def handle(self, *args, **options):
if options["job_id"] is None:
logger.error("You must specify a job ID.")
return 1
try:
job_type = ProcessorPipeline[options["job_name"]]
except KeyError:
logger.error("You must specify a valid job name.")
return 1
if job_type is ProcessorPipeline.AFFY_TO_PCL:
affy_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.TRANSCRIPTOME_INDEX:
build_transcriptome_index(options["job_id"])
elif job_type is ProcessorPipeline.NO_OP:
no_op_processor(options["job_id"])
else:
logger.error(
("A valid job name was specified for job %s with id %d but "
"no processor function is known to run it."),
options["job_name"], options["job_id"])
return 1
return 0
def handle(self, *args, **options):
if options["job_id"] is None:
logger.error("You must specify a job ID.",
job_id=options["job_id"])
sys.exit(1)
try:
job_type = ProcessorPipeline[options["job_name"]]
except KeyError:
logger.error("You must specify a valid job name.",
job_name=options["job_name"],
job_id=options["job_id"])
sys.exit(1)
if job_type is ProcessorPipeline.AFFY_TO_PCL:
from data_refinery_workers.processors.array_express import affy_to_pcl
affy_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.TRANSCRIPTOME_INDEX_SHORT:
from data_refinery_workers.processors.transcriptome_index import build_transcriptome_index
build_transcriptome_index(options["job_id"], length="short")
elif job_type is ProcessorPipeline.TRANSCRIPTOME_INDEX_LONG:
from data_refinery_workers.processors.transcriptome_index import build_transcriptome_index
build_transcriptome_index(options["job_id"], length="long")
elif job_type is ProcessorPipeline.AGILENT_TWOCOLOR_TO_PCL:
from data_refinery_workers.processors.agilent_twocolor import agilent_twocolor_to_pcl
agilent_twocolor_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.ILLUMINA_TO_PCL:
from data_refinery_workers.processors.illumina import illumina_to_pcl
illumina_to_pcl(options["job_id"])
elif job_type is ProcessorPipeline.SALMON:
from data_refinery_workers.processors.salmon import salmon
salmon(options["job_id"])
elif job_type is ProcessorPipeline.SMASHER:
from data_refinery_workers.processors.smasher import smash
smash(options["job_id"])
elif job_type is ProcessorPipeline.NO_OP:
from data_refinery_workers.processors.no_op import no_op_processor
no_op_processor(options["job_id"])
elif job_type is ProcessorPipeline.JANITOR:
from data_refinery_workers.processors.janitor import run_janitor
run_janitor(options["job_id"])
elif job_type is ProcessorPipeline.QN_REFERENCE:
from data_refinery_workers.processors import qn_reference
qn_reference.create_qn_reference(options["job_id"])
else:
logger.error(
("A valid job name was specified for job %s with id %d but "
"no processor function is known to run it."),
options["job_name"], options["job_id"])
sys.exit(1)
sys.exit(0)
def test_tx(self):
""" """
# Make sure the work dirs don't exist cause this will fail the job.
shutil.rmtree(
"/home/user/data_store/raw/TEST/TRANSCRIPTOME_INDEX/"
"AEGILOPS_TAUSCHII/SHORT/processor_job_1",
ignore_errors=True,
)
shutil.rmtree(
"/home/user/data_store/raw/TEST/TRANSCRIPTOME_INDEX/"
"AEGILOPS_TAUSCHII/LONG/processor_job_2",
ignore_errors=True,
)
job1 = prepare_job("short")
job_context1 = transcriptome_index.build_transcriptome_index(
job1.pk, length="short", cleanup=False)
job1 = ProcessorJob.objects.get(id=job1.pk)
self.assertTrue(job1.success)
self.assertEqual(job_context1["length"], "short")
job2 = prepare_job("long")
job_context2 = transcriptome_index.build_transcriptome_index(
job2.pk, length="long", cleanup=False)
job2 = ProcessorJob.objects.get(id=job2.pk)
self.assertTrue(job2.success)
self.assertEqual(job_context2["length"], "long")
self.assertNotEqual(job_context1["output_dir"],
job_context2["output_dir"])
self.assertTrue(
os.path.exists(
job_context1["computed_file"].get_synced_file_path()))
self.assertTrue(
os.path.exists(
job_context2["computed_file"].get_synced_file_path()))
self.assertNotEqual(
job_context1["computed_file"].get_synced_file_path(),
job_context2["computed_file"].get_synced_file_path(),
)
# This is the same logic as in `salmon._find_index`
file = job_context1["computed_file"]
unpacked = "/".join(file.get_synced_file_path().split("/")[:-1])
self.assertTrue("SHORT" in unpacked)
file2 = job_context2["computed_file"]
unpacked2 = "/".join(file2.get_synced_file_path().split("/")[:-1])
self.assertTrue("LONG" in unpacked2)