feat: add debug assertions for new bulk append unsafe code

Add debug_assert! statements before unsafe blocks in the new bulk
append methods (impl_append_to_builder macro, append_booleans,
append_timestamps, append_dates) and the read_row_at macro.

Assertions verify null pointer and element_offset validity before
raw pointer dereference in the hot path for array element iteration.

Author: andygrove

native/core/src/execution/shuffle/spark_unsafe/list.rs

@@ -49,6 +49,8 @@ macro_rules! impl_append_to_builder {
             if NULLABLE {
                 let mut ptr = self.element_offset as *const $element_type;
                 let null_words = self.null_bitset_ptr();
+                debug_assert!(!null_words.is_null(), "null_bitset_ptr is null");
+                debug_assert!(!ptr.is_null(), "element_offset pointer is null");
                 for idx in 0..num_elements {
                     let word_idx = idx >> 6;
                     let bit_idx = idx & 0x3f;
@@ -66,6 +68,7 @@ macro_rules! impl_append_to_builder {
                 }
             } else {
                 // SAFETY: element_offset points to contiguous data of length num_elements
+                debug_assert!(self.element_offset != 0, "element_offset is null");
                 let slice = unsafe {
                     std::slice::from_raw_parts(
                         self.element_offset as *const $element_type,
@@ -168,9 +171,11 @@ impl SparkUnsafeArray {
         }
 
         let mut ptr = self.element_offset as *const u8;
+        debug_assert!(!ptr.is_null(), "append_booleans: element_offset pointer is null");
 
         if NULLABLE {
             let null_words = self.null_bitset_ptr();
+            debug_assert!(!null_words.is_null(), "append_booleans: null_bitset_ptr is null");
             for idx in 0..num_elements {
                 let word_idx = idx >> 6;
                 let bit_idx = idx & 0x3f;
@@ -208,6 +213,8 @@ impl SparkUnsafeArray {
         if NULLABLE {
             let mut ptr = self.element_offset as *const i64;
             let null_words = self.null_bitset_ptr();
+            debug_assert!(!null_words.is_null(), "append_timestamps: null_bitset_ptr is null");
+            debug_assert!(!ptr.is_null(), "append_timestamps: element_offset pointer is null");
             for idx in 0..num_elements {
                 let word_idx = idx >> 6;
                 let bit_idx = idx & 0x3f;
@@ -225,6 +232,7 @@ impl SparkUnsafeArray {
             }
         } else {
             // SAFETY: element_offset points to contiguous i64 data of length num_elements
+            debug_assert!(self.element_offset != 0, "append_timestamps: element_offset is null");
             let slice = unsafe {
                 std::slice::from_raw_parts(self.element_offset as *const i64, num_elements)
             };
@@ -245,6 +253,8 @@ impl SparkUnsafeArray {
         if NULLABLE {
             let mut ptr = self.element_offset as *const i32;
             let null_words = self.null_bitset_ptr();
+            debug_assert!(!null_words.is_null(), "append_dates: null_bitset_ptr is null");
+            debug_assert!(!ptr.is_null(), "append_dates: element_offset pointer is null");
             for idx in 0..num_elements {
                 let word_idx = idx >> 6;
                 let bit_idx = idx & 0x3f;
@@ -262,6 +272,7 @@ impl SparkUnsafeArray {
             }
         } else {
             // SAFETY: element_offset points to contiguous i32 data of length num_elements
+            debug_assert!(self.element_offset != 0, "append_dates: element_offset is null");
             let slice = unsafe {
                 std::slice::from_raw_parts(self.element_offset as *const i32, num_elements)
             };

native/core/src/execution/shuffle/spark_unsafe/row.rs

@@ -726,6 +726,8 @@ fn append_nested_struct_fields_field_major(
 macro_rules! read_row_at {
     ($row:expr, $row_addresses_ptr:expr, $row_sizes_ptr:expr, $i:expr) => {{
         // SAFETY: Caller guarantees pointers are valid for this index (see macro doc)
+        debug_assert!(!$row_addresses_ptr.is_null(), "read_row_at: null row_addresses_ptr");
+        debug_assert!(!$row_sizes_ptr.is_null(), "read_row_at: null row_sizes_ptr");
         let row_addr = unsafe { *$row_addresses_ptr.add($i) };
         let row_size = unsafe { *$row_sizes_ptr.add($i) };
         $row.point_to(row_addr, row_size);