forked from galaxyproject/galaxy
-
Notifications
You must be signed in to change notification settings - Fork 1
/
populators.py
1804 lines (1478 loc) · 74.4 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
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Abstractions used by the Galaxy testing frameworks for interacting with the Galaxy API.
These abstractions are geared toward testing use cases and populating fixtures.
For a more general framework for working with the Galaxy API checkout `bioblend
<https://github.com/galaxyproject/bioblend>`__.
The populators are broken into different categories of data one might want to populate
and work with (datasets, histories, libraries, and workflows). Within each populator
type abstract classes describe high-level functionality that depend on abstract
HTTP verbs executions (e.g. methods for executing GET, POST, DELETE). The abstract
classes are :class:`galaxy_test.base.populators.BaseDatasetPopulator`,
:class:`galaxy_test.base.populators.BaseWorkflowPopulator`, and
:class:`galaxy_test.base.populators.BaseDatasetCollectionPopulator`.
There are a few different concrete ways to supply these low-level verb executions.
For instance :class:`galaxy_test.base.populators.DatasetPopulator` implements the abstract
:class:`galaxy_test.base.populators.BaseDatasetPopulator` by leveraging a galaxy interactor
:class:`galaxy.tool_util.interactor.GalaxyInteractorApi`. It is non-intuitive
that the Galaxy testing framework uses the tool testing code inside Galaxy's code
base for a lot of heavy lifting. This is due to the API testing framework organically
growing from the tool testing framework that predated it and then the tool testing
framework being extracted for re-use in `Planemo <https://github.com/galaxyproject/planemo>`__, etc..
These other two concrete implementation of the populators are much more
direct and intuitive. :class:`galaxy_test.base.populators.GiDatasetPopulator`, et. al.
are populators built based on Bioblend ``gi`` objects to build URLs and describe
API keys. :class:`galaxy_test.selenium.framework.SeleniumSessionDatasetPopulator`,
et al. are populators built based on Selenium sessions to leverage Galaxy cookies
for auth for instance.
All three of these implementations are now effectively light wrappers around
`requests <https://requests.readthedocs.io/>`__. Not leveraging requests directly
is a bit ugly and this ugliness again stems from these organically growing from a
framework that originally didn't use requests at all.
API tests and Selenium tests routinely use requests directly and that is totally fine,
requests should just be filtered through the verb abstractions if that functionality
is then added to populators to be shared across tests or across testing frameworks.
"""
import contextlib
import json
import os
import random
import string
import unittest
from abc import ABCMeta, abstractmethod
from collections import namedtuple
from functools import wraps
from io import StringIO
from operator import itemgetter
from typing import Any, Callable, Dict, Optional
import requests
import yaml
from bioblend.galaxy import GalaxyClient
from gxformat2 import (
convert_and_import_workflow,
ImporterGalaxyInterface,
)
from gxformat2._yaml import ordered_load
from pkg_resources import resource_string
from requests.models import Response
from galaxy.tool_util.client.staging import InteractorStaging
from galaxy.tool_util.verify.test_data import TestDataResolver
from galaxy.tool_util.verify.wait import (
timeout_type,
TimeoutAssertionError,
wait_on as tool_util_wait_on,
)
from galaxy.util import unicodify
from . import api_asserts
from .api import ApiTestInteractor
# Simple workflow that takes an input and call cat wrapper on it.
workflow_str = unicodify(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 = unicodify(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 unittest.SkipTest:
raise
except Exception:
if SKIP_FLAKEY_TESTS_ON_ERROR:
raise unittest.SkipTest("Error encountered during test marked as @flakey.")
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 if 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 if the datatype 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 is_site_up(url):
try:
response = requests.get(url, timeout=10)
return response.status_code == 200
except Exception:
return False
def skip_if_site_down(url):
def method_wrapper(method):
@wraps(method)
def wrapped_method(api_test_case, *args, **kwargs):
_raise_skip_if(not is_site_up(url), f"Test depends on [{url}] being up and it appears to be down.")
method(api_test_case, *args, **kwargs)
return wrapped_method
return method_wrapper
skip_if_toolshed_down = skip_if_site_down("https://toolshed.g2.bx.psu.edu")
skip_if_github_down = skip_if_site_down("https://github.com/")
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 uses_test_history(**test_history_kwd):
"""Can override require_new and cancel_executions using kwds to decorator.
"""
def method_wrapper(method):
@wraps(method)
def wrapped_method(api_test_case, *args, **kwds):
with api_test_case.dataset_populator.test_history(**test_history_kwd) as history_id:
method(api_test_case, history_id, *args, **kwds)
return wrapped_method
return method_wrapper
def _raise_skip_if(check, *args):
if check:
from nose.plugins.skip import SkipTest
raise SkipTest(*args)
class BasePopulator(metaclass=ABCMeta):
@abstractmethod
def _post(self, route, data=None, files=None, headers=None, admin=False, json: bool = False) -> Response:
"""POST data to target Galaxy instance on specified route."""
@abstractmethod
def _put(self, route, data=None, headers=None, admin=False) -> Response:
"""PUT data to target Galaxy instance on specified route."""
@abstractmethod
def _get(self, route, data=None, headers=None, admin=False) -> Response:
"""GET data from target Galaxy instance on specified route."""
@abstractmethod
def _delete(self, route, data=None, headers=None, admin=False) -> Response:
"""DELETE against target Galaxy instance on specified route."""
class BaseDatasetPopulator(BasePopulator):
""" Abstract description of API operations optimized for testing
Galaxy - implementations must implement _get, _post and _delete.
"""
def new_dataset(self, history_id: str, content=None, wait: bool = False, **kwds) -> str:
"""Create a new history dataset instance (HDA) and return its ID.
:returns: the HDA id of the new object
"""
run_response = self.new_dataset_request(history_id, content=content, wait=wait, **kwds)
assert run_response.status_code == 200, "Failed to create new dataset with response: %s" % run_response.text
return run_response.json()["outputs"][0]
def new_dataset_request(self, history_id: str, content=None, wait: bool = False, **kwds) -> requests.Response:
"""Lower-level dataset creation that returns the upload tool response object.
"""
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 fetch(self, payload: dict, assert_ok: bool = True, timeout: timeout_type = DEFAULT_TIMEOUT, wait: Optional[bool] = None):
tool_response = self._post("tools/fetch", data=payload)
if wait is None:
wait = assert_ok
if wait:
job = self.check_run(tool_response)
self.wait_for_job(job["id"], timeout=timeout)
if assert_ok:
job = tool_response.json()["jobs"][0]
details = self.get_job_details(job["id"]).json()
assert details["state"] == "ok", details
return tool_response
def wait_for_tool_run(self, history_id: str, run_response: requests.Response, timeout: timeout_type = DEFAULT_TIMEOUT, assert_ok: bool = True):
job = self.check_run(run_response)
self.wait_for_job(job["id"], timeout=timeout)
self.wait_for_history(history_id, assert_ok=assert_ok, timeout=timeout)
return run_response
def check_run(self, run_response: requests.Response) -> dict:
run = run_response.json()
assert run_response.status_code == 200, run
job = run["jobs"][0]
return job
def wait_for_history(self, history_id: str, assert_ok: bool = False, timeout: timeout_type = DEFAULT_TIMEOUT) -> str:
try:
return wait_on_state(lambda: self._get("histories/%s" % history_id), desc="history state", assert_ok=assert_ok, timeout=timeout)
except AssertionError:
self._summarize_history(history_id)
raise
def wait_for_history_jobs(self, history_id: str, assert_ok: bool = False, timeout: timeout_type = DEFAULT_TIMEOUT):
def has_active_jobs():
active_jobs = self.active_history_jobs(history_id)
if len(active_jobs) == 0:
return True
else:
return None
try:
wait_on(has_active_jobs, "active jobs", timeout=timeout)
except TimeoutAssertionError as e:
jobs = self.history_jobs(history_id)
message = f"Failed waiting on active jobs to complete, current jobs are [{jobs}]. {e}"
raise TimeoutAssertionError(message)
if assert_ok:
return self.wait_for_history(history_id, assert_ok=True, timeout=timeout)
def wait_for_job(self, job_id: str, assert_ok: bool = False, timeout: timeout_type = DEFAULT_TIMEOUT):
return wait_on_state(lambda: self.get_job_details(job_id), desc="job state", assert_ok=assert_ok, timeout=timeout)
def get_job_details(self, job_id: str, full: bool = False) -> Response:
return self._get(f"jobs/{job_id}?full={full}")
def cancel_history_jobs(self, history_id: str, wait=True) -> None:
active_jobs = self.active_history_jobs(history_id)
for active_job in active_jobs:
self.cancel_job(active_job["id"])
def history_jobs(self, history_id: str) -> dict:
query_params = {"history_id": history_id, "order_by": "create_time"}
jobs_response = self._get("jobs", query_params)
assert jobs_response.status_code == 200
return jobs_response.json()
def active_history_jobs(self, history_id: str) -> list:
all_history_jobs = self.history_jobs(history_id)
active_jobs = [j for j in all_history_jobs if j["state"] in ["new", "upload", "waiting", "queued", "running"]]
return active_jobs
def cancel_job(self, job_id: str) -> Response:
return self._delete("jobs/%s" % job_id)
def delete_history(self, history_id: str) -> None:
delete_response = self._delete(f"histories/{history_id}")
delete_response.raise_for_status()
def delete_dataset(self, history_id: str, content_id: str) -> Response:
delete_response = self._delete(f"histories/{history_id}/contents/{content_id}")
return delete_response
def create_tool_from_path(self, tool_path: str) -> Response:
tool_directory = os.path.dirname(os.path.abspath(tool_path))
payload = dict(
src="from_path",
path=tool_path,
tool_directory=tool_directory,
)
return self._create_tool_raw(payload)
def create_tool(self, representation, tool_directory: Optional[str] = None) -> Response:
if isinstance(representation, dict):
representation = json.dumps(representation)
payload = dict(
representation=representation,
tool_directory=tool_directory,
)
return self._create_tool_raw(payload)
def _create_tool_raw(self, payload) -> Response:
try:
create_response = self._post("dynamic_tools", data=payload, admin=True)
except TypeError:
create_response = self._post("dynamic_tools", data=payload)
assert create_response.status_code == 200, create_response.text
return create_response.json()
def list_dynamic_tools(self) -> list:
list_response = self._get("dynamic_tools", admin=True)
assert list_response.status_code == 200, list_response
return list_response.json()
def show_dynamic_tool(self, uuid) -> dict:
show_response = self._get("dynamic_tools/%s" % uuid, admin=True)
assert show_response.status_code == 200, show_response
return show_response.json()
def deactivate_dynamic_tool(self, uuid) -> dict:
delete_response = self._delete("dynamic_tools/%s" % uuid, admin=True)
return delete_response.json()
def _summarize_history(self, history_id: str) -> None:
"""Abstract method for summarizing a target history - override to provide details."""
@contextlib.contextmanager
def test_history(self, cancel_executions: bool = True, require_new: bool = True, **kwds):
cleanup = "GALAXY_TEST_NO_CLEANUP" not in os.environ
history_id = None
def wrap_up():
if cleanup and cancel_executions:
self.cancel_history_jobs(history_id)
try:
if not require_new:
history_id = kwds.get("GALAXY_TEST_HISTORY_ID", None)
history_id = history_id or self.new_history()
yield history_id
wrap_up()
except Exception:
if history_id:
self._summarize_history(history_id)
wrap_up()
raise
def new_history(self, name="API Test History", **kwds) -> str:
create_history_response = self._post("histories", data=dict(name=name))
assert "id" in create_history_response.json(), create_history_response.text
history_id = create_history_response.json()["id"]
return history_id
def upload_payload(self, history_id: str, content: str = None, **kwds) -> dict:
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: str = "ftp") -> dict:
response = self._get("remote_files", data={"target": target})
response.raise_for_status()
return response.json()
def run_tool_payload(self, tool_id: str, inputs: dict, history_id: str, **kwds) -> dict:
# Remove files_%d|file_data parameters from inputs dict and attach
# as __files dictionary.
for key, value in list(inputs.items()):
if key.startswith("files_") and key.endswith("|file_data"):
if "__files" not in kwds:
kwds["__files"] = {}
kwds["__files"][key] = value
del inputs[key]
return dict(
tool_id=tool_id,
inputs=json.dumps(inputs),
history_id=history_id,
**kwds
)
def build_tool_state(self, tool_id: str, history_id: str):
response = self._post(f"tools/{tool_id}/build?history_id={history_id}")
response.raise_for_status()
return response.json()
def run_tool(self, tool_id: str, inputs: dict, history_id: str, assert_ok: bool = 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: dict, url="tools") -> Response:
tool_response = self._post(url, data=payload)
return tool_response
def get_history_dataset_content(self, history_id: str, wait=True, filename=None, type='text', raw=False, **kwds):
dataset_id = self.__history_content_id(history_id, wait=wait, **kwds)
data = {}
if filename:
data["filename"] = filename
if raw:
data['raw'] = True
display_response = self._get_contents_request(history_id, "/%s/display" % dataset_id, data=data)
assert display_response.status_code == 200, display_response.text
if type == 'text':
return display_response.text
else:
return display_response.content
def get_history_dataset_details(self, history_id: str, **kwds) -> dict:
dataset_id = self.__history_content_id(history_id, **kwds)
details_response = self.get_history_dataset_details_raw(history_id, dataset_id)
details_response.raise_for_status()
return details_response.json()
def get_history_dataset_details_raw(self, history_id: str, dataset_id: str) -> Response:
details_response = self._get_contents_request(history_id, f"/datasets/{dataset_id}")
return details_response
def get_history_dataset_extra_files(self, history_id: str, **kwds) -> list:
dataset_id = self.__history_content_id(history_id, **kwds)
details_response = self._get_contents_request(history_id, "/%s/extra_files" % dataset_id)
assert details_response.status_code == 200, details_response.content
return details_response.json()
def get_history_collection_details(self, history_id: str, **kwds) -> dict:
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: str, hdca_id: str) -> Response:
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: str, hdca_id: str) -> dict:
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: str, wait=True, **kwds) -> str:
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(f"Could not find content with HID [{hid}] in [{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: str, suffix: str = "", data=None) -> Response:
if data is None:
data = {}
url = "histories/%s/contents" % history_id
if suffix:
url = f"{url}{suffix}"
return self._get(url, data=data)
def ds_entry(self, history_content: dict) -> dict:
src = 'hda'
if 'history_content_type' in history_content and history_content['history_content_type'] == "dataset_collection":
src = 'hdca'
return dict(src=src, id=history_content["id"])
def dataset_storage_info(self, dataset_id: str) -> dict:
storage_response = self._get(f"datasets/{dataset_id}/storage")
storage_response.raise_for_status()
return storage_response.json()
def get_roles(self) -> list:
roles_response = self._get("roles", admin=True)
assert roles_response.status_code == 200
return roles_response.json()
def user_email(self) -> str:
users_response = self._get("users")
users = users_response.json()
assert len(users) == 1
return users[0]["email"]
def user_id(self) -> str:
users_response = self._get("users")
users = users_response.json()
assert len(users) == 1
return users[0]["id"]
def user_private_role_id(self) -> str:
user_email = self.user_email()
roles = self.get_roles()
users_roles = [r for r in roles if r["name"] == user_email]
assert len(users_roles) == 1, f"Did not find exactly one role for email {user_email} - {users_roles}"
role = users_roles[0]
assert "id" in role, role
return role["id"]
def create_role(self, user_ids: list, description: str = None) -> dict:
payload = {
"name": self.get_random_name(prefix="testpop"),
"description": description or "Test Role",
"user_ids": user_ids,
}
role_response = self._post("roles", data=payload, admin=True, json=True)
assert role_response.status_code == 200
return role_response.json()
def create_quota(self, quota_payload: dict) -> dict:
quota_response = self._post("quotas", data=quota_payload, admin=True)
quota_response.raise_for_status()
return quota_response.json()
def get_quotas(self) -> list:
quota_response = self._get("quotas", admin=True)
quota_response.raise_for_status()
return quota_response.json()
def make_private(self, history_id: str, dataset_id: str) -> dict:
role_id = self.user_private_role_id()
# Give manage permission to the user.
payload = {
"access": json.dumps([role_id]),
"manage": json.dumps([role_id]),
}
url = f"histories/{history_id}/contents/{dataset_id}/permissions"
update_response = self._put(url, payload, admin=True)
assert update_response.status_code == 200, update_response.content
return update_response.json()
def validate_dataset(self, history_id, dataset_id):
url = f"histories/{history_id}/contents/{dataset_id}/validate"
update_response = self.galaxy_interactor._put(url, {})
assert update_response.status_code == 200, update_response.content
return update_response.json()
def validate_dataset_and_wait(self, history_id, dataset_id):
self.validate_dataset(history_id, dataset_id)
def validated():
metadata = self.get_history_dataset_details(history_id, dataset_id=dataset_id)
validated_state = metadata['validated_state']
if validated_state == 'unknown':
return
else:
return validated_state
return wait_on(
validated,
"dataset validation"
)
def setup_history_for_export_testing(self, history_name):
history_id = self.new_history(name=history_name)
self.new_dataset(history_id, content="1 2 3")
deleted_hda = self.new_dataset(history_id, content="1 2 3", wait=True)
self.delete_dataset(history_id, deleted_hda["id"])
deleted_details = self.get_history_dataset_details(history_id, id=deleted_hda["id"])
assert deleted_details["deleted"]
return history_id
def prepare_export(self, history_id, data):
url = "histories/%s/exports" % history_id
put_response = self._put(url, data)
put_response.raise_for_status()
if put_response.status_code == 202:
def export_ready_response():
put_response = self._put(url)
if put_response.status_code == 202:
return None
return put_response
put_response = wait_on(export_ready_response, desc="export ready")
api_asserts.assert_status_code_is(put_response, 200)
return put_response
else:
job_desc = put_response.json()
assert "job_id" in job_desc
return self.wait_for_job(job_desc["job_id"])
def export_url(self, history_id, data, check_download=True):
put_response = self.prepare_export(history_id, data)
response = put_response.json()
api_asserts.assert_has_keys(response, "download_url")
download_url = response["download_url"]
if check_download:
self.get_export_url(download_url)
return download_url
def get_export_url(self, export_url):
full_download_url = f"{export_url}?key={self._api_key}"
download_response = self._get(full_download_url)
api_asserts.assert_status_code_is(download_response, 200)
return download_response
def import_history(self, import_data):
files = {}
archive_file = import_data.pop("archive_file", None)
if archive_file:
files["archive_file"] = archive_file
import_response = self._post("histories", data=import_data, files=files)
api_asserts.assert_status_code_is(import_response, 200)
def import_history_and_wait_for_name(self, import_data, history_name):
def history_names():
return {h["name"]: h for h in self.get_histories()}
import_name = "imported from archive: %s" % history_name
assert import_name not in history_names()
self.import_history(import_data)
def has_history_with_name():
histories = history_names()
return histories.get(import_name, None)
imported_history = wait_on(has_history_with_name, desc="import history")
imported_history_id = imported_history["id"]
self.wait_for_history(imported_history_id)
return imported_history_id
def rename_history(self, history_id, new_name):
update_url = "histories/%s" % history_id
put_response = self._put(update_url, {"name": new_name})
return put_response
def get_histories(self):
history_index_response = self._get("histories")
api_asserts.assert_status_code_is(history_index_response, 200)
return history_index_response.json()
def wait_on_history_length(self, history_id, wait_on_history_length):
def history_has_length():
history_length = self.history_length(history_id)
return None if history_length != wait_on_history_length else True
wait_on(history_has_length, desc="import history population")
def history_length(self, history_id):
contents_response = self._get("histories/%s/contents" % history_id)
api_asserts.assert_status_code_is(contents_response, 200)
contents = contents_response.json()
return len(contents)
def reimport_history(self, history_id, history_name, wait_on_history_length, export_kwds, url, api_key):
# Export the history.
download_path = self.export_url(history_id, export_kwds, check_download=True)
# Create download for history
full_download_url = f"{url}{download_path}?key={api_key}"
import_data = dict(archive_source=full_download_url, archive_type="url")
imported_history_id = self.import_history_and_wait_for_name(import_data, history_name)
if wait_on_history_length:
self.wait_on_history_length(imported_history_id, wait_on_history_length)
return imported_history_id
def get_random_name(self, prefix=None, suffix=None, len=10):
# stolen from navigates_galaxy.py
return '{}{}{}'.format(
prefix or '',
''.join(random.choice(string.ascii_lowercase + string.digits) for _ in range(len)),
suffix or '',
)
def wait_for_dataset(self, history_id, dataset_id, assert_ok=False, timeout=DEFAULT_TIMEOUT):
return wait_on_state(lambda: self._get(f"histories/{history_id}/contents/{dataset_id}"), desc="dataset state", assert_ok=assert_ok, timeout=timeout)
class GalaxyInteractorHttpMixin:
galaxy_interactor: ApiTestInteractor
@property
def _api_key(self):
return self.galaxy_interactor.api_key
def _post(self, route, data=None, files=None, headers=None, admin=False, json: bool = False) -> Response:
return self.galaxy_interactor.post(route, data, files=files, admin=admin, headers=headers, json=json)
def _put(self, route, data=None, headers=None, admin=False):
return self.galaxy_interactor.put(route, data, headers=headers, admin=admin)
def _get(self, route, data=None, headers=None, admin=False):
if data is None:
data = {}
return self.galaxy_interactor.get(route, data=data, headers=headers, admin=admin)
def _delete(self, route, data=None, headers=None, admin=False):
if data is None:
data = {}
return self.galaxy_interactor.delete(route, data=data, headers=headers, admin=admin)
class DatasetPopulator(GalaxyInteractorHttpMixin, BaseDatasetPopulator):
def __init__(self, galaxy_interactor):
self.galaxy_interactor = galaxy_interactor
def _summarize_history(self, history_id):
self.galaxy_interactor._summarize_history(history_id)
class BaseWorkflowPopulator(BasePopulator):
def load_workflow(self, name: str, content: str = workflow_str, add_pja=False) -> dict:
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: str) -> dict:
return self.load_workflow(name, content=workflow_random_x2_str)
def load_workflow_from_resource(self, name: str, filename: Optional[str] = None) -> dict:
if filename is None:
filename = "data/%s.ga" % name
content = unicodify(resource_string(__name__, filename))
return self.load_workflow(name, content=content)
def simple_workflow(self, name: str, **create_kwds) -> str:
workflow = self.load_workflow(name)
return self.create_workflow(workflow, **create_kwds)
def import_workflow_from_path(self, from_path: str) -> str:
data = dict(
from_path=from_path
)
import_response = self._post("workflows", data=data)
api_asserts.assert_status_code_is(import_response, 200)
return import_response.json()["id"]
def create_workflow(self, workflow: dict, **create_kwds) -> str:
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: dict, **create_kwds) -> Response:
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) -> str:
round_trip_conversion = kwds.get("round_trip_format_conversion", False)
client_convert = kwds.pop("client_convert", not round_trip_conversion)
kwds["convert"] = client_convert
workflow = convert_and_import_workflow(has_yaml, galaxy_interface=self, **kwds)
workflow_id = workflow["id"]
if round_trip_conversion:
workflow_yaml_wrapped = self.download_workflow(workflow_id, style="format2_wrapped_yaml")
assert "yaml_content" in workflow_yaml_wrapped, workflow_yaml_wrapped
round_trip_converted_content = workflow_yaml_wrapped["yaml_content"]
workflow_id = self.upload_yaml_workflow(round_trip_converted_content, client_convert=False, round_trip_conversion=False)
return workflow_id
def wait_for_invocation(self, workflow_id: str, invocation_id: str, timeout: timeout_type = DEFAULT_TIMEOUT, assert_ok: bool = True):
url = f"workflows/{workflow_id}/usage/{invocation_id}"
def workflow_state():
return self._get(url)
return wait_on_state(workflow_state, desc="workflow invocation state", timeout=timeout, assert_ok=assert_ok)
def history_invocations(self, history_id: str) -> list:
history_invocations_response = self._get("invocations", {"history_id": history_id})
api_asserts.assert_status_code_is(history_invocations_response, 200)
return history_invocations_response.json()
def wait_for_history_workflows(self, history_id, assert_ok=True, timeout=DEFAULT_TIMEOUT, expected_invocation_count=None):
if expected_invocation_count is not None:
def invocation_count():
invocations = self.history_invocations(history_id)
if len(invocations) == expected_invocation_count:
return True
wait_on(invocation_count, "%s history invocations" % expected_invocation_count)
for invocation in self.history_invocations(history_id):
workflow_id = invocation["workflow_id"]
invocation_id = invocation["id"]
self.wait_for_workflow(workflow_id, invocation_id, history_id, timeout=timeout, assert_ok=assert_ok)
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, assert_ok=assert_ok)
self.dataset_populator.wait_for_history_jobs(history_id, assert_ok=assert_ok, timeout=timeout)
def get_invocation(self, invocation_id):
r = self._get("invocations/%s" % invocation_id)
r.raise_for_status()
return r.json()
def get_biocompute_object(self, invocation_id):
bco_response = self._get("invocations/%s/biocompute" % invocation_id)
bco_response.raise_for_status()
return bco_response.json()
def validate_biocompute_object(self, bco, expected_schema_version='https://w3id.org/ieee/ieee-2791-schema/2791object.json'):
# TODO: actually use jsonref and jsonschema to validate this someday
api_asserts.assert_has_keys(bco, "object_id", "spec_version", "etag", "provenance_domain", "usability_domain", "description_domain", "execution_domain", "parametric_domain", "io_domain", "error_domain")
assert bco['spec_version'] == expected_schema_version
api_asserts.assert_has_keys(bco['description_domain'], "keywords", "xref", "platform", "pipeline_steps")
api_asserts.assert_has_keys(bco['execution_domain'], "script_access_type", "script", "script_driver", "software_prerequisites", "external_data_endpoints", "environment_variables")
for p in bco['parametric_domain']:
api_asserts.assert_has_keys(p, "param", "value", "step")
api_asserts.assert_has_keys(bco['io_domain'], "input_subdomain", "output_subdomain")
def invoke_workflow_raw(self, workflow_id, request: dict) -> Response:
url = "workflows/%s/usage" % (workflow_id)
invocation_response = self._post(url, data=request)
return invocation_response
def invoke_workflow(self, history_id: str, workflow_id: str, inputs: Optional[dict] = None, request: Optional[dict] = None, assert_ok: bool = True):
if inputs is None:
inputs = {}
if request is None:
request = {}
request["history"] = "hist_id=%s" % history_id,
if inputs:
request["inputs"] = json.dumps(inputs)
request["inputs_by"] = 'step_index'
invocation_response = self.invoke_workflow_raw(workflow_id, 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
def workflow_report_json(self, workflow_id: str, invocation_id: str) -> dict:
response = self._get(f"workflows/{workflow_id}/invocations/{invocation_id}/report")
api_asserts.assert_status_code_is(response, 200)
return response.json()
def download_workflow(self, workflow_id: str, style: Optional[str] = None, history_id: Optional[str] = None) -> dict:
params = {}
if style is not None:
params["style"] = style
if history_id is not None:
params['history_id'] = history_id
response = self._get("workflows/%s/download" % workflow_id, data=params)
api_asserts.assert_status_code_is(response, 200)
if style != "format2":
return response.json()
else:
return ordered_load(response.text)
def update_workflow(self, workflow_id: str, workflow_object: dict) -> Response:
data = dict(
workflow=workflow_object
)
raw_url = 'workflows/%s' % workflow_id
put_response = self._put(raw_url, json.dumps(data))
return put_response
def refactor_workflow(self, workflow_id: str, actions: list, dry_run: Optional[bool] = None, style: Optional[str] = None) -> Response:
data: Dict[str, Any] = dict(
actions=actions,
)
if style is not None:
data["style"] = style
if dry_run is not None:
data["dry_run"] = dry_run
raw_url = 'workflows/%s/refactor' % workflow_id
put_response = self._put(raw_url, json.dumps(data))
return put_response
@contextlib.contextmanager
def export_for_update(self, workflow_id):
workflow_object = self.download_workflow(workflow_id)
yield workflow_object
put_respose = self.update_workflow(workflow_id, workflow_object)