forked from snakemake/snakemake
-
Notifications
You must be signed in to change notification settings - Fork 0
/
__init__.py
2942 lines (2766 loc) · 120 KB
/
__init__.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
__author__ = "Johannes Köster"
__copyright__ = "Copyright 2021, Johannes Köster"
__email__ = "johannes.koester@uni-due.de"
__license__ = "MIT"
import os
import subprocess
import glob
from argparse import ArgumentError, ArgumentDefaultsHelpFormatter
import logging as _logging
import re
import sys
import inspect
import threading
import webbrowser
from functools import partial
import importlib
import shutil
import shlex
from importlib.machinery import SourceFileLoader
from snakemake.workflow import Workflow
from snakemake.dag import Batch
from snakemake.exceptions import print_exception, WorkflowError
from snakemake.logging import setup_logger, logger, SlackLogger, WMSLogger
from snakemake.io import load_configfile, wait_for_files
from snakemake.shell import shell
from snakemake.utils import update_config, available_cpu_count
from snakemake.common import Mode, __version__, MIN_PY_VERSION, get_appdirs
from snakemake.resources import parse_resources, DefaultResources
SNAKEFILE_CHOICES = [
"Snakefile",
"snakefile",
"workflow/Snakefile",
"workflow/snakefile",
]
def snakemake(
snakefile,
batch=None,
cache=None,
report=None,
report_stylesheet=None,
containerize=False,
lint=None,
generate_unit_tests=None,
listrules=False,
list_target_rules=False,
cores=1,
nodes=1,
local_cores=1,
max_threads=None,
resources=dict(),
overwrite_threads=None,
overwrite_scatter=None,
default_resources=None,
overwrite_resources=None,
config=dict(),
configfiles=None,
config_args=None,
workdir=None,
targets=None,
dryrun=False,
touch=False,
forcetargets=False,
forceall=False,
forcerun=[],
until=[],
omit_from=[],
prioritytargets=[],
stats=None,
printreason=False,
printshellcmds=False,
debug_dag=False,
printdag=False,
printrulegraph=False,
printfilegraph=False,
printd3dag=False,
nocolor=False,
quiet=False,
keepgoing=False,
cluster=None,
cluster_config=None,
cluster_sync=None,
drmaa=None,
drmaa_log_dir=None,
jobname="snakejob.{rulename}.{jobid}.sh",
immediate_submit=False,
standalone=False,
ignore_ambiguity=False,
snakemakepath=None,
lock=True,
unlock=False,
cleanup_metadata=None,
conda_cleanup_envs=False,
cleanup_shadow=False,
cleanup_scripts=True,
force_incomplete=False,
force_params_changed=False,
ignore_incomplete=False,
list_version_changes=False,
list_code_changes=False,
list_input_changes=False,
list_params_changes=False,
list_untracked=False,
list_resources=False,
summary=False,
archive=None,
delete_all_output=False,
delete_temp_output=False,
detailed_summary=False,
latency_wait=3,
wait_for_files=None,
print_compilation=False,
debug=False,
notemp=False,
all_temp=False,
keep_remote_local=False,
nodeps=False,
keep_target_files=False,
allowed_rules=None,
jobscript=None,
greediness=None,
no_hooks=False,
overwrite_shellcmd=None,
updated_files=None,
log_handler=[],
keep_logger=False,
max_jobs_per_second=None,
max_status_checks_per_second=100,
restart_times=0,
attempt=1,
verbose=False,
force_use_threads=False,
use_conda=False,
use_singularity=False,
use_env_modules=False,
singularity_args="",
conda_frontend="conda",
conda_prefix=None,
conda_cleanup_pkgs=None,
list_conda_envs=False,
singularity_prefix=None,
shadow_prefix=None,
scheduler="ilp",
scheduler_ilp_solver=None,
conda_create_envs_only=False,
mode=Mode.default,
wrapper_prefix=None,
kubernetes=None,
container_image=None,
tibanna=False,
tibanna_sfn=None,
google_lifesciences=False,
google_lifesciences_regions=None,
google_lifesciences_location=None,
google_lifesciences_cache=False,
tes=None,
preemption_default=None,
preemptible_rules=None,
precommand="",
default_remote_provider=None,
default_remote_prefix="",
tibanna_config=False,
assume_shared_fs=True,
cluster_status=None,
export_cwl=None,
show_failed_logs=False,
keep_incomplete=False,
keep_metadata=True,
messaging=None,
edit_notebook=None,
envvars=None,
overwrite_groups=None,
group_components=None,
max_inventory_wait_time=20,
execute_subworkflows=True,
conda_not_block_search_path_envvars=False,
scheduler_solver_path=None,
conda_base_path=None,
):
"""Run snakemake on a given snakefile.
This function provides access to the whole snakemake functionality. It is not thread-safe.
Args:
snakefile (str): the path to the snakefile
batch (Batch): whether to compute only a partial DAG, defined by the given Batch object (default None)
report (str): create an HTML report for a previous run at the given path
lint (str): print lints instead of executing (None, "plain" or "json", default None)
listrules (bool): list rules (default False)
list_target_rules (bool): list target rules (default False)
cores (int): the number of provided cores (ignored when using cluster support) (default 1)
nodes (int): the number of provided cluster nodes (ignored without cluster support) (default 1)
local_cores (int): the number of provided local cores if in cluster mode (ignored without cluster support) (default 1)
resources (dict): provided resources, a dictionary assigning integers to resource names, e.g. {gpu=1, io=5} (default {})
default_resources (DefaultResources): default values for resources not defined in rules (default None)
config (dict): override values for workflow config
workdir (str): path to working directory (default None)
targets (list): list of targets, e.g. rule or file names (default None)
dryrun (bool): only dry-run the workflow (default False)
touch (bool): only touch all output files if present (default False)
forcetargets (bool): force given targets to be re-created (default False)
forceall (bool): force all output files to be re-created (default False)
forcerun (list): list of files and rules that shall be re-created/re-executed (default [])
execute_subworkflows (bool): execute subworkflows if present (default True)
prioritytargets (list): list of targets that shall be run with maximum priority (default [])
stats (str): path to file that shall contain stats about the workflow execution (default None)
printreason (bool): print the reason for the execution of each job (default false)
printshellcmds (bool): print the shell command of each job (default False)
printdag (bool): print the dag in the graphviz dot language (default False)
printrulegraph (bool): print the graph of rules in the graphviz dot language (default False)
printfilegraph (bool): print the graph of rules with their input and output files in the graphviz dot language (default False)
printd3dag (bool): print a D3.js compatible JSON representation of the DAG (default False)
nocolor (bool): do not print colored output (default False)
quiet (bool): do not print any default job information (default False)
keepgoing (bool): keep goind upon errors (default False)
cluster (str): submission command of a cluster or batch system to use, e.g. qsub (default None)
cluster_config (str,list): configuration file for cluster options, or list thereof (default None)
cluster_sync (str): blocking cluster submission command (like SGE 'qsub -sync y') (default None)
drmaa (str): if not None use DRMAA for cluster support, str specifies native args passed to the cluster when submitting a job
drmaa_log_dir (str): the path to stdout and stderr output of DRMAA jobs (default None)
jobname (str): naming scheme for cluster job scripts (default "snakejob.{rulename}.{jobid}.sh")
immediate_submit (bool): immediately submit all cluster jobs, regardless of dependencies (default False)
standalone (bool): kill all processes very rudely in case of failure (do not use this if you use this API) (default False) (deprecated)
ignore_ambiguity (bool): ignore ambiguous rules and always take the first possible one (default False)
snakemakepath (str): deprecated parameter whose value is ignored. Do not use.
lock (bool): lock the working directory when executing the workflow (default True)
unlock (bool): just unlock the working directory (default False)
cleanup_metadata (list): just cleanup metadata of given list of output files (default None)
drop_metadata (bool): drop metadata file tracking information after job finishes (--report and --list_x_changes information will be incomplete) (default False)
conda_cleanup_envs (bool): just cleanup unused conda environments (default False)
cleanup_shadow (bool): just cleanup old shadow directories (default False)
cleanup_scripts (bool): delete wrapper scripts used for execution (default True)
force_incomplete (bool): force the re-creation of incomplete files (default False)
force_params_changed (bool): force the re-creation of files with updated parameters (default False)
ignore_incomplete (bool): ignore incomplete files (default False)
list_version_changes (bool): list output files with changed rule version (default False)
list_code_changes (bool): list output files with changed rule code (default False)
list_input_changes (bool): list output files with changed input files (default False)
list_params_changes (bool): list output files with changed params (default False)
list_untracked (bool): list files in the workdir that are not used in the workflow (default False)
summary (bool): list summary of all output files and their status (default False)
archive (str): archive workflow into the given tarball
delete_all_output (bool): remove all files generated by the workflow (default False)
delete_temp_output (bool): remove all temporary files generated by the workflow (default False)
latency_wait (int): how many seconds to wait for an output file to appear after the execution of a job, e.g. to handle filesystem latency (default 3)
wait_for_files (list): wait for given files to be present before executing the workflow
list_resources (bool): list resources used in the workflow (default False)
summary (bool): list summary of all output files and their status (default False). If no option is specified a basic summary will be ouput. If 'detailed' is added as an option e.g --summary detailed, extra info about the input and shell commands will be included
detailed_summary (bool): list summary of all input and output files and their status (default False)
print_compilation (bool): print the compilation of the snakefile (default False)
debug (bool): allow to use the debugger within rules
notemp (bool): ignore temp file flags, e.g. do not delete output files marked as temp after use (default False)
keep_remote_local (bool): keep local copies of remote files (default False)
nodeps (bool): ignore dependencies (default False)
keep_target_files (bool): do not adjust the paths of given target files relative to the working directory.
allowed_rules (set): restrict allowed rules to the given set. If None or empty, all rules are used.
jobscript (str): path to a custom shell script template for cluster jobs (default None)
greediness (float): set the greediness of scheduling. This value between 0 and 1 determines how careful jobs are selected for execution. The default value (0.5 if prioritytargets are used, 1.0 else) provides the best speed and still acceptable scheduling quality.
overwrite_shellcmd (str): a shell command that shall be executed instead of those given in the workflow. This is for debugging purposes only.
updated_files(list): a list that will be filled with the files that are updated or created during the workflow execution
verbose (bool): show additional debug output (default False)
max_jobs_per_second (int): maximal number of cluster/drmaa jobs per second, None to impose no limit (default None)
restart_times (int): number of times to restart failing jobs (default 0)
attempt (int): initial value of Job.attempt. This is intended for internal use only (default 1).
force_use_threads: whether to force use of threads over processes. helpful if shared memory is full or unavailable (default False)
use_conda (bool): use conda environments for each job (defined with conda directive of rules)
use_singularity (bool): run jobs in singularity containers (if defined with singularity directive)
use_env_modules (bool): load environment modules if defined in rules
singularity_args (str): additional arguments to pass to singularity
conda_prefix (str): the directory in which conda environments will be created (default None)
conda_cleanup_pkgs (snakemake.deployment.conda.CondaCleanupMode):
whether to clean up conda tarballs after env creation (default None), valid values: "tarballs", "cache"
singularity_prefix (str): the directory to which singularity images will be pulled (default None)
shadow_prefix (str): prefix for shadow directories. The job-specific shadow directories will be created in $SHADOW_PREFIX/shadow/ (default None)
conda_create_envs_only (bool): if specified, only builds the conda environments specified for each job, then exits.
list_conda_envs (bool): list conda environments and their location on disk.
mode (snakemake.common.Mode): execution mode
wrapper_prefix (str): prefix for wrapper script URLs (default None)
kubernetes (str): submit jobs to kubernetes, using the given namespace.
container_image (str): Docker image to use, e.g., for kubernetes.
default_remote_provider (str): default remote provider to use instead of local files (e.g. S3, GS)
default_remote_prefix (str): prefix for default remote provider (e.g. name of the bucket).
tibanna (bool): submit jobs to AWS cloud using Tibanna.
tibanna_sfn (str): Step function (Unicorn) name of Tibanna (e.g. tibanna_unicorn_monty). This must be deployed first using tibanna cli.
google_lifesciences (bool): submit jobs to Google Cloud Life Sciences (pipelines API).
google_lifesciences_regions (list): a list of regions (e.g., us-east1)
google_lifesciences_location (str): Life Sciences API location (e.g., us-central1)
google_lifesciences_cache (bool): save a cache of the compressed working directories in Google Cloud Storage for later usage.
tes (str): Execute workflow tasks on GA4GH TES server given by url.
precommand (str): commands to run on AWS cloud before the snakemake command (e.g. wget, git clone, unzip, etc). Use with --tibanna.
preemption_default (int): set a default number of preemptible instance retries (for Google Life Sciences executor only)
preemptible_rules (list): define custom preemptible instance retries for specific rules (for Google Life Sciences executor only)
tibanna_config (list): Additional tibanna config e.g. --tibanna-config spot_instance=true subnet=<subnet_id> security group=<security_group_id>
assume_shared_fs (bool): assume that cluster nodes share a common filesystem (default true).
cluster_status (str): status command for cluster execution. If None, Snakemake will rely on flag files. Otherwise, it expects the command to return "success", "failure" or "running" when executing with a cluster jobid as single argument.
export_cwl (str): Compile workflow to CWL and save to given file
log_handler (function): redirect snakemake output to this custom log handler, a function that takes a log message dictionary (see below) as its only argument (default None). The log message dictionary for the log handler has to following entries:
keep_incomplete (bool): keep incomplete output files of failed jobs
edit_notebook (object): "notebook.Listen" object to configuring notebook server for interactive editing of a rule notebook. If None, do not edit.
scheduler (str): Select scheduling algorithm (default ilp)
scheduler_ilp_solver (str): Set solver for ilp scheduler.
overwrite_groups (dict): Rule to group assignments (default None)
group_components (dict): Number of connected components given groups shall span before being split up (1 by default if empty)
conda_not_block_search_path_envvars (bool): Do not block search path envvars (R_LIBS, PYTHONPATH, ...) when using conda environments.
scheduler_solver_path (str): Path to Snakemake environment (this can be used to e.g. overwrite the search path for the ILP solver used during scheduling).
conda_base_path (str): Path to conda base environment (this can be used to overwrite the search path for conda, mamba and activate).
log_handler (list): redirect snakemake output to this list of custom log handler, each a function that takes a log message dictionary (see below) as its only argument (default []). The log message dictionary for the log handler has to following entries:
:level:
the log level ("info", "error", "debug", "progress", "job_info")
:level="info", "error" or "debug":
:msg:
the log message
:level="progress":
:done:
number of already executed jobs
:total:
number of total jobs
:level="job_info":
:input:
list of input files of a job
:output:
list of output files of a job
:log:
path to log file of a job
:local:
whether a job is executed locally (i.e. ignoring cluster)
:msg:
the job message
:reason:
the job reason
:priority:
the job priority
:threads:
the threads of the job
Returns:
bool: True if workflow execution was successful.
"""
assert not immediate_submit or (
immediate_submit and notemp
), "immediate_submit has to be combined with notemp (it does not support temp file handling)"
if tibanna:
assume_shared_fs = False
default_remote_provider = "S3"
default_remote_prefix = default_remote_prefix.rstrip("/")
assert (
default_remote_prefix
), "default_remote_prefix needed if tibanna is specified"
assert tibanna_sfn, "tibanna_sfn needed if tibanna is specified"
if tibanna_config:
tibanna_config_dict = dict()
for cf in tibanna_config:
k, v = cf.split("=")
if v == "true":
v = True
elif v == "false":
v = False
elif v.isnumeric():
v = int(v)
else:
try:
v = float(v)
except ValueError:
pass
tibanna_config_dict.update({k: v})
tibanna_config = tibanna_config_dict
# Google Cloud Life Sciences API uses compute engine and storage
if google_lifesciences:
assume_shared_fs = False
default_remote_provider = "GS"
default_remote_prefix = default_remote_prefix.rstrip("/")
# Currently preemptible instances only supported for Google LifeSciences Executor
if preemption_default or preemptible_rules and not google_lifesciences:
logger.warning(
"Preemptible instances are only available for the Google Life Sciences Executor."
)
if updated_files is None:
updated_files = list()
if isinstance(cluster_config, str):
# Loading configuration from one file is still supported for
# backward compatibility
cluster_config = [cluster_config]
if cluster_config:
# Load all configuration files
configs = [load_configfile(f) for f in cluster_config]
# Merge in the order as specified, overriding earlier values with
# later ones
cluster_config_content = configs[0]
for other in configs[1:]:
update_config(cluster_config_content, other)
else:
cluster_config_content = dict()
run_local = not (
cluster
or cluster_sync
or drmaa
or kubernetes
or tibanna
or google_lifesciences
or tes
)
if run_local:
if not dryrun:
# clean up all previously recorded jobids.
shell.cleanup()
else:
if edit_notebook:
raise WorkflowError(
"Notebook edit mode is only allowed with local execution."
)
shell.conda_block_conflicting_envvars = not conda_not_block_search_path_envvars
# force thread use for any kind of cluster
use_threads = (
force_use_threads
or (os.name not in ["posix", "nt"])
or cluster
or cluster_sync
or drmaa
)
if not keep_logger:
stdout = (
(
dryrun
and not (printdag or printd3dag or printrulegraph or printfilegraph)
)
or listrules
or list_target_rules
or list_resources
)
setup_logger(
handler=log_handler,
quiet=quiet,
printreason=printreason,
printshellcmds=printshellcmds,
debug_dag=debug_dag,
nocolor=nocolor,
stdout=stdout,
debug=verbose,
use_threads=use_threads,
mode=mode,
show_failed_logs=show_failed_logs,
)
if greediness is None:
greediness = 0.5 if prioritytargets else 1.0
else:
if not (0 <= greediness <= 1.0):
logger.error("Error: greediness must be a float between 0 and 1.")
return False
if not os.path.exists(snakefile):
logger.error('Error: Snakefile "{}" not found.'.format(snakefile))
return False
snakefile = os.path.abspath(snakefile)
cluster_mode = (
(cluster is not None) + (cluster_sync is not None) + (drmaa is not None)
)
if cluster_mode > 1:
logger.error("Error: cluster and drmaa args are mutually exclusive")
return False
if debug and (cluster_mode or cores is not None and cores > 1):
logger.error(
"Error: debug mode cannot be used with more than one core or cluster execution."
)
return False
overwrite_config = dict()
if configfiles is None:
configfiles = []
for f in configfiles:
# get values to override. Later configfiles override earlier ones.
overwrite_config.update(load_configfile(f))
# convert provided paths to absolute paths
configfiles = list(map(os.path.abspath, configfiles))
# directly specified elements override any configfiles
if config:
overwrite_config.update(config)
if config_args is None:
config_args = unparse_config(config)
if workdir:
olddir = os.getcwd()
if not os.path.exists(workdir):
logger.info("Creating specified working directory {}.".format(workdir))
os.makedirs(workdir)
workdir = os.path.abspath(workdir)
os.chdir(workdir)
logger.setup_logfile()
try:
# handle default remote provider
_default_remote_provider = None
if default_remote_provider is not None:
try:
rmt = importlib.import_module(
"snakemake.remote." + default_remote_provider
)
except ImportError as e:
raise WorkflowError("Unknown default remote provider.")
if rmt.RemoteProvider.supports_default:
_default_remote_provider = rmt.RemoteProvider(
keep_local=True, is_default=True
)
else:
raise WorkflowError(
"Remote provider {} does not (yet) support to "
"be used as default provider."
)
workflow = Workflow(
snakefile=snakefile,
jobscript=jobscript,
overwrite_shellcmd=overwrite_shellcmd,
overwrite_config=overwrite_config,
overwrite_workdir=workdir,
overwrite_configfiles=configfiles,
overwrite_clusterconfig=cluster_config_content,
overwrite_threads=overwrite_threads,
max_threads=max_threads,
overwrite_scatter=overwrite_scatter,
overwrite_groups=overwrite_groups,
overwrite_resources=overwrite_resources,
group_components=group_components,
config_args=config_args,
debug=debug,
verbose=verbose,
use_conda=use_conda or list_conda_envs or conda_cleanup_envs,
use_singularity=use_singularity,
use_env_modules=use_env_modules,
conda_frontend=conda_frontend,
conda_prefix=conda_prefix,
conda_cleanup_pkgs=conda_cleanup_pkgs,
singularity_prefix=singularity_prefix,
shadow_prefix=shadow_prefix,
singularity_args=singularity_args,
scheduler_type=scheduler,
scheduler_ilp_solver=scheduler_ilp_solver,
mode=mode,
wrapper_prefix=wrapper_prefix,
printshellcmds=printshellcmds,
restart_times=restart_times,
attempt=attempt,
default_remote_provider=_default_remote_provider,
default_remote_prefix=default_remote_prefix,
run_local=run_local,
default_resources=default_resources,
cache=cache,
cores=cores,
nodes=nodes,
resources=resources,
edit_notebook=edit_notebook,
envvars=envvars,
max_inventory_wait_time=max_inventory_wait_time,
conda_not_block_search_path_envvars=conda_not_block_search_path_envvars,
execute_subworkflows=execute_subworkflows,
scheduler_solver_path=scheduler_solver_path,
conda_base_path=conda_base_path,
check_envvars=not lint, # for linting, we do not need to check whether requested envvars exist
all_temp=all_temp,
)
success = True
workflow.include(
snakefile, overwrite_first_rule=True, print_compilation=print_compilation
)
workflow.check()
if not print_compilation:
if lint:
success = not workflow.lint(json=lint == "json")
elif containerize:
workflow.containerize()
elif listrules:
workflow.list_rules()
elif list_target_rules:
workflow.list_rules(only_targets=True)
elif list_resources:
workflow.list_resources()
else:
# if not printdag and not printrulegraph:
# handle subworkflows
subsnakemake = partial(
snakemake,
local_cores=local_cores,
max_threads=max_threads,
cache=cache,
overwrite_threads=overwrite_threads,
overwrite_scatter=overwrite_scatter,
overwrite_resources=overwrite_resources,
default_resources=default_resources,
dryrun=dryrun,
touch=touch,
printreason=printreason,
printshellcmds=printshellcmds,
debug_dag=debug_dag,
nocolor=nocolor,
quiet=quiet,
keepgoing=keepgoing,
cluster=cluster,
cluster_sync=cluster_sync,
drmaa=drmaa,
drmaa_log_dir=drmaa_log_dir,
jobname=jobname,
immediate_submit=immediate_submit,
standalone=standalone,
ignore_ambiguity=ignore_ambiguity,
restart_times=restart_times,
attempt=attempt,
lock=lock,
unlock=unlock,
cleanup_metadata=cleanup_metadata,
conda_cleanup_envs=conda_cleanup_envs,
cleanup_shadow=cleanup_shadow,
cleanup_scripts=cleanup_scripts,
force_incomplete=force_incomplete,
force_params_changed=force_params_changed,
ignore_incomplete=ignore_incomplete,
latency_wait=latency_wait,
verbose=verbose,
notemp=notemp,
all_temp=all_temp,
keep_remote_local=keep_remote_local,
nodeps=nodeps,
jobscript=jobscript,
greediness=greediness,
no_hooks=no_hooks,
overwrite_shellcmd=overwrite_shellcmd,
config=config,
config_args=config_args,
cluster_config=cluster_config,
keep_logger=True,
force_use_threads=use_threads,
use_conda=use_conda,
use_singularity=use_singularity,
use_env_modules=use_env_modules,
conda_prefix=conda_prefix,
conda_cleanup_pkgs=conda_cleanup_pkgs,
conda_frontend=conda_frontend,
singularity_prefix=singularity_prefix,
shadow_prefix=shadow_prefix,
singularity_args=singularity_args,
scheduler=scheduler,
scheduler_ilp_solver=scheduler_ilp_solver,
list_conda_envs=list_conda_envs,
kubernetes=kubernetes,
container_image=container_image,
conda_create_envs_only=conda_create_envs_only,
default_remote_provider=default_remote_provider,
default_remote_prefix=default_remote_prefix,
tibanna=tibanna,
tibanna_sfn=tibanna_sfn,
google_lifesciences=google_lifesciences,
google_lifesciences_regions=google_lifesciences_regions,
google_lifesciences_location=google_lifesciences_location,
google_lifesciences_cache=google_lifesciences_cache,
tes=tes,
precommand=precommand,
preemption_default=preemption_default,
preemptible_rules=preemptible_rules,
tibanna_config=tibanna_config,
assume_shared_fs=assume_shared_fs,
cluster_status=cluster_status,
max_jobs_per_second=max_jobs_per_second,
max_status_checks_per_second=max_status_checks_per_second,
overwrite_groups=overwrite_groups,
group_components=group_components,
max_inventory_wait_time=max_inventory_wait_time,
conda_not_block_search_path_envvars=conda_not_block_search_path_envvars,
)
success = workflow.execute(
targets=targets,
dryrun=dryrun,
generate_unit_tests=generate_unit_tests,
touch=touch,
scheduler_type=scheduler,
scheduler_ilp_solver=scheduler_ilp_solver,
local_cores=local_cores,
forcetargets=forcetargets,
forceall=forceall,
forcerun=forcerun,
prioritytargets=prioritytargets,
until=until,
omit_from=omit_from,
quiet=quiet,
keepgoing=keepgoing,
printshellcmds=printshellcmds,
printreason=printreason,
printrulegraph=printrulegraph,
printfilegraph=printfilegraph,
printdag=printdag,
cluster=cluster,
cluster_sync=cluster_sync,
jobname=jobname,
drmaa=drmaa,
drmaa_log_dir=drmaa_log_dir,
kubernetes=kubernetes,
container_image=container_image,
tibanna=tibanna,
tibanna_sfn=tibanna_sfn,
google_lifesciences=google_lifesciences,
google_lifesciences_regions=google_lifesciences_regions,
google_lifesciences_location=google_lifesciences_location,
google_lifesciences_cache=google_lifesciences_cache,
tes=tes,
precommand=precommand,
preemption_default=preemption_default,
preemptible_rules=preemptible_rules,
tibanna_config=tibanna_config,
max_jobs_per_second=max_jobs_per_second,
max_status_checks_per_second=max_status_checks_per_second,
printd3dag=printd3dag,
immediate_submit=immediate_submit,
ignore_ambiguity=ignore_ambiguity,
stats=stats,
force_incomplete=force_incomplete,
force_params_changed=force_params_changed,
ignore_incomplete=ignore_incomplete,
list_version_changes=list_version_changes,
list_code_changes=list_code_changes,
list_input_changes=list_input_changes,
list_params_changes=list_params_changes,
list_untracked=list_untracked,
list_conda_envs=list_conda_envs,
summary=summary,
archive=archive,
delete_all_output=delete_all_output,
delete_temp_output=delete_temp_output,
latency_wait=latency_wait,
wait_for_files=wait_for_files,
detailed_summary=detailed_summary,
nolock=not lock,
unlock=unlock,
notemp=notemp,
keep_remote_local=keep_remote_local,
nodeps=nodeps,
keep_target_files=keep_target_files,
cleanup_metadata=cleanup_metadata,
conda_cleanup_envs=conda_cleanup_envs,
cleanup_shadow=cleanup_shadow,
cleanup_scripts=cleanup_scripts,
subsnakemake=subsnakemake,
updated_files=updated_files,
allowed_rules=allowed_rules,
greediness=greediness,
no_hooks=no_hooks,
force_use_threads=use_threads,
conda_create_envs_only=conda_create_envs_only,
assume_shared_fs=assume_shared_fs,
cluster_status=cluster_status,
report=report,
report_stylesheet=report_stylesheet,
export_cwl=export_cwl,
batch=batch,
keepincomplete=keep_incomplete,
keepmetadata=keep_metadata,
)
except BrokenPipeError:
# ignore this exception and stop. It occurs if snakemake output is piped into less and less quits before reading the whole output.
# in such a case, snakemake shall stop scheduling and quit with error 1
success = False
except (Exception, BaseException) as ex:
if "workflow" in locals():
print_exception(ex, workflow.linemaps)
else:
print_exception(ex, dict())
success = False
if workdir:
os.chdir(olddir)
if "workflow" in locals() and workflow.persistence:
workflow.persistence.unlock()
if not keep_logger:
logger.cleanup()
return success
def parse_set_threads(args):
return parse_set_ints(
args.set_threads,
"Invalid threads definition: entries have to be defined as RULE=THREADS pairs "
"(with THREADS being a positive integer).",
)
def parse_set_resources(args):
errmsg = (
"Invalid resource definition: entries have to be defined as RULE:RESOURCE=VALUE, with "
"VALUE being a positive integer or a string."
)
assignments = dict()
if args.set_resources is not None:
for entry in args.set_resources:
key, value = parse_key_value_arg(entry, errmsg=errmsg)
key = key.split(":")
if not len(key) == 2:
raise ValueError(errmsg)
rule, resource = key
try:
value = int(value)
except ValueError:
assignments[rule][resource] = value
continue
if value < 0:
raise ValueError(errmsg)
assignments[rule][resource] = value
return assignments
def parse_set_scatter(args):
return parse_set_ints(
args.set_scatter,
"Invalid scatter definition: entries have to be defined as NAME=SCATTERITEMS pairs "
"(with SCATTERITEMS being a positive integer).",
)
def parse_set_ints(arg, errmsg):
assignments = dict()
if arg is not None:
for entry in arg:
key, value = parse_key_value_arg(entry, errmsg=errmsg)
try:
value = int(value)
except ValueError:
raise ValueError(errmsg)
if value < 0:
raise ValueError(errmsg)
assignments[key] = value
return assignments
def parse_batch(args):
errmsg = "Invalid batch definition: batch entry has to be defined as RULE=BATCH/BATCHES (with integers BATCH <= BATCHES, BATCH >= 1)."
if args.batch is not None:
rule, batchdef = parse_key_value_arg(args.batch, errmsg=errmsg)
try:
batch, batches = batchdef.split("/")
batch = int(batch)
batches = int(batches)
except ValueError:
raise ValueError(errmsg)
if batch > batches or batch < 1:
raise ValueError(errmsg)
return Batch(rule, batch, batches)
return None
def parse_groups(args):
errmsg = "Invalid groups definition: entries have to be defined as RULE=GROUP pairs"
overwrite_groups = dict()
if args.groups is not None:
for entry in args.groups:
rule, group = parse_key_value_arg(entry, errmsg=errmsg)
overwrite_groups[rule] = group
return overwrite_groups
def parse_group_components(args):
errmsg = "Invalid group components definition: entries have to be defined as GROUP=COMPONENTS pairs (with COMPONENTS being a positive integer)"
group_components = dict()
if args.group_components is not None:
for entry in args.group_components:
group, count = parse_key_value_arg(entry, errmsg=errmsg)
try:
count = int(count)
except ValueError:
raise ValueError(errmsg)
if count <= 0:
raise ValueError(errmsg)
group_components[group] = count
return group_components
def parse_key_value_arg(arg, errmsg):
try:
key, val = arg.split("=", 1)
except ValueError:
raise ValueError(errmsg + " Unparseable value: %r." % arg)
return key, val
def _bool_parser(value):
if value == "True":
return True
elif value == "False":
return False
raise ValueError
def parse_config(args):
"""Parse config from args."""
import yaml
yaml_base_load = lambda s: yaml.load(s, Loader=yaml.loader.BaseLoader)
parsers = [int, float, _bool_parser, yaml_base_load, str]
config = dict()
if args.config is not None:
valid = re.compile(r"[a-zA-Z_]\w*$")
for entry in args.config:
key, val = parse_key_value_arg(
entry,
errmsg="Invalid config definition: Config entries have to be defined as name=value pairs.",
)
if not valid.match(key):
raise ValueError(
"Invalid config definition: Config entry must start with a valid identifier."
)
v = None
for parser in parsers:
try:
v = parser(val)
# avoid accidental interpretation as function
if not callable(v):
break
except:
pass
assert v is not None
config[key] = v
return config
def unparse_config(config):
if not isinstance(config, dict):
raise ValueError("config is not a dict")
items = []
for key, value in config.items():
if isinstance(value, dict):
raise ValueError("config may only be a flat dict")
encoded = "'{}'".format(value) if isinstance(value, str) else value
items.append("{}={}".format(key, encoded))
return items
def get_profile_file(profile, file, return_default=False):
dirs = get_appdirs()
if os.path.exists(profile):
search_dirs = [os.path.dirname(profile)]
profile = os.path.basename(profile)
else:
search_dirs = [os.getcwd(), dirs.user_config_dir, dirs.site_config_dir]
get_path = lambda d: os.path.join(d, profile, file)
for d in search_dirs:
p = get_path(d)
# "file" can actually be a full command. If so, `p` won't exist as the
# below would check if e.g. '/path/to/profile/script --arg1 val --arg2'
# exists. To fix this, we use shlex.split() to get the path to the
# script. We check for both, in case the path contains spaces or some
# other thing that would cause shlex.split() to mangle the path
# inaccurately.
if os.path.exists(p) or os.path.exists(shlex.split(p)[0]):
return p
if return_default:
return file
return None
def get_argument_parser(profile=None):
"""Generate and return argument parser."""
import configargparse
from configargparse import YAMLConfigFileParser
dirs = get_appdirs()
config_files = []
if profile:
if profile == "":