Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion datafusion/core/tests/custom_sources_cases/statistics.rs
Original file line number Diff line number Diff line change
Expand Up @@ -272,7 +272,7 @@ async fn sql_filter() -> Result<()> {

let physical_plan = df.create_physical_plan().await.unwrap();
let stats = physical_plan.partition_statistics(None)?;
assert_eq!(stats.num_rows, Precision::Inexact(1));
assert_eq!(stats.num_rows, Precision::Inexact(7));

Ok(())
}
Expand Down
15 changes: 13 additions & 2 deletions datafusion/physical-expr/src/analysis.rs
Original file line number Diff line number Diff line change
Expand Up @@ -167,6 +167,7 @@ pub fn analyze(
schema: &Schema,
) -> Result<AnalysisContext> {
let initial_boundaries = &context.boundaries;

if initial_boundaries
.iter()
.all(|bound| bound.interval.is_none())
Expand Down Expand Up @@ -277,8 +278,18 @@ fn calculate_selectivity(
let mut acc: f64 = 1.0;
for (initial, target) in initial_boundaries.iter().zip(target_boundaries) {
match (initial.interval.as_ref(), target.interval.as_ref()) {
(Some(initial), Some(target)) => {
acc *= cardinality_ratio(initial, target);
(Some(initial_interval), Some(target_interval)) => {
// If it is equality predicate, calculate selectivity as `1 / distinct_count`
if let Precision::Exact(distinct_count)
| Precision::Inexact(distinct_count) = target.distinct_count
&& distinct_count > 0
&& !target_interval.lower().is_null()
&& target_interval.lower() == target_interval.upper()
{
acc *= 1.0 / distinct_count as f64;
continue;
}
acc *= cardinality_ratio(initial_interval, target_interval);
}
(None, Some(_)) => {
return internal_err!(
Expand Down
Loading