def setUp(self):
super(DataRetrieverServiceIntTest, self).setUp()
self._start_container()
self.container.start_rel_from_url('res/deploy/r2dm.yml')
self.couch = self.container.datastore_manager.get_datastore(
'test_data_retriever', profile=DataStore.DS_PROFILE.SCIDATA)
self.datastore_name = 'test_data_retriever'
self.dr_cli = DataRetrieverServiceClient(node=self.container.node)
self.dsm_cli = DatasetManagementServiceClient(node=self.container.node)
self.rr_cli = ResourceRegistryServiceClient(node=self.container.node)
self.ps_cli = PubsubManagementServiceClient(node=self.container.node)
self.tms_cli = TransformManagementServiceClient(
node=self.container.node)
self.pd_cli = ProcessDispatcherServiceClient(node=self.container.node)
xs_dot_xp = CFG.core_xps.science_data
try:
self.XS, xp_base = xs_dot_xp.split('.')
self.XP = '.'.join([bootstrap.get_sys_name(), xp_base])
except ValueError:
raise StandardError(
'Invalid CFG for core_xps.science_data: "%s"; must have "xs.xp" structure'
% xs_dot_xp)
self.thread_pool = list()
def setUp(self):
# Start container
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
# Now create client to DataProductManagementService
self.rrclient = ResourceRegistryServiceClient(node=self.container.node)
self.damsclient = DataAcquisitionManagementServiceClient(
node=self.container.node)
self.pubsubcli = PubsubManagementServiceClient(
node=self.container.node)
self.imsclient = InstrumentManagementServiceClient(
node=self.container.node)
self.dpclient = DataProductManagementServiceClient(
node=self.container.node)
self.datasetclient = DatasetManagementServiceClient(
node=self.container.node)
self.processdispatchclient = ProcessDispatcherServiceClient(
node=self.container.node)
self.dataprocessclient = DataProcessManagementServiceClient(
node=self.container.node)
self.dataproductclient = DataProductManagementServiceClient(
node=self.container.node)
self.dataretrieverclient = DataRetrieverServiceClient(
node=self.container.node)
self.dataset_management = DatasetManagementServiceClient()
#setup listerner vars
self._data_greenlets = []
self._no_samples = None
self._samples_received = []
self.event_publisher = EventPublisher()
def setUp(self):
# Start container
super(TestActivateRSNVel3DInstrument, self).setUp()
config = DotDict()
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml', config)
# Now create client to DataProductManagementService
self.rrclient = ResourceRegistryServiceClient(node=self.container.node)
self.damsclient = DataAcquisitionManagementServiceClient(
node=self.container.node)
self.pubsubcli = PubsubManagementServiceClient(
node=self.container.node)
self.imsclient = InstrumentManagementServiceClient(
node=self.container.node)
self.dpclient = DataProductManagementServiceClient(
node=self.container.node)
self.datasetclient = DatasetManagementServiceClient(
node=self.container.node)
self.processdispatchclient = ProcessDispatcherServiceClient(
node=self.container.node)
self.dataprocessclient = DataProcessManagementServiceClient(
node=self.container.node)
self.dataproductclient = DataProductManagementServiceClient(
node=self.container.node)
self.dataretrieverclient = DataRetrieverServiceClient(
node=self.container.node)
self.dataset_management = DatasetManagementServiceClient()
def setUp(self):
# Start container
#print 'instantiating container'
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.dpsc_cli = DataProductManagementServiceClient()
self.rrclient = ResourceRegistryServiceClient()
self.damsclient = DataAcquisitionManagementServiceClient()
self.pubsubcli = PubsubManagementServiceClient()
self.ingestclient = IngestionManagementServiceClient()
self.process_dispatcher = ProcessDispatcherServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.unsc = UserNotificationServiceClient()
self.data_retriever = DataRetrieverServiceClient()
#------------------------------------------
# Create the environment
#------------------------------------------
datastore_name = CACHE_DATASTORE_NAME
self.db = self.container.datastore_manager.get_datastore(
datastore_name)
self.stream_def_id = self.pubsubcli.create_stream_definition(
name='SBE37_CDM')
self.process_definitions = {}
ingestion_worker_definition = ProcessDefinition(
name='ingestion worker')
ingestion_worker_definition.executable = {
'module':
'ion.processes.data.ingestion.science_granule_ingestion_worker',
'class': 'ScienceGranuleIngestionWorker'
}
process_definition_id = self.process_dispatcher.create_process_definition(
process_definition=ingestion_worker_definition)
self.process_definitions['ingestion_worker'] = process_definition_id
self.pids = []
self.exchange_points = []
self.exchange_names = []
#------------------------------------------------------------------------------------------------
# First launch the ingestors
#------------------------------------------------------------------------------------------------
self.exchange_space = 'science_granule_ingestion'
self.exchange_point = 'science_data'
config = DotDict()
config.process.datastore_name = 'datasets'
config.process.queue_name = self.exchange_space
self.exchange_names.append(self.exchange_space)
self.exchange_points.append(self.exchange_point)
pid = self.process_dispatcher.schedule_process(
self.process_definitions['ingestion_worker'], configuration=config)
log.debug("the ingestion worker process id: %s", pid)
self.pids.append(pid)
def setUp(self):
# Start container
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
# Now create client to DataAcquisitionManagementService
self.client = DataAcquisitionManagementServiceClient(node=self.container.node)
self.rrclient = ResourceRegistryServiceClient(node=self.container.node)
self.dataproductclient = DataProductManagementServiceClient(node=self.container.node)
self.dams_client = DataAcquisitionManagementServiceClient(node=self.container.node)
self.pubsub_client = PubsubManagementServiceClient(node=self.container.node)
self.processdispatchclient = ProcessDispatcherServiceClient(node=self.container.node)
self.data_retriever = DataRetrieverServiceClient(node=self.container.node)
self._container_client = ContainerAgentClient(node=self.container.node, name=self.container.name)
# Data async and subscription TODO: Replace with new subscriber
self._finished_count = None
#TODO: Switch to gevent.queue.Queue
self._async_finished_result = AsyncResult()
self._finished_events_received = []
self._finished_event_subscriber = None
self._start_finished_event_subscriber()
self.addCleanup(self._stop_finished_event_subscriber)
self.DVR_CONFIG = {}
self.DVR_CONFIG = {
'dvr_mod' : 'ion.agents.data.handlers.slocum_data_handler',
'dvr_cls' : 'SlocumDataHandler',
}
self._setup_resources()
self.agent_config = {
'driver_config' : self.DVR_CONFIG,
'stream_config' : {},
'agent' : {'resource_id': self.EDA_RESOURCE_ID},
'test_mode' : True
}
datasetagent_instance_obj = IonObject(RT.ExternalDatasetAgentInstance, name='ExternalDatasetAgentInstance1', description='external data agent instance',
handler_module=self.EDA_MOD, handler_class=self.EDA_CLS,
dataset_driver_config=self.DVR_CONFIG, dataset_agent_config=self.agent_config )
self.dataset_agent_instance_id = self.dams_client.create_external_dataset_agent_instance(external_dataset_agent_instance=datasetagent_instance_obj,
external_dataset_agent_id=self.datasetagent_id, external_dataset_id=self.EDA_RESOURCE_ID)
#TG: Setup/configure the granule logger to log granules as they're published
pid = self.dams_client.start_external_dataset_agent_instance(self.dataset_agent_instance_id)
dataset_agent_instance_obj= self.dams_client.read_external_dataset_agent_instance(self.dataset_agent_instance_id)
print 'TestBulkIngest: Dataset agent instance obj: = ', dataset_agent_instance_obj
# Start a resource agent client to talk with the instrument agent.
self._ia_client = ResourceAgentClient('datasetagentclient', name=pid, process=FakeProcess())
log.debug(" test_createTransformsThenActivateInstrument:: got ia client %s", str(self._ia_client))
def setUp(self):
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.pubsub_management = PubsubManagementServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.data_product_management = DataProductManagementServiceClient()
self.data_acquisition_management = DataAcquisitionManagementServiceClient()
self.data_retriever = DataRetrieverServiceClient()
self.process_dispatch_client = ProcessDispatcherServiceClient(node=self.container.node)
self.resource_registry = self.container.resource_registry
self.context_ids = self.build_param_contexts()
self.setup_resources()
def assert_raw_granules_ingested(self, count, payload_size):
#--------------------------------------------------------------------------------
# Test the slicing capabilities
#--------------------------------------------------------------------------------
data_retriever = DataRetrieverServiceClient()
for i in range(0, count - 1):
granule = data_retriever.retrieve(dataset_id=self._raw_dataset_id,
query={'tdoa': slice(i, i + 1)})
rdt = RecordDictionaryTool.load_from_granule(granule)
log.info("Granule index: %d, time: %s, size: %s", i,
rdt['time'][0], len(rdt['raw'][0]))
self.assertEqual(payload_size, len(rdt['raw'][0]))
def setUp(self): # Love the non pep-8 convention
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.process_dispatcher = ProcessDispatcherServiceClient()
self.pubsub_management = PubsubManagementServiceClient()
self.resource_registry = ResourceRegistryServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.ingestion_management = IngestionManagementServiceClient()
self.data_retriever = DataRetrieverServiceClient()
self.event = Event()
self.exchange_space_name = 'test_granules'
self.exchange_point_name = 'science_data'
self.i = 0
self.cci = 0
def setUp(self):
# Start container
#print 'instantiating container'
self._start_container()
log.debug("Start rel from url")
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.DPMS = DataProductManagementServiceClient()
self.RR = ResourceRegistryServiceClient()
self.RR2 = EnhancedResourceRegistryClient(self.RR)
self.DAMS = DataAcquisitionManagementServiceClient()
self.PSMS = PubsubManagementServiceClient()
self.ingestclient = IngestionManagementServiceClient()
self.PD = ProcessDispatcherServiceClient()
self.DSMS = DatasetManagementServiceClient()
self.unsc = UserNotificationServiceClient()
self.data_retriever = DataRetrieverServiceClient()
#------------------------------------------
# Create the environment
#------------------------------------------
log.debug("get datastore")
datastore_name = CACHE_DATASTORE_NAME
self.db = self.container.datastore_manager.get_datastore(
datastore_name)
self.stream_def_id = self.PSMS.create_stream_definition(
name='SBE37_CDM')
self.process_definitions = {}
ingestion_worker_definition = ProcessDefinition(
name='ingestion worker')
ingestion_worker_definition.executable = {
'module':
'ion.processes.data.ingestion.science_granule_ingestion_worker',
'class': 'ScienceGranuleIngestionWorker'
}
process_definition_id = self.PD.create_process_definition(
process_definition=ingestion_worker_definition)
self.process_definitions['ingestion_worker'] = process_definition_id
self.pids = []
self.exchange_points = []
self.exchange_names = []
self.addCleanup(self.cleaning_up)
def setUp(self):
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.resource_registry = self.container.resource_registry
self.RR2 = EnhancedResourceRegistryClient(self.resource_registry)
self.data_acquisition_management = DataAcquisitionManagementServiceClient()
self.pubsub_management = PubsubManagementServiceClient()
self.instrument_management = InstrumentManagementServiceClient()
self.data_product_management = DataProductManagementServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.process_dispatcher = ProcessDispatcherServiceClient()
self.data_process_management = DataProcessManagementServiceClient()
self.data_product_management = DataProductManagementServiceClient()
self.data_retriever = DataRetrieverServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.user_notification = UserNotificationServiceClient()
self.workflow_management = WorkflowManagementServiceClient()
self.visualization = VisualizationServiceClient()
def setUp(self):
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.RR = ResourceRegistryServiceClient()
self.RR2 = EnhancedResourceRegistryClient(self.RR)
self.OMS = ObservatoryManagementServiceClient()
self.org_management_service = OrgManagementServiceClient()
self.IMS = InstrumentManagementServiceClient()
self.dpclient = DataProductManagementServiceClient()
self.pubsubcli = PubsubManagementServiceClient()
self.damsclient = DataAcquisitionManagementServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.data_retriever = DataRetrieverServiceClient()
self.data_product_management = DataProductManagementServiceClient()
self._load_stage = 0
self._resources = {}
def setUp(self):
self.i = 0
self._start_container()
self.container.start_rel_from_url('res/deploy/r2params.yml')
self.dataset_management = DatasetManagementServiceClient()
self.pubsub_management = PubsubManagementServiceClient()
self.data_product_management = DataProductManagementServiceClient()
self.resource_registry = self.container.resource_registry
self.data_retriever = DataRetrieverServiceClient()
pdicts, _ = self.resource_registry.find_resources(
restype='ParameterDictionary', id_only=False)
self.dp_ids = []
for pdict in pdicts:
stream_def_id = self.pubsub_management.create_stream_definition(
pdict.name, parameter_dictionary_id=pdict._id)
dp_id = self.make_dp(stream_def_id)
if dp_id: self.dp_ids.append(dp_id)
def setUp(self):
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
self.resource_registry = self.container.resource_registry
self.RR2 = EnhancedResourceRegistryClient(self.resource_registry)
self.data_acquisition_management = DataAcquisitionManagementServiceClient()
self.pubsub_management = PubsubManagementServiceClient()
self.instrument_management = InstrumentManagementServiceClient()
self.discovery = DiscoveryServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.process_dispatcher = ProcessDispatcherServiceClient()
self.data_process_management = DataProcessManagementServiceClient()
self.data_product_management = DataProductManagementServiceClient()
self.data_retriever = DataRetrieverServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.user_notification = UserNotificationServiceClient()
self.observatory_management = ObservatoryManagementServiceClient()
self.visualization = VisualizationServiceClient()
self.ph = ParameterHelper(self.dataset_management, self.addCleanup)
self.ctd_count = 0
def setUp(self):
# Start container
super(TestActivateInstrumentIntegration, self).setUp()
config = DotDict()
config.bootstrap.use_es = True
self._start_container()
self.addCleanup(TestActivateInstrumentIntegration.es_cleanup)
self.container.start_rel_from_url('res/deploy/r2deploy.yml', config)
# Now create client to DataProductManagementService
self.rrclient = ResourceRegistryServiceClient(node=self.container.node)
self.damsclient = DataAcquisitionManagementServiceClient(
node=self.container.node)
self.pubsubcli = PubsubManagementServiceClient(
node=self.container.node)
self.imsclient = InstrumentManagementServiceClient(
node=self.container.node)
self.dpclient = DataProductManagementServiceClient(
node=self.container.node)
self.datasetclient = DatasetManagementServiceClient(
node=self.container.node)
self.processdispatchclient = ProcessDispatcherServiceClient(
node=self.container.node)
self.dataprocessclient = DataProcessManagementServiceClient(
node=self.container.node)
self.dataproductclient = DataProductManagementServiceClient(
node=self.container.node)
self.dataretrieverclient = DataRetrieverServiceClient(
node=self.container.node)
self.dataset_management = DatasetManagementServiceClient()
self.usernotificationclient = UserNotificationServiceClient()
#setup listerner vars
self._data_greenlets = []
self._no_samples = None
self._samples_received = []
self.event_publisher = EventPublisher()
def setUp(self):
# Start container
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
# Now create client to DataProductManagementService
self.rrclient = ResourceRegistryServiceClient(node=self.container.node)
self.damsclient = DataAcquisitionManagementServiceClient(
node=self.container.node)
self.pubsubcli = PubsubManagementServiceClient(
node=self.container.node)
self.imsclient = InstrumentManagementServiceClient(
node=self.container.node)
self.dpclient = DataProductManagementServiceClient(
node=self.container.node)
self.datasetclient = DatasetManagementServiceClient(
node=self.container.node)
self.processdispatchclient = ProcessDispatcherServiceClient(
node=self.container.node)
self.dataprocessclient = DataProcessManagementServiceClient(
node=self.container.node)
self.dataproductclient = DataProductManagementServiceClient(
node=self.container.node)
self.dataretrieverclient = DataRetrieverServiceClient(
node=self.container.node)
self.dataset_management = DatasetManagementServiceClient()
#setup listerner vars
self._data_greenlets = []
self._no_samples = None
self._samples_received = []
self.event_publisher = EventPublisher()
self.egg_url_good = "http://sddevrepo.oceanobservatories.org/releases/seabird_sbe37smb_ooicore-0.0.1a-py2.7.egg"
self.egg_url_bad = "http://sddevrepo.oceanobservatories.org/releases/seabird_sbe37smb_ooicore-0.1a-py2.7.egg"
self.egg_url_404 = "http://sddevrepo.oceanobservatories.org/releases/completely_made_up_404.egg"
def setUp(self):
super(DataRetrieverIntTest, self).setUp()
self._start_container()
self.container.start_rel_from_url('res/deploy/r2dm.yml')
self.datastore_name = 'test_datasets'
self.datastore = self.container.datastore_manager.get_datastore(
self.datastore_name, profile=DataStore.DS_PROFILE.SCIDATA)
self.data_retriever = DataRetrieverServiceClient()
self.dataset_management = DatasetManagementServiceClient()
self.resource_registry = ResourceRegistryServiceClient()
self.pubsub_management = PubsubManagementServiceClient()
xs_dot_xp = CFG.core_xps.science_data
try:
self.XS, xp_base = xs_dot_xp.split('.')
self.XP = '.'.join([get_sys_name(), xp_base])
except ValueError:
raise StandardError(
'Invalid CFG for core_xps.science_data: "%s"; must have "xs.xp" structure'
% xs_dot_xp)
def test_replay_integration(self):
'''
test_replay_integration
'''
import numpy as np
# Keep the import it's used in the vector comparison below even though pycharm says its unused.
cc = self.container
XP = self.XP
assertions = self.assertTrue
### Every thing below here can be run as a script:
log.debug('Got it')
pubsub_management_service = PubsubManagementServiceClient(node=cc.node)
ingestion_management_service = IngestionManagementServiceClient(
node=cc.node)
dataset_management_service = DatasetManagementServiceClient(
node=cc.node)
data_retriever_service = DataRetrieverServiceClient(node=cc.node)
datastore_name = 'dm_test_replay_integration'
producer = Publisher(name=(XP, 'stream producer'))
ingestion_configuration_id = ingestion_management_service.create_ingestion_configuration(
exchange_point_id=XP,
couch_storage=CouchStorage(datastore_name=datastore_name,
datastore_profile='SCIDATA'),
hdf_storage=HdfStorage(),
number_of_workers=1)
ingestion_management_service.activate_ingestion_configuration(
ingestion_configuration_id=ingestion_configuration_id)
definition = SBE37_CDM_stream_definition()
data_stream_id = definition.data_stream_id
encoding_id = definition.identifiables[data_stream_id].encoding_id
element_count_id = definition.identifiables[
data_stream_id].element_count_id
stream_def_id = pubsub_management_service.create_stream_definition(
container=definition)
stream_id = pubsub_management_service.create_stream(
stream_definition_id=stream_def_id)
dataset_id = dataset_management_service.create_dataset(
stream_id=stream_id,
datastore_name=datastore_name,
view_name='datasets/dataset_by_id')
ingestion_management_service.create_dataset_configuration(
dataset_id=dataset_id,
archive_data=True,
archive_metadata=True,
ingestion_configuration_id=ingestion_configuration_id)
definition.stream_resource_id = stream_id
packet = _create_packet(definition)
input_file = FileSystem.mktemp()
input_file.write(packet.identifiables[data_stream_id].values)
input_file_path = input_file.name
input_file.close()
fields = [
'conductivity', 'height', 'latitude', 'longitude', 'pressure',
'temperature', 'time'
]
input_vectors = acquire_data([input_file_path], fields, 2).next()
producer.publish(msg=packet, to_name=(XP, '%s.data' % stream_id))
replay_id, replay_stream_id = data_retriever_service.define_replay(
dataset_id)
ar = gevent.event.AsyncResult()
def sub_listen(msg, headers):
assertions(isinstance(msg, StreamGranuleContainer),
'replayed message is not a granule.')
hdf_string = msg.identifiables[data_stream_id].values
sha1 = hashlib.sha1(hdf_string).hexdigest().upper()
assertions(sha1 == msg.identifiables[encoding_id].sha1,
'Checksum failed.')
assertions(
msg.identifiables[element_count_id].value == 1,
'record replay count is incorrect %d.' %
msg.identifiables[element_count_id].value)
output_file = FileSystem.mktemp()
output_file.write(msg.identifiables[data_stream_id].values)
output_file_path = output_file.name
output_file.close()
output_vectors = acquire_data([output_file_path], fields, 2).next()
for field in fields:
comparison = (input_vectors[field]['values'] ==
output_vectors[field]['values'])
assertions(
comparison.all(), 'vector mismatch: %s vs %s' %
(input_vectors[field]['values'],
output_vectors[field]['values']))
FileSystem.unlink(output_file_path)
ar.set(True)
subscriber = Subscriber(name=(XP, 'replay listener'),
callback=sub_listen)
g = gevent.Greenlet(subscriber.listen,
binding='%s.data' % replay_stream_id)
g.start()
data_retriever_service.start_replay(replay_id)
ar.get(timeout=10)
FileSystem.unlink(input_file_path)
def test_dm_integration(self):
'''
test_salinity_transform
Test full DM Services Integration
'''
cc = self.container
assertions = self.assertTrue
#-----------------------------
# Copy below here to run as a script (don't forget the imports of course!)
#-----------------------------
# Create some service clients...
pubsub_management_service = PubsubManagementServiceClient(node=cc.node)
ingestion_management_service = IngestionManagementServiceClient(
node=cc.node)
dataset_management_service = DatasetManagementServiceClient(
node=cc.node)
data_retriever_service = DataRetrieverServiceClient(node=cc.node)
transform_management_service = TransformManagementServiceClient(
node=cc.node)
process_dispatcher = ProcessDispatcherServiceClient(node=cc.node)
# declare some handy variables
datastore_name = 'test_dm_integration'
###
### In the beginning there were two stream definitions...
###
# create a stream definition for the data from the ctd simulator
ctd_stream_def = SBE37_CDM_stream_definition()
ctd_stream_def_id = pubsub_management_service.create_stream_definition(
container=ctd_stream_def, name='Simulated CTD data')
# create a stream definition for the data from the salinity Transform
sal_stream_def_id = pubsub_management_service.create_stream_definition(
container=SalinityTransform.outgoing_stream_def,
name='Scalar Salinity data stream')
###
### And two process definitions...
###
# one for the ctd simulator...
producer_definition = ProcessDefinition()
producer_definition.executable = {
'module': 'ion.processes.data.ctd_stream_publisher',
'class': 'SimpleCtdPublisher'
}
ctd_sim_procdef_id = process_dispatcher.create_process_definition(
process_definition=producer_definition)
# one for the salinity transform
producer_definition = ProcessDefinition()
producer_definition.executable = {
'module': 'ion.processes.data.transforms.ctd.ctd_L2_salinity',
'class': 'SalinityTransform'
}
salinity_transform_procdef_id = process_dispatcher.create_process_definition(
process_definition=producer_definition)
#---------------------------
# Set up ingestion - this is an operator concern - not done by SA in a deployed system
#---------------------------
# Configure ingestion using eight workers, ingesting to test_dm_integration datastore with the SCIDATA profile
log.debug('Calling create_ingestion_configuration')
ingestion_configuration_id = ingestion_management_service.create_ingestion_configuration(
exchange_point_id='science_data',
couch_storage=CouchStorage(datastore_name=datastore_name,
datastore_profile='SCIDATA'),
number_of_workers=1)
#
ingestion_management_service.activate_ingestion_configuration(
ingestion_configuration_id=ingestion_configuration_id)
#---------------------------
# Set up the producer (CTD Simulator)
#---------------------------
# Create the stream
ctd_stream_id = pubsub_management_service.create_stream(
stream_definition_id=ctd_stream_def_id)
# Set up the datasets
ctd_dataset_id = dataset_management_service.create_dataset(
stream_id=ctd_stream_id,
datastore_name=datastore_name,
view_name='datasets/stream_join_granule')
# Configure ingestion of this dataset
ctd_dataset_config_id = ingestion_management_service.create_dataset_configuration(
dataset_id=ctd_dataset_id,
archive_data=True,
archive_metadata=True,
ingestion_configuration_id=
ingestion_configuration_id, # you need to know the ingestion configuration id!
)
# Hold onto ctd_dataset_config_id if you want to stop/start ingestion of that dataset by the ingestion service
#---------------------------
# Set up the salinity transform
#---------------------------
# Create the stream
sal_stream_id = pubsub_management_service.create_stream(
stream_definition_id=sal_stream_def_id)
# Set up the datasets
sal_dataset_id = dataset_management_service.create_dataset(
stream_id=sal_stream_id,
datastore_name=datastore_name,
view_name='datasets/stream_join_granule')
# Configure ingestion of the salinity as a dataset
sal_dataset_config_id = ingestion_management_service.create_dataset_configuration(
dataset_id=sal_dataset_id,
archive_data=True,
archive_metadata=True,
ingestion_configuration_id=
ingestion_configuration_id, # you need to know the ingestion configuration id!
)
# Hold onto sal_dataset_config_id if you want to stop/start ingestion of that dataset by the ingestion service
# Create a subscription as input to the transform
sal_transform_input_subscription_id = pubsub_management_service.create_subscription(
query=StreamQuery(stream_ids=[
ctd_stream_id,
]),
exchange_name='salinity_transform_input'
) # how do we make these names??? i.e. Should they be anonymous?
# create the salinity transform
sal_transform_id = transform_management_service.create_transform(
name='example salinity transform',
in_subscription_id=sal_transform_input_subscription_id,
out_streams={
'output': sal_stream_id,
},
process_definition_id=salinity_transform_procdef_id,
# no configuration needed at this time...
)
# start the transform - for a test case it makes sense to do it before starting the producer but it is not required
transform_management_service.activate_transform(
transform_id=sal_transform_id)
# Start the ctd simulator to produce some data
configuration = {
'process': {
'stream_id': ctd_stream_id,
}
}
ctd_sim_pid = process_dispatcher.schedule_process(
process_definition_id=ctd_sim_procdef_id,
configuration=configuration)
###
### Make a subscriber in the test to listen for salinity data
###
salinity_subscription_id = pubsub_management_service.create_subscription(
query=StreamQuery([
sal_stream_id,
]),
exchange_name='salinity_test',
name="test salinity subscription",
)
pid = cc.spawn_process(name='dummy_process_for_test',
module='pyon.ion.process',
cls='SimpleProcess',
config={})
dummy_process = cc.proc_manager.procs[pid]
subscriber_registrar = StreamSubscriberRegistrar(process=dummy_process,
node=cc.node)
result = gevent.event.AsyncResult()
results = []
def message_received(message, headers):
# Heads
log.warn('Salinity data received!')
results.append(message)
if len(results) > 3:
result.set(True)
subscriber = subscriber_registrar.create_subscriber(
exchange_name='salinity_test', callback=message_received)
subscriber.start()
# after the queue has been created it is safe to activate the subscription
pubsub_management_service.activate_subscription(
subscription_id=salinity_subscription_id)
# Assert that we have received data
assertions(result.get(timeout=10))
# stop the flow parse the messages...
process_dispatcher.cancel_process(
ctd_sim_pid
) # kill the ctd simulator process - that is enough data
for message in results:
psd = PointSupplementStreamParser(
stream_definition=SalinityTransform.outgoing_stream_def,
stream_granule=message)
# Test the handy info method for the names of fields in the stream def
assertions('salinity' in psd.list_field_names())
# you have to know the name of the coverage in stream def
salinity = psd.get_values('salinity')
import numpy
assertions(isinstance(salinity, numpy.ndarray))
assertions(numpy.nanmin(salinity) >
0.0) # salinity should always be greater than 0
def test_usgs_integration(self):
'''
test_usgs_integration
Test full DM Services Integration using usgs
'''
cc = self.container
assertions = self.assertTrue
#-----------------------------
# Copy below here
#-----------------------------
pubsub_management_service = PubsubManagementServiceClient(node=cc.node)
ingestion_management_service = IngestionManagementServiceClient(node=cc.node)
dataset_management_service = DatasetManagementServiceClient(node=cc.node)
data_retriever_service = DataRetrieverServiceClient(node=cc.node)
transform_management_service = TransformManagementServiceClient(node=cc.node)
process_dispatcher = ProcessDispatcherServiceClient(node=cc.node)
process_list = []
datasets = []
datastore_name = 'test_usgs_integration'
#---------------------------
# Set up ingestion
#---------------------------
# Configure ingestion using eight workers, ingesting to test_dm_integration datastore with the SCIDATA profile
log.debug('Calling create_ingestion_configuration')
ingestion_configuration_id = ingestion_management_service.create_ingestion_configuration(
exchange_point_id='science_data',
couch_storage=CouchStorage(datastore_name=datastore_name,datastore_profile='SCIDATA'),
number_of_workers=8
)
#
ingestion_management_service.activate_ingestion_configuration(
ingestion_configuration_id=ingestion_configuration_id)
usgs_stream_def = USGS_stream_definition()
stream_def_id = pubsub_management_service.create_stream_definition(container=usgs_stream_def, name='Junk definition')
#---------------------------
# Set up the producers (CTD Simulators)
#---------------------------
# Launch five simulated CTD producers
for iteration in xrange(2):
# Make a stream to output on
stream_id = pubsub_management_service.create_stream(stream_definition_id=stream_def_id)
#---------------------------
# Set up the datasets
#---------------------------
dataset_id = dataset_management_service.create_dataset(
stream_id=stream_id,
datastore_name=datastore_name,
view_name='datasets/stream_join_granule'
)
# Keep track of the datasets
datasets.append(dataset_id)
stream_policy_id = ingestion_management_service.create_dataset_configuration(
dataset_id = dataset_id,
archive_data = True,
archive_metadata = True,
ingestion_configuration_id = ingestion_configuration_id
)
producer_definition = ProcessDefinition()
producer_definition.executable = {
'module':'eoi.agent.handler.usgs_stream_publisher',
'class':'UsgsPublisher'
}
configuration = {
'process':{
'stream_id':stream_id,
}
}
procdef_id = process_dispatcher.create_process_definition(process_definition=producer_definition)
log.debug('LUKE_DEBUG: procdef_id: %s', procdef_id)
pid = process_dispatcher.schedule_process(process_definition_id=procdef_id, configuration=configuration)
# Keep track, we'll kill 'em later.
process_list.append(pid)
# Get about 4 seconds of data
time.sleep(4)
#---------------------------
# Stop producing data
#---------------------------
for process in process_list:
process_dispatcher.cancel_process(process)
#----------------------------------------------
# The replay and the transform, a love story.
#----------------------------------------------
# Happy Valentines to the clever coder who catches the above!
transform_definition = ProcessDefinition()
transform_definition.executable = {
'module':'ion.processes.data.transforms.transform_example',
'class':'TransformCapture'
}
transform_definition_id = process_dispatcher.create_process_definition(process_definition=transform_definition)
dataset_id = datasets.pop() # Just need one for now
replay_id, stream_id = data_retriever_service.define_replay(dataset_id=dataset_id)
#--------------------------------------------
# I'm Selling magazine subscriptions here!
#--------------------------------------------
subscription = pubsub_management_service.create_subscription(query=StreamQuery(stream_ids=[stream_id]),
exchange_name='transform_capture_point')
#--------------------------------------------
# Start the transform (capture)
#--------------------------------------------
transform_id = transform_management_service.create_transform(
name='capture_transform',
in_subscription_id=subscription,
process_definition_id=transform_definition_id
)
transform_management_service.activate_transform(transform_id=transform_id)
#--------------------------------------------
# BEGIN REPLAY!
#--------------------------------------------
data_retriever_service.start_replay(replay_id=replay_id)
#--------------------------------------------
# Lets get some boundaries
#--------------------------------------------
bounds = dataset_management_service.get_dataset_bounds(dataset_id=dataset_id)
