adriangb commented on code in PR #12978:
URL: https://github.com/apache/datafusion/pull/12978#discussion_r1819102669
##########
datafusion/core/src/physical_optimizer/pruning.rs:
##########
@@ -3443,6 +3525,385 @@ mod tests {
);
}
+ /// Creates a setup for chunk pruning, modeling a utf8 column "s1"
+ /// with 5 different containers (e.g. RowGroups). They have [min,
+ /// max]:
+ /// s1 ["A", "Z"]
+ /// s1 ["A", "L"]
+ /// s1 ["N", "Z"]
+ /// s1 [NULL, NULL]
+ /// s1 ["A", NULL]
+ /// s1 ["", "A"]
+ /// s1 ["", ""]
+ /// s1 ["AB", "A\u{10ffff}"]
+ /// s1 ["A\u{10ffff}\u{10ffff}\u{10ffff}", "A\u{10ffff}\u{10ffff}"]
+ fn utf8_setup() -> (SchemaRef, TestStatistics) {
+ let schema = Arc::new(Schema::new(vec![Field::new("s1",
DataType::Utf8, true)]));
+
+ let statistics = TestStatistics::new().with(
+ "s1",
+ ContainerStats::new_utf8(
+ vec![
+ Some("A"),
+ Some("A"),
+ Some("N"),
+ Some("M"),
+ None,
+ Some("A"),
+ Some(""),
+ Some(""),
+ Some("AB"),
+ Some("A\u{10ffff}"),
Review Comment:
Thank you, this is great! I believe I fixed it in
https://github.com/apache/datafusion/pull/12978/commits/cc0b70b8af42502a4feea0d7b544c7b1f81fafda
😄
--
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]
