def _get_backup_file(ds):
backup_filename = ds.backup_filename
if os.path.exists(backup_filename):
# backup file already exists, open it. We use parallel
# h5py if it is available
if communication_system.communicators[-1].size > 1 and h5py.get_config(
).mpi:
mpi4py_communicator = communication_system.communicators[-1].comm
f = h5py.File(backup_filename,
mode="r+",
driver="mpio",
comm=mpi4py_communicator)
else:
f = h5py.File(backup_filename, mode="r+")
yield f
f.close()
else:
# backup file does not exist, create it
with _create_new_gdf(
ds,
backup_filename,
data_author=None,
data_comment=None,
particle_type_name="dark_matter",
) as f:
yield f
def _create_new_gdf(ds,
gdf_path,
data_author=None,
data_comment=None,
dataset_units=None,
particle_type_name="dark_matter",
clobber=False):
# Make sure we have the absolute path to the file first
gdf_path = os.path.abspath(gdf_path)
# Is the file already there? If so, are we allowing
# clobbering?
if os.path.exists(gdf_path) and not clobber:
raise YTGDFAlreadyExists(gdf_path)
###
# Create and open the file with h5py. We use parallel
# h5py if it is available.
###
if communication_system.communicators[-1].size > 1 and \
h5py.get_config().mpi is True:
mpi4py_communicator = communication_system.communicators[-1].comm
f = h5py.File(gdf_path, "w", driver='mpio', comm=mpi4py_communicator)
else:
f = h5py.File(gdf_path, "w")
###
# "gridded_data_format" group
###
g = f.create_group("gridded_data_format")
g.attrs["data_software"] = "yt"
g.attrs["data_software_version"] = yt_version
if data_author is not None:
g.attrs["data_author"] = data_author
if data_comment is not None:
g.attrs["data_comment"] = data_comment
###
# "simulation_parameters" group
###
g = f.create_group("simulation_parameters")
g.attrs["refine_by"] = ds.refine_by
g.attrs["dimensionality"] = ds.dimensionality
g.attrs["domain_dimensions"] = ds.domain_dimensions
g.attrs["current_time"] = ds.current_time
g.attrs["domain_left_edge"] = ds.domain_left_edge
g.attrs["domain_right_edge"] = ds.domain_right_edge
g.attrs["unique_identifier"] = ds.unique_identifier
g.attrs["cosmological_simulation"] = ds.cosmological_simulation
# @todo: Where is this in the yt API?
g.attrs["num_ghost_zones"] = 0
# @todo: Where is this in the yt API?
g.attrs["field_ordering"] = 0
# @todo: not yet supported by yt.
g.attrs["boundary_conditions"] = np.array([0, 0, 0, 0, 0, 0], 'int32')
if ds.cosmological_simulation:
g.attrs["current_redshift"] = ds.current_redshift
g.attrs["omega_matter"] = ds.omega_matter
g.attrs["omega_lambda"] = ds.omega_lambda
g.attrs["hubble_constant"] = ds.hubble_constant
if dataset_units is None:
dataset_units = {}
g = f.create_group("dataset_units")
for u in ["length", "time", "mass", "velocity", "magnetic"]:
unit_name = u + "_unit"
if unit_name in dataset_units:
value, units = dataset_units[unit_name]
else:
attr = getattr(ds, unit_name)
value = float(attr)
units = str(attr.units)
d = g.create_dataset(unit_name, data=value)
d.attrs["unit"] = units
###
# "field_types" group
###
g = f.create_group("field_types")
###
# "particle_types" group
###
g = f.create_group("particle_types")
# @todo: Particle type iterator
sg = g.create_group(particle_type_name)
sg["particle_type_name"] = np.string_(particle_type_name)
###
# root datasets -- info about the grids
###
f["grid_dimensions"] = ds.index.grid_dimensions
f["grid_left_index"] = np.array([
grid.get_global_startindex() for grid in ds.index.grids
]).reshape(ds.index.grid_dimensions.shape[0], 3)
f["grid_level"] = ds.index.grid_levels.flat
# @todo: Fill with proper values
f["grid_parent_id"] = -np.ones(ds.index.grid_dimensions.shape[0])
f["grid_particle_count"] = ds.index.grid_particle_count
###
# "data" group -- where we should spend the most time
###
g = f.create_group("data")
for grid in ds.index.grids:
# add group for this grid
grid_group = g.create_group("grid_%010i" % (grid.id - grid._id_offset))
# add group for the particles on this grid
particles_group = grid_group.create_group("particles")
particles_group.create_group(particle_type_name)
yield f
# close the file when done
f.close()