fix: array_any_value returns NULL for empty list elements

datafusion/functions-nested/src/extract.rs

@@ -970,7 +970,7 @@ where
 
 #[user_doc(
     doc_section(label = "Array Functions"),
-    description = "Returns the first non-null element in the array.",
+    description = "Returns the first non-null element in the array. Returns NULL if the array is empty or NULL.",
     syntax_example = "array_any_value(array)",
     sql_example = r#"```sql
 > select array_any_value([NULL, 1, 2, 3]);
@@ -1062,13 +1062,21 @@ where
 
     for (row_index, offset_window) in array.offsets().windows(2).enumerate() {
         let start = offset_window[0];
+        let end = offset_window[1];
 
-        // array is null
+        // the list element is null
         if array.is_null(row_index) {
             mutable.try_extend_nulls(1)?;
             continue;
         }
 
+        // the list element is empty; there is no value to take, so the result
+        // is NULL.
+        if start == end {
+            mutable.try_extend_nulls(1)?;
+            continue;
+        }
+
         let row_value = array.value(row_index);
         match row_value.nulls() {
             Some(row_nulls_buffer) => {

datafusion/sqllogictest/test_files/array/array_any_value.slt

@@ -145,6 +145,35 @@ select array_any_value(make_array(NULL, 1, 2, 3, 4, 5)), array_any_value(column1
 1 41
 1 51
 
+# array_any_value with empty (length-0) list elements
+# A non-null but empty list must yield NULL, including a trailing empty element
+# whose start offset equals the values length
+statement ok
+create table any_value_empty (id int, tags bigint[]) as values
+  (1, make_array(10)),
+  (2, cast(make_array() as bigint[])),
+  (3, make_array(20, 30)),
+  (4, cast(make_array() as bigint[]));
+
+query II
+select id, array_any_value(tags) from any_value_empty order by id;
+----
+1 10
+2 NULL
+3 20
+4 NULL
+
+query II
+select id, array_any_value(arrow_cast(tags, 'LargeList(Int64)')) from any_value_empty order by id;
+----
+1 10
+2 NULL
+3 20
+4 NULL
+
+statement ok
+drop table any_value_empty;
+
 # make_array with nulls
 query ???????
 select make_array(make_array('a','b'), null),

docs/source/user-guide/sql/scalar_functions.md

@@ -3430,7 +3430,7 @@ any_match(array, predicate)
 
 ### `array_any_value`
 
-Returns the first non-null element in the array.
+Returns the first non-null element in the array. Returns NULL if the array is empty or NULL.
 
 ```sql
 array_any_value(array)