Skip to content

Migrate join_selection tests to snapshot-based testing #17974

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

Merged
merged 2 commits into from
Oct 9, 2025
Merged

Migrate join_selection tests to snapshot-based testing #17974

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c4a02e5
Migrate join_selection tests to snapshot-based testing
Oct 8, 2025
ac49f68
Merge branch 'main' into join-selection-migration
alamb Oct 9, 2025
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
36 changes: 18 additions & 18 deletions datafusion/core/tests/physical_optimizer/join_selection.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
// specific language governing permissions and limitations
// under the License.

use insta::assert_snapshot;
use std::sync::Arc;
use std::{
any::Any,
Expand Down Expand Up @@ -426,21 +427,19 @@ async fn test_join_with_swap_mark() {

/// Compare the input plan with the plan after running the probe order optimizer.
macro_rules! assert_optimized {
($EXPECTED_LINES: expr, $PLAN: expr) => {
let expected_lines = $EXPECTED_LINES.iter().map(|s| *s).collect::<Vec<&str>>();
($PLAN: expr, @$EXPECTED_LINES: literal $(,)?) => {

let plan = Arc::new($PLAN);
let optimized = JoinSelection::new()
.optimize(plan.clone(), &ConfigOptions::new())
.unwrap();

let plan_string = displayable(optimized.as_ref()).indent(true).to_string();
let actual_lines = plan_string.split("\n").collect::<Vec<&str>>();
let actual = plan_string.trim();

assert_eq!(
&expected_lines, &actual_lines,
"\n\nexpected:\n\n{:#?}\nactual:\n\n{:#?}\n\n",
expected_lines, actual_lines
assert_snapshot!(
actual,
@$EXPECTED_LINES
);
};
}
Expand Down Expand Up @@ -489,17 +488,18 @@ async fn test_nested_join_swap() {
// The first hash join's left is 'small' table (with 1000 rows), and the second hash join's
// left is the F(small IJ big) which has an estimated cardinality of 2000 rows (vs medium which
// has an exact cardinality of 10_000 rows).
let expected = [
"ProjectionExec: expr=[medium_col@2 as medium_col, big_col@0 as big_col, small_col@1 as small_col]",
" HashJoinExec: mode=CollectLeft, join_type=Right, on=[(small_col@1, medium_col@0)]",
" ProjectionExec: expr=[big_col@1 as big_col, small_col@0 as small_col]",
" HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(small_col@0, big_col@0)]",
" StatisticsExec: col_count=1, row_count=Inexact(1000)",
" StatisticsExec: col_count=1, row_count=Inexact(100000)",
" StatisticsExec: col_count=1, row_count=Inexact(10000)",
"",
];
assert_optimized!(expected, join);
assert_optimized!(
join,
@r"
ProjectionExec: expr=[medium_col@2 as medium_col, big_col@0 as big_col, small_col@1 as small_col]
HashJoinExec: mode=CollectLeft, join_type=Right, on=[(small_col@1, medium_col@0)]
ProjectionExec: expr=[big_col@1 as big_col, small_col@0 as small_col]
HashJoinExec: mode=CollectLeft, join_type=Inner, on=[(small_col@0, big_col@0)]
StatisticsExec: col_count=1, row_count=Inexact(1000)
StatisticsExec: col_count=1, row_count=Inexact(100000)
StatisticsExec: col_count=1, row_count=Inexact(10000)
"
);
}

#[tokio::test]
Expand Down