alamb commented on code in PR #8440:
URL: https://github.com/apache/arrow-datafusion/pull/8440#discussion_r1417688911
##########
datafusion/core/src/physical_optimizer/pruning.rs:
##########
@@ -993,95 +1099,139 @@ mod tests {
///
/// Note All `ArrayRefs` must be the same size.
struct ContainerStats {
- min: ArrayRef,
- max: ArrayRef,
+ min: Option<ArrayRef>,
+ max: Option<ArrayRef>,
/// Optional values
null_counts: Option<ArrayRef>,
+ /// Optional known values (e.g. mimic a bloom filter)
+ /// (value, contains)
+ /// If present, all BooleanArrays must be the same size as min/max
+ contains: Vec<(HashSet<ScalarValue>, BooleanArray)>,
}
impl ContainerStats {
+ fn new() -> Self {
+ Default::default()
+ }
fn new_decimal128(
min: impl IntoIterator<Item = Option<i128>>,
max: impl IntoIterator<Item = Option<i128>>,
precision: u8,
scale: i8,
) -> Self {
- Self {
- min: Arc::new(
+ Self::new()
+ .with_min(Arc::new(
min.into_iter()
.collect::<Decimal128Array>()
.with_precision_and_scale(precision, scale)
.unwrap(),
- ),
- max: Arc::new(
+ ))
+ .with_max(Arc::new(
max.into_iter()
.collect::<Decimal128Array>()
.with_precision_and_scale(precision, scale)
.unwrap(),
- ),
- null_counts: None,
- }
+ ))
}
fn new_i64(
min: impl IntoIterator<Item = Option<i64>>,
max: impl IntoIterator<Item = Option<i64>>,
) -> Self {
- Self {
- min: Arc::new(min.into_iter().collect::<Int64Array>()),
- max: Arc::new(max.into_iter().collect::<Int64Array>()),
- null_counts: None,
- }
+ Self::new()
+ .with_min(Arc::new(min.into_iter().collect::<Int64Array>()))
+ .with_max(Arc::new(max.into_iter().collect::<Int64Array>()))
}
fn new_i32(
min: impl IntoIterator<Item = Option<i32>>,
max: impl IntoIterator<Item = Option<i32>>,
) -> Self {
- Self {
- min: Arc::new(min.into_iter().collect::<Int32Array>()),
- max: Arc::new(max.into_iter().collect::<Int32Array>()),
- null_counts: None,
- }
+ Self::new()
+ .with_min(Arc::new(min.into_iter().collect::<Int32Array>()))
+ .with_max(Arc::new(max.into_iter().collect::<Int32Array>()))
}
fn new_utf8<'a>(
min: impl IntoIterator<Item = Option<&'a str>>,
max: impl IntoIterator<Item = Option<&'a str>>,
) -> Self {
- Self {
- min: Arc::new(min.into_iter().collect::<StringArray>()),
- max: Arc::new(max.into_iter().collect::<StringArray>()),
- null_counts: None,
- }
+ Self::new()
+ .with_min(Arc::new(min.into_iter().collect::<StringArray>()))
+ .with_max(Arc::new(max.into_iter().collect::<StringArray>()))
}
fn new_bool(
min: impl IntoIterator<Item = Option<bool>>,
max: impl IntoIterator<Item = Option<bool>>,
) -> Self {
- Self {
- min: Arc::new(min.into_iter().collect::<BooleanArray>()),
- max: Arc::new(max.into_iter().collect::<BooleanArray>()),
- null_counts: None,
- }
+ Self::new()
+ .with_min(Arc::new(min.into_iter().collect::<BooleanArray>()))
+ .with_max(Arc::new(max.into_iter().collect::<BooleanArray>()))
}
fn min(&self) -> Option<ArrayRef> {
- Some(self.min.clone())
+ self.min.clone()
}
fn max(&self) -> Option<ArrayRef> {
- Some(self.max.clone())
+ self.max.clone()
}
fn null_counts(&self) -> Option<ArrayRef> {
self.null_counts.clone()
}
+ /// return an iterator over all arrays in this statistics
+ fn arrays(&self) -> Vec<ArrayRef> {
Review Comment:
this is testing infrastructure
--
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]
