srowen commented on a change in pull request #31199:
URL: https://github.com/apache/spark/pull/31199#discussion_r559234630
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/CharVarcharUtils.scala
##########
@@ -200,69 +212,60 @@ object CharVarcharUtils extends Logging {
*/
def stringLengthCheck(expr: Expression, targetAttr: Attribute): Expression =
{
getRawType(targetAttr.metadata).map { rawType =>
- stringLengthCheck(expr, rawType, needTrim = true)
+ stringLengthCheck(expr, rawType)
}.getOrElse(expr)
}
private def raiseError(typeName: String, length: Int): Expression = {
val errMsg = UTF8String.fromString(s"Exceeds $typeName type length
limitation: $length")
- RaiseError(Literal(errMsg, StringType), StringType)
+ RaiseError(Literal(errMsg, StringType), StringType)
}
- private def stringLengthCheck(expr: Expression, dt: DataType, needTrim:
Boolean): Expression = {
+ private def stringLengthCheck(expr: Expression, dt: DataType): Expression = {
dt match {
case CharType(length) =>
- val trimmed = if (needTrim) StringTrimRight(expr) else expr
+ val trimmed = StringTrimRight(expr)
// Trailing spaces do not count in the length check. We don't need to
retain the trailing
// spaces, as we will pad char type columns/fields at read time.
- If(
- GreaterThan(Length(trimmed), Literal(length)),
- raiseError("char", length),
- trimmed)
+ If(GreaterThan(Length(trimmed), Literal(length)), raiseError("char",
length), trimmed)
case VarcharType(length) =>
- if (needTrim) {
- val trimmed = StringTrimRight(expr)
- // Trailing spaces do not count in the length check. We need to
retain the trailing spaces
- // (truncate to length N), as there is no read-time padding for
varchar type.
- // TODO: create a special TrimRight function that can trim to a
certain length.
- If(
- LessThanOrEqual(Length(expr), Literal(length)),
- expr,
- If(
- GreaterThan(Length(trimmed), Literal(length)),
- raiseError("varchar", length),
- StringRPad(trimmed, Literal(length))))
- } else {
- If(GreaterThan(Length(expr), Literal(length)), raiseError("varchar",
length), expr)
- }
+ val trimmed = StringTrimRight(expr)
Review comment:
I'm sure you're right, but just for more info, why does that change?
this sounds like an optimization and I wasn't clear why that would mean
read-side doesn't trim anymore.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
