Skip to content

[SPARK-55559][SQL] Fix BitCount to respect input integer type bit width #54631

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

Open
xiaoxuandev wants to merge 1 commit into
base: master
Choose a base branch
from
+37 −5
Open

[SPARK-55559][SQL] Fix BitCount to respect input integer type bit width #54631

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
21 changes: 16 additions & 5 deletions ...atalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/bitwiseExpressions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,15 +237,26 @@ case class BitwiseCount(child: Expression)

override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = child.dataType match {
case BooleanType => defineCodeGen(ctx, ev, c => s"($c) ? 1 : 0")
case _ => defineCodeGen(ctx, ev, c => s"java.lang.Long.bitCount($c)")
case ByteType => defineCodeGen(ctx, ev, c =>
s"java.lang.Integer.bitCount(java.lang.Byte.toUnsignedInt($c))")
case ShortType => defineCodeGen(ctx, ev, c =>
s"java.lang.Integer.bitCount(java.lang.Short.toUnsignedInt($c))")
case IntegerType =>
defineCodeGen(ctx, ev, c => s"java.lang.Integer.bitCount($c)")
case LongType =>
defineCodeGen(ctx, ev, c => s"java.lang.Long.bitCount($c)")
}

protected override def nullSafeEval(input: Any): Any = child.dataType match {
case BooleanType => if (input.asInstanceOf[Boolean]) 1 else 0
case ByteType => java.lang.Long.bitCount(input.asInstanceOf[Byte])
case ShortType => java.lang.Long.bitCount(input.asInstanceOf[Short])
case IntegerType => java.lang.Long.bitCount(input.asInstanceOf[Int])
case LongType => java.lang.Long.bitCount(input.asInstanceOf[Long])
case ByteType => java.lang.Integer.bitCount(
java.lang.Byte.toUnsignedInt(input.asInstanceOf[Byte]))
case ShortType => java.lang.Integer.bitCount(
java.lang.Short.toUnsignedInt(input.asInstanceOf[Short]))
case IntegerType =>
java.lang.Integer.bitCount(input.asInstanceOf[Int])
case LongType =>
java.lang.Long.bitCount(input.asInstanceOf[Long])
}

override protected def withNewChildInternal(newChild: Expression): BitwiseCount =
Expand Down
21 changes: 21 additions & 0 deletions ...st/src/test/scala/org/apache/spark/sql/catalyst/expressions/BitwiseExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,6 +175,27 @@ class BitwiseExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
checkEvaluation(BitwiseCount(Literal(-9223372036854775808L)), 1)
}

test("BitCount should respect input integer type bit width") {
// BIT_COUNT(-1) should return the number of bits in the type, not always 64
checkEvaluation(BitwiseCount(Literal((-1).toByte)), 8)
checkEvaluation(BitwiseCount(Literal((-1).toShort)), 16)
checkEvaluation(BitwiseCount(Literal(-1)), 32)
checkEvaluation(BitwiseCount(Literal(-1L)), 64)

// Additional cases with specific negative values
checkEvaluation(BitwiseCount(Literal(Int.MinValue)), 1)
checkEvaluation(BitwiseCount(Literal(-65536)), 16)
checkEvaluation(BitwiseCount(Literal(-256)), 24)
checkEvaluation(BitwiseCount(Literal(Byte.MinValue)), 1)
checkEvaluation(BitwiseCount(Literal((-256).toShort)), 8)
checkEvaluation(BitwiseCount(Literal(Short.MinValue)), 1)
checkEvaluation(BitwiseCount(Literal(Long.MinValue)), 1)

DataTypeTestUtils.integralType.foreach { dt =>
checkConsistencyBetweenInterpretedAndCodegen(BitwiseCount, dt)
}
}

test("BitGet") {
val nullLongLiteral = Literal.create(null, LongType)
val nullIntLiteral = Literal.create(null, IntegerType)
Expand Down