Fix error on array_distinct when input is empty #13810 (#14034)

* fix * add test * oops --------- Co-authored-by: Cyprien Huet <[email protected]>
apache · Jan 8, 2025 · 05b6f93 · 05b6f93
1 parent b0bd899
commit 05b6f93
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/datafusion/functions-nested/src/set_ops.rs b/datafusion/functions-nested/src/set_ops.rs
@@ -513,7 +513,7 @@ fn general_array_distinct<OffsetSize: OffsetSizeTrait>(
     array: &GenericListArray<OffsetSize>,
     field: &FieldRef,
 ) -> Result<ArrayRef> {
-    if array.len() == 0 {
+    if array.is_empty() {
         return Ok(Arc::new(array.clone()) as ArrayRef);
     }
     let dt = array.value_type();
@@ -542,6 +542,9 @@ fn general_array_distinct<OffsetSize: OffsetSizeTrait>(
         };
         new_arrays.push(array);
     }
+    if new_arrays.is_empty() {
+        return Ok(Arc::new(array.clone()) as ArrayRef);
+    }
     let offsets = OffsetBuffer::new(offsets.into());
     let new_arrays_ref = new_arrays.iter().map(|v| v.as_ref()).collect::<Vec<_>>();
     let values = compute::concat(&new_arrays_ref)?;

diff --git a/datafusion/sqllogictest/test_files/array.slt b/datafusion/sqllogictest/test_files/array.slt
@@ -5681,6 +5681,11 @@ select array_distinct(a) from values ([1, 2, 3]), (null), ([1, 3, 1]) as X(a);
 NULL
 [1, 3]
 
+query ?
+select array_distinct(arrow_cast(null, 'LargeList(Int64)'));
+----
+NULL
+
 query ?
 select array_distinct([]);
 ----
-Original file line number
+Diff line change
@@ Expand Up @@
     NULL
     [1, 3]
+    query ?
+    select array_distinct(arrow_cast(null, 'LargeList(Int64)'));
+    ----
+    NULL
     query ?
     select array_distinct([]);
     ----
@@ Expand Down @@