Ted-Jiang commented on code in PR #5268:
URL: https://github.com/apache/arrow-datafusion/pull/5268#discussion_r1105340349
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -1331,6 +1330,80 @@ mod tests {
assert_eq!(get_value(&metrics, "pushdown_rows_filtered"), 5);
}
+ #[tokio::test]
+ async fn evolved_schema_disjoint_schema_with_page_index_pushdown() {
+ let c1: ArrayRef = Arc::new(StringArray::from(vec![
+ // Page 1
+ Some("Foo"),
+ Some("Bar"),
+ // Page 2
+ Some("Foo2"),
+ Some("Bar2"),
+ // Page 3
+ Some("Foo3"),
+ Some("Bar3"),
+ ]));
+
+ let c2: ArrayRef = Arc::new(Int64Array::from(vec![
+ // Page 1:
+ Some(1),
+ Some(2),
+ // Page 2: (pruned)
+ Some(3),
+ Some(4),
+ // Page 3: (pruned)
+ Some(5),
+ None,
+ ]));
+
+ // batch1: c1(string)
+ let batch1 = create_batch(vec![("c1", c1.clone())]);
+
+ // batch2: c2(int64)
+ let batch2 = create_batch(vec![("c2", c2.clone())]);
+
+ // batch3 (has c2, c1) -- both columns, should still prune
+ let batch3 = create_batch(vec![("c1", c1.clone()), ("c2",
c2.clone())]);
+
+ // batch4 (has c2, c1) -- different column order, should still prune
Review Comment:
Nice test case 👍
--
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
