Skip to content

fix: Fallback to Spark if named_struct contains duplicate field names #1016

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

Merged
viirya merged 1 commit into from
Oct 13, 2024
Merged

fix: Fallback to Spark if named_struct contains duplicate field names #1016

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2453,6 +2453,11 @@ object QueryPlanSerde extends Logging with ShimQueryPlanSerde with CometExprShim
}

case struct @ CreateNamedStruct(_) =>
if (struct.names.length != struct.names.distinct.length) {
withInfo(expr, "CreateNamedStruct with duplicate field names are not supported")
return None
}

val valExprs = struct.valExprs.map(exprToProto(_, inputs, binding))

if (valExprs.forall(_.isDefined)) {
Expand Down
22 changes: 21 additions & 1 deletion spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ import org.apache.hadoop.fs.Path
import org.apache.spark.sql.{CometTestBase, DataFrame, Row}
import org.apache.spark.sql.catalyst.optimizer.SimplifyExtractValueOps
import org.apache.spark.sql.comet.CometProjectExec
import org.apache.spark.sql.execution.{ColumnarToRowExec, InputAdapter, WholeStageCodegenExec}
import org.apache.spark.sql.execution.{ColumnarToRowExec, InputAdapter, ProjectExec, WholeStageCodegenExec}
import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper
import org.apache.spark.sql.functions._
import org.apache.spark.sql.internal.SQLConf
Expand Down Expand Up @@ -2062,6 +2062,26 @@ class CometExpressionSuite extends CometTestBase with AdaptiveSparkPlanHelper {
}
}

test("named_struct with duplicate field names") {
Seq(true, false).foreach { dictionaryEnabled =>
withTempDir { dir =>
val path = new Path(dir.toURI.toString, "test.parquet")
makeParquetFileAllTypes(path, dictionaryEnabled = dictionaryEnabled, 10000)
withParquetTable(path.toString, "tbl") {
checkSparkAnswerAndOperator(
"SELECT named_struct('a', _1, 'a', _2) FROM tbl",
classOf[ProjectExec])
checkSparkAnswerAndOperator(
"SELECT named_struct('a', _1, 'a', 2) FROM tbl",
classOf[ProjectExec])
checkSparkAnswerAndOperator(
"SELECT named_struct('a', named_struct('b', _1, 'b', _2)) FROM tbl",
classOf[ProjectExec])
}
}
}
}

test("to_json") {
Seq(true, false).foreach { dictionaryEnabled =>
withParquetTable(
Expand Down