-
Notifications
You must be signed in to change notification settings - Fork 23
/
test_zarr_compat.py
268 lines (241 loc) · 7.19 KB
/
test_zarr_compat.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
import json
import numpy as np
import pytest
import xarray as xr
from xpublish import SingleDatasetRest
from .utils import TestMapper, create_dataset
@pytest.mark.parametrize(
'start, end, freq, nlats, nlons, var_const, calendar, use_cftime',
[
('2018-01-01', '2021-01-01', 'MS', 180, 360, True, 'standard', False),
('2018-01-01', '2021-01-01', 'D', 180, 360, False, 'noleap', True),
('2018-01-01', '2021-01-01', '6H', 180, 360, True, 'gregorian', False),
('2018-01-01', '2050-01-01', 'A', 180, 360, None, '360_day', True),
],
)
def test_zmetadata_identical(start, end, freq, nlats, nlons, var_const, calendar, use_cftime):
ds = create_dataset(
start=start,
end=end,
freq=freq,
nlats=nlats,
nlons=nlons,
var_const=var_const,
use_cftime=use_cftime,
calendar=calendar,
)
ds = ds.chunk(ds.dims)
zarr_dict = {}
ds.to_zarr(zarr_dict, consolidated=True)
mapper = TestMapper(SingleDatasetRest(ds).app)
actual = json.loads(mapper['.zmetadata'].decode())
expected = json.loads(zarr_dict['.zmetadata'].decode())
assert actual == expected
@pytest.mark.parametrize(
'start, end, freq, nlats, nlons, var_const, calendar, use_cftime',
[
pytest.param(
'2018-01-01',
'2021-01-01',
'MS',
15,
30,
True,
'standard',
False,
marks=pytest.mark.xfail(
reason="Xarray's ordering of metadata coords in a string can very"
),
),
],
)
def test_zmetadata_identical_coords(
start, end, freq, nlats, nlons, var_const, calendar, use_cftime
):
ds = create_dataset(
start=start,
end=end,
freq=freq,
nlats=nlats,
nlons=nlons,
var_const=var_const,
use_cftime=use_cftime,
calendar=calendar,
use_xy_dim=True,
)
ds = ds.chunk(ds.dims)
zarr_dict = {}
ds.to_zarr(zarr_dict, consolidated=True)
mapper = TestMapper(SingleDatasetRest(ds).app)
actual = json.loads(mapper['.zmetadata'].decode())
expected = json.loads(zarr_dict['.zmetadata'].decode())
assert (
actual == expected
), "Zarr metadata did not match, likely because array coordinates aren't sorted by Xarray"
@pytest.mark.parametrize(
'start, end, freq, nlats, nlons, var_const, calendar, use_cftime',
[
(
'2018-01-01',
'2021-01-01',
'MS',
15,
30,
True,
'standard',
False,
),
],
)
def test_zmetadata_identical_coords_sorted(
start, end, freq, nlats, nlons, var_const, calendar, use_cftime
):
"""Test that zmetadata passes when coords are explicitly sorted"""
ds = create_dataset(
start=start,
end=end,
freq=freq,
nlats=nlats,
nlons=nlons,
var_const=var_const,
use_cftime=use_cftime,
calendar=calendar,
use_xy_dim=True,
)
ds = ds.chunk(ds.dims)
zarr_dict = {}
ds.to_zarr(zarr_dict, consolidated=True)
mapper = TestMapper(SingleDatasetRest(ds).app)
actual = json.loads(mapper['.zmetadata'].decode())
expected = json.loads(zarr_dict['.zmetadata'].decode())
for key in ['tmin/.zattrs', 'tmax/.zattrs']:
coords = expected['metadata'][key]['coordinates']
expected['metadata'][key]['coordinates'] = ' '.join(sorted(coords.split(' ')))
assert actual == expected
@pytest.mark.parametrize(
'start, end, freq, nlats, nlons, var_const, calendar, use_cftime',
[
('2018-01-01', '2021-01-01', 'MS', 180, 360, True, 'standard', False),
('2018-01-01', '2021-01-01', 'D', 180, 360, False, 'noleap', True),
('2018-01-01', '2021-01-01', '6H', 180, 360, True, 'gregorian', False),
('2018-01-01', '2050-01-01', 'A', 180, 360, None, '360_day', True),
],
)
def test_roundtrip(start, end, freq, nlats, nlons, var_const, calendar, use_cftime):
ds = create_dataset(
start=start,
end=end,
freq=freq,
nlats=nlats,
nlons=nlons,
var_const=var_const,
use_cftime=use_cftime,
calendar=calendar,
)
ds = ds.chunk(ds.dims)
mapper = TestMapper(SingleDatasetRest(ds).app)
actual = xr.open_zarr(mapper, consolidated=True)
xr.testing.assert_identical(actual, ds)
xfail_reason = """Currently, xarray casts datetimes arrays to NumPy compatible arrays.
This ends up producing unexpected behavior when calling encode_zarr_varible()
on datasets with variables containing datetime like dtypes.
See: https://github.com/xpublish-community/xpublish/pull/10#discussion_r388028417"""
@pytest.mark.parametrize(
'start, end, freq, nlats, nlons, var_const, calendar, use_cftime, chunks, decode_times',
[
('2018-01-01', '2021-01-01', 'MS', 180, 360, True, 'standard', False, {'time': 10}, False),
(
'2018-01-01',
'2021-01-01',
'D',
300,
600,
False,
'noleap',
True,
{'time': 10, 'lat': 300, 'lon': 300},
False,
),
pytest.param(
'2018-01-01',
'2021-01-01',
'D',
300,
600,
False,
'noleap',
True,
{'time': 10, 'lat': 300, 'lon': 300},
True,
marks=pytest.mark.xfail(reason=xfail_reason),
),
(
'2018-01-01',
'2021-01-01',
'12H',
180,
360,
True,
'gregorian',
False,
{'time': 36, 'lat': 10},
False,
),
(
'2018-01-01',
'2038-01-01',
'A',
300,
600,
None,
'360_day',
True,
{'time': 10, 'lat': 75, 'lon': 120},
False,
),
pytest.param(
'2018-01-01',
'2038-01-01',
'A',
300,
600,
None,
'360_day',
True,
{'time': 10, 'lat': 75, 'lon': 120},
True,
marks=pytest.mark.xfail(reason=xfail_reason),
),
],
)
def test_roundtrip_custom_chunks(
start, end, freq, nlats, nlons, var_const, calendar, use_cftime, chunks, decode_times
):
ds = create_dataset(
start=start,
end=end,
freq=freq,
nlats=nlats,
nlons=nlons,
var_const=var_const,
use_cftime=use_cftime,
calendar=calendar,
decode_times=decode_times,
)
ds = ds.chunk(chunks)
mapper = TestMapper(SingleDatasetRest(ds).app)
actual = xr.open_zarr(mapper, consolidated=True, decode_times=decode_times)
xr.testing.assert_identical(actual, ds)
def test_scalar_variable():
ds = xr.Dataset(
{
'scalar': xr.DataArray(
np.float32(0.0),
dims=(),
name='scalar',
)
}
)
mapper = TestMapper(SingleDatasetRest(ds).app)
actual = xr.open_zarr(mapper, consolidated=True)
xr.testing.assert_identical(actual, ds)