Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/6356#discussion_r30918892
--- Diff: sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala ---
@@ -1321,3 +1201,137 @@ object SQLContext {
}
}
}
+
+
+
+/**
+ * :: DeveloperApi ::
+ * The primary workflow for executing relational queries using Spark.
Designed to allow easy
+ * access to the intermediate phases of query execution for developers.
+ */
+@DeveloperApi
+class QueryExecution(val sqlContext: SQLContext, val logical: LogicalPlan)
{
+ val analyzer = sqlContext.analyzer
+ val optimizer = sqlContext.optimizer
+ val planner = sqlContext.planner
+ val cacheManager = sqlContext.cacheManager
+ val prepareForExecution = sqlContext.prepareForExecution
+
+ def assertAnalyzed(): Unit = analyzer.checkAnalysis(analyzed)
+
+ lazy val analyzed: LogicalPlan = analyzer.execute(logical)
+ lazy val withCachedData: LogicalPlan = {
+ assertAnalyzed()
+ cacheManager.useCachedData(analyzed)
+ }
+ lazy val optimizedPlan: LogicalPlan = optimizer.execute(withCachedData)
+
+ // TODO: Don't just pick the first one...
+ lazy val sparkPlan: SparkPlan = {
+ SparkPlan.currentContext.set(sqlContext)
+ planner.plan(optimizedPlan).next()
+ }
+ // executedPlan should not be used to initialize any SparkPlan. It
should be
+ // only used for execution.
+ lazy val executedPlan: SparkPlan = prepareForExecution.execute(sparkPlan)
+
+ /** Internal version of the RDD. Avoids copies and has no schema */
+ lazy val toRdd: RDD[Row] = executedPlan.execute()
+
+ protected def stringOrError[A](f: => A): String =
+ try f.toString catch { case e: Throwable => e.toString }
+
+ def simpleString: String =
+ s"""== Physical Plan ==
+ |${stringOrError(executedPlan)}
+ """.stripMargin.trim
+
+ override def toString: String = {
+ def output =
+ analyzed.output.map(o => s"${o.name}:
${o.dataType.simpleString}").mkString(", ")
+
+ // TODO previously will output RDD details by run
(${stringOrError(toRdd.toDebugString)})
+ // however, the `toRdd` will cause the real execution, which is not
what we want.
+ // We need to think about how to avoid the side effect.
+ s"""== Parsed Logical Plan ==
+ |${stringOrError(logical)}
+ |== Analyzed Logical Plan ==
+ |${stringOrError(output)}
+ |${stringOrError(analyzed)}
+ |== Optimized Logical Plan ==
+ |${stringOrError(optimizedPlan)}
+ |== Physical Plan ==
+ |${stringOrError(executedPlan)}
+ |Code Generation: ${stringOrError(executedPlan.codegenEnabled)}
+ |== RDD ==
+ """.stripMargin.trim
+ }
+}
+
+
+class SparkPlanner(val sqlContext: SQLContext) extends
org.apache.spark.sql.execution.SparkStrategies {
--- End diff --
can we move this into the execution package?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
