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

Properly encode STRING_AGG, NTH_VALUE in physical plan protobufs #9027

Merged
merged 2 commits into from
Jan 28, 2024
Merged

Properly encode STRING_AGG, NTH_VALUE in physical plan protobufs #9027

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
033d9a6
Properly encode STRING_AGG in physical plan protobufs
scsmithr Jan 27, 2024
53bc2df
reference issue for nth_value
scsmithr Jan 27, 2024
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
10 changes: 7 additions & 3 deletions datafusion/proto/src/physical_plan/to_proto.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,9 @@ use datafusion::physical_plan::expressions::{
CastExpr, Column, Correlation, Count, Covariance, CovariancePop, CumeDist,
DistinctArrayAgg, DistinctBitXor, DistinctCount, DistinctSum, FirstValue, Grouping,
InListExpr, IsNotNullExpr, IsNullExpr, LastValue, LikeExpr, Literal, Max, Median,
Min, NegativeExpr, NotExpr, NthValue, Ntile, OrderSensitiveArrayAgg, Rank, RankType,
Regr, RegrType, RowNumber, Stddev, StddevPop, Sum, TryCastExpr, Variance,
VariancePop, WindowShift,
Min, NegativeExpr, NotExpr, NthValue, NthValueAgg, Ntile, OrderSensitiveArrayAgg,
Rank, RankType, Regr, RegrType, RowNumber, Stddev, StddevPop, StringAgg, Sum,
TryCastExpr, Variance, VariancePop, WindowShift,
};
use datafusion::physical_plan::udaf::AggregateFunctionExpr;
use datafusion::physical_plan::windows::{BuiltInWindowExpr, PlainAggregateWindowExpr};
Expand Down Expand Up @@ -363,6 +363,10 @@ fn aggr_expr_to_aggr_fn(expr: &dyn AggregateExpr) -> Result<AggrFn> {
protobuf::AggregateFunction::FirstValueAgg
} else if aggr_expr.downcast_ref::<LastValue>().is_some() {
protobuf::AggregateFunction::LastValueAgg
} else if aggr_expr.downcast_ref::<StringAgg>().is_some() {
protobuf::AggregateFunction::StringAgg
} else if aggr_expr.downcast_ref::<NthValueAgg>().is_some() {
protobuf::AggregateFunction::NthValueAgg
} else {
return not_impl_err!("Aggregate function not supported: {expr:?}");
};
Expand Down
55 changes: 41 additions & 14 deletions datafusion/proto/tests/cases/roundtrip_physical_plan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,8 @@ use datafusion::physical_plan::analyze::AnalyzeExec;
use datafusion::physical_plan::empty::EmptyExec;
use datafusion::physical_plan::expressions::{
binary, cast, col, in_list, like, lit, Avg, BinaryExpr, Column, DistinctCount,
GetFieldAccessExpr, GetIndexedFieldExpr, NotExpr, NthValue, PhysicalSortExpr, Sum,
GetFieldAccessExpr, GetIndexedFieldExpr, NotExpr, NthValue, PhysicalSortExpr,
StringAgg, Sum,
};
use datafusion::physical_plan::filter::FilterExec;
use datafusion::physical_plan::insert::FileSinkExec;
Expand Down Expand Up @@ -328,20 +329,46 @@ fn rountrip_aggregate() -> Result<()> {
let groups: Vec<(Arc<dyn PhysicalExpr>, String)> =
vec![(col("a", &schema)?, "unused".to_string())];

let aggregates: Vec<Arc<dyn AggregateExpr>> = vec![Arc::new(Avg::new(
cast(col("b", &schema)?, &schema, DataType::Float64)?,
"AVG(b)".to_string(),
DataType::Float64,
))];
let test_cases: Vec<Vec<Arc<dyn AggregateExpr>>> = vec![
// AVG
vec![Arc::new(Avg::new(
cast(col("b", &schema)?, &schema, DataType::Float64)?,
"AVG(b)".to_string(),
DataType::Float64,
))],
// TODO: See <https://github.com/apache/arrow-datafusion/issues/9028>
// // NTH_VALUE
// vec![Arc::new(NthValueAgg::new(
// col("b", &schema)?,
// 1,
// "NTH_VALUE(b, 1)".to_string(),
// DataType::Int64,
// false,
// Vec::new(),
// Vec::new(),
// ))],
// STRING_AGG
vec![Arc::new(StringAgg::new(
cast(col("b", &schema)?, &schema, DataType::Utf8)?,
lit(ScalarValue::Utf8(Some(",".to_string()))),
"STRING_AGG(name, ',')".to_string(),
DataType::Utf8,
))],
];

roundtrip_test(Arc::new(AggregateExec::try_new(
AggregateMode::Final,
PhysicalGroupBy::new_single(groups.clone()),
aggregates.clone(),
vec![None],
Arc::new(EmptyExec::new(schema.clone())),
schema,
)?))
for aggregates in test_cases {
let schema = schema.clone();
roundtrip_test(Arc::new(AggregateExec::try_new(
AggregateMode::Final,
PhysicalGroupBy::new_single(groups.clone()),
aggregates,
vec![None],
Arc::new(EmptyExec::new(schema.clone())),
schema,
)?))?;
}

Ok(())
}

#[test]
Expand Down
Loading