-
Notifications
You must be signed in to change notification settings - Fork 967
/
modules.py
1288 lines (1078 loc) · 55.6 KB
/
modules.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
"""
Modules used in building workflows
"""
import logging
import re
from json import loads
from xml.etree.ElementTree import (
Element,
XML
)
from galaxy import (
exceptions,
model,
web
)
from galaxy.dataset_collections import matching
from galaxy.exceptions import ToolMissingException
from galaxy.jobs.actions.post import ActionBox
from galaxy.model import PostJobAction
from galaxy.tools import (
DefaultToolState,
ToolInputsNotReadyException
)
from galaxy.tools.execute import execute, MappingParameters, PartialJobExecution
from galaxy.tools.parameters import (
check_param,
params_to_incoming,
visit_input_values
)
from galaxy.tools.parameters.basic import (
BooleanToolParameter,
DataCollectionToolParameter,
DataToolParameter,
is_runtime_value,
parameter_types,
RuntimeValue,
SelectToolParameter,
TextToolParameter,
workflow_building_modes
)
from galaxy.tools.parameters.wrapped import make_dict_copy
from galaxy.util.bunch import Bunch
from galaxy.util.json import safe_loads
from galaxy.util.odict import odict
from galaxy.util.rules_dsl import RuleSet
from galaxy.util.template import fill_template
from tool_shed.util import common_util
log = logging.getLogger(__name__)
# Key into Tool state to describe invocation-specific runtime properties.
RUNTIME_STEP_META_STATE_KEY = "__STEP_META_STATE__"
# Key into step runtime state dict describing invocation-specific post job
# actions (i.e. PJA specified at runtime on top of the workflow-wide defined
# ones.
RUNTIME_POST_JOB_ACTIONS_KEY = "__POST_JOB_ACTIONS__"
class NoReplacement(object):
def __str__(self):
return "NO_REPLACEMENT singleton"
NO_REPLACEMENT = NoReplacement()
class WorkflowModule(object):
def __init__(self, trans, content_id=None, **kwds):
self.trans = trans
self.content_id = content_id
self.state = DefaultToolState()
# ---- Creating modules from various representations ---------------------
@classmethod
def from_dict(Class, trans, d, **kwds):
module = Class(trans, **kwds)
module.recover_state(d.get("tool_state"), **kwds)
module.label = d.get("label")
return module
@classmethod
def from_workflow_step(Class, trans, step, **kwds):
module = Class(trans, **kwds)
module.recover_state(step.tool_inputs)
module.label = step.label
return module
# ---- Saving in various forms ------------------------------------------
def save_to_step(self, step):
step.type = self.type
step.tool_inputs = self.get_state()
# ---- General attributes -----------------------------------------------
def get_type(self):
return self.type
def get_name(self):
return self.name
def get_version(self):
return None
def get_content_id(self):
""" If this component has an identifier external to the step (such
as a tool or another workflow) return the identifier for that content.
"""
return None
def get_tooltip(self, static_path=''):
return None
# ---- Configuration time -----------------------------------------------
def get_state(self, nested=True):
""" Return a serializable representation of the persistable state of
the step.
"""
inputs = self.get_inputs()
if inputs:
return self.state.encode(Bunch(inputs=inputs), self.trans.app, nested=nested)
else:
return self.state.inputs
def recover_state(self, state, **kwds):
""" Recover state `dict` from simple dictionary describing configuration
state (potentially from persisted step state).
Sub-classes should supply a `default_state` method which contains the
initial state `dict` with key, value pairs for all available attributes.
"""
self.state = DefaultToolState()
inputs = self.get_inputs()
if inputs:
self.state.decode(state, Bunch(inputs=inputs), self.trans.app)
else:
self.state.inputs = safe_loads(state) or {}
def get_errors(self):
""" This returns a step related error message as string or None """
return None
def get_inputs(self):
""" This returns inputs displayed in the workflow editor """
return {}
def get_data_inputs(self):
""" Get configure time data input descriptions. """
return []
def get_data_outputs(self):
return []
def get_post_job_actions(self, incoming):
return []
def check_and_update_state(self):
"""
If the state is not in sync with the current implementation of the
module, try to update. Returns a list of messages to be displayed
"""
pass
def add_dummy_datasets(self, connections=None, steps=None):
""" Replace connected inputs with placeholder/dummy values. """
pass
def get_config_form(self):
""" Serializes input parameters of a module into input dictionaries. """
return {
'title' : self.name,
'inputs': [param.to_dict(self.trans) for param in self.get_inputs().values()]
}
# ---- Run time ---------------------------------------------------------
def get_runtime_state(self):
raise TypeError("Abstract method")
def get_runtime_inputs(self, **kwds):
""" Used internally by modules and when displaying inputs in workflow
editor and run workflow templates.
"""
return {}
def compute_runtime_state(self, trans, step_updates=None):
""" Determine the runtime state (potentially different from self.state
which describes configuration state). This (again unlike self.state) is
currently always a `DefaultToolState` object.
If `step_updates` is `None`, this is likely for rendering the run form
for instance and no runtime properties are available and state must be
solely determined by the default runtime state described by the step.
If `step_updates` are available they describe the runtime properties
supplied by the workflow runner.
"""
state = self.get_runtime_state()
step_errors = {}
if step_updates:
def update_value(input, context, prefixed_name, **kwargs):
if prefixed_name in step_updates:
value, error = check_param(trans, input, step_updates.get(prefixed_name), context)
if error is not None:
step_errors[prefixed_name] = error
return value
return NO_REPLACEMENT
visit_input_values(self.get_runtime_inputs(), state.inputs, update_value, no_replacement_value=NO_REPLACEMENT)
return state, step_errors
def encode_runtime_state(self, runtime_state):
""" Takes the computed runtime state and serializes it during run request creation. """
return runtime_state.encode(Bunch(inputs=self.get_runtime_inputs()), self.trans.app)
def decode_runtime_state(self, runtime_state):
""" Takes the serialized runtime state and decodes it when running the workflow. """
state = DefaultToolState()
state.decode(runtime_state, Bunch(inputs=self.get_runtime_inputs()), self.trans.app)
return state
def execute(self, trans, progress, invocation_step, use_cached_job=False):
""" Execute the given workflow invocation step.
Use the supplied workflow progress object to track outputs, find
inputs, etc....
Return a False if there is additional processing required to
on subsequent workflow scheduling runs, None or True means the workflow
step executed properly.
"""
raise TypeError("Abstract method")
def do_invocation_step_action(self, step, action):
""" Update or set the workflow invocation state action - generic
extension point meant to allows users to interact with interactive
workflow modules. The action object returned from this method will
be attached to the WorkflowInvocationStep and be available the next
time the workflow scheduler visits the workflow.
"""
raise exceptions.RequestParameterInvalidException("Attempting to perform invocation step action on module that does not support actions.")
def recover_mapping(self, invocation_step, progress):
""" Re-populate progress object with information about connections
from previously executed steps recorded via invocation_steps.
"""
outputs = {}
for output_dataset_assoc in invocation_step.output_datasets:
outputs[output_dataset_assoc.output_name] = output_dataset_assoc.dataset
for output_dataset_collection_assoc in invocation_step.output_dataset_collections:
outputs[output_dataset_collection_assoc.output_name] = output_dataset_collection_assoc.dataset_collection
progress.set_step_outputs(invocation_step, outputs, already_persisted=True)
def get_replacement_parameters(self, step):
"""Return a list of replacement parameters."""
return []
class SubWorkflowModule(WorkflowModule):
# Two step improvements to build runtime inputs for subworkflow modules
# - First pass verify nested workflow doesn't have an RuntimeInputs
# - Second pass actually turn RuntimeInputs into inputs if possible.
type = "subworkflow"
name = "Subworkflow"
@classmethod
def from_dict(Class, trans, d, **kwds):
module = super(SubWorkflowModule, Class).from_dict(trans, d, **kwds)
if "subworkflow" in d:
module.subworkflow = d["subworkflow"]
elif "content_id" in d:
from galaxy.managers.workflows import WorkflowsManager
module.subworkflow = WorkflowsManager(trans.app).get_owned_workflow(trans, d["content_id"])
else:
raise Exception("Step associated subworkflow could not be found.")
return module
@classmethod
def from_workflow_step(Class, trans, step, **kwds):
module = super(SubWorkflowModule, Class).from_workflow_step(trans, step, **kwds)
module.subworkflow = step.subworkflow
return module
def save_to_step(self, step):
step.type = self.type
step.subworkflow = self.subworkflow
def get_name(self):
if hasattr(self.subworkflow, 'name'):
return self.subworkflow.name
return self.name
def get_data_inputs(self):
""" Get configure time data input descriptions. """
# Filter subworkflow steps and get inputs
step_to_input_type = {
"data_input": "dataset",
"data_collection_input": "dataset_collection",
}
inputs = []
if hasattr(self.subworkflow, 'input_steps'):
for step in self.subworkflow.input_steps:
name = step.label
if not name:
step_module = module_factory.from_workflow_step(self.trans, step)
name = "%s:%s" % (step.order_index, step_module.get_name())
step_type = step.type
assert step_type in step_to_input_type
input = dict(
input_subworkflow_step_id=step.order_index,
name=name,
label=name,
multiple=False,
extensions=["data"],
input_type=step_to_input_type[step_type],
)
inputs.append(input)
return inputs
def get_data_outputs(self):
outputs = []
if hasattr(self.subworkflow, 'workflow_outputs'):
from galaxy.managers.workflows import WorkflowContentsManager
workflow_contents_manager = WorkflowContentsManager(self.trans.app)
subworkflow_dict = workflow_contents_manager._workflow_to_dict_editor(trans=self.trans,
stored=self.subworkflow.stored_workflow,
workflow=self.subworkflow,
tooltip=False)
for order_index in sorted(subworkflow_dict['steps']):
step = subworkflow_dict['steps'][order_index]
data_outputs = subworkflow_dict['steps'][order_index]['data_outputs']
for workflow_output in step['workflow_outputs']:
label = workflow_output['label']
if not label:
label = "%s:%s" % (order_index, workflow_output['output_name'])
for data_output in data_outputs:
if data_output['name'] == workflow_output['output_name']:
data_output['label'] = label
data_output['name'] = label
# That's the right data_output
break
else:
# This hopefully can't happen, but let's be clear
raise Exception("Workflow output '%s' defined, but not listed among data outputs" % workflow_output['output_name'])
outputs.append(data_output)
return outputs
def get_content_id(self):
return self.trans.security.encode_id(self.subworkflow.id)
def execute(self, trans, progress, invocation_step, use_cached_job=False):
""" Execute the given workflow step in the given workflow invocation.
Use the supplied workflow progress object to track outputs, find
inputs, etc...
"""
step = invocation_step.workflow_step
subworkflow_invoker = progress.subworkflow_invoker(trans, step, use_cached_job=use_cached_job)
subworkflow_invoker.invoke()
subworkflow = subworkflow_invoker.workflow
subworkflow_progress = subworkflow_invoker.progress
outputs = {}
for workflow_output in subworkflow.workflow_outputs:
workflow_output_label = workflow_output.label or "%s:%s" % (workflow_output.workflow_step.order_index, workflow_output.output_name)
replacement = subworkflow_progress.get_replacement_workflow_output(workflow_output)
outputs[workflow_output_label] = replacement
progress.set_step_outputs(invocation_step, outputs)
return None
def get_runtime_state(self):
state = DefaultToolState()
state.inputs = dict()
return state
def get_runtime_inputs(self, connections=None):
inputs = {}
for step in self.subworkflow.steps:
if step.type == "tool":
tool = step.module.tool
tool_inputs = step.module.state
def callback(input, prefixed_name, prefixed_label, value=None, **kwds):
# All data parameters are represented as runtime values, skip them
# here.
if input.type in ['data', 'data_collection']:
return
if is_runtime_value(value):
input_name = "%d|%s" % (step.order_index, prefixed_name)
inputs[input_name] = InputProxy(input, input_name)
visit_input_values(tool.inputs, tool_inputs.inputs, callback)
return inputs
def get_replacement_parameters(self, step):
"""Return a list of replacement parameters."""
replacement_parameters = set()
for subworkflow_step in self.subworkflow.steps:
module = subworkflow_step.module
for replacement_parameter in module.get_replacement_parameters(subworkflow_step):
replacement_parameters.add(replacement_parameter)
return list(replacement_parameters)
class InputProxy(object):
"""Provide InputParameter-interfaces over inputs but renamed for workflow context."""
def __init__(self, input, prefixed_name):
self.input = input
self.prefixed_name = prefixed_name
def to_dict(self, *args, **kwds):
as_dict = self.input.to_dict(*args, **kwds)
as_dict["name"] = self.prefixed_name
return as_dict
class InputModule(WorkflowModule):
def get_runtime_state(self):
state = DefaultToolState()
state.inputs = dict(input=None)
return state
def get_data_inputs(self):
return []
def execute(self, trans, progress, invocation_step, use_cached_job=False):
invocation = invocation_step.workflow_invocation
step = invocation_step.workflow_step
step_outputs = dict(output=step.state.inputs['input'])
# Web controller may set copy_inputs_to_history, API controller always sets
# inputs.
if invocation.copy_inputs_to_history:
for input_dataset_hda in list(step_outputs.values()):
content_type = input_dataset_hda.history_content_type
if content_type == "dataset":
new_hda = input_dataset_hda.copy()
invocation.history.add_dataset(new_hda)
step_outputs['input_ds_copy'] = new_hda
elif content_type == "dataset_collection":
new_hdca = input_dataset_hda.copy()
invocation.history.add_dataset_collection(new_hdca)
step_outputs['input_ds_copy'] = new_hdca
else:
raise Exception("Unknown history content encountered")
# If coming from UI - we haven't registered invocation inputs yet,
# so do that now so dependent steps can be recalculated. In the future
# everything should come in from the API and this can be eliminated.
if not invocation.has_input_for_step(step.id):
content = next(iter(step_outputs.values()))
if content:
invocation.add_input(content, step.id)
progress.set_outputs_for_input(invocation_step, step_outputs)
def recover_mapping(self, invocation_step, progress):
progress.set_outputs_for_input(invocation_step)
class InputDataModule(InputModule):
type = "data_input"
name = "Input dataset"
def get_data_outputs(self):
return [dict(name='output', extensions=['input'])]
def get_filter_set(self, connections=None):
filter_set = []
if connections:
for oc in connections:
for ic in oc.input_step.module.get_data_inputs():
if 'extensions' in ic and ic['extensions'] != 'input' and ic['name'] == oc.input_name:
filter_set += ic['extensions']
if not filter_set:
filter_set = ['data']
return ', '.join(filter_set)
def get_runtime_inputs(self, connections=None):
return dict(input=DataToolParameter(None, Element("param", name="input", label=self.label, multiple=False, type="data", format=self.get_filter_set(connections)), self.trans))
class InputDataCollectionModule(InputModule):
type = "data_collection_input"
name = "Input dataset collection"
default_collection_type = "list"
collection_type = default_collection_type
def get_inputs(self):
collection_type = self.state.inputs.get("collection_type", self.default_collection_type)
input_collection_type = TextToolParameter(None, XML(
'''
<param name="collection_type" label="Collection type" type="text" value="%s">
<option value="list">List of Datasets</option>
<option value="paired">Dataset Pair</option>
<option value="list:paired">List of Dataset Pairs</option>
</param>
''' % collection_type))
return dict(collection_type=input_collection_type)
def get_runtime_inputs(self, **kwds):
collection_type = self.state.inputs.get("collection_type", self.default_collection_type)
input_element = Element("param", name="input", label=self.label, type="data_collection", collection_type=collection_type)
return dict(input=DataCollectionToolParameter(None, input_element, self.trans))
def get_data_outputs(self):
return [
dict(
name='output',
extensions=['input_collection'],
collection=True,
collection_type=self.state.inputs.get('collection_type', self.default_collection_type)
)
]
class InputParameterModule(WorkflowModule):
type = "parameter_input"
name = "Input parameter"
default_parameter_type = "text"
default_optional = False
parameter_type = default_parameter_type
optional = default_optional
def get_inputs(self):
# TODO: Use an external xml or yaml file to load the parameter definition
parameter_type = self.state.inputs.get("parameter_type", self.default_parameter_type)
optional = self.state.inputs.get("optional", self.default_optional)
input_parameter_type = SelectToolParameter(None, XML(
'''
<param name="parameter_type" label="Parameter type" type="select" value="%s">
<option value="text">Text</option>
<option value="integer">Integer</option>
<option value="float">Float</option>
<option value="boolean">Boolean (True or False)</option>
<option value="color">Color</option>
</param>
''' % parameter_type))
return odict([("parameter_type", input_parameter_type),
("optional", BooleanToolParameter(None, Element("param", name="optional", label="Optional", type="boolean", value=optional)))])
def get_runtime_inputs(self, **kwds):
parameter_type = self.state.inputs.get("parameter_type", self.default_parameter_type)
optional = self.state.inputs.get("optional", self.default_optional)
if parameter_type not in ["text", "boolean", "integer", "float", "color"]:
raise ValueError("Invalid parameter type for workflow parameters encountered.")
parameter_class = parameter_types[parameter_type]
parameter_kwds = {}
if parameter_type in ["integer", "float"]:
parameter_kwds["value"] = str(0)
# TODO: Use a dict-based description from YAML tool source
element = Element("param", name="input", label=self.label, type=parameter_type, optional=str(optional), **parameter_kwds)
input = parameter_class(None, element)
return dict(input=input)
def get_runtime_state(self):
state = DefaultToolState()
state.inputs = dict(input=None)
return state
def get_data_inputs(self):
return []
def execute(self, trans, progress, invocation_step, use_cached_job=False):
step = invocation_step.workflow_step
step_outputs = dict(output=step.state.inputs['input'])
progress.set_outputs_for_input(invocation_step, step_outputs)
class PauseModule(WorkflowModule):
""" Initially this module will unconditionally pause a workflow - will aim
to allow conditional pausing later on.
"""
type = "pause"
name = "Pause for dataset review"
def get_data_inputs(self):
input = dict(
name="input",
label="Dataset for Review",
multiple=False,
extensions='input',
input_type="dataset",
)
return [input]
def get_data_outputs(self):
return [dict(name="output", label="Reviewed Dataset", extensions=['input'])]
def get_runtime_state(self):
state = DefaultToolState()
state.inputs = dict()
return state
def execute(self, trans, progress, invocation_step, use_cached_job=False):
step = invocation_step.workflow_step
progress.mark_step_outputs_delayed(step, why="executing pause step")
def recover_mapping(self, invocation_step, progress):
if invocation_step:
step = invocation_step.workflow_step
action = invocation_step.action
if action:
connection = step.input_connections_by_name["input"][0]
replacement = progress.replacement_for_connection(connection)
progress.set_step_outputs(invocation_step, {'output': replacement})
return
elif action is False:
raise CancelWorkflowEvaluation()
delayed_why = "workflow paused at this step waiting for review"
raise DelayedWorkflowEvaluation(why=delayed_why)
def do_invocation_step_action(self, step, action):
""" Update or set the workflow invocation state action - generic
extension point meant to allows users to interact with interactive
workflow modules. The action object returned from this method will
be attached to the WorkflowInvocationStep and be available the next
time the workflow scheduler visits the workflow.
"""
return bool(action)
class ToolModule(WorkflowModule):
type = "tool"
name = "Tool"
def __init__(self, trans, tool_id, tool_version=None, exact_tools=True, **kwds):
super(ToolModule, self).__init__(trans, content_id=tool_id, **kwds)
self.tool_id = tool_id
self.tool_version = tool_version
self.tool = trans.app.toolbox.get_tool(tool_id, tool_version=tool_version, exact=exact_tools)
if self.tool and tool_version and exact_tools and str(self.tool.version) != str(tool_version):
log.info("Exact tool specified during workflow module creation for [%s] but couldn't find correct version [%s]." % (tool_id, tool_version))
self.tool = None
self.post_job_actions = {}
self.runtime_post_job_actions = {}
self.workflow_outputs = []
self.version_changes = []
# ---- Creating modules from various representations ---------------------
@classmethod
def from_dict(Class, trans, d, **kwds):
tool_id = d.get('content_id') or d.get('tool_id')
if tool_id is None:
raise exceptions.RequestParameterInvalidException("No tool id could be located for step [%s]." % d)
tool_version = d.get('tool_version')
if tool_version:
tool_version = str(tool_version)
module = super(ToolModule, Class).from_dict(trans, d, tool_id=tool_id, tool_version=tool_version, **kwds)
module.post_job_actions = d.get('post_job_actions', {})
module.workflow_outputs = d.get('workflow_outputs', [])
if module.tool:
message = ""
if tool_id != module.tool_id:
message += "The tool (id '%s') specified in this step is not available. Using the tool with id %s instead." % (tool_id, module.tool_id)
if d.get('tool_version', 'Unspecified') != module.get_version():
message += "%s: using version '%s' instead of version '%s' specified in this workflow." % (tool_id, module.get_version(), d.get('tool_version', 'Unspecified'))
if message:
log.debug(message)
module.version_changes.append(message)
return module
@classmethod
def from_workflow_step(Class, trans, step, **kwds):
tool_id = trans.app.toolbox.get_tool_id(step.tool_id) or step.tool_id
tool_version = step.tool_version
module = super(ToolModule, Class).from_workflow_step(trans, step, tool_id=tool_id, tool_version=tool_version, **kwds)
module.workflow_outputs = step.workflow_outputs
module.post_job_actions = {}
for pja in step.post_job_actions:
module.post_job_actions[pja.action_type] = pja
if module.tool:
message = ""
if step.tool_id != module.tool_id: # This means the exact version of the tool is not installed. We inform the user.
old_tool_shed = step.tool_id.split("/repos/")[0]
if old_tool_shed not in tool_id: # Only display the following warning if the tool comes from a different tool shed
old_tool_shed_url = common_util.get_tool_shed_url_from_tool_shed_registry(trans.app, old_tool_shed)
if not old_tool_shed_url: # a tool from a different tool_shed has been found, but the original tool shed has been deactivated
old_tool_shed_url = "http://" + old_tool_shed # let's just assume it's either http, or a http is forwarded to https.
old_url = old_tool_shed_url + "/view/%s/%s/" % (module.tool.repository_owner, module.tool.repository_name)
new_url = module.tool.sharable_url + '/%s/' % module.tool.changeset_revision
new_tool_shed_url = new_url.split("/view")[0]
message += "The tool \'%s\', version %s by the owner %s installed from <a href=\"%s\" target=\"_blank\">%s</a> is not available. " % (module.tool.name, tool_version, module.tool.repository_owner, old_url, old_tool_shed_url)
message += "A derivation of this tool installed from <a href=\"%s\" target=\"_blank\">%s</a> will be used instead. " % (new_url, new_tool_shed_url)
if step.tool_version and (step.tool_version != module.tool.version):
message += "<span title=\"tool id '%s'\">Using version '%s' instead of version '%s' specified in this workflow. " % (tool_id, module.tool.version, step.tool_version)
if message:
log.debug(message)
module.version_changes.append(message)
else:
log.warning("The tool '%s' is missing. Cannot build workflow module." % tool_id)
return module
# ---- Saving in various forms ------------------------------------------
def save_to_step(self, step):
super(ToolModule, self).save_to_step(step)
step.tool_id = self.tool_id
step.tool_version = self.get_version()
for k, v in self.post_job_actions.items():
pja = self.__to_pja(k, v, step)
self.trans.sa_session.add(pja)
# ---- General attributes ------------------------------------------------
def get_name(self):
return self.tool.name if self.tool else self.tool_id
def get_content_id(self):
return self.tool_id
def get_version(self):
return self.tool.version if self.tool else self.tool_version
def get_tooltip(self, static_path=''):
if self.tool and self.tool.help:
return self.tool.help.render(host_url=web.url_for('/'), static_path=static_path)
# ---- Configuration time -----------------------------------------------
def get_errors(self):
return None if self.tool else "Tool is not installed."
def get_inputs(self):
return self.tool.inputs if self.tool else {}
def get_data_inputs(self):
data_inputs = []
if self.tool:
def callback(input, prefixed_name, prefixed_label, **kwargs):
if not hasattr(input, 'hidden') or not input.hidden:
if isinstance(input, DataToolParameter):
data_inputs.append(dict(
name=prefixed_name,
label=prefixed_label,
multiple=input.multiple,
extensions=input.extensions,
input_type="dataset", ))
elif isinstance(input, DataCollectionToolParameter):
data_inputs.append(dict(
name=prefixed_name,
label=prefixed_label,
multiple=input.multiple,
input_type="dataset_collection",
collection_types=input.collection_types,
extensions=input.extensions,
))
visit_input_values(self.tool.inputs, self.state.inputs, callback)
return data_inputs
def get_data_outputs(self):
data_outputs = []
if self.tool:
for name, tool_output in self.tool.outputs.items():
extra_kwds = {}
if tool_output.collection:
extra_kwds["collection"] = True
collection_type = tool_output.structure.collection_type
if not collection_type and tool_output.structure.collection_type_from_rules:
rule_param = tool_output.structure.collection_type_from_rules
if rule_param in self.state.inputs:
rule_json_str = self.state.inputs[rule_param]
if rule_json_str: # initialized to None...
rules = rule_json_str
if rules:
rule_set = RuleSet(rules)
collection_type = rule_set.collection_type
extra_kwds["collection_type"] = collection_type
extra_kwds["collection_type_source"] = tool_output.structure.collection_type_source
formats = ['input'] # TODO: fix
elif tool_output.format_source is not None:
formats = ['input'] # default to special name "input" which remove restrictions on connections
else:
formats = [tool_output.format]
for change_elem in tool_output.change_format:
for when_elem in change_elem.findall('when'):
format = when_elem.get('format', None)
if format and format not in formats:
formats.append(format)
if tool_output.label:
try:
params = make_dict_copy(self.state.inputs)
params['on_string'] = 'input dataset(s)'
params['tool'] = self.tool
extra_kwds['label'] = fill_template(tool_output.label, context=params)
except Exception:
pass
data_outputs.append(
dict(
name=name,
extensions=formats,
**extra_kwds
)
)
return data_outputs
def get_config_form(self):
if self.tool:
self.add_dummy_datasets()
incoming = {}
params_to_incoming(incoming, self.tool.inputs, self.state.inputs, self.trans.app)
return self.tool.to_json(self.trans, incoming, workflow_building_mode=True)
def check_and_update_state(self):
if self.tool:
return self.tool.check_and_update_param_values(self.state.inputs, self.trans, workflow_building_mode=True)
def add_dummy_datasets(self, connections=None, steps=None):
if self.tool:
if connections:
# Store connections by input name
input_connections_by_name = dict((conn.input_name, conn) for conn in connections)
else:
input_connections_by_name = {}
# Any input needs to have value RuntimeValue or obtain the value from connected steps
def callback(input, prefixed_name, context, **kwargs):
if isinstance(input, DataToolParameter) or isinstance(input, DataCollectionToolParameter):
if connections is not None and steps is not None and self.trans.workflow_building_mode is workflow_building_modes.USE_HISTORY:
if prefixed_name in input_connections_by_name:
connection = input_connections_by_name[prefixed_name]
output_step = next(output_step for output_step in steps if connection.output_step_id == output_step.id)
if output_step.type.startswith('data'):
output_inputs = output_step.module.get_runtime_inputs(connections=connections)
output_value = output_inputs['input'].get_initial_value(self.trans, context)
if isinstance(input, DataToolParameter) and isinstance(output_value, self.trans.app.model.HistoryDatasetCollectionAssociation):
return output_value.to_hda_representative()
return output_value
return RuntimeValue()
else:
return input.get_initial_value(self.trans, context)
elif connections is None or prefixed_name in input_connections_by_name:
return RuntimeValue()
visit_input_values(self.tool.inputs, self.state.inputs, callback)
else:
raise ToolMissingException("Tool %s missing. Cannot add dummy datasets." % self.tool_id)
def get_post_job_actions(self, incoming):
return ActionBox.handle_incoming(incoming)
# ---- Run time ---------------------------------------------------------
def recover_state(self, state, **kwds):
""" Recover state `dict` from simple dictionary describing configuration
state (potentially from persisted step state).
Sub-classes should supply a `default_state` method which contains the
initial state `dict` with key, value pairs for all available attributes.
"""
super(ToolModule, self).recover_state(state, **kwds)
if kwds.get("fill_defaults", False) and self.tool:
self.compute_runtime_state(self.trans, step_updates=None)
self.tool.check_and_update_param_values(self.state.inputs, self.trans, workflow_building_mode=True)
def get_runtime_state(self):
state = DefaultToolState()
state.inputs = self.state.inputs
return state
def get_runtime_inputs(self, **kwds):
return self.get_inputs()
def compute_runtime_state(self, trans, step_updates=None):
# Warning: This method destructively modifies existing step state.
if self.tool:
step_errors = {}
state = self.state
self.runtime_post_job_actions = {}
if step_updates:
state, step_errors = super(ToolModule, self).compute_runtime_state(trans, step_updates)
self.runtime_post_job_actions = step_updates.get(RUNTIME_POST_JOB_ACTIONS_KEY, {})
step_metadata_runtime_state = self.__step_meta_runtime_state()
if step_metadata_runtime_state:
state.inputs[RUNTIME_STEP_META_STATE_KEY] = step_metadata_runtime_state
return state, step_errors
else:
raise ToolMissingException("Tool %s missing. Cannot compute runtime state." % self.tool_id)
def decode_runtime_state(self, runtime_state):
""" Take runtime state from persisted invocation and convert it
into a DefaultToolState object for use during workflow invocation.
"""
if self.tool:
state = super(ToolModule, self).decode_runtime_state(runtime_state)
if RUNTIME_STEP_META_STATE_KEY in runtime_state:
self.__restore_step_meta_runtime_state(loads(runtime_state[RUNTIME_STEP_META_STATE_KEY]))
return state
else:
raise ToolMissingException("Tool %s missing. Cannot recover runtime state." % self.tool_id)
def execute(self, trans, progress, invocation_step, use_cached_job=False):
invocation = invocation_step.workflow_invocation
step = invocation_step.workflow_step
tool = trans.app.toolbox.get_tool(step.tool_id, tool_version=step.tool_version)
if not tool.is_workflow_compatible:
message = "Specified tool [%s] in workflow is not workflow-compatible." % tool.id
raise Exception(message)
tool_state = step.state
# Not strictly needed - but keep Tool state clean by stripping runtime
# metadata parameters from it.
if RUNTIME_STEP_META_STATE_KEY in tool_state.inputs:
del tool_state.inputs[RUNTIME_STEP_META_STATE_KEY]
collections_to_match = self._find_collections_to_match(tool, progress, step)
# Have implicit collections...
if collections_to_match.has_collections():
collection_info = self.trans.app.dataset_collections_service.match_collections(collections_to_match)
else:
collection_info = None
param_combinations = []
if collection_info:
iteration_elements_iter = collection_info.slice_collections()
else:
iteration_elements_iter = [None]
resource_parameters = invocation.resource_parameters
for iteration_elements in iteration_elements_iter:
execution_state = tool_state.copy()
# TODO: Move next step into copy()
execution_state.inputs = make_dict_copy(execution_state.inputs)
expected_replacement_keys = set(step.input_connections_by_name.keys())
found_replacement_keys = set()
# Connect up
def callback(input, prefixed_name, **kwargs):
replacement = NO_REPLACEMENT
if isinstance(input, DataToolParameter) or isinstance(input, DataCollectionToolParameter):
if iteration_elements and prefixed_name in iteration_elements:
if isinstance(input, DataToolParameter):
# Pull out dataset instance from element.
replacement = iteration_elements[prefixed_name].dataset_instance
if hasattr(iteration_elements[prefixed_name], u'element_identifier') and iteration_elements[prefixed_name].element_identifier:
replacement.element_identifier = iteration_elements[prefixed_name].element_identifier
else:
# If collection - just use element model object.
replacement = iteration_elements[prefixed_name]
else:
replacement = progress.replacement_for_tool_input(step, input, prefixed_name)
else:
replacement = progress.replacement_for_tool_input(step, input, prefixed_name)
if replacement is not NO_REPLACEMENT:
found_replacement_keys.add(prefixed_name)
return replacement
try:
# Replace DummyDatasets with historydatasetassociations
visit_input_values(tool.inputs, execution_state.inputs, callback, no_replacement_value=NO_REPLACEMENT)
except KeyError as k:
message_template = "Error due to input mapping of '%s' in '%s'. A common cause of this is conditional outputs that cannot be determined until runtime, please review your workflow."
message = message_template % (tool.name, k.message)
raise exceptions.MessageException(message)
unmatched_input_connections = expected_replacement_keys - found_replacement_keys
if unmatched_input_connections:
log.warn("Failed to use input connections for inputs [%s]" % unmatched_input_connections)
param_combinations.append(execution_state.inputs)
complete = False
completed_jobs = {}
for i, param in enumerate(param_combinations):
if use_cached_job:
completed_jobs[i] = tool.job_search.by_tool_input(
trans=trans,
tool_id=tool.id,
tool_version=tool.version,
param=param,
param_dump=tool.params_to_strings(param, trans.app, nested=True),
job_state=None,
)
else:
completed_jobs[i] = None
try:
mapping_params = MappingParameters(tool_state.inputs, param_combinations)
max_num_jobs = progress.maximum_jobs_to_schedule_or_none
execution_tracker = execute(
trans=self.trans,
tool=tool,
mapping_params=mapping_params,
history=invocation.history,