etseidl commented on code in PR #9794:
URL: https://github.com/apache/arrow-rs/pull/9794#discussion_r3173869733
##########
parquet/tests/arrow_reader/bad_data.rs:
##########
@@ -147,11 +148,38 @@ fn read_file(name: &str) -> Result<usize, ParquetError> {
Ok(num_rows)
}
+#[test]
+fn non_standard_delta_blocks() {
+ let file = Bytes::from_static(include_bytes!("bigdelta.parquet"));
+ use parquet::arrow::arrow_reader::{RowSelection, RowSelector};
+
+ let selectors = vec![RowSelector::skip(1000), RowSelector::select(5)];
+
+ let selection: RowSelection = selectors.into();
+ let reader = ArrowReaderBuilder::try_new(file)
+ .unwrap()
+ .with_row_selection(selection)
+ .build()
+ .unwrap();
+
+ if let Some(maybe_batch) = reader.into_iter().next() {
+ // TODO: uncomment if we ever allow skipping miniblocks > 64 elements
+ //let batch = maybe_batch.expect("skip should succeed");
+ //assert_eq!(batch.num_rows(), 5);
+ assert!(maybe_batch.is_err());
Review Comment:
done in
https://github.com/apache/arrow-rs/pull/9794/commits/0f488635128e7c1b61a55fa85b7923a027f774f6
--
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]
