alamb commented on code in PR #7574:
URL: https://github.com/apache/arrow-rs/pull/7574#discussion_r2121801326
##########
parquet/tests/arrow_reader/statistics.rs:
##########
@@ -354,7 +376,45 @@ impl Test<'_> {
//
// Remaining cases
// f64::NAN
-// - Using truncated statistics ("exact min value" and "exact max value"
https://docs.rs/parquet/latest/parquet/file/statistics/enum.Statistics.html#method.max_is_exact)
+
+#[tokio::test]
+async fn test_max_and_min_value_truncated() {
+ let reader = TestReader {
+ scenario: Scenario::TruncatedUTF8,
+ row_per_group: 5,
+ }
+ .build()
+ .await;
+
+ Test {
+ reader: &reader,
+ // min is truncated to
+ // 1. `"a".repeate(64)`, original value is `"a".repeat(64) + "1"`
+ // 2. "", since there's a null in the second row group
+ // 3. "j"
+ expected_min: Arc::new(StringArray::from(vec![&("a".repeat(64)), "",
"j"])),
Review Comment:
An issue sounds like a good idea. Let me know if you need any help
Thanks again for looking at it
--
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...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
