[SPARK-51012][SQL] Remove SparkStrategy from Connect Shims

hvanhovell · hvanhovell · commit 98957380be98 · 2025-01-28T09:59:42.000-04:00
### What changes were proposed in this pull request? This PR removes SparkStrategy from the Connect shims. ### Why are the changes needed? SparkStrategy in Connect shims is causing some headaches Scala reflection based tests in Catalyst (see apache#48818). This was the smallest change that fixes this particular issues. Another approach would have been to split the shims projects into a sql-shims and a core-shims project. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Existing tests. I manually executed `org.apache.spark.sql.catalyst.encoders.EncoderResolutionSuite` in both SBT and Maven. ### Was this patch authored or co-authored using generative AI tooling? No. Closes apache#49701 from hvanhovell/SPARK-51012. Authored-by: Herman van Hovell <herman@databricks.com> Signed-off-by: Herman van Hovell <herman@databricks.com>
diff --git a/sql/api/src/main/scala/org/apache/spark/sql/package.scala b/sql/api/src/main/scala/org/apache/spark/sql/package.scala
@@ -16,9 +16,6 @@
  */
 package org.apache.spark
 
-import org.apache.spark.annotation.{DeveloperApi, Unstable}
-import org.apache.spark.sql.execution.SparkStrategy
-
 /**
  * Allows the execution of relational queries, including those expressed in SQL using Spark.
  *
@@ -33,16 +30,6 @@ import org.apache.spark.sql.execution.SparkStrategy
  */
 package object sql {
 
-  /**
-   * Converts a logical plan into zero or more SparkPlans. This API is exposed for experimenting
-   * with the query planner and is not designed to be stable across spark releases. Developers
-   * writing libraries should instead consider using the stable APIs provided in
-   * [[org.apache.spark.sql.sources]]
-   */
-  @DeveloperApi
-  @Unstable
-  type Strategy = SparkStrategy
-
   type DataFrame = Dataset[Row]
 
   /**
diff --git a/sql/connect/shims/src/main/scala/org/apache/spark/shims.scala b/sql/connect/shims/src/main/scala/org/apache/spark/shims.scala
@@ -35,7 +35,6 @@ package sql {
 
   package execution {
     class QueryExecution
-    class SparkStrategy
   }
   package internal {
     class SharedState
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/ExperimentalMethods.scala b/sql/core/src/main/scala/org/apache/spark/sql/ExperimentalMethods.scala
@@ -20,6 +20,7 @@ package org.apache.spark.sql
 import org.apache.spark.annotation.{Experimental, Unstable}
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.classic.Strategy
 
 /**
  * :: Experimental ::
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SparkSessionExtensions.scala b/sql/core/src/main/scala/org/apache/spark/sql/SparkSessionExtensions.scala
@@ -28,6 +28,7 @@ import org.apache.spark.sql.catalyst.expressions.ExpressionInfo
 import org.apache.spark.sql.catalyst.parser.ParserInterface
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.execution.{ColumnarRule, SparkPlan}
 
 /**
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/classic/package.scala b/sql/core/src/main/scala/org/apache/spark/sql/classic/package.scala
@@ -17,6 +17,9 @@
 
 package org.apache.spark.sql
 
+import org.apache.spark.annotation.{DeveloperApi, Unstable}
+import org.apache.spark.sql.execution.SparkStrategy
+
 /**
  * Allows the execution of relational queries, including those expressed in SQL using Spark.
  *
@@ -30,4 +33,14 @@ package org.apache.spark.sql
  */
 package object classic {
   type DataFrame = Dataset[Row]
+
+  /**
+   * Converts a logical plan into zero or more SparkPlans. This API is exposed for experimenting
+   * with the query planner and is not designed to be stable across spark releases. Developers
+   * writing libraries should instead consider using the stable APIs provided in
+   * [[org.apache.spark.sql.sources]]
+   */
+  @DeveloperApi
+  @Unstable
+  type Strategy = SparkStrategy
 }
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStageStrategy.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStageStrategy.scala
@@ -17,11 +17,11 @@
 
 package org.apache.spark.sql.execution.adaptive
 
-import org.apache.spark.sql.Strategy
 import org.apache.spark.sql.catalyst.optimizer.{BuildLeft, BuildRight}
 import org.apache.spark.sql.catalyst.planning.{ExtractEquiJoinKeys, ExtractSingleColumnNullAwareAntiJoin}
 import org.apache.spark.sql.catalyst.plans.LeftAnti
 import org.apache.spark.sql.catalyst.plans.logical.{Join, LogicalPlan}
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.execution.{joins, SparkPlan}
 import org.apache.spark.sql.execution.joins.{BroadcastHashJoinExec, BroadcastNestedLoopJoinExec}
 
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/V2CommandStrategy.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/V2CommandStrategy.scala
@@ -17,10 +17,10 @@
 
 package org.apache.spark.sql.execution.command.v2
 
-import org.apache.spark.sql.Strategy
 import org.apache.spark.sql.catalyst.analysis.ResolvedIdentifier
 import org.apache.spark.sql.catalyst.expressions.VariableReference
 import org.apache.spark.sql.catalyst.plans.logical._
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.execution.SparkPlan
 
 object V2CommandStrategy extends Strategy {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
@@ -27,7 +27,7 @@ import org.apache.hadoop.fs.Path
 import org.apache.spark.internal.{Logging, MDC}
 import org.apache.spark.internal.LogKeys.PREDICATES
 import org.apache.spark.rdd.RDD
-import org.apache.spark.sql.{Row, SaveMode, Strategy}
+import org.apache.spark.sql.{Row, SaveMode}
 import org.apache.spark.sql.catalyst.{expressions, CatalystTypeConverters, InternalRow, QualifiedTableName, SQLConfHelper}
 import org.apache.spark.sql.catalyst.CatalystTypeConverters.convertToScala
 import org.apache.spark.sql.catalyst.analysis._
@@ -41,7 +41,7 @@ import org.apache.spark.sql.catalyst.rules.Rule
 import org.apache.spark.sql.catalyst.streaming.StreamingRelationV2
 import org.apache.spark.sql.catalyst.types.DataTypeUtils
 import org.apache.spark.sql.catalyst.util.{GeneratedColumn, IdentityColumn, ResolveDefaultColumns, V2ExpressionBuilder}
-import org.apache.spark.sql.classic.SparkSession
+import org.apache.spark.sql.classic.{SparkSession, Strategy}
 import org.apache.spark.sql.connector.catalog.{SupportsRead, V1Table}
 import org.apache.spark.sql.connector.catalog.TableCapability._
 import org.apache.spark.sql.connector.expressions.{Expression => V2Expression, NullOrdering, SortDirection, SortOrder => V2SortOrder, SortValue}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileSourceStrategy.scala
@@ -31,6 +31,7 @@ import org.apache.spark.sql.catalyst.planning.ScanOperation
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.trees.TreePattern.{PLAN_EXPRESSION, SCALAR_SUBQUERY}
 import org.apache.spark.sql.catalyst.types.DataTypeUtils
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.execution.{FileSourceScanExec, SparkPlan}
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.types.{DoubleType, FloatType, StructType}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala
@@ -17,7 +17,7 @@
 package org.apache.spark.sql.internal
 
 import org.apache.spark.annotation.Unstable
-import org.apache.spark.sql.{DataSourceRegistration, ExperimentalMethods, SparkSessionExtensions, Strategy, UDTFRegistration}
+import org.apache.spark.sql.{DataSourceRegistration, ExperimentalMethods, SparkSessionExtensions, UDTFRegistration}
 import org.apache.spark.sql.artifact.ArtifactManager
 import org.apache.spark.sql.catalyst.analysis.{Analyzer, EvalSubqueriesForTimeTravel, FunctionRegistry, InvokeProcedures, ReplaceCharWithVarchar, ResolveDataSource, ResolveSessionCatalog, ResolveTranspose, TableFunctionRegistry}
 import org.apache.spark.sql.catalyst.analysis.resolver.ResolverExtension
@@ -27,7 +27,7 @@ import org.apache.spark.sql.catalyst.optimizer.Optimizer
 import org.apache.spark.sql.catalyst.parser.ParserInterface
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
-import org.apache.spark.sql.classic.{SparkSession, StreamingQueryManager, UDFRegistration}
+import org.apache.spark.sql.classic.{SparkSession, Strategy, StreamingQueryManager, UDFRegistration}
 import org.apache.spark.sql.connector.catalog.CatalogManager
 import org.apache.spark.sql.errors.QueryCompilationErrors
 import org.apache.spark.sql.execution.{ColumnarRule, CommandExecutionMode, QueryExecution, SparkOptimizer, SparkPlanner, SparkSqlParser}
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/ExtraStrategiesSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/ExtraStrategiesSuite.scala
@@ -21,6 +21,7 @@ import org.apache.spark.rdd.RDD
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, Project}
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.execution.{LeafExecNode, SparkPlan}
 import org.apache.spark.sql.test.SharedSparkSession
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/SparkPlannerSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/SparkPlannerSuite.scala
@@ -17,9 +17,9 @@
 
 package org.apache.spark.sql.execution
 
-import org.apache.spark.sql.Strategy
 import org.apache.spark.sql.catalyst.expressions.Attribute
 import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, LocalRelation, LogicalPlan, ReturnAnswer, Union}
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.test.SharedSparkSession
 
 class SparkPlannerSuite extends SharedSparkSession {
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
@@ -28,11 +28,12 @@ import org.apache.spark.SparkException
 import org.apache.spark.rdd.RDD
 import org.apache.spark.scheduler.{SparkListener, SparkListenerEvent, SparkListenerJobStart}
 import org.apache.spark.shuffle.sort.SortShuffleManager
-import org.apache.spark.sql.{DataFrame, Dataset, QueryTest, Row, SparkSession, Strategy}
+import org.apache.spark.sql.{DataFrame, Dataset, QueryTest, Row, SparkSession}
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.expressions.Attribute
 import org.apache.spark.sql.catalyst.optimizer.{BuildLeft, BuildRight}
 import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan}
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.execution._
 import org.apache.spark.sql.execution.aggregate.BaseAggregateExec
 import org.apache.spark.sql.execution.columnar.{InMemoryTableScanExec, InMemoryTableScanLike}
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala
@@ -24,14 +24,14 @@ import scala.util.control.NonFatal
 import org.apache.hadoop.hive.ql.exec.{UDAF, UDF}
 import org.apache.hadoop.hive.ql.udf.generic.{AbstractGenericUDAFResolver, GenericUDF, GenericUDTF}
 
-import org.apache.spark.sql.{AnalysisException, Strategy}
+import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.analysis.{Analyzer, EvalSubqueriesForTimeTravel, InvokeProcedures, ReplaceCharWithVarchar, ResolveDataSource, ResolveSessionCatalog, ResolveTranspose}
 import org.apache.spark.sql.catalyst.analysis.resolver.ResolverExtension
 import org.apache.spark.sql.catalyst.catalog.{ExternalCatalogWithListener, InvalidUDFClassException}
 import org.apache.spark.sql.catalyst.expressions.Expression
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
-import org.apache.spark.sql.classic.SparkSession
+import org.apache.spark.sql.classic.{SparkSession, Strategy}
 import org.apache.spark.sql.errors.QueryCompilationErrors
 import org.apache.spark.sql.execution.SparkPlanner
 import org.apache.spark.sql.execution.aggregate.ResolveEncodersInScalaAgg
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala
@@ -28,6 +28,7 @@ import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.planning._
 import org.apache.spark.sql.catalyst.plans.logical.{DeleteFromTable, InsertIntoDir, InsertIntoStatement, LogicalPlan, ScriptTransformation, Statistics, SubqueryAlias}
 import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.classic.Strategy
 import org.apache.spark.sql.errors.QueryCompilationErrors
 import org.apache.spark.sql.execution._
 import org.apache.spark.sql.execution.command.{CreateTableCommand, DDLUtils, InsertIntoDataSourceDirCommand}

Original file line number	Diff line number	Diff line change
`@@ -35,7 +35,6 @@ package sql {`
`35`	`35`
`36`	`36`	`package execution {`
`37`	`37`	`class QueryExecution`
`38`		`- class SparkStrategy`
`39`	`38`	`}`
`40`	`39`	`package internal {`
`41`	`40`	`class SharedState`