Adding assertion to check for regular JSON inputs of size greater tha…

…n `INT_MAX` bytes (#17057)

Addresses #17017 

Libcudf does not support parsing regular JSON inputs of size greater than `INT_MAX` bytes. Note that the batched reader can only be used for JSON lines inputs.

Authors:
  - Shruti Shivakumar (https://github.com/shrshi)

Approvers:
  - Muhammad Haseeb (https://github.com/mhaseeb123)
  - Vukasin Milovanovic (https://github.com/vuule)
  - Karthikeyan (https://github.com/karthikeyann)

URL: #17057

cpp/src/io/json/nested_json_gpu.cu

@@ -83,8 +83,7 @@ struct tree_node {
 void check_input_size(std::size_t input_size)
 {
   // Transduce() writes symbol offsets that may be as large input_size-1
-  CUDF_EXPECTS(input_size == 0 ||
-                 (input_size - 1) <= std::numeric_limits<cudf::io::json::SymbolOffsetT>::max(),
+  CUDF_EXPECTS(input_size == 0 || (input_size - 1) <= std::numeric_limits<int32_t>::max(),
                "Given JSON input is too large");
 }
 }  // namespace

cpp/src/io/json/read_json.cu

@@ -351,10 +351,16 @@ table_with_metadata read_json(host_span<std::unique_ptr<datasource>> sources,
    * JSON inputs.
    */
   std::size_t const total_source_size = sources_size(sources, 0, 0);
-  std::size_t chunk_offset            = reader_opts.get_byte_range_offset();
-  std::size_t chunk_size              = reader_opts.get_byte_range_size();
-  chunk_size                          = !chunk_size ? total_source_size - chunk_offset
-                                                    : std::min(chunk_size, total_source_size - chunk_offset);
+
+  // Batching is enabled only for JSONL inputs, not regular JSON files
+  CUDF_EXPECTS(
+    reader_opts.is_enabled_lines() || total_source_size < std::numeric_limits<int32_t>::max(),
+    "Parsing Regular JSON inputs of size greater than INT_MAX bytes is not supported");
+
+  std::size_t chunk_offset = reader_opts.get_byte_range_offset();
+  std::size_t chunk_size   = reader_opts.get_byte_range_size();
+  chunk_size               = !chunk_size ? total_source_size - chunk_offset
+                                         : std::min(chunk_size, total_source_size - chunk_offset);
 
   std::size_t const size_per_subchunk      = estimate_size_per_subchunk(chunk_size);
   std::size_t const batch_size_upper_bound = get_batch_size_upper_bound();