This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new eb6d63fb93 Optimize MIN/MAX when relation is empty (#8940)
eb6d63fb93 is described below
commit eb6d63fb939b0ea01b6404ca5e44e50ee83e2dbc
Author: Liang-Chi Hsieh <vii...@gmail.com>
AuthorDate: Thu Jan 25 10:34:44 2024 -0800
Optimize MIN/MAX when relation is empty (#8940)
* Optimize MIN/MAX when relation is empty
* Fix clippy
---
.../src/physical_optimizer/aggregate_statistics.rs | 98 ++++++++++++++--------
datafusion/sqllogictest/test_files/aggregate.slt | 20 +++++
2 files changed, 84 insertions(+), 34 deletions(-)
diff --git a/datafusion/core/src/physical_optimizer/aggregate_statistics.rs
b/datafusion/core/src/physical_optimizer/aggregate_statistics.rs
index 0a53c775aa..4fe11c14a7 100644
--- a/datafusion/core/src/physical_optimizer/aggregate_statistics.rs
+++ b/datafusion/core/src/physical_optimizer/aggregate_statistics.rs
@@ -198,30 +198,45 @@ fn take_optimizable_min(
stats: &Statistics,
) -> Option<(ScalarValue, String)> {
if let Precision::Exact(num_rows) = &stats.num_rows {
- if *num_rows > 0 {
- let col_stats = &stats.column_statistics;
- if let Some(casted_expr) =
- agg_expr.as_any().downcast_ref::<expressions::Min>()
- {
- if casted_expr.expressions().len() == 1 {
- // TODO optimize with exprs other than Column
- if let Some(col_expr) = casted_expr.expressions()[0]
- .as_any()
- .downcast_ref::<expressions::Column>()
+ match *num_rows {
+ 0 => {
+ // MIN/MAX with 0 rows is always null
+ if let Some(casted_expr) =
+ agg_expr.as_any().downcast_ref::<expressions::Min>()
+ {
+ if let Ok(min_data_type) =
+
ScalarValue::try_from(casted_expr.field().unwrap().data_type())
{
- if let Precision::Exact(val) =
- &col_stats[col_expr.index()].min_value
+ return Some((min_data_type,
casted_expr.name().to_string()));
+ }
+ }
+ }
+ value if value > 0 => {
+ let col_stats = &stats.column_statistics;
+ if let Some(casted_expr) =
+ agg_expr.as_any().downcast_ref::<expressions::Min>()
+ {
+ if casted_expr.expressions().len() == 1 {
+ // TODO optimize with exprs other than Column
+ if let Some(col_expr) = casted_expr.expressions()[0]
+ .as_any()
+ .downcast_ref::<expressions::Column>()
{
- if !val.is_null() {
- return Some((
- val.clone(),
- casted_expr.name().to_string(),
- ));
+ if let Precision::Exact(val) =
+ &col_stats[col_expr.index()].min_value
+ {
+ if !val.is_null() {
+ return Some((
+ val.clone(),
+ casted_expr.name().to_string(),
+ ));
+ }
}
}
}
}
}
+ _ => {}
}
}
None
@@ -233,30 +248,45 @@ fn take_optimizable_max(
stats: &Statistics,
) -> Option<(ScalarValue, String)> {
if let Precision::Exact(num_rows) = &stats.num_rows {
- if *num_rows > 0 {
- let col_stats = &stats.column_statistics;
- if let Some(casted_expr) =
- agg_expr.as_any().downcast_ref::<expressions::Max>()
- {
- if casted_expr.expressions().len() == 1 {
- // TODO optimize with exprs other than Column
- if let Some(col_expr) = casted_expr.expressions()[0]
- .as_any()
- .downcast_ref::<expressions::Column>()
+ match *num_rows {
+ 0 => {
+ // MIN/MAX with 0 rows is always null
+ if let Some(casted_expr) =
+ agg_expr.as_any().downcast_ref::<expressions::Max>()
+ {
+ if let Ok(max_data_type) =
+
ScalarValue::try_from(casted_expr.field().unwrap().data_type())
{
- if let Precision::Exact(val) =
- &col_stats[col_expr.index()].max_value
+ return Some((max_data_type,
casted_expr.name().to_string()));
+ }
+ }
+ }
+ value if value > 0 => {
+ let col_stats = &stats.column_statistics;
+ if let Some(casted_expr) =
+ agg_expr.as_any().downcast_ref::<expressions::Max>()
+ {
+ if casted_expr.expressions().len() == 1 {
+ // TODO optimize with exprs other than Column
+ if let Some(col_expr) = casted_expr.expressions()[0]
+ .as_any()
+ .downcast_ref::<expressions::Column>()
{
- if !val.is_null() {
- return Some((
- val.clone(),
- casted_expr.name().to_string(),
- ));
+ if let Precision::Exact(val) =
+ &col_stats[col_expr.index()].max_value
+ {
+ if !val.is_null() {
+ return Some((
+ val.clone(),
+ casted_expr.name().to_string(),
+ ));
+ }
}
}
}
}
}
+ _ => {}
}
}
None
diff --git a/datafusion/sqllogictest/test_files/aggregate.slt
b/datafusion/sqllogictest/test_files/aggregate.slt
index e9c92f53e0..5cd728c434 100644
--- a/datafusion/sqllogictest/test_files/aggregate.slt
+++ b/datafusion/sqllogictest/test_files/aggregate.slt
@@ -3084,6 +3084,26 @@ SELECT MAX(col0) FROM empty WHERE col0=1;
----
NULL
+query TT
+EXPLAIN SELECT MIN(col0) FROM empty;
+----
+logical_plan
+Aggregate: groupBy=[[]], aggr=[[MIN(empty.col0)]]
+--TableScan: empty projection=[col0]
+physical_plan
+ProjectionExec: expr=[NULL as MIN(empty.col0)]
+--PlaceholderRowExec
+
+query TT
+EXPLAIN SELECT MAX(col0) FROM empty;
+----
+logical_plan
+Aggregate: groupBy=[[]], aggr=[[MAX(empty.col0)]]
+--TableScan: empty projection=[col0]
+physical_plan
+ProjectionExec: expr=[NULL as MAX(empty.col0)]
+--PlaceholderRowExec
+
statement ok
DROP TABLE empty;
