wiedld commented on code in PR #15409:
URL: https://github.com/apache/datafusion/pull/15409#discussion_r2053132567
##########
datafusion/datasource/src/memory.rs:
##########
@@ -902,4 +1130,319 @@ mod tests {
Ok(())
}
+
+ fn batch(row_size: usize) -> RecordBatch {
+ let a: ArrayRef = Arc::new(Int32Array::from(vec![1; row_size]));
+ let b: ArrayRef = Arc::new(StringArray::from_iter(vec![Some("foo");
row_size]));
+ let c: ArrayRef = Arc::new(Int64Array::from_iter(vec![1; row_size]));
+ RecordBatch::try_from_iter(vec![("a", a), ("b", b), ("c", c)]).unwrap()
+ }
+
+ fn schema() -> SchemaRef {
+ batch(1).schema()
+ }
+
+ fn memorysrcconfig_no_partitions(
+ sort_information: Vec<LexOrdering>,
+ ) -> Result<MemorySourceConfig> {
+ let partitions = vec![];
+ MemorySourceConfig::try_new(&partitions, schema(), None)?
+ .try_with_sort_information(sort_information)
+ }
+
+ fn memorysrcconfig_1_partition_1_batch(
+ sort_information: Vec<LexOrdering>,
+ ) -> Result<MemorySourceConfig> {
+ let partitions = vec![vec![batch(100)]];
+ MemorySourceConfig::try_new(&partitions, schema(), None)?
+ .try_with_sort_information(sort_information)
+ }
+
+ fn memorysrcconfig_3_partitions_1_batch_each(
+ sort_information: Vec<LexOrdering>,
+ ) -> Result<MemorySourceConfig> {
+ let partitions = vec![vec![batch(100)], vec![batch(100)],
vec![batch(100)]];
+ MemorySourceConfig::try_new(&partitions, schema(), None)?
+ .try_with_sort_information(sort_information)
+ }
+
+ fn memorysrcconfig_3_partitions_with_2_batches_each(
+ sort_information: Vec<LexOrdering>,
+ ) -> Result<MemorySourceConfig> {
+ let partitions = vec![
+ vec![batch(100), batch(100)],
+ vec![batch(100), batch(100)],
+ vec![batch(100), batch(100)],
+ ];
+ MemorySourceConfig::try_new(&partitions, schema(), None)?
+ .try_with_sort_information(sort_information)
+ }
+
+ fn memorysrcconfig_1_partition_with_different_sized_batches(
+ sort_information: Vec<LexOrdering>,
+ ) -> Result<MemorySourceConfig> {
+ let partitions = vec![vec![batch(100_000), batch(10_000), batch(100),
batch(1)]];
+ MemorySourceConfig::try_new(&partitions, schema(), None)?
+ .try_with_sort_information(sort_information)
+ }
+
+ fn memorysrcconfig_2_partition_with_different_sized_batches(
+ sort_information: Vec<LexOrdering>,
+ ) -> Result<MemorySourceConfig> {
+ let partitions = vec![
+ vec![batch(100_000), batch(10_000), batch(1_000)],
Review Comment:
Excellent idea, and it caught a bug. I've updated the algo & added the test:
https://github.com/apache/datafusion/pull/15409/commits/c661d97221f12b53520690a7d707439fc3100205
thank you.
--
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
