diff options
author | Cheng Hao <hao.cheng@intel.com> | 2014-08-25 17:43:56 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2014-08-25 17:43:56 -0700 |
commit | 156eb3966176de02ec3ec90ae10e50a7ebfbbf4f (patch) | |
tree | 344f6147dc5fcf5cea0db78618c5001105077a3c /sql/hive | |
parent | cae9414d3805c6cf00eab6a6144d8f90cd0212f8 (diff) | |
download | spark-156eb3966176de02ec3ec90ae10e50a7ebfbbf4f.tar.gz spark-156eb3966176de02ec3ec90ae10e50a7ebfbbf4f.tar.bz2 spark-156eb3966176de02ec3ec90ae10e50a7ebfbbf4f.zip |
[SPARK-3058] [SQL] Support EXTENDED for EXPLAIN
Provide `extended` keyword support for `explain` command in SQL. e.g.
```
explain extended select key as a1, value as a2 from src where key=1;
== Parsed Logical Plan ==
Project ['key AS a1#3,'value AS a2#4]
Filter ('key = 1)
UnresolvedRelation None, src, None
== Analyzed Logical Plan ==
Project [key#8 AS a1#3,value#9 AS a2#4]
Filter (CAST(key#8, DoubleType) = CAST(1, DoubleType))
MetastoreRelation default, src, None
== Optimized Logical Plan ==
Project [key#8 AS a1#3,value#9 AS a2#4]
Filter (CAST(key#8, DoubleType) = 1.0)
MetastoreRelation default, src, None
== Physical Plan ==
Project [key#8 AS a1#3,value#9 AS a2#4]
Filter (CAST(key#8, DoubleType) = 1.0)
HiveTableScan [key#8,value#9], (MetastoreRelation default, src, None), None
Code Generation: false
== RDD ==
(2) MappedRDD[14] at map at HiveContext.scala:350
MapPartitionsRDD[13] at mapPartitions at basicOperators.scala:42
MapPartitionsRDD[12] at mapPartitions at basicOperators.scala:57
MapPartitionsRDD[11] at mapPartitions at TableReader.scala:112
MappedRDD[10] at map at TableReader.scala:240
HadoopRDD[9] at HadoopRDD at TableReader.scala:230
```
It's the sub task of #1847. But can go without any dependency.
Author: Cheng Hao <hao.cheng@intel.com>
Closes #1962 from chenghao-intel/explain_extended and squashes the following commits:
295db74 [Cheng Hao] Fix bug in printing the simple execution plan
48bc989 [Cheng Hao] Support EXTENDED for EXPLAIN
Diffstat (limited to 'sql/hive')
4 files changed, 58 insertions, 5 deletions
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 29baefe714..d9b2bc7348 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 @@ -424,7 +424,7 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { logical match { case _: NativeCommand => "<Native command: executed by Hive>" case _: SetCommand => "<SET command: executed by Hive, and noted by SQLContext>" - case _ => executedPlan.toString + case _ => super.simpleString } } } diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala index 1d9ba1b24a..5da6e8df03 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala @@ -409,10 +409,9 @@ private[hive] object HiveQl { ExplainCommand(NoRelation) case Token("TOK_EXPLAIN", explainArgs) => // Ignore FORMATTED if present. - val Some(query) :: _ :: _ :: Nil = + val Some(query) :: _ :: extended :: Nil = getClauses(Seq("TOK_QUERY", "FORMATTED", "EXTENDED"), explainArgs) - // TODO: support EXTENDED? - ExplainCommand(nodeToPlan(query)) + ExplainCommand(nodeToPlan(query), extended != None) case Token("TOK_DESCTABLE", describeArgs) => // Reference: https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveExplainSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveExplainSuite.scala new file mode 100644 index 0000000000..4ed58f4be1 --- /dev/null +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveExplainSuite.scala @@ -0,0 +1,54 @@ +/* + * 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.hive.execution + +import org.apache.spark.sql.QueryTest +import org.apache.spark.sql.hive.test.TestHive +import org.apache.spark.sql.hive.test.TestHive._ +import org.apache.spark.sql.Row + +/** + * A set of tests that validates support for Hive Explain command. + */ +class HiveExplainSuite extends QueryTest { + private def check(sqlCmd: String, exists: Boolean, keywords: String*) { + val outputs = sql(sqlCmd).collect().map(_.getString(0)).mkString + for (key <- keywords) { + if (exists) { + assert(outputs.contains(key), s"Failed for $sqlCmd ($key doens't exist in result)") + } else { + assert(!outputs.contains(key), s"Failed for $sqlCmd ($key existed in the result)") + } + } + } + + test("explain extended command") { + check(" explain select * from src where key=123 ", true, + "== Physical Plan ==") + check(" explain select * from src where key=123 ", false, + "== Parsed Logical Plan ==", + "== Analyzed Logical Plan ==", + "== Optimized Logical Plan ==") + check(" explain extended select * from src where key=123 ", true, + "== Parsed Logical Plan ==", + "== Analyzed Logical Plan ==", + "== Optimized Logical Plan ==", + "== Physical Plan ==", + "Code Generation", "== RDD ==") + } +} 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 26e4ec6e6d..6d925e56e6 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 @@ -327,7 +327,7 @@ class HiveQuerySuite extends HiveComparisonTest { def isExplanation(result: SchemaRDD) = { val explanation = result.select('plan).collect().map { case Row(plan: String) => plan } - explanation.size > 1 && explanation.head.startsWith("Physical execution plan") + explanation.exists(_ == "== Physical Plan ==") } test("SPARK-1704: Explain commands as a SchemaRDD") { |