-
Notifications
You must be signed in to change notification settings - Fork 3
/
test_pipelineconfig.py
301 lines (274 loc) · 12.6 KB
/
test_pipelineconfig.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
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
import os
from typing import Any, Dict
import uuid
from django.conf import settings
from django.contrib.auth.models import AnonymousUser
from django.test import SimpleTestCase, override_settings
import strictyaml as yaml
from vast_pipeline.management.commands.initpiperun import make_config_template
from vast_pipeline.pipeline.config import PipelineConfig
from vast_pipeline.pipeline.errors import PipelineConfigError
from vast_pipeline.utils.utils import dict_merge
TEST_ROOT = os.path.join(settings.BASE_DIR, "vast_pipeline", "tests")
@override_settings(
PIPELINE_WORKING_DIR=os.path.join(TEST_ROOT, "pipeline-runs"),
MAX_PIPERUN_IMAGES=10,
)
class CheckRunConfigValidationTest(SimpleTestCase):
def setUp(self):
# load a base run configuration file
self.config_path = os.path.join(
settings.PIPELINE_WORKING_DIR, "basic-association", "config.yaml"
)
with open(self.config_path) as fh:
config_text = fh.read()
config_dict: Dict[str, Any] = yaml.load(config_text).data
config_dict["run"]["path"] = os.path.dirname(self.config_path)
# make a template config based on defaults
config_defaults_str = make_config_template(
PipelineConfig.TEMPLATE_PATH, **settings.PIPE_RUN_CONFIG_DEFAULTS
)
config_defaults_dict: Dict[str, Any] = yaml.load(config_defaults_str).data
# merge configs
self.config_dict = dict_merge(config_defaults_dict, config_dict)
def test_valid_config(self):
config_yaml = yaml.as_document(self.config_dict)
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_duplicated_files(self):
for input_type in PipelineConfig._REQUIRED_INPUT_TYPES:
with self.subTest(input_type=input_type):
# duplicate the first input file
input_file_list = self.config_dict["inputs"][input_type]
input_file_list[1] = input_file_list[0]
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_nr_files_differs(self):
for input_type in PipelineConfig._REQUIRED_INPUT_TYPES:
with self.subTest(input_type=input_type):
# add a new unique input file
input_file_list = self.config_dict["inputs"][input_type]
input_file_list.append(input_file_list[0].replace("01", "0x"))
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_source_finder_value(self):
self.config_dict["measurements"]["source_finder"] = "foo"
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_association_method_value(self):
# test valid options
for method in PipelineConfig._VALID_ASSOC_METHODS:
with self.subTest(method=method):
self.config_dict["source_association"]["method"] = method
config_yaml = yaml.as_document(self.config_dict)
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
# test invalid option
method = "foo"
with self.subTest(method=method):
self.config_dict["source_association"]["method"] = method
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_background_optional(self):
"""Background inputs are optional if source monitoring is false."""
self.config_dict["source_monitoring"]["monitor"] = False
del self.config_dict["inputs"]["background"]
config_yaml = yaml.as_document(self.config_dict)
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_background_for_source_monitoring(self):
"""Background input images must be provided if source monitoring is true."""
self.config_dict["source_monitoring"]["monitor"] = True
del self.config_dict["inputs"]["background"]
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_maximum_input_images(self):
max_files = settings.MAX_PIPERUN_IMAGES
user = AnonymousUser()
n_files_to_add = max_files - len(self.config_dict["inputs"]["image"]) + 1
for input_type in PipelineConfig._REQUIRED_INPUT_TYPES:
input_file_list = self.config_dict["inputs"][input_type]
input_file_list.extend([str(uuid.uuid4()) for _ in range(n_files_to_add)])
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate(user=user) # type: ignore[arg-type]
def test_minimum_two_inputs(self):
for input_type in PipelineConfig._REQUIRED_INPUT_TYPES:
self.config_dict["inputs"][input_type] = [
self.config_dict["inputs"][input_type][0],
]
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_input_files_exist(self):
# add a fake input file to each input list
for input_type in PipelineConfig._REQUIRED_INPUT_TYPES:
input_file_list = self.config_dict["inputs"][input_type]
input_file_list.append(input_file_list[0].replace("01", "0x"))
config_yaml = yaml.as_document(self.config_dict)
with self.assertRaises(PipelineConfigError):
pipeline_config = PipelineConfig(config_yaml)
pipeline_config.validate()
def test_input_glob(self):
"""Test simple glob expressions, one for each input"""
config_yaml_original = yaml.as_document(self.config_dict)
pipeline_config_original = PipelineConfig(config_yaml_original)
pipeline_config_original.validate()
# replace the inputs with glob expressions
self.config_dict["inputs"]["image"] = {
"glob": "vast_pipeline/tests/data/epoch??.fits"
}
self.config_dict["inputs"]["selavy"] = {
"glob": "vast_pipeline/tests/data/epoch??.selavy.components.txt"
}
self.config_dict["inputs"]["noise"] = {
"glob": "vast_pipeline/tests/data/epoch??.noiseMap.fits"
}
self.config_dict["inputs"]["background"] = {
"glob": "vast_pipeline/tests/data/epoch??.meanMap.fits"
}
config_yaml_globs = yaml.as_document(self.config_dict)
pipeline_config_globs = PipelineConfig(config_yaml_globs)
pipeline_config_globs.validate()
# after validation, the glob expressions should be resolved and be identical to
# the original config
self.assertDictEqual(
pipeline_config_original._yaml.data, pipeline_config_globs._yaml.data
)
def test_input_multiple_globs(self):
"""Test multiple consecutive glob expressions"""
config_yaml_original = yaml.as_document(self.config_dict)
pipeline_config_original = PipelineConfig(config_yaml_original)
pipeline_config_original.validate()
# replace the inputs with glob expressions
self.config_dict["inputs"]["image"] = {
"glob": [
"vast_pipeline/tests/data/epoch0[12].fits",
"vast_pipeline/tests/data/epoch0[34].fits",
],
}
self.config_dict["inputs"]["selavy"] = {
"glob": [
"vast_pipeline/tests/data/epoch0[12].selavy.components.txt",
"vast_pipeline/tests/data/epoch0[34].selavy.components.txt",
],
}
self.config_dict["inputs"]["noise"] = {
"glob": [
"vast_pipeline/tests/data/epoch0[12].noiseMap.fits",
"vast_pipeline/tests/data/epoch0[34].noiseMap.fits",
],
}
self.config_dict["inputs"]["background"] = {
"glob": [
"vast_pipeline/tests/data/epoch0[12].meanMap.fits",
"vast_pipeline/tests/data/epoch0[34].meanMap.fits",
],
}
config_yaml_globs = yaml.as_document(self.config_dict)
pipeline_config_globs = PipelineConfig(config_yaml_globs)
pipeline_config_globs.validate()
# after validation, the glob expressions should be resolved and be identical to
# the original config
self.assertDictEqual(
pipeline_config_original._yaml.data, pipeline_config_globs._yaml.data
)
def test_input_globs_epoch_mode(self):
"""Test glob expressions with user-defined epochs."""
# modify the config to define arbitrary epochs, i.e. "epoch-mode"
self.config_dict["inputs"]["image"] = {
"A": [
"vast_pipeline/tests/data/epoch01.fits",
"vast_pipeline/tests/data/epoch02.fits",
],
"B": [
"vast_pipeline/tests/data/epoch03.fits",
"vast_pipeline/tests/data/epoch04.fits",
],
}
self.config_dict["inputs"]["selavy"] = {
"A": [
"vast_pipeline/tests/data/epoch01.selavy.components.txt",
"vast_pipeline/tests/data/epoch02.selavy.components.txt",
],
"B": [
"vast_pipeline/tests/data/epoch03.selavy.components.txt",
"vast_pipeline/tests/data/epoch04.selavy.components.txt",
],
}
self.config_dict["inputs"]["noise"] = {
"A": [
"vast_pipeline/tests/data/epoch01.noiseMap.fits",
"vast_pipeline/tests/data/epoch02.noiseMap.fits",
],
"B": [
"vast_pipeline/tests/data/epoch03.noiseMap.fits",
"vast_pipeline/tests/data/epoch04.noiseMap.fits",
],
}
self.config_dict["inputs"]["background"] = {
"A": [
"vast_pipeline/tests/data/epoch01.meanMap.fits",
"vast_pipeline/tests/data/epoch02.meanMap.fits",
],
"B": [
"vast_pipeline/tests/data/epoch03.meanMap.fits",
"vast_pipeline/tests/data/epoch04.meanMap.fits",
],
}
config_yaml_original = yaml.as_document(self.config_dict)
pipeline_config_original = PipelineConfig(config_yaml_original)
pipeline_config_original.validate()
# replace the inputs with glob expressions
self.config_dict["inputs"]["image"] = {
"A": {
"glob": "vast_pipeline/tests/data/epoch0[12].fits",
},
"B": {
"glob": "vast_pipeline/tests/data/epoch0[34].fits",
},
}
self.config_dict["inputs"]["selavy"] = {
"A": {
"glob": "vast_pipeline/tests/data/epoch0[12].selavy.components.txt",
},
"B": {
"glob": "vast_pipeline/tests/data/epoch0[34].selavy.components.txt",
},
}
self.config_dict["inputs"]["noise"] = {
"A": {
"glob": "vast_pipeline/tests/data/epoch0[12].noiseMap.fits",
},
"B": {
"glob": "vast_pipeline/tests/data/epoch0[34].noiseMap.fits",
},
}
self.config_dict["inputs"]["background"] = {
"A": {
"glob": "vast_pipeline/tests/data/epoch0[12].meanMap.fits",
},
"B": {
"glob": "vast_pipeline/tests/data/epoch0[34].meanMap.fits",
},
}
config_yaml_globs = yaml.as_document(self.config_dict)
pipeline_config_globs = PipelineConfig(config_yaml_globs)
pipeline_config_globs.validate()
# after validation, the glob expressions should be resolved and be identical to
# the original config
self.assertDictEqual(
pipeline_config_original._yaml.data, pipeline_config_globs._yaml.data
)