isidentical commented on code in PR #3787:
URL: https://github.com/apache/arrow-datafusion/pull/3787#discussion_r993810253
##########
datafusion/core/src/physical_plan/join_utils.rs:
##########
@@ -296,6 +299,154 @@ impl<T> Clone for OnceFut<T> {
}
}
+/// A shared state between statistic aggregators for a join
+/// operation.
+#[derive(Clone, Debug, Default)]
+struct PartialJoinStatistics {
+ pub num_rows: usize,
+ pub column_statistics: Vec<ColumnStatistics>,
+}
+
+/// Calculate the statistics for the given join's output.
+pub(crate) fn join_statistics(
+ left: Arc<dyn ExecutionPlan>,
+ right: Arc<dyn ExecutionPlan>,
+ on: JoinOn,
+ join_type: &JoinType,
+) -> Statistics {
+ let left_stats = left.statistics();
+ let right_stats = right.statistics();
+
+ let join_stats = join_cardinality(join_type, left_stats, right_stats, &on);
+ let (num_rows, column_statistics) = match join_stats {
+ Some(stats) => (Some(stats.num_rows), Some(stats.column_statistics)),
+ None => (None, None),
+ };
+ Statistics {
+ num_rows,
+ total_byte_size: None,
+ column_statistics,
+ is_exact: false,
+ }
+}
+
+// Estimate the cardinality for the given join with input statistics.
+fn join_cardinality(
Review Comment:
Makes perfect sense!
--
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]
