Dandandan commented on code in PR #8721:
URL: https://github.com/apache/arrow-datafusion/pull/8721#discussion_r1441725545
##########
datafusion/physical-expr/src/aggregate/count_distinct.rs:
##########
@@ -192,6 +262,164 @@ impl Accumulator for DistinctCountAccumulator {
}
}
+#[derive(Debug)]
+struct NativeDistinctCountAccumulator<T>
+where
+ T: ArrowPrimitiveType + Send,
+ T::Native: Eq + Hash,
+{
+ values: HashSet<T::Native, RandomState>,
+}
+
+impl<T> NativeDistinctCountAccumulator<T>
+where
+ T: ArrowPrimitiveType + Send,
+ T::Native: Eq + Hash,
+{
+ fn new() -> Self {
+ Self {
+ values: HashSet::default(),
+ }
+ }
+}
+
+impl<T> Accumulator for NativeDistinctCountAccumulator<T>
+where
+ T: ArrowPrimitiveType + Send + Debug,
+ T::Native: Eq + Hash,
+{
+ fn state(&self) -> Result<Vec<ScalarValue>> {
+ let arr = Arc::new(PrimitiveArray::<T>::from_iter_values(
+ self.values.iter().cloned(),
+ )) as ArrayRef;
+ let list = Arc::new(array_into_list_array(arr)) as ArrayRef;
+ Ok(vec![ScalarValue::List(list)])
+ }
+
+ fn update_batch(&mut self, values: &[ArrayRef]) -> Result<()> {
+ if values.is_empty() {
+ return Ok(());
+ }
+
+ let arr = as_primitive_array::<T>(&values[0])?;
+ arr.iter().for_each(|value| {
+ if let Some(value) = value {
+ self.values.insert(value);
+ }
+ });
+
+ Ok(())
+ }
+
+ fn merge_batch(&mut self, states: &[ArrayRef]) -> Result<()> {
+ if states.is_empty() {
+ return Ok(());
+ }
+ assert_eq!(
+ states.len(),
+ 1,
+ "count_distinct states must be single array"
+ );
+
+ let arr = as_list_array(&states[0])?;
+ arr.iter().try_for_each(|maybe_list| {
+ if let Some(list) = maybe_list {
+ let list = as_primitive_array::<T>(&list)?;
+ self.values.extend(list.values())
+ };
+ Ok(())
+ })
+ }
+
+ fn evaluate(&self) -> Result<ScalarValue> {
+ Ok(ScalarValue::Int64(Some(self.values.len() as i64)))
+ }
+
+ fn size(&self) -> usize {
+ std::mem::size_of_val(self)
+ + std::mem::size_of_val(&self.values)
+ + (std::mem::size_of::<T::Native>() * self.values.capacity())
Review Comment:
We probably need to address in different places where we use HashMap /
HashSets / RawTable, so I'm fine with keeping this out of this PR for now.
--
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]
