alamb commented on code in PR #3444:
URL: https://github.com/apache/arrow-rs/pull/3444#discussion_r1062372820
##########
arrow-flight/src/encode.rs:
##########
@@ -506,6 +512,48 @@ mod tests {
assert_eq!(concat_batches(&batch.schema(), &split).unwrap(), batch);
}
+ #[test]
+ fn test_split_batch_for_grpc_response_sizes() {
+ // 2000 8 byte entries into 2k pieces: 8 chunks of 250 rows
+ verify_split(2000, 2 * 1024, vec![250, 250, 250, 250, 250, 250, 250,
250]);
+
+ // 2000 8 byte entries into 4k pieces: 4 chunks of 500 rows
+ verify_split(2000, 4 * 1024, vec![500, 500, 500, 500]);
+
+ // 2023 8 byte entries into 3k pieces does not divide evenly
+ verify_split(2023, 3 * 1024, vec![337, 337, 337, 337, 337, 337, 1]);
+
+ // 10 8 byte entries into 1 byte pieces means each rows gets its own
+ verify_split(10, 1, vec![1, 1, 1, 1, 1, 1, 1, 1, 1, 1]);
+
+ // 10 8 byte entries into 1k byte pieces means one piece
+ verify_split(10, 1024, vec![10]);
+ }
+
+ /// Creates a UInt64Array of 8 byte integers with input_rows rows
+ /// `max_flight_data_size_bytes` pieces and verifies the row counts in
+ /// those pieces
+ fn verify_split(
+ num_input_rows: u64,
+ max_flight_data_size_bytes: usize,
+ expected_sizes: Vec<usize>,
+ ) {
+ let array: UInt64Array = (0..num_input_rows).collect();
Review Comment:
🤔 I guess we hope for small dictionaries
--
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]
