#include "llvm/Support/raw_ostream.h"
#include "tensorflow/compiler/mlir/lite/schema/schema_generated.h"
#include "tensorflow/compiler/mlir/lite/schema/schema_utils.h"
#include "tensorflow/lite/model.h"

using llvm::cl::opt;

// RUN: flatbuffer_translate -mlir-to-tflite-flatbuffer %s.mlir -o - \
// RUN:   | %p/importer_test_min_max - \
// RUN:   | flatbuffer_translate --tflite-flatbuffer-to-mlir - -o - \
// RUN:   | FileCheck %s

                             const tflite::Model* input_model,
                             BufferType quant_type,
                             bool use_updated_hybrid_scheme) {
  tflite::TensorType inference_type;
  switch (quant_type) {
    case BufferType::QUANTIZED_FLOAT16:
      inference_type = tflite::TensorType_FLOAT16;
      break;
    default:
      inference_type = tflite::TensorType_INT8;
  }

  flatbuffers::Offset<tflite::Model> input_model_location =
      tflite::Model::Pack(input_builder, &input_model);
  tflite::FinishModelBuffer(input_builder, input_model_location);

  std::string serialized_model(
      reinterpret_cast<const char*>(input_builder.GetBufferPointer()),
      input_builder.GetSize());

  OwningOpRef<mlir::ModuleOp> module = tflite::FlatBufferToMlir(

               << ", input_inference_type: "
               << tflite::EnumNameTensorType(input_type)
               << ", output_inference_type: "
               << tflite::EnumNameTensorType(output_type) << "\n";
  mlir::Builder mlir_builder(&context);
  mlir::Type input_mlir_type =
      tflite::ConvertElementType(input_type, mlir_builder);
  mlir::Type output_mlir_type =
      tflite::ConvertElementType(output_type, mlir_builder);

        return tensorflow::PyoOrThrow(
            tflite::MlirSparsifyModel(input_contents_txt_raw.ptr()));
      },
      py::arg("input_contents_txt_raw"),
      R"pbdoc(
      Returns a sparsified model.
    )pbdoc");
  m.def(
      "RegisterCustomOpdefs",
      [](py::object custom_opdefs_txt_raw) {
        return tensorflow::PyoOrThrow(
            tflite::RegisterCustomOpdefs(custom_opdefs_txt_raw.ptr()));
      },

  // Load input model
  auto input_fbm = tflite::FlatBufferModel::BuildFromFile(
      "tensorflow/lite/testdata/sparse_tensor.bin");
  tflite::ModelT input_model;
  input_fbm->GetModel()->UnPackTo(&input_model);

  // Populate input metadata
  auto model_metadata_buffer = std::make_unique<tflite::BufferT>();
  model_metadata_buffer->data =
      std::vector<uint8_t>(expected_value.begin(), expected_value.end());

#include "mlir/Support/LLVM.h"  // from @llvm-project
#include "tensorflow/compiler/mlir/lite/experimental/tac/common/targets.h"
#include "tensorflow/compiler/mlir/lite/experimental/tac/hardwares/target_hardware.h"
#include "tensorflow/compiler/mlir/lite/experimental/tac/runtime_metadata_generated.h"
#include "tensorflow/compiler/mlir/lite/ir/tfl_ops.h"
#include "tensorflow/compiler/mlir/lite/quantization/ir/QuantOps.h"

// quantization, specifically for
// third_party/tensorflow/lite/tools/optimize/quantize_weights.h.
// TODO(b/202468183): Selective quantization + quant debugger support for
// dynamic range quantization for verify_numeric and whole_model_verify flags.
TfLiteStatus QuantizeWeights(
    flatbuffers::FlatBufferBuilder* builder, const tflite::Model* input_model,
    const tflite::TensorType& inference_type,

#include "flatbuffers/flatbuffers.h"  // from @flatbuffers
#include "flatbuffers/minireflect.h"  // from @flatbuffers
#include "tensorflow/compiler/mlir/lite/schema/reflection/schema_generated.h"
#if FLATBUFFERS_LITTLEENDIAN == 0
#include "tensorflow/lite/core/model_builder.h"
#endif

namespace tflite {
namespace {

// Reads a model from a provided file path and verifies if it is a valid

// of double, and call TOCO's quantization routines to maintain bit-exactness of
// the values with the TOCO quantizer.
TfLiteStatus QuantizeModel(
    absl::string_view model_buffer, const tflite::TensorType &input_type,
    const tflite::TensorType &output_type,
    const tflite::TensorType &inference_type,
    const std::unordered_set<std::string> &operator_names,
    bool disable_per_channel, bool fully_quantize, std::string &output_buffer,