From c3de557ee383f3bb96ab5401db146c4cf2a13124 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Tue, 10 Sep 2019 17:44:59 +0800
Subject: [PATCH 01/14] save change

---
 .../hive/execution/HiveTableScanExec.scala    | 33 +++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala
index 5b00e2ebafa4..1b0e5a0c0bb2 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala
@@ -20,8 +20,11 @@ package org.apache.spark.sql.hive.execution
 import scala.collection.JavaConverters._
 
 import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.hive.common.JavaUtils
+import org.apache.hadoop.hive.ql.exec.Utilities
 import org.apache.hadoop.hive.ql.metadata.{Partition => HivePartition}
 import org.apache.hadoop.hive.ql.plan.TableDesc
+import org.apache.hadoop.hive.ql.session.SessionState
 import org.apache.hadoop.hive.serde.serdeConstants
 import org.apache.hadoop.hive.serde2.objectinspector._
 import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.ObjectInspectorCopyOption
@@ -120,6 +123,36 @@ case class HiveTableScanExec(
 
     HiveShim.appendReadColumns(hiveConf, neededColumnIDs, output.map(_.name))
 
+    logInfo(s"Test ADD JAR  ${SessionState.get()}")
+    if (SessionState.get() != null) {
+      logInfo(s"Test ADD JAR  ${SessionState.get().getConf.getClassLoader}")
+      logInfo("Test ADD JAR with SessionState.getConf.getClassLoader")
+      // scalastyle:off
+      try {
+        Class.forName(tableDesc.getSerdeClassName(), true, SessionState.get().getConf.getClassLoader)
+      } catch {
+        case e:Exception =>
+          logInfo("Failed Test ADD JAR with SessionState.getConf.getClassLoader")
+      }
+    }
+
+    logInfo(s"JavaUtils.getClassLoader => ${JavaUtils.getClassLoader}")
+    logInfo(s"SessionState.SharedState.jarClssLoader => ${sparkSession.sharedState.jarClassLoader}")
+    logInfo("Test ADD JAR with sharedState's JarClassloader")
+    // scalastyle:off
+    try {
+      Class.forName(tableDesc.getSerdeClassName(), true, sparkSession.sharedState.jarClassLoader)
+    } catch {
+      case e: Exception =>
+        logInfo("Failed Test ADD JAR with sharedState's JarClassloader")
+    }
+    logInfo("Test ADD JAR with JavaUtils.getClassLoader")
+    try {
+      Class.forName(tableDesc.getSerdeClassName(), true, JavaUtils.getClassLoader)
+    } catch {
+      case e: Exception =>
+        logInfo("Failed Test ADD JAR with JavaUtils.getClassLoader")
+    }
     val deserializer = tableDesc.getDeserializerClass.getConstructor().newInstance()
     deserializer.initialize(hiveConf, tableDesc.getProperties)
 

From 2cf3153f046a25e38173fad0cddc1c581ed42b93 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Tue, 10 Sep 2019 19:05:07 +0800
Subject: [PATCH 02/14] Revert "save change"

This reverts commit c3de557ee383f3bb96ab5401db146c4cf2a13124.
---
 .../hive/execution/HiveTableScanExec.scala    | 33 -------------------
 1 file changed, 33 deletions(-)

diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala
index 1b0e5a0c0bb2..5b00e2ebafa4 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala
@@ -20,11 +20,8 @@ package org.apache.spark.sql.hive.execution
 import scala.collection.JavaConverters._
 
 import org.apache.hadoop.conf.Configuration
-import org.apache.hadoop.hive.common.JavaUtils
-import org.apache.hadoop.hive.ql.exec.Utilities
 import org.apache.hadoop.hive.ql.metadata.{Partition => HivePartition}
 import org.apache.hadoop.hive.ql.plan.TableDesc
-import org.apache.hadoop.hive.ql.session.SessionState
 import org.apache.hadoop.hive.serde.serdeConstants
 import org.apache.hadoop.hive.serde2.objectinspector._
 import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.ObjectInspectorCopyOption
@@ -123,36 +120,6 @@ case class HiveTableScanExec(
 
     HiveShim.appendReadColumns(hiveConf, neededColumnIDs, output.map(_.name))
 
-    logInfo(s"Test ADD JAR  ${SessionState.get()}")
-    if (SessionState.get() != null) {
-      logInfo(s"Test ADD JAR  ${SessionState.get().getConf.getClassLoader}")
-      logInfo("Test ADD JAR with SessionState.getConf.getClassLoader")
-      // scalastyle:off
-      try {
-        Class.forName(tableDesc.getSerdeClassName(), true, SessionState.get().getConf.getClassLoader)
-      } catch {
-        case e:Exception =>
-          logInfo("Failed Test ADD JAR with SessionState.getConf.getClassLoader")
-      }
-    }
-
-    logInfo(s"JavaUtils.getClassLoader => ${JavaUtils.getClassLoader}")
-    logInfo(s"SessionState.SharedState.jarClssLoader => ${sparkSession.sharedState.jarClassLoader}")
-    logInfo("Test ADD JAR with sharedState's JarClassloader")
-    // scalastyle:off
-    try {
-      Class.forName(tableDesc.getSerdeClassName(), true, sparkSession.sharedState.jarClassLoader)
-    } catch {
-      case e: Exception =>
-        logInfo("Failed Test ADD JAR with sharedState's JarClassloader")
-    }
-    logInfo("Test ADD JAR with JavaUtils.getClassLoader")
-    try {
-      Class.forName(tableDesc.getSerdeClassName(), true, JavaUtils.getClassLoader)
-    } catch {
-      case e: Exception =>
-        logInfo("Failed Test ADD JAR with JavaUtils.getClassLoader")
-    }
     val deserializer = tableDesc.getDeserializerClass.getConstructor().newInstance()
     deserializer.initialize(hiveConf, tableDesc.getProperties)
 

From 6dc61e75fa4fd8c93be0c9b0ef540af1b9ab689a Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Wed, 18 Sep 2019 15:10:02 +0800
Subject: [PATCH 03/14] TEST-SPARK-29015

---
 .../sql/hive/thriftserver/CliSuite.scala      | 55 +++++++++++++++++++
 .../sql/hive/client/HiveClientImpl.scala      |  7 +++
 2 files changed, 62 insertions(+)

diff --git a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
index 6d45041e1282..5af6b3669b91 100644
--- a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
+++ b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
@@ -227,6 +227,34 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging {
     )
   }
 
+  test("Commands using SerDe provided jars in conf hive.aux.jars.path") {
+
+    val dataFilePath =
+      Thread.currentThread().getContextClassLoader.getResource("data/files/small_kv.txt")
+    val hiveContribJar = HiveTestUtils.getHiveContribJar.getCanonicalPath
+
+    runCliWithin(
+      3.minute,
+      Seq("--conf", s"spark.hadoop.${ConfVars.HIVEAUXJARS}=$hiveContribJar"))(
+      """CREATE TABLE addJarWithHiveAux(key string, val string)
+        |ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe';
+      """.stripMargin
+        -> "",
+      "CREATE TABLE sourceTableForWithHiveAux (key INT, val STRING);"
+        -> "",
+      s"LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE sourceTableForWithHiveAux;"
+        -> "",
+      "INSERT INTO TABLE addJarWithHiveAux SELECT key, val FROM sourceTableForWithHiveAux;"
+        -> "",
+      "SELECT collect_list(array(val)) FROM addJarWithHiveAux;"
+        -> """[["val_238"],["val_86"],["val_311"],["val_27"],["val_165"]]""",
+      "DROP TABLE addJarWithHiveAux;"
+        -> "",
+      "DROP TABLE sourceTableForWithHiveAux;"
+        -> ""
+    )
+  }
+
   test("SPARK-11188 Analysis error reporting") {
     runCliWithin(timeout = 2.minute,
       errorResponses = Seq("AnalysisException"))(
@@ -332,4 +360,31 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging {
       "SELECT concat_ws(',', 'First', example_max(1234321), 'Third');" -> "First,1234321,Third"
     )
   }
+
+  test("SPARK-29022 Commands using SerDe provided in ADD JAR sql") {
+    val dataFilePath =
+      Thread.currentThread().getContextClassLoader.getResource("data/files/small_kv.txt")
+    val hiveContribJar = HiveTestUtils.getHiveContribJar.getCanonicalPath
+
+    runCliWithin(
+      3.minute)(
+      s"ADD JAR ${hiveContribJar};" -> "",
+      """CREATE TABLE addJarWithSQL(key string, val string)
+        |ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe';
+      """.stripMargin
+        -> "",
+      "CREATE TABLE sourceTableForWithSQL(key INT, val STRING);"
+        -> "",
+      s"LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE sourceTableForWithSQL;"
+        -> "",
+      "INSERT INTO TABLE addJarWithSQL SELECT key, val FROM sourceTableForWithSQL;"
+        -> "",
+      "SELECT collect_list(array(val)) FROM addJarWithSQL;"
+        -> """[["val_238"],["val_86"],["val_311"],["val_27"],["val_165"]]""",
+      "DROP TABLE addJarWithSQL;"
+        -> "",
+      "DROP TABLE sourceTableForWithSQL;"
+        -> ""
+    )
+  }
 }
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
index 96e61bd54280..e3a8afa0f590 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
@@ -145,6 +145,13 @@ private[hive] class HiveClientImpl(
         warehouseDir.foreach { dir =>
           ret.getConf.setVar(ConfVars.METASTOREWAREHOUSE, dir)
         }
+        // ret != null means we have a CliSessionState instance in current thread which initialized
+        // by SparkSQLCLIDriver. The class loader of CliSessionState's conf is current main thread's
+        // class loader used to load jars passed by --jars. One class loader used by AddJarCommand
+        // is clientLoader.classLoader which contain jar path passed by --jars in main thread.
+        // We set CliSessionState's conf class loader to clientLoader.classLoader. Thus we can load
+        // all jars passed by --jars and AddJarCommand.
+        ret.getConf.setClassLoader(clientLoader.classLoader)
         ret
       } else {
         newState()

From f087b10954a660192826b7b170891d5ac1dd9401 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Wed, 18 Sep 2019 15:10:23 +0800
Subject: [PATCH 04/14] Revert "TEST-SPARK-29015"

This reverts commit 6dc61e75fa4fd8c93be0c9b0ef540af1b9ab689a.
---
 .../sql/hive/thriftserver/CliSuite.scala      | 55 -------------------
 .../sql/hive/client/HiveClientImpl.scala      |  7 ---
 2 files changed, 62 deletions(-)

diff --git a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
index 5af6b3669b91..6d45041e1282 100644
--- a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
+++ b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/CliSuite.scala
@@ -227,34 +227,6 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging {
     )
   }
 
-  test("Commands using SerDe provided jars in conf hive.aux.jars.path") {
-
-    val dataFilePath =
-      Thread.currentThread().getContextClassLoader.getResource("data/files/small_kv.txt")
-    val hiveContribJar = HiveTestUtils.getHiveContribJar.getCanonicalPath
-
-    runCliWithin(
-      3.minute,
-      Seq("--conf", s"spark.hadoop.${ConfVars.HIVEAUXJARS}=$hiveContribJar"))(
-      """CREATE TABLE addJarWithHiveAux(key string, val string)
-        |ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe';
-      """.stripMargin
-        -> "",
-      "CREATE TABLE sourceTableForWithHiveAux (key INT, val STRING);"
-        -> "",
-      s"LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE sourceTableForWithHiveAux;"
-        -> "",
-      "INSERT INTO TABLE addJarWithHiveAux SELECT key, val FROM sourceTableForWithHiveAux;"
-        -> "",
-      "SELECT collect_list(array(val)) FROM addJarWithHiveAux;"
-        -> """[["val_238"],["val_86"],["val_311"],["val_27"],["val_165"]]""",
-      "DROP TABLE addJarWithHiveAux;"
-        -> "",
-      "DROP TABLE sourceTableForWithHiveAux;"
-        -> ""
-    )
-  }
-
   test("SPARK-11188 Analysis error reporting") {
     runCliWithin(timeout = 2.minute,
       errorResponses = Seq("AnalysisException"))(
@@ -360,31 +332,4 @@ class CliSuite extends SparkFunSuite with BeforeAndAfterAll with Logging {
       "SELECT concat_ws(',', 'First', example_max(1234321), 'Third');" -> "First,1234321,Third"
     )
   }
-
-  test("SPARK-29022 Commands using SerDe provided in ADD JAR sql") {
-    val dataFilePath =
-      Thread.currentThread().getContextClassLoader.getResource("data/files/small_kv.txt")
-    val hiveContribJar = HiveTestUtils.getHiveContribJar.getCanonicalPath
-
-    runCliWithin(
-      3.minute)(
-      s"ADD JAR ${hiveContribJar};" -> "",
-      """CREATE TABLE addJarWithSQL(key string, val string)
-        |ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe';
-      """.stripMargin
-        -> "",
-      "CREATE TABLE sourceTableForWithSQL(key INT, val STRING);"
-        -> "",
-      s"LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE sourceTableForWithSQL;"
-        -> "",
-      "INSERT INTO TABLE addJarWithSQL SELECT key, val FROM sourceTableForWithSQL;"
-        -> "",
-      "SELECT collect_list(array(val)) FROM addJarWithSQL;"
-        -> """[["val_238"],["val_86"],["val_311"],["val_27"],["val_165"]]""",
-      "DROP TABLE addJarWithSQL;"
-        -> "",
-      "DROP TABLE sourceTableForWithSQL;"
-        -> ""
-    )
-  }
 }
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
index e3a8afa0f590..96e61bd54280 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
@@ -145,13 +145,6 @@ private[hive] class HiveClientImpl(
         warehouseDir.foreach { dir =>
           ret.getConf.setVar(ConfVars.METASTOREWAREHOUSE, dir)
         }
-        // ret != null means we have a CliSessionState instance in current thread which initialized
-        // by SparkSQLCLIDriver. The class loader of CliSessionState's conf is current main thread's
-        // class loader used to load jars passed by --jars. One class loader used by AddJarCommand
-        // is clientLoader.classLoader which contain jar path passed by --jars in main thread.
-        // We set CliSessionState's conf class loader to clientLoader.classLoader. Thus we can load
-        // all jars passed by --jars and AddJarCommand.
-        ret.getConf.setClassLoader(clientLoader.classLoader)
         ret
       } else {
         newState()

From 5aa2ed67e74aaae69fea4b996588ec5196828857 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Fri, 20 Sep 2019 00:01:09 +0800
Subject: [PATCH 05/14] SUPPORT IN/EXISTS in join condition

---
 .../spark/sql/catalyst/analysis/Analyzer.scala     |  2 ++
 .../sql/catalyst/analysis/CheckAnalysis.scala      |  4 ++--
 .../catalyst/analysis/ResolveSubquerySuite.scala   | 14 +++++++++++++-
 3 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
index 76e59fa78542..81af81a30490 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
@@ -1761,6 +1761,8 @@ class Analyzer(
         resolveSubQueries(q, q.children)
       case d: DeleteFromTable if d.childrenResolved =>
         resolveSubQueries(d, d.children)
+      case j: Join if j.childrenResolved =>
+        resolveSubQueries(j, Seq(j, j.left, j.right))
     }
   }
 
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index 4a19806bd80f..2a6b33529604 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -596,9 +596,9 @@ trait CheckAnalysis extends PredicateHelper {
 
       case inSubqueryOrExistsSubquery =>
         plan match {
-          case _: Filter | _: DeleteFromTable => // Ok
+          case _: Filter | _: DeleteFromTable | _: Join => // Ok
           case _ =>
-            failAnalysis(s"IN/EXISTS predicate sub-queries can only be used in" +
+            failAnalysis(s"IN/EXISTS/JOIN predicate sub-queries can only be used in" +
                 s" Filter/DeleteFromTable: $plan")
         }
     }
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
index 74a8590b5eef..49393ee21381 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
@@ -20,7 +20,8 @@ package org.apache.spark.sql.catalyst.analysis
 import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.expressions.{InSubquery, ListQuery}
-import org.apache.spark.sql.catalyst.plans.logical.{Filter, LocalRelation, Project}
+import org.apache.spark.sql.catalyst.plans.logical.{Filter, Join, LocalRelation, Project}
+import org.apache.spark.sql.catalyst.plans.Inner
 
 /**
  * Unit tests for [[ResolveSubquery]].
@@ -29,8 +30,10 @@ class ResolveSubquerySuite extends AnalysisTest {
 
   val a = 'a.int
   val b = 'b.int
+  val c = 'c.int
   val t1 = LocalRelation(a)
   val t2 = LocalRelation(b)
+  val t3 = LocalRelation(c)
 
   test("SPARK-17251 Improve `OuterReference` to be `NamedExpression`") {
     val expr = Filter(
@@ -41,4 +44,13 @@ class ResolveSubquerySuite extends AnalysisTest {
     assert(m.contains(
       "Expressions referencing the outer query are not supported outside of WHERE/HAVING clauses"))
   }
+
+  test("SPARK-29145 Support subquery in join condition") {
+    val expr = Join(t1,
+      t2,
+      Inner,
+      Some(InSubquery(Seq(a), ListQuery(Project(Seq(UnresolvedAttribute("c")), t3)))),
+      null)
+    assertAnalysisSuccess(expr)
+  }
 }

From fa55b3ab2783972c55ae0c8c21aed88fe1b1c220 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Fri, 20 Sep 2019 07:51:15 +0800
Subject: [PATCH 06/14] fix scala style

---
 .../spark/sql/catalyst/analysis/ResolveSubquerySuite.scala      | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
index 49393ee21381..505e1a3ac6ba 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
@@ -20,8 +20,8 @@ package org.apache.spark.sql.catalyst.analysis
 import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.expressions.{InSubquery, ListQuery}
-import org.apache.spark.sql.catalyst.plans.logical.{Filter, Join, LocalRelation, Project}
 import org.apache.spark.sql.catalyst.plans.Inner
+import org.apache.spark.sql.catalyst.plans.logical.{Filter, Join, LocalRelation, Project}
 
 /**
  * Unit tests for [[ResolveSubquery]].

From bd7c0981c977f23e8e50acac88aa9be0eac2bd1c Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Fri, 20 Sep 2019 10:07:36 +0800
Subject: [PATCH 07/14] add end-to-end test

---
 .../org/apache/spark/sql/SubquerySuite.scala  | 24 +++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
index a1d7792941ed..be425ea69909 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
@@ -204,6 +204,30 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
     }
   }
 
+  test("SPARK-29145: JOIN Condition use QueryList") {
+    withTempView("s1", "s2", "s3") {
+      Seq(1, 3, 5, 7, 9).toDF("id").createOrReplaceTempView("s1")
+      Seq(1, 3, 4, 6, 9).toDF("id").createOrReplaceTempView("s2")
+      Seq(3, 4, 6, 9).toDF("id").createOrReplaceTempView("s3")
+
+      checkAnswer(
+        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id IN (select 9)"),
+        Row(9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id NOT IN (select 9)"),
+        Row(1) :: Row(3) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        Row(3) :: Row(9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        Row(1) :: Nil)
+    }
+  }
+
   test("SPARK-14791: scalar subquery inside broadcast join") {
     val df = sql("select a, sum(b) as s from l group by a having a > (select avg(a) from l)")
     val expected = Row(3, 2.0, 3, 3.0) :: Row(6, null, 6, null) :: Nil

From dd37df8c6bfe47187233eb01fec04f63ff71245b Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Tue, 15 Oct 2019 18:30:34 +0800
Subject: [PATCH 08/14] remove DeleteFromTable

---
 .../scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala | 2 --
 .../org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala  | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
index 18ba5f02a3d4..2434192c63e2 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
@@ -1696,8 +1696,6 @@ class Analyzer(
       // Only a few unary nodes (Project/Filter/Aggregate) can contain subqueries.
       case q: UnaryNode if q.childrenResolved =>
         resolveSubQueries(q, q.children)
-      case d: DeleteFromTable if d.childrenResolved =>
-        resolveSubQueries(d, d.children)
       case j: Join if j.childrenResolved =>
         resolveSubQueries(j, Seq(j, j.left, j.right))
       case s: SupportsSubquery if s.childrenResolved =>
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index abd75cfe87a3..4a9e4f9f6fe8 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -602,7 +602,7 @@ trait CheckAnalysis extends PredicateHelper {
 
       case inSubqueryOrExistsSubquery =>
         plan match {
-          case _: Filter | _: DeleteFromTable | _: SupportsSubquery |_: Join  => // Ok
+          case _: Filter | _: SupportsSubquery |_: Join  => // Ok
           case _ =>
             failAnalysis(s"IN/EXISTS predicate sub-queries can only be used in" +
                 s" Filter and a few commands: $plan")

From 6b58893bd7ea8bab8941939997288616aeab1353 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Tue, 15 Oct 2019 18:33:21 +0800
Subject: [PATCH 09/14] fix scala style

---
 .../org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala  | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index 4a9e4f9f6fe8..0f86519a32e1 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -602,7 +602,7 @@ trait CheckAnalysis extends PredicateHelper {
 
       case inSubqueryOrExistsSubquery =>
         plan match {
-          case _: Filter | _: SupportsSubquery |_: Join  => // Ok
+          case _: Filter | _: SupportsSubquery | _: Join => // Ok
           case _ =>
             failAnalysis(s"IN/EXISTS predicate sub-queries can only be used in" +
                 s" Filter and a few commands: $plan")

From 25f31dc54fc71bb9ce2c65632a84736cc49d3a13 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Wed, 16 Oct 2019 14:16:55 +0800
Subject: [PATCH 10/14] fllow comment

---
 .../org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala  | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index 0f86519a32e1..e4167fd64596 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -605,7 +605,7 @@ trait CheckAnalysis extends PredicateHelper {
           case _: Filter | _: SupportsSubquery | _: Join => // Ok
           case _ =>
             failAnalysis(s"IN/EXISTS predicate sub-queries can only be used in" +
-                s" Filter and a few commands: $plan")
+                s" Filter/SupportsSubquery/Join and a few commands: $plan")
         }
     }
 

From 2ead3780f1b32d5223afff3fce4eacee6cba7628 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Wed, 23 Oct 2019 13:52:07 +0800
Subject: [PATCH 11/14] follow comment

---
 .../apache/spark/sql/catalyst/analysis/CheckAnalysis.scala    | 2 +-
 .../spark/sql/catalyst/analysis/ResolveSubquerySuite.scala    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index e4167fd64596..f036d822c5f4 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -605,7 +605,7 @@ trait CheckAnalysis extends PredicateHelper {
           case _: Filter | _: SupportsSubquery | _: Join => // Ok
           case _ =>
             failAnalysis(s"IN/EXISTS predicate sub-queries can only be used in" +
-                s" Filter/SupportsSubquery/Join and a few commands: $plan")
+                s" Filter/Join and a few commands: $plan")
         }
     }
 
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
index 505e1a3ac6ba..5aa80e1a9bd7 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/ResolveSubquerySuite.scala
@@ -21,7 +21,7 @@ import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.dsl.expressions._
 import org.apache.spark.sql.catalyst.expressions.{InSubquery, ListQuery}
 import org.apache.spark.sql.catalyst.plans.Inner
-import org.apache.spark.sql.catalyst.plans.logical.{Filter, Join, LocalRelation, Project}
+import org.apache.spark.sql.catalyst.plans.logical._
 
 /**
  * Unit tests for [[ResolveSubquery]].
@@ -50,7 +50,7 @@ class ResolveSubquerySuite extends AnalysisTest {
       t2,
       Inner,
       Some(InSubquery(Seq(a), ListQuery(Project(Seq(UnresolvedAttribute("c")), t3)))),
-      null)
+      JoinHint.NONE)
     assertAnalysisSuccess(expr)
   }
 }

From 3db4aaf0648122cc1498e9af71be47c3013903c9 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Wed, 23 Oct 2019 18:24:04 +0800
Subject: [PATCH 12/14] Add more UT case

---
 .../org/apache/spark/sql/SubquerySuite.scala  | 54 +++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
index be425ea69909..919dd691cdba 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
@@ -218,13 +218,67 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
         sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id NOT IN (select 9)"),
         Row(1) :: Row(3) :: Nil)
 
+      // case `IN`
       checkAnswer(
         sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id IN (select id from s3)"),
         Row(3) :: Row(9) :: Nil)
 
+      checkAnswer(
+        sql("SELECT s1.id as id2 from s1 LEFT SEMI JOIN s2 " +
+          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        Row(3) :: Row(9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id as id2 from s1 LEFT ANTI JOIN s2 " +
+          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        Row(1) :: Row(5) :: Row(7) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id, s2.id as id2 from s1 LEFT OUTER JOIN s2 " +
+          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        Row(1, null) :: Row(3, 3) :: Row(5, null) :: Row(7, null) :: Row(9, 9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id, s2.id as id2 from s1 RIGHT OUTER JOIN s2 " +
+          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        Row(null, 1) :: Row(3, 3) :: Row(null, 4) :: Row(null, 6) :: Row(9, 9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id, s2.id as id2 from s1 FULL OUTER JOIN s2 " +
+          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        Row(1, null) :: Row(3, 3) :: Row(5, null) :: Row(7, null) :: Row(9, 9) ::
+          Row(null, 1) :: Row(null, 4) :: Row(null, 6) :: Nil)
+
+      // case `NOT IN`
       checkAnswer(
         sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
         Row(1) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id as id2 from s1 LEFT SEMI JOIN s2 " +
+          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        Row(1) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id as id2 from s1 LEFT ANTI JOIN s2 " +
+          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        Row(3) :: Row(5) :: Row(7) :: Row(9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id, s2.id as id2 from s1 LEFT OUTER JOIN s2 " +
+          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        Row(1, 1) :: Row(3, null) :: Row(5, null) :: Row(7, null) :: Row(9, null) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id, s2.id as id2 from s1 RIGHT OUTER JOIN s2 " +
+          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        Row(1, 1) :: Row(null, 3) :: Row(null, 4) :: Row(null, 6) :: Row(null, 9) :: Nil)
+
+      checkAnswer(
+        sql("SELECT s1.id, s2.id as id2 from s1 FULL OUTER JOIN s2 " +
+          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        Row(1, 1) :: Row(3, null) :: Row(5, null) :: Row(7, null) :: Row(9, null) ::
+          Row(null, 3) :: Row(null, 4) :: Row(null, 6) :: Row(null, 9) :: Nil)
     }
   }
 

From 4ba7a174873bcde6e2251e135a17c8ec97f8ea87 Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Thu, 24 Oct 2019 13:26:03 +0800
Subject: [PATCH 13/14] make test case sql clear

---
 .../org/apache/spark/sql/SubquerySuite.scala  | 104 ++++++++++++++----
 1 file changed, 80 insertions(+), 24 deletions(-)

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
index 919dd691cdba..bf65cd630815 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
@@ -211,72 +211,128 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
       Seq(3, 4, 6, 9).toDF("id").createOrReplaceTempView("s3")
 
       checkAnswer(
-        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id IN (select 9)"),
+        sql(
+          """
+            | SELECT s1.id FROM s1
+            | JOIN s2 ON s1.id = s2.id
+            | AND s1.id IN (SELECT 9)""".stripMargin),
         Row(9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id NOT IN (select 9)"),
+        sql(
+          """
+            | SELECT s1.id FROM s1
+            | JOIN s2 ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT 9)""".stripMargin),
         Row(1) :: Row(3) :: Nil)
 
       // case `IN`
       checkAnswer(
-        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id FROM s1
+            | JOIN s2 ON s1.id = s2.id
+            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
         Row(3) :: Row(9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id as id2 from s1 LEFT SEMI JOIN s2 " +
-          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id AS id2 FROM s1
+            | LEFT SEMI JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
         Row(3) :: Row(9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id as id2 from s1 LEFT ANTI JOIN s2 " +
-          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id as id2 FROM s1
+            | LEFT ANTI JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
         Row(1) :: Row(5) :: Row(7) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id, s2.id as id2 from s1 LEFT OUTER JOIN s2 " +
-          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id, s2.id as id2 FROM s1
+            | LEFT OUTER JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
         Row(1, null) :: Row(3, 3) :: Row(5, null) :: Row(7, null) :: Row(9, 9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id, s2.id as id2 from s1 RIGHT OUTER JOIN s2 " +
-          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id, s2.id as id2 FROM s1
+            | RIGHT OUTER JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
         Row(null, 1) :: Row(3, 3) :: Row(null, 4) :: Row(null, 6) :: Row(9, 9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id, s2.id as id2 from s1 FULL OUTER JOIN s2 " +
-          "ON s1.id = s2.id and s1.id IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id, s2.id AS id2 FROM s1
+            | FULL OUTER JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
         Row(1, null) :: Row(3, 3) :: Row(5, null) :: Row(7, null) :: Row(9, 9) ::
           Row(null, 1) :: Row(null, 4) :: Row(null, 6) :: Nil)
 
       // case `NOT IN`
       checkAnswer(
-        sql("SELECT s1.id from s1 JOIN s2 ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id FROM s1
+            | JOIN s2 ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
         Row(1) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id as id2 from s1 LEFT SEMI JOIN s2 " +
-          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id AS id2 FROM s1
+            | LEFT SEMI JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
         Row(1) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id as id2 from s1 LEFT ANTI JOIN s2 " +
-          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id AS id2 FROM s1
+            | LEFT ANTI JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
         Row(3) :: Row(5) :: Row(7) :: Row(9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id, s2.id as id2 from s1 LEFT OUTER JOIN s2 " +
-          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id, s2.id AS id2 FROM s1
+            | LEFT OUTER JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
         Row(1, 1) :: Row(3, null) :: Row(5, null) :: Row(7, null) :: Row(9, null) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id, s2.id as id2 from s1 RIGHT OUTER JOIN s2 " +
-          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id, s2.id AS id2 FROM s1
+            | RIGHT OUTER JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
         Row(1, 1) :: Row(null, 3) :: Row(null, 4) :: Row(null, 6) :: Row(null, 9) :: Nil)
 
       checkAnswer(
-        sql("SELECT s1.id, s2.id as id2 from s1 FULL OUTER JOIN s2 " +
-          "ON s1.id = s2.id and s1.id NOT IN (select id from s3)"),
+        sql(
+          """
+            | SELECT s1.id, s2.id AS id2 FROM s1
+            | FULL OUTER JOIN s2
+            | ON s1.id = s2.id
+            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
         Row(1, 1) :: Row(3, null) :: Row(5, null) :: Row(7, null) :: Row(9, null) ::
           Row(null, 3) :: Row(null, 4) :: Row(null, 6) :: Row(null, 9) :: Nil)
     }

From 307802a5e599fadfafc9fb4ffe2ccbd10d60f6ba Mon Sep 17 00:00:00 2001
From: angerszhu <angers.zhu@gmail.com>
Date: Thu, 24 Oct 2019 13:29:17 +0800
Subject: [PATCH 14/14] format code

---
 .../org/apache/spark/sql/SubquerySuite.scala  | 42 ++++++++++++-------
 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
index bf65cd630815..266f8e23712d 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala
@@ -215,7 +215,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
           """
             | SELECT s1.id FROM s1
             | JOIN s2 ON s1.id = s2.id
-            | AND s1.id IN (SELECT 9)""".stripMargin),
+            | AND s1.id IN (SELECT 9)
+          """.stripMargin),
         Row(9) :: Nil)
 
       checkAnswer(
@@ -223,7 +224,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
           """
             | SELECT s1.id FROM s1
             | JOIN s2 ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT 9)""".stripMargin),
+            | AND s1.id NOT IN (SELECT 9)
+          """.stripMargin),
         Row(1) :: Row(3) :: Nil)
 
       // case `IN`
@@ -232,7 +234,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
           """
             | SELECT s1.id FROM s1
             | JOIN s2 ON s1.id = s2.id
-            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(3) :: Row(9) :: Nil)
 
       checkAnswer(
@@ -241,7 +244,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id AS id2 FROM s1
             | LEFT SEMI JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(3) :: Row(9) :: Nil)
 
       checkAnswer(
@@ -250,7 +254,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id as id2 FROM s1
             | LEFT ANTI JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1) :: Row(5) :: Row(7) :: Nil)
 
       checkAnswer(
@@ -259,7 +264,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id, s2.id as id2 FROM s1
             | LEFT OUTER JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1, null) :: Row(3, 3) :: Row(5, null) :: Row(7, null) :: Row(9, 9) :: Nil)
 
       checkAnswer(
@@ -268,7 +274,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id, s2.id as id2 FROM s1
             | RIGHT OUTER JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(null, 1) :: Row(3, 3) :: Row(null, 4) :: Row(null, 6) :: Row(9, 9) :: Nil)
 
       checkAnswer(
@@ -277,7 +284,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id, s2.id AS id2 FROM s1
             | FULL OUTER JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1, null) :: Row(3, 3) :: Row(5, null) :: Row(7, null) :: Row(9, 9) ::
           Row(null, 1) :: Row(null, 4) :: Row(null, 6) :: Nil)
 
@@ -287,7 +295,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
           """
             | SELECT s1.id FROM s1
             | JOIN s2 ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id NOT IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1) :: Nil)
 
       checkAnswer(
@@ -296,7 +305,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id AS id2 FROM s1
             | LEFT SEMI JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id NOT IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1) :: Nil)
 
       checkAnswer(
@@ -305,7 +315,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id AS id2 FROM s1
             | LEFT ANTI JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id NOT IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(3) :: Row(5) :: Row(7) :: Row(9) :: Nil)
 
       checkAnswer(
@@ -314,7 +325,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id, s2.id AS id2 FROM s1
             | LEFT OUTER JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id NOT IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1, 1) :: Row(3, null) :: Row(5, null) :: Row(7, null) :: Row(9, null) :: Nil)
 
       checkAnswer(
@@ -323,7 +335,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id, s2.id AS id2 FROM s1
             | RIGHT OUTER JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id NOT IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1, 1) :: Row(null, 3) :: Row(null, 4) :: Row(null, 6) :: Row(null, 9) :: Nil)
 
       checkAnswer(
@@ -332,7 +345,8 @@ class SubquerySuite extends QueryTest with SharedSparkSession {
             | SELECT s1.id, s2.id AS id2 FROM s1
             | FULL OUTER JOIN s2
             | ON s1.id = s2.id
-            | AND s1.id NOT IN (SELECT id FROM s3)""".stripMargin),
+            | AND s1.id NOT IN (SELECT id FROM s3)
+          """.stripMargin),
         Row(1, 1) :: Row(3, null) :: Row(5, null) :: Row(7, null) :: Row(9, null) ::
           Row(null, 3) :: Row(null, 4) :: Row(null, 6) :: Row(null, 9) :: Nil)
     }