From a9ec033c8cf489898cc47e2043bd9e86b7df1ff8 Mon Sep 17 00:00:00 2001
From: Zongheng Yang <zongheng.y@gmail.com>
Date: Mon, 9 Jun 2014 16:47:44 -0700
Subject: [PATCH] [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.
---
.../catalyst/plans/logical/LogicalPlan.scala | 8 +++--
.../org/apache/spark/sql/SQLContext.scala | 6 ++++
.../spark/sql/execution/SparkStrategies.scala | 11 +++++++
.../apache/spark/sql/execution/commands.scala | 32 +++++++++++++++++++
.../apache/spark/sql/hive/HiveContext.scala | 3 +-
.../sql/hive/execution/HiveQuerySuite.scala | 12 +++++++
6 files changed, 68 insertions(+), 4 deletions(-)
create mode 100644 sql/core/src/main/scala/org/apache/spark/sql/execution/commands.scala
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala
index 2b8fbdcde9..4f641cd3a6 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala
@@ -20,7 +20,7 @@ package org.apache.spark.sql.catalyst.plans.logical
import org.apache.spark.sql.catalyst.errors.TreeNodeException
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.QueryPlan
-import org.apache.spark.sql.catalyst.types.StructType
+import org.apache.spark.sql.catalyst.types.{StringType, StructType}
import org.apache.spark.sql.catalyst.trees
abstract class LogicalPlan extends QueryPlan[LogicalPlan] {
@@ -102,7 +102,7 @@ abstract class LeafNode extends LogicalPlan with trees.LeafNode[LogicalPlan] {
*/
abstract class Command extends LeafNode {
self: Product =>
- def output = Seq.empty
+ def output: Seq[Attribute] = Seq.empty
}
/**
@@ -115,7 +115,9 @@ case class NativeCommand(cmd: String) extends Command
* Returned by a parser when the users only wants to see what query plan would be executed, without
* actually performing the execution.
*/
-case class ExplainCommand(plan: LogicalPlan) extends Command
+case class ExplainCommand(plan: LogicalPlan) extends Command {
+ override def output = Seq(AttributeReference("plan", StringType, nullable = false)())
+}
/**
* A logical plan node with single child.
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
+}
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala
index fbab2ac16b..4b97dc25ac 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala
@@ -218,6 +218,7 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) {
val hiveContext = self
override val strategies: Seq[Strategy] = Seq(
+ CommandStrategy(self),
TakeOrdered,
ParquetOperations,
HiveTableScans,
@@ -304,7 +305,7 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) {
*/
def stringResult(): Seq[String] = analyzed match {
case NativeCommand(cmd) => runSqlHive(cmd)
- case ExplainCommand(plan) => new QueryExecution { val logical = plan }.toString.split("\n")
+ case ExplainCommand(plan) => mkQueryExecution(plan).toString.split("\n")
case query =>
val result: Seq[Seq[Any]] = toRdd.collect().toSeq
// We need the types so we can output struct field names
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
index 125cc18bfb..c56eee2580 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
@@ -18,6 +18,7 @@
package org.apache.spark.sql.hive.execution
import org.apache.spark.sql.hive.test.TestHive._
+import org.apache.spark.sql.hive.test.TestHive
/**
* A set of test cases expressed in Hive QL that are not covered by the tests included in the hive distribution.
@@ -159,4 +160,15 @@ class HiveQuerySuite extends HiveComparisonTest {
hql("SHOW TABLES").toString
hql("SELECT * FROM src").toString
}
+
+ test("SPARK-1704: Explain commands as a SchemaRDD") {
+ hql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)")
+ val rdd = hql("explain select key, count(value) from src group by key")
+ assert(rdd.collect().size == 1)
+ assert(rdd.toString.contains("ExplainCommand"))
+ assert(rdd.filter(row => row.toString.contains("ExplainCommand")).collect().size == 0,
+ "actual contents of the result should be the plans of the query to be explained")
+ TestHive.reset()
+ }
+
}
--
GitLab