def test_data_product_search(self):
# Create the dataproduct
dp = DataProduct(name='test_product')
dp.data_format.name = 'test_signal'
dp.data_format.description = 'test signal'
dp.data_format.character_set = 'utf8'
dp.data_format.nominal_sampling_rate_maximum = '44000'
dp.data_format.nominal_sampling_rate_minimum = '44000'
dp.data_product_level = 'basic'
dp_id, _ = self.rr.create(dp)
search_string = "search 'data_format.name' is 'test_signal' from 'data_products_index'"
results = self.poll(9, self.discovery.parse, search_string)
self.assertIsNotNone(results, 'Results not found')
self.assertTrue(results[0]['_id'] == dp_id)
search_string = "search 'data_product_level' is 'basic' from 'data_products_index'"
results = self.poll(9, self.discovery.parse, search_string)
self.assertIsNotNone(results, 'Results not found')
self.assertTrue(results[0]['_id'] == dp_id)
search_string = "search 'data_format.character_set' is 'utf8' from 'data_products_index'"
results = self.poll(9, self.discovery.parse, search_string)
self.assertIsNotNone(results, 'Results not found')
self.assertTrue(results[0]['_id'] == dp_id)
def test_data_product_search(self):
# Create the dataproduct
dp = DataProduct(name='test_product')
dp.data_format.name = 'test_signal'
dp.data_format.description = 'test signal'
dp.data_format.character_set = 'utf8'
dp.data_format.nominal_sampling_rate_maximum = '44000'
dp.data_format.nominal_sampling_rate_minimum = '44000'
dp.CDM_data_type = 'basic'
dp_id, _ = self.rr.create(dp)
search_string = "search 'data_format.name' is 'test_signal' from 'data_products_index'"
results = self.poll(9, self.discovery.parse, search_string)
self.assertIsNotNone(results, 'Results not found')
self.assertTrue(results[0]['_id'] == dp_id)
search_string = "search 'CDM_data_type' is 'basic' from 'data_products_index'"
results = self.poll(9, self.discovery.parse, search_string)
self.assertIsNotNone(results, 'Results not found')
self.assertTrue(results[0]['_id'] == dp_id)
search_string = "search 'data_format.character_set' is 'utf8' from 'data_products_index'"
results = self.poll(9, self.discovery.parse, search_string)
self.assertIsNotNone(results, 'Results not found')
self.assertTrue(results[0]['_id'] == dp_id)
def test_data_product_subscription(self):
pdict_id = self.dataset_management.read_parameter_dictionary_by_name('ctd_parsed_param_dict', id_only=True)
stream_def_id = self.pubsub_management.create_stream_definition('ctd parsed', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='ctd parsed')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(data_product=dp, stream_definition_id=stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
subscription_id = self.pubsub_management.create_subscription('validator', data_product_ids=[data_product_id])
self.addCleanup(self.pubsub_management.delete_subscription, subscription_id)
validated = Event()
def validation(msg, route, stream_id):
validated.set()
stream_ids, _ = self.resource_registry.find_objects(subject=data_product_id, predicate=PRED.hasStream, id_only=True)
dp_stream_id = stream_ids.pop()
validator = StandaloneStreamSubscriber('validator', callback=validation)
validator.start()
self.addCleanup(validator.stop)
self.pubsub_management.activate_subscription(subscription_id)
self.addCleanup(self.pubsub_management.deactivate_subscription, subscription_id)
route = self.pubsub_management.read_stream_route(dp_stream_id)
publisher = StandaloneStreamPublisher(dp_stream_id, route)
publisher.publish('hi')
self.assertTrue(validated.wait(10))
def setup_resource(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition('example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='example')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id, PRED.hasDataset, id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
# Yield to other greenlets, had an issue with connectivity
gevent.sleep(1)
self.offering_id = dataset_id
def test_pydap(self):
if not CFG.get_safe('bootstrap.use_pydap',False):
raise unittest.SkipTest('PyDAP is off (bootstrap.use_pydap)')
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition('example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='example')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id, PRED.hasDataset, id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt,10)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(1) # Yield to other greenlets, had an issue with connectivity
pydap_host = CFG.get_safe('server.pydap.host','localhost')
pydap_port = CFG.get_safe('server.pydap.port',8001)
url = 'http://%s:%s/%s' %(pydap_host, pydap_port, dataset_id)
ds = open_url(url)
np.testing.assert_array_equal(ds['time'][:], np.arange(10))
untested = []
for k,v in rdt.iteritems():
if k==rdt.temporal_parameter:
continue
context = rdt.context(k)
if isinstance(context.param_type, QuantityType):
np.testing.assert_array_equal(ds[k][k][:][0], rdt[k])
elif isinstance(context.param_type, ArrayType):
values = np.empty(rdt[k].shape, dtype='O')
for i,obj in enumerate(rdt[k]):
values[i] = str(obj)
np.testing.assert_array_equal(ds[k][k][:][0], values)
elif isinstance(context.param_type, ConstantType):
np.testing.assert_array_equal(ds[k][k][:][0], rdt[k])
elif isinstance(context.param_type, CategoryType):
np.testing.assert_array_equal(ds[k][k][:][0], rdt[k])
else:
untested.append('%s (%s)' % (k,context.param_type))
if untested:
raise AssertionError('Untested parameters: %s' % untested)
def make_data_product(self, pdict_name, dp_name, available_fields=[]):
pdict_id = self.dataset_management.read_parameter_dictionary_by_name(pdict_name, id_only=True)
stream_def_id = self.pubsub_management.create_stream_definition('%s stream_def' % dp_name, parameter_dictionary_id=pdict_id, available_fields=available_fields or None)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
tdom = tdom.dump()
sdom = sdom.dump()
dp_obj = DataProduct(name=dp_name)
dp_obj.temporal_domain = tdom
dp_obj.spatial_domain = sdom
data_product_id = self.data_product_management.create_data_product(dp_obj, stream_definition_id=stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
return data_product_id
def test_qc_attachment(self):
instrument_device = InstrumentDevice(name='whatever')
instrument_device_id,_ = self.rrclient.create(instrument_device)
self.addCleanup(self.rrclient.delete, instrument_device_id)
self.client.register_instrument(instrument_device_id)
self.addCleanup(self.client.unregister_instrument, instrument_device_id)
dp = DataProduct(name='instrument output')
dp_id,_ = self.rrclient.create(dp)
self.addCleanup(self.rrclient.delete, dp_id)
parser_id = self.make_grt_parser()
attachment = Attachment(name='qc ref', attachment_type=AttachmentType.REFERENCE,content=global_range_test_document, context=ReferenceAttachmentContext(parser_id=parser_id))
att_id = self.rrclient.create_attachment(dp_id, attachment)
self.addCleanup(self.rrclient.delete_attachment, att_id)
attachment2 = Attachment(name='qc ref2', attachment_type=AttachmentType.REFERENCE, content=global_range_test_document2, context=ReferenceAttachmentContext(parser_id=parser_id))
att2_id = self.rrclient.create_attachment(dp_id, attachment2)
self.addCleanup(self.rrclient.delete_attachment, att2_id)
self.client.assign_data_product(instrument_device_id, dp_id)
self.addCleanup(self.client.unassign_data_product, instrument_device_id, dp_id)
svm = StoredValueManager(self.container)
doc = svm.read_value('grt_CE01ISSM-MF005-01-CTDBPC999_TEMPWAT')
np.testing.assert_array_almost_equal(doc['grt_min_value'], -2.)
def load_data_product(self):
dset_i = 0
dataset_management = DatasetManagementServiceClient()
pubsub_management = PubsubManagementServiceClient()
data_product_management = DataProductManagementServiceClient()
resource_registry = self.container.instance.resource_registry
dp_obj = DataProduct(
name='instrument_data_product_%i' % dset_i,
description='ctd stream test',
processing_level_code='Parsed_Canonical')
pdict_id = dataset_management.read_parameter_dictionary_by_name('ctd_parsed_param_dict', id_only=True)
stream_def_id = pubsub_management.create_stream_definition(name='parsed', parameter_dictionary_id=pdict_id)
self.addCleanup(pubsub_management.delete_stream_definition, stream_def_id)
data_product_id = data_product_management.create_data_product(data_product=dp_obj, stream_definition_id=stream_def_id)
self.addCleanup(data_product_management.delete_data_product, data_product_id)
data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(data_product_management.suspend_data_product_persistence, data_product_id)
stream_ids, assocs = resource_registry.find_objects(subject=data_product_id, predicate='hasStream', id_only=True)
stream_id = stream_ids[0]
route = pubsub_management.read_stream_route(stream_id)
dataset_ids, assocs = resource_registry.find_objects(subject=data_product_id, predicate='hasDataset', id_only=True)
dataset_id = dataset_ids[0]
return data_product_id, stream_id, route, stream_def_id, dataset_id
def test_get_data_from_FDW(self):
# generate a data product and check that the FDW can get data
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition('example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='example')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id, PRED.hasDataset, id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(1) # Yield to other greenlets, had an issue with connectivity
print "--------------------------------"
print dataset_id
coverage_path = DatasetManagementService()._get_coverage_path(dataset_id)
print coverage_path
print "--------------------------------"
#verify table exists in the DB (similar to above)
# ....code...
# check that the geoserver layer exists as above
# ... code ....
# make a WMS/WFS request...somet like this (or both)
url = self.gs_host+'/geoserver/geonode/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=geonode:ooi_' + dataset_id + '_ooi&maxFeatures=1&outputFormat=csv'
r = requests.get(url)
assertTrue(r.status_code == 200)
def test_create_dataset_verify_geoserver_layer(self):
#generate layer and check that the service created it in geoserver
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition('example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='example')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id, PRED.hasDataset, id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(1) # Yield to other greenlets, had an issue with connectivity
log.debug("--------------------------------")
log.debug(dataset_id)
coverage_path = DatasetManagementService()._get_coverage_path(dataset_id)
log.debug(coverage_path)
log.debug("--------------------------------")
# verify that the layer exists in geoserver
try:
r = requests.get(self.gs_rest_url + '/layers/ooi_' + dataset_id + '_ooi.xml', auth=(self.username, self.PASSWORD))
self.assertTrue(r.status_code == 200)
except Exception as e:
log.error("check service and layer exist...%s", e)
self.assertTrue(False)
def make_dp(self, stream_def_id):
stream_def = self.resource_registry.read(stream_def_id)
dp_obj = DataProduct(name=stream_def.name,
description=stream_def.name,
processing_level_code='Parsed_Canonical')
data_product_id = self.data_product_management.create_data_product(
dp_obj, stream_definition_id=stream_def_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
return data_product_id
def test_get_data_from_FDW(self):
# generate a data product and check that the FDW can get data
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition(
'example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
dp = DataProduct(name='example')
data_product_id = self.data_product_management.create_data_product(
dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id,
PRED.hasDataset,
id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(
1) # Yield to other greenlets, had an issue with connectivity
print "--------------------------------"
print dataset_id
coverage_path = DatasetManagementService()._get_coverage_path(
dataset_id)
print coverage_path
print "--------------------------------"
#verify table exists in the DB (similar to above)
# ....code...
# check that the geoserver layer exists as above
# ... code ....
# make a WMS/WFS request...somet like this (or both)
url = self.gs_host + '/geoserver/geonode/ows?service=WFS&version=1.0.0&request=GetFeature&typeName=geonode:ooi_' + dataset_id + '_ooi&maxFeatures=1&outputFormat=csv'
r = requests.get(url)
assertTrue(r.status_code == 200)
def test_create_dataset_verify_geoserver_layer(self):
#generate layer and check that the service created it in geoserver
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition(
'example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
dp = DataProduct(name='example')
data_product_id = self.data_product_management.create_data_product(
dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id,
PRED.hasDataset,
id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(
1) # Yield to other greenlets, had an issue with connectivity
log.debug("--------------------------------")
log.debug(dataset_id)
coverage_path = DatasetManagementService()._get_coverage_path(
dataset_id)
log.debug(coverage_path)
log.debug("--------------------------------")
# verify that the layer exists in geoserver
try:
r = requests.get(self.gs_rest_url + '/layers/ooi_' + dataset_id +
'_ooi.xml',
auth=(self.username, self.PASSWORD))
self.assertTrue(r.status_code == 200)
except Exception as e:
log.error("check service and layer exist...%s", e)
self.assertTrue(False)
def test_ownership_searching(self):
# Create two data products so that there is competition to the search, one is parsed
# (with conductivity as a parameter) and the other is raw
dp = DataProduct(name='example dataproduct')
pdict_id = self.dataset_management.read_parameter_dictionary_by_name('ctd_parsed_param_dict')
stream_def_id = self.pubsub_management.create_stream_definition('ctd parsed', parameter_dictionary_id=pdict_id)
tdom, sdom = time_series_domain()
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
dp_id = self.data_product_management.create_data_product(dp, stream_definition_id=stream_def_id, exchange_point='xp1')
pdict_id = self.dataset_management.read_parameter_dictionary_by_name('ctd_raw_param_dict')
stream_def_id = self.pubsub_management.create_stream_definition('ctd raw', parameter_dictionary_id=pdict_id)
dp = DataProduct(name='WRONG')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
self.data_product_management.create_data_product(dp, stream_definition_id=stream_def_id, exchange_point='xp1')
parameter_search = 'search "name" is "conductivity" from "resources_index"'
results = self.poll(9, self.discovery.parse, parameter_search)
param_id = results[0]['_id']
data_product_search = 'search "name" is "*" from "data_products_index" and has "%s"' % param_id
results = self.poll(9, self.discovery.parse, data_product_search)
print results
self.assertEquals(results[0], dp_id)
def create_data_product(self, name='', description='', stream_def_id=''):
dp_obj = DataProduct(name=name,
description=description,
processing_level_code='Parsed_Canonical')
data_product_id = self.data_product_management.create_data_product(
data_product=dp_obj, stream_definition_id=stream_def_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
return data_product_id
def test_create_dataset(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition('example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='example')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id, PRED.hasDataset, id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
# Yield to other greenlets, had an issue with connectivity
gevent.sleep(1)
log.debug("--------------------------------")
log.debug(dataset_id)
coverage_path = DatasetManagementService()._get_coverage_path(dataset_id)
log.debug(coverage_path)
log.debug("--------------------------------")
breakpoint(locals(), globals())
def create_data_product(self, name='', description='', stream_def_id=''):
tdom, sdom = time_series_domain()
tdom = tdom.dump()
sdom = sdom.dump()
dp_obj = DataProduct(
name=name,
description=description,
processing_level_code='Parsed_Canonical',
temporal_domain=tdom,
spatial_domain=sdom)
data_product_id = self.data_product_management.create_data_product(data_product=dp_obj, stream_definition_id=stream_def_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
return data_product_id
def make_dp(self, stream_def_id):
tdom, sdom = time_series_domain()
tdom = tdom.dump()
sdom = sdom.dump()
stream_def = self.resource_registry.read(stream_def_id)
dp_obj = DataProduct(name=stream_def.name,
description=stream_def.name,
processing_level_code='Parsed_Canonical',
temporal_domain=tdom,
spatial_domain=sdom)
data_product_id = self.data_product_management.create_data_product(
dp_obj, stream_definition_id=stream_def_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
return data_product_id
def create_data_product(self,name, stream_def_id='', param_dict_name='', pdict_id='', stream_configuration=None):
if not (stream_def_id or param_dict_name or pdict_id):
raise AssertionError('Attempted to create a Data Product without a parameter dictionary')
dp = DataProduct(name=name)
stream_def_id = stream_def_id or self.create_stream_definition('%s stream def' % name,
parameter_dictionary_id=pdict_id or self.RR2.find_resource_by_name(RT.ParameterDictionary,
param_dict_name, id_only=True))
stream_config = stream_configuration or StreamConfiguration(stream_name='parsed_ctd', stream_type=StreamConfigurationType.PARSED)
data_product_id = self.data_product_management.create_data_product(dp, stream_definition_id=stream_def_id, default_stream_configuration=stream_config)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
return data_product_id
def make_data_product(self, pdict_name, dp_name, available_fields=None):
self.pubsub_management = PubsubManagementServiceClient()
if available_fields is None: available_fields = []
pdict_id = self.dataset_management.read_parameter_dictionary_by_name(
pdict_name, id_only=True)
stream_def_id = self.pubsub_management.create_stream_definition(
'%s stream_def' % dp_name,
parameter_dictionary_id=pdict_id,
available_fields=available_fields or None)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
dp_obj = DataProduct(name=dp_name)
data_product_id = self.data_product_management.create_data_product(
dp_obj, stream_definition_id=stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
return data_product_id
def create_data_product(self,name, stream_def_id='', param_dict_name='', pdict_id=''):
if not (stream_def_id or param_dict_name or pdict_id):
raise AssertionError('Attempted to create a Data Product without a parameter dictionary')
tdom, sdom = time_series_domain()
dp = DataProduct(name=name,
spatial_domain = sdom.dump(),
temporal_domain = tdom.dump(),
)
stream_def_id = stream_def_id or self.create_stream_definition('%s stream def' % name,
parameter_dictionary_id=pdict_id or self.RR2.find_resource_by_name(RT.ParameterDictionary,
param_dict_name, id_only=True))
data_product_id = self.data_product_management.create_data_product(dp, stream_definition_id=stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
return data_product_id
def test_create_dataset(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition(
'example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
dp = DataProduct(name='example')
data_product_id = self.data_product_management.create_data_product(
dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id,
PRED.hasDataset,
id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
# Yield to other greenlets, had an issue with connectivity
gevent.sleep(1)
log.debug("--------------------------------")
log.debug(dataset_id)
coverage_path = DatasetManagementService()._get_coverage_path(
dataset_id)
log.debug(coverage_path)
log.debug("--------------------------------")
breakpoint(locals(), globals())
def test_fdt_created_during(self):
# generate a data product and check that the FDT exists
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition(
'example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
dp = DataProduct(name='example')
data_product_id = self.data_product_management.create_data_product(
dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id,
PRED.hasDataset,
id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(
1) # Yield to other greenlets, had an issue with connectivity
print "--------------------------------"
print dataset_id
coverage_path = DatasetManagementService()._get_coverage_path(
dataset_id)
print coverage_path
print "--------------------------------"
def setup_resource(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition(
'example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
dp = DataProduct(name='example')
data_product_id = self.data_product_management.create_data_product(
dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id,
PRED.hasDataset,
id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 100)
ph.publish_rdt_to_data_product(data_product_id, rdt)
# Yield to other greenlets, had an issue with connectivity
gevent.sleep(1)
self.offering_id = dataset_id
def test_add_parameter_to_data_product(self):
#self.preload_ui()
self.test_add_parameter_function()
data_product_id = self.data_product_id
stream_def_id = self.resource_registry.find_objects(
data_product_id, PRED.hasStreamDefinition, id_only=True)[0][0]
pdict_id = self.resource_registry.find_objects(
stream_def_id, PRED.hasParameterDictionary, id_only=True)[0][0]
# Create a new data product htat represents the L1 temp from the ctd simulator
dp = DataProduct(name='CTD Simulator TEMPWAT L1',
category=DataProductTypeEnum.DERIVED)
stream_def_id = self.pubsub_management.create_stream_definition(
name='tempwat_l1',
parameter_dictionary_id=pdict_id,
available_fields=['time', 'temp'])
dp_id = self.data_product_management.create_data_product(
dp,
stream_definition_id=stream_def_id,
parent_data_product_id=data_product_id)
parameter_function = ParameterFunction(name='linear_corr',
function_type=PFT.NUMEXPR,
function='a * x + b',
args=['x', 'a', 'b'])
pf_id = self.dataset_management.create_parameter_function(
parameter_function)
dpd = DataProcessDefinition(name='linear_corr',
description='Linear Correction')
self.data_process_management.create_data_process_definition(dpd, pf_id)
parameter = ParameterContext(name='temperature_corrected',
parameter_type='function',
parameter_function_id=pf_id,
parameter_function_map={
'x': 'temp',
'a': 1.03,
'b': 0.25
},
value_encoding='float32',
units='deg_C',
display_name='Temperature Corrected')
p_id = self.dataset_management.create_parameter(parameter)
# Add it to the parent or parsed data product
self.data_product_management.add_parameter_to_data_product(
p_id, data_product_id)
# Then update the child's stream definition to include it
stream_def = self.pubsub_management.read_stream_definition(
stream_def_id)
stream_def.available_fields.append('temperature_corrected')
self.resource_registry.update(stream_def)
dataset_id = self.RR2.find_dataset_id_of_data_product_using_has_dataset(
data_product_id)
# For some reason, it takes numerous seconds of yielding with gevent for the coverage to actually save...
gevent.sleep(10)
granule = self.data_retriever.retrieve(dataset_id)
rdt = RecordDictionaryTool.load_from_granule(granule)
np.testing.assert_array_almost_equal(
rdt['temperature_corrected'],
np.arange(30, dtype=np.float32) * 1.03 + 0.25,
decimal=5)
def test_lookup_values(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_lookups()
stream_def_id = self.pubsubcli.create_stream_definition(
'lookup', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsubcli.delete_stream_definition, stream_def_id)
data_product = DataProduct(name='lookup data product')
tdom, sdom = time_series_domain()
data_product.temporal_domain = tdom.dump()
data_product.spatial_domain = sdom.dump()
data_product_id = self.dpsc_cli.create_data_product(
data_product, stream_definition_id=stream_def_id)
self.addCleanup(self.dpsc_cli.delete_data_product, data_product_id)
data_producer = DataProducer(name='producer')
data_producer.producer_context = DataProcessProducerContext()
data_producer.producer_context.configuration['qc_keys'] = [
'offset_document'
]
data_producer_id, _ = self.rrclient.create(data_producer)
self.addCleanup(self.rrclient.delete, data_producer_id)
assoc, _ = self.rrclient.create_association(
subject=data_product_id,
object=data_producer_id,
predicate=PRED.hasDataProducer)
self.addCleanup(self.rrclient.delete_association, assoc)
document_keys = self.damsclient.list_qc_references(data_product_id)
self.assertEquals(document_keys, ['offset_document'])
svm = StoredValueManager(self.container)
svm.stored_value_cas('offset_document', {'offset_a': 2.0})
self.dpsc_cli.activate_data_product_persistence(data_product_id)
dataset_ids, _ = self.rrclient.find_objects(subject=data_product_id,
predicate=PRED.hasDataset,
id_only=True)
dataset_id = dataset_ids[0]
dataset_monitor = DatasetMonitor(dataset_id)
self.addCleanup(dataset_monitor.stop)
rdt = RecordDictionaryTool(stream_definition_id=stream_def_id)
rdt['time'] = [0]
rdt['temp'] = [20.]
granule = rdt.to_granule()
stream_ids, _ = self.rrclient.find_objects(subject=data_product_id,
predicate=PRED.hasStream,
id_only=True)
stream_id = stream_ids[0]
route = self.pubsubcli.read_stream_route(stream_id=stream_id)
publisher = StandaloneStreamPublisher(stream_id, route)
publisher.publish(granule)
self.assertTrue(dataset_monitor.event.wait(10))
granule = self.data_retriever.retrieve(dataset_id)
rdt2 = RecordDictionaryTool.load_from_granule(granule)
np.testing.assert_array_equal(rdt['temp'], rdt2['temp'])
np.testing.assert_array_almost_equal(rdt2['calibrated'],
np.array([22.0]))
svm.stored_value_cas('updated_document', {'offset_a': 3.0})
dataset_monitor = DatasetMonitor(dataset_id)
self.addCleanup(dataset_monitor.stop)
ep = EventPublisher(event_type=OT.ExternalReferencesUpdatedEvent)
ep.publish_event(origin=data_product_id,
reference_keys=['updated_document'])
rdt = RecordDictionaryTool(stream_definition_id=stream_def_id)
rdt['time'] = [1]
rdt['temp'] = [20.]
granule = rdt.to_granule()
gevent.sleep(2) # Yield so that the event goes through
publisher.publish(granule)
self.assertTrue(dataset_monitor.event.wait(10))
granule = self.data_retriever.retrieve(dataset_id)
rdt2 = RecordDictionaryTool.load_from_granule(granule)
np.testing.assert_array_equal(rdt2['temp'], np.array([20., 20.]))
np.testing.assert_array_almost_equal(rdt2['calibrated'],
np.array([22.0, 23.0]))
def test_pydap(self):
if not CFG.get_safe('bootstrap.use_pydap', False):
raise unittest.SkipTest('PyDAP is off (bootstrap.use_pydap)')
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition(
'example', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition,
stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name='example')
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(
dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product,
data_product_id)
self.data_product_management.activate_data_product_persistence(
data_product_id)
self.addCleanup(
self.data_product_management.suspend_data_product_persistence,
data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id,
PRED.hasDataset,
id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 10)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.event.wait(10))
gevent.sleep(
1) # Yield to other greenlets, had an issue with connectivity
pydap_host = CFG.get_safe('server.pydap.host', 'localhost')
pydap_port = CFG.get_safe('server.pydap.port', 8001)
url = 'http://%s:%s/%s' % (pydap_host, pydap_port, dataset_id)
for i in xrange(
3
): # Do it three times to test that the cache doesn't corrupt the requests/responses
ds = open_url(url)
np.testing.assert_array_equal(ds['time'][:], np.arange(10))
untested = []
for k, v in rdt.iteritems():
if k == rdt.temporal_parameter:
continue
context = rdt.context(k)
if isinstance(context.param_type, QuantityType):
np.testing.assert_array_equal(ds[k][k][:][0], rdt[k])
elif isinstance(context.param_type, ArrayType):
if context.param_type.inner_encoding is None:
values = np.empty(rdt[k].shape, dtype='O')
for i, obj in enumerate(rdt[k]):
values[i] = str(obj)
np.testing.assert_array_equal(ds[k][k][:][0], values)
elif len(rdt[k].shape) > 1:
values = np.empty(rdt[k].shape[0], dtype='O')
for i in xrange(rdt[k].shape[0]):
values[i] = ','.join(
map(lambda x: str(x), rdt[k][i].tolist()))
elif isinstance(context.param_type, ConstantType):
np.testing.assert_array_equal(ds[k][k][:][0], rdt[k])
elif isinstance(context.param_type, CategoryType):
np.testing.assert_array_equal(ds[k][k][:][0], rdt[k])
else:
untested.append('%s (%s)' % (k, context.param_type))
if untested:
raise AssertionError('Untested parameters: %s' % untested)
def test_derived_data_product(self):
pdict_id = self.dataset_management.read_parameter_dictionary_by_name(
'ctd_parsed_param_dict', id_only=True)
ctd_stream_def_id = self.pubsubcli.create_stream_definition(
name='ctd parsed', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsubcli.delete_stream_definition,
ctd_stream_def_id)
dp = DataProduct(name='Instrument DP')
dp_id = self.dpsc_cli.create_data_product(
dp, stream_definition_id=ctd_stream_def_id)
self.addCleanup(self.dpsc_cli.force_delete_data_product, dp_id)
self.dpsc_cli.activate_data_product_persistence(dp_id)
self.addCleanup(self.dpsc_cli.suspend_data_product_persistence, dp_id)
dataset_ids, _ = self.rrclient.find_objects(subject=dp_id,
predicate=PRED.hasDataset,
id_only=True)
if not dataset_ids:
raise NotFound("Data Product %s dataset does not exist" %
str(dp_id))
dataset_id = dataset_ids[0]
# Make the derived data product
simple_stream_def_id = self.pubsubcli.create_stream_definition(
name='TEMPWAT stream def',
parameter_dictionary_id=pdict_id,
available_fields=['time', 'temp'])
tempwat_dp = DataProduct(name='TEMPWAT',
category=DataProductTypeEnum.DERIVED)
tempwat_dp_id = self.dpsc_cli.create_data_product(
tempwat_dp,
stream_definition_id=simple_stream_def_id,
parent_data_product_id=dp_id)
self.addCleanup(self.dpsc_cli.delete_data_product, tempwat_dp_id)
# Check that the streams associated with the data product are persisted with
stream_ids, _ = self.rrclient.find_objects(dp_id, PRED.hasStream,
RT.Stream, True)
for stream_id in stream_ids:
self.assertTrue(self.ingestclient.is_persisted(stream_id))
stream_id = stream_ids[0]
route = self.pubsubcli.read_stream_route(stream_id=stream_id)
rdt = RecordDictionaryTool(stream_definition_id=ctd_stream_def_id)
rdt['time'] = np.arange(20)
rdt['temp'] = np.arange(20)
rdt['pressure'] = np.arange(20)
publisher = StandaloneStreamPublisher(stream_id, route)
dataset_modified = Event()
def cb(*args, **kwargs):
dataset_modified.set()
es = EventSubscriber(event_type=OT.DatasetModified,
callback=cb,
origin=dataset_id,
auto_delete=True)
es.start()
self.addCleanup(es.stop)
publisher.publish(rdt.to_granule())
self.assertTrue(dataset_modified.wait(30))
tempwat_dataset_ids, _ = self.rrclient.find_objects(tempwat_dp_id,
PRED.hasDataset,
id_only=True)
tempwat_dataset_id = tempwat_dataset_ids[0]
granule = self.data_retriever.retrieve(
tempwat_dataset_id, delivery_format=simple_stream_def_id)
rdt = RecordDictionaryTool.load_from_granule(granule)
np.testing.assert_array_equal(rdt['time'], np.arange(20))
self.assertEquals(set(rdt.fields), set(['time', 'temp']))
def _setup_resources(self):
# TODO: some or all of this (or some variation) should move to DAMS'
# Build the test resources for the dataset
dams_cli = DataAcquisitionManagementServiceClient()
dpms_cli = DataProductManagementServiceClient()
rr_cli = ResourceRegistryServiceClient()
eda = ExternalDatasetAgent()
eda_id = dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = dams_cli.create_external_dataset_agent_instance(eda_inst, external_dataset_agent_id=eda_id)
# Create and register the necessary resources/objects
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(), contact=ContactInformation())
dprov.contact.name = 'Christopher Mueller'
dprov.contact.email = '*****@*****.**'
# Create DataSource
dsrc = DataSource(protocol_type='FILE', institution=Institution(), contact=ContactInformation())
dsrc.connection_params['base_data_url'] = ''
dsrc.contact.name='Tim Giguere'
dsrc.contact.email = '*****@*****.**'
# Create ExternalDataset
ds_name = 'slocum_test_dataset'
dset = ExternalDataset(name=ds_name, dataset_description=DatasetDescription(), update_description=UpdateDescription(), contact=ContactInformation())
dset.dataset_description.parameters['dataset_path'] = 'test_data/ru05-2012-021-0-0-sbd.dat'
dset.dataset_description.parameters['temporal_dimension'] = None
dset.dataset_description.parameters['zonal_dimension'] = None
dset.dataset_description.parameters['meridional_dimension'] = None
dset.dataset_description.parameters['vertical_dimension'] = None
dset.dataset_description.parameters['variables'] = [
'c_wpt_y_lmc',
'sci_water_cond',
'm_y_lmc',
'u_hd_fin_ap_inflection_holdoff',
'sci_m_present_time',
'm_leakdetect_voltage_forward',
'sci_bb3slo_b660_scaled',
'c_science_send_all',
'm_gps_status',
'm_water_vx',
'm_water_vy',
'c_heading',
'sci_fl3slo_chlor_units',
'u_hd_fin_ap_gain',
'm_vacuum',
'u_min_water_depth',
'm_gps_lat',
'm_veh_temp',
'f_fin_offset',
'u_hd_fin_ap_hardover_holdoff',
'c_alt_time',
'm_present_time',
'm_heading',
'sci_bb3slo_b532_scaled',
'sci_fl3slo_cdom_units',
'm_fin',
'x_cycle_overrun_in_ms',
'sci_water_pressure',
'u_hd_fin_ap_igain',
'sci_fl3slo_phyco_units',
'm_battpos',
'sci_bb3slo_b470_scaled',
'm_lat',
'm_gps_lon',
'sci_ctd41cp_timestamp',
'm_pressure',
'c_wpt_x_lmc',
'c_ballast_pumped',
'x_lmc_xy_source',
'm_lon',
'm_avg_speed',
'sci_water_temp',
'u_pitch_ap_gain',
'm_roll',
'm_tot_num_inflections',
'm_x_lmc',
'u_pitch_ap_deadband',
'm_final_water_vy',
'm_final_water_vx',
'm_water_depth',
'm_leakdetect_voltage',
'u_pitch_max_delta_battpos',
'm_coulomb_amphr',
'm_pitch',
]
# Create DataSourceModel
dsrc_model = DataSourceModel(name='slocum_model')
dsrc_model.model = 'SLOCUM'
dsrc_model.data_handler_module = 'N/A'
dsrc_model.data_handler_class = 'N/A'
## Run everything through DAMS
ds_id = dams_cli.create_external_dataset(external_dataset=dset)
ext_dprov_id = dams_cli.create_external_data_provider(external_data_provider=dprov)
ext_dsrc_id = dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = dams_cli.register_external_data_set(external_dataset_id=ds_id)
# Or using each method
dams_cli.assign_data_source_to_external_data_provider(data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
dams_cli.assign_data_source_to_data_model(data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
dams_cli.assign_external_dataset_to_data_source(external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
dams_cli.assign_external_dataset_to_agent_instance(external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=self.eda_id, agent_instance_id=self.eda_inst_id)
# Generate the data product and associate it to the ExternalDataset
dprod = DataProduct(name='slocum_parsed_product', description='parsed slocum product')
dproduct_id = dpms_cli.create_data_product(data_product=dprod)
dams_cli.assign_data_product(input_resource_id=ds_id, data_product_id=dproduct_id, create_stream=True)
stream_id, assn = rr_cli.find_objects(subject=dproduct_id, predicate=PRED.hasStream, object_type=RT.Stream, id_only=True)
stream_id = stream_id[0]
log.info('Created resources: {0}'.format({'ExternalDataset':ds_id, 'ExternalDataProvider':ext_dprov_id, 'DataSource':ext_dsrc_id, 'DataSourceModel':ext_dsrc_model_id, 'DataProducer':dproducer_id, 'DataProduct':dproduct_id, 'Stream':stream_id}))
#CBM: Use CF standard_names
ttool = TaxyTool()
ttool.add_taxonomy_set('c_wpt_y_lmc'),
ttool.add_taxonomy_set('sci_water_cond'),
ttool.add_taxonomy_set('m_y_lmc'),
ttool.add_taxonomy_set('u_hd_fin_ap_inflection_holdoff'),
ttool.add_taxonomy_set('sci_m_present_time'),
ttool.add_taxonomy_set('m_leakdetect_voltage_forward'),
ttool.add_taxonomy_set('sci_bb3slo_b660_scaled'),
ttool.add_taxonomy_set('c_science_send_all'),
ttool.add_taxonomy_set('m_gps_status'),
ttool.add_taxonomy_set('m_water_vx'),
ttool.add_taxonomy_set('m_water_vy'),
ttool.add_taxonomy_set('c_heading'),
ttool.add_taxonomy_set('sci_fl3slo_chlor_units'),
ttool.add_taxonomy_set('u_hd_fin_ap_gain'),
ttool.add_taxonomy_set('m_vacuum'),
ttool.add_taxonomy_set('u_min_water_depth'),
ttool.add_taxonomy_set('m_gps_lat'),
ttool.add_taxonomy_set('m_veh_temp'),
ttool.add_taxonomy_set('f_fin_offset'),
ttool.add_taxonomy_set('u_hd_fin_ap_hardover_holdoff'),
ttool.add_taxonomy_set('c_alt_time'),
ttool.add_taxonomy_set('m_present_time'),
ttool.add_taxonomy_set('m_heading'),
ttool.add_taxonomy_set('sci_bb3slo_b532_scaled'),
ttool.add_taxonomy_set('sci_fl3slo_cdom_units'),
ttool.add_taxonomy_set('m_fin'),
ttool.add_taxonomy_set('x_cycle_overrun_in_ms'),
ttool.add_taxonomy_set('sci_water_pressure'),
ttool.add_taxonomy_set('u_hd_fin_ap_igain'),
ttool.add_taxonomy_set('sci_fl3slo_phyco_units'),
ttool.add_taxonomy_set('m_battpos'),
ttool.add_taxonomy_set('sci_bb3slo_b470_scaled'),
ttool.add_taxonomy_set('m_lat'),
ttool.add_taxonomy_set('m_gps_lon'),
ttool.add_taxonomy_set('sci_ctd41cp_timestamp'),
ttool.add_taxonomy_set('m_pressure'),
ttool.add_taxonomy_set('c_wpt_x_lmc'),
ttool.add_taxonomy_set('c_ballast_pumped'),
ttool.add_taxonomy_set('x_lmc_xy_source'),
ttool.add_taxonomy_set('m_lon'),
ttool.add_taxonomy_set('m_avg_speed'),
ttool.add_taxonomy_set('sci_water_temp'),
ttool.add_taxonomy_set('u_pitch_ap_gain'),
ttool.add_taxonomy_set('m_roll'),
ttool.add_taxonomy_set('m_tot_num_inflections'),
ttool.add_taxonomy_set('m_x_lmc'),
ttool.add_taxonomy_set('u_pitch_ap_deadband'),
ttool.add_taxonomy_set('m_final_water_vy'),
ttool.add_taxonomy_set('m_final_water_vx'),
ttool.add_taxonomy_set('m_water_depth'),
ttool.add_taxonomy_set('m_leakdetect_voltage'),
ttool.add_taxonomy_set('u_pitch_max_delta_battpos'),
ttool.add_taxonomy_set('m_coulomb_amphr'),
ttool.add_taxonomy_set('m_pitch'),
#CBM: Eventually, probably want to group this crap somehow - not sure how yet...
# Create the logger for receiving publications
self.create_stream_and_logger(name='slocum',stream_id=stream_id)
self.EDA_RESOURCE_ID = ds_id
self.EDA_NAME = ds_name
self.DVR_CONFIG['dh_cfg'] = {
'TESTING':True,
'stream_id':stream_id,
'external_dataset_res':dset,
'taxonomy':ttool.dump(),
'data_producer_id':dproducer_id,#CBM: Should this be put in the main body of the config - with mod & cls?
'max_records':20,
}
def test_lookup_values(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_lookups()
stream_def_id = self.pubsubcli.create_stream_definition('lookup', parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsubcli.delete_stream_definition, stream_def_id)
data_product = DataProduct(name='lookup data product')
tdom, sdom = time_series_domain()
data_product.temporal_domain = tdom.dump()
data_product.spatial_domain = sdom.dump()
data_product_id = self.dpsc_cli.create_data_product(data_product, stream_definition_id=stream_def_id)
self.addCleanup(self.dpsc_cli.delete_data_product, data_product_id)
data_producer = DataProducer(name='producer')
data_producer.producer_context = DataProcessProducerContext()
data_producer.producer_context.configuration['qc_keys'] = ['offset_document']
data_producer_id, _ = self.rrclient.create(data_producer)
self.addCleanup(self.rrclient.delete, data_producer_id)
assoc,_ = self.rrclient.create_association(subject=data_product_id, object=data_producer_id, predicate=PRED.hasDataProducer)
self.addCleanup(self.rrclient.delete_association, assoc)
document_keys = self.damsclient.list_qc_references(data_product_id)
self.assertEquals(document_keys, ['offset_document'])
svm = StoredValueManager(self.container)
svm.stored_value_cas('offset_document', {'offset_a':2.0})
self.dpsc_cli.activate_data_product_persistence(data_product_id)
dataset_ids, _ = self.rrclient.find_objects(subject=data_product_id, predicate=PRED.hasDataset, id_only=True)
dataset_id = dataset_ids[0]
dataset_monitor = DatasetMonitor(dataset_id)
self.addCleanup(dataset_monitor.stop)
rdt = RecordDictionaryTool(stream_definition_id=stream_def_id)
rdt['time'] = [0]
rdt['temp'] = [20.]
granule = rdt.to_granule()
stream_ids, _ = self.rrclient.find_objects(subject=data_product_id, predicate=PRED.hasStream, id_only=True)
stream_id = stream_ids[0]
route = self.pubsubcli.read_stream_route(stream_id=stream_id)
publisher = StandaloneStreamPublisher(stream_id, route)
publisher.publish(granule)
self.assertTrue(dataset_monitor.event.wait(10))
granule = self.data_retriever.retrieve(dataset_id)
rdt2 = RecordDictionaryTool.load_from_granule(granule)
np.testing.assert_array_equal(rdt['temp'], rdt2['temp'])
np.testing.assert_array_almost_equal(rdt2['calibrated'], np.array([22.0]))
svm.stored_value_cas('updated_document', {'offset_a':3.0})
dataset_monitor = DatasetMonitor(dataset_id)
self.addCleanup(dataset_monitor.stop)
ep = EventPublisher(event_type=OT.ExternalReferencesUpdatedEvent)
ep.publish_event(origin=data_product_id, reference_keys=['updated_document'])
rdt = RecordDictionaryTool(stream_definition_id=stream_def_id)
rdt['time'] = [1]
rdt['temp'] = [20.]
granule = rdt.to_granule()
gevent.sleep(2) # Yield so that the event goes through
publisher.publish(granule)
self.assertTrue(dataset_monitor.event.wait(10))
granule = self.data_retriever.retrieve(dataset_id)
rdt2 = RecordDictionaryTool.load_from_granule(granule)
np.testing.assert_array_equal(rdt2['temp'],np.array([20.,20.]))
np.testing.assert_array_almost_equal(rdt2['calibrated'], np.array([22.0,23.0]))
def test_get_data_product_provenance_report(self):
#Create a test device
device_obj = Device(name='Device1', description='test instrument site')
device_id, _ = self.rrclient.create(device_obj)
self.addCleanup(self.rrclient.delete, device_id)
#Create a test DataProduct
data_product1_obj = DataProduct(name='DataProduct1',
description='test data product 1')
data_product1_id, _ = self.rrclient.create(data_product1_obj)
self.addCleanup(self.rrclient.delete, data_product1_id)
#Create a test DataProcess
data_process_obj = DataProcess(name='DataProcess',
description='test data process')
data_process_id, _ = self.rrclient.create(data_process_obj)
self.addCleanup(self.rrclient.delete, data_process_id)
#Create a second test DataProduct
data_product2_obj = DataProduct(name='DataProduct2',
description='test data product 2')
data_product2_id, _ = self.rrclient.create(data_product2_obj)
self.addCleanup(self.rrclient.delete, data_product2_id)
#Create a test DataProducer
data_producer_obj = DataProducer(name='DataProducer',
description='test data producer')
data_producer_id, rev = self.rrclient.create(data_producer_obj)
#Link the DataProcess to the second DataProduct manually
assoc_id, _ = self.rrclient.create_association(
subject=data_process_id,
predicate=PRED.hasInputProduct,
object=data_product2_id)
self.addCleanup(self.rrclient.delete_association, assoc_id)
# Register the instrument and process. This links the device and the data process
# with their own producers
self.damsclient.register_instrument(device_id)
self.addCleanup(self.damsclient.unregister_instrument, device_id)
self.damsclient.register_process(data_process_id)
self.addCleanup(self.damsclient.unregister_process, data_process_id)
#Manually link the first DataProduct with the test DataProducer
assoc_id, _ = self.rrclient.create_association(
subject=data_product1_id,
predicate=PRED.hasDataProducer,
object=data_producer_id)
#Get the DataProducer linked to the DataProcess (created in register_process above)
#Associate that with with DataProduct1's DataProducer
data_process_producer_ids, _ = self.rrclient.find_objects(
subject=data_process_id,
predicate=PRED.hasDataProducer,
object_type=RT.DataProducer,
id_only=True)
assoc_id, _ = self.rrclient.create_association(
subject=data_process_producer_ids[0],
predicate=PRED.hasParent,
object=data_producer_id)
self.addCleanup(self.rrclient.delete_association, assoc_id)
#Get the DataProducer linked to the Device (created in register_instrument
#Associate that with the DataProcess's DataProducer
device_producer_ids, _ = self.rrclient.find_objects(
subject=device_id,
predicate=PRED.hasDataProducer,
object_type=RT.DataProducer,
id_only=True)
assoc_id, _ = self.rrclient.create_association(
subject=data_producer_id,
predicate=PRED.hasParent,
object=device_producer_ids[0])
#Create the links between the Device, DataProducts, DataProcess, and all DataProducers
self.damsclient.assign_data_product(input_resource_id=device_id,
data_product_id=data_product1_id)
self.addCleanup(self.damsclient.unassign_data_product, device_id,
data_product1_id)
self.damsclient.assign_data_product(input_resource_id=data_process_id,
data_product_id=data_product2_id)
self.addCleanup(self.damsclient.unassign_data_product, data_process_id,
data_product2_id)
#Traverse through the relationships to get the links between objects
res = self.dpmsclient.get_data_product_provenance_report(
data_product2_id)
#Make sure there are four keys
self.assertEqual(len(res.keys()), 4)
parent_count = 0
config_count = 0
for v in res.itervalues():
if 'parent' in v:
parent_count += 1
if 'config' in v:
config_count += 1
#Make sure there are three parents and four configs
self.assertEqual(parent_count, 3)
self.assertEqual(config_count, 4)
def _setup_resources(self):
# TODO: some or all of this (or some variation) should move to DAMS'
# Build the test resources for the dataset
dams_cli = DataAcquisitionManagementServiceClient()
dpms_cli = DataProductManagementServiceClient()
rr_cli = ResourceRegistryServiceClient()
eda = ExternalDatasetAgent()
eda_id = dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = dams_cli.create_external_dataset_agent_instance(
eda_inst, external_dataset_agent_id=eda_id)
# Create and register the necessary resources/objects
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(),
contact=ContactInformation())
dprov.contact.name = 'Christopher Mueller'
dprov.contact.email = '*****@*****.**'
# Create DataSource
dsrc = DataSource(protocol_type='DAP',
institution=Institution(),
contact=ContactInformation())
dsrc.connection_params['base_data_url'] = ''
dsrc.contact.name = 'Tim Giguere'
dsrc.contact.email = '*****@*****.**'
# Create ExternalDataset
ds_name = 'usgs_test_dataset'
dset = ExternalDataset(name=ds_name,
dataset_description=DatasetDescription(),
update_description=UpdateDescription(),
contact=ContactInformation())
# The usgs.nc test dataset is a download of the R1 dataset found here:
# http://thredds-test.oceanobservatories.org/thredds/dodsC/ooiciData/E66B1A74-A684-454A-9ADE-8388C2C634E5.ncml
dset.dataset_description.parameters[
'dataset_path'] = 'test_data/usgs.nc'
dset.dataset_description.parameters['temporal_dimension'] = 'time'
dset.dataset_description.parameters['zonal_dimension'] = 'lon'
dset.dataset_description.parameters['meridional_dimension'] = 'lat'
dset.dataset_description.parameters['vertical_dimension'] = 'z'
dset.dataset_description.parameters['variables'] = [
'water_temperature',
'streamflow',
'water_temperature_bottom',
'water_temperature_middle',
'specific_conductance',
'data_qualifier',
]
# Create DataSourceModel
dsrc_model = DataSourceModel(name='dap_model')
dsrc_model.model = 'DAP'
dsrc_model.data_handler_module = 'N/A'
dsrc_model.data_handler_class = 'N/A'
## Run everything through DAMS
ds_id = dams_cli.create_external_dataset(external_dataset=dset)
ext_dprov_id = dams_cli.create_external_data_provider(
external_data_provider=dprov)
ext_dsrc_id = dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = dams_cli.register_external_data_set(
external_dataset_id=ds_id)
# Or using each method
dams_cli.assign_data_source_to_external_data_provider(
data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
dams_cli.assign_data_source_to_data_model(
data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
dams_cli.assign_external_dataset_to_data_source(
external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
dams_cli.assign_external_dataset_to_agent_instance(
external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=self.eda_id, agent_instance_id=self.eda_inst_id)
# Generate the data product and associate it to the ExternalDataset
dprod = DataProduct(name='usgs_parsed_product',
description='parsed usgs product')
dproduct_id = dpms_cli.create_data_product(data_product=dprod)
dams_cli.assign_data_product(input_resource_id=ds_id,
data_product_id=dproduct_id,
create_stream=True)
stream_id, assn = rr_cli.find_objects(subject=dproduct_id,
predicate=PRED.hasStream,
object_type=RT.Stream,
id_only=True)
stream_id = stream_id[0]
log.info('Created resources: {0}'.format({
'ExternalDataset': ds_id,
'ExternalDataProvider': ext_dprov_id,
'DataSource': ext_dsrc_id,
'DataSourceModel': ext_dsrc_model_id,
'DataProducer': dproducer_id,
'DataProduct': dproduct_id,
'Stream': stream_id
}))
#CBM: Use CF standard_names
ttool = TaxyTool()
ttool.add_taxonomy_set('time', 'time')
ttool.add_taxonomy_set('lon', 'longitude')
ttool.add_taxonomy_set('lat', 'latitude')
ttool.add_taxonomy_set('z', 'water depth')
ttool.add_taxonomy_set('water_temperature',
'average water temperature')
ttool.add_taxonomy_set('water_temperature_bottom',
'water temperature at bottom of water column')
ttool.add_taxonomy_set('water_temperature_middle',
'water temperature at middle of water column')
ttool.add_taxonomy_set('streamflow', 'flow velocity of stream')
ttool.add_taxonomy_set('specific_conductance',
'specific conductance of water')
ttool.add_taxonomy_set('data_qualifier', 'data qualifier flag')
ttool.add_taxonomy_set('coords',
'This group contains coordinate parameters')
ttool.add_taxonomy_set('data', 'This group contains data parameters')
# Create the logger for receiving publications
self.create_stream_and_logger(name='usgs', stream_id=stream_id)
self.EDA_RESOURCE_ID = ds_id
self.EDA_NAME = ds_name
self.DVR_CONFIG['dh_cfg'] = {
'TESTING': True,
'stream_id': stream_id,
'taxonomy': ttool.dump(),
'data_producer_id':
dproducer_id, #CBM: Should this be put in the main body of the config - with mod & cls?
'max_records': 4,
}
def _setup_ncom(self):
# TODO: some or all of this (or some variation) should move to DAMS
# Create and register the necessary resources/objects
eda = ExternalDatasetAgent()
eda_id = self.dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = self.dams_cli.create_external_dataset_agent_instance(
eda_inst, external_dataset_agent_id=eda_id)
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(),
contact=ContactInformation())
# dprov.institution.name = "OOI CGSN"
dprov.contact.name = "Robert Weller"
dprov.contact.email = "*****@*****.**"
# Create DataSource
dsrc = DataSource(protocol_type="DAP",
institution=Institution(),
contact=ContactInformation())
# dsrc.connection_params["base_data_url"] = "http://ooi.whoi.edu/thredds/dodsC/"
dsrc.connection_params["base_data_url"] = ""
dsrc.contact.name = "Rich Signell"
dsrc.contact.email = "*****@*****.**"
# Create ExternalDataset
dset = ExternalDataset(name="test",
dataset_description=DatasetDescription(),
update_description=UpdateDescription(),
contact=ContactInformation())
# dset.dataset_description.parameters["dataset_path"] = "ooi/AS02CPSM_R_M.nc"
dset.dataset_description.parameters[
"dataset_path"] = "test_data/ncom.nc"
dset.dataset_description.parameters["temporal_dimension"] = "time"
dset.dataset_description.parameters["zonal_dimension"] = "lon"
dset.dataset_description.parameters["meridional_dimension"] = "lat"
# Create DataSourceModel
dsrc_model = DataSourceModel(name="dap_model")
dsrc_model.model = "DAP"
dsrc_model.data_handler_module = "eoi.agent.handler.dap_external_data_handler"
dsrc_model.data_handler_class = "DapExternalDataHandler"
## Run everything through DAMS
ds_id = self.ncom_ds_id = self.dams_cli.create_external_dataset(
external_dataset=dset)
ext_dprov_id = self.dams_cli.create_external_data_provider(
external_data_provider=dprov)
ext_dsrc_id = self.dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = self.dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = self.dams_cli.register_external_data_set(
external_dataset_id=ds_id)
## Associate everything
# Convenience method
# self.dams_cli.assign_eoi_resources(external_data_provider_id=ext_dprov_id, data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id, external_dataset_id=ds_id, external_data_agent_id=eda_id, agent_instance_id=eda_inst_id)
# Or using each method
self.dams_cli.assign_data_source_to_external_data_provider(
data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
self.dams_cli.assign_data_source_to_data_model(
data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
self.dams_cli.assign_external_dataset_to_data_source(
external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
self.dams_cli.assign_external_dataset_to_agent_instance(
external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# self.dams_cli.assign_external_dataset_agent_to_data_model(external_data_agent_id=eda_id, data_source_model_id=ext_dsrc_model_id)
# self.dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=eda_id, agent_instance_id=eda_inst_id)
# Generate the data product and associate it to the ExternalDataset
dprod = DataProduct(name='ncom_product',
description='raw ncom product')
dproduct_id = self.dpms_cli.create_data_product(data_product=dprod)
self.dams_cli.assign_data_product(input_resource_id=ds_id,
data_product_id=dproduct_id,
create_stream=True)
def test_pydap(self):
ph = ParameterHelper(self.dataset_management, self.addCleanup)
pdict_id = ph.create_extended_parsed()
stream_def_id = self.pubsub_management.create_stream_definition("example", parameter_dictionary_id=pdict_id)
self.addCleanup(self.pubsub_management.delete_stream_definition, stream_def_id)
tdom, sdom = time_series_domain()
dp = DataProduct(name="example")
dp.spatial_domain = sdom.dump()
dp.temporal_domain = tdom.dump()
data_product_id = self.data_product_management.create_data_product(dp, stream_def_id)
self.addCleanup(self.data_product_management.delete_data_product, data_product_id)
self.data_product_management.activate_data_product_persistence(data_product_id)
self.addCleanup(self.data_product_management.suspend_data_product_persistence, data_product_id)
dataset_id = self.resource_registry.find_objects(data_product_id, PRED.hasDataset, id_only=True)[0][0]
monitor = DatasetMonitor(dataset_id)
self.addCleanup(monitor.stop)
rdt = ph.get_rdt(stream_def_id)
ph.fill_rdt(rdt, 10)
ph.publish_rdt_to_data_product(data_product_id, rdt)
self.assertTrue(monitor.wait())
gevent.sleep(1) # Yield to other greenlets, had an issue with connectivity
pydap_host = CFG.get_safe("server.pydap.host", "localhost")
pydap_port = CFG.get_safe("server.pydap.port", 8001)
url = "http://%s:%s/%s" % (pydap_host, pydap_port, data_product_id)
for i in xrange(3): # Do it three times to test that the cache doesn't corrupt the requests/responses
ds = open_url(url)
np.testing.assert_array_equal(list(ds["data"]["time"]), np.arange(10))
untested = []
for k, v in rdt.iteritems():
if k == rdt.temporal_parameter:
continue
context = rdt.context(k)
if isinstance(context.param_type, QuantityType):
np.testing.assert_array_equal(list(ds["data"][k]), rdt[k])
elif isinstance(context.param_type, ArrayType):
if context.param_type.inner_encoding is None:
values = np.empty(rdt[k].shape, dtype="O")
for i, obj in enumerate(rdt[k]):
values[i] = str(obj)
np.testing.assert_array_equal(list(ds["data"][k]), values)
elif len(rdt[k].shape) > 1:
values = np.empty(rdt[k].shape[0], dtype="O")
for i in xrange(rdt[k].shape[0]):
values[i] = ",".join(map(lambda x: str(x), rdt[k][i].tolist()))
elif isinstance(context.param_type, ConstantType):
np.testing.assert_array_equal(list(ds["data"][k]), rdt[k])
elif isinstance(context.param_type, CategoryType):
np.testing.assert_array_equal(list(ds["data"][k]), rdt[k])
else:
untested.append("%s (%s)" % (k, context.param_type))
if untested:
raise AssertionError("Untested parameters: %s" % untested)
def _setup_hfr(self):
# TODO: some or all of this (or some variation) should move to DAMS
# Create and register the necessary resources/objects
eda = ExternalDatasetAgent()
eda_id = self.dams_cli.create_external_dataset_agent(eda)
eda_inst = ExternalDatasetAgentInstance()
eda_inst_id = self.dams_cli.create_external_dataset_agent_instance(
eda_inst, external_dataset_agent_id=eda_id)
# Create DataProvider
dprov = ExternalDataProvider(institution=Institution(),
contact=ContactInformation())
# dprov.institution.name = "HFR UCSD"
# Create DataSource
dsrc = DataSource(protocol_type="DAP",
institution=Institution(),
contact=ContactInformation())
dsrc.connection_params[
"base_data_url"] = "http://hfrnet.ucsd.edu:8080/thredds/dodsC/"
# Create ExternalDataset
dset = ExternalDataset(name="UCSD HFR",
dataset_description=DatasetDescription(),
update_description=UpdateDescription(),
contact=ContactInformation())
dset.dataset_description.parameters[
"dataset_path"] = "HFRNet/USEGC/6km/hourly/RTV"
# dset.dataset_description.parameters["dataset_path"] = "test_data/hfr.nc"
dset.dataset_description.parameters["temporal_dimension"] = "time"
dset.dataset_description.parameters["zonal_dimension"] = "lon"
dset.dataset_description.parameters["meridional_dimension"] = "lat"
# Create DataSourceModel
dsrc_model = DataSourceModel(name="dap_model")
dsrc_model.model = "DAP"
dsrc_model.data_handler_module = "eoi.agent.handler.dap_external_data_handler"
dsrc_model.data_handler_class = "DapExternalDataHandler"
## Run everything through DAMS
ds_id = self.hfr_ds_id = self.dams_cli.create_external_dataset(
external_dataset=dset)
ext_dprov_id = self.dams_cli.create_external_data_provider(
external_data_provider=dprov)
ext_dsrc_id = self.dams_cli.create_data_source(data_source=dsrc)
ext_dsrc_model_id = self.dams_cli.create_data_source_model(dsrc_model)
# Register the ExternalDataset
dproducer_id = self.dams_cli.register_external_data_set(
external_dataset_id=ds_id)
## Associate everything
# Convenience method
# self.dams_cli.assign_eoi_resources(external_data_provider_id=ext_dprov_id, data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id, external_dataset_id=ds_id, external_data_agent_id=eda_id, agent_instance_id=eda_inst_id)
# Or using each method
self.dams_cli.assign_data_source_to_external_data_provider(
data_source_id=ext_dsrc_id, external_data_provider_id=ext_dprov_id)
self.dams_cli.assign_data_source_to_data_model(
data_source_id=ext_dsrc_id, data_source_model_id=ext_dsrc_model_id)
self.dams_cli.assign_external_dataset_to_data_source(
external_dataset_id=ds_id, data_source_id=ext_dsrc_id)
self.dams_cli.assign_external_dataset_to_agent_instance(
external_dataset_id=ds_id, agent_instance_id=eda_inst_id)
# self.dams_cli.assign_external_dataset_agent_to_data_model(external_data_agent_id=eda_id, data_source_model_id=ext_dsrc_model_id)
# self.dams_cli.assign_external_data_agent_to_agent_instance(external_data_agent_id=eda_id, agent_instance_id=eda_inst_id)
# Generate the data product and associate it to the ExternalDataset
dprod = DataProduct(name='hfr_product', description='raw hfr product')
dproduct_id = self.dpms_cli.create_data_product(data_product=dprod)
self.dams_cli.assign_data_product(input_resource_id=ds_id,
data_product_id=dproduct_id,
create_stream=True)