rdettai commented on a change in pull request #965:
URL: https://github.com/apache/arrow-datafusion/pull/965#discussion_r706860145
##########
File path: datafusion/src/physical_plan/limit.rs
##########
@@ -135,6 +135,27 @@ impl ExecutionPlan for GlobalLimitExec {
}
}
}
+
+ fn statistics(&self) -> Statistics {
+ let input_stats = self.input.statistics();
+ match input_stats {
+ // if the input does not reach the limit globally, return input
stats
+ Statistics {
+ num_rows: Some(nr), ..
+ } if nr <= self.limit => input_stats,
+ // if the input is greater than the limit, the num_row will be the
limit
+ // but we won't be able to predict the other statistics
+ Statistics {
+ num_rows: Some(nr), ..
+ } if nr > self.limit => Statistics {
+ num_rows: Some(self.limit),
+ is_exact: input_stats.is_exact,
Review comment:
See
https://github.com/apache/arrow-datafusion/pull/965#issuecomment-917665454
##########
File path: datafusion/src/physical_plan/hash_join.rs
##########
@@ -462,6 +462,13 @@ impl ExecutionPlan for HashJoinExec {
fn metrics(&self) -> Option<MetricsSet> {
Some(self.metrics.clone_inner())
}
+
+ fn statistics(&self) -> Statistics {
+ // TODO stats: it is not possible in general to know the output size
of joins
Review comment:
See
https://github.com/apache/arrow-datafusion/pull/965#issuecomment-917665454
##########
File path: datafusion/src/physical_plan/filter.rs
##########
@@ -144,6 +144,11 @@ impl ExecutionPlan for FilterExec {
fn metrics(&self) -> Option<MetricsSet> {
Some(self.metrics.clone_inner())
}
+
+ /// The output statistics of a filtering operation are unknown
Review comment:
See
https://github.com/apache/arrow-datafusion/pull/965#issuecomment-917665454
--
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]
