Skip to content

[SPARK-56912][SQL] Simplify Cast to boolean codegen under ANSI mode #55937

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
gengliangwang wants to merge 2 commits into from
Closed

[SPARK-56912][SQL] Simplify Cast to boolean codegen under ANSI mode #55937

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
b186a2a
[SPARK-56912][SQL] Refactor Cast to boolean codegen under ANSI mode
gengliangwang May 17, 2026
83a3cbb
address cloud-fan review: move stringToBooleanExact to UTF8StringUtil…
gengliangwang May 28, 2026
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
20 changes: 8 additions & 12 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -695,18 +695,16 @@ case class Cast(

// UDFToBoolean
private[this] def castToBoolean(from: DataType): Any => Any = from match {
case _: StringType if ansiEnabled =>
buildCast[UTF8String](_, s => UTF8StringUtils.toBooleanExact(s, getContextOrNull()))
case _: StringType =>
buildCast[UTF8String](_, s => {
if (StringUtils.isTrueString(s)) {
true
} else if (StringUtils.isFalseString(s)) {
false
} else {
if (ansiEnabled) {
throw QueryExecutionErrors.invalidInputSyntaxForBooleanError(s, getContextOrNull())
} else {
null
}
null
}
})
case TimestampType =>
Expand Down Expand Up @@ -1881,22 +1879,20 @@ case class Cast(
private[this] def castToBooleanCode(
from: DataType,
ctx: CodegenContext): CastFunction = from match {
case _: StringType if ansiEnabled =>
val stringUtils = UTF8StringUtils.getClass.getCanonicalName.stripSuffix("$")
val errorContext = getContextOrNullCode(ctx)
(c, evPrim, _) => code"$evPrim = $stringUtils.toBooleanExact($c, $errorContext);"
case _: StringType =>
val stringUtils = inline"${StringUtils.getClass.getName.stripSuffix("$")}"
(c, evPrim, evNull) =>
val castFailureCode = if (ansiEnabled) {
val errorContext = getContextOrNullCode(ctx)
s"throw QueryExecutionErrors.invalidInputSyntaxForBooleanError($c, $errorContext);"
} else {
s"$evNull = true;"
}
code"""
if ($stringUtils.isTrueString($c)) {
$evPrim = true;
} else if ($stringUtils.isFalseString($c)) {
$evPrim = false;
} else {
$castFailureCode
$evNull = true;
}
"""
case TimestampType =>
Expand Down
8 changes: 7 additions & 1 deletion sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UTF8StringUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ import org.apache.spark.sql.types.{ByteType, DataType, IntegerType, LongType, Sh
import org.apache.spark.unsafe.types.UTF8String

/**
* Helper functions for casting string to numeric values.
* Helper functions for casting string to primitive values under ANSI mode.
*/
object UTF8StringUtils {

Expand All @@ -39,6 +39,12 @@ object UTF8StringUtils {
def toByteExact(s: UTF8String, context: QueryContext): Byte =
withException(s.toByteExact, context, ByteType, s)

def toBooleanExact(s: UTF8String, context: QueryContext): Boolean = {
if (StringUtils.isTrueString(s)) true
else if (StringUtils.isFalseString(s)) false
else throw QueryExecutionErrors.invalidInputSyntaxForBooleanError(s, context)
}

private def withException[A](
f: => A,
context: QueryContext,
Expand Down