#include "tensorflow/core/protobuf/tensorflow_server.pb.h"

namespace {

using ::tensorflow::string;

void ReplaceTaskInServerDef(tensorflow::ServerDef* server_def, int task_index) {
  tensorflow::JobDef* job_def = server_def->mutable_cluster()->mutable_job(0);
  int port = tensorflow::testing::PickUnusedPortOrDie();
  job_def->mutable_tasks()->at(task_index) =
      tensorflow::strings::StrCat("localhost:", port);
}

int TF_CheckpointReaderHasTensor(TF_CheckpointReader* reader,
                                 const char* name) {
  return reader->HasTensor(name);
}

const char* TF_CheckpointReaderGetVariable(TF_CheckpointReader* reader,
                                           int index) {
  return reader->variable_list[index].c_str();
}

int TF_CheckpointReaderSize(TF_CheckpointReader* reader) {

}

void TF_InitPlugin(TF_FilesystemPluginInfo* info) {
  info->plugin_memory_allocate = plugin_memory_allocate;
  info->plugin_memory_free = plugin_memory_free;
  info->num_schemes = 2;
  info->ops = static_cast<TF_FilesystemPluginOps*>(
      plugin_memory_allocate(info->num_schemes * sizeof(info->ops[0])));
  ProvideFilesystemSupportFor(&info->ops[0], "");
  ProvideFilesystemSupportFor(&info->ops[1], "file");

// data.
bool IsValidStrideCompactRowMajorData(int64_t* shape_arr, int64_t* stride_arr,
                                      int ndim) {
  bool valid = true;
  int64_t expected_stride = 1;
  for (int i = ndim - 1; i >= 0; --i) {
    // Empty tensors are always compact regardless of strides.
    if (shape_arr[i] == 0) return true;

  EXPECT_TRUE(executed);
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK) << TF_Message(status.get());
  TFE_DeleteTensorHandle(retval);

  // Explicit placement still forces the op onto the requested device
  matmul.reset(MatMulOp(context.get(), hcustom0.get(), hcpu.get()));
  TFE_OpSetDevice(matmul.get(), "/job:localhost/replica:0/task:0/device:CPU:0",
                  status.get());

      TF_AllocateTensor(TF_INT8, dims, num_dims, sizeof(char) * num_values);
  memcpy(TF_TensorData(t), values, sizeof(char) * num_values);
  return t;
}

TF_Tensor* Int32Tensor(const int64_t* dims, int num_dims,
                       const int32_t* values) {
  int64_t num_values = 1;
  for (int i = 0; i < num_dims; ++i) {
    num_values *= dims[i];
  }
  TF_Tensor* t =

//
// Since this function is used to satisfy the TFE_CustomDevice C API,
// device_info is passed in using a C-style generic. It must always be a
// ParallelDevice.
void DeleteParallelDevice(void* device_info) {
  delete reinterpret_cast<NamedParallelDevice*>(device_info);
}

}  // namespace

void AllocateParallelDevice(const char* device_name,

    const TF_Graph* fn_body, const char* fn_name, int ninputs,
    const TF_Output* inputs, std::vector<OutputTensor>* input_tensors,
    std::unordered_map<const Node*, std::vector<int>>* input_nodes)
    TF_EXCLUSIVE_LOCKS_REQUIRED(fn_body->mu) {
  input_tensors->reserve(ninputs);
  for (int i = 0; i < ninputs; ++i) {
    Node* node = inputs[i].oper ? &inputs[i].oper->node : nullptr;
    int idx = inputs[i].index;

    TF_SetStatus(status, TF_OK, "");
    return 0;
  }
  if (!IsCacheEnabled() || (n > max_bytes_)) {
    // The cache is effectively disabled, so we pass the read through to the
    // fetcher without breaking it up into blocks.
    return block_fetcher_(filename, offset, n, buffer, status);
  }
  // Calculate the block-aligned start and end of the read.
  size_t start = block_size_ * (offset / block_size_);

  TF_Tensor* result_tensor = TFE_TensorHandleResolve(result_t, status.get());

  // Copy Tensor data into an array.
  float result_data[4] = {0};
  memcpy(&result_data[0], TF_TensorData(result_tensor),
         TF_TensorByteSize(result_tensor));

  int data_len = 4;  // length of result_data
  for (int i = 0; i < data_len; i++) {
    EXPECT_EQ(result_data[i], 0);
  }

  TF_DeleteTensor(result_tensor);