[GitHub] [spark] allisonwang-db commented on a diff in pull request #36689: [SPARK-39306][SQL] Support scalar subquery in time travel

[GitBox <gi...@apache.org>]

allisonwang-db commented on code in PR #36689:
URL: https://github.com/apache/spark/pull/36689#discussion_r883231536


##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/PlanParserSuite.scala:
##########
@@ -1296,10 +1296,15 @@ class PlanParserSuite extends AnalysisTest {
         Some(UnresolvedFunction(Seq("current_date"), Nil, isDistinct = false)),
         None)))
 
+    testTimestamp("(SELECT current_date())", Project(Seq(UnresolvedStar(None)),
+      RelationTimeTravel(
+        UnresolvedRelation(Seq("a", "b", "c")),
+        Some(ScalarSubquery(Project(UnresolvedAlias(UnresolvedFunction(
+          Seq("current_date"), Nil, isDistinct = false)) :: Nil, OneRowRelation()))),
+        None)))
+
     intercept("SELECT * FROM a.b.c TIMESTAMP AS OF col",
       "timestamp expression cannot refer to any columns")
-    intercept("SELECT * FROM a.b.c TIMESTAMP AS OF (select 1)",

Review Comment:
   Not sure if it's possible but what if it's an IN or EXISTS subquery?



##########
sql/core/src/test/scala/org/apache/spark/sql/connector/DataSourceV2SQLSuite.scala:
##########
@@ -2752,6 +2758,22 @@ class DataSourceV2SQLSuite
         sql("WITH x AS (SELECT 1) SELECT * FROM x VERSION AS OF 1")
       )
       assert(e7.message.contains("Cannot time travel subqueries from WITH clause"))
+
+      def checkSubqueryError(subquery: String, errMsg: String): Unit = {
+        val e1 = intercept[Exception](
+          sql(s"SELECT * FROM t TIMESTAMP AS OF ($subquery)").collect()
+        )
+        assert(e1.getMessage.contains(errMsg))
+        // Nested subquery should also report error correctly.
+        val e2 = intercept[Exception](
+          sql(s"SELECT * FROM t TIMESTAMP AS OF (SELECT ($subquery))").collect()
+        )
+        assert(e2.getMessage.contains(errMsg))
+      }
+      checkSubqueryError("SELECT 1 FROM non_exist", "Table or view not found: non_exist")
+      checkSubqueryError("SELECT col", "MISSING_COLUMN")
+      checkSubqueryError("SELECT 1, 2", "Scalar subquery must return only one column")
+      checkSubqueryError("SELECT * FROM VALUES (1), (2)", "MULTI_VALUE_SUBQUERY_ERROR")

Review Comment:
   Can we also add one more test for a correlated subquery?



##########
sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/EvalSubquerisForTimeTravel.scala:
##########
@@ -0,0 +1,60 @@
+/*
+ * 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.catalyst.analysis
+
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.expressions.{Literal, ScalarSubquery, SubqueryExpression}
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.catalyst.trees.TreePattern.RELATION_TIME_TRAVEL
+import org.apache.spark.sql.execution.{QueryExecution, ScalarSubquery => ScalarSubqueryExec, SubqueryExec}
+
+class EvalSubquerisForTimeTravel extends Rule[LogicalPlan] {

Review Comment:
   ```suggestion
   class EvalSubqueriesForTimeTravel extends Rule[LogicalPlan] {
   ```



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org