1
|
|
|
#!/usr/bin/env python3 |
2
|
|
|
# -*- coding: utf-8 -*- |
3
|
|
|
""" |
4
|
|
|
Created on Fri Feb 22 15:49:18 2019 |
5
|
|
|
|
6
|
|
|
@author: Paolo Cozzi <[email protected]> |
7
|
|
|
""" |
8
|
|
|
|
9
|
|
|
import os |
10
|
|
|
import logging |
11
|
|
|
|
12
|
|
|
from unittest.mock import patch |
13
|
|
|
from collections import namedtuple |
14
|
|
|
|
15
|
|
|
from django.test import TestCase |
16
|
|
|
|
17
|
|
|
from common.tests import WebSocketMixin |
18
|
|
|
from image_app.models import ( |
19
|
|
|
DictSex, DictBreed, Name, Animal, |
20
|
|
|
Sample, DictUberon, DictCountry) |
21
|
|
|
from image_app.tests.mixins import ( |
22
|
|
|
DataSourceMixinTestCase, FileReaderMixinTestCase) |
23
|
|
|
|
24
|
|
|
from ..helpers import ( |
25
|
|
|
logger, CRBAnimReader, upload_crbanim, fill_uid_breed, fill_uid_names, |
26
|
|
|
fill_uid_animal, fill_uid_sample, find_storage_type, sanitize_url) |
27
|
|
|
from .common import BaseTestCase |
28
|
|
|
|
29
|
|
|
|
30
|
|
|
class CRBAnimMixin(DataSourceMixinTestCase, WebSocketMixin): |
31
|
|
|
"""Common test for CRBanim classes""" |
32
|
|
|
|
33
|
|
|
# define the method to upload data from. Since the function is now inside |
34
|
|
|
# a class it becomes a method, specifically a bound method and is supposed |
35
|
|
|
# to receive the self attribute by default. If we don't want to get the |
36
|
|
|
# self attribute, we have to declare function as a staticmetho |
37
|
|
|
# https://stackoverflow.com/a/35322635/4385116 |
38
|
|
|
upload_method = staticmethod(upload_crbanim) |
39
|
|
|
|
40
|
|
|
def test_upload_crbanim(self): |
41
|
|
|
"""Testing uploading and importing data from crbanim to UID""" |
42
|
|
|
|
43
|
|
|
# test data loaded |
44
|
|
|
message = "CRBAnim import completed for submission" |
45
|
|
|
self.upload_datasource(message) |
46
|
|
|
|
47
|
|
|
# check async message called |
48
|
|
|
notification_message = ( |
49
|
|
|
'CRBAnim import completed for submission: 1') |
50
|
|
|
validation_message = { |
51
|
|
|
'animals': 1, 'samples': 2, |
52
|
|
|
'animal_unkn': 1, 'sample_unkn': 2, |
53
|
|
|
'animal_issues': 0, 'sample_issues': 0} |
54
|
|
|
|
55
|
|
|
# check async message called using WebSocketMixin.check_message |
56
|
|
|
self.check_message('Loaded', notification_message, validation_message) |
57
|
|
|
|
58
|
|
|
def check_errors(self, my_check, message, notification_message): |
59
|
|
|
"""Common stuff for error in crbanim loading""" |
60
|
|
|
|
61
|
|
|
super().check_errors(my_check, message) |
62
|
|
|
|
63
|
|
|
# check async message called using WebSocketMixin.check_message |
64
|
|
|
self.check_message('Error', notification_message) |
65
|
|
|
|
66
|
|
|
|
67
|
|
|
class CRBAnimReaderTestCase( |
68
|
|
|
FileReaderMixinTestCase, DataSourceMixinTestCase, BaseTestCase, |
69
|
|
|
TestCase): |
70
|
|
|
def setUp(self): |
71
|
|
|
# calling my base class setup |
72
|
|
|
super().setUp() |
73
|
|
|
|
74
|
|
|
# crate a CRBAnimReade object |
75
|
|
|
self.reader = CRBAnimReader() |
76
|
|
|
|
77
|
|
|
# get filenames for DataSourceMixinTestCase.dst_path |
78
|
|
|
self.reader.read_file(self.dst_path) |
79
|
|
|
|
80
|
|
|
def test_has_columns(self): |
81
|
|
|
"""Test if class has columns""" |
82
|
|
|
|
83
|
|
|
reference = [ |
84
|
|
|
'BRC_identifier', |
85
|
|
|
'BRC_name', |
86
|
|
|
'associated_research_project_name', |
87
|
|
|
'BRC_responsible_last_name', |
88
|
|
|
'BRC_responsible_first_name', |
89
|
|
|
'BRC_contact_email', |
90
|
|
|
'organization_name', |
91
|
|
|
'organisation_adress', |
92
|
|
|
'organization_url', |
93
|
|
|
'organization_country', |
94
|
|
|
'BRC_address', |
95
|
|
|
'BRC_url', |
96
|
|
|
'BRC_country', |
97
|
|
|
'sample_identifier', |
98
|
|
|
'EBI_Biosample_identifier', |
99
|
|
|
'sample_availability', |
100
|
|
|
'sample_bibliographic_references', |
101
|
|
|
'animal_ID', |
102
|
|
|
'sex', |
103
|
|
|
'species_latin_name', |
104
|
|
|
'NCBI_taxo_id', |
105
|
|
|
'breed_name', |
106
|
|
|
'country_of_origin', |
107
|
|
|
'sampling_protocol_url', |
108
|
|
|
'sampling_date', |
109
|
|
|
'sample_type_name', |
110
|
|
|
'sample_type_identifier', |
111
|
|
|
'sample_type_ontology', |
112
|
|
|
'body_part_name', |
113
|
|
|
'body_part_identifier', |
114
|
|
|
'body_part_ontology', |
115
|
|
|
'animal_birth_date', |
116
|
|
|
'sample_storage_temperature', |
117
|
|
|
'sample_container_type', |
118
|
|
|
'sample_fixer_nature'] |
119
|
|
|
|
120
|
|
|
self.assertEqual(reference, self.reader.header) |
121
|
|
|
|
122
|
|
|
def test_debug_row(self): |
123
|
|
|
"""Assert a function is callable""" |
124
|
|
|
|
125
|
|
|
self.reader.print_line(0) |
126
|
|
|
self.assertLogs(logger=logger, level=logging.DEBUG) |
127
|
|
|
|
128
|
|
|
def test_filter_by_column(self): |
129
|
|
|
"""Filter records by column value""" |
130
|
|
|
|
131
|
|
|
# filter out biosample records from mydata |
132
|
|
|
data = self.reader.filter_by_column_values( |
133
|
|
|
"EBI_Biosample_identifier", |
134
|
|
|
[None]) |
135
|
|
|
data = list(data) |
136
|
|
|
|
137
|
|
|
self.assertEqual(len(data), 2) |
138
|
|
|
|
139
|
|
|
def test_filter_by_column_case(self): |
140
|
|
|
"""Filter records by column value case insensitive""" |
141
|
|
|
|
142
|
|
|
# filter out biosample records from mydata |
143
|
|
|
# record have capital letter. No record after filtering case sensitive |
144
|
|
|
data = self.reader.filter_by_column_values( |
145
|
|
|
"sex", |
146
|
|
|
['female'], |
147
|
|
|
ignorecase=False) |
148
|
|
|
data = list(data) |
149
|
|
|
|
150
|
|
|
self.assertEqual(len(data), 0) |
151
|
|
|
|
152
|
|
|
# filtering female case insensitive |
153
|
|
|
data = self.reader.filter_by_column_values( |
154
|
|
|
"sex", |
155
|
|
|
['female'], |
156
|
|
|
ignorecase=True) |
157
|
|
|
data = list(data) |
158
|
|
|
|
159
|
|
|
self.assertEqual(len(data), 1) |
160
|
|
|
|
161
|
|
|
# No record after filtering foo case insensitive |
162
|
|
|
data = self.reader.filter_by_column_values( |
163
|
|
|
"sex", |
164
|
|
|
['foo'], |
165
|
|
|
ignorecase=True) |
166
|
|
|
data = list(data) |
167
|
|
|
|
168
|
|
|
self.assertEqual(len(data), 0) |
169
|
|
|
|
170
|
|
|
def test_is_valid(self): |
171
|
|
|
"""Test recognizing a good CRBanim file""" |
172
|
|
|
|
173
|
|
|
with open(self.dst_path) as handle: |
174
|
|
|
chunk = handle.read(2048) |
175
|
|
|
|
176
|
|
|
check, not_found = self.reader.is_valid(chunk) |
177
|
|
|
|
178
|
|
|
# a good crbanim file returns True and an empty list |
179
|
|
|
self.assertTrue(check) |
180
|
|
|
self.assertEqual(not_found, []) |
181
|
|
|
|
182
|
|
|
# assert a not good file. self.base_dir comes from |
183
|
|
|
# common.tests.mixins.DataSourceMixinTestCase |
184
|
|
|
filename = os.path.join( |
185
|
|
|
self.base_dir, |
186
|
|
|
"Mapping_rules_CRB-Anim_InjectTool_v1.csv") |
187
|
|
|
|
188
|
|
|
with open(filename) as handle: |
189
|
|
|
chunk = handle.read(2048) |
190
|
|
|
|
191
|
|
|
check, not_found = self.reader.is_valid(chunk) |
192
|
|
|
|
193
|
|
|
# a invalid crbanim file returns False and a list |
194
|
|
|
self.assertFalse(check) |
195
|
|
|
self.assertGreater(len(not_found), 0) |
196
|
|
|
|
197
|
|
|
|
198
|
|
|
class ProcessRecordTestCase(DataSourceMixinTestCase, BaseTestCase, TestCase): |
199
|
|
|
"""A class to test function which process record""" |
200
|
|
|
|
201
|
|
|
def setUp(self): |
202
|
|
|
# calling my base class setup |
203
|
|
|
super().setUp() |
204
|
|
|
|
205
|
|
|
# crate a CRBAnimReade object |
206
|
|
|
self.reader = CRBAnimReader() |
207
|
|
|
|
208
|
|
|
# get filenames for DataSourceMixinTestCase.dst_path |
209
|
|
|
self.reader.read_file(self.dst_path) |
210
|
|
|
|
211
|
|
|
# filter out biosample records from mydata |
212
|
|
|
data = self.reader.filter_by_column_values( |
213
|
|
|
"EBI_Biosample_identifier", |
214
|
|
|
[None]) |
215
|
|
|
self.data = list(data) |
216
|
|
|
|
217
|
|
|
# track the sample record for test |
218
|
|
|
self.record = self.data[0] |
219
|
|
|
|
220
|
|
|
# set a country |
221
|
|
|
self.country = DictCountry.objects.get(label="United Kingdom") |
222
|
|
|
|
223
|
|
|
# fill object to test inserts. Fill breed |
224
|
|
|
self.breed = fill_uid_breed(self.record, self.country) |
225
|
|
|
|
226
|
|
|
# fill names |
227
|
|
|
self.animal_name, self.sample_name = fill_uid_names( |
228
|
|
|
self.record, self.submission) |
229
|
|
|
|
230
|
|
|
# filling animal and samples |
231
|
|
|
self.animal = fill_uid_animal( |
232
|
|
|
self.record, |
233
|
|
|
self.animal_name, |
234
|
|
|
self.breed, |
235
|
|
|
self.submission, |
236
|
|
|
{}) |
237
|
|
|
|
238
|
|
|
# testing samples |
239
|
|
|
self.sample = fill_uid_sample( |
240
|
|
|
self.record, |
241
|
|
|
self.sample_name, |
242
|
|
|
self.animal, |
243
|
|
|
self.submission) |
244
|
|
|
|
245
|
|
|
def test_fill_uid_breed(self): |
246
|
|
|
"""testing fill_uid_breed""" |
247
|
|
|
|
248
|
|
|
# testing output |
249
|
|
|
self.assertIsInstance(self.breed, DictBreed) |
250
|
|
|
self.assertEqual(self.breed.supplied_breed, self.record.breed_name) |
251
|
|
|
self.assertEqual( |
252
|
|
|
self.breed.specie.label, self.record.species_latin_name) |
253
|
|
|
|
254
|
|
|
def test_fill_uid_names(self): |
255
|
|
|
# testing output |
256
|
|
|
self.assertIsInstance(self.animal_name, Name) |
257
|
|
|
self.assertIsInstance(self.sample_name, Name) |
258
|
|
|
|
259
|
|
|
self.assertEqual(self.animal_name.name, self.record.animal_ID) |
260
|
|
|
self.assertEqual(self.sample_name.name, self.record.sample_identifier) |
261
|
|
|
|
262
|
|
|
def test_fill_uid_animals(self): |
263
|
|
|
# testing animal |
264
|
|
|
self.assertIsInstance(self.animal, Animal) |
265
|
|
|
|
266
|
|
|
# testing animal attributes |
267
|
|
|
sex = DictSex.objects.get(label__iexact=self.record.sex) |
268
|
|
|
self.assertEqual(self.animal.sex, sex) |
269
|
|
|
|
270
|
|
|
def test_fill_uid_samples(self): |
271
|
|
|
# testing sample |
272
|
|
|
self.assertIsInstance(self.sample, Sample) |
273
|
|
|
|
274
|
|
|
# testing sample attributes |
275
|
|
|
organism_part = DictUberon.objects.get( |
276
|
|
|
label__iexact="bone marrow") |
277
|
|
|
self.assertEqual(self.sample.organism_part, organism_part) |
278
|
|
|
|
279
|
|
|
def test_organism_part(self): |
280
|
|
|
"""Check that an 'unknown' organims_part generate a DictUberon |
281
|
|
|
relying on sample_type_name (see crbanim_test_data.csv file)""" |
282
|
|
|
|
283
|
|
|
# get a new record |
284
|
|
|
record = self.data[1] |
285
|
|
|
|
286
|
|
|
# fill breeds |
287
|
|
|
breed = fill_uid_breed(record, self.country) |
288
|
|
|
|
289
|
|
|
# creating name |
290
|
|
|
animal_name, sample_name = fill_uid_names( |
291
|
|
|
record, self.submission) |
292
|
|
|
|
293
|
|
|
# filling animal and samples |
294
|
|
|
animal = fill_uid_animal( |
295
|
|
|
record, |
296
|
|
|
animal_name, |
297
|
|
|
breed, |
298
|
|
|
self.submission, |
299
|
|
|
{}) |
300
|
|
|
|
301
|
|
|
# testing samples |
302
|
|
|
sample = fill_uid_sample( |
303
|
|
|
record, |
304
|
|
|
sample_name, |
305
|
|
|
animal, |
306
|
|
|
self.submission) |
307
|
|
|
|
308
|
|
|
# testing sample attributes |
309
|
|
|
organism_part = DictUberon.objects.get( |
310
|
|
|
label__iexact="uterus") |
311
|
|
|
self.assertEqual(sample.organism_part, organism_part) |
312
|
|
|
|
313
|
|
|
def test_find_storage_type(self): |
314
|
|
|
"""Asserting storage type conversion""" |
315
|
|
|
|
316
|
|
|
result = find_storage_type(self.record) |
317
|
|
|
self.assertEqual(result, 2) |
318
|
|
|
|
319
|
|
|
# create a fare record object |
320
|
|
|
Data = namedtuple("Data", ["sample_storage_temperature"]) |
321
|
|
|
record = Data._make(["meow"]) |
322
|
|
|
|
323
|
|
|
result = find_storage_type(record) |
324
|
|
|
self.assertIsNone(result) |
325
|
|
|
|
326
|
|
|
|
327
|
|
|
class UploadCRBAnimTestCase(CRBAnimMixin, BaseTestCase, TestCase): |
328
|
|
|
|
329
|
|
|
@patch("crbanim.helpers.CRBAnimReader.check_species", |
330
|
|
|
return_value=[False, 'Rainbow trout']) |
331
|
|
|
def test_upload_crbanim_errors_with_species(self, my_check): |
332
|
|
|
"""Testing importing with data into UID with errors""" |
333
|
|
|
|
334
|
|
|
message = "Some species are not loaded in UID database" |
335
|
|
|
notification_message = ( |
336
|
|
|
'Error in importing data: Some species ' |
337
|
|
|
'are not loaded in UID database: Rainbow ' |
338
|
|
|
'trout') |
339
|
|
|
|
340
|
|
|
# check crbanim import fails |
341
|
|
|
self.check_errors(my_check, message, notification_message) |
342
|
|
|
|
343
|
|
|
@patch("crbanim.helpers.CRBAnimReader.check_sex", |
344
|
|
|
return_value=[False, 'unknown']) |
345
|
|
|
def test_upload_crbanim_errors_with_sex(self, my_check): |
346
|
|
|
"""Testing importing with data into UID with errors""" |
347
|
|
|
|
348
|
|
|
message = "Not all Sex terms are loaded into database" |
349
|
|
|
notification_message = ( |
350
|
|
|
'Error in importing data: Not all Sex ' |
351
|
|
|
'terms are loaded into database: check ' |
352
|
|
|
'for unknown in your dataset') |
353
|
|
|
|
354
|
|
|
# check crbanim import fails |
355
|
|
|
self.check_errors(my_check, message, notification_message) |
356
|
|
|
|
357
|
|
|
|
358
|
|
|
class ReloadCRBAnimTestCase(CRBAnimMixin, BaseTestCase, TestCase): |
359
|
|
|
|
360
|
|
|
"""Simulate a crbanim reload case. Load data as in |
361
|
|
|
UploadCRBAnimTestCase, then call test which reload the same data""" |
362
|
|
|
|
363
|
|
|
# override used fixtures |
364
|
|
|
fixtures = [ |
365
|
|
|
'crbanim/auth', |
366
|
|
|
'crbanim/dictspecie', |
367
|
|
|
'crbanim/image_app', |
368
|
|
|
'crbanim/submission', |
369
|
|
|
'language/speciesynonym' |
370
|
|
|
] |
371
|
|
|
|
372
|
|
|
|
373
|
|
|
class SanitizeAccessionTest(TestCase): |
374
|
|
|
|
375
|
|
|
def setUp(self): |
376
|
|
|
self.queries = [ |
377
|
|
|
( |
378
|
|
|
("https://crb-anim.fr/access-to-collection/#/simplesearch?" |
379
|
|
|
"SAMPLEIDENTIFIER=Ovar-Mér-3796-1"), |
380
|
|
|
("https://crb-anim.fr/access-to-collection/#/simplesearch?" |
381
|
|
|
"SAMPLEIDENTIFIER=Ovar-M%C3%A9r-3796-1") |
382
|
|
|
), |
383
|
|
|
] |
384
|
|
|
|
385
|
|
|
def test_sanitize_accession(self): |
386
|
|
|
for query in self.queries: |
387
|
|
|
url, reference = query |
388
|
|
|
test = sanitize_url(url) |
389
|
|
|
self.assertEqual(reference, test) |
390
|
|
|
|