apacheGH-37437: [C++] Fix MakeArrayOfNull for list array with large s…

…tring values type (apache#37467)

### Rationale for this change

`MakeArrayOfNull` for list type was assuming that the values child field didn't need to be considered, but those values could also require a minimum buffer size (eg for offsets) and which could be of greater size than the list offsets if those are int32 offsets.

### Are these changes tested?

Yes

* Closes: apache#37437

Authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>
Signed-off-by: Antoine Pitrou <antoine@python.org>

cpp/src/arrow/array/array_test.cc

@@ -388,7 +388,12 @@ static std::vector<std::shared_ptr<DataType>> TestArrayUtilitiesAgainstTheseType
       large_utf8(),
       list(utf8()),
       list(int64()),  // NOTE: Regression case for ARROW-9071/MakeArrayOfNull
+      list(large_utf8()),
+      list(list(int64())),
+      list(list(large_utf8())),
+      large_list(utf8()),
       large_list(large_utf8()),
+      large_list(list(large_utf8())),
       fixed_size_list(utf8(), 3),
       fixed_size_list(int64(), 4),
       dictionary(int32(), utf8()),

cpp/src/arrow/array/util.cc

@@ -366,9 +366,11 @@ class NullArrayFactory {
     }
 
     template <typename T>
-    enable_if_var_size_list<T, Status> Visit(const T&) {
+    enable_if_var_size_list<T, Status> Visit(const T& type) {
       // values array may be empty, but there must be at least one offset of 0
-      return MaxOf(sizeof(typename T::offset_type) * (length_ + 1));
+      RETURN_NOT_OK(MaxOf(sizeof(typename T::offset_type) * (length_ + 1)));
+      RETURN_NOT_OK(MaxOf(GetBufferLength(type.value_type(), length_)));
+      return Status::OK();
     }
 
     template <typename T>

cpp/src/arrow/array/validate.cc

@@ -713,8 +713,10 @@ struct ValidateArrayImpl {
     }
 
     // An empty list array can have 0 offsets
-    const auto required_offsets = (data.length > 0) ? data.length + data.offset + 1 : 0;
     const auto offsets_byte_size = data.buffers[1]->size();
+    const auto required_offsets = ((data.length > 0) || (offsets_byte_size > 0))
+                                      ? data.length + data.offset + 1
+                                      : 0;
     if (offsets_byte_size / static_cast<int32_t>(sizeof(offset_type)) <
         required_offsets) {
       return Status::Invalid("Offsets buffer size (bytes): ", offsets_byte_size,