alamb commented on code in PR #7981:
URL: https://github.com/apache/arrow-datafusion/pull/7981#discussion_r1379180032
##########
datafusion/expr/src/logical_plan/plan.rs:
##########
@@ -2132,9 +2181,96 @@ pub struct Limit {
/// Removes duplicate rows from the input
#[derive(Clone, PartialEq, Eq, Hash)]
-pub struct Distinct {
+pub enum Distinct {
+ /// Plain `DISTINCT` referencing all selection expressions
+ All(Arc<LogicalPlan>),
+ /// The `Postgres` addition, allowing separate control over DISTINCT'd and
selected columns
+ On(DistinctOn),
+}
+
+/// Removes duplicate rows from the input
+#[derive(Clone, PartialEq, Eq, Hash)]
+pub struct DistinctOn {
+ /// The `DISTINCT ON` clause expression list
+ pub on_expr: Vec<Expr>,
+ /// The selected projection expression list
+ pub select_expr: Vec<Expr>,
+ /// The `ORDER BY` clause, whose initial expressions must match those of
the `ON` clause
+ pub sort_expr: Option<Vec<Expr>>,
/// The logical plan that is being DISTINCT'd
pub input: Arc<LogicalPlan>,
+ /// The schema description of the DISTINCT ON output
+ pub schema: DFSchemaRef,
+}
+
+impl DistinctOn {
+ /// Create a new `DistintOn` struct.
+ pub fn try_new(
+ on_expr: Vec<Expr>,
+ select_expr: Vec<Expr>,
+ sort_expr: Option<Vec<Expr>>,
+ input: Arc<LogicalPlan>,
+ ) -> Result<Self> {
+ let on_expr = normalize_cols(on_expr, input.as_ref())?;
+
+ // Create fields with any qualifier stuffed in the name itself
Review Comment:
> This is sort of a hack, but the reason I was forced to do it is so that
the plan schema remains unchanged after replace_distinct_aggregate.
Note https://github.com/apache/arrow-datafusion/pull/7997 may be related
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
