Ted-Jiang commented on code in PR #2156:
URL: https://github.com/apache/arrow-datafusion/pull/2156#discussion_r841780981
##########
datafusion/physical-expr/src/expressions/in_list.rs:
##########
@@ -220,17 +260,63 @@ fn not_in_list_utf8<OffsetSize: StringOffsetSizeTrait>(
compare_op_scalar!(array, values, |x, v: &[&str]| !v.contains(&x))
}
+//check all filter values of In clause are static.
+//include `CastExpr + Literal` or `Literal`
+fn check_all_static_filter_expr(list: &[Arc<dyn PhysicalExpr>]) -> bool {
+ list.iter().all(|v| {
+ let cast = v.as_any().downcast_ref::<expressions::CastExpr>();
+ if let Some(c) = cast {
+ c.expr()
+ .as_any()
+ .downcast_ref::<expressions::Literal>()
+ .is_some()
+ } else {
+ let cast = v.as_any().downcast_ref::<expressions::Literal>();
+ cast.is_some()
+ }
+ })
+}
+
+fn cast_static_filter_to_set(list: &[Arc<dyn PhysicalExpr>]) ->
HashSet<ScalarValue> {
+ HashSet::from_iter(list.iter().map(|expr| {
+ if let Some(cast) =
expr.as_any().downcast_ref::<expressions::CastExpr>() {
+ cast.expr()
+ .as_any()
+ .downcast_ref::<expressions::Literal>()
+ .unwrap()
+ .value()
+ .clone()
+ } else {
+ expr.as_any()
+ .downcast_ref::<expressions::Literal>()
+ .unwrap()
+ .value()
+ .clone()
+ }
+ }))
+}
+
impl InListExpr {
/// Create a new InList expression
pub fn new(
expr: Arc<dyn PhysicalExpr>,
list: Vec<Arc<dyn PhysicalExpr>>,
negated: bool,
) -> Self {
- Self {
- expr,
- list,
- negated,
+ if list.len() > OPTIMIZER_INSET_THRESHOLD &&
check_all_static_filter_expr(&list) {
Review Comment:
According to Spark, default set 400.
--
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]
