berkaysynnada commented on code in PR #15954:
URL: https://github.com/apache/datafusion/pull/15954#discussion_r2105794126
##########
datafusion/core/tests/physical_optimizer/partition_statistics.rs:
##########
@@ -488,4 +520,213 @@ mod test {
assert_eq!(statistics[0], expected_statistic_partition);
Ok(())
}
+
+ #[tokio::test]
+ async fn test_statistic_by_partition_of_agg() -> Result<()> {
+ let scan = create_scan_exec_with_statistics(None, Some(2)).await;
+
+ let scan_schema = scan.schema();
+
+ let group_by = PhysicalGroupBy::new_single(vec![
+ (col("id", &scan_schema)?, "id".to_string()),
+ (
+ binary(
+ lit(1),
+ Operator::Plus,
+ col("id", &scan_schema)?,
+ &scan_schema,
+ )?,
+ "expr".to_string(),
+ ),
+ ]);
+
+ let aggr_expr = vec![AggregateExprBuilder::new(count_udaf(),
vec![lit(1)])
+ .schema(Arc::clone(&scan_schema))
+ .alias(String::from("COUNT(c)"))
+ .build()
+ .map(Arc::new)?];
+
+ let aggregate_exec_partial = Arc::new(AggregateExec::try_new(
+ AggregateMode::Partial,
+ group_by.clone(),
+ aggr_expr.clone(),
+ vec![None],
+ Arc::clone(&scan),
+ scan_schema.clone(),
+ )?);
Review Comment:
you can apply the same to the other plans to ease reviews
##########
datafusion/core/tests/physical_optimizer/partition_statistics.rs:
##########
@@ -488,4 +520,213 @@ mod test {
assert_eq!(statistics[0], expected_statistic_partition);
Ok(())
}
+
+ #[tokio::test]
+ async fn test_statistic_by_partition_of_agg() -> Result<()> {
+ let scan = create_scan_exec_with_statistics(None, Some(2)).await;
+
+ let scan_schema = scan.schema();
+
+ let group_by = PhysicalGroupBy::new_single(vec![
+ (col("id", &scan_schema)?, "id".to_string()),
+ (
+ binary(
+ lit(1),
+ Operator::Plus,
+ col("id", &scan_schema)?,
+ &scan_schema,
+ )?,
+ "expr".to_string(),
+ ),
+ ]);
+
+ let aggr_expr = vec![AggregateExprBuilder::new(count_udaf(),
vec![lit(1)])
+ .schema(Arc::clone(&scan_schema))
+ .alias(String::from("COUNT(c)"))
+ .build()
+ .map(Arc::new)?];
+
+ let aggregate_exec_partial = Arc::new(AggregateExec::try_new(
+ AggregateMode::Partial,
+ group_by.clone(),
+ aggr_expr.clone(),
+ vec![None],
+ Arc::clone(&scan),
+ scan_schema.clone(),
+ )?);
Review Comment:
```suggestion
)?) as _;
let mut plan_string = get_plan_string(&aggregate_exec_partial);
let _ = plan_string.swap_remove(1);
let expected_plan = vec![
"AggregateExec: mode=Partial, gby=[id@0 as id, 1 + id@0 as
expr], aggr=[COUNT(c)]",
//" DataSourceExec: file_groups={2 groups:
[[.../datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-01/j5fUeSDQo22oPyPU.parquet,
.../datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-02/j5fUeSDQo22oPyPU.parquet],
[.../datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-03/j5fUeSDQo22oPyPU.parquet,
.../datafusion/core/tests/data/test_statistics_per_partition/date=2025-03-04/j5fUeSDQo22oPyPU.parquet]]},
projection=[id, date], file_type=parquet
];
assert_eq!(plan_string, expected_plan);
```
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
