alamb commented on a change in pull request #2000:
URL: https://github.com/apache/arrow-datafusion/pull/2000#discussion_r838874385
##########
File path: datafusion/tests/path_partition.rs
##########
@@ -40,6 +40,63 @@ use datafusion::{
};
use futures::{stream, StreamExt};
+#[tokio::test]
+async fn parquet_distinct_partition_col() -> Result<()> {
+ let mut ctx = SessionContext::new();
+
+ register_partitioned_alltypes_parquet(
+ &mut ctx,
+ &[
+ "year=2021/month=09/day=09/file.parquet",
+ "year=2021/month=10/day=09/file.parquet",
+ "year=2021/month=10/day=28/file.parquet",
+ ],
+ &["year", "month", "day"],
+ "",
+ "alltypes_plain.parquet",
+ )
+ .await;
+
+ let result = ctx
+ .sql("SELECT distinct year,month,day FROM t")
+ .await?
+ .collect()
+ .await?;
+
+ let expected = vec![
+ "+------+-------+-----+",
+ "| year | month | day |",
+ "+------+-------+-----+",
+ "| 2021 | 09 | 09 |",
+ "| 2021 | 10 | 09 |",
+ "| 2021 | 10 | 28 |",
+ "+------+-------+-----+",
+ ];
+ assert_batches_sorted_eq!(expected, &result);
+
+ let actual_row_count: usize = ctx
+ .sql("SELECT id from t")
+ .await?
+ .collect()
+ .await?
+ .into_iter()
+ .map(|batch| batch.num_rows())
+ .sum();
+
+ let partition_row_count: usize = ctx
Review comment:
Given there is special case handling for `LIMIT` perhaps we should also
add a test that uses a limit, such as `LIMIT 1`?
--
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]
