alamb commented on code in PR #2170:
URL: https://github.com/apache/arrow-datafusion/pull/2170#discussion_r844309727
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -878,6 +880,39 @@ mod tests {
assert_batches_sorted_eq!(expected, &read);
}
+ #[tokio::test]
+ async fn evolved_schema_intersection_filter() {
+ let c1: ArrayRef =
+ Arc::new(StringArray::from(vec![Some("Foo"), None, Some("bar")]));
+
+ let c2: ArrayRef = Arc::new(Int64Array::from(vec![Some(1), Some(2),
None]));
+
+ let c3: ArrayRef = Arc::new(Int8Array::from(vec![Some(10), Some(20),
None]));
+
+ // batch1: c1(string), c2(int64), c3(int8)
+ let batch1 = create_batch(vec![("c1", c1), ("c3", c3.clone())]);
+
+ // batch2: c3(int8), c2(int64), c1(string)
+ let batch2 = create_batch(vec![("c3", c3), ("c2", c2)]);
+
+ let filter = col("c2").eq(lit(0_i64));
+
+ // read/write them files:
+ let read = round_trip_to_parquet(vec![batch1, batch2], None, None,
Some(filter))
+ .await
+ .unwrap();
+ let expected = vec![
+ "+-----+----+----+",
+ "| c1 | c3 | c2 |",
Review Comment:
Makes sense -- a comment in the test to explain why it is ok would be
helpful for future readers
--
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]
