaseWhenBase(branches, elseValue) with CodegenFallback with Serializable {
-
-  override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
-    super[CodegenFallback].doGenCode(ctx, ev)
-  }
-
-  def toCodegen(): CaseWhenCodegen = {
-    CaseWhenCodegen(branches, elseValue)
-  }
-}
-
-/**
- * CaseWhen expression used when code generation condition is satisfied.
- * OptimizeCodegen optimizer replaces CaseWhen into CaseWhenCodegen.
- *
- * @param branches seq of (branch condition, branch value)
- * @param elseValue optional value for the else branch
- */
-case class CaseWhenCodegen(
-    val branches: Seq[(Expression, Expression)],
-    val elseValue: Option[Expression] = None)
-  extends CaseWhenBase(branches, elseValue) with Serializable {
 
   override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
-    // Generate code that looks like:
-    //
-    // condA = ...
-    // if (condA) {
-    //   valueA
-    // } else {
-    //   condB = ...
-    //   if (condB) {
-    //     valueB
-    //   } else {
-    //     condC = ...
-    //     if (condC) {
-    //       valueC
-    //     } else {
-    //       elseValue
-    //     }
-    //   }
-    // }
+    val conditionMet = ctx.freshName("caseWhenConditionMet")
+    ctx.addMutableState("boolean", ev.isNull, "")
+    ctx.addMutableState(ctx.javaType(dataType), ev.value, "")
     val cases = branches.map { case (condExpr, valueExpr) =>
       val cond = condExpr.genCode(ctx)
       val res = valueExpr.genCode(ctx)
       s"""
-        ${cond.code}
-        if (!${cond.isNull} && ${cond.value}) {
-          ${res.code}
-          ${ev.isNull} = ${res.isNull};
-          ${ev.value} = ${res.value};
+        if(!$conditionMet) {
+          ${cond.code}
+          if (!${cond.isNull} && ${cond.value}) {
+            ${res.code}
+            ${ev.isNull} = ${res.isNull};
+            ${ev.value} = ${res.value};
+            $conditionMet = true;
+          }
         }
       """
     }
 
-    var generatedCode = cases.mkString("", "\nelse {\n", "\nelse {\n")
-
-    elseValue.foreach { elseExpr =>
+    val elseCode = elseValue.map { elseExpr =>
       val res = elseExpr.genCode(ctx)
-      generatedCode +=
-        s"""
+      s"""
+        if(!$conditionMet) {
           ${res.code}
           ${ev.isNull} = ${res.isNull};
           ${ev.value} = ${res.value};
-        """
-    }
+        }
+      """
+    }.getOrElse("")
 
-    generatedCode += "}\n" * cases.size
+    val casesCode = if (ctx.INPUT_ROW == null || ctx.currentVars != null) {
+      cases.mkString("\n")
+    } else {
+      ctx.splitExpressions(cases, "caseWhen",
+        ("InternalRow", ctx.INPUT_ROW) :: ("boolean", conditionMet) :: Nil, returnType = "boolean",
+        makeSplitFunction = {
+          func =>
+            s"""
+              $func
+              return $conditionMet;
+            """
+        },
+        foldFunctions = { funcCalls =>
+          funcCalls.map(funcCall => s"$conditionMet = $funcCall;").mkString("\n")
+        })
+    }
 
     ev.copy(code = s"""
-      boolean ${ev.isNull} = true;
-      ${ctx.javaType(dataType)} ${ev.value} = ${ctx.defaultValue(dataType)};
-      $generatedCode""")
+      ${ev.isNull} = true;
+      ${ev.value} = ${ctx.defaultValue(dataType)};
+      boolean $conditionMet = false;
+      $casesCode
+      $elseCode""")
   }
 }
 

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

@@ -138,8 +138,6 @@ abstract class Optimizer(sessionCatalog: SessionCatalog)
     // The following batch should be executed after batch "Join Reorder" and "LocalRelation".
     Batch("Check Cartesian Products", Once,
       CheckCartesianProducts) ::
-    Batch("OptimizeCodegen", Once,
-      OptimizeCodegen) ::
     Batch("RewriteSubquery", Once,
       RewritePredicateSubquery,
       CollapseProject) :: Nil

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

@@ -552,21 +552,6 @@ object FoldablePropagation extends Rule[LogicalPlan] {
 }
 
 
-/**
- * Optimizes expressions by replacing according to CodeGen configuration.
- */
-object OptimizeCodegen extends Rule[LogicalPlan] {
-  def apply(plan: LogicalPlan): LogicalPlan = plan transformAllExpressions {
-    case e: CaseWhen if canCodegen(e) => e.toCodegen()
-  }
-
-  private def canCodegen(e: CaseWhen): Boolean = {
-    val numBranches = e.branches.size + e.elseValue.size
-    numBranches <= SQLConf.get.maxCaseBranchesForCodegen
-  }
-}
-
-
 /**
  * Removes [[Cast Casts]] that are unnecessary because the input is already the correct type.
  */

sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala

@@ -570,12 +570,6 @@ object SQLConf {
     .booleanConf
     .createWithDefault(true)
 
-  val MAX_CASES_BRANCHES = buildConf("spark.sql.codegen.maxCaseBranches")
-    .internal()
-    .doc("The maximum number of switches supported with codegen.")
-    .intConf
-    .createWithDefault(20)
-
   val CODEGEN_LOGGING_MAX_LINES = buildConf("spark.sql.codegen.logging.maxLines")
     .internal()
     .doc("The maximum number of codegen lines to log when errors occur. Use -1 for unlimited.")
@@ -1084,8 +1078,6 @@ class SQLConf extends Serializable with Logging {
 
   def codegenFallback: Boolean = getConf(CODEGEN_FALLBACK)
 
-  def maxCaseBranchesForCodegen: Int = getConf(MAX_CASES_BRANCHES)
-
   def loggingMaxLinesForCodegen: Int = getConf(CODEGEN_LOGGING_MAX_LINES)
 
   def hugeMethodLimit: Int = getConf(WHOLESTAGE_HUGE_METHOD_LIMIT)

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CodeGenerationSuite.scala

@@ -77,7 +77,7 @@ class CodeGenerationSuite extends SparkFunSuite with ExpressionEvalHelper {
   }
 
   test("SPARK-13242: case-when expression with large number of branches (or cases)") {
-    val cases = 50
+    val cases = 500
     val clauses = 20
 
     // Generate an individual case

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeCodegenSuite.scala

@@ -90,7 +90,7 @@ class FlatMapGroupsWithState_StateManager(
     val deser = stateEncoder.resolveAndBind().deserializer.transformUp {
       case BoundReference(ordinal, _, _) => GetStructField(boundRefToNestedState, ordinal)
     }
-    CaseWhen(Seq(IsNull(boundRefToNestedState) -> Literal(null)), elseValue = deser).toCodegen()
+    CaseWhen(Seq(IsNull(boundRefToNestedState) -> Literal(null)), elseValue = deser)
   }
 
   // Converters for translating state between rows and Java objects