mustafasrepo commented on code in PR #6904:
URL: https://github.com/apache/arrow-datafusion/pull/6904#discussion_r1260684595
##########
datafusion/physical-expr/src/aggregate/count.rs:
##########
@@ -76,6 +85,114 @@ impl Count {
}
}
+/// An accumulator to compute the counts of [`PrimitiveArray<T>`].
+/// Stores values as native types, and does overflow checking
+///
+/// Unlike most other accumulators, COUNT never produces NULLs. If no
+/// non-null values are seen in any group the output is 0. Thus, this
+/// accumulator has no additional null or seen filter tracking.
+#[derive(Debug)]
+struct CountGroupsAccumulator {
+ /// Count per group.
+ ///
+ /// Note this is an i64 and not a u64 (or usize) because the
+ /// output type of count is `DataType::Int64`. Thus by using `i64`
+ /// for the counts, the output [`Int64Array`] can be created
+ /// without copy.
+ counts: Vec<i64>,
+}
+
+impl CountGroupsAccumulator {
+ pub fn new() -> Self {
+ Self { counts: vec![] }
+ }
+}
+
+impl GroupsAccumulator for CountGroupsAccumulator {
+ fn update_batch(
+ &mut self,
+ values: &[ArrayRef],
+ group_indices: &[usize],
+ opt_filter: Option<&arrow_array::BooleanArray>,
+ total_num_groups: usize,
+ ) -> Result<()> {
+ assert_eq!(values.len(), 1, "single argument to update_batch");
+ let values = values.get(0).unwrap();
+
+ // Add one to each group's counter for each non null, non
+ // filtered value
+ self.counts.resize(total_num_groups, 0);
+ accumulate_indices(
+ group_indices,
+ values.nulls(), // ignore values
+ opt_filter,
+ |group_index| {
+ self.counts[group_index] += 1;
+ },
+ );
+
+ Ok(())
+ }
+
+ fn merge_batch(
+ &mut self,
+ values: &[ArrayRef],
+ group_indices: &[usize],
+ opt_filter: Option<&arrow_array::BooleanArray>,
+ total_num_groups: usize,
+ ) -> Result<()> {
+ assert_eq!(values.len(), 1, "one argument to merge_batch");
+ // first batch is counts, second is partial sums
+ let partial_counts =
values.get(0).unwrap().as_primitive::<Int64Type>();
Review Comment:
Similar to you can use values[0]
--
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]
