def tearDown(self):
"""
Cleanup. Delete Subscription, Stream, Process Definition
"""
for fname in self.fnames:
FileSystem.unlink(fname)
def tearDown(self):
"""
Cleanup. Delete Subscription, Stream, Process Definition
"""
for fname in self.fnames:
FileSystem.unlink(fname)
def create_known(dataset_name, rootgrp_name, grp_name):
"""
A known array to compare against during tests
"""
known_array = numpy.ones((10,20))
filename = FileSystem.get_url(FS.TEMP,random_name(), ".hdf5")
# Write an hdf file with known values to compare against
h5pyfile = h5py.File(filename, mode = 'w', driver='core')
grp = h5pyfile.create_group(rootgrp_name)
subgrp = grp.create_group(grp_name)
dataset = subgrp.create_dataset(dataset_name, known_array.shape, known_array.dtype.str, maxshape=(None,None))
dataset.write_direct(known_array)
h5pyfile.close()
# convert the hdf file into a binary string
f = open(filename, mode='rb')
# read the binary string representation of the file
known_hdf_as_string = f.read() # this is a known string to compare against during tests
f.close()
# cleaning up
FileSystem.unlink(f.name)
return known_array, known_hdf_as_string
def create_known(dataset_name, rootgrp_name, grp_name):
"""
A known array to compare against during tests
"""
known_array = numpy.random.rand(10, 20)
filename = FileSystem.get_url(FS.TEMP, random_name(), ".hdf5")
# Write an hdf file with known values to compare against
h5pyfile = h5py.File(filename, mode='w', driver='core')
grp = h5pyfile.create_group(rootgrp_name)
subgrp = grp.create_group(grp_name)
dataset = subgrp.create_dataset(dataset_name,
known_array.shape,
known_array.dtype.str,
compression='gzip',
compression_opts=4,
maxshape=(None, None))
dataset.write_direct(known_array)
h5pyfile.close()
# convert the hdf file into a binary string
f = open(filename, mode='rb')
# read the binary string representation of the file
known_hdf_as_string = f.read(
) # this is a known string to compare against during tests
f.close()
# cleaning up
FileSystem.unlink(f.name)
return known_array, known_hdf_as_string
def sub_listen(msg, headers):
assertions(isinstance(msg, StreamGranuleContainer),
'replayed message is not a granule.')
hdf_string = msg.identifiables[data_stream_id].values
sha1 = hashlib.sha1(hdf_string).hexdigest().upper()
assertions(sha1 == msg.identifiables[encoding_id].sha1,
'Checksum failed.')
assertions(
msg.identifiables[element_count_id].value == 1,
'record replay count is incorrect %d.' %
msg.identifiables[element_count_id].value)
output_file = FileSystem.mktemp()
output_file.write(msg.identifiables[data_stream_id].values)
output_file_path = output_file.name
output_file.close()
output_vectors = acquire_data([output_file_path], fields, 2).next()
for field in fields:
comparison = (input_vectors[field]['values'] ==
output_vectors[field]['values'])
assertions(
comparison.all(), 'vector mismatch: %s vs %s' %
(input_vectors[field]['values'],
output_vectors[field]['values']))
FileSystem.unlink(output_file_path)
ar.set(True)
def _get_time_index(self, granule, timeval):
'''
@brief Obtains the index where a time's value is
@param granule must be a complete dataset (hdf_string provided)
@param timeval the vector value
@return Index value for timeval or closest approx such that timeval is IN the subset
'''
assert isinstance(granule,
StreamGranuleContainer), 'object is not a granule.'
assert granule.identifiables[
self.data_stream_id].values, 'hdf_string is not provided.'
hdf_string = granule.identifiables[self.data_stream_id].values
file_path = self._get_hdf_from_string(hdf_string)
#-------------------------------------------------------------------------------------
# Determine the field_id for the temporal coordinate vector (aka time)
#-------------------------------------------------------------------------------------
time_field = self.definition.identifiables[
self.time_id].coordinate_ids[0]
value_path = granule.identifiables[
time_field].values_path or self.definition.identifiables[
time_field].values_path
record_count = granule.identifiables[self.element_count_id].value
#-------------------------------------------------------------------------------------
# Go through the time vector and get the indexes that correspond to the timeval
# It will find a value such that
# t_n <= i < t_(n+1), where i is the index
#-------------------------------------------------------------------------------------
var_name = value_path.split('/').pop()
res = acquire_data([file_path], [var_name], record_count).next()
time_vector = res[var_name]['values']
retval = 0
for i in xrange(len(time_vector)):
if time_vector[i] == timeval:
retval = i
break
elif i == 0 and time_vector[i] > timeval:
retval = i
break
elif (i + 1) < len(time_vector): # not last val
if time_vector[i] < timeval and time_vector[i + 1] > timeval:
retval = i
break
else: # last val
retval = i
break
FileSystem.unlink(file_path)
return retval
def _slice(self, granule, slice_):
'''
@brief Creates a granule which is a slice of the granule parameter
@param granule the superset
@param slice_ The slice values for which to create the granule
@return Crafted subset granule of the parameter granule.
'''
retval = copy.deepcopy(granule)
fields = self._list_data(self.definition, granule)
record_count = slice_.stop - slice_.start
assert record_count > 0, 'slice is malformed'
pairs = self._pair_up(granule)
var_names = list([i[0]
for i in pairs]) # Get the var_names from the pairs
log.debug('var_names: %s', var_names)
file_path = self._get_hdf_from_string(
granule.identifiables[self.data_stream_id].values)
codec = HDFEncoder()
vectors = acquire_data([file_path], var_names, record_count,
slice_).next()
for row, value in vectors.iteritems():
vp = self._find_vp(pairs, row)
# Determine the range_id reverse dictionary lookup
#@todo: improve this pattern
for field, path in fields.iteritems():
if vp == path:
range_id = field
break
bounds_id = retval.identifiables[range_id].bounds_id
# Recalculate the bounds for this fields and update the granule
range = value['range']
retval.identifiables[bounds_id].value_pair[0] = float(range[0])
retval.identifiables[bounds_id].value_pair[1] = float(range[1])
codec.add_hdf_dataset(vp, value['values'])
record_count = len(value['values'])
#----- DEBUGGING ---------
log.debug('slice- row: %s', row)
log.debug('slice- value_path: %s', vp)
log.debug('slice- range_id: %s', range_id)
log.debug('slice- bounds_id: %s', bounds_id)
log.debug('slice- limits: %s', value['range'])
#-------------------------
retval.identifiables[self.element_count_id].value = record_count
hdf_string = codec.encoder_close()
self._patch_granule(retval, hdf_string)
FileSystem.unlink(file_path)
return retval
def _get_time_index(self, granule, timeval):
'''
@brief Obtains the index where a time's value is
@param granule must be a complete dataset (hdf_string provided)
@param timeval the vector value
@return Index value for timeval or closest approx such that timeval is IN the subset
'''
assert isinstance(granule, StreamGranuleContainer), 'object is not a granule.'
assert granule.identifiables[self.data_stream_id].values, 'hdf_string is not provided.'
hdf_string = granule.identifiables[self.data_stream_id].values
file_path = self._get_hdf_from_string(hdf_string)
#-------------------------------------------------------------------------------------
# Determine the field_id for the temporal coordinate vector (aka time)
#-------------------------------------------------------------------------------------
time_field = self.definition.identifiables[self.time_id].coordinate_ids[0]
value_path = granule.identifiables[time_field].values_path or self.definition.identifiables[time_field].values_path
record_count = granule.identifiables[self.element_count_id].value
#-------------------------------------------------------------------------------------
# Go through the time vector and get the indexes that correspond to the timeval
# It will find a value such that
# t_n <= i < t_(n+1), where i is the index
#-------------------------------------------------------------------------------------
var_name = value_path.split('/').pop()
res = acquire_data([file_path], [var_name], record_count).next()
time_vector = res[var_name]['values']
retval = 0
for i in xrange(len(time_vector)):
if time_vector[i] == timeval:
retval = i
break
elif i==0 and time_vector[i] > timeval:
retval = i
break
elif (i+1) < len(time_vector): # not last val
if time_vector[i] < timeval and time_vector[i+1] > timeval:
retval = i
break
else: # last val
retval = i
break
FileSystem.unlink(file_path)
return retval
def _slice(self,granule,slice_):
'''
@brief Creates a granule which is a slice of the granule parameter
@param granule the superset
@param slice_ The slice values for which to create the granule
@return Crafted subset granule of the parameter granule.
'''
retval = copy.deepcopy(granule)
fields = self._list_data(self.definition,granule)
record_count = slice_.stop - slice_.start
assert record_count > 0, 'slice is malformed'
pairs = self._pair_up(granule)
var_names = list([i[0] for i in pairs]) # Get the var_names from the pairs
log.debug('var_names: %s',var_names)
file_path = self._get_hdf_from_string(granule.identifiables[self.data_stream_id].values)
codec = HDFEncoder()
vectors = acquire_data([file_path],var_names,record_count,slice_ ).next()
for row, value in vectors.iteritems():
vp = self._find_vp(pairs, row)
# Determine the range_id reverse dictionary lookup
#@todo: improve this pattern
for field,path in fields.iteritems():
if vp==path:
range_id = field
break
bounds_id = retval.identifiables[range_id].bounds_id
# Recalculate the bounds for this fields and update the granule
range = value['range']
retval.identifiables[bounds_id].value_pair[0] = float(range[0])
retval.identifiables[bounds_id].value_pair[1] = float(range[1])
codec.add_hdf_dataset(vp, value['values'])
record_count = len(value['values'])
#----- DEBUGGING ---------
log.debug('slice- row: %s', row)
log.debug('slice- value_path: %s', vp)
log.debug('slice- range_id: %s', range_id)
log.debug('slice- bounds_id: %s', bounds_id)
log.debug('slice- limits: %s', value['range'])
#-------------------------
retval.identifiables[self.element_count_id].value = record_count
hdf_string = codec.encoder_close()
self._patch_granule(retval, hdf_string)
FileSystem.unlink(file_path)
return retval
def sub_listen(msg, headers):
assertions(isinstance(msg,StreamGranuleContainer),'replayed message is not a granule.')
hdf_string = msg.identifiables[data_stream_id].values
sha1 = hashlib.sha1(hdf_string).hexdigest().upper()
assertions(sha1 == msg.identifiables[encoding_id].sha1,'Checksum failed.')
assertions(msg.identifiables[element_count_id].value==1, 'record replay count is incorrect %d.' % msg.identifiables[element_count_id].value)
output_file = FileSystem.mktemp()
output_file.write(msg.identifiables[data_stream_id].values)
output_file_path = output_file.name
output_file.close()
output_vectors = acquire_data([output_file_path],fields,2).next()
for field in fields:
comparison = (input_vectors[field]['values']==output_vectors[field]['values'])
assertions(comparison.all(), 'vector mismatch: %s vs %s' %
(input_vectors[field]['values'],output_vectors[field]['values']))
FileSystem.unlink(output_file_path)
ar.set(True)
def hdf_to_string(self):
"""
Convert the temporary hdf file holding the data into a binary string. Cleanup by deleting the hdf file and
return the binary string.
@retval hdf_string
"""
# Return Value
# ------------
# hdf_string: ''
#
try:
# open the hdf5 file using python 'open()'
f = open(self.filename, mode='rb')
# read the binary string representation of the file
hdf_string = f.read()
f.close()
except IOError:
log.exception("Error opening binary file for reading out hdfstring in HDFEncoder. ")
raise HDFEncoderException("Error while trying to open file. ")
finally:
FileSystem.unlink(self.filename)
return hdf_string
def __del__(self):
# This is dangerous - I don't like implementing del!!!
# Clean up files!
FileSystem.unlink(self.filename)
def test_dm_integration(self):
'''
test_dm_integration
Test full DM Services Integration
'''
cc = self.container
assertions = self.assertTrue
#-----------------------------
# Copy below here
#-----------------------------
pubsub_management_service = PubsubManagementServiceClient(node=cc.node)
ingestion_management_service = IngestionManagementServiceClient(node=cc.node)
dataset_management_service = DatasetManagementServiceClient(node=cc.node)
data_retriever_service = DataRetrieverServiceClient(node=cc.node)
transform_management_service = TransformManagementServiceClient(node=cc.node)
process_dispatcher = ProcessDispatcherServiceClient(node=cc.node)
process_list = []
datasets = []
datastore_name = 'test_dm_integration'
#---------------------------
# Set up ingestion
#---------------------------
# Configure ingestion using eight workers, ingesting to test_dm_integration datastore with the SCIDATA profile
log.debug('Calling create_ingestion_configuration')
ingestion_configuration_id = ingestion_management_service.create_ingestion_configuration(
exchange_point_id='science_data',
couch_storage=CouchStorage(datastore_name=datastore_name,datastore_profile='SCIDATA'),
number_of_workers=8
)
#
ingestion_management_service.activate_ingestion_configuration(
ingestion_configuration_id=ingestion_configuration_id)
ctd_stream_def = ctd_stream_definition()
stream_def_id = pubsub_management_service.create_stream_definition(container=ctd_stream_def, name='Junk definition')
#---------------------------
# Set up the producers (CTD Simulators)
#---------------------------
# Launch five simulated CTD producers
for iteration in xrange(5):
# Make a stream to output on
stream_id = pubsub_management_service.create_stream(stream_definition_id=stream_def_id)
#---------------------------
# Set up the datasets
#---------------------------
dataset_id = dataset_management_service.create_dataset(
stream_id=stream_id,
datastore_name=datastore_name,
view_name='datasets/stream_join_granule'
)
# Keep track of the datasets
datasets.append(dataset_id)
stream_policy_id = ingestion_management_service.create_dataset_configuration(
dataset_id = dataset_id,
archive_data = True,
archive_metadata = True,
ingestion_configuration_id = ingestion_configuration_id
)
producer_definition = ProcessDefinition()
producer_definition.executable = {
'module':'ion.processes.data.ctd_stream_publisher',
'class':'SimpleCtdPublisher'
}
configuration = {
'process':{
'stream_id':stream_id,
'datastore_name':datastore_name
}
}
procdef_id = process_dispatcher.create_process_definition(process_definition=producer_definition)
log.debug('LUKE_DEBUG: procdef_id: %s', procdef_id)
pid = process_dispatcher.schedule_process(process_definition_id=procdef_id, configuration=configuration)
# Keep track, we'll kill 'em later.
process_list.append(pid)
# Get about 4 seconds of data
time.sleep(4)
#---------------------------
# Stop producing data
#---------------------------
for process in process_list:
process_dispatcher.cancel_process(process)
#----------------------------------------------
# The replay and the transform, a love story.
#----------------------------------------------
# Happy Valentines to the clever coder who catches the above!
transform_definition = ProcessDefinition()
transform_definition.executable = {
'module':'ion.processes.data.transforms.transform_example',
'class':'TransformCapture'
}
transform_definition_id = process_dispatcher.create_process_definition(process_definition=transform_definition)
dataset_id = datasets.pop() # Just need one for now
replay_id, stream_id = data_retriever_service.define_replay(dataset_id=dataset_id)
#--------------------------------------------
# I'm Selling magazine subscriptions here!
#--------------------------------------------
subscription = pubsub_management_service.create_subscription(query=StreamQuery(stream_ids=[stream_id]),
exchange_name='transform_capture_point')
#--------------------------------------------
# Start the transform (capture)
#--------------------------------------------
transform_id = transform_management_service.create_transform(
name='capture_transform',
in_subscription_id=subscription,
process_definition_id=transform_definition_id
)
transform_management_service.activate_transform(transform_id=transform_id)
#--------------------------------------------
# BEGIN REPLAY!
#--------------------------------------------
data_retriever_service.start_replay(replay_id=replay_id)
#--------------------------------------------
# Lets get some boundaries
#--------------------------------------------
bounds = dataset_management_service.get_dataset_bounds(dataset_id=dataset_id)
assertions('latitude_bounds' in bounds, 'dataset_id: %s' % dataset_id)
assertions('longitude_bounds' in bounds)
assertions('pressure_bounds' in bounds)
#--------------------------------------------
# Make sure the transform capture worked
#--------------------------------------------
time.sleep(3) # Give the other processes up to 3 seconds to catch up
stats = os.stat(FileSystem.get_url(FS.TEMP,'transform_output'))
assertions(stats.st_blksize > 0)
# BEAUTIFUL!
FileSystem.unlink(FileSystem.get_url(FS.TEMP,'transform_output'))
def test_replay_integration(self):
'''
test_replay_integration
'''
import numpy as np
# Keep the import it's used in the vector comparison below even though pycharm says its unused.
cc = self.container
XP = self.XP
assertions = self.assertTrue
### Every thing below here can be run as a script:
log.debug('Got it')
pubsub_management_service = PubsubManagementServiceClient(node=cc.node)
ingestion_management_service = IngestionManagementServiceClient(node=cc.node)
dataset_management_service = DatasetManagementServiceClient(node=cc.node)
data_retriever_service = DataRetrieverServiceClient(node=cc.node)
datastore_name = 'dm_test_replay_integration'
producer = Publisher(name=(XP,'stream producer'))
ingestion_configuration_id = ingestion_management_service.create_ingestion_configuration(
exchange_point_id=XP,
couch_storage=CouchStorage(datastore_name=datastore_name,datastore_profile='SCIDATA'),
hdf_storage=HdfStorage(),
number_of_workers=1
)
ingestion_management_service.activate_ingestion_configuration(
ingestion_configuration_id=ingestion_configuration_id
)
definition = SBE37_CDM_stream_definition()
data_stream_id = definition.data_stream_id
encoding_id = definition.identifiables[data_stream_id].encoding_id
element_count_id = definition.identifiables[data_stream_id].element_count_id
stream_def_id = pubsub_management_service.create_stream_definition(
container=definition
)
stream_id = pubsub_management_service.create_stream(
stream_definition_id=stream_def_id
)
dataset_id = dataset_management_service.create_dataset(
stream_id=stream_id,
datastore_name=datastore_name,
view_name='datasets/dataset_by_id'
)
ingestion_management_service.create_dataset_configuration(
dataset_id=dataset_id,
archive_data=True,
archive_metadata=True,
ingestion_configuration_id = ingestion_configuration_id
)
definition.stream_resource_id = stream_id
packet = _create_packet(definition)
input_file = FileSystem.mktemp()
input_file.write(packet.identifiables[data_stream_id].values)
input_file_path = input_file.name
input_file.close()
fields=[
'conductivity',
'height',
'latitude',
'longitude',
'pressure',
'temperature',
'time'
]
input_vectors = acquire_data([input_file_path],fields , 2).next()
producer.publish(msg=packet, to_name=(XP,'%s.data' % stream_id))
replay_id, replay_stream_id = data_retriever_service.define_replay(dataset_id)
ar = gevent.event.AsyncResult()
def sub_listen(msg, headers):
assertions(isinstance(msg,StreamGranuleContainer),'replayed message is not a granule.')
hdf_string = msg.identifiables[data_stream_id].values
sha1 = hashlib.sha1(hdf_string).hexdigest().upper()
assertions(sha1 == msg.identifiables[encoding_id].sha1,'Checksum failed.')
assertions(msg.identifiables[element_count_id].value==1, 'record replay count is incorrect %d.' % msg.identifiables[element_count_id].value)
output_file = FileSystem.mktemp()
output_file.write(msg.identifiables[data_stream_id].values)
output_file_path = output_file.name
output_file.close()
output_vectors = acquire_data([output_file_path],fields,2).next()
for field in fields:
comparison = (input_vectors[field]['values']==output_vectors[field]['values'])
assertions(comparison.all(), 'vector mismatch: %s vs %s' %
(input_vectors[field]['values'],output_vectors[field]['values']))
FileSystem.unlink(output_file_path)
ar.set(True)
subscriber = Subscriber(name=(XP,'replay listener'),callback=sub_listen)
g = gevent.Greenlet(subscriber.listen, binding='%s.data' % replay_stream_id)
g.start()
data_retriever_service.start_replay(replay_id)
ar.get(timeout=10)
FileSystem.unlink(input_file_path)
def subset(self, granule, coverages):
'''
@param granule
@return dataset subset based on the fields
'''
assert isinstance(granule,
StreamGranuleContainer), 'object is not a granule.'
field_ids = self.field_ids
element_count_id = self.element_count_id
values_path = list()
domain_ids = list()
coverage_ids = list()
coverages = list(coverages)
log.debug('Coverages include %s of type %s', coverages,
type(coverages))
#-----------------------------------------------------------------------------------------------------------
# Iterate through the fields IAW stream definition and check for rangesets and coordinate axises
# - If its a coordinate axis, it belongs regardless of what the client desires. (It's part of the domain)
# - If its a rangeset make sure that it's part of what the client asked for, if not discard it
#-----------------------------------------------------------------------------------------------------------
for field_id in field_ids:
range_id = self.definition.identifiables[field_id].range_id
#-------------------------------------------------------------------------------------
# Coordinate Axis
# - Keep track of this in our domains
# - Add it to the paths we need to grab from the file(s)
#-------------------------------------------------------------------------------------
if isinstance(self.definition.identifiables[range_id],
CoordinateAxis):
log.debug('got a domain: %s' % range_id)
domain_ids.append(field_id)
if granule.identifiables.has_key(range_id):
value_path = granule.identifiables[
range_id].values_path or self.definition.identifiables[
range_id].values_path
values_path.append(value_path)
else:
value_path = self.definition.identifiables[
range_id].values_path
values_path.append(value_path)
continue
#-------------------------------------------------------------------------------------
# Range Set
# - If it's part of the coverages we want to keep
# - Add it to the list of ranges we're tracking
# - Add the value path to the paths we're tracking.
#-------------------------------------------------------------------------------------
if isinstance(self.definition.identifiables[range_id], RangeSet):
# If its a rangeset, a specified coverage and the granule has it, add it to the list
if field_id in coverages:
if granule.identifiables.has_key(range_id):
log.debug('got a range: %s' % range_id)
coverage_ids.append(field_id)
if granule.identifiables.has_key(range_id):
value_path = granule.identifiables[
range_id].values_path or self.definition.identifiables[
range_id].values_path
values_path.append(value_path)
else:
value_path = self.definition.identifiables[
range_id].values_path
values_path.append(value_path)
continue
# ----
# We need to track the range and bounds because,
# you guessed it, we need to update the bounds
# ----
range_id = self.definition.identifiables[field_id].range_id
bounds_id = self.definition.identifiables[range_id].bounds_id
#---
# Lastly, if the field is there and we don't want it, we need to strip it
#---
if not (field_id in coverages):
log.debug('%s doesn\'t belong in %s.', field_id, coverages)
log.debug('rebool: %s', bool(field_id in coverages))
if granule.identifiables.has_key(range_id):
log.debug('Removing %s from granule', range_id)
del granule.identifiables[range_id]
if granule.identifiables.has_key(bounds_id):
log.debug('Removing %s from granule', bounds_id)
del granule.identifiables[bounds_id]
log.debug('Domains: %s', domain_ids)
log.debug('Ranges: %s', coverage_ids)
log.debug('Values_paths: %s', values_path)
file_path = self._get_hdf_from_string(
granule.identifiables[self.data_stream_id].values)
full_coverage = list(domain_ids + coverage_ids)
log.debug('Full coverage: %s' % full_coverage)
log.debug('Calling acquire_data with: %s, %s, %s', [file_path],
values_path, granule.identifiables[element_count_id].value)
codec = HDFEncoder()
pairs = self._pair_up(granule)
var_names = list([i[0] for i in pairs])
record_count = granule.identifiables[self.element_count_id].value
data = acquire_data([file_path], var_names, record_count).next()
for row, value in data.iteritems():
vp = self._find_vp(pairs, row)
codec.add_hdf_dataset(vp, value['values'])
hdf_string = codec.encoder_close()
self._patch_granule(granule, hdf_string)
FileSystem.unlink(file_path)
return granule
def test_replay_integration(self):
'''
test_replay_integration
'''
import numpy as np
# Keep the import it's used in the vector comparison below even though pycharm says its unused.
cc = self.container
XP = self.XP
assertions = self.assertTrue
### Every thing below here can be run as a script:
log.debug('Got it')
pubsub_management_service = PubsubManagementServiceClient(node=cc.node)
ingestion_management_service = IngestionManagementServiceClient(
node=cc.node)
dataset_management_service = DatasetManagementServiceClient(
node=cc.node)
data_retriever_service = DataRetrieverServiceClient(node=cc.node)
datastore_name = 'dm_test_replay_integration'
producer = Publisher(name=(XP, 'stream producer'))
ingestion_configuration_id = ingestion_management_service.create_ingestion_configuration(
exchange_point_id=XP,
couch_storage=CouchStorage(datastore_name=datastore_name,
datastore_profile='SCIDATA'),
hdf_storage=HdfStorage(),
number_of_workers=1)
ingestion_management_service.activate_ingestion_configuration(
ingestion_configuration_id=ingestion_configuration_id)
definition = SBE37_CDM_stream_definition()
data_stream_id = definition.data_stream_id
encoding_id = definition.identifiables[data_stream_id].encoding_id
element_count_id = definition.identifiables[
data_stream_id].element_count_id
stream_def_id = pubsub_management_service.create_stream_definition(
container=definition)
stream_id = pubsub_management_service.create_stream(
stream_definition_id=stream_def_id)
dataset_id = dataset_management_service.create_dataset(
stream_id=stream_id,
datastore_name=datastore_name,
view_name='datasets/dataset_by_id')
ingestion_management_service.create_dataset_configuration(
dataset_id=dataset_id,
archive_data=True,
archive_metadata=True,
ingestion_configuration_id=ingestion_configuration_id)
definition.stream_resource_id = stream_id
packet = _create_packet(definition)
input_file = FileSystem.mktemp()
input_file.write(packet.identifiables[data_stream_id].values)
input_file_path = input_file.name
input_file.close()
fields = [
'conductivity', 'height', 'latitude', 'longitude', 'pressure',
'temperature', 'time'
]
input_vectors = acquire_data([input_file_path], fields, 2).next()
producer.publish(msg=packet, to_name=(XP, '%s.data' % stream_id))
replay_id, replay_stream_id = data_retriever_service.define_replay(
dataset_id)
ar = gevent.event.AsyncResult()
def sub_listen(msg, headers):
assertions(isinstance(msg, StreamGranuleContainer),
'replayed message is not a granule.')
hdf_string = msg.identifiables[data_stream_id].values
sha1 = hashlib.sha1(hdf_string).hexdigest().upper()
assertions(sha1 == msg.identifiables[encoding_id].sha1,
'Checksum failed.')
assertions(
msg.identifiables[element_count_id].value == 1,
'record replay count is incorrect %d.' %
msg.identifiables[element_count_id].value)
output_file = FileSystem.mktemp()
output_file.write(msg.identifiables[data_stream_id].values)
output_file_path = output_file.name
output_file.close()
output_vectors = acquire_data([output_file_path], fields, 2).next()
for field in fields:
comparison = (input_vectors[field]['values'] ==
output_vectors[field]['values'])
assertions(
comparison.all(), 'vector mismatch: %s vs %s' %
(input_vectors[field]['values'],
output_vectors[field]['values']))
FileSystem.unlink(output_file_path)
ar.set(True)
subscriber = Subscriber(name=(XP, 'replay listener'),
callback=sub_listen)
g = gevent.Greenlet(subscriber.listen,
binding='%s.data' % replay_stream_id)
g.start()
data_retriever_service.start_replay(replay_id)
ar.get(timeout=10)
FileSystem.unlink(input_file_path)
def subset(self,granule,coverages):
'''
@param granule
@return dataset subset based on the fields
'''
assert isinstance(granule, StreamGranuleContainer), 'object is not a granule.'
field_ids = self.field_ids
element_count_id = self.element_count_id
values_path = list()
domain_ids = list()
coverage_ids = list()
coverages = list(coverages)
log.debug('Coverages include %s of type %s', coverages, type(coverages))
#-----------------------------------------------------------------------------------------------------------
# Iterate through the fields IAW stream definition and check for rangesets and coordinate axises
# - If its a coordinate axis, it belongs regardless of what the client desires. (It's part of the domain)
# - If its a rangeset make sure that it's part of what the client asked for, if not discard it
#-----------------------------------------------------------------------------------------------------------
for field_id in field_ids:
range_id = self.definition.identifiables[field_id].range_id
#-------------------------------------------------------------------------------------
# Coordinate Axis
# - Keep track of this in our domains
# - Add it to the paths we need to grab from the file(s)
#-------------------------------------------------------------------------------------
if isinstance(self.definition.identifiables[range_id], CoordinateAxis):
log.debug('got a domain: %s' % range_id)
domain_ids.append(field_id)
if granule.identifiables.has_key(range_id):
value_path = granule.identifiables[range_id].values_path or self.definition.identifiables[range_id].values_path
values_path.append(value_path)
else:
value_path = self.definition.identifiables[range_id].values_path
values_path.append(value_path)
continue
#-------------------------------------------------------------------------------------
# Range Set
# - If it's part of the coverages we want to keep
# - Add it to the list of ranges we're tracking
# - Add the value path to the paths we're tracking.
#-------------------------------------------------------------------------------------
if isinstance(self.definition.identifiables[range_id], RangeSet):
# If its a rangeset, a specified coverage and the granule has it, add it to the list
if field_id in coverages:
if granule.identifiables.has_key(range_id):
log.debug('got a range: %s' % range_id)
coverage_ids.append(field_id)
if granule.identifiables.has_key(range_id):
value_path = granule.identifiables[range_id].values_path or self.definition.identifiables[range_id].values_path
values_path.append(value_path)
else:
value_path = self.definition.identifiables[range_id].values_path
values_path.append(value_path)
continue
# ----
# We need to track the range and bounds because,
# you guessed it, we need to update the bounds
# ----
range_id = self.definition.identifiables[field_id].range_id
bounds_id = self.definition.identifiables[range_id].bounds_id
#---
# Lastly, if the field is there and we don't want it, we need to strip it
#---
if not (field_id in coverages):
log.debug('%s doesn\'t belong in %s.', field_id, coverages)
log.debug('rebool: %s', bool(field_id in coverages))
if granule.identifiables.has_key(range_id):
log.debug('Removing %s from granule', range_id)
del granule.identifiables[range_id]
if granule.identifiables.has_key(bounds_id):
log.debug('Removing %s from granule', bounds_id)
del granule.identifiables[bounds_id]
log.debug('Domains: %s', domain_ids)
log.debug('Ranges: %s', coverage_ids)
log.debug('Values_paths: %s', values_path)
file_path = self._get_hdf_from_string(granule.identifiables[self.data_stream_id].values)
full_coverage = list(domain_ids + coverage_ids)
log.debug('Full coverage: %s' % full_coverage)
log.debug('Calling acquire_data with: %s, %s, %s', [file_path],values_path,granule.identifiables[element_count_id].value)
codec = HDFEncoder()
pairs = self._pair_up(granule)
var_names = list([i[0] for i in pairs])
record_count = granule.identifiables[self.element_count_id].value
data = acquire_data([file_path], var_names, record_count).next()
for row,value in data.iteritems():
vp = self._find_vp(pairs, row)
codec.add_hdf_dataset(vp, value['values'])
hdf_string = codec.encoder_close()
self._patch_granule(granule,hdf_string)
FileSystem.unlink(file_path)
return granule
