Skip to content

Implement tree explain for AggregateExec #15103

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 3 commits into from
Mar 11, 2025
Merged

Implement tree explain for AggregateExec #15103

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
d0bfddc
Implement tree explain for AggregateExec
zebsme Mar 9, 2025
d07d095
Extract expr formatting logic for readability
zebsme Mar 11, 2025
d810201
fix empty group_by display
zebsme Mar 11, 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
77 changes: 53 additions & 24 deletions datafusion/physical-plan/src/aggregates/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -742,21 +742,23 @@ impl DisplayAs for AggregateExec {
t: DisplayFormatType,
f: &mut std::fmt::Formatter,
) -> std::fmt::Result {
let format_expr_with_alias =
|(e, alias): &(Arc<dyn PhysicalExpr>, String)| -> String {
let e = e.to_string();
if &e != alias {
format!("{e} as {alias}")
} else {
e
}
};
match t {
DisplayFormatType::Default | DisplayFormatType::Verbose => {
write!(f, "AggregateExec: mode={:?}", self.mode)?;
let g: Vec<String> = if self.group_by.is_single() {
self.group_by
.expr
.iter()
.map(|(e, alias)| {
let e = e.to_string();
if &e != alias {
format!("{e} as {alias}")
} else {
e
}
})
.map(format_expr_with_alias)
.collect()
} else {
self.group_by
Expand All @@ -768,21 +770,11 @@ impl DisplayAs for AggregateExec {
.enumerate()
.map(|(idx, is_null)| {
if *is_null {
let (e, alias) = &self.group_by.null_expr[idx];
let e = e.to_string();
if &e != alias {
format!("{e} as {alias}")
} else {
e
}
format_expr_with_alias(
&self.group_by.null_expr[idx],
)
} else {
let (e, alias) = &self.group_by.expr[idx];
let e = e.to_string();
if &e != alias {
format!("{e} as {alias}")
} else {
e
}
format_expr_with_alias(&self.group_by.expr[idx])
}
})
.collect::<Vec<String>>()
Expand All @@ -809,8 +801,45 @@ impl DisplayAs for AggregateExec {
}
}
DisplayFormatType::TreeRender => {
// TODO: collect info
write!(f, "")?;
let g: Vec<String> = if self.group_by.is_single() {
self.group_by
.expr
.iter()
.map(format_expr_with_alias)
.collect()
} else {
self.group_by
.groups
.iter()
.map(|group| {
let terms = group
.iter()
.enumerate()
.map(|(idx, is_null)| {
if *is_null {
format_expr_with_alias(
&self.group_by.null_expr[idx],
)
} else {
format_expr_with_alias(&self.group_by.expr[idx])
}
})
.collect::<Vec<String>>()
.join(", ");
format!("({terms})")
})
.collect()
};
let a: Vec<String> = self
.aggr_expr
.iter()
.map(|agg| agg.name().to_string())
.collect();
writeln!(f, "mode={:?}", self.mode)?;
if !g.is_empty() {
writeln!(f, "group_by={}", g.join(", "))?;
}
writeln!(f, "aggr={}", a.join(", "))?;
}
}
Ok(())
Expand Down
77 changes: 50 additions & 27 deletions datafusion/sqllogictest/test_files/explain_tree.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -166,25 +166,42 @@ explain SELECT string_col, SUM(bigint_col) FROM table1 GROUP BY string_col;
physical_plan
01)┌───────────────────────────┐
02)│ AggregateExec │
03)└─────────────┬─────────────┘
04)┌─────────────┴─────────────┐
05)│ CoalesceBatchesExec │
06)└─────────────┬─────────────┘
07)┌─────────────┴─────────────┐
08)│ RepartitionExec │
09)└─────────────┬─────────────┘
10)┌─────────────┴─────────────┐
11)│ AggregateExec │
03)│ -------------------- │
04)│ aggr: │
05)│ sum(table1.bigint_col) │
06)│ │
07)│ group_by: │
08)│ string_col@0 as string_col│
09)│ │
10)│ mode: │
11)│ FinalPartitioned │
12)└─────────────┬─────────────┘
13)┌─────────────┴─────────────┐
14)│ RepartitionExec │
14)│ CoalesceBatchesExec │
15)└─────────────┬─────────────┘
16)┌─────────────┴─────────────┐
17)│ DataSourceExec │
18)│ -------------------- │
19)│ files: 1 │
20)│ format: csv │
21)└───────────────────────────┘
17)│ RepartitionExec │
18)└─────────────┬─────────────┘
19)┌─────────────┴─────────────┐
20)│ AggregateExec │
21)│ -------------------- │
22)│ aggr: │
23)│ sum(table1.bigint_col) │
24)│ │
25)│ group_by: │
26)│ string_col@0 as string_col│
27)│ │
28)│ mode: Partial │
29)└─────────────┬─────────────┘
30)┌─────────────┴─────────────┐
31)│ RepartitionExec │
32)└─────────────┬─────────────┘
33)┌─────────────┴─────────────┐
34)│ DataSourceExec │
35)│ -------------------- │
36)│ files: 1 │
37)│ format: csv │
38)└───────────────────────────┘

# Limit
query TT
Expand Down Expand Up @@ -1076,22 +1093,28 @@ physical_plan
11)└───────────────────────────┘└─────────────┬─────────────┘
12)-----------------------------┌─────────────┴─────────────┐
13)-----------------------------│ AggregateExec │
14)-----------------------------└─────────────┬─────────────┘
15)-----------------------------┌─────────────┴─────────────┐
16)-----------------------------│ CoalescePartitionsExec │
14)-----------------------------│ -------------------- │
15)-----------------------------│ aggr: count(Int64(1)) │
16)-----------------------------│ mode: Final │
17)-----------------------------└─────────────┬─────────────┘
18)-----------------------------┌─────────────┴─────────────┐
19)-----------------------------│ AggregateExec │
19)-----------------------------│ CoalescePartitionsExec │
20)-----------------------------└─────────────┬─────────────┘
21)-----------------------------┌─────────────┴─────────────┐
22)-----------------------------│ RepartitionExec │
23)-----------------------------└─────────────┬─────────────┘
24)-----------------------------┌─────────────┴─────────────┐
25)-----------------------------│ DataSourceExec │
26)-----------------------------│ -------------------- │
27)-----------------------------│ files: 1 │
28)-----------------------------│ format: parquet │
29)-----------------------------└───────────────────────────┘
22)-----------------------------│ AggregateExec │
23)-----------------------------│ -------------------- │
24)-----------------------------│ aggr: count(Int64(1)) │
25)-----------------------------│ mode: Partial │
26)-----------------------------└─────────────┬─────────────┘
27)-----------------------------┌─────────────┴─────────────┐
28)-----------------------------│ RepartitionExec │
29)-----------------------------└─────────────┬─────────────┘
30)-----------------------------┌─────────────┴─────────────┐
31)-----------------------------│ DataSourceExec │
32)-----------------------------│ -------------------- │
33)-----------------------------│ files: 1 │
34)-----------------------------│ format: parquet │
35)-----------------------------└───────────────────────────┘

# Query with cross join.
query TT
Expand Down