fix: handle array/map types in ffi schema example and test (#1497)

## What changes are proposed in this pull request?
We had a bug where we used the _output_ size to try and constrain the
_input_ size when using `snprintf`. This caused us to read out of bounds
on the name string. This fixes that.

## How was this change tested?
Added a new test that we can read `nested_types`, which was failing
before.

Author: nicklan

ffi/examples/read-table/CMakeLists.txt

@@ -16,6 +16,7 @@ set(DatPath "../../../../acceptance/tests/dat/out/reader_tests/generated")
 set(ExpectedPath "../../../tests/read-table-testing/expected-data")
 set(KernelTestPath "../../../../kernel/tests/data")
 add_test(NAME read_and_print_all_prim COMMAND ${TestRunner} ${DatPath}/all_primitive_types/delta/ ${ExpectedPath}/all-prim-types.expected)
+add_test(NAME read_and_print_nested COMMAND ${TestRunner} ${DatPath}/nested_types/delta/ ${ExpectedPath}/nested-types.expected)
 add_test(NAME read_and_print_basic_partitioned COMMAND ${TestRunner} ${DatPath}/basic_partitioned/delta/ ${ExpectedPath}/basic-partitioned.expected)
 add_test(NAME read_and_print_with_dv_small COMMAND ${TestRunner} ${KernelTestPath}/table-with-dv-small/ ${ExpectedPath}/table-with-dv-small.expected)
 

ffi/examples/read-table/schema.h

@@ -148,8 +148,10 @@ void visit_array(
 {
   SchemaBuilder* builder = data;
   char* name_ptr = malloc(sizeof(char) * (name.len + 22));
-  snprintf(name_ptr, name.len + 1, "%s", name.ptr);
-  snprintf(name_ptr + name.len, 22, " (is nullable: %s)", is_nullable ? "true" : "false");
+  // NOTE: we truncate to the max int size because the format specifier "%.*s" requires an int length specifier
+  int name_chars = name.len > INT_MAX ? INT_MAX : (int)name.len; // handle _REALLY_ long names by truncation
+  int wrote = snprintf(name_ptr, name.len + 1, "%.*s", name_chars, name.ptr);
+  snprintf(name_ptr + wrote, 22, " (is nullable: %s)", is_nullable ? "true" : "false");
   print_physical_name(name_ptr, metadata);
   PRINT_CHILD_VISIT("array", name_ptr, sibling_list_id, "Types", child_list_id);
   SchemaItem* array_item = add_to_list(&builder->lists[sibling_list_id], name_ptr, "array", is_nullable);
@@ -166,8 +168,10 @@ void visit_map(
 {
   SchemaBuilder* builder = data;
   char* name_ptr = malloc(sizeof(char) * (name.len + 22));
-  snprintf(name_ptr, name.len + 1, "%s", name.ptr);
-  snprintf(name_ptr + name.len, 22, " (is nullable: %s)", is_nullable ? "true" : "false");
+  // NOTE: we truncate to the max int size because the format specifier "%.*s" requires an int length specifier
+  int name_chars = name.len > INT_MAX ? INT_MAX : (int)name.len; // handle _REALLY_ long names by truncation
+  int wrote = snprintf(name_ptr, name.len + 1, "%.*s", name_chars, name.ptr);
+  snprintf(name_ptr + wrote, 22, " (is nullable: %s)", is_nullable ? "true" : "false");
   print_physical_name(name_ptr, metadata);
   PRINT_CHILD_VISIT("map", name_ptr, sibling_list_id, "Types", child_list_id);
   SchemaItem* map_item = add_to_list(&builder->lists[sibling_list_id], name_ptr, "map", is_nullable);

ffi/tests/read-table-testing/expected-data/nested-types.expected

@@ -0,0 +1,115 @@
+Reading table at ../../../../acceptance/tests/dat/out/reader_tests/generated/nested_types/delta/
+version: 0
+
+Schema:
+├─ pk: integer
+├─ struct: struct
+│  ├─ float64: double
+│  └─ bool: boolean
+├─ array (is nullable: true): array
+│  └─ array_element: short
+└─ map (is nullable: true): map
+   ├─ map_key: string
+   └─ map_value: integer
+
+pk:  [
+  0,
+  1,
+  2,
+  3,
+  4
+]
+struct:  -- is_valid: all not null
+-- child 0 type: double
+  [
+    0,
+    1,
+    2,
+    3,
+    4
+  ]
+-- child 1 type: bool
+  [
+    true,
+    false,
+    true,
+    false,
+    true
+  ]
+array:  [
+  [
+    0
+  ],
+  [
+    0,
+    1
+  ],
+  [
+    0,
+    1,
+    2
+  ],
+  [
+    0,
+    1,
+    2,
+    3
+  ],
+  [
+    0,
+    1,
+    2,
+    3,
+    4
+  ]
+]
+map:  [
+  keys:
+  []
+  values:
+  [],
+  keys:
+  [
+    "0"
+  ]
+  values:
+  [
+    0
+  ],
+  keys:
+  [
+    "0",
+    "1"
+  ]
+  values:
+  [
+    0,
+    1
+  ],
+  keys:
+  [
+    "0",
+    "1",
+    "2"
+  ]
+  values:
+  [
+    0,
+    1,
+    2
+  ],
+  keys:
+  [
+    "0",
+    "1",
+    "2",
+    "3"
+  ]
+  values:
+  [
+    0,
+    1,
+    2,
+    3
+  ]
+]