Skip to content
Merged
Changes from all commits
Commits
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
27 changes: 23 additions & 4 deletions datafusion/core/tests/fuzz_cases/null_aware_join_fuzz.rs
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ use rand::{Rng, SeedableRng};
#[tokio::test(flavor = "multi_thread")]
async fn null_aware_join_matches_reference() {
let mut plans = NullAwarePlans::default();
let cases = cases();
for seed in 0..20 {
let mut rng = StdRng::seed_from_u64(seed);
let outer = random_table(&mut rng, &["id", "k", "a", "b", "c"], &["n", "m"], 6);
Expand All @@ -39,6 +40,25 @@ async fn null_aware_join_matches_reference() {
let inner_rows = if seed % 2 == 0 { 6 } else { 2 };
let inner =
random_table(&mut rng, &["k", "x", "y", "z"], &["v", "w"], inner_rows);

// Reference results depend only on this seed's tables, so compute
// them once with a stable configuration instead of repeating them
// for every batch size and partition count below.
let reference_ctx = SessionContext::new_with_config(
SessionConfig::new().with_target_partitions(1),
);
reference_ctx
.register_table("o", Arc::clone(&outer) as _)
.unwrap();
reference_ctx
.register_table("i", Arc::clone(&inner) as _)
.unwrap();
let mut expected_rows = Vec::with_capacity(cases.len());
for (_, reference) in &cases {
let (expected, _) = run(&reference_ctx, reference).await;
expected_rows.push(expected);
}

for target_partitions in [1, 4] {
for batch_size in [1, 3, 8192] {
let config = SessionConfig::new()
Expand All @@ -57,12 +77,11 @@ async fn null_aware_join_matches_reference() {
let ctx = SessionContext::new_with_config(config);
ctx.register_table("o", Arc::clone(&outer) as _).unwrap();
ctx.register_table("i", Arc::clone(&inner) as _).unwrap();
for (query, reference) in cases() {
let (actual, plan) = run(&ctx, &query).await;
for ((query, reference), expected) in cases.iter().zip(&expected_rows) {
let (actual, plan) = run(&ctx, query).await;
plans.record(plan.as_ref());
let (expected, _) = run(&ctx, &reference).await;
assert_eq!(
actual, expected,
actual, *expected,
"seed={seed} target_partitions={target_partitions} \
batch_size={batch_size}\nquery: {query}\nreference: {reference}"
);
Expand Down
Loading