Skip to content

[SPARK-40149][SQL][FOLLOWUP] Avoid adding extra Project in AddMetadataColumns #39895

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
allisonwang-db wants to merge 2 commits into from
Closed

[SPARK-40149][SQL][FOLLOWUP] Avoid adding extra Project in AddMetadataColumns #39895

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4a6f280
fix
allisonwang-db Feb 6, 2023
524753a
add tests
allisonwang-db Feb 6, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -992,7 +992,7 @@ class Analyzer(override val catalogManager: CatalogManager) extends RuleExecutor
if (metaCols.isEmpty) {
node
} else {
val newNode = addMetadataCol(node, metaCols.map(_.exprId).toSet)
val newNode = node.mapChildren(addMetadataCol(_, metaCols.map(_.exprId).toSet))
// We should not change the output schema of the plan. We should project away the extra
// metadata columns if necessary.
if (newNode.sameOutput(node)) {
Expand Down
19 changes: 18 additions & 1 deletion sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression, Count, Sum}
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser.parsePlan
import org.apache.spark.sql.catalyst.plans.{Cross, Inner}
import org.apache.spark.sql.catalyst.plans.{Cross, FullOuter, Inner, UsingJoin}
import org.apache.spark.sql.catalyst.plans.logical._
import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, Partitioning, RangePartitioning, RoundRobinPartitioning}
import org.apache.spark.sql.catalyst.util._
Expand Down Expand Up @@ -1387,4 +1387,21 @@ class AnalysisSuite extends AnalysisTest with Matchers {
assert(!cg.rightOrder.flatMap(_.references).exists(cg.left.output.contains))
}
}

test("SPARK-40149: add metadata column with no extra project") {
val t1 = LocalRelation($"key".int, $"value".string).as("t1")
val t2 = LocalRelation($"key".int, $"value".string).as("t2")
val query =
Project(Seq($"t1.key", $"t2.key"),
Join(t1, t2, UsingJoin(FullOuter, Seq("key")), None, JoinHint.NONE))
checkAnalysis(
query,
Project(Seq($"t1.key", $"t2.key"),
Project(Seq(coalesce($"t1.key", $"t2.key").as("key"),
$"t1.value", $"t2.value", $"t1.key", $"t2.key"),
Join(t1, t2, FullOuter, Some($"t1.key" === $"t2.key"), JoinHint.NONE)
)
).analyze
)
}
}