// Copyright Yangqing Jia 2013
//
// This script converts the MNIST dataset to the leveldb format used
// by caffe to perform classification.
// Usage:
//    convert_mnist_data input_image_file input_label_file output_db_file
// The MNIST dataset could be downloaded at
//    http://yann.lecun.com/exdb/mnist/

#include <google/protobuf/text_format.h>
#include <glog/logging.h>
#include <leveldb/db.h>

#include <stdint.h>
#include <iostream>
#include <fstream>

#include "caffe/proto/caffe.pb.h"

uint32_t swap_endian( uint32_t val )
{
    val = ((val << 8) & 0xFF00FF00 ) | ((val >> 8) & 0xFF00FF );
    return (val << 16) | (val >> 16);
}

void convert_dataset(const char* image_filename, const char* label_filename,
        const char* db_filename) {
  // Open files
  std::ifstream image_file(image_filename, std::ios::in | std::ios::binary);
  std::ifstream label_file(label_filename, std::ios::in | std::ios::binary);
  CHECK(image_file) << "Unable to open file " << image_filename;
  CHECK(label_file) << "Unable to open file " << label_file;
  // Read the magic and the meta data
  uint32_t magic;
  uint32_t num_items;
  uint32_t num_labels;
  uint32_t rows;
  uint32_t cols;

  image_file.read((char*)(&magic), 4);
  magic = swap_endian(magic);
  CHECK_EQ(magic, 2051) << "Incorrect image file magic.";
  label_file.read((char*)(&magic), 4);
  magic = swap_endian(magic);
  CHECK_EQ(magic, 2049) << "Incorrect label file magic.";
  image_file.read((char*)(&num_items), 4);
  num_items = swap_endian(num_items);
  label_file.read((char*)(&num_labels), 4);
  num_labels = swap_endian(num_labels);
  CHECK_EQ(num_items, num_labels);
  image_file.read((char*)(&rows), 4);
  rows = swap_endian(rows);
  image_file.read((char*)(&cols), 4);
  cols = swap_endian(cols);

  // Open leveldb
  leveldb::DB* db;
  leveldb::Options options;
  options.create_if_missing = true;
  options.error_if_exists = true;
  leveldb::Status status = leveldb::DB::Open(
      options, db_filename, &db);
  CHECK(status.ok()) << "Failed to open leveldb " << db_filename
      << ". Is it already existing?";

  char label;
  char* pixels = new char[rows * cols];
  char key[10];
  std::string value;

  caffe::Datum datum;
  datum.set_channels(1);
  datum.set_height(rows);
  datum.set_width(cols);
  LOG(INFO) << "A total of " << num_items << " items.";
  LOG(INFO) << "Rows: " << rows << " Cols: " << cols;
  for (int itemid = 0; itemid < num_items; ++itemid) {
    image_file.read(pixels, rows * cols);
    label_file.read(&label, 1);
    datum.set_data(pixels, rows*cols);
    datum.set_label(label);
    datum.SerializeToString(&value);
    sprintf(key, "%08d", itemid);
    db->Put(leveldb::WriteOptions(), std::string(key), value);
  }

  delete db;
  delete pixels;
}

int main (int argc, char** argv) {
  if (argc != 4) {
    printf("This script converts the MNIST dataset to the leveldb format used\n"
           "by caffe to perform classification.\n"
           "Usage:\n"
           "    convert_mnist_data input_image_file input_label_file "
           "output_db_file\n"
           "The MNIST dataset could be downloaded at\n"
           "    http://yann.lecun.com/exdb/mnist/\n"
           "You should gunzip them after downloading.\n");
  } else {
    google::InitGoogleLogging(argv[0]);
    convert_dataset(argv[1], argv[2], argv[3]);
  }
  return 0;
}