Optimize MIN/MAX when relation is empty

viirya · Jan 21, 2024 · 8b2839a · 8b2839a
1 parent f5a97d5
commit 8b2839a
Show file tree

Hide file tree

Showing 2 changed files with 42 additions and 0 deletions.
diff --git a/datafusion/core/src/physical_optimizer/aggregate_statistics.rs b/datafusion/core/src/physical_optimizer/aggregate_statistics.rs
@@ -222,6 +222,17 @@ fn take_optimizable_min(
                     }
                 }
             }
+        } else if *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())
+                {
+                    return Some((min_data_type, casted_expr.name().to_string()));
+                }
+            }
         }
     }
     None
@@ -257,6 +268,17 @@ fn take_optimizable_max(
                     }
                 }
             }
+        } else if *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())
+                {
+                    return Some((max_data_type, casted_expr.name().to_string()));
+                }
+            }
         }
     }
     None

diff --git a/datafusion/sqllogictest/test_files/aggregate.slt b/datafusion/sqllogictest/test_files/aggregate.slt
@@ -3276,6 +3276,26 @@ 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;