cloud-fan commented on code in PR #58077:
URL: https://github.com/apache/spark/pull/58077#discussion_r3910711535
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/subquery.scala:
##########
@@ -165,14 +197,187 @@ case class InSubqueryExec(
}
}
+ // Invariant schema/ordering data for the multi-column evaluator, computed
once after the result
+ // is available. @transient so that serialization (result=null) does not
trigger evaluation.
+ @transient private lazy val multiColFieldTypes: Array[DataType] =
+ plan.output.map(_.dataType).toArray
+ @transient private lazy val multiColFieldOrderings: Array[Ordering[Any]] =
+ multiColFieldTypes.map(TypeUtils.getInterpretedOrdering)
+ // Struct-level ordering used to index fully non-null result rows in a
TreeSet.
+ @transient private lazy val multiColRowOrdering: Ordering[InternalRow] =
+
TypeUtils.getInterpretedOrdering(child.dataType).asInstanceOf[Ordering[InternalRow]]
+
+ // Split collected rows into two sorted sets, both using the struct-level
Catalyst ordering
+ // so that duplicate rows are deduplicated. Fully non-null rows go into
multiColNonNullSet
+ // for O(log n) membership tests; rows with at least one null field go into
multiColNullRows
+ // (also a TreeSet, not an Array) so each distinct null-containing row is
scanned at most
+ // once per outer row regardless of RHS duplicate multiplicity. See
SPARK-58481.
+ @transient private lazy val (multiColNonNullSet, multiColNullRows) = {
+ val withNull = TreeSet.newBuilder[InternalRow](multiColRowOrdering)
+ val nonNull = TreeSet.newBuilder[InternalRow](multiColRowOrdering)
+ result.foreach { r =>
+ val row = r.asInstanceOf[InternalRow]
+ if (row.anyNull) withNull += row else nonNull += row
+ }
+ (nonNull.result(), withNull.result().toArray)
+ }
+
+ // Three-valued IN semantics for multi-column subqueries.
+ // Result rows are InternalRow objects; InSet's TreeSet uses Catalyst
ordering, but membership
+ // cannot distinguish a definitively-false candidate from an indeterminate
one.
+ //
+ // When the LHS struct has no null fields:
+ // Fast path: O(log n) TreeSet lookup against fully non-null result rows
for TRUE.
+ // Slow path: linear scan over null-containing result rows only for
potential UNKNOWN.
+ //
+ // When the LHS struct has at least one null field, the fast path cannot be
used (a null LHS
+ // field produces UNKNOWN against any non-null RHS row whose non-null fields
all match). Both
+ // sets of result rows are scanned linearly, stopping once UNKNOWN is
established.
+ //
+ // Per-candidate three-valued logic: TRUE if every field matches; UNKNOWN if
no field is
+ // definitively unequal but at least one comparison involves null; FALSE
otherwise.
+ private def evalMultiColumn(inputRow: InternalRow): Any = {
+ // Mirror InSet.eval: if the candidate set is empty, return false before
evaluating the LHS.
+ // Under legacy behavior (ANSI off by default), the SQL standard says IN
(empty set) is
Review Comment:
**Non-blocking (P2):** The compatibility description is reversed here.
`spark.sql.legacy.nullInEmptyListBehavior` preserves the old NULL result;
current behavior returns FALSE for an empty set. Also, only the current branch
skips `child.eval` - with the legacy flag enabled, the LHS is still evaluated.
Please describe those two branches explicitly so this comment matches the guard
below.
##########
sql/core/src/test/scala/org/apache/spark/sql/SubquerySuite.scala:
##########
@@ -2678,4 +2682,275 @@ class SubquerySuite extends SharedSparkSession
assert(exposedAttribute.exprId == outerReferenceAttribute.exprId)
}
+
+ test("SPARK-58481: InSubqueryExec nullable correctly accounts for subquery
output nullability") {
+ // 5 NOT IN (99, NULL) is UNKNOWN, not TRUE or FALSE. A join condition
that is not TRUE
+ // matches no rows, so a FULL OUTER JOIN must emit null-padded rows for
every row in each
+ // side -- 3 + 3 = 6 null-padded rows -- not the full cross product (9
rows).
+ withTable("t0", "t1", "t3") {
+ sql("CREATE TABLE t0(c0 INT) USING PARQUET")
+ sql("INSERT INTO t0 VALUES (1), (2), (3)")
+ sql("CREATE TABLE t1(c0 INT) USING PARQUET")
+ sql("INSERT INTO t1 VALUES (10), (20), (30)")
+ sql("CREATE TABLE t3(c0 INT) USING PARQUET")
+ sql("INSERT INTO t3 VALUES (99), (CAST(NULL AS INT))")
+
+ // Unmatched t1 rows null-pad t0; unmatched t0 rows null-pad t1.
+ val expected = Seq(
+ Row(null, 10), Row(null, 20), Row(null, 30), // unmatched t1, t0
column null-padded
+ Row(1, null), Row(2, null), Row(3, null)) // unmatched t0, t1
column null-padded
+ checkAnswer(
+ sql("SELECT t0.c0, t1.c0 FROM t1 FULL OUTER JOIN t0 ON (5 NOT IN
(SELECT t3.c0 FROM t3))"),
+ expected)
+ }
+ }
+
+ test("SPARK-58481: multi-column IN subquery with nullable non-head output is
nullable") {
+ // Disable the optimizer's join-condition IN rewrite so the query
exercises InSubqueryExec.
+ // Use VALUES-derived temp views: their nullability is inferred from the
literals (no NULL
+ // literal => non-nullable), rather than declared and then widened.
Parquet file-source
+ // analysis applies dataSchema.asNullable regardless of DDL NOT NULL,
which would defeat
+ // the nullability control this test relies on.
+ withSQLConf(
+
"spark.sql.optimizer.optimizeUncorrelatedInSubqueriesInJoinCondition.enabled"
-> "false"
+ ) {
+ // Case A: NULL after a definitive match (null in non-head position
after matching head).
+ // RHS: (99,99) and (1,NULL).
+ // (1,1) vs (99,99): first field 1!=99 => FALSE.
+ // (1,1) vs (1,NULL): first fields equal, second null => UNKNOWN.
+ // Overall for (1,1): UNKNOWN => NOT IN = null-padded.
+ // (2,2) vs both: all FALSE => NOT IN = TRUE => joins with both rhs
rows.
+ withTempView("lhs", "rhs") {
+ sql("CREATE TEMPORARY VIEW lhs AS SELECT * FROM VALUES (1, 1), (2, 2)
AS t(a, b)")
+ sql(
+ """CREATE TEMPORARY VIEW rhs AS
+ |SELECT * FROM VALUES (99, 99), (1, CAST(NULL AS INT)) AS t(a,
b)""".stripMargin)
+ checkAnswer(
+ sql(
+ """SELECT lhs.a, rhs.a FROM lhs FULL OUTER JOIN rhs
+ |ON ((lhs.a, lhs.b) NOT IN (SELECT a, b FROM
rhs))""".stripMargin),
+ Seq(Row(1, null), Row(2, 99), Row(2, 1)))
+ }
+
+ // Case B: NULL in head position followed by a definitive mismatch in a
later field.
+ // RHS: (NULL, 99).
+ // (1,1) vs (NULL,99): first field null => UNKNOWN so far; second
field 1!=99 => FALSE.
+ // A later definitive mismatch must override the earlier UNKNOWN:
result is FALSE,
+ // NOT IN = TRUE. A field-order regression would leave (1,1) as
UNKNOWN instead.
+ withTempView("lhs2", "rhs2") {
+ sql("CREATE TEMPORARY VIEW lhs2 AS SELECT * FROM VALUES (1, 1) AS t(a,
b)")
+ sql(
+ """CREATE TEMPORARY VIEW rhs2 AS
+ |SELECT * FROM VALUES (CAST(NULL AS INT), 99) AS t(a,
b)""".stripMargin)
+ // (1,1) NOT IN ((NULL,99)): second field 1!=99 makes the candidate
FALSE =>
+ // NOT IN = TRUE => inner join returns the single matching row.
+ checkAnswer(
+ sql(
+ """SELECT lhs2.a FROM lhs2 JOIN (SELECT 1 AS a)
+ |ON ((lhs2.a, lhs2.b) NOT IN (SELECT a, b FROM
rhs2))""".stripMargin),
+ Seq(Row(1)))
+ }
+
+ // Case C: UNKNOWN candidate followed by an exact-match candidate => IN
= TRUE.
+ // RHS: (1,NULL) and (1,1).
+ // (1,1) vs (1,NULL): first fields equal, second null => UNKNOWN.
+ // (1,1) vs (1,1): exact match => TRUE.
+ // The exact match must dominate the UNKNOWN: IN = TRUE, NOT IN =
FALSE.
+ // A candidate-order regression would short-circuit on UNKNOWN and
miss the TRUE.
+ withTempView("lhs3", "rhs3") {
+ sql("CREATE TEMPORARY VIEW lhs3 AS SELECT * FROM VALUES (1, 1) AS t(a,
b)")
+ sql(
+ """CREATE TEMPORARY VIEW rhs3 AS
+ |SELECT * FROM VALUES (1, CAST(NULL AS INT)), (1, 1) AS t(a,
b)""".stripMargin)
+ // (1,1) IN ((1,NULL),(1,1)): exact match exists => IN = TRUE => inner
join returns row.
+ checkAnswer(
+ sql(
+ """SELECT lhs3.a FROM lhs3 JOIN (SELECT 1 AS a)
+ |ON ((lhs3.a, lhs3.b) IN (SELECT a, b FROM
rhs3))""".stripMargin),
+ Seq(Row(1)))
+ }
+ }
+ }
+
+ test("SPARK-58481: multi-column IN subquery uses Catalyst ordering for
BinaryType fields") {
+ // Object.equals on Array[Byte] compares by identity, not value; Catalyst
ordering compares
+ // by content. A multi-column IN where one field is BinaryType would
incorrectly return FALSE
+ // (no match) with JVM equality even when the bytes are equal. Use an
inner join to keep the
+ // assertion simple: the join condition is TRUE iff the IN match succeeds.
+ withSQLConf(
+
"spark.sql.optimizer.optimizeUncorrelatedInSubqueriesInJoinCondition.enabled"
-> "false"
+ ) {
+ withTable("lbin", "rbin") {
+ sql("CREATE TABLE lbin(id INT NOT NULL, b BINARY NOT NULL) USING
PARQUET")
+ sql("INSERT INTO lbin VALUES (1, X'01')")
+ sql("CREATE TABLE rbin(id INT NOT NULL, b BINARY NOT NULL) USING
PARQUET")
+ sql("INSERT INTO rbin VALUES (1, X'01')")
+ // (1, 0x01) IN ((1, 0x01)) must be TRUE; the join should return one
row.
+ checkAnswer(
+ sql(
+ """SELECT lbin.id FROM lbin JOIN rbin
+ |ON ((lbin.id, lbin.b) IN (SELECT id, b FROM
rbin))""".stripMargin),
+ Seq(Row(1)))
+ }
+ }
+ }
+
+ test("SPARK-58481: multi-column NOT IN with nullable LHS and non-nullable
RHS is nullable") {
+ // CreateNamedStruct.nullable is always false, so child.nullable would
return false for a
+ // multi-column LHS even when individual fields are nullable. The
generated NOT IN code
+ // would then suppress null handling and turn UNKNOWN into TRUE, producing
wrong results.
+ // Fixture: lhs.a is nullable; rhs columns are NOT NULL (VALUES-derived to
avoid Parquet
+ // dataSchema.asNullable widening that would defeat the RHS
non-nullability control).
+ // (NULL, 2) vs (99, 2): second fields equal (2=2), first field is null =>
UNKNOWN.
+ // (1, 1) vs (99, 2): first field 1!=99 => FALSE => NOT IN = TRUE =>
matches all rhs rows.
+ // FULL OUTER JOIN: (NULL,2) gets null-padded (UNKNOWN condition); (1,1)
joins with (99,2);
+ // since (1,1) matched rhs(99,2), rhs(99,2) is not null-padded.
+ // Pre-fix: (NULL,2) NOT IN is wrongly TRUE (null suppressed) => emits
(null,99); no
+ // null-padded rows. Post-fix: UNKNOWN propagated => emits (null,null)
for (NULL,2).
+ withSQLConf(
+
"spark.sql.optimizer.optimizeUncorrelatedInSubqueriesInJoinCondition.enabled"
-> "false"
+ ) {
+ withTable("lhs") {
+ withTempView("rhs") {
+ sql("CREATE TABLE lhs(a INT, b INT NOT NULL) USING PARQUET")
+ sql("INSERT INTO lhs VALUES (1, 1), (NULL, 2)")
+ // rhs as VALUES view: both columns inferred non-nullable from
all-literal rows.
+ sql("CREATE TEMPORARY VIEW rhs AS SELECT * FROM VALUES (99, 2) AS
t(a, b)")
+ // (NULL, 2) NOT IN ((99,2)): second fields match, first is null =>
UNKNOWN
+ // => join condition not TRUE => (NULL,2) is null-padded:
Row(null, null).
+ // (1, 1) NOT IN ((99,2)): first field 1!=99 => FALSE => NOT IN =
TRUE
+ // => (1,1) joins with rhs(99,2): Row(1, 99). rhs(99,2) is
matched; no null-padded rhs.
+ checkAnswer(
+ sql(
+ """SELECT lhs.a, rhs.a FROM lhs FULL OUTER JOIN rhs
+ |ON ((lhs.a, lhs.b) NOT IN (SELECT a, b FROM
rhs))""".stripMargin),
+ Seq(Row(1, 99), Row(null, null)))
+ }
+ }
+ }
+ }
+
+ test("SPARK-58481: LEGACY_IN_SUBQUERY_NULLABILITY suppresses RHS-only
nullability") {
+ // Legacy mode suppresses only RHS-derived nullability (plan.output
nullable).
+ // A non-nullable scalar LHS (Literal 5) has lhsNullable=false; with RHS
suppressed,
+ // nullable=false. The generated code omits null handling and NOT IN on a
subquery that
+ // returns NULL evaluates to TRUE -- the pre-fix single-column behaviour
the flag preserves.
+ // Note: intentionally codegen-specific. The interpreted path correctly
returns UNKNOWN
+ // regardless of nullable (6 rows); the assertion of 9 verifies codegen
ran.
+ withSQLConf(
+ SQLConf.LEGACY_IN_SUBQUERY_NULLABILITY.key -> "true",
+
"spark.sql.optimizer.optimizeUncorrelatedInSubqueriesInJoinCondition.enabled"
-> "false"
+ ) {
+ withTable("t0", "t1", "t3") {
+ sql("CREATE TABLE t0(c0 INT) USING PARQUET")
+ sql("INSERT INTO t0 VALUES (1), (2), (3)")
+ sql("CREATE TABLE t1(c0 INT) USING PARQUET")
+ sql("INSERT INTO t1 VALUES (10), (20), (30)")
+ sql("CREATE TABLE t3(c0 INT) USING PARQUET")
+ sql("INSERT INTO t3 VALUES (99), (CAST(NULL AS INT))")
+
+ // Legacy: lhsNullable=false (Literal 5), rhsNullable suppressed =>
nullable=false.
+ // Generated code suppresses null; 5 NOT IN (99, NULL) evaluates to
TRUE.
+ // FULL OUTER JOIN condition is TRUE => full cross product of 3 x 3 =
9 rows.
+ assert(sql(
+ "SELECT t0.c0, t1.c0 FROM t1 FULL OUTER JOIN t0 ON (5 NOT IN (SELECT
t3.c0 FROM t3))")
+ .count() === 9)
+ }
+ }
+ }
+
+ test("SPARK-58481: LEGACY_IN_SUBQUERY_NULLABILITY preserves nullable LHS
fields multi-column") {
+ // Legacy mode suppresses RHS nullability but preserves LHS field
nullability.
+ // With a nullable LHS field, lhsNullable=true even in legacy mode, so
nullable=true.
+ // Generated NOT IN code propagates UNKNOWN correctly; result is identical
to non-legacy.
+ withSQLConf(
+ SQLConf.LEGACY_IN_SUBQUERY_NULLABILITY.key -> "true",
+
"spark.sql.optimizer.optimizeUncorrelatedInSubqueriesInJoinCondition.enabled"
-> "false"
+ ) {
+ withTable("lhs", "rhs") {
+ sql("CREATE TABLE lhs(a INT, b INT NOT NULL) USING PARQUET")
+ sql("INSERT INTO lhs VALUES (1, 1), (NULL, 2)")
+ sql("CREATE TABLE rhs(a INT NOT NULL, b INT NOT NULL) USING PARQUET")
+ sql("INSERT INTO rhs VALUES (99, 2)")
+ // (NULL, 2) NOT IN ((99,2)): first field null => UNKNOWN =>
null-padded: Row(null, null).
+ // (1, 1) NOT IN ((99,2)): 1!=99 => FALSE => NOT IN=TRUE => joins:
Row(1, 99).
+ checkAnswer(
+ sql(
+ """SELECT lhs.a, rhs.a FROM lhs FULL OUTER JOIN rhs
+ |ON ((lhs.a, lhs.b) NOT IN (SELECT a, b FROM
rhs))""".stripMargin),
+ Seq(Row(1, 99), Row(null, null)))
+ }
+ }
+ }
+
+ test("SPARK-58481: InSubqueryExec.doGenCode registers Nondeterministic
children " +
+ "for partition-level initialization") {
+ // CheckAnalysis rejects nondeterministic expressions in any join or
filter IN subquery
Review Comment:
**Non-blocking (P2):** This rationale names both the wrong phase and the
wrong failure type. CheckAnalysis exempts Filter; filter IN subqueries
disappear later in RewritePredicateSubquery, while nondeterministic joins are
rejected. Also, `Nondeterministic.eval` uses `require(initialized)`, so a
pre-initialize call raises IllegalArgumentException, not IllegalStateException.
Please update or simplify the comment.
--
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]
