This is an automated email from the ASF dual-hosted git repository. dongjoon pushed a commit to branch branch-3.5 in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.5 by this push: new dbb61981b80 [SPARK-45580][SQL][3.5] Handle case where a nested subquery becomes an existence join dbb61981b80 is described below commit dbb61981b804dbc03cf140c7c76653348e2ac740 Author: Bruce Robbins <bersprock...@gmail.com> AuthorDate: Wed Dec 6 15:24:48 2023 -0800 [SPARK-45580][SQL][3.5] Handle case where a nested subquery becomes an existence join ### What changes were proposed in this pull request? This is a back-port of #44193. In `RewritePredicateSubquery`, prune existence flags from the final join when `rewriteExistentialExpr` returns an existence join. This change prunes the flags (attributes with the name "exists") by adding a `Project` node. For example: ``` Join LeftSemi, ((a#13 = c1#15) OR exists#19) :- Join ExistenceJoin(exists#19), (a#13 = col1#17) : :- LocalRelation [a#13] : +- LocalRelation [col1#17] +- LocalRelation [c1#15] ``` becomes ``` Project [a#13] +- Join LeftSemi, ((a#13 = c1#15) OR exists#19) :- Join ExistenceJoin(exists#19), (a#13 = col1#17) : :- LocalRelation [a#13] : +- LocalRelation [col1#17] +- LocalRelation [c1#15] ``` This change always adds the `Project` node, whether `rewriteExistentialExpr` returns an existence join or not. In the case when `rewriteExistentialExpr` does not return an existence join, `RemoveNoopOperators` will remove the unneeded `Project` node. ### Why are the changes needed? This query returns an extraneous boolean column when run in spark-sql: ``` create or replace temp view t1(a) as values (1), (2), (3), (7); create or replace temp view t2(c1) as values (1), (2), (3); create or replace temp view t3(col1) as values (3), (9); select * from t1 where exists ( select c1 from t2 where a = c1 or a in (select col1 from t3) ); 1 false 2 false 3 true ``` (Note: the above query will not have the extraneous boolean column when run from the Dataset API. That is because the Dataset API truncates the rows based on the schema of the analyzed plan. The bug occurs during optimization). This query fails when run in either spark-sql or using the Dataset API: ``` select ( select * from t1 where exists ( select c1 from t2 where a = c1 or a in (select col1 from t3) ) limit 1 ) from range(1); java.lang.AssertionError: assertion failed: Expects 1 field, but got 2; something went wrong in analysis ``` ### Does this PR introduce _any_ user-facing change? No, except for the removal of the extraneous boolean flag and the fix to the error condition. ### How was this patch tested? New unit test. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #44215 from bersprockets/schema_change_br35. Authored-by: Bruce Robbins <bersprock...@gmail.com> Signed-off-by: Dongjoon Hyun <dh...@apple.com> --- .../spark/sql/catalyst/optimizer/subquery.scala | 9 +++-- .../scala/org/apache/spark/sql/SubquerySuite.scala | 46 ++++++++++++++++++++++ 2 files changed, 52 insertions(+), 3 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala index 91cd838ad61..ee200531578 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/subquery.scala @@ -118,16 +118,19 @@ object RewritePredicateSubquery extends Rule[LogicalPlan] with PredicateHelper { withSubquery.foldLeft(newFilter) { case (p, Exists(sub, _, _, conditions, subHint)) => val (joinCond, outerPlan) = rewriteExistentialExpr(conditions, p) - buildJoin(outerPlan, sub, LeftSemi, joinCond, subHint) + val join = buildJoin(outerPlan, sub, LeftSemi, joinCond, subHint) + Project(p.output, join) case (p, Not(Exists(sub, _, _, conditions, subHint))) => val (joinCond, outerPlan) = rewriteExistentialExpr(conditions, p) - buildJoin(outerPlan, sub, LeftAnti, joinCond, subHint) + val join = buildJoin(outerPlan, sub, LeftAnti, joinCond, subHint) + Project(p.output, join) case (p, InSubquery(values, ListQuery(sub, _, _, _, conditions, subHint))) => // Deduplicate conflicting attributes if any. val newSub = dedupSubqueryOnSelfJoin(p, sub, Some(values)) val inConditions = values.zip(newSub.output).map(EqualTo.tupled) val (joinCond, outerPlan) = rewriteExistentialExpr(inConditions ++ conditions, p) - Join(outerPlan, newSub, LeftSemi, joinCond, JoinHint(None, subHint)) + val join = Join(outerPlan, newSub, LeftSemi, joinCond, JoinHint(None, subHint)) + Project(p.output, join) case (p, Not(InSubquery(values, ListQuery(sub, _, _, _, conditions, subHint)))) => // This is a NULL-aware (left) anti join (NAAJ) e.g. col NOT IN expr // Construct the condition. A NULL in one of the conditions is regarded as a positive 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 a7a0f6156cb..fbc256b3396 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 @@ -2736,4 +2736,50 @@ class SubquerySuite extends QueryTest Row(1, "a", 3) :: Row(2, "a", 3) :: Row(3, "a", 3) :: Nil) } } + + test("SPARK-45580: Handle case where a nested subquery becomes an existence join") { + withTempView("t1", "t2", "t3") { + Seq((1), (2), (3), (7)).toDF("a").persist().createOrReplaceTempView("t1") + Seq((1), (2), (3)).toDF("c1").persist().createOrReplaceTempView("t2") + Seq((3), (9)).toDF("col1").persist().createOrReplaceTempView("t3") + + val query1 = + """ + |SELECT * + |FROM t1 + |WHERE EXISTS ( + | SELECT c1 + | FROM t2 + | WHERE a = c1 + | OR a IN (SELECT col1 FROM t3) + |)""".stripMargin + val df1 = sql(query1) + checkAnswer(df1, Row(1) :: Row(2) :: Row(3) :: Nil) + + val query2 = + """ + |SELECT * + |FROM t1 + |WHERE a IN ( + | SELECT c1 + | FROM t2 + | where a IN (SELECT col1 FROM t3) + |)""".stripMargin + val df2 = sql(query2) + checkAnswer(df2, Row(3)) + + val query3 = + """ + |SELECT * + |FROM t1 + |WHERE NOT EXISTS ( + | SELECT c1 + | FROM t2 + | WHERE a = c1 + | OR a IN (SELECT col1 FROM t3) + |)""".stripMargin + val df3 = sql(query3) + checkAnswer(df3, Row(7)) + } + } } --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org