def on_start(self):
'''
Starts the process
'''
log.info('Replay Process Started')
super(ReplayProcess,self).on_start()
dsm_cli = DatasetManagementServiceProcessClient(process=self)
pubsub = PubsubManagementServiceProcessClient(process=self)
self.dataset_id = self.CFG.get_safe('process.dataset_id', None)
self.delivery_format = self.CFG.get_safe('process.delivery_format',{})
self.start_time = self.CFG.get_safe('process.query.start_time', None)
self.end_time = self.CFG.get_safe('process.query.end_time', None)
self.stride_time = self.CFG.get_safe('process.query.stride_time', None)
self.parameters = self.CFG.get_safe('process.query.parameters',None)
self.publish_limit = self.CFG.get_safe('process.query.publish_limit', 10)
self.tdoa = self.CFG.get_safe('process.query.tdoa',None)
self.stream_id = self.CFG.get_safe('process.publish_streams.output', '')
self.stream_def = pubsub.read_stream_definition(stream_id=self.stream_id)
self.stream_def_id = self.stream_def._id
self.replay_thread = None
self.publishing.clear()
self.play.set()
self.end.clear()
if self.dataset_id is None:
raise BadRequest('dataset_id not specified')
self.dataset = dsm_cli.read_dataset(self.dataset_id)
self.pubsub = PubsubManagementServiceProcessClient(process=self)
def on_start(self):
'''
Starts the process
'''
log.info('Replay Process Started')
super(ReplayProcess,self).on_start()
dsm_cli = DatasetManagementServiceProcessClient(process=self)
pubsub = PubsubManagementServiceProcessClient(process=self)
self.dataset_id = self.CFG.get_safe('process.dataset_id', None)
self.delivery_format = self.CFG.get_safe('process.delivery_format',{})
self.start_time = self.CFG.get_safe('process.query.start_time', None)
self.end_time = self.CFG.get_safe('process.query.end_time', None)
self.stride_time = self.CFG.get_safe('process.query.stride_time', None)
self.parameters = self.CFG.get_safe('process.query.parameters',None)
self.publish_limit = self.CFG.get_safe('process.query.publish_limit', 10)
self.tdoa = self.CFG.get_safe('process.query.tdoa',None)
self.stream_id = self.CFG.get_safe('process.publish_streams.output', '')
self.stream_def = pubsub.read_stream_definition(stream_id=self.stream_id)
self.stream_def_id = self.stream_def._id
self.publishing.clear()
self.play.set()
self.end.clear()
if self.dataset_id is None:
raise BadRequest('dataset_id not specified')
self.dataset = dsm_cli.read_dataset(self.dataset_id)
self.pubsub = PubsubManagementServiceProcessClient(process=self)
class BootstrapParameterDefinitions(BootstrapPlugin):
'''
Bootstrap plugin for preloading standard parameter definitions
'''
def on_initial_bootstrap(self, process, config, **kwargs):
self.dataset_management = DatasetManagementServiceProcessClient(
process=process)
self.dict_defs = config.get_safe('process.bootstrap.dict_defs',
'res/config/param_dict_defs.yml')
self.context_path = config.get_safe('process.bootstrap.definitions',
'ion.core.plugin')
self.loader_config = config.get_safe('process.bootstrap.config', {})
contexts = self.load_contexts()
self.load_dictionaries(self.dict_defs, contexts)
def load_contexts(self):
try:
contexts = ParameterLoader.build_contexts(self.context_path,
self.loader_config)
for name, context in contexts.iteritems():
context_id = self.dataset_management.create_parameter_context(
name=name, parameter_context=context.dump())
contexts[name] = context_id
except Exception as e:
print 'Exception %s: %s' % (type(e), e.message)
print 'Loaded %s Parameter Contexts' % len(contexts)
return contexts
def load_dictionaries(self, path, contexts):
try:
body = None
with open(path) as f:
body = yaml.load(f)
for name, context_names in body.iteritems():
temporal_contexts = [
cname for cname in context_names if '*' in cname
]
temporal_context = temporal_contexts[0].strip(
'*') if temporal_contexts else ''
context_names = [
context_name
if '*' not in context_name else context_name.strip('*')
for context_name in context_names
]
context_ids = [
contexts[i] for i in context_names if i in contexts
]
self.dataset_management.create_parameter_dictionary(
name=name,
parameter_context_ids=context_ids,
temporal_context=temporal_context)
except Exception as e:
log.error('Problem loading dictionaries, stopping: %s', e.message)
def on_initial_bootstrap(self, process, config, **kwargs):
self.dataset_management = DatasetManagementServiceProcessClient(
process=process)
self.dict_defs = config.get_safe('process.bootstrap.dict_defs',
'res/config/param_dict_defs.yml')
self.context_path = config.get_safe('process.bootstrap.definitions',
'ion.core.plugin')
self.loader_config = config.get_safe('process.bootstrap.config', {})
contexts = self.load_contexts()
self.load_dictionaries(self.dict_defs, contexts)
def on_start(self):
#print ">>>>>>>>>>>>>>>>>>>>>> MPL CFG = ", self.CFG
self.pubsub_management = PubsubManagementServiceProcessClient(process=self)
self.ssclient = SchedulerServiceProcessClient(process=self)
self.rrclient = ResourceRegistryServiceProcessClient(process=self)
self.data_retriever_client = DataRetrieverServiceProcessClient(process=self)
self.dsm_client = DatasetManagementServiceProcessClient(process=self)
self.pubsub_client = PubsubManagementServiceProcessClient(process = self)
self.stream_info = self.CFG.get_safe('process.publish_streams',{})
self.stream_names = self.stream_info.keys()
self.stream_ids = self.stream_info.values()
if not self.stream_names:
raise BadRequest('MPL Transform has no output streams.')
graph_time_periods= self.CFG.get_safe('graph_time_periods')
# If this is meant to be an event driven process, schedule an event to be generated every few minutes/hours
self.event_timer_interval = self.CFG.get_safe('graph_gen_interval')
if self.event_timer_interval:
event_origin = "Interval_Timer_Matplotlib"
sub = EventSubscriber(event_type="ResourceEvent", callback=self.interval_timer_callback, origin=event_origin)
sub.start()
self.interval_timer_id = self.ssclient.create_interval_timer(start_time="now" , interval=self._str_to_secs(self.event_timer_interval),
event_origin=event_origin, event_subtype="")
super(VizTransformMatplotlibGraphs,self).on_start()
def setUp(self):
# Start container
logging.disable(logging.ERROR)
self._start_container()
self.container.start_rel_from_url('res/deploy/r2deploy.yml')
# simulate preloading
preload_ion_params(self.container)
logging.disable(logging.NOTSET)
#Instantiate a process to represent the test
process=VisualizationServiceTestProcess()
# Now create client to DataProductManagementService
self.rrclient = ResourceRegistryServiceProcessClient(node=self.container.node, process=process)
self.damsclient = DataAcquisitionManagementServiceProcessClient(node=self.container.node, process=process)
self.pubsubclient = PubsubManagementServiceProcessClient(node=self.container.node, process=process)
self.ingestclient = IngestionManagementServiceProcessClient(node=self.container.node, process=process)
self.imsclient = InstrumentManagementServiceProcessClient(node=self.container.node, process=process)
self.dataproductclient = DataProductManagementServiceProcessClient(node=self.container.node, process=process)
self.dataprocessclient = DataProcessManagementServiceProcessClient(node=self.container.node, process=process)
self.datasetclient = DatasetManagementServiceProcessClient(node=self.container.node, process=process)
self.workflowclient = WorkflowManagementServiceProcessClient(node=self.container.node, process=process)
self.process_dispatcher = ProcessDispatcherServiceProcessClient(node=self.container.node, process=process)
self.data_retriever = DataRetrieverServiceProcessClient(node=self.container.node, process=process)
self.vis_client = VisualizationServiceProcessClient(node=self.container.node, process=process)
self.ctd_stream_def = SBE37_CDM_stream_definition()
def on_initial_bootstrap(self, process, config, **kwargs):
self.dataset_management = DatasetManagementServiceProcessClient(process=process)
self.dict_defs = config.get_safe('process.bootstrap.dict_defs','res/config/param_dict_defs.yml')
self.context_path = config.get_safe('process.bootstrap.definitions', 'ion.core.plugin')
self.loader_config = config.get_safe('process.bootstrap.config', {})
contexts = self.load_contexts()
self.load_dictionaries(self.dict_defs, contexts)
class BootstrapParameterDefinitions(BootstrapPlugin):
'''
Bootstrap plugin for preloading standard parameter definitions
'''
def on_initial_bootstrap(self, process, config, **kwargs):
self.dataset_management = DatasetManagementServiceProcessClient(process=process)
self.dict_defs = config.get_safe('process.bootstrap.dict_defs','res/config/param_dict_defs.yml')
self.context_path = config.get_safe('process.bootstrap.definitions', 'ion.core.plugin')
self.loader_config = config.get_safe('process.bootstrap.config', {})
contexts = self.load_contexts()
self.load_dictionaries(self.dict_defs, contexts)
def load_contexts(self):
try:
contexts = ParameterLoader.build_contexts(self.context_path, self.loader_config)
for name, context in contexts.iteritems():
context_id = self.dataset_management.create_parameter_context(name=name, parameter_context=context.dump())
contexts[name] = context_id
except Exception as e:
print 'Exception %s: %s' %(type(e), e.message)
print 'Loaded %s Parameter Contexts' % len(contexts)
return contexts
def load_dictionaries(self, path, contexts):
try:
body = None
with open(path) as f:
body = yaml.load(f)
for name,context_names in body.iteritems():
temporal_contexts = [cname for cname in context_names if '*' in cname]
temporal_context = temporal_contexts[0].strip('*') if temporal_contexts else ''
context_names = [context_name if '*' not in context_name else context_name.strip('*') for context_name in context_names]
context_ids = [contexts[i] for i in context_names if i in contexts]
self.dataset_management.create_parameter_dictionary(name=name,
parameter_context_ids=context_ids,
temporal_context = temporal_context)
except Exception as e:
log.error('Problem loading dictionaries, stopping: %s', e.message)
def on_start(self):
#print ">>>>>>>>>>>>>>>>>>>>>> MPL CFG = ", self.CFG
self.pubsub_management = PubsubManagementServiceProcessClient(
process=self)
self.ssclient = SchedulerServiceProcessClient(process=self)
self.rrclient = ResourceRegistryServiceProcessClient(process=self)
self.data_retriever_client = DataRetrieverServiceProcessClient(
process=self)
self.dsm_client = DatasetManagementServiceProcessClient(process=self)
self.pubsub_client = PubsubManagementServiceProcessClient(process=self)
self.stream_info = self.CFG.get_safe('process.publish_streams', {})
self.stream_names = self.stream_info.keys()
self.stream_ids = self.stream_info.values()
if not self.stream_names:
raise BadRequest('MPL Transform has no output streams.')
graph_time_periods = self.CFG.get_safe('graph_time_periods')
# If this is meant to be an event driven process, schedule an event to be generated every few minutes/hours
self.event_timer_interval = self.CFG.get_safe('graph_gen_interval')
if self.event_timer_interval:
event_origin = "Interval_Timer_Matplotlib"
sub = EventSubscriber(event_type="ResourceEvent",
callback=self.interval_timer_callback,
origin=event_origin)
sub.start()
self.interval_timer_id = self.ssclient.create_interval_timer(
start_time="now",
interval=self._str_to_secs(self.event_timer_interval),
event_origin=event_origin,
event_subtype="")
super(VizTransformMatplotlibGraphs, self).on_start()
class VizTransformMatplotlibGraphs(TransformStreamPublisher, TransformEventListener, TransformStreamListener):
"""
This class is used for instantiating worker processes that have subscriptions to data streams and convert
incoming data from CDM format to Matplotlib graphs
"""
output_bindings = ['graph_image_param_dict']
event_timer_interval = None
def on_start(self):
#print ">>>>>>>>>>>>>>>>>>>>>> MPL CFG = ", self.CFG
self.pubsub_management = PubsubManagementServiceProcessClient(process=self)
self.ssclient = SchedulerServiceProcessClient(process=self)
self.rrclient = ResourceRegistryServiceProcessClient(process=self)
self.data_retriever_client = DataRetrieverServiceProcessClient(process=self)
self.dsm_client = DatasetManagementServiceProcessClient(process=self)
self.pubsub_client = PubsubManagementServiceProcessClient(process = self)
self.stream_info = self.CFG.get_safe('process.publish_streams',{})
self.stream_names = self.stream_info.keys()
self.stream_ids = self.stream_info.values()
if not self.stream_names:
raise BadRequest('MPL Transform has no output streams.')
graph_time_periods= self.CFG.get_safe('graph_time_periods')
# If this is meant to be an event driven process, schedule an event to be generated every few minutes/hours
self.event_timer_interval = self.CFG.get_safe('graph_gen_interval')
if self.event_timer_interval:
event_origin = "Interval_Timer_Matplotlib"
sub = EventSubscriber(event_type="ResourceEvent", callback=self.interval_timer_callback, origin=event_origin)
sub.start()
self.interval_timer_id = self.ssclient.create_interval_timer(start_time="now" , interval=self._str_to_secs(self.event_timer_interval),
event_origin=event_origin, event_subtype="")
super(VizTransformMatplotlibGraphs,self).on_start()
# when tranform is used as a data process
def recv_packet(self, packet, in_stream_route, in_stream_id):
#Check to see if the class instance was set up as a event triggered transform. If yes, skip the packet
if self.event_timer_interval:
return
log.info('Received packet')
mpl_data_granule = VizTransformMatplotlibGraphsAlgorithm.execute(packet, params=self.get_stream_definition())
for stream_name in self.stream_names:
publisher = getattr(self, stream_name)
publisher.publish(mpl_data_granule)
def get_stream_definition(self):
stream_id = self.stream_ids[0]
stream_def = self.pubsub_management.read_stream_definition(stream_id=stream_id)
return stream_def._id
def process_event(self, msg, headers):
return
def interval_timer_callback(self, *args, **kwargs):
#Find out the input data product to this process
in_dp_id = self.CFG.get_safe('in_dp_id')
print " >>>>>>>>>>>>>> IN DP ID from cfg : ", in_dp_id
# get the dataset_id associated with the data_product. Need it to do the data retrieval
ds_ids,_ = self.rrclient.find_objects(in_dp_id, PRED.hasDataset, RT.Dataset, True)
if ds_ids is None or not ds_ids:
return None
# retrieve data for the specified time interval. Setup up query from pass config first
query = {}
param_list_str = self.CFG.get_safe('parameters')
if param_list_str:
query['parameters'] = param_list_str.split(', ')
# append time if not present in list of parameters
if not 'time' in query['parameters']:
query['parameters'].append('time')
query['start_time'] = query['end_time'] = ntplib.system_to_ntp_time(time.time()) # Now
query['stride_time'] = 1
if self.CFG.get_safe('graph_time_period'):
query['start_time'] = query['end_time'] - self._str_to_secs(self.CFG.get_safe('graph_time_period'))
#print " >>>>>>>>>>>>>> QUERY = ", query
#retrieved_granule = self.data_retriever_client.retrieve(ds_ids[0],{'start_time':start_time,'end_time':end_time})
retrieved_granule = self.data_retriever_client.retrieve(ds_ids[0], query=query)
# add extra parameters to query passed in config that are not needed by data retrieval
if self.CFG.get_safe('resolution'):
query['resolution'] = self.CFG.get_safe('resolution')
# send the granule through the Algorithm code to get the matplotlib graphs
mpl_pdict_id = self.dsm_client.read_parameter_dictionary_by_name('graph_image_param_dict',id_only=True)
mpl_stream_def = self.pubsub_client.create_stream_definition('mpl', parameter_dictionary_id=mpl_pdict_id)
fileName = self.CFG.get_safe('graph_time_period')
mpl_data_granule = VizTransformMatplotlibGraphsAlgorithm.execute(retrieved_granule, config=query, params=mpl_stream_def, fileName=fileName)
if mpl_data_granule == None:
return None
# publish on all specified output streams
for stream_name in self.stream_names:
publisher = getattr(self, stream_name)
publisher.publish(mpl_data_granule)
return
def _str_to_secs(self, time_period):
# this method converts commonly used time periods to its actual seconds counterpart
#separate alpha and numeric parts of the time period
time_n = time_period.lower().rstrip('abcdefghijklmnopqrstuvwxyz ')
time_a = time_period.lower().lstrip('0123456789. ')
# determine if user specified, secs, mins, hours, days, weeks, months, years
factor = None
if time_a == 'sec' or time_a == "secs" or time_a == 'second' or time_a == "seconds":
factor = 1
if time_a == "min" or time_a == "mins" or time_a == "minute" or time_a == "minutes":
factor = 60
if time_a == "hr" or time_a == "hrs" or time_a == "hour" or time_a == "hours":
factor = 60 * 60
if time_a == "day" or time_a == "days":
factor = 60 * 60 * 24
if time_a == "wk" or time_a == "wks" or time_a == "week" or time_a == "weeks":
factor = 60 * 60 * 24 * 7
if time_a == "mon" or time_a == "mons" or time_a == "month" or time_a == "months":
factor = 60 * 60 * 24 * 30
if time_a == "yr" or time_a == "yrs" or time_a == "year" or time_a == "years":
factor = 60 * 60 * 24 * 365
time_period_secs = float(time_n) * factor
return time_period_secs
def on_quit(self):
#Cancel the timer
if hasattr(self, 'interval_timer_id'):
self.ssclient.cancel_timer(self.interval_timer_id)
super(VizTransformMatplotlibGraphs,self).on_quit()
class VizTransformMatplotlibGraphs(TransformStreamPublisher,
TransformEventListener,
TransformStreamListener):
"""
This class is used for instantiating worker processes that have subscriptions to data streams and convert
incoming data from CDM format to Matplotlib graphs
"""
output_bindings = ['graph_image_param_dict']
event_timer_interval = None
def on_start(self):
#print ">>>>>>>>>>>>>>>>>>>>>> MPL CFG = ", self.CFG
self.pubsub_management = PubsubManagementServiceProcessClient(
process=self)
self.ssclient = SchedulerServiceProcessClient(process=self)
self.rrclient = ResourceRegistryServiceProcessClient(process=self)
self.data_retriever_client = DataRetrieverServiceProcessClient(
process=self)
self.dsm_client = DatasetManagementServiceProcessClient(process=self)
self.pubsub_client = PubsubManagementServiceProcessClient(process=self)
self.stream_info = self.CFG.get_safe('process.publish_streams', {})
self.stream_names = self.stream_info.keys()
self.stream_ids = self.stream_info.values()
if not self.stream_names:
raise BadRequest('MPL Transform has no output streams.')
graph_time_periods = self.CFG.get_safe('graph_time_periods')
# If this is meant to be an event driven process, schedule an event to be generated every few minutes/hours
self.event_timer_interval = self.CFG.get_safe('graph_gen_interval')
if self.event_timer_interval:
event_origin = "Interval_Timer_Matplotlib"
sub = EventSubscriber(event_type="ResourceEvent",
callback=self.interval_timer_callback,
origin=event_origin)
sub.start()
self.interval_timer_id = self.ssclient.create_interval_timer(
start_time="now",
interval=self._str_to_secs(self.event_timer_interval),
event_origin=event_origin,
event_subtype="")
super(VizTransformMatplotlibGraphs, self).on_start()
# when tranform is used as a data process
def recv_packet(self, packet, in_stream_route, in_stream_id):
#Check to see if the class instance was set up as a event triggered transform. If yes, skip the packet
if self.event_timer_interval:
return
log.info('Received packet')
mpl_data_granule = VizTransformMatplotlibGraphsAlgorithm.execute(
packet, params=self.get_stream_definition())
for stream_name in self.stream_names:
publisher = getattr(self, stream_name)
publisher.publish(mpl_data_granule)
def get_stream_definition(self):
stream_id = self.stream_ids[0]
stream_def = self.pubsub_management.read_stream_definition(
stream_id=stream_id)
return stream_def._id
def process_event(self, msg, headers):
return
def interval_timer_callback(self, *args, **kwargs):
#Find out the input data product to this process
in_dp_id = self.CFG.get_safe('in_dp_id')
print " >>>>>>>>>>>>>> IN DP ID from cfg : ", in_dp_id
# get the dataset_id associated with the data_product. Need it to do the data retrieval
ds_ids, _ = self.rrclient.find_objects(in_dp_id, PRED.hasDataset,
RT.Dataset, True)
if ds_ids is None or not ds_ids:
return None
# retrieve data for the specified time interval. Setup up query from pass config first
query = {}
param_list_str = self.CFG.get_safe('parameters')
if param_list_str:
query['parameters'] = param_list_str.split(', ')
# append time if not present in list of parameters
if not 'time' in query['parameters']:
query['parameters'].append('time')
query['start_time'] = query['end_time'] = ntplib.system_to_ntp_time(
time.time()) # Now
query['stride_time'] = 1
if self.CFG.get_safe('graph_time_period'):
query['start_time'] = query['end_time'] - self._str_to_secs(
self.CFG.get_safe('graph_time_period'))
#print " >>>>>>>>>>>>>> QUERY = ", query
#retrieved_granule = self.data_retriever_client.retrieve(ds_ids[0],{'start_time':start_time,'end_time':end_time})
retrieved_granule = self.data_retriever_client.retrieve(ds_ids[0],
query=query)
# add extra parameters to query passed in config that are not needed by data retrieval
if self.CFG.get_safe('resolution'):
query['resolution'] = self.CFG.get_safe('resolution')
# send the granule through the Algorithm code to get the matplotlib graphs
mpl_pdict_id = self.dsm_client.read_parameter_dictionary_by_name(
'graph_image_param_dict', id_only=True)
mpl_stream_def = self.pubsub_client.create_stream_definition(
'mpl', parameter_dictionary_id=mpl_pdict_id)
fileName = self.CFG.get_safe('graph_time_period')
mpl_data_granule = VizTransformMatplotlibGraphsAlgorithm.execute(
retrieved_granule,
config=query,
params=mpl_stream_def,
fileName=fileName)
if mpl_data_granule == None:
return None
# publish on all specified output streams
for stream_name in self.stream_names:
publisher = getattr(self, stream_name)
publisher.publish(mpl_data_granule)
return
def _str_to_secs(self, time_period):
# this method converts commonly used time periods to its actual seconds counterpart
#separate alpha and numeric parts of the time period
time_n = time_period.lower().rstrip('abcdefghijklmnopqrstuvwxyz ')
time_a = time_period.lower().lstrip('0123456789. ')
# determine if user specified, secs, mins, hours, days, weeks, months, years
factor = None
if time_a == 'sec' or time_a == "secs" or time_a == 'second' or time_a == "seconds":
factor = 1
if time_a == "min" or time_a == "mins" or time_a == "minute" or time_a == "minutes":
factor = 60
if time_a == "hr" or time_a == "hrs" or time_a == "hour" or time_a == "hours":
factor = 60 * 60
if time_a == "day" or time_a == "days":
factor = 60 * 60 * 24
if time_a == "wk" or time_a == "wks" or time_a == "week" or time_a == "weeks":
factor = 60 * 60 * 24 * 7
if time_a == "mon" or time_a == "mons" or time_a == "month" or time_a == "months":
factor = 60 * 60 * 24 * 30
if time_a == "yr" or time_a == "yrs" or time_a == "year" or time_a == "years":
factor = 60 * 60 * 24 * 365
time_period_secs = float(time_n) * factor
return time_period_secs
def on_quit(self):
#Cancel the timer
if hasattr(self, 'interval_timer_id'):
self.ssclient.cancel_timer(self.interval_timer_id)
super(VizTransformMatplotlibGraphs, self).on_quit()