AdamGS commented on code in PR #24027:
URL: https://github.com/apache/datafusion/pull/24027#discussion_r3719994742
##########
datafusion/common/src/stats.rs:
##########
@@ -3345,4 +3347,33 @@ mod tests {
precision_add_for_sum_in_place(&mut lhs, &Precision::Absent);
assert_eq!(lhs, Precision::Absent);
}
+
+ #[test]
+ fn test_calculate_total_byte_size() {
+ let primitive_schema = Schema::new(vec![Field::new("a",
DataType::Int32, false)]);
+ let non_primitive_schema =
+ Schema::new(vec![Field::new("a", DataType::Utf8, false)]);
+
+ // All-primitive schema with a known row count computes an exact size.
+ let mut stats = Statistics::new_unknown(&primitive_schema);
+ stats.num_rows = Precision::Exact(10);
+ stats.calculate_total_byte_size(&primitive_schema);
+ assert_eq!(stats.total_byte_size, Precision::Exact(40));
+
+ // All-primitive schema with an unknown row count keeps a previously
+ // known `total_byte_size`, downgraded to inexact, instead of
+ // discarding it to `Absent`.
+ let mut stats = Statistics::new_unknown(&primitive_schema);
+ stats.total_byte_size = Precision::Inexact(1234);
Review Comment:
Should this start as `Exact` so it actually downgrades?
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
