alamb commented on code in PR #5268:
URL: https://github.com/apache/arrow-datafusion/pull/5268#discussion_r1105045157
##########
datafusion/core/src/physical_plan/file_format/parquet.rs:
##########
@@ -1635,27 +1740,38 @@ mod tests {
#[tokio::test]
async fn parquet_page_index_exec_metrics() {
- let c1: ArrayRef = Arc::new(Int32Array::from(vec![Some(1), None,
Some(2)]));
- let c2: ArrayRef = Arc::new(Int32Array::from(vec![Some(3), Some(4),
Some(5)]));
+ let c1: ArrayRef = Arc::new(Int32Array::from(vec![
+ Some(1),
+ None,
+ Some(2),
+ Some(3),
+ Some(4),
+ Some(5),
+ ]));
let batch1 = create_batch(vec![("int", c1.clone())]);
- let batch2 = create_batch(vec![("int", c2.clone())]);
let filter = col("int").eq(lit(4_i32));
let rt = RoundTrip::new()
.with_predicate(filter)
.with_page_index_predicate()
- .round_trip(vec![batch1, batch2])
+ .round_trip(vec![batch1])
.await;
let metrics = rt.parquet_exec.metrics().unwrap();
// assert the batches and some metrics
+ #[rustfmt::skip]
let expected = vec![
- "+-----+", "| int |", "+-----+", "| 3 |", "| 4 |", "| 5 |",
"+-----+",
+ "+-----+",
Review Comment:
this is different because previously the page layout was as follows
Page1:
1
None
2
Page 2
3
4
5
Now the page layout is
Page1:
1
None
Page2
2
3
Page3
4
5
##########
datafusion/core/src/physical_plan/file_format/parquet/page_filter.rs:
##########
@@ -223,6 +222,64 @@ impl PagePruningPredicate {
}
}
+/// Returns the column index in the row group metadata for the single
+/// column of a single column pruning predicate.
+///
+/// For example, give the predicate `y > 5`
+///
+/// And columns in the RowGroupMetadata like `['x', 'y', 'z']` will
+/// return 1.
Review Comment:
```suggestion
/// For example, give the predicate `y > 5`and columns in the
/// RowGroupMetadata like `['x', 'y', 'z']` will return 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]
