tshauck commented on code in PR #10972: URL: https://github.com/apache/datafusion/pull/10972#discussion_r1643805987
########## datafusion/core/tests/parquet/arrow_statistics.rs: ########## @@ -507,9 +507,84 @@ async fn test_multiple_data_pages_nulls_and_negatives() { /////////////// MORE GENERAL TESTS ////////////////////// // . Many columns in a file -// . Differnet data types +// . Different data types // . Different row group sizes +// Float 16, 32, 64 +#[tokio::test] +async fn test_float_16() { + let reader = TestReader { + scenario: Scenario::Float16, + row_per_group: 5, + } + .build() + .await; + + Test { + reader: &reader, + expected_min: Arc::new(Float16Array::from( + vec![-5.0, -4.0, -0.0, 5.0] + .into_iter() + .map(f16::from_f32) + .collect::<Vec<_>>(), + )), + expected_max: Arc::new(Float16Array::from( + vec![-1.0, 0.0, 4.0, 9.0] + .into_iter() + .map(f16::from_f32) + .collect::<Vec<_>>(), + )), + expected_null_counts: UInt64Array::from(vec![0, 0, 0, 0]), + expected_row_counts: Some(UInt64Array::from(vec![5, 5, 5, 5])), + column_name: "f", + check: Check::RowGroup, Review Comment: I'm stretching a here, but doing a bit of looking I think it's due to the physical type for an f16 being a fixed length byte array. I think `column_page_index_per_row_group_per_column` is an `Index::FIXED_LEN_BYTE_ARRAY` which seemingly isn't playing well with some of the conversion, so the values coming through end up being None. -- 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...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org