Dandandan commented on a change in pull request #9806:
URL: https://github.com/apache/arrow/pull/9806#discussion_r606779504
##########
File path: rust/datafusion/src/physical_plan/union.rs
##########
@@ -60,15 +60,31 @@ impl ExecutionPlan for UnionExec {
/// Output of the union is the combination of all output partitions of the
inputs
fn output_partitioning(&self) -> Partitioning {
- // Sums all the output partitions
- let num_partitions = self
- .inputs
+ let intial: Option<Partitioning> = None;
+ self.inputs
.iter()
- .map(|plan| plan.output_partitioning().partition_count())
- .sum();
- // TODO: this loses partitioning info in case of same partitioning
scheme (for example `Partitioning::Hash`)
- // https://issues.apache.org/jira/browse/ARROW-11991
- Partitioning::UnknownPartitioning(num_partitions)
+ .fold(intial, |acc, input| {
+ match (acc, input.output_partitioning()) {
+ (None, partition) => Some(partition),
+ (
+ Some(Partitioning::Hash(mut vector_acc, size_acc)),
+ Partitioning::Hash(vector, size),
+ ) => {
+ vector_acc.append(&mut vector.clone());
+ Some(Partitioning::Hash(vector_acc, size_acc + size))
+ }
+ (
+ Some(Partitioning::RoundRobinBatch(size_acc)),
+ Partitioning::RoundRobinBatch(size),
+ ) => Some(Partitioning::RoundRobinBatch(size_acc + size)),
Review comment:
`RoundRobinBatch(1000)` means it still has 1000 partitions as output
after repartitioning with round robin.
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
