Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[MINOR]: Parametrize sort-preservation tests to exercise all situations (unbounded/bounded sources and flag behavior) #8575

Merged
merged 2 commits into from
Dec 18, 2023
Merged

[MINOR]: Parametrize sort-preservation tests to exercise all situations (unbounded/bounded sources and flag behavior) #8575

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cedea84
Re-introduce unbounded tests with new executor
mustafasrepo Dec 18, 2023
f63c327
Remove unnecessary test
mustafasrepo Dec 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 9 additions & 10 deletions datafusion/core/src/physical_optimizer/enforce_sorting.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -769,7 +769,7 @@ mod tests {
use crate::physical_plan::repartition::RepartitionExec;
use crate::physical_plan::{displayable, get_plan_string, Partitioning};
use crate::prelude::{SessionConfig, SessionContext};
use crate::test::csv_exec_sorted;
use crate::test::{csv_exec_sorted, stream_exec_ordered};

use arrow::compute::SortOptions;
use arrow::datatypes::{DataType, Field, Schema, SchemaRef};
Expand Down Expand Up @@ -2141,11 +2141,11 @@ mod tests {
}

#[tokio::test]
#[ignore]
async fn test_with_lost_ordering_unbounded() -> Result<()> {
let schema = create_test_schema3()?;
let sort_exprs = vec![sort_expr("a", &schema)];
let source = csv_exec_sorted(&schema, sort_exprs);
// create an unbounded source
let source = stream_exec_ordered(&schema, sort_exprs);
let repartition_rr = repartition_exec(source);
let repartition_hash = Arc::new(RepartitionExec::try_new(
repartition_rr,
Expand All @@ -2159,25 +2159,24 @@ mod tests {
" CoalescePartitionsExec",
" RepartitionExec: partitioning=Hash([c@2], 10), input_partitions=10",
" RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
" CsvExec: file_groups={1 group: [[x]]}, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC], has_header=false"
" StreamingTableExec: partition_sizes=1, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC]",
];
let expected_optimized = [
"SortPreservingMergeExec: [a@0 ASC]",
" RepartitionExec: partitioning=Hash([c@2], 10), input_partitions=10, preserve_order=true, sort_exprs=a@0 ASC",
" RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
" CsvExec: file_groups={1 group: [[x]]}, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC], has_header=false",
" StreamingTableExec: partition_sizes=1, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC]",
];
assert_optimized!(expected_input, expected_optimized, physical_plan, true);
Ok(())
}

#[tokio::test]
#[ignore]
async fn test_with_lost_ordering_unbounded_parallelize_off() -> Result<()> {
let schema = create_test_schema3()?;
let sort_exprs = vec![sort_expr("a", &schema)];
// Make source unbounded
let source = csv_exec_sorted(&schema, sort_exprs);
// create an unbounded source
let source = stream_exec_ordered(&schema, sort_exprs);
let repartition_rr = repartition_exec(source);
let repartition_hash = Arc::new(RepartitionExec::try_new(
repartition_rr,
Expand All @@ -2190,13 +2189,13 @@ mod tests {
" CoalescePartitionsExec",
" RepartitionExec: partitioning=Hash([c@2], 10), input_partitions=10",
" RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
" CsvExec: file_groups={1 group: [[x]]}, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC], has_header=false"
" StreamingTableExec: partition_sizes=1, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC]",
];
let expected_optimized = [
"SortPreservingMergeExec: [a@0 ASC]",
" RepartitionExec: partitioning=Hash([c@2], 10), input_partitions=10, preserve_order=true, sort_exprs=a@0 ASC",
" RepartitionExec: partitioning=RoundRobinBatch(10), input_partitions=1",
" CsvExec: file_groups={1 group: [[x]]}, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC], has_header=false",
" StreamingTableExec: partition_sizes=1, projection=[a, b, c, d, e], infinite_source=true, output_ordering=[a@0 ASC]",
];
assert_optimized!(expected_input, expected_optimized, physical_plan, false);
Ok(())
Expand Down
Loading