beliefer commented on a change in pull request #27058: [SPARK-30276][SQL]
Support Filter expression allows simultaneous use of DISTINCT
URL: https://github.com/apache/spark/pull/27058#discussion_r371613436
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/dsl/package.scala
##########
@@ -165,20 +165,35 @@ package object dsl {
}
def rand(e: Long): Expression = Rand(e)
- def sum(e: Expression): Expression = Sum(e).toAggregateExpression()
- def sumDistinct(e: Expression): Expression =
Sum(e).toAggregateExpression(isDistinct = true)
- def count(e: Expression): Expression = Count(e).toAggregateExpression()
+ def sum(e: Expression, filter: Option[Expression] = None): Expression =
+ Sum(e).toAggregateExpression(false, filter)
+ def sumDistinct(e: Expression, filter: Option[Expression] = None):
Expression =
+ Sum(e).toAggregateExpression(true, filter)
+ def count(e: Expression, filter: Option[Expression] = None): Expression =
+ Count(e).toAggregateExpression(false, filter)
def countDistinct(e: Expression*): Expression =
Count(e).toAggregateExpression(isDistinct = true)
- def approxCountDistinct(e: Expression, rsd: Double = 0.05): Expression =
- HyperLogLogPlusPlus(e, rsd).toAggregateExpression()
- def avg(e: Expression): Expression = Average(e).toAggregateExpression()
- def first(e: Expression): Expression = new First(e).toAggregateExpression()
- def last(e: Expression): Expression = new Last(e).toAggregateExpression()
- def min(e: Expression): Expression = Min(e).toAggregateExpression()
- def minDistinct(e: Expression): Expression =
Min(e).toAggregateExpression(isDistinct = true)
- def max(e: Expression): Expression = Max(e).toAggregateExpression()
- def maxDistinct(e: Expression): Expression =
Max(e).toAggregateExpression(isDistinct = true)
+ def countDistinct(filter: Option[Expression], e: Expression*): Expression =
+ Count(e).toAggregateExpression(true, filter)
+ def approxCountDistinct(
+ e: Expression,
+ rsd: Double = 0.05,
+ filter: Option[Expression] = None): Expression =
+ HyperLogLogPlusPlus(e, rsd).toAggregateExpression(true, filter)
+ def avg(e: Expression, filter: Option[Expression] = None): Expression =
+ Average(e).toAggregateExpression(false, filter)
+ def first(e: Expression, filter: Option[Expression] = None): Expression =
+ new First(e).toAggregateExpression(false, filter)
+ def last(e: Expression, filter: Option[Expression] = None): Expression =
+ new Last(e).toAggregateExpression(false, filter)
+ def min(e: Expression, filter: Option[Expression] = None): Expression =
+ Min(e).toAggregateExpression(false, filter)
+ def minDistinct(e: Expression, filter: Option[Expression] = None):
Expression =
+ Min(e).toAggregateExpression(true, filter)
+ def max(e: Expression, filter: Option[Expression] = None): Expression =
+ Max(e).toAggregateExpression(false, filter)
+ def maxDistinct(e: Expression, filter: Option[Expression] = None):
Expression =
+ Max(e).toAggregateExpression(true, filter)
def upper(e: Expression): Expression = Upper(e)
Review comment:
Ok
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
