This is an automated email from the ASF dual-hosted git repository.
comphead pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 23d7fff0f8 Improve documentation for
AggregateUDFImpl::value_from_stats (#12689)
23d7fff0f8 is described below
commit 23d7fff0f88409f3183151b7a4f8441e9bcc08fd
Author: Andrew Lamb <[email protected]>
AuthorDate: Tue Oct 1 15:01:21 2024 -0400
Improve documentation for AggregateUDFImpl::value_from_stats (#12689)
* Improve documentation for AggregateUDFImpl::value_from_stats
* Update datafusion/expr/src/udaf.rs
Co-authored-by: Oleks V <[email protected]>
---------
Co-authored-by: Oleks V <[email protected]>
---
datafusion/expr/src/udaf.rs | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/datafusion/expr/src/udaf.rs b/datafusion/expr/src/udaf.rs
index d8592bce60..780ea36910 100644
--- a/datafusion/expr/src/udaf.rs
+++ b/datafusion/expr/src/udaf.rs
@@ -95,8 +95,11 @@ impl fmt::Display for AggregateUDF {
}
}
+/// Arguments passed to [`AggregateUDFImpl::value_from_stats`]
pub struct StatisticsArgs<'a> {
+ /// The statistics of the aggregate input
pub statistics: &'a Statistics,
+ /// The resolved return type of the aggregate function
pub return_type: &'a DataType,
/// Whether the aggregate function is distinct.
///
@@ -251,13 +254,16 @@ impl AggregateUDF {
}
/// Returns true if the function is max, false if the function is min
- /// None in all other cases, used in certain optimizations or
+ /// None in all other cases, used in certain optimizations for
/// or aggregate
- ///
pub fn is_descending(&self) -> Option<bool> {
self.inner.is_descending()
}
+ /// Return the value of this aggregate function if it can be determined
+ /// entirely from statistics and arguments.
+ ///
+ /// See [`AggregateUDFImpl::value_from_stats`] for more details.
pub fn value_from_stats(
&self,
statistics_args: &StatisticsArgs,
@@ -577,7 +583,15 @@ pub trait AggregateUDFImpl: Debug + Send + Sync {
fn is_descending(&self) -> Option<bool> {
None
}
- // Return the value of the current UDF from the statistics
+
+ /// Return the value of this aggregate function if it can be determined
+ /// entirely from statistics and arguments.
+ ///
+ /// Using a [`ScalarValue`] rather than a runtime computation can
significantly
+ /// improving query performance.
+ ///
+ /// For example, if the minimum value of column `x` is known to be `42`
from
+ /// statistics, then the aggregate `MIN(x)` should return
`Some(ScalarValue(42))`
fn value_from_stats(&self, _statistics_args: &StatisticsArgs) ->
Option<ScalarValue> {
None
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
