Skip to content

[SPARK-28224][SQL] Check overflow in decimal Sum aggregate #25033

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
wants to merge 10 commits into from
Closed

[SPARK-28224][SQL] Check overflow in decimal Sum aggregate #25033

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4845bb7
aggregation not handled
mickjermsurawong-stripe Jul 1, 2019
bb9a477
register test data
mickjermsurawong-stripe Jul 2, 2019
023639f
test other datatypes int/double are not affected
mickjermsurawong-stripe Jul 2, 2019
549257f
simplify test
mickjermsurawong-stripe Jul 2, 2019
893881a
use previate more explicit variable
mickjermsurawong-stripe Jul 2, 2019
04a3164
use matched result type
mickjermsurawong-stripe Jul 5, 2019
d2f7843
more specific exception
mickjermsurawong-stripe Aug 17, 2019
8110ad1
remove unnecessary create temp view
mickjermsurawong-stripe Aug 17, 2019
873c702
remove unnecessary test
mickjermsurawong-stripe Aug 19, 2019
db2d9a5
move fixture to test itself
mickjermsurawong-stripe Aug 19, 2019
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
7 changes: 6 additions & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Sum.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.util.TypeUtils
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types._

@ExpressionDescription(
Expand Down Expand Up @@ -89,5 +90,9 @@ case class Sum(child: Expression) extends DeclarativeAggregate with ImplicitCast
)
}

override lazy val evaluateExpression: Expression = sum
override lazy val evaluateExpression: Expression = resultType match {
case d: DecimalType => CheckOverflow(sum, d, SQLConf.get.decimalOperationsNullOnOverflow)
case _ => sum
}

}
23 changes: 22 additions & 1 deletion sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ import org.apache.spark.sql.execution.exchange.{BroadcastExchangeExec, ReusedExc
import org.apache.spark.sql.functions._
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.{ExamplePoint, ExamplePointUDT, SharedSparkSession}
import org.apache.spark.sql.test.SQLTestData.{NullStrings, TestData2}
import org.apache.spark.sql.test.SQLTestData.{DecimalData, NullStrings, TestData2}
import org.apache.spark.sql.types._
import org.apache.spark.util.Utils
import org.apache.spark.util.random.XORShiftRandom
Expand Down Expand Up @@ -156,6 +156,27 @@ class DataFrameSuite extends QueryTest with SharedSparkSession {
structDf.select(xxhash64($"a", $"record.*")))
}

test("SPARK-28224: Aggregate sum big decimal overflow") {
val largeDecimals = spark.sparkContext.parallelize(
DecimalData(BigDecimal("1"* 20 + ".123"), BigDecimal("1"* 20 + ".123")) ::
DecimalData(BigDecimal("9"* 20 + ".123"), BigDecimal("9"* 20 + ".123")) :: Nil).toDF()

Seq(true, false).foreach { nullOnOverflow =>
withSQLConf((SQLConf.DECIMAL_OPERATIONS_NULL_ON_OVERFLOW.key, nullOnOverflow.toString)) {
val structDf = largeDecimals.select("a").agg(sum("a"))
if (nullOnOverflow) {
checkAnswer(structDf, Row(null))
} else {
val e = intercept[SparkException] {
structDf.collect
}
assert(e.getCause.getClass.equals(classOf[ArithmeticException]))
assert(e.getCause.getMessage.contains("cannot be represented as Decimal"))
}
}
}
}

test("Star Expansion - explode should fail with a meaningful message if it takes a star") {
val df = Seq(("1,2"), ("4"), ("7,8,9")).toDF("csv")
val e = intercept[AnalysisException] {
Expand Down