alamb commented on code in PR #8243:
URL: https://github.com/apache/arrow-datafusion/pull/8243#discussion_r1414535729
##########
datafusion/physical-plan/src/filter.rs:
##########
@@ -994,4 +1014,22 @@ mod tests {
Ok(())
}
+
+ #[tokio::test]
+ async fn test_validation_filter_selectivity() -> Result<()> {
Review Comment:
> Not sure however how
[this](https://github.com/apache/arrow-datafusion/blob/main/datafusion/physical-plan/src/filter.rs#L221)
should be handled
That code will be invoked for 'complicated' predicates -- maybe we could
fake it with something like `sin(x) = 4.0`.
##########
datafusion/physical-plan/src/filter.rs:
##########
@@ -994,4 +1014,54 @@ mod tests {
Ok(())
}
+
+ #[tokio::test]
+ async fn test_validation_filter_selectivity() -> Result<()> {
+ let schema = Schema::new(vec![Field::new("a", DataType::Int32,
false)]);
+ let input = Arc::new(StatisticsExec::new(
+ Statistics::new_unknown(&schema),
+ schema,
+ ));
+ // WHERE a = 10
+ let predicate = Arc::new(BinaryExpr::new(
+ Arc::new(Column::new("a", 0)),
+ Operator::Eq,
+ Arc::new(Literal::new(ScalarValue::Int32(Some(10)))),
+ ));
+ let filter = FilterExec::try_new(predicate, input)?;
+ assert!(filter.with_default_selectivity(120).is_err());
+ Ok(())
+ }
+
+ #[tokio::test]
+ async fn test_custom_filter_selectivity() -> Result<()> {
+ // Need a decimal to trigger inexact selectivity
+ let schema =
+ Schema::new(vec![Field::new("a", DataType::Decimal128(2, 3),
false)]);
+ let input = Arc::new(StatisticsExec::new(
+ Statistics {
+ num_rows: Precision::Inexact(1000),
+ total_byte_size: Precision::Inexact(4000),
+ column_statistics: vec![ColumnStatistics {
+ ..Default::default()
+ }],
+ },
+ schema,
+ ));
+ // WHERE a = 10
+ let predicate = Arc::new(BinaryExpr::new(
+ Arc::new(Column::new("a", 0)),
+ Operator::Eq,
+ Arc::new(Literal::new(ScalarValue::Decimal128(Some(10), 10, 10))),
+ ));
+ let filter = FilterExec::try_new(predicate, input)?;
+ let statistics = filter.statistics()?;
+ assert_eq!(statistics.num_rows, Precision::Inexact(200));
Review Comment:
👌 very nice
##########
datafusion/physical-plan/src/filter.rs:
##########
@@ -994,4 +1014,54 @@ mod tests {
Ok(())
}
+
+ #[tokio::test]
+ async fn test_validation_filter_selectivity() -> Result<()> {
+ let schema = Schema::new(vec![Field::new("a", DataType::Int32,
false)]);
+ let input = Arc::new(StatisticsExec::new(
+ Statistics::new_unknown(&schema),
+ schema,
+ ));
+ // WHERE a = 10
+ let predicate = Arc::new(BinaryExpr::new(
+ Arc::new(Column::new("a", 0)),
+ Operator::Eq,
+ Arc::new(Literal::new(ScalarValue::Int32(Some(10)))),
+ ));
+ let filter = FilterExec::try_new(predicate, input)?;
+ assert!(filter.with_default_selectivity(120).is_err());
+ Ok(())
+ }
+
+ #[tokio::test]
+ async fn test_custom_filter_selectivity() -> Result<()> {
+ // Need a decimal to trigger inexact selectivity
+ let schema =
+ Schema::new(vec![Field::new("a", DataType::Decimal128(2, 3),
false)]);
+ let input = Arc::new(StatisticsExec::new(
+ Statistics {
+ num_rows: Precision::Inexact(1000),
+ total_byte_size: Precision::Inexact(4000),
+ column_statistics: vec![ColumnStatistics {
+ ..Default::default()
+ }],
+ },
+ schema,
+ ));
+ // WHERE a = 10
+ let predicate = Arc::new(BinaryExpr::new(
+ Arc::new(Column::new("a", 0)),
+ Operator::Eq,
+ Arc::new(Literal::new(ScalarValue::Decimal128(Some(10), 10, 10))),
+ ));
+ let filter = FilterExec::try_new(predicate, input)?;
+ let statistics = filter.statistics()?;
+ assert_eq!(statistics.num_rows, Precision::Inexact(200));
Review Comment:
👌 very nice
--
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]
