pratham76 commented on code in PR #58656:
URL: https://github.com/apache/spark/pull/58656#discussion_r4274291543
##########
sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala:
##########
@@ -3227,4 +3224,426 @@ class SubquerySuite extends SharedSparkSession
}
}
}
+
+ /**
+ * Checks the result of `query`, that every node of its optimized plan can
produce the attributes
+ * it references, and that the existence join a nested subquery was
rewritten into sits on the
+ * subquery side of the semi/anti join.
+ *
+ * The plan checks are what SPARK-59351 is about: an existence join whose
condition references an
+ * attribute produced by neither of its children can still return the right
answer when the
+ * nested relation is empty at runtime, because the invalid condition is
then never bound, and a
+ * rewrite that placed the join on the other side would return the right
answer here too. Note
+ * that missingInput cannot see a subquery expression that survives in a
condition, since
+ * QueryPlan.references folds only the outer attributes of one and collect
does not walk its
+ * plan, so it is not a substitute for asserting the shape.
+ */
+ private def checkAnswerAndPlan(
+ query: String,
+ expected: Seq[Row],
+ existenceJoinOnSubqueryPlan: Boolean = true): Unit = {
+ val df = sql(query)
+ val plan = df.queryExecution.optimizedPlan
+ val invalidNodes = plan.collect { case p if p.missingInput.nonEmpty => p }
+ assert(invalidNodes.isEmpty,
+ s"""Plan nodes reference non-reachable attributes:
+ |${invalidNodes.mkString("\n")}
+ |$plan""".stripMargin)
+ if (existenceJoinOnSubqueryPlan) {
+ val semiOrAnti = plan.collectFirst {
+ case j: Join if j.joinType == LeftSemi || j.joinType == LeftAnti => j
+ }
+ assert(semiOrAnti.nonEmpty, s"expected a semi or anti join in\n$plan")
+ val existenceJoins = plan.collect {
+ case j: Join if j.joinType.isInstanceOf[ExistenceJoin] => j
+ }
+ assert(existenceJoins.nonEmpty, s"expected an existence join in\n$plan")
+ // The existence join must be under the right side of the semi/anti
join, which is the
+ // subquery plan, and not under its left side, which is the outer plan.
+ assert(existenceJoins.forall(j =>
semiOrAnti.get.right.exists(_.fastEquals(j))),
+ s"the existence join must sit on the subquery side in\n$plan")
+ }
+ checkAnswer(df, expected)
+ }
+
+ test("SPARK-59351: nested subquery referencing the inner query becomes an
existence join") {
+ // SPARK-45580 covers the case where the nested subquery references the
outer query, in which
+ // case its existence join is built on top of the outer plan. Here the
nested subquery
+ // references the query it is nested in, so the existence join has to be
built on top of the
+ // subquery plan instead.
+ withTempView("t1", "t2", "t3", "t3n", "t4", "t5") {
+ Seq((1), (2), (3), (7),
(9)).toDF("a").persist().createOrReplaceTempView("t1")
+ Seq((1), (8), (9)).toDF("c1").persist().createOrReplaceTempView("t2")
+ // t3 shares a value with t2, t5 does not, so the nested subquery
decides the answer below.
+ Seq((3), (9)).toDF("col1").persist().createOrReplaceTempView("t3")
+ Seq((3), (7)).toDF("col1").persist().createOrReplaceTempView("t5")
+ Seq(Some(3), Some(9),
None).toDF("col1").persist().createOrReplaceTempView("t3n")
+ // A correlated nested IN over t4 is false for every c1 in t2, while the
same IN without its
+ // correlated predicate is true for 1 and 9, so the correlation decides
the answer below.
+ Seq((1, 9), (9, 1)).toDF("col1",
"k").persist().createOrReplaceTempView("t4")
+
+ // EXISTS rewritten as a left semi join. The correlated predicate is a
disjunction, so it
+ // is pulled up as a whole and carries the nested IN-subquery, which
references c1, out of
+ // the subquery plan.
+ val query1 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT c1
+ | FROM t2
+ | WHERE a = c1
+ | OR c1 IN (SELECT col1 FROM t3)
+ |)""".stripMargin
+ checkAnswerAndPlan(query1, Row(1) :: Row(2) :: Row(3) :: Row(7) ::
Row(9) :: Nil)
+
+ // Same over t5, which shares no value with t2, so the nested IN is
false for every c1 and
+ // only the correlated predicate can hold: a mistake making it true
would return every row.
+ val query2 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT c1
+ | FROM t2
+ | WHERE a = c1
+ | OR c1 IN (SELECT col1 FROM t5)
+ |)""".stripMargin
+ checkAnswerAndPlan(query2, Row(1) :: Row(9) :: Nil)
+
+ // NOT EXISTS rewritten as a left anti join.
+ val query3 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE NOT EXISTS (
+ | SELECT c1
+ | FROM t2
+ | WHERE a = c1
+ | OR c1 IN (SELECT col1 FROM t5)
+ |)""".stripMargin
+ checkAnswerAndPlan(query3, Row(2) :: Row(3) :: Row(7) :: Nil)
+
+ // IN-subquery rewritten as a left semi join. The hoisted predicate is a
> c1 rather than
+ // the key equality a = c1, so the answer is a IN (t2 INTERSECT t3) and
depends on the
+ // nested subquery: dropping it would leave no row at all.
+ val query4 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE a IN (
+ | SELECT c1
+ | FROM t2
+ | WHERE a > c1
+ | OR c1 IN (SELECT col1 FROM t3)
+ |)""".stripMargin
+ checkAnswerAndPlan(query4, Row(9) :: Nil)
+
+ // NOT IN-subquery rewritten as a null-aware left anti join, with a
nested EXISTS. Only the
+ // nested EXISTS keeps 9 out of the answer, as a > c1 alone does not
hold for it.
+ val query5 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE a NOT IN (
+ | SELECT c1
+ | FROM t2
+ | WHERE a > c1
+ | OR EXISTS (SELECT 1 FROM t3 WHERE col1 = c1)
+ |)""".stripMargin
+ checkAnswerAndPlan(query5, Row(1) :: Row(2) :: Row(3) :: Row(7) :: Nil)
+
+ // A nested NOT IN-subquery keeps its null-aware semantics: c1 NOT IN
(3, 9, NULL) is never
+ // true, so only the correlated predicate can be satisfied. Compare with
query7, where the
+ // same NOT IN over a relation without NULL holds for c1 = 1 and returns
every row.
+ val query6 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT c1
+ | FROM t2
+ | WHERE a = c1
+ | OR c1 NOT IN (SELECT col1 FROM t3n)
+ |)""".stripMargin
+ checkAnswerAndPlan(query6, Row(1) :: Row(9) :: Nil)
+
+ val query7 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT c1
+ | FROM t2
+ | WHERE a = c1
+ | OR c1 NOT IN (SELECT col1 FROM t3)
+ |)""".stripMargin
+ checkAnswerAndPlan(query7, Row(1) :: Row(2) :: Row(3) :: Row(7) ::
Row(9) :: Nil)
+
+ // A nested subquery correlated to the query it is nested in, on a
column it does not
+ // project, so its correlated predicate changes the answer: without it
the nested IN would
+ // hold for c1 = 1 and row 1 would be returned as well.
+ val query8 =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT c1
+ | FROM t2
+ | WHERE a > c1
+ | OR c1 IN (SELECT col1 FROM t4 WHERE k = c1)
+ |)""".stripMargin
+ checkAnswerAndPlan(query8, Row(2) :: Row(3) :: Row(7) :: Row(9) :: Nil)
+ }
+ }
+
+ test("SPARK-59351: nested subquery referencing both the outer and the inner
query") {
+ withTempView("t1", "t2", "t3", "t4") {
+ Seq((1), (2), (3)).toDF("a").persist().createOrReplaceTempView("t1")
+ Seq((1), (8), (9)).toDF("c1").persist().createOrReplaceTempView("t2")
+ Seq((3), (9)).toDF("col1").persist().createOrReplaceTempView("t3")
+ // Correlated, this is false for every c1 in t2; without its correlated
predicate it holds
+ // for 1 and 9, so the correlation decides the answer below.
+ Seq((1, 9), (9, 1)).toDF("col1",
"k").persist().createOrReplaceTempView("t4")
+
+ // The nested subquery references the outer query through its values and
the inner query
+ // through its own correlated predicate, so it can be rewritten into an
existence join on
+ // neither side and stays in the join condition. Planning it there as an
in-subquery filter
+ // drops its correlated predicate col1 = c1, which is why it is rejected
rather than left.
+ // These rows do not distinguish the two forms; the EXISTS form of this
shape does, and
+ // returned an extra row before the rejection was added.
+ //
+ // NOT IN is the outer predicate on purpose: its rewrite returns a bare
Join, which
+ // RewritePredicateSubquery does not offer to its own handling of
predicate subqueries in
+ // join conditions, so this rejection is the only one that can fire.
With EXISTS the rewrite
+ // returns a Project over the join, which that handling then rejects on
its own under the
+ // default configuration, and the assertion would hold either way.
+ val correlated =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE a NOT IN (
+ | SELECT c1
+ | FROM t2
+ | WHERE a = c1
+ | OR a IN (SELECT col1 FROM t3 WHERE col1 = c1)
+ |)""".stripMargin
+ Seq("true", "false").foreach { decorrelateInJoinCondition =>
+
withSQLConf(SQLConf.DECORRELATE_PREDICATE_SUBQUERIES_IN_JOIN_CONDITION.key ->
+ decorrelateInJoinCondition) {
+ val e = intercept[AnalysisException](sql(correlated).collect())
+ assert(e.getCondition == "UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY."
+
+ "NESTED_SUBQUERY_REFERENCING_OUTER_AND_INNER_QUERY")
+ // The message must name the subquery that was rejected.
+ val reported = e.getMessageParameters.get("subqueryExpression")
+ assert(reported.contains("IN") && reported.contains("listquery"),
+ s"unexpected subqueryExpression: $reported")
+ }
+ }
+
+ // A correlated predicate that BooleanSimplification has eliminated:
+ // PullupCorrelatedPredicates retains c1 as an outer attribute of the
nested subquery for
+ // idempotency, but the subquery
+ // no longer reads it, so there is no condition to lose. It must still
be rewritten against
+ // the outer plan, which is the only plan it effectively references,
rather than be treated
+ // as referencing the subquery plan and rejected.
+ val simplifiedAwayCorrelation =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT 1
+ | FROM t2
+ | WHERE a = c1
+ | OR a IN (SELECT col1 FROM t3 WHERE false AND col1 = c1)
+ |)""".stripMargin
+ Seq("true", "false").foreach { decorrelateInJoinCondition =>
+
withSQLConf(SQLConf.DECORRELATE_PREDICATE_SUBQUERIES_IN_JOIN_CONDITION.key ->
+ decorrelateInJoinCondition) {
+ checkAnswer(sql(simplifiedAwayCorrelation), Row(1) :: Nil)
+ }
+ }
+
+ // A subquery that stays in the join condition stays there whole, since
the rewrite does
+ // not descend into one it declines, so a correlated subquery below it
is left as well.
+ // Its own references make it look routable, being owned by the subquery
plan, but
+ // nothing reaches it and planning a list query as an in-subquery filter
drops the
+ // predicate the pull-up hoisted into it. The enclosing subquery is
rejected for
+ // carrying it: PostgreSQL and DuckDB return 1 and 3 here, and losing
the correlation
+ // returns 2 as well.
+ val carriedCorrelation =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT 1
+ | FROM t2
+ | WHERE a = c1
+ | OR (a + (CASE WHEN c1 IN (SELECT col1 FROM t4 WHERE k = c1) THEN
1 ELSE 0 END))
+ | IN (SELECT col1 FROM t3)
+ |)""".stripMargin
+ Seq("true", "false").foreach { decorrelateInJoinCondition =>
+
withSQLConf(SQLConf.DECORRELATE_PREDICATE_SUBQUERIES_IN_JOIN_CONDITION.key ->
+ decorrelateInJoinCondition) {
+ val e =
intercept[AnalysisException](sql(carriedCorrelation).collect())
+ assert(e.getCondition == "UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY."
+
+ "NESTED_SUBQUERY_REFERENCING_OUTER_AND_INNER_QUERY")
+ }
+ }
+
+ // An uncorrelated nested subquery referencing both queries has no
correlated predicate to
+ // lose, so it stays in the join condition and is planned as an
in-subquery filter. The
+ // configuration is disabled because the rewrite of predicate subqueries
in join conditions
+ // rejects a subquery referencing both join inputs, which is what this
one becomes.
+ val uncorrelated =
+ """
+ |SELECT *
+ |FROM t1
+ |WHERE EXISTS (
+ | SELECT 1
+ | FROM t2
+ | WHERE a = c1
+ | OR (a + c1) IN (SELECT col1 FROM t3)
+ |)""".stripMargin
+ withSQLConf(
+ SQLConf.DECORRELATE_PREDICATE_SUBQUERIES_IN_JOIN_CONDITION.key ->
"false") {
+ // No existence join here: this subquery stays in the join condition,
which is the
+ // point of the case, so only the result and the reachability of the
plan are
+ // checked.
+ checkAnswerAndPlan(uncorrelated, Row(1) :: Row(2) :: Nil,
+ existenceJoinOnSubqueryPlan = false)
+ }
+ }
+ }
+
+ test("SPARK-59351: nested IN subquery whose result can be unknown") {
+ withTempView("t1", "t2", "t2n", "t3n", "t3", "t4", "tb") {
+ Seq((1), (2), (3)).toDF("a").persist().createOrReplaceTempView("t1")
+ Seq((1), (8), (9)).toDF("c1").persist().createOrReplaceTempView("t2")
+ // A nullable compared value, against a subquery column that is not
nullable.
+ Seq(Some(1), None).toDF("c1").persist().createOrReplaceTempView("t2n")
+ Seq((1, 1), (9, 9)).toDF("col1",
"k").persist().createOrReplaceTempView("t4")
+ // A boolean relation, to compare the result of a nested IN subquery
against.
+ Seq(false).toDF("b").persist().createOrReplaceTempView("tb")
+ // The NULL matches no value of t2, so c1 IN (SELECT col1 FROM t3n) is
unknown there, and
+ // c1 NOT IN (SELECT col1 FROM t3n) is never true.
+ Seq(Some(3), None).toDF("col1").persist().createOrReplaceTempView("t3n")
+ Seq((3), (9)).toDF("col1").persist().createOrReplaceTempView("t3")
+
+ // An existence join only records whether a row matched, so its exists
attribute is false
+ // where IN is unknown. That is not observable while the value feeds a
predicate, but it is
+ // once it reaches anything else, so these are rejected rather than
rewritten. Both
+ // configurations are checked, as the rejection must not depend on the
rewrite of predicate
+ // subqueries in join conditions.
+ Seq(
+ "(c1 IN (SELECT col1 FROM t3n)) <=> false",
+ "(c1 IN (SELECT col1 FROM t3n)) IS NULL",
+ // COALESCE to a non-false default does tell unknown from false.
+ "COALESCE(c1 IN (SELECT col1 FROM t3n), true)",
+ "(c1 NOT IN (SELECT col1 FROM t3n)) <=> false").foreach { predicate =>
+ Seq("true", "false").foreach { decorrelateInJoinCondition =>
+
withSQLConf(SQLConf.DECORRELATE_PREDICATE_SUBQUERIES_IN_JOIN_CONDITION.key ->
+ decorrelateInJoinCondition) {
+ val e = intercept[AnalysisException] {
+ sql(s"SELECT * FROM t1 WHERE EXISTS (SELECT 1 FROM t2 WHERE a =
c1 OR $predicate)")
+ .collect()
+ }
+ assert(e.getCondition ==
"UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY." +
+ "NESTED_IN_SUBQUERY_WITH_UNKNOWN_RESULT")
+ // A NOT IN must be reported as a NOT IN, not as the IN underneath
it.
+ val reported = e.getMessageParameters.get("subqueryExpression")
+ assert(reported.startsWith("(NOT ") == predicate.contains("NOT
IN"),
+ s"unexpected subqueryExpression for $predicate: $reported")
+ }
+ }
+ }
+
+ // The ordinary case: the value of the nested IN feeds a predicate,
where unknown and
+ // false cannot be told apart, so it is still rewritten even though it
can be unknown.
+ checkAnswerAndPlan(
+ """SELECT * FROM t1 WHERE EXISTS (
+ | SELECT 1 FROM t2 WHERE a = c1 OR c1 IN (SELECT col1 FROM
t3n))""".stripMargin,
+ Row(1) :: Nil)
+
+ // And a nested IN that cannot be unknown is rewritten even outside a
predicate.
+ checkAnswerAndPlan(
+ """SELECT * FROM t1 WHERE EXISTS (
+ | SELECT 1 FROM t2
+ | WHERE a = c1 OR ((c1 IN (SELECT col1 FROM t3)) <=>
false))""".stripMargin,
+ Row(1) :: Row(2) :: Row(3) :: Nil)
+
+ // Only truth is observed by `<=> true`, by an IF predicate and by a
CASE WHEN
+ // condition, so those are rewritten rather than rejected.
SimplifyConditionals folds
+ // the latter two into the first, so ordinary SQL reaches this position.
+ //
+ // The result branches of a conditional are consumed wherever the
conditional is, so
+ // under a filter predicate they are truth-only as well. The last two
cases do not
+ // fold, so they exercise that inheritance rather than the rewrites
above.
+ Seq(
+ "(c1 IN (SELECT col1 FROM t3n)) <=> true",
+ "IF(c1 IN (SELECT col1 FROM t3n), true, false)",
+ "CASE WHEN c1 IN (SELECT col1 FROM t3n) THEN true ELSE false END",
+ "IF(c1 > 0, c1 IN (SELECT col1 FROM t3n), false)",
+ "CASE WHEN c1 > 0 THEN c1 IN (SELECT col1 FROM t3n) ELSE false END",
+ "CASE WHEN c1 > 100 THEN false ELSE c1 IN (SELECT col1 FROM t3n) END",
+ // COALESCE to false maps unknown and false alike, so only truth is
observed.
+ "COALESCE(c1 IN (SELECT col1 FROM t3n), false)")
+ .foreach { predicate =>
+ checkAnswerAndPlan(
+ s"SELECT * FROM t1 WHERE EXISTS (SELECT 1 FROM t2 WHERE a = c1 OR
$predicate)",
+ Row(1) :: Nil)
+ }
+
+ // The unknown can come from the compared value rather than from the
subquery column.
+ // spark.sql.legacy.inSubqueryNullability makes InSubquery.nullable
ignore the
+ // nullability of the list query columns, but it always keeps that of
the compared
+ // values, and the guard re-derives both, so this case is rejected under
either value.
+ Seq("true", "false").foreach { legacyNullability =>
Review Comment:
The coverage gap is real — you are right that the existing loop uses
nullable compared values, so both flag values report them nullable and the loop
would not notice a regression on the RHS-derived side. I have added the case.
Your premise about what it would show does not hold, though, and I would
have asserted the wrong thing if I had followed the recommendation. With a
non-nullable compared value (`t2.c1`) and a nullable list output (`t3n.col1`),
the two settings legitimately disagree:
| `spark.sql.legacy.inSubqueryNullability` | outcome |
|---|---|
| `false` (default) | `NESTED_IN_SUBQUERY_WITH_UNKNOWN_RESULT`,
subqueryExpression `(t2.c1 IN (listquery()))` |
| `true` | accepted, returns `1` — **the correct answer** |
Under legacy mode the query is not an UNKNOWN collapsed to FALSE. Because
`InSubquery.nullable` is false there, `SimplifyBinaryComparison` turns `x <=>
false` into `NOT x`, and a `NOT` directly over an IN takes the null-aware
rewrite:
```
Join LeftSemi, ((value#103 = c1#114) OR NOT exists#127)
+- Join ExistenceJoin(exists#127), ((c1#114 = col1#121) OR isnull((c1#114 =
col1#121)))
```
`exists` is TRUE where the comparison is unknown, so `NOT exists` is FALSE
there — which is exactly what `unknown <=> false` is. DuckDB returns `1` for
the same data, so legacy mode is right here, by a different route. The guard is
not reached because there is no longer an `EqualNullSafe` to reach, not because
it failed to re-derive nullability.
So the test now pins the rejection under the default and the *correct answer
and plan* under legacy mode, with a comment explaining why they differ.
Asserting rejection under both, as recommended, would have been asserting a bug.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
