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

Fix convert_to_state bug in GroupsAccumulatorAdapter #12834

Merged
merged 2 commits into from
Oct 9, 2024
Merged

Fix convert_to_state bug in GroupsAccumulatorAdapter #12834

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
f9c4c6a
Fix convert_to_state bug
alamb Oct 9, 2024
6d32043
fmt
alamb Oct 9, 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
18 changes: 6 additions & 12 deletions datafusion/core/tests/fuzz_cases/aggregate_fuzz.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -254,10 +254,8 @@ async fn test_basic_string_aggr_group_by_single_int64() {
let fuzzer = builder
.data_gen_config(data_gen_config)
.data_gen_rounds(8)
// FIXME: Encounter error in min/max
// ArrowError(InvalidArgumentError("number of columns(1) must match number of fields(2) in schema"))
// .add_sql("SELECT b, max(a) FROM fuzz_table GROUP BY b")
// .add_sql("SELECT b, min(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, max(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, min(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, count(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, count(distinct a) FROM fuzz_table GROUP BY b")
.table_name("fuzz_table")
Expand Down Expand Up @@ -291,10 +289,8 @@ async fn test_basic_string_aggr_group_by_single_string() {
let fuzzer = builder
.data_gen_config(data_gen_config)
.data_gen_rounds(16)
// FIXME: Encounter error in min/max
// ArrowError(InvalidArgumentError("number of columns(1) must match number of fields(2) in schema"))
// .add_sql("SELECT b, max(a) FROM fuzz_table GROUP BY b")
// .add_sql("SELECT b, min(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, max(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, min(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, count(a) FROM fuzz_table GROUP BY b")
.add_sql("SELECT b, count(distinct a) FROM fuzz_table GROUP BY b")
.table_name("fuzz_table")
Expand Down Expand Up @@ -329,10 +325,8 @@ async fn test_basic_string_aggr_group_by_mixed_string_int64() {
let fuzzer = builder
.data_gen_config(data_gen_config)
.data_gen_rounds(16)
// FIXME: Encounter error in min/max
// ArrowError(InvalidArgumentError("number of columns(1) must match number of fields(2) in schema"))
// .add_sql("SELECT b, c, max(a) FROM fuzz_table GROUP BY b, c")
// .add_sql("SELECT b, c, min(a) FROM fuzz_table GROUP BY b, c")
.add_sql("SELECT b, c, max(a) FROM fuzz_table GROUP BY b, c")
.add_sql("SELECT b, c, min(a) FROM fuzz_table GROUP BY b, c")
.add_sql("SELECT b, c, count(a) FROM fuzz_table GROUP BY b, c")
.add_sql("SELECT b, c, count(distinct a) FROM fuzz_table GROUP BY b, c")
.table_name("fuzz_table")
Expand Down
13 changes: 13 additions & 0 deletions datafusion/functions-aggregate-common/src/aggregate/groups_accumulator.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ pub mod bool_op;
pub mod nulls;
pub mod prim_op;

use arrow::array::new_empty_array;
use arrow::{
array::{ArrayRef, AsArray, BooleanArray, PrimitiveArray},
compute,
Expand Down Expand Up @@ -405,6 +406,18 @@ impl GroupsAccumulator for GroupsAccumulatorAdapter {
) -> Result<Vec<ArrayRef>> {
let num_rows = values[0].len();

// If there are no rows, return empty arrays
if num_rows == 0 {
// create empty accumulator to get the state types
let empty_state = (self.factory)()?.state()?;
let empty_arrays = empty_state
.into_iter()
.map(|state_val| new_empty_array(&state_val.data_type()))
.collect::<Vec<_>>();

return Ok(empty_arrays);
}

// Each row has its respective group
let mut results = vec![];
for row_idx in 0..num_rows {
Expand Down