Skip to content

feat: implement tree explain for ProjectionExec #15082

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 6 commits into from
Mar 9, 2025
Merged

feat: implement tree explain for ProjectionExec #15082

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
a1e5a41
feat: implement tree explain for ProjectionExec
Standing-Man Mar 8, 2025
6bd76e6
feat(test): support more tests
Standing-Man Mar 8, 2025
d986b43
chore(explain): Reduce redundant output
Standing-Man Mar 8, 2025
d83eff9
Propose a different projection formatting
alamb Mar 8, 2025
ac3644d
feat: add project exec tree rendering for hash join
Standing-Man Mar 9, 2025
83f78a1
Merge remote-tracking branch 'apache/main' into projection-exec
alamb Mar 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
11 changes: 9 additions & 2 deletions datafusion/physical-plan/src/projection.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,8 +168,15 @@ impl DisplayAs for ProjectionExec {
write!(f, "ProjectionExec: expr=[{}]", expr.join(", "))
}
DisplayFormatType::TreeRender => {
// TODO: collect info
write!(f, "")
for (i, (e, alias)) in self.expr().iter().enumerate() {
let e = e.to_string();
if &e == alias {
writeln!(f, "expr{i}={e}")?;
} else {
writeln!(f, "{alias}={e}")?;
}
}
Ok(())
}
}
}
Expand Down
232 changes: 206 additions & 26 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 @@ -539,6 +539,158 @@ physical_plan
17)│ format: arrow │
18)└───────────────────────────┘

# Query with projection on csv
query TT
explain SELECT int_col, bigint_col, int_col+bigint_col AS sum_col FROM table1;
----
logical_plan
01)Projection: table1.int_col, table1.bigint_col, CAST(table1.int_col AS Int64) + table1.bigint_col AS sum_col
02)--TableScan: table1 projection=[int_col, bigint_col]
physical_plan
01)┌───────────────────────────┐
02)│ ProjectionExec │
03)│ -------------------- │
04)│ bigint_col: │
05)│ bigint_col@1 │
06)│ │
07)│ int_col: int_col@0 │
08)│ │
09)│ sum_col: │
10)│ CAST(int_col@0 AS Int64) +│
11)│ bigint_col@1 │
12)└─────────────┬─────────────┘
13)┌─────────────┴─────────────┐
14)│ RepartitionExec │
15)└─────────────┬─────────────┘
16)┌─────────────┴─────────────┐
17)│ DataSourceExec │
18)│ -------------------- │
19)│ files: 1 │
20)│ format: csv │
21)└───────────────────────────┘


# Query with projection on parquet
query TT
explain SELECT int_col, bigint_col, int_col+bigint_col AS sum_col FROM table2;
----
logical_plan
01)Projection: table2.int_col, table2.bigint_col, CAST(table2.int_col AS Int64) + table2.bigint_col AS sum_col
02)--TableScan: table2 projection=[int_col, bigint_col]
physical_plan
01)┌───────────────────────────┐
02)│ ProjectionExec │
03)│ -------------------- │
04)│ bigint_col: │
05)│ bigint_col@1 │
06)│ │
07)│ int_col: int_col@0 │
08)│ │
09)│ sum_col: │
10)│ CAST(int_col@0 AS Int64) +│
11)│ bigint_col@1 │
12)└─────────────┬─────────────┘
13)┌─────────────┴─────────────┐
14)│ RepartitionExec │
15)└─────────────┬─────────────┘
16)┌─────────────┴─────────────┐
17)│ DataSourceExec │
18)│ -------------------- │
19)│ files: 1 │
20)│ format: parquet │
21)└───────────────────────────┘


# Query with projection on memory
query TT
explain SELECT int_col, bigint_col, int_col+bigint_col AS sum_col FROM table3;
----
logical_plan
01)Projection: table3.int_col, table3.bigint_col, CAST(table3.int_col AS Int64) + table3.bigint_col AS sum_col
02)--TableScan: table3 projection=[int_col, bigint_col]
physical_plan
01)┌───────────────────────────┐
02)│ ProjectionExec │
03)│ -------------------- │
04)│ bigint_col: │
05)│ bigint_col@1 │
06)│ │
07)│ int_col: int_col@0 │
08)│ │
09)│ sum_col: │
10)│ CAST(int_col@0 AS Int64) +│
11)│ bigint_col@1 │
12)└─────────────┬─────────────┘
13)┌─────────────┴─────────────┐
14)│ DataSourceExec │
15)│ -------------------- │
16)│ bytes: 1560 │
17)│ format: memory │
18)│ rows: 1 │
19)└───────────────────────────┘



# Query with projection on json
query TT
explain SELECT int_col, bigint_col, int_col+bigint_col AS sum_col FROM table4;
----
logical_plan
01)Projection: table4.int_col, table4.bigint_col, table4.int_col + table4.bigint_col AS sum_col
02)--TableScan: table4 projection=[bigint_col, int_col]
physical_plan
01)┌───────────────────────────┐
02)│ ProjectionExec │
03)│ -------------------- │
04)│ bigint_col: │
05)│ bigint_col@0 │
06)│ │
07)│ int_col: int_col@1 │
08)│ │
09)│ sum_col: │
10)│ int_col@1 + bigint_col@0 │
11)└─────────────┬─────────────┘
12)┌─────────────┴─────────────┐
13)│ RepartitionExec │
14)└─────────────┬─────────────┘
15)┌─────────────┴─────────────┐
16)│ DataSourceExec │
17)│ -------------------- │
18)│ files: 1 │
19)│ format: json │
20)└───────────────────────────┘


# Query with projection on arrow
query TT
explain SELECT int_col, bigint_col, int_col+bigint_col AS sum_col FROM table5;
----
logical_plan
01)Projection: table5.int_col, table5.bigint_col, CAST(table5.int_col AS Int64) + table5.bigint_col AS sum_col
02)--TableScan: table5 projection=[int_col, bigint_col]
physical_plan
01)┌───────────────────────────┐
02)│ ProjectionExec │
03)│ -------------------- │
04)│ bigint_col: │
05)│ bigint_col@1 │
06)│ │
07)│ int_col: int_col@0 │
08)│ │
09)│ sum_col: │
10)│ CAST(int_col@0 AS Int64) +│
11)│ bigint_col@1 │
12)└─────────────┬─────────────┘
13)┌─────────────┴─────────────┐
14)│ RepartitionExec │
15)└─────────────┬─────────────┘
16)┌─────────────┴─────────────┐
17)│ DataSourceExec │
18)│ -------------------- │
19)│ files: 1 │
20)│ format: arrow │
21)└───────────────────────────┘

# Query with PartialSortExec.
query TT
EXPLAIN SELECT *
Expand Down Expand Up @@ -614,19 +766,33 @@ physical_plan
18)└─────────────┬─────────────┘└─────────────┬─────────────┘
19)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
20)│ ProjectionExec ││ RepartitionExec │
21)└─────────────┬─────────────┘└─────────────┬─────────────┘
22)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
23)│ RepartitionExec ││ DataSourceExec │
24)│ ││ -------------------- │
25)│ ││ files: 1 │
26)│ ││ format: parquet │
27)└─────────────┬─────────────┘└───────────────────────────┘
28)┌─────────────┴─────────────┐
29)│ DataSourceExec │
30)│ -------------------- │
31)│ files: 1 │
32)│ format: csv │
33)└───────────────────────────┘
21)│ -------------------- ││ │
22)│ CAST(table1.string_col AS ││ │
23)│ Utf8View): ││ │
24)│ CAST(string_col@1 AS ││ │
25)│ Utf8View) ││ │
26)│ ││ │
27)│ bigint_col: ││ │
28)│ bigint_col@2 ││ │
29)│ ││ │
30)│ date_col: date_col@3 ││ │
31)│ int_col: int_col@0 ││ │
32)│ ││ │
33)│ string_col: ││ │
34)│ string_col@1 ││ │
35)└─────────────┬─────────────┘└─────────────┬─────────────┘
36)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
37)│ RepartitionExec ││ DataSourceExec │
38)│ ││ -------------------- │
39)│ ││ files: 1 │
40)│ ││ format: parquet │
41)└─────────────┬─────────────┘└───────────────────────────┘
42)┌─────────────┴─────────────┐
43)│ DataSourceExec │
44)│ -------------------- │
45)│ files: 1 │
46)│ format: csv │
47)└───────────────────────────┘

# Query with outer hash join.
query TT
Expand Down Expand Up @@ -659,19 +825,33 @@ physical_plan
20)└─────────────┬─────────────┘└─────────────┬─────────────┘
21)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
22)│ ProjectionExec ││ RepartitionExec │
23)└─────────────┬─────────────┘└─────────────┬─────────────┘
24)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
25)│ RepartitionExec ││ DataSourceExec │
26)│ ││ -------------------- │
27)│ ││ files: 1 │
28)│ ││ format: parquet │
29)└─────────────┬─────────────┘└───────────────────────────┘
30)┌─────────────┴─────────────┐
31)│ DataSourceExec │
32)│ -------------------- │
33)│ files: 1 │
34)│ format: csv │
35)└───────────────────────────┘
23)│ -------------------- ││ │
24)│ CAST(table1.string_col AS ││ │
25)│ Utf8View): ││ │
26)│ CAST(string_col@1 AS ││ │
27)│ Utf8View) ││ │
28)│ ││ │
29)│ bigint_col: ││ │
30)│ bigint_col@2 ││ │
31)│ ││ │
32)│ date_col: date_col@3 ││ │
33)│ int_col: int_col@0 ││ │
34)│ ││ │
35)│ string_col: ││ │
36)│ string_col@1 ││ │
37)└─────────────┬─────────────┘└─────────────┬─────────────┘
38)┌─────────────┴─────────────┐┌─────────────┴─────────────┐
39)│ RepartitionExec ││ DataSourceExec │
40)│ ││ -------------------- │
41)│ ││ files: 1 │
42)│ ││ format: parquet │
43)└─────────────┬─────────────┘└───────────────────────────┘
44)┌─────────────┴─────────────┐
45)│ DataSourceExec │
46)│ -------------------- │
47)│ files: 1 │
48)│ format: csv │
49)└───────────────────────────┘

# cleanup
statement ok
Expand Down