This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 3764fe760a Fix array_concat with NULL arrays (#16348)
3764fe760a is described below
commit 3764fe760ad9b1e2cbff0aabbd46dd1de59a98a8
Author: alexanderbianchi <75697973+alexanderbian...@users.noreply.github.com>
AuthorDate: Thu Jun 12 08:24:48 2025 -0400
Fix array_concat with NULL arrays (#16348)
* Fix array_concat with NULL arrays to avoid Arrow concat error
- Fix array_concat_inner to properly handle NULL list arrays by checking
null_count
- Add logic to create properly typed empty arrays for all-null inputs
- Support NULL handling for List, LargeList, and FixedSizeList types
- Add comprehensive test coverage for NULL array scenarios
Fixes issue where 'select array_concat(NULL::integer[])' would throw
'Arrow error: Compute error: concat requires input of at least one array'
* Simplify null count check and null array generation
---
datafusion/functions-nested/src/concat.rs | 20 ++++++++++++----
datafusion/sqllogictest/test_files/array.slt | 36 ++++++++++++++++++++++++++++
2 files changed, 52 insertions(+), 4 deletions(-)
diff --git a/datafusion/functions-nested/src/concat.rs
b/datafusion/functions-nested/src/concat.rs
index dd8784d36c..e8b7fc27b4 100644
--- a/datafusion/functions-nested/src/concat.rs
+++ b/datafusion/functions-nested/src/concat.rs
@@ -23,7 +23,7 @@ use std::sync::Arc;
use crate::make_array::make_array_inner;
use crate::utils::{align_array_dimensions, check_datatypes,
make_scalar_function};
use arrow::array::{
- Array, ArrayRef, Capacities, GenericListArray, MutableArrayData, NullArray,
+ Array, ArrayData, ArrayRef, Capacities, GenericListArray, MutableArrayData,
NullBufferBuilder, OffsetSizeTrait,
};
use arrow::buffer::OffsetBuffer;
@@ -42,6 +42,7 @@ use datafusion_expr::{
ColumnarValue, Documentation, ScalarUDFImpl, Signature, Volatility,
};
use datafusion_macros::user_doc;
+use itertools::Itertools;
make_udf_expr_and_func!(
ArrayAppend,
@@ -364,12 +365,23 @@ pub(crate) fn array_concat_inner(args: &[ArrayRef]) ->
Result<ArrayRef> {
DataType::LargeList(_) => large_list = true,
_ => (),
}
-
- all_null = false
+ if arg.null_count() < arg.len() {
+ all_null = false;
+ }
}
if all_null {
- Ok(Arc::new(NullArray::new(args[0].len())))
+ // Return a null array with the same type as the first non-null-type
argument
+ let return_type = args
+ .iter()
+ .map(|arg| arg.data_type())
+ .find_or_first(|d| !d.is_null())
+ .unwrap(); // Safe because args is non-empty
+
+ Ok(arrow::array::make_array(ArrayData::new_null(
+ return_type,
+ args[0].len(),
+ )))
} else if large_list {
concat_internal::<i64>(args)
} else {
diff --git a/datafusion/sqllogictest/test_files/array.slt
b/datafusion/sqllogictest/test_files/array.slt
index 3f0233325e..0139daecca 100644
--- a/datafusion/sqllogictest/test_files/array.slt
+++ b/datafusion/sqllogictest/test_files/array.slt
@@ -3070,6 +3070,42 @@ select array_concat([]);
----
[]
+# test with NULL array
+query ?
+select array_concat(NULL::integer[]);
+----
+NULL
+
+# test with multiple NULL arrays
+query ?
+select array_concat(NULL::integer[], NULL::integer[]);
+----
+NULL
+
+# test with NULL LargeList
+query ?
+select array_concat(arrow_cast(NULL::string[], 'LargeList(Utf8)'));
+----
+NULL
+
+# test with NULL FixedSizeList
+query ?
+select array_concat(arrow_cast(NULL::string[], 'FixedSizeList(2, Utf8)'));
+----
+NULL
+
+# test with mix of NULL and empty arrays
+query ?
+select array_concat(NULL::integer[], []);
+----
+[]
+
+# test with mix of NULL and non-empty arrays
+query ?
+select array_concat(NULL::integer[], [1, 2, 3]);
+----
+[1, 2, 3]
+
# Concatenating strings arrays
query ?
select array_concat(
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@datafusion.apache.org
For additional commands, e-mail: commits-h...@datafusion.apache.org
