zhuqi-lucas commented on code in PR #14566:
URL: https://github.com/apache/datafusion/pull/14566#discussion_r1957146770
##########
datafusion/physical-plan/src/aggregates/order/partial.rs:
##########
@@ -207,46 +222,151 @@ impl GroupOrderingPartial {
let max_group_index = total_num_groups - 1;
- // compute the sort key values for each group
- let sort_keys = self.compute_sort_keys(batch_group_values)?;
-
- let old_state = std::mem::take(&mut self.state);
- let (mut current_sort, mut sort_key) = match &old_state {
+ let (current_sort, sort_key) = match std::mem::take(&mut self.state) {
State::Taken => unreachable!("State previously taken"),
- State::Start => (0, sort_keys.row(0)),
+ State::Start => (0, None),
State::InProgress {
current_sort,
sort_key,
..
- } => (*current_sort, sort_key.row()),
+ } => (current_sort, Some(sort_key)),
State::Complete => {
panic!("Saw new group after the end of input");
}
};
- // Find latest sort key
- let iter = group_indices.iter().zip(sort_keys.iter());
- for (&group_index, group_sort_key) in iter {
- // Does this group have seen a new sort_key?
- if sort_key != group_sort_key {
- current_sort = group_index;
- sort_key = group_sort_key;
- }
- }
+ // Select the sort key columns
+ let sort_keys = self.compute_sort_keys(batch_group_values);
+
+ // Check if the sort keys indicate a boundary inside the batch
+ let ranges = partition(&sort_keys)?.ranges();
+ let last_range = ranges.last().unwrap();
+
+ let range_current_sort = group_indices[last_range.start];
+ let range_sort_key = get_row_at_idx(&sort_keys, last_range.start)?;
+
+ let (current_sort, sort_key) = if last_range.start == 0 {
+ // There was no boundary in the batch. Compare with wthe previous
sort_key (if present)
Review Comment:
Minor typo:
with wthe previous
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
