Skip to content

Fix array_sort for empty record batch #290

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 1 commit into from
Mar 24, 2025
Merged

Fix array_sort for empty record batch #290

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
33 changes: 13 additions & 20 deletions datafusion/functions-array/src/sort.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ use crate::utils::make_scalar_function;
use arrow::compute;
use arrow_array::{Array, ArrayRef, ListArray};
use arrow_buffer::{BooleanBufferBuilder, NullBuffer, OffsetBuffer};
use arrow_schema::DataType::{FixedSizeList, LargeList, List};
use arrow_schema::{DataType, Field, SortOptions};
use datafusion_common::cast::{as_list_array, as_string_array};
use datafusion_common::{exec_err, Result};
Expand Down Expand Up @@ -67,19 +66,9 @@ impl ScalarUDFImpl for ArraySort {

fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
match &arg_types[0] {
List(field) | FixedSizeList(field, _) => Ok(List(Arc::new(Field::new(
"item",
field.data_type().clone(),
true,
)))),
LargeList(field) => Ok(LargeList(Arc::new(Field::new(
"item",
field.data_type().clone(),
true,
)))),
_ => exec_err!(
"Not reachable, data_type should be List, LargeList or FixedSizeList"
),
DataType::Null => Ok(DataType::Null),
arg_type @ DataType::List(_) => Ok(arg_type.clone()),
arg_type => exec_err!("{} does not support type {arg_type}", self.name()),
}
}

Expand All @@ -98,6 +87,16 @@ pub fn array_sort_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
return exec_err!("array_sort expects one to three arguments");
}

if args[0].data_type().is_null() {
return Ok(Arc::clone(&args[0]));
}

let list_array = as_list_array(&args[0])?;
let row_count = list_array.len();
if row_count == 0 || list_array.value_type().is_null() {
return Ok(Arc::clone(&args[0]));
}

let sort_option = match args.len() {
1 => None,
2 => {
Expand All @@ -118,12 +117,6 @@ pub fn array_sort_inner(args: &[ArrayRef]) -> Result<ArrayRef> {
_ => return exec_err!("array_sort expects 1 to 3 arguments"),
};

let list_array = as_list_array(&args[0])?;
let row_count = list_array.len();
if row_count == 0 {
return Ok(args[0].clone());
}

let mut array_lengths = vec![];
let mut arrays = vec![];
let mut valid = BooleanBufferBuilder::new(row_count);
Expand Down
11 changes: 8 additions & 3 deletions datafusion/sqllogictest/test_files/array.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2038,11 +2038,16 @@ NULL
[, 51, 52, 54, 55, 56, 57, 58, 59, 60]
[61, 62, 63, 64, 65, 66, 67, 68, 69, 70]

# test with empty array
# test with empty table
query ?
select array_sort([]);
select array_sort(column1, 'DESC', 'NULLS FIRST') from arrays_values where false;
----
[]

# test with empty array
query ??
select array_sort([]), array_sort(NULL);
----
[] NULL

# test with empty row, the row that does not match the condition has row count 0
statement ok
Expand Down
Loading