forked from galaxyproject/galaxy
/
populators.py
823 lines (656 loc) · 31.9 KB
/
populators.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
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
import contextlib
import json
import os
import time
from functools import wraps
from operator import itemgetter
import requests
from pkg_resources import resource_string
from six import StringIO
from . import api_asserts
from .workflows_format_2 import (
convert_and_import_workflow,
ImporterGalaxyInterface,
)
# Simple workflow that takes an input and call cat wrapper on it.
workflow_str = resource_string(__name__, "data/test_workflow_1.ga")
# Simple workflow that takes an input and filters with random lines twice in a
# row - first grabbing 8 lines at random and then 6.
workflow_random_x2_str = resource_string(__name__, "data/test_workflow_2.ga")
DEFAULT_TIMEOUT = 60 # Secs to wait for state to turn ok
SKIP_FLAKEY_TESTS_ON_ERROR = os.environ.get("GALAXY_TEST_SKIP_FLAKEY_TESTS_ON_ERROR", None)
def flakey(method):
@wraps(method)
def wrapped_method(test_case, *args, **kwargs):
try:
method(test_case, *args, **kwargs)
except Exception:
if SKIP_FLAKEY_TESTS_ON_ERROR:
from nose.plugins.skip import SkipTest
raise SkipTest()
else:
raise
return wrapped_method
def skip_without_tool(tool_id):
"""Decorate an API test method as requiring a specific tool.
Have test framework skip the test case is the tool is unavailable.
"""
def method_wrapper(method):
def get_tool_ids(api_test_case):
index = api_test_case.galaxy_interactor.get("tools", data=dict(in_panel=False))
tools = index.json()
# In panels by default, so flatten out sections...
tool_ids = [itemgetter("id")(_) for _ in tools]
return tool_ids
@wraps(method)
def wrapped_method(api_test_case, *args, **kwargs):
_raise_skip_if(tool_id not in get_tool_ids(api_test_case))
return method(api_test_case, *args, **kwargs)
return wrapped_method
return method_wrapper
def skip_without_datatype(extension):
"""Decorate an API test method as requiring a specific datatype.
Have test framework skip the test case is the tool is unavailable.
"""
def has_datatype(api_test_case):
index_response = api_test_case.galaxy_interactor.get("datatypes")
assert index_response.status_code == 200, "Failed to fetch datatypes for target Galaxy."
datatypes = index_response.json()
assert isinstance(datatypes, list)
return extension in datatypes
def method_wrapper(method):
@wraps(method)
def wrapped_method(api_test_case, *args, **kwargs):
_raise_skip_if(not has_datatype(api_test_case))
method(api_test_case, *args, **kwargs)
return wrapped_method
return method_wrapper
def summarize_instance_history_on_error(method):
@wraps(method)
def wrapped_method(api_test_case, *args, **kwds):
try:
method(api_test_case, *args, **kwds)
except Exception:
api_test_case.dataset_populator._summarize_history(api_test_case.history_id)
raise
return wrapped_method
def _raise_skip_if(check):
if check:
from nose.plugins.skip import SkipTest
raise SkipTest()
# Deprecated mixin, use dataset populator instead.
# TODO: Rework existing tests to target DatasetPopulator in a setup method instead.
class TestsDatasets:
def _new_dataset(self, history_id, content='TestData123', **kwds):
return DatasetPopulator(self.galaxy_interactor).new_dataset(history_id, content=content, **kwds)
def _wait_for_history(self, history_id, assert_ok=False):
return DatasetPopulator(self.galaxy_interactor).wait_for_history(history_id, assert_ok=assert_ok)
def _new_history(self, **kwds):
return DatasetPopulator(self.galaxy_interactor).new_history(**kwds)
def _upload_payload(self, history_id, content, **kwds):
return DatasetPopulator(self.galaxy_interactor).upload_payload(history_id, content, **kwds)
def _run_tool_payload(self, tool_id, inputs, history_id, **kwds):
return DatasetPopulator(self.galaxy_interactor).run_tool_payload(tool_id, inputs, history_id, **kwds)
class BaseDatasetPopulator(object):
""" Abstract description of API operations optimized for testing
Galaxy - implementations must implement _get and _post.
"""
def new_dataset(self, history_id, content=None, wait=False, **kwds):
run_response = self.new_dataset_request(history_id, content=content, wait=wait, **kwds)
return run_response.json()["outputs"][0]
def new_dataset_request(self, history_id, content=None, wait=False, **kwds):
if content is None and "ftp_files" not in kwds:
content = "TestData123"
payload = self.upload_payload(history_id, content=content, **kwds)
run_response = self.tools_post(payload)
if wait:
self.wait_for_tool_run(history_id, run_response, assert_ok=kwds.get('assert_ok', True))
return run_response
def wait_for_tool_run(self, history_id, run_response, timeout=DEFAULT_TIMEOUT, assert_ok=True):
run = run_response.json()
assert run_response.status_code == 200, run
job = run["jobs"][0]
self.wait_for_job(job["id"], timeout=timeout)
self.wait_for_history(history_id, assert_ok=assert_ok, timeout=timeout)
return run_response
def wait_for_history(self, history_id, assert_ok=False, timeout=DEFAULT_TIMEOUT):
try:
return wait_on_state(lambda: self._get("histories/%s" % history_id), assert_ok=assert_ok, timeout=timeout)
except AssertionError:
self._summarize_history(history_id)
raise
def wait_for_history_jobs(self, history_id, assert_ok=False, timeout=DEFAULT_TIMEOUT):
query_params = {"history_id": history_id}
def has_active_jobs():
jobs_response = self._get("jobs", query_params)
assert jobs_response.status_code == 200
active_jobs = [j for j in jobs_response.json() if j["state"] in ["new", "upload", "waiting", "queued", "running"]]
if len(active_jobs) == 0:
return True
else:
return None
wait_on(has_active_jobs, "active jobs", timeout=timeout)
if assert_ok:
return self.wait_for_history(history_id, assert_ok=True, timeout=timeout)
def wait_for_job(self, job_id, assert_ok=False, timeout=DEFAULT_TIMEOUT):
return wait_on_state(lambda: self.get_job_details(job_id), assert_ok=assert_ok, timeout=timeout)
def get_job_details(self, job_id, full=False):
return self._get("jobs/%s?full=%s" % (job_id, full))
def cancel_job(self, job_id):
return self._delete("jobs/%s" % job_id)
def _summarize_history(self, history_id):
pass
@contextlib.contextmanager
def test_history(self, **kwds):
# TODO: In the future allow targetting a specfic history here
# and/or deleting everything in the resulting history when done.
# These would be cool options for remote Galaxy test execution.
try:
history_id = self.new_history()
yield history_id
except Exception:
self._summarize_history(history_id)
raise
def new_history(self, **kwds):
name = kwds.get("name", "API Test History")
create_history_response = self._post("histories", data=dict(name=name))
history_id = create_history_response.json()["id"]
return history_id
def upload_payload(self, history_id, content=None, **kwds):
name = kwds.get("name", "Test Dataset")
dbkey = kwds.get("dbkey", "?")
file_type = kwds.get("file_type", 'txt')
upload_params = {
'files_0|NAME': name,
'dbkey': dbkey,
'file_type': file_type,
}
if dbkey is None:
del upload_params["dbkey"]
if content is None:
upload_params["files_0|ftp_files"] = kwds.get("ftp_files")
elif hasattr(content, 'read'):
upload_params["files_0|file_data"] = content
else:
upload_params['files_0|url_paste'] = content
if "to_posix_lines" in kwds:
upload_params["files_0|to_posix_lines"] = kwds["to_posix_lines"]
if "space_to_tab" in kwds:
upload_params["files_0|space_to_tab"] = kwds["space_to_tab"]
if "auto_decompress" in kwds:
upload_params["files_0|auto_decompress"] = kwds["auto_decompress"]
upload_params.update(kwds.get("extra_inputs", {}))
return self.run_tool_payload(
tool_id='upload1',
inputs=upload_params,
history_id=history_id,
upload_type='upload_dataset'
)
def get_remote_files(self, target="ftp"):
return self._get("remote_files", data={"target": target}).json()
def run_tool_payload(self, tool_id, inputs, history_id, **kwds):
if "files_0|file_data" in inputs:
kwds["__files"] = {"files_0|file_data": inputs["files_0|file_data"]}
del inputs["files_0|file_data"]
return dict(
tool_id=tool_id,
inputs=json.dumps(inputs),
history_id=history_id,
**kwds
)
def run_tool(self, tool_id, inputs, history_id, assert_ok=True, **kwds):
payload = self.run_tool_payload(tool_id, inputs, history_id, **kwds)
tool_response = self.tools_post(payload)
if assert_ok:
api_asserts.assert_status_code_is(tool_response, 200)
return tool_response.json()
else:
return tool_response
def tools_post(self, payload):
tool_response = self._post("tools", data=payload)
return tool_response
def get_history_dataset_content(self, history_id, wait=True, filename=None, **kwds):
dataset_id = self.__history_content_id(history_id, wait=wait, **kwds)
data = {}
if filename:
data["filename"] = filename
display_response = self._get_contents_request(history_id, "/%s/display" % dataset_id, data=data)
assert display_response.status_code == 200, display_response.content
return display_response.content
def get_history_dataset_details(self, history_id, **kwds):
dataset_id = self.__history_content_id(history_id, **kwds)
details_response = self._get_contents_request(history_id, "/datasets/%s" % dataset_id)
assert details_response.status_code == 200
return details_response.json()
def get_history_collection_details(self, history_id, **kwds):
hdca_id = self.__history_content_id(history_id, **kwds)
details_response = self._get_contents_request(history_id, "/dataset_collections/%s" % hdca_id)
assert details_response.status_code == 200, details_response.content
return details_response.json()
def run_collection_creates_list(self, history_id, hdca_id):
inputs = {
"input1": {"src": "hdca", "id": hdca_id},
}
self.wait_for_history(history_id, assert_ok=True)
return self.run_tool("collection_creates_list", inputs, history_id)
def run_exit_code_from_file(self, history_id, hdca_id):
exit_code_inputs = {
"input": {'batch': True, 'values': [{"src": "hdca", "id": hdca_id}]},
}
response = self.run_tool("exit_code_from_file", exit_code_inputs, history_id, assert_ok=False).json()
self.wait_for_history(history_id, assert_ok=False)
return response
def __history_content_id(self, history_id, wait=True, **kwds):
if wait:
assert_ok = kwds.get("assert_ok", True)
self.wait_for_history(history_id, assert_ok=assert_ok)
# kwds should contain a 'dataset' object response, a 'dataset_id' or
# the last dataset in the history will be fetched.
if "dataset_id" in kwds:
history_content_id = kwds["dataset_id"]
elif "content_id" in kwds:
history_content_id = kwds["content_id"]
elif "dataset" in kwds:
history_content_id = kwds["dataset"]["id"]
else:
hid = kwds.get("hid", None) # If not hid, just grab last dataset
history_contents = self._get_contents_request(history_id).json()
if hid:
history_content_id = None
for history_item in history_contents:
if history_item["hid"] == hid:
history_content_id = history_item["id"]
if history_content_id is None:
raise Exception("Could not find content with HID [%s] in [%s]" % (hid, history_contents))
else:
# No hid specified - just grab most recent element.
history_content_id = history_contents[-1]["id"]
return history_content_id
def _get_contents_request(self, history_id, suffix="", data={}):
url = "histories/%s/contents" % history_id
if suffix:
url = "%s%s" % (url, suffix)
return self._get(url, data=data)
class DatasetPopulator(BaseDatasetPopulator):
def __init__(self, galaxy_interactor):
self.galaxy_interactor = galaxy_interactor
def _post(self, route, data={}, files=None):
files = data.get("__files", None)
if files is not None:
del data["__files"]
return self.galaxy_interactor.post(route, data, files=files)
def _get(self, route, data={}):
return self.galaxy_interactor.get(route, data=data)
def _delete(self, route, data={}):
return self.galaxy_interactor.delete(route, data=data)
def _summarize_history(self, history_id):
self.galaxy_interactor._summarize_history(history_id)
def wait_for_dataset(self, history_id, dataset_id, assert_ok=False, timeout=DEFAULT_TIMEOUT):
return wait_on_state(lambda: self._get("histories/%s/contents/%s" % (history_id, dataset_id)), assert_ok=assert_ok, timeout=timeout)
class BaseWorkflowPopulator(object):
def load_workflow(self, name, content=workflow_str, add_pja=False):
workflow = json.loads(content)
workflow["name"] = name
if add_pja:
tool_step = workflow["steps"]["2"]
tool_step["post_job_actions"]["RenameDatasetActionout_file1"] = dict(
action_type="RenameDatasetAction",
output_name="out_file1",
action_arguments=dict(newname="foo ${replaceme}"),
)
return workflow
def load_random_x2_workflow(self, name):
return self.load_workflow(name, content=workflow_random_x2_str)
def load_workflow_from_resource(self, name, filename=None):
if filename is None:
filename = "data/%s.ga" % name
content = resource_string(__name__, filename)
return self.load_workflow(name, content=content)
def simple_workflow(self, name, **create_kwds):
workflow = self.load_workflow(name)
return self.create_workflow(workflow, **create_kwds)
def create_workflow(self, workflow, **create_kwds):
upload_response = self.create_workflow_response(workflow, **create_kwds)
uploaded_workflow_id = upload_response.json()["id"]
return uploaded_workflow_id
def create_workflow_response(self, workflow, **create_kwds):
data = dict(
workflow=json.dumps(workflow),
**create_kwds
)
upload_response = self._post("workflows/upload", data=data)
return upload_response
def upload_yaml_workflow(self, has_yaml, **kwds):
workflow = convert_and_import_workflow(has_yaml, galaxy_interface=self, **kwds)
return workflow["id"]
def wait_for_invocation(self, workflow_id, invocation_id, timeout=DEFAULT_TIMEOUT):
url = "workflows/%s/usage/%s" % (workflow_id, invocation_id)
return wait_on_state(lambda: self._get(url), timeout=timeout)
def wait_for_workflow(self, workflow_id, invocation_id, history_id, assert_ok=True, timeout=DEFAULT_TIMEOUT):
""" Wait for a workflow invocation to completely schedule and then history
to be complete. """
self.wait_for_invocation(workflow_id, invocation_id, timeout=timeout)
self.dataset_populator.wait_for_history_jobs(history_id, assert_ok=assert_ok, timeout=timeout)
def invoke_workflow(self, history_id, workflow_id, inputs={}, request={}, assert_ok=True):
request["history"] = "hist_id=%s" % history_id,
if inputs:
request["inputs"] = json.dumps(inputs)
request["inputs_by"] = 'step_index'
url = "workflows/%s/usage" % (workflow_id)
invocation_response = self._post(url, data=request)
if assert_ok:
api_asserts.assert_status_code_is(invocation_response, 200)
invocation_id = invocation_response.json()["id"]
return invocation_id
else:
return invocation_response
class WorkflowPopulator(BaseWorkflowPopulator, ImporterGalaxyInterface):
def __init__(self, galaxy_interactor):
self.galaxy_interactor = galaxy_interactor
self.dataset_populator = DatasetPopulator(galaxy_interactor)
def _post(self, route, data={}):
return self.galaxy_interactor.post(route, data)
def _get(self, route, data={}):
return self.galaxy_interactor.get(route, data=data)
# Required for ImporterGalaxyInterface interface - so we can recurisvely import
# nested workflows.
def import_workflow(self, workflow, **kwds):
workflow_str = json.dumps(workflow, indent=4)
data = {
'workflow': workflow_str,
}
data.update(**kwds)
upload_response = self._post("workflows", data=data)
assert upload_response.status_code == 200, upload_response
return upload_response.json()
class LibraryPopulator(object):
def __init__(self, galaxy_interactor):
self.galaxy_interactor = galaxy_interactor
def new_private_library(self, name):
library = self.new_library(name)
library_id = library["id"]
role_id = self.user_private_role_id()
self.set_permissions(library_id, role_id)
return library
def new_library(self, name):
data = dict(name=name)
create_response = self.galaxy_interactor.post("libraries", data=data, admin=True)
return create_response.json()
def set_permissions(self, library_id, role_id=None):
if role_id:
perm_list = json.dumps(role_id)
else:
perm_list = json.dumps([])
permissions = dict(
LIBRARY_ACCESS_in=perm_list,
LIBRARY_MODIFY_in=perm_list,
LIBRARY_ADD_in=perm_list,
LIBRARY_MANAGE_in=perm_list,
)
self.galaxy_interactor.post("libraries/%s/permissions" % library_id, data=permissions, admin=True)
def user_email(self):
users_response = self.galaxy_interactor.get("users")
users = users_response.json()
assert len(users) == 1
return users[0]["email"]
def user_private_role_id(self):
user_email = self.user_email()
roles_response = self.galaxy_interactor.get("roles", admin=True)
users_roles = [r for r in roles_response.json() if r["name"] == user_email]
assert len(users_roles) == 1
return users_roles[0]["id"]
def create_dataset_request(self, library, **kwds):
upload_option = kwds.get("upload_option", "upload_file")
create_data = {
"folder_id": kwds.get("folder_id", library["root_folder_id"]),
"create_type": "file",
"files_0|NAME": kwds.get("name", "NewFile"),
"upload_option": upload_option,
"file_type": kwds.get("file_type", "auto"),
"db_key": kwds.get("db_key", "?"),
}
if upload_option == "upload_file":
files = {
"files_0|file_data": kwds.get("file", StringIO(kwds.get("contents", "TestData"))),
}
elif upload_option == "upload_paths":
create_data["filesystem_paths"] = kwds["paths"]
files = {}
elif upload_option == "upload_directory":
create_data["server_dir"] = kwds["server_dir"]
files = {}
return create_data, files
def new_library_dataset(self, name, **create_dataset_kwds):
library = self.new_private_library(name)
payload, files = self.create_dataset_request(library, **create_dataset_kwds)
dataset = self.raw_library_contents_create(library["id"], payload, files=files).json()[0]
def show():
return self.galaxy_interactor.get("libraries/%s/contents/%s" % (library["id"], dataset["id"]))
wait_on_state(show, timeout=DEFAULT_TIMEOUT)
return show().json()
def raw_library_contents_create(self, library_id, payload, files={}):
url_rel = "libraries/%s/contents" % library_id
return self.galaxy_interactor.post(url_rel, payload, files=files)
def show_ldda(self, library_id, library_dataset_id):
return self.galaxy_interactor.get("libraries/%s/contents/%s" % (library_id, library_dataset_id))
def new_library_dataset_in_private_library(self, library_name="private_dataset", wait=True):
library = self.new_private_library(library_name)
payload, files = self.create_dataset_request(library, file_type="txt", contents="create_test")
create_response = self.galaxy_interactor.post("libraries/%s/contents" % library["id"], payload, files=files)
api_asserts.assert_status_code_is(create_response, 200)
library_datasets = create_response.json()
assert len(library_datasets) == 1
library_dataset = library_datasets[0]
if wait:
def show():
return self.show_ldda(library["id"], library_dataset["id"])
wait_on_state(show, assert_ok=True)
library_dataset = show().json()
return library, library_dataset
class BaseDatasetCollectionPopulator(object):
def create_list_from_pairs(self, history_id, pairs, name="Dataset Collection from pairs"):
return self.create_nested_collection(history_id=history_id,
collection=pairs,
collection_type='list:paired',
name=name)
def nested_collection_identifiers(self, history_id, collection_type):
rank_types = list(reversed(collection_type.split(":")))
assert len(rank_types) > 0
rank_type_0 = rank_types[0]
if rank_type_0 == "list":
identifiers = self.list_identifiers(history_id)
else:
identifiers = self.pair_identifiers(history_id)
nested_collection_type = rank_type_0
for i, rank_type in enumerate(reversed(rank_types[1:])):
name = "test_level_%d" % (i + 1) if rank_type == "list" else "paired"
identifiers = [dict(
src="new_collection",
name=name,
collection_type=nested_collection_type,
element_identifiers=identifiers,
)]
nested_collection_type = "%s:%s" % (rank_type, nested_collection_type)
return identifiers
def create_nested_collection(self, history_id, collection_type, name=None, collection=None, element_identifiers=None):
"""Create a nested collection either from collection or using collection_type)."""
assert collection_type is not None
name = name or "Test %s" % collection_type
if collection is not None:
assert element_identifiers is None
element_identifiers = []
for i, pair in enumerate(collection):
element_identifiers.append(dict(
name="test%d" % i,
src="hdca",
id=pair
))
if element_identifiers is None:
element_identifiers = self.nested_collection_identifiers(history_id, collection_type)
payload = dict(
instance_type="history",
history_id=history_id,
element_identifiers=json.dumps(element_identifiers),
collection_type=collection_type,
name=name,
)
return self.__create(payload)
def create_list_of_pairs_in_history(self, history_id, **kwds):
pair1 = self.create_pair_in_history(history_id, **kwds).json()["id"]
return self.create_list_from_pairs(history_id, [pair1])
def create_list_of_list_in_history(self, history_id, **kwds):
# create_nested_collection will generate nested collection from just datasets,
# this function uses recursive generation of history hdcas.
collection_type = kwds.pop('collection_type', 'list:list')
collection_types = collection_type.split(':')
list = self.create_list_in_history(history_id, **kwds).json()['id']
current_collection_type = 'list'
for collection_type in collection_types[1:]:
current_collection_type = "%s:%s" % (current_collection_type, collection_type)
response = self.create_nested_collection(history_id=history_id,
collection_type=current_collection_type,
name=current_collection_type,
collection=[list])
list = response.json()['id']
return response
def create_pair_in_history(self, history_id, **kwds):
payload = self.create_pair_payload(
history_id,
instance_type="history",
**kwds
)
return self.__create(payload)
def create_list_in_history(self, history_id, **kwds):
payload = self.create_list_payload(
history_id,
instance_type="history",
**kwds
)
return self.__create(payload)
def create_list_payload(self, history_id, **kwds):
return self.__create_payload(history_id, identifiers_func=self.list_identifiers, collection_type="list", **kwds)
def create_pair_payload(self, history_id, **kwds):
return self.__create_payload(history_id, identifiers_func=self.pair_identifiers, collection_type="paired", **kwds)
def __create_payload(self, history_id, identifiers_func, collection_type, **kwds):
contents = None
if "contents" in kwds:
contents = kwds["contents"]
del kwds["contents"]
if "element_identifiers" not in kwds:
kwds["element_identifiers"] = json.dumps(identifiers_func(history_id, contents=contents))
if "name" not in kwds:
kwds["name"] = "Test Dataset Collection"
payload = dict(
history_id=history_id,
collection_type=collection_type,
**kwds
)
return payload
def pair_identifiers(self, history_id, contents=None):
hda1, hda2 = self.__datasets(history_id, count=2, contents=contents)
element_identifiers = [
dict(name="forward", src="hda", id=hda1["id"]),
dict(name="reverse", src="hda", id=hda2["id"]),
]
return element_identifiers
def list_identifiers(self, history_id, contents=None):
count = 3 if contents is None else len(contents)
# Contents can be a list of strings (with name auto-assigned here) or a list of
# 2-tuples of form (name, dataset_content).
if contents and isinstance(contents[0], tuple):
hdas = self.__datasets(history_id, count=count, contents=[c[1] for c in contents])
def hda_to_identifier(i, hda):
return dict(name=contents[i][0], src="hda", id=hda["id"])
else:
hdas = self.__datasets(history_id, count=count, contents=contents)
def hda_to_identifier(i, hda):
return dict(name="data%d" % (i + 1), src="hda", id=hda["id"])
element_identifiers = [hda_to_identifier(i, hda) for (i, hda) in enumerate(hdas)]
return element_identifiers
def __create(self, payload):
return self._create_collection(payload)
def __datasets(self, history_id, count, contents=None):
datasets = []
for i in range(count):
new_kwds = {}
if contents:
new_kwds["content"] = contents[i]
datasets.append(self.dataset_populator.new_dataset(history_id, **new_kwds))
return datasets
def wait_for_dataset_collection(self, create_payload, assert_ok=False, timeout=DEFAULT_TIMEOUT):
for element in create_payload["elements"]:
if element['element_type'] == 'hda':
self.dataset_populator.wait_for_dataset(history_id=element['object']['history_id'],
dataset_id=element['object']['id'],
assert_ok=assert_ok,
timeout=timeout)
elif element['element_type'] == 'dataset_collection':
self.wait_for_dataset_collection(element['object'], assert_ok=assert_ok, timeout=timeout)
class DatasetCollectionPopulator(BaseDatasetCollectionPopulator):
def __init__(self, galaxy_interactor):
self.galaxy_interactor = galaxy_interactor
self.dataset_populator = DatasetPopulator(galaxy_interactor)
def _create_collection(self, payload):
create_response = self.galaxy_interactor.post("dataset_collections", data=payload)
return create_response
def wait_on_state(state_func, skip_states=["running", "queued", "new", "ready"], assert_ok=False, timeout=DEFAULT_TIMEOUT):
def get_state():
response = state_func()
assert response.status_code == 200, "Failed to fetch state update while waiting."
state = response.json()["state"]
if state in skip_states:
return None
else:
if assert_ok:
assert state == "ok", "Final state - %s - not okay." % state
return state
return wait_on(get_state, desc="state", timeout=timeout)
class GiPostGetMixin:
"""Mixin for adapting Galaxy testing populators helpers to bioblend."""
def _get(self, route, data={}):
return self._gi.make_get_request(self.__url(route), data)
def _post(self, route, data={}):
data = data.copy()
data['key'] = self._gi.key
return requests.post(self.__url(route), data=data)
def _delete(self, route, data={}):
data = data.copy()
data['key'] = self._gi.key
return requests.delete(self.__url(route), data=data)
def __url(self, route):
return self._gi.url + "/" + route
class GiDatasetPopulator(BaseDatasetPopulator, GiPostGetMixin):
"""Implementation of BaseDatasetPopulator backed by bioblend."""
def __init__(self, gi):
"""Construct a dataset populator from a bioblend GalaxyInstance."""
self._gi = gi
class GiDatasetCollectionPopulator(BaseDatasetCollectionPopulator, GiPostGetMixin):
"""Implementation of BaseDatasetCollectionPopulator backed by bioblend."""
def __init__(self, gi):
"""Construct a dataset collection populator from a bioblend GalaxyInstance."""
self._gi = gi
self.dataset_populator = GiDatasetPopulator(gi)
def _create_collection(self, payload):
create_response = self._post("dataset_collections", data=payload)
return create_response
class GiWorkflowPopulator(BaseWorkflowPopulator, GiPostGetMixin):
"""Implementation of BaseWorkflowPopulator backed by bioblend."""
def __init__(self, gi):
"""Construct a workflow populator from a bioblend GalaxyInstance."""
self._gi = gi
self.dataset_populator = GiDatasetPopulator(gi)
def wait_on(function, desc, timeout=DEFAULT_TIMEOUT):
delta = .25
iteration = 0
while True:
total_wait = delta * iteration
if total_wait > timeout:
timeout_message = "Timed out after %s seconds waiting on %s." % (
total_wait, desc
)
assert False, timeout_message
iteration += 1
value = function()
if value is not None:
return value
time.sleep(delta)