Skip to content

feat(substrait): support order_by in aggregate functions #13114

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 1 commit into from
Oct 29, 2024
Merged

feat(substrait): support order_by in aggregate functions #13114

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 15 additions & 2 deletions datafusion/substrait/src/logical_plan/consumer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,14 +713,27 @@ pub async fn from_substrait_rel(
}
_ => false,
};
let order_by = if !f.sorts.is_empty() {
Some(
from_substrait_sorts(
ctx,
&f.sorts,
input.schema(),
extensions,
)
.await?,
)
} else {
None
};

from_substrait_agg_func(
ctx,
f,
input.schema(),
extensions,
filter,
// TODO: Add parsing of order_by also
None,
order_by,
distinct,
)
.await
Expand Down
16 changes: 15 additions & 1 deletion datafusion/substrait/tests/cases/roundtrip_logical_plan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -680,6 +680,19 @@ async fn aggregate_wo_projection_consume() -> Result<()> {
.await
}

#[tokio::test]
async fn aggregate_wo_projection_sorted_consume() -> Result<()> {
let proto_plan =
read_json("tests/testdata/test_plans/aggregate_sorted_no_project.substrait.json");

assert_expected_plan_substrait(
proto_plan,
"Aggregate: groupBy=[[data.a]], aggr=[[count(data.a) ORDER BY [data.a DESC NULLS FIRST] AS countA]]\
\n TableScan: data projection=[a]",
)
.await
}

#[tokio::test]
async fn simple_intersect_consume() -> Result<()> {
let proto_plan = read_json("tests/testdata/test_plans/intersect.substrait.json");
Expand Down Expand Up @@ -1020,8 +1033,9 @@ async fn roundtrip_aggregate_udf() -> Result<()> {

let ctx = create_context().await?;
ctx.register_udaf(dummy_agg);
roundtrip_with_ctx("select dummy_agg(a) from data", ctx.clone()).await?;
roundtrip_with_ctx("select dummy_agg(a order by a) from data", ctx.clone()).await?;

roundtrip_with_ctx("select dummy_agg(a) from data", ctx).await?;
Ok(())
}

Expand Down
113 changes: 113 additions & 0 deletions datafusion/substrait/tests/testdata/test_plans/aggregate_sorted_no_project.substrait.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,113 @@
{
"extensionUris": [
{
"uri": "https://github.com/substrait-io/substrait/blob/main/extensions/functions_aggregate_generic.yaml"
}
],
"extensions": [
{
"extensionFunction": {
"functionAnchor": 185,
"name": "count:any"
}
}
],
"relations": [
{
"root": {
"input": {
"aggregate": {
"input": {
"read": {
"common": {
"direct": {}
},
"baseSchema": {
"names": [
"a"
],
"struct": {
"types": [
{
"i64": {
"nullability": "NULLABILITY_NULLABLE"
}
}
],
"nullability": "NULLABILITY_NULLABLE"
}
},
"namedTable": {
"names": [
"data"
]
}
}
},
"groupings": [
{
"groupingExpressions": [
{
"selection": {
"directReference": {
"structField": {}
},
"rootReference": {}
}
}
]
}
],
"measures": [
{
"measure": {
"functionReference": 185,
"phase": "AGGREGATION_PHASE_INITIAL_TO_RESULT",
"outputType": {
"i64": {}
},
"arguments": [
{
"value": {
"selection": {
"directReference": {
"structField": {}
},
"rootReference": {}
}
}
}
],
"sorts": [
{
"expr": {
"selection": {
"directReference": {
"structField": {
"field": 0
}
},
"rootReference": {
}
}
},
"direction": "SORT_DIRECTION_DESC_NULLS_FIRST"
}
]
}
}
]
}
},
"names": [
"a",
"countA"
]
}
}
],
"version": {
"minorNumber": 54,
"producer": "manual"
}
}