diff options
author | Zongheng Yang <zongheng.y@gmail.com> | 2014-06-09 16:47:44 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2014-06-09 16:47:44 -0700 |
commit | a9ec033c8cf489898cc47e2043bd9e86b7df1ff8 (patch) | |
tree | 5b73a963028a019c1b89f15f61326097fcf87d4b /sql/core | |
parent | c6e041d171e3d9882ab15e2bd7a7217dc19647f6 (diff) | |
download | spark-a9ec033c8cf489898cc47e2043bd9e86b7df1ff8.tar.gz spark-a9ec033c8cf489898cc47e2043bd9e86b7df1ff8.tar.bz2 spark-a9ec033c8cf489898cc47e2043bd9e86b7df1ff8.zip |
[SPARK-1704][SQL] Fully support EXPLAIN commands as SchemaRDD.
This PR attempts to resolve [SPARK-1704](https://issues.apache.org/jira/browse/SPARK-1704) by introducing a physical plan for EXPLAIN commands, which just prints out the debug string (containing various SparkSQL's plans) of the corresponding QueryExecution for the actual query.
Author: Zongheng Yang <zongheng.y@gmail.com>
Closes #1003 from concretevitamin/explain-cmd and squashes the following commits:
5b7911f [Zongheng Yang] Add a regression test.
1bfa379 [Zongheng Yang] Modify output().
719ada9 [Zongheng Yang] Override otherCopyArgs for ExplainCommandPhysical.
4318fd7 [Zongheng Yang] Make all output one Row.
439c6ab [Zongheng Yang] Minor cleanups.
408f574 [Zongheng Yang] SPARK-1704: Add CommandStrategy and ExplainCommandPhysical.
Diffstat (limited to 'sql/core')
3 files changed, 49 insertions, 0 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala index 5626f0da22..fde4c485b5 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/SQLContext.scala @@ -191,6 +191,7 @@ class SQLContext(@transient val sparkContext: SparkContext) val sparkContext = self.sparkContext val strategies: Seq[Strategy] = + CommandStrategy(self) :: TakeOrdered :: PartialAggregation :: LeftSemiJoin :: @@ -256,6 +257,11 @@ class SQLContext(@transient val sparkContext: SparkContext) Batch("Prepare Expressions", Once, new BindReferences[SparkPlan]) :: Nil } + // TODO: or should we make QueryExecution protected[sql]? + protected[sql] def mkQueryExecution(plan: LogicalPlan) = new QueryExecution { + val logical = plan + } + /** * The primary workflow for executing relational queries using Spark. Designed to allow easy * access to the intermediate phases of query execution for developers. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala index 6463f47510..295c265b16 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala @@ -233,4 +233,15 @@ private[sql] abstract class SparkStrategies extends QueryPlanner[SparkPlan] { case _ => Nil } } + + // TODO: this should be merged with SPARK-1508's SetCommandStrategy + case class CommandStrategy(context: SQLContext) extends Strategy { + def apply(plan: LogicalPlan): Seq[SparkPlan] = plan match { + case logical.ExplainCommand(child) => + val qe = context.mkQueryExecution(child) + Seq(execution.ExplainCommandPhysical(qe.executedPlan, plan.output)(context)) + case _ => Nil + } + } + } diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/commands.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/commands.scala new file mode 100644 index 0000000000..5371d2f479 --- /dev/null +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/commands.scala @@ -0,0 +1,32 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.execution + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{SQLContext, Row} +import org.apache.spark.sql.catalyst.expressions.{GenericRow, Attribute} + +case class ExplainCommandPhysical(child: SparkPlan, output: Seq[Attribute]) + (@transient context: SQLContext) extends UnaryNode { + def execute(): RDD[Row] = { + val planString = new GenericRow(Array[Any](child.toString)) + context.sparkContext.parallelize(Seq(planString)) + } + + override def otherCopyArgs = context :: Nil +} |