def _start_output_stream_listener(self,
data_product_stream_ids,
message_count_per_stream=10):
cc = self.container
assertions = self.assertTrue
###
### Make a subscriber in the test to listen for transformed data
###
salinity_subscription_id = self.pubsubclient.create_subscription(
query=StreamQuery(data_product_stream_ids),
exchange_name='workflow_test',
name="test workflow transformations",
)
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(' data received!')
results.append(message)
if len(results) >= len(
data_product_stream_ids
) * message_count_per_stream: #Only wait for so many messages - per stream
result.set(True)
subscriber = subscriber_registrar.create_subscriber(
exchange_name='workflow_test', callback=message_received)
subscriber.start()
# after the queue has been created it is safe to activate the subscription
self.pubsubclient.activate_subscription(
subscription_id=salinity_subscription_id)
# Assert that we have received data
assertions(result.get(timeout=30))
self.pubsubclient.deactivate_subscription(
subscription_id=salinity_subscription_id)
subscriber.stop()
return results
def setUp(self):
self._start_container()
self.container.start_rel_from_url('res/deploy/r2dm.yml')
self.pubsub_cli = PubsubManagementServiceClient(node=self.container.node)
self.ctd_stream1_id = self.pubsub_cli.create_stream(name="SampleStream1",
description="Sample Stream 1 Description")
self.ctd_stream2_id = self.pubsub_cli.create_stream(name="SampleStream2",
description="Sample Stream 2 Description")
# Make a subscription to two input streams
exchange_name = "a_queue"
query = StreamQuery([self.ctd_stream1_id, self.ctd_stream2_id])
self.ctd_subscription_id = self.pubsub_cli.create_subscription(query,
exchange_name,
"SampleSubscription",
"Sample Subscription Description")
# Make a subscription to all streams on an exchange point
exchange_name = "another_queue"
query = ExchangeQuery()
self.exchange_subscription_id = self.pubsub_cli.create_subscription(query,
exchange_name,
"SampleExchangeSubscription",
"Sample Exchange Subscription Description")
pid = self.container.spawn_process(name='dummy_process_for_test',
module='pyon.ion.process',
cls='SimpleProcess',
config={})
dummy_process = self.container.proc_manager.procs[pid]
# Normally the user does not see or create the publisher, this is part of the containers business.
# For the test we need to set it up explicitly
publisher_registrar = StreamPublisherRegistrar(process=dummy_process, node=self.container.node)
self.ctd_stream1_publisher = publisher_registrar.create_publisher(stream_id=self.ctd_stream1_id)
self.ctd_stream2_publisher = publisher_registrar.create_publisher(stream_id=self.ctd_stream2_id)
# Cheat and use the cc as the process - I don't think it is used for anything...
self.stream_subscriber = StreamSubscriberRegistrar(process=dummy_process, node=self.container.node)
def _start_data_subscribers(self):
"""
"""
# Create a pubsub client to create streams.
pubsub_client = PubsubManagementServiceClient(node=self.container.node)
# A callback for processing subscribed-to data.
def consume_data(message, headers):
log.info('Subscriber received data message: %s.', str(message))
self._samples_received.append(message)
if self._no_samples and self._no_samples == len(self._samples_received):
self._async_data_result.set()
# Create a stream subscriber registrar to create subscribers.
subscriber_registrar = StreamSubscriberRegistrar(process=self.container,
node=self.container.node)
# Create streams and subscriptions for each stream named in driver.
self._stream_config = {}
self._data_subscribers = []
for (stream_name, val) in PACKET_CONFIG.iteritems():
stream_def = ctd_stream_definition(stream_id=None)
stream_def_id = pubsub_client.create_stream_definition(
container=stream_def)
stream_id = pubsub_client.create_stream(
name=stream_name,
stream_definition_id=stream_def_id,
original=True,
encoding='ION R2')
self._stream_config[stream_name] = stream_id
# Create subscriptions for each stream.
exchange_name = '%s_queue' % stream_name
sub = subscriber_registrar.create_subscriber(exchange_name=exchange_name,
callback=consume_data)
self._listen(sub)
self._data_subscribers.append(sub)
query = StreamQuery(stream_ids=[stream_id])
sub_id = pubsub_client.create_subscription(\
query=query, exchange_name=exchange_name)
pubsub_client.activate_subscription(sub_id)
def on_start(self):
pubsub_cli = PubsubManagementServiceProcessClient(
process=self, node=self.container.node)
# Get the stream(s)
stream_id = self.CFG.get_safe('process.stream_id', '')
query = StreamQuery(stream_ids=[
stream_id,
])
exchange_name = 'dispatcher_%s' % self.id
subscription_id = pubsub_cli.create_subscription(
query=query,
exchange_name=exchange_name,
name="SampleSubscription",
description="Sample Subscription Description")
stream_subscriber = StreamSubscriberRegistrar(process=self,
node=self.container.node)
def message_received(granule, h):
rdt = RecordDictionaryTool.load_from_granule(granule)
log.warn(
'Logging Record Dictionary received in logger subscription \n%s',
rdt.pretty_print())
subscriber = stream_subscriber.create_subscriber(
exchange_name=exchange_name, callback=message_received)
subscriber.start()
pubsub_cli.activate_subscription(subscription_id)
def instrument_test_driver(container):
org_client = OrgManagementServiceClient(node=container.node)
id_client = IdentityManagementServiceClient(node=container.node)
system_actor = id_client.find_actor_identity_by_name(name=CFG.system.system_actor)
log.info('system actor:' + system_actor._id)
sa_header_roles = get_role_message_headers(org_client.find_all_roles_by_user(system_actor._id))
# Names of agent data streams to be configured.
parsed_stream_name = 'ctd_parsed'
raw_stream_name = 'ctd_raw'
# Driver configuration.
#Simulator
driver_config = {
'svr_addr': 'localhost',
'cmd_port': 5556,
'evt_port': 5557,
'dvr_mod': 'ion.agents.instrument.drivers.sbe37.sbe37_driver',
'dvr_cls': 'SBE37Driver',
'comms_config': {
SBE37Channel.CTD: {
'method':'ethernet',
'device_addr': CFG.device.sbe37.host,
'device_port': CFG.device.sbe37.port,
'server_addr': 'localhost',
'server_port': 8888
}
}
}
#Hardware
_container_client = ContainerAgentClient(node=container.node,
name=container.name)
# Create a pubsub client to create streams.
_pubsub_client = PubsubManagementServiceClient(node=container.node)
# A callback for processing subscribed-to data.
def consume(message, headers):
log.info('Subscriber received message: %s', str(message))
# Create a stream subscriber registrar to create subscribers.
subscriber_registrar = StreamSubscriberRegistrar(process=container,
node=container.node)
subs = []
# Create streams for each stream named in driver.
stream_config = {}
for (stream_name, val) in PACKET_CONFIG.iteritems():
stream_def = ctd_stream_definition(stream_id=None)
stream_def_id = _pubsub_client.create_stream_definition(
container=stream_def)
stream_id = _pubsub_client.create_stream(
name=stream_name,
stream_definition_id=stream_def_id,
original=True,
encoding='ION R2', headers={'ion-actor-id': system_actor._id, 'ion-actor-roles': sa_header_roles })
stream_config[stream_name] = stream_id
# Create subscriptions for each stream.
exchange_name = '%s_queue' % stream_name
sub = subscriber_registrar.create_subscriber(exchange_name=exchange_name, callback=consume)
sub.start()
query = StreamQuery(stream_ids=[stream_id])
sub_id = _pubsub_client.create_subscription(\
query=query, exchange_name=exchange_name )
_pubsub_client.activate_subscription(sub_id)
subs.append(sub)
# Create agent config.
agent_resource_id = '123xyz'
agent_config = {
'driver_config' : driver_config,
'stream_config' : stream_config,
'agent' : {'resource_id': agent_resource_id}
}
# Launch an instrument agent process.
_ia_name = 'agent007'
_ia_mod = 'ion.agents.instrument.instrument_agent'
_ia_class = 'InstrumentAgent'
_ia_pid = _container_client.spawn_process(name=_ia_name,
module=_ia_mod, cls=_ia_class,
config=agent_config)
log.info('got pid=%s for resource_id=%s' % (str(_ia_pid), str(agent_resource_id)))
def setUp(self):
"""
Setup the test environment to exersice use of instrumet agent, including:
* define driver_config parameters.
* create container with required services and container client.
* create publication stream ids for each driver data stream.
* create stream_config parameters.
* create and activate subscriptions for agent data streams.
* spawn instrument agent process and create agent client.
* add cleanup functions to cause subscribers to get stopped.
"""
# params = { ('CTD', 'TA2'): -1.9434316e-05,
# ('CTD', 'PTCA1'): 1.3206866,
# ('CTD', 'TCALDATE'): [8, 11, 2006] }
# for tup in params:
# print tup
self.addCleanup(self.customCleanUp)
# Names of agent data streams to be configured.
parsed_stream_name = 'ctd_parsed'
raw_stream_name = 'ctd_raw'
# Driver configuration.
#Simulator
self.driver_config = {
'svr_addr': 'localhost',
'cmd_port': 5556,
'evt_port': 5557,
'dvr_mod': 'ion.agents.instrument.drivers.sbe37.sbe37_driver',
'dvr_cls': 'SBE37Driver',
'comms_config': {
SBE37Channel.CTD: {
'method': 'ethernet',
'device_addr': CFG.device.sbe37.host,
'device_port': CFG.device.sbe37.port,
'server_addr': 'localhost',
'server_port': 8888
}
}
}
#Hardware
'''
self.driver_config = {
'svr_addr': 'localhost',
'cmd_port': 5556,
'evt_port': 5557,
'dvr_mod': 'ion.agents.instrument.drivers.sbe37.sbe37_driver',
'dvr_cls': 'SBE37Driver',
'comms_config': {
SBE37Channel.CTD: {
'method':'ethernet',
'device_addr': '137.110.112.119',
'device_port': 4001,
'server_addr': 'localhost',
'server_port': 8888
}
}
}
'''
# Start container.
self._start_container()
# Establish endpoint with container (used in tests below)
self._container_client = ContainerAgentClient(node=self.container.node,
name=self.container.name)
# Bring up services in a deploy file (no need to message)
self.container.start_rel_from_url('res/deploy/r2dm.yml')
# Create a pubsub client to create streams.
self._pubsub_client = PubsubManagementServiceClient(
node=self.container.node)
# A callback for processing subscribed-to data.
def consume(message, headers):
log.info('Subscriber received message: %s', str(message))
# Create a stream subscriber registrar to create subscribers.
subscriber_registrar = StreamSubscriberRegistrar(
process=self.container, node=self.container.node)
self.subs = []
# Create streams for each stream named in driver.
self.stream_config = {}
for (stream_name, val) in PACKET_CONFIG.iteritems():
stream_def = ctd_stream_definition(stream_id=None)
stream_def_id = self._pubsub_client.create_stream_definition(
container=stream_def)
stream_id = self._pubsub_client.create_stream(
name=stream_name,
stream_definition_id=stream_def_id,
original=True,
encoding='ION R2')
self.stream_config[stream_name] = stream_id
# Create subscriptions for each stream.
exchange_name = '%s_queue' % stream_name
sub = subscriber_registrar.create_subscriber(
exchange_name=exchange_name, callback=consume)
sub.start()
query = StreamQuery(stream_ids=[stream_id])
sub_id = self._pubsub_client.create_subscription(\
query=query, exchange_name=exchange_name)
self._pubsub_client.activate_subscription(sub_id)
self.subs.append(sub)
# Add cleanup function to stop subscribers.
def stop_subscriber(sub_list):
for sub in sub_list:
sub.stop()
self.addCleanup(stop_subscriber, self.subs)
# Create agent config.
self.agent_resource_id = '123xyz'
self.agent_config = {
'driver_config': self.driver_config,
'stream_config': self.stream_config,
'agent': {
'resource_id': self.agent_resource_id
}
}
# Launch an instrument agent process.
self._ia_name = 'agent007'
self._ia_mod = 'ion.agents.instrument.instrument_agent'
self._ia_class = 'InstrumentAgent'
self._ia_pid = self._container_client.spawn_process(
name=self._ia_name,
module=self._ia_mod,
cls=self._ia_class,
config=self.agent_config)
log.info('got pid=%s', str(self._ia_pid))
self._ia_client = None
# Start a resource agent client to talk with the instrument agent.
self._ia_client = ResourceAgentClient(self.agent_resource_id,
process=FakeProcess())
log.info('got ia client %s', str(self._ia_client))
def on_start(self):
rr_cli = ResourceRegistryServiceProcessClient(process=self,
node=self.container.node)
pubsub_cli = PubsubManagementServiceProcessClient(
process=self, node=self.container.node)
# Get the stream(s)
data_product_id = self.CFG.get_safe('dispatcher.data_product_id', '')
stream_ids, _ = rr_cli.find_objects(subject=data_product_id,
predicate=PRED.hasStream,
id_only=True)
log.info('Got Stream Ids: "%s"', stream_ids)
assert stream_ids, 'No streams found for this data product!'
query = StreamQuery(stream_ids=stream_ids)
exchange_name = 'dispatcher_%s' % str(os.getpid())
subscription_id = pubsub_cli.create_subscription(
query=query,
exchange_name=exchange_name,
name="SampleSubscription",
description="Sample Subscription Description")
stream_subscriber = StreamSubscriberRegistrar(process=self,
node=self.container.node)
stream_defs = {}
def message_received(granule, h):
stream_id = granule.stream_resource_id
data_stream_id = granule.data_stream_id
data_stream = granule.identifiables[data_stream_id]
tstamp = get_datetime(data_stream.timestamp.value)
records = granule.identifiables['record_count'].value
log.info(
'Received a message from stream %s with time stamp %s and %d records'
% (stream_id, tstamp, records))
if stream_id not in stream_defs:
stream_defs[stream_id] = pubsub_cli.find_stream_definition(
stream_id, id_only=False).container
stream_def = stream_defs.get(stream_id)
sp = PointSupplementStreamParser(stream_definition=stream_def,
stream_granule=granule)
last_data = {}
for field in sp.list_field_names():
last_data[field] = sp.get_values(field)[-1]
log.info('Last values in the message: %s' % str(last_data))
subscriber = stream_subscriber.create_subscriber(
exchange_name=exchange_name, callback=message_received)
subscriber.start()
pubsub_cli.activate_subscription(subscription_id)
def on_start(self):
# The data dictionary object holds a copy of all the viz products created by the service. The viz
# products are indexed by the viz_product_type and data_product_id (which could be google_datatables or
# mpl_graphs
self.viz_data_dictionary = {}
self.viz_data_dictionary['google_dt'] = {}
self.viz_data_dictionary['google_realtime_dt'] = {}
self.viz_data_dictionary['matplotlib_graphs'] = {}
# Kind of redundant but we will maintain a separate list of data product_ids registered with the viz_service
self.data_products = []
# Create clients to interface with PubSub, Transform Management Service and Resource Registry
self.pubsub_cli = self.clients.pubsub_management
self.tms_cli = self.clients.transform_management
self.rr_cli = self.clients.resource_registry
self.dr_cli = self.clients.data_retriever
self.dsm_cli = self.clients.dataset_management
"""
# Create process definitions which will used to spawn off the transform processes
self.matplotlib_proc_def = IonObject(RT.ProcessDefinition, name='viz_transform_process'+'.'+self.random_id_generator())
self.matplotlib_proc_def.executable = {
'module': 'ion.services.ans.visualization_service',
'class':'VizTransformProcForMatplotlibGraphs'
}
self.matplotlib_proc_def_id, _ = self.rr_cli.create(self.matplotlib_proc_def)
self.google_dt_proc_def = IonObject(RT.ProcessDefinition, name='viz_transform_process'+'.'+self.random_id_generator())
self.google_dt_proc_def.executable = {
'module': 'ion.services.ans.visualization_service',
'class':'VizTransformProcForGoogleDT'
}
self.google_dt_proc_def_id, _ = self.rr_cli.create(self.google_dt_proc_def)
"""
# Query resource registry to get process definitions and streams ids made by the bootstrap
proc_def_ids, _ = self.rr_cli.find_resources(
restype=RT.ProcessDefinition,
lcstate=None,
name="viz_matplotlib_transform_process",
id_only=True)
self.matplotlib_proc_def_id = proc_def_ids[0]
proc_def_ids, _ = self.rr_cli.find_resources(
restype=RT.ProcessDefinition,
lcstate=None,
name="viz_google_dt_transform_process",
id_only=True)
self.google_dt_proc_def_id = proc_def_ids[0]
# Create a stream that all the transform processes will use to submit data back to the viz service
self.viz_service_submit_stream_id = self.pubsub_cli.create_stream(
name="visualization_service_submit_stream." +
self.random_id_generator())
# subscribe to this stream since all the results from transforms will be submitted here
query = StreamQuery(stream_ids=[
self.viz_service_submit_stream_id,
])
self.viz_service_submit_stream_sub_id = self.pubsub_cli.create_subscription(
query=query, exchange_name="visualization_service_submit_queue")
submit_stream_subscriber_registrar = StreamSubscriberRegistrar(
process=self.container, node=self.container.node)
submit_stream_subscriber = submit_stream_subscriber_registrar.create_subscriber(
exchange_name='visualization_service_submit_queue',
callback=self.process_submission)
submit_stream_subscriber.start()
self.pubsub_cli.activate_subscription(
self.viz_service_submit_stream_sub_id)
# Discover the existing data_product_ids active in the system
sys_prod_ids, _ = self.rr_cli.find_resources(RT.DataProduct, None,
None, True)
# Register all the streams in the system, which will in turn start transform processes
for dp_id in sys_prod_ids:
self.register_new_data_product(dp_id)
# listen for events when new data_products show up
self.event_subscriber = EventSubscriber(
event_type="ResourceModifiedEvent",
origin_type="DataProduct",
sub_type="UPDATE",
callback=self.receive_new_dataproduct_event)
self.event_subscriber.activate()
return
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_raw_stream_integration(self):
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)
process_dispatcher = ProcessDispatcherServiceClient(node=cc.node)
# declare some handy variables
datastore_name = 'test_dm_integration'
###
### In the beginning there was one stream definitions...
###
# create a stream definition for the data from the ctd simulator
raw_ctd_stream_def = SBE37_RAW_stream_definition()
raw_ctd_stream_def_id = pubsub_management_service.create_stream_definition(
container=raw_ctd_stream_def, name='Simulated RAW CTD data')
###
### And two process definitions...
###
# one for the ctd simulator...
producer_definition = ProcessDefinition()
producer_definition.executable = {
'module': 'ion.processes.data.raw_stream_publisher',
'class': 'RawStreamPublisher'
}
raw_ctd_sim_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
raw_ctd_stream_id = pubsub_management_service.create_stream(
stream_definition_id=raw_ctd_stream_def_id)
# Set up the datasets
raw_ctd_dataset_id = dataset_management_service.create_dataset(
stream_id=raw_ctd_stream_id,
datastore_name=datastore_name,
view_name='datasets/stream_join_granule')
# Configure ingestion of this dataset
raw_ctd_dataset_config_id = ingestion_management_service.create_dataset_configuration(
dataset_id=raw_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
# Start the ctd simulator to produce some data
configuration = {
'process': {
'stream_id': raw_ctd_stream_id,
}
}
raw_sim_pid = process_dispatcher.schedule_process(
process_definition_id=raw_ctd_sim_procdef_id,
configuration=configuration)
###
### Make a subscriber in the test to listen for salinity data
###
raw_subscription_id = pubsub_management_service.create_subscription(
query=StreamQuery([
raw_ctd_stream_id,
]),
exchange_name='raw_test',
name="test raw subscription",
)
# this is okay - even in cei mode!
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('Raw data received!')
results.append(message)
if len(results) > 3:
result.set(True)
subscriber = subscriber_registrar.create_subscriber(
exchange_name='raw_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=raw_subscription_id)
# Assert that we have received data
assertions(result.get(timeout=10))
# stop the flow parse the messages...
process_dispatcher.cancel_process(
raw_sim_pid
) # kill the ctd simulator process - that is enough data
gevent.sleep(1)
for message in results:
sha1 = message.identifiables['stream_encoding'].sha1
data = message.identifiables['data_stream'].values
filename = FileSystem.get_hierarchical_url(FS.CACHE, sha1, ".raw")
with open(filename, 'r') as f:
assertions(data == f.read())
def test_integrated_transform(self):
'''
This example script runs a chained three way transform:
B
A <
C
Where A is the even_odd transform (generates a stream of even and odd numbers from input)
and B and C are the basic transforms that receive even and odd input
'''
cc = self.container
assertions = self.assertTrue
pubsub_cli = PubsubManagementServiceClient(node=cc.node)
rr_cli = ResourceRegistryServiceClient(node=cc.node)
tms_cli = TransformManagementServiceClient(node=cc.node)
#-------------------------------
# Process Definition
#-------------------------------
# Create the process definition for the basic transform
process_definition = IonObject(RT.ProcessDefinition, name='basic_transform_definition')
process_definition.executable = {
'module': 'ion.processes.data.transforms.transform_example',
'class':'TransformExample'
}
basic_transform_definition_id, _ = rr_cli.create(process_definition)
# Create The process definition for the TransformEvenOdd
process_definition = IonObject(RT.ProcessDefinition, name='evenodd_transform_definition')
process_definition.executable = {
'module': 'ion.processes.data.transforms.transform_example',
'class':'TransformEvenOdd'
}
evenodd_transform_definition_id, _ = rr_cli.create(process_definition)
#-------------------------------
# Streams
#-------------------------------
streams = [pubsub_cli.create_stream() for i in xrange(5)]
#-------------------------------
# Subscriptions
#-------------------------------
query = StreamQuery(stream_ids=[streams[0]])
input_subscription_id = pubsub_cli.create_subscription(query=query, exchange_name='input_queue')
query = StreamQuery(stream_ids = [streams[1]]) # even output
even_subscription_id = pubsub_cli.create_subscription(query=query, exchange_name='even_queue')
query = StreamQuery(stream_ids = [streams[2]]) # odd output
odd_subscription_id = pubsub_cli.create_subscription(query=query, exchange_name='odd_queue')
#-------------------------------
# Launch the EvenOdd Transform
#-------------------------------
evenodd_id = tms_cli.create_transform(name='even_odd',
in_subscription_id=input_subscription_id,
out_streams={'even':streams[1], 'odd':streams[2]},
process_definition_id=evenodd_transform_definition_id,
configuration={})
tms_cli.activate_transform(evenodd_id)
#-------------------------------
# Launch the Even Processing Transform
#-------------------------------
even_transform_id = tms_cli.create_transform(name='even_transform',
in_subscription_id = even_subscription_id,
out_streams={'even_plus1':streams[3]},
process_definition_id=basic_transform_definition_id,
configuration={})
tms_cli.activate_transform(even_transform_id)
#-------------------------------
# Launch the Odd Processing Transform
#-------------------------------
odd_transform_id = tms_cli.create_transform(name='odd_transform',
in_subscription_id = odd_subscription_id,
out_streams={'odd_plus1':streams[4]},
process_definition_id=basic_transform_definition_id,
configuration={})
tms_cli.activate_transform(odd_transform_id)
#-------------------------------
# Set up final subscribers
#-------------------------------
evenplus1_subscription_id = pubsub_cli.create_subscription(
query=StreamQuery([streams[3]]),
exchange_name='evenplus1_queue',
name='EvenPlus1Subscription',
description='EvenPlus1 SubscriptionDescription'
)
oddplus1_subscription_id = pubsub_cli.create_subscription(
query=StreamQuery([streams[4]]),
exchange_name='oddplus1_queue',
name='OddPlus1Subscription',
description='OddPlus1 SubscriptionDescription'
)
total_msg_count = 2
msgs = gevent.queue.Queue()
def even1_message_received(message, headers):
input = int(message.get('num'))
assertions( (input % 2) ) # Assert it is odd (transform adds 1)
msgs.put(True)
def odd1_message_received(message, headers):
input = int(message.get('num'))
assertions(not (input % 2)) # Assert it is even
msgs.put(True)
subscriber_registrar = StreamSubscriberRegistrar(process=cc, node=cc.node)
even_subscriber = subscriber_registrar.create_subscriber(exchange_name='evenplus1_queue', callback=even1_message_received)
odd_subscriber = subscriber_registrar.create_subscriber(exchange_name='oddplus1_queue', callback=odd1_message_received)
# Start subscribers
even_subscriber.start()
odd_subscriber.start()
# Activate subscriptions
pubsub_cli.activate_subscription(evenplus1_subscription_id)
pubsub_cli.activate_subscription(oddplus1_subscription_id)
#-------------------------------
# Set up fake stream producer
#-------------------------------
pid = cc.spawn_process(name='dummy_process_for_test',
module='pyon.ion.process',
cls='SimpleProcess',
config={})
dummy_process = cc.proc_manager.procs[pid]
# Normally the user does not see or create the publisher, this is part of the containers business.
# For the test we need to set it up explicitly
publisher_registrar = StreamPublisherRegistrar(process=dummy_process, node=cc.node)
stream_publisher = publisher_registrar.create_publisher(stream_id=streams[0])
#-------------------------------
# Start test
#-------------------------------
# Publish a stream
for i in xrange(total_msg_count):
stream_publisher.publish({'num':str(i)})
time.sleep(0.5)
for i in xrange(total_msg_count * 2):
try:
msgs.get()
except Empty:
assertions(False, "Failed to process all messages correctly.")
def test_activateInstrumentStream(self):
# Create InstrumentModel
instModel_obj = IonObject(RT.InstrumentModel,
name='SBE37IMModel',
description="SBE37IMModel",
model_label="SBE37IMModel")
try:
instModel_id = self.imsclient.create_instrument_model(
instModel_obj)
except BadRequest as ex:
self.fail("failed to create new InstrumentModel: %s" % ex)
print 'new InstrumentModel id = ', instModel_id
# Create InstrumentAgent
instAgent_obj = IonObject(
RT.InstrumentAgent,
name='agent007',
description="SBE37IMAgent",
driver_module="ion.agents.instrument.instrument_agent",
driver_class="InstrumentAgent")
try:
instAgent_id = self.imsclient.create_instrument_agent(
instAgent_obj)
except BadRequest as ex:
self.fail("failed to create new InstrumentAgent: %s" % ex)
print 'new InstrumentAgent id = ', instAgent_id
self.imsclient.assign_instrument_model_to_instrument_agent(
instModel_id, instAgent_id)
# Create InstrumentDevice
log.debug(
'test_activateInstrumentStream: Create instrument resource to represent the SBE37 (SA Req: L4-CI-SA-RQ-241) '
)
instDevice_obj = IonObject(RT.InstrumentDevice,
name='SBE37IMDevice',
description="SBE37IMDevice",
serial_number="12345")
try:
instDevice_id = self.imsclient.create_instrument_device(
instrument_device=instDevice_obj)
self.imsclient.assign_instrument_model_to_instrument_device(
instModel_id, instDevice_id)
except BadRequest as ex:
self.fail("failed to create new InstrumentDevice: %s" % ex)
log.debug(
"test_activateInstrumentStream: new InstrumentDevice id = %s (SA Req: L4-CI-SA-RQ-241) ",
instDevice_id)
driver_config = {
'dvr_mod': 'ion.agents.instrument.drivers.sbe37.sbe37_driver',
'dvr_cls': 'SBE37Driver',
'workdir': '/tmp/',
}
instAgentInstance_obj = IonObject(
RT.InstrumentAgentInstance,
name='SBE37IMAgentInstance',
description="SBE37IMAgentInstance",
driver_config=driver_config,
comms_device_address='sbe37-simulator.oceanobservatories.org',
comms_device_port=4001,
port_agent_work_dir='/tmp/',
port_agent_delimeter=['<<', '>>'])
instAgentInstance_id = self.imsclient.create_instrument_agent_instance(
instAgentInstance_obj, instAgent_id, instDevice_id)
# create a stream definition for the data from the ctd simulator
ctd_stream_def = SBE37_CDM_stream_definition()
ctd_stream_def_id = self.pubsubcli.create_stream_definition(
container=ctd_stream_def)
log.debug(
'test_activateInstrumentStream new Stream Definition id = %s',
instDevice_id)
log.debug(
'test_activateInstrumentStream Creating new CDM data product with a stream definition'
)
dp_obj = IonObject(RT.DataProduct,
name='the parsed data',
description='ctd stream test')
try:
data_product_id1 = self.dpclient.create_data_product(
dp_obj, ctd_stream_def_id)
except BadRequest as ex:
self.fail("failed to create new data product: %s" % ex)
log.debug('test_activateInstrumentStream new dp_id = %s',
str(data_product_id1))
self.damsclient.assign_data_product(input_resource_id=instDevice_id,
data_product_id=data_product_id1)
self.dpclient.activate_data_product_persistence(
data_product_id=data_product_id1,
persist_data=True,
persist_metadata=True)
# Retrieve the id of the OUTPUT stream from the out Data Product
stream_ids, _ = self.rrclient.find_objects(data_product_id1,
PRED.hasStream, None, True)
log.debug('test_activateInstrumentStream Data product streams1 = %s',
str(stream_ids))
simdata_subscription_id = self.pubsubcli.create_subscription(
query=StreamQuery([stream_ids[0]]),
exchange_name='Sim_data_queue',
name='SimDataSubscription',
description='SimData SubscriptionDescription')
def simdata_message_received(message, headers):
input = str(message)
log.debug("test_activateInstrumentStream: granule received: %s",
input)
subscriber_registrar = StreamSubscriberRegistrar(
process=self.container, node=self.container.node)
simdata_subscriber = subscriber_registrar.create_subscriber(
exchange_name='Sim_data_queue', callback=simdata_message_received)
# Start subscribers
simdata_subscriber.start()
# Activate subscriptions
self.pubsubcli.activate_subscription(simdata_subscription_id)
log.debug(
'test_activateInstrumentStream Creating new RAW data product with a stream definition'
)
raw_stream_def = SBE37_RAW_stream_definition()
raw_stream_def_id = self.pubsubcli.create_stream_definition(
container=raw_stream_def)
dp_obj = IonObject(RT.DataProduct,
name='the raw data',
description='raw stream test')
try:
data_product_id2 = self.dpclient.create_data_product(
dp_obj, raw_stream_def_id)
except BadRequest as ex:
self.fail("failed to create new data product: %s" % ex)
log.debug('test_activateInstrumentStream new dp_id = %s',
str(data_product_id2))
self.damsclient.assign_data_product(input_resource_id=instDevice_id,
data_product_id=data_product_id2)
self.dpclient.activate_data_product_persistence(
data_product_id=data_product_id2,
persist_data=True,
persist_metadata=True)
# Retrieve the id of the OUTPUT stream from the out Data Product
stream_ids, _ = self.rrclient.find_objects(data_product_id2,
PRED.hasStream, None, True)
log.debug('test_activateInstrumentStream Data product streams2 = %s',
str(stream_ids))
self.imsclient.start_instrument_agent_instance(
instrument_agent_instance_id=instAgentInstance_id)
inst_agent_instance_obj = self.imsclient.read_instrument_agent_instance(
instAgentInstance_id)
log.debug(
'test_activateInstrumentStream Instrument agent instance obj: = %s',
str(inst_agent_instance_obj))
# Start a resource agent client to talk with the instrument agent.
#self._ia_client = ResourceAgentClient('123xyz', name=inst_agent_instance_obj.agent_process_id, process=FakeProcess())
self._ia_client = ResourceAgentClient(instDevice_id,
process=FakeProcess())
log.debug('test_activateInstrumentStream: got ia client %s',
str(self._ia_client))
log.debug("test_activateInstrumentStream: got ia client %s",
str(self._ia_client))
cmd = AgentCommand(command='initialize')
retval = self._ia_client.execute_agent(cmd)
log.debug("test_activateInstrumentStream: initialize %s", str(retval))
time.sleep(2)
log.debug(
"test_activateInstrumentStream: Sending go_active command (L4-CI-SA-RQ-334)"
)
cmd = AgentCommand(command='go_active')
reply = self._ia_client.execute_agent(cmd)
log.debug(
"test_activateInstrumentStream: return value from go_active %s",
str(reply))
time.sleep(2)
cmd = AgentCommand(command='get_current_state')
retval = self._ia_client.execute_agent(cmd)
state = retval.result
log.debug(
"test_activateInstrumentStream: current state after sending go_active command %s (L4-CI-SA-RQ-334)",
str(state))
cmd = AgentCommand(command='run')
reply = self._ia_client.execute_agent(cmd)
log.debug("test_activateInstrument: run %s", str(reply))
time.sleep(2)
log.debug("test_activateInstrumentStream: calling go_streaming ")
cmd = AgentCommand(command='go_streaming')
reply = self._ia_client.execute(cmd)
log.debug("test_activateInstrumentStream: return from go_streaming %s",
str(reply))
time.sleep(15)
log.debug("test_activateInstrumentStream: calling go_observatory")
cmd = AgentCommand(command='go_observatory')
reply = self._ia_client.execute(cmd)
log.debug(
"test_activateInstrumentStream: return from go_observatory %s",
str(reply))
time.sleep(2)
log.debug("test_activateInstrumentStream: calling reset ")
cmd = AgentCommand(command='reset')
reply = self._ia_client.execute_agent(cmd)
log.debug("test_activateInstrumentStream: return from reset %s",
str(reply))
time.sleep(2)
#-------------------------------
# Deactivate InstrumentAgentInstance
#-------------------------------
self.imsclient.stop_instrument_agent_instance(
instrument_agent_instance_id=instAgentInstance_id)
