Skip to content

feat: [CometFuzz] Add support for literal arguments [WIP] #2645

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

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

feat: [CometFuzz] Add support for literal arguments [WIP] #2645

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2601bf1
sometimes pick literal args to functions
andygrove Oct 24, 2025
211bb11
provide hints
andygrove Oct 24, 2025
9ccd6d2
save [skip ci]
andygrove Oct 24, 2025
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
8 changes: 7 additions & 1 deletion fuzz-testing/src/main/scala/org/apache/comet/fuzz/Meta.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@ case class SparkArrayType(elementType: SparkType) extends SparkType
case class SparkMapType(keyType: SparkType, valueType: SparkType) extends SparkType
case class SparkStructType(fields: Seq[SparkType]) extends SparkType
case object SparkAnyType extends SparkType
case class SparkTypeWithValues(sparkType: SparkType, validValues: Seq[String]) extends SparkType

case class FunctionSignature(inputTypes: Seq[SparkType])

Expand Down Expand Up @@ -302,7 +303,12 @@ object Meta {
createFunctionWithInputTypes("hour", Seq(SparkDateOrTimestampType)),
createFunctionWithInputTypes("minute", Seq(SparkDateOrTimestampType)),
createFunctionWithInputTypes("second", Seq(SparkDateOrTimestampType)),
createFunctionWithInputTypes("trunc", Seq(SparkDateOrTimestampType, SparkStringType)),
createFunctionWithInputTypes(
"date_trunc",
Seq(SparkDateOrTimestampType, SparkTypeWithValues(SparkStringType, Seq("year", "week")))),
createFunctionWithInputTypes(
"trunc",
Seq(SparkDateOrTimestampType, SparkTypeWithValues(SparkStringType, Seq("year", "week")))),
createFunctionWithInputTypes("year", Seq(SparkDateOrTimestampType)),
createFunctionWithInputTypes("month", Seq(SparkDateOrTimestampType)),
createFunctionWithInputTypes("day", Seq(SparkDateOrTimestampType)),
Expand Down
36 changes: 35 additions & 1 deletion fuzz-testing/src/main/scala/org/apache/comet/fuzz/QueryGen.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ object QueryGen {
val func = Utils.randomChoice(Meta.scalarFunc, r)
try {
val signature = Utils.randomChoice(func.signatures, r)
val args = signature.inputTypes.map(x => pickRandomColumn(r, table, x))
val args = signature.inputTypes.map(x => pickRandomColumnOrLiteral(r, table, x))

// Example SELECT c0, log(c0) as x FROM test0
s"SELECT ${args.mkString(", ")}, ${func.name}(${args.mkString(", ")}) AS x " +
Expand All @@ -117,6 +117,40 @@ object QueryGen {
}
}

private def pickRandomColumnOrLiteral(
r: Random,
df: DataFrame,
targetType: SparkType): String = {
if (r.nextBoolean) {
targetType match {
case SparkIntegralType =>
r.nextInt(10).toString
case SparkStringType =>
formatLiteral(r.nextString(4), SparkStringType)
case SparkTimestampType =>
"now()"
case SparkTypeWithValues(sparkType, values) =>
// choose between known valid input and random input
if (r.nextBoolean()) {
formatLiteral(Utils.randomChoice(values, r), sparkType)
} else {
pickRandomColumnOrLiteral(r, df, sparkType)
}
case _ =>
pickRandomColumn(r, df, targetType)
}
} else {
pickRandomColumn(r, df, targetType)
}
}

private def formatLiteral(validValue: Any, sparkType: SparkType): String = {
sparkType match {
case SparkStringType => s""""$validValue""""
case _ => validValue.toString
}
}

private def pickRandomColumn(r: Random, df: DataFrame, targetType: SparkType): String = {
targetType match {
case SparkAnyType =>
Expand Down