def test_chunksizes(tmpnetcdf_filename):
nco = create_netcdf(tmpnetcdf_filename)
x = numpy.arange(3, dtype='float32')
y = numpy.arange(5, dtype='float32')
coord1 = create_coordinate(nco, 'x', x, 'm')
coord2 = create_coordinate(nco, 'y', y, 'm')
assert coord1 is not None and coord2 is not None
no_chunks = create_variable(nco, 'no_chunks',
Variable(numpy.dtype('int16'), None, ('x', 'y'), None))
min_max_chunks = create_variable(nco, 'min_max_chunks',
Variable(numpy.dtype('int16'), None, ('x', 'y'), None),
chunksizes=(2, 50))
assert no_chunks is not None
assert min_max_chunks is not None
strings = numpy.array(["AAa", 'bbb', 'CcC'], dtype='S')
strings = xr.DataArray(strings, dims=['x'], coords={'x': x})
create_variable(nco, 'strings_unchunked', strings)
create_variable(nco, 'strings_chunked', strings, chunksizes=(1,))
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert nco['no_chunks'].chunking() == 'contiguous'
assert nco['min_max_chunks'].chunking() == [2, 5]
assert nco['strings_unchunked'].chunking() == 'contiguous'
assert nco['strings_chunked'].chunking() == [1, 3]
def make_fake_netcdf_dataset(nc_name, doc_text):
t = np.asarray([parse_time('2001-01-29 07:06:05.432')], dtype=np.datetime64)
npdata = np.asarray([doc_text], dtype='S')
with create_netcdf(nc_name) as nco:
create_coordinate(nco, 'time', t, 'seconds since 1970-01-01 00:00:00')
nc_dataset = create_variable(nco, 'dataset',
Variable(npdata.dtype, None, ('time',), None))
nc_dataset[:] = netcdfy_data(npdata)
assert 'dataset_nchar' in nco.dimensions
def test_create_string_variable(tmpnetcdf_filename, s1, s2, s3):
str_var = 'str_var'
nco = create_netcdf(tmpnetcdf_filename)
coord = create_coordinate(nco, 'greg', numpy.array([1.0, 3.0, 9.0]), 'cubic gregs')
assert coord is not None
dtype = numpy.dtype('S100')
data = numpy.array([s1, s2, s3], dtype=dtype)
var = create_variable(nco, str_var, Variable(dtype, None, ('greg',), None))
var[:] = netcdfy_data(data)
nco.close()
with netCDF4.Dataset(tmpnetcdf_filename) as nco:
assert str_var in nco.variables
for returned, expected in zip(read_strings_from_netcdf(tmpnetcdf_filename, variable=str_var), (s1, s2, s3)):
assert returned == expected
def make_fake_netcdf_dataset(nc_name, doc_text):
from datacube.drivers.netcdf.writer import (
Variable,
create_variable,
create_coordinate,
netcdfy_data,
create_netcdf
)
from datacube.utils.dates import parse_time
import numpy as np
t = np.asarray([parse_time('2001-01-29 07:06:05.432')], dtype=np.datetime64)
npdata = np.asarray([doc_text], dtype='S')
with create_netcdf(nc_name) as nco:
create_coordinate(nco, 'time', t, 'seconds since 1970-01-01 00:00:00')
nc_dataset = create_variable(nco, 'dataset',
Variable(npdata.dtype, None, ('time',), None))
nc_dataset[:] = netcdfy_data(npdata)
assert 'dataset_nchar' in nco.dimensions