Function parse_header

include/libnpy/npy.hpp:349–399

inline header_t parse_header(std::string header) {
  /*
     The first 6 bytes are a magic string: exactly "x93NUMPY".
     The next 1 byte is an unsigned byte: the major version number of the file format, e.g. x01.
     The next 1 byte is an unsigned byte: the minor version number of the file format, e.g. x00. Note: the version of the file format is not tied to the version of the numpy package.
     The next 2 bytes form a little-endian unsigned short int: the length of the header data HEADER_LEN.
     The next HEADER_LEN bytes form the header data describing the array's format. It is an ASCII string which contains a Python literal expression of a dictionary. It is terminated by a newline ('n') and padded with spaces ('x20') to make the total length of the magic string + 4 + HEADER_LEN be evenly divisible by 16 for alignment purposes.
     The dictionary contains three keys:

     "descr" : dtype.descr
     An object that can be passed as an argument to the numpy.dtype() constructor to create the array's dtype.
     "fortran_order" : bool
     Whether the array data is Fortran-contiguous or not. Since Fortran-contiguous arrays are a common form of non-C-contiguity, we allow them to be written directly to disk for efficiency.
     "shape" : tuple of int
     The shape of the array.
     For repeatability and readability, this dictionary is formatted using pprint.pformat() so the keys are in alphabetic order.
   */

  // remove trailing newline
  if (header.back() != '\n')
    throw std::runtime_error("invalid header");
  header.pop_back();

  // parse the dictionary
  std::vector <std::string> keys{"descr", "fortran_order", "shape"};
  auto dict_map = npy::pyparse::parse_dict(header, keys);

  if (dict_map.size() == 0)
    throw std::runtime_error("invalid dictionary in header");

  std::string descr_s = dict_map["descr"];
  std::string fortran_s = dict_map["fortran_order"];
  std::string shape_s = dict_map["shape"];

  std::string descr = npy::pyparse::parse_str(descr_s);
  dtype_t dtype = parse_descr(descr);

  // convert literal Python bool to C++ bool
  bool fortran_order = npy::pyparse::parse_bool(fortran_s);

  // parse the shape tuple
  auto shape_v = npy::pyparse::parse_tuple(shape_s);

  std::vector <ndarray_len_t> shape;
  for (auto item : shape_v) {
    ndarray_len_t dim = static_cast<ndarray_len_t>(std::stoul(item));
    shape.push_back(dim);
  }

  return {dtype, fortran_order, shape};
}


inline std::string