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

Fix UNION ALL aliasing #6373

Merged
merged 3 commits into from
May 18, 2023
Merged

Fix UNION ALL aliasing #6373

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0ccc591
Fix UNION ALL aliasing
comphead May 17, 2023
882c18a
fmt
comphead May 17, 2023
47f93a3
fmt
comphead May 17, 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
27 changes: 27 additions & 0 deletions datafusion/core/tests/sqllogictests/test_files/union.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,3 +446,30 @@ drop table t1

statement ok
drop table t2

# test UNION ALL aliases correctly with all aliased
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I double checked that this plan is different on main (the aliases remain as a, b and c) 👍

❯ explain select 1 a group by a union all select 2 b union all select 3 c;
+---------------+--------------------------------------------------------------------------------------------------------------+
| plan_type     | plan                                                                                                         |
+---------------+--------------------------------------------------------------------------------------------------------------+
| logical_plan  | Union                                                                                                        |
|               |   Projection: Int64(1) AS a                                                                                  |
|               |     Aggregate: groupBy=[[Int64(1)]], aggr=[[]]                                                               |
|               |       EmptyRelation                                                                                          |
|               |   Projection: Int64(2) AS b                                                                                  |
|               |     EmptyRelation                                                                                            |
|               |   Projection: Int64(3) AS c                                                                                  |
|               |     EmptyRelation                                                                                            |
| physical_plan | UnionExec                                                                                                    |
|               |   ProjectionExec: expr=[Int64(1)@0 as a]                                                                     |
|               |     AggregateExec: mode=FinalPartitioned, gby=[Int64(1)@0 as Int64(1)], aggr=[]                              |
|               |       CoalesceBatchesExec: target_batch_size=8192                                                            |
|               |         RepartitionExec: partitioning=Hash([Column { name: "Int64(1)", index: 0 }], 16), input_partitions=16 |
|               |           RepartitionExec: partitioning=RoundRobinBatch(16), input_partitions=1                              |
|               |             AggregateExec: mode=Partial, gby=[1 as Int64(1)], aggr=[]                                        |
|               |               EmptyExec: produce_one_row=true                                                                |
|               |   ProjectionExec: expr=[2 as b]                                                                              |
|               |     EmptyExec: produce_one_row=true                                                                          |
|               |   ProjectionExec: expr=[3 as c]                                                                              |
|               |     EmptyExec: produce_one_row=true                                                                          |
|               |                                                                                                              |
+---------------+--------------------------------------------------------------------------------------------------------------+

query TT
explain select 1 a group by a union all select 2 b union all select 3 c
----
logical_plan
Union
--Projection: Int64(1) AS a
----Aggregate: groupBy=[[Int64(1)]], aggr=[[]]
------EmptyRelation
--Projection: Int64(2) AS a
----EmptyRelation
--Projection: Int64(3) AS a
----EmptyRelation
physical_plan
UnionExec
--ProjectionExec: expr=[Int64(1)@0 as a]
----AggregateExec: mode=FinalPartitioned, gby=[Int64(1)@0 as Int64(1)], aggr=[]
------CoalesceBatchesExec: target_batch_size=8192
--------RepartitionExec: partitioning=Hash([Column { name: "Int64(1)", index: 0 }], 4), input_partitions=4
----------RepartitionExec: partitioning=RoundRobinBatch(4), input_partitions=1
------------AggregateExec: mode=Partial, gby=[1 as Int64(1)], aggr=[]
--------------EmptyExec: produce_one_row=true
--ProjectionExec: expr=[2 as a]
----EmptyExec: produce_one_row=true
--ProjectionExec: expr=[3 as a]
----EmptyExec: produce_one_row=true
11 changes: 8 additions & 3 deletions datafusion/expr/src/logical_plan/builder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1133,9 +1133,14 @@ pub fn project_with_column_index(
.into_iter()
.enumerate()
.map(|(i, e)| match e {
alias @ Expr::Alias { .. }
if &alias.display_name().unwrap() != schema.field(i).name() =>
{
alias.unalias().alias(schema.field(i).name())
}
ignore_alias @ Expr::Alias { .. } => ignore_alias,
ignore_col @ Expr::Column { .. } => ignore_col,
x => x.alias(schema.field(i).name()),
expr => expr.alias(schema.field(i).name()),
})
.collect::<Vec<_>>();
Ok(LogicalPlan::Projection(Projection::try_new_with_schema(
Expand Down Expand Up @@ -1187,7 +1192,7 @@ pub fn union(left_plan: LogicalPlan, right_plan: LogicalPlan) -> Result<LogicalP
.into_iter()
.flat_map(|p| match p {
LogicalPlan::Union(Union { inputs, .. }) => inputs,
x => vec![Arc::new(x)],
other_plan => vec![Arc::new(other_plan)],
})
.map(|p| {
let plan = coerce_plan_expr_for_schema(&p, &union_schema)?;
Expand All @@ -1199,7 +1204,7 @@ pub fn union(left_plan: LogicalPlan, right_plan: LogicalPlan) -> Result<LogicalP
Arc::new(union_schema.clone()),
)?))
}
x => Ok(Arc::new(x)),
other_plan => Ok(Arc::new(other_plan)),
}
})
.collect::<Result<Vec<_>>>()?;
Expand Down