def execute(self, context):
hook = DataFlowHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep)
hook.start_template_dataflow(self.job_name, self.dataflow_default_options,
self.parameters, self.template)
def execute(self, context):
"""Execute the python dataflow job."""
bucket_helper = GoogleCloudBucketHelper(
self.gcp_conn_id, self.delegate_to)
self.py_file = bucket_helper.google_cloud_to_local(self.py_file)
hook = DataFlowHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep)
dataflow_options = self.dataflow_default_options.copy()
dataflow_options.update(self.options)
# Convert argument names from lowerCamelCase to snake case.
camel_to_snake = lambda name: re.sub(
r'[A-Z]', lambda x: '_' + x.group(0).lower(), name)
formatted_options = {camel_to_snake(key): dataflow_options[key]
for key in dataflow_options}
hook.start_python_dataflow(
self.job_name, formatted_options,
self.py_file, self.py_options, py_interpreter=self.py_interpreter)
def execute(self, context):
hook = DataFlowHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to,
poll_sleep=self.poll_sleep)
dataflow_options = copy.copy(self.dataflow_default_options)
dataflow_options.update(self.options)
is_running = False
if self.check_if_running != CheckJobRunning.IgnoreJob:
is_running = hook.is_job_dataflow_running(self.job_name, dataflow_options)
while is_running and self.check_if_running == CheckJobRunning.WaitForRun:
is_running = hook.is_job_dataflow_running(self.job_name, dataflow_options)
if not is_running:
bucket_helper = GoogleCloudBucketHelper(
self.gcp_conn_id, self.delegate_to)
self.jar = bucket_helper.google_cloud_to_local(self.jar)
hook.start_java_dataflow(self.job_name, dataflow_options,
self.jar, self.job_class, True, self.multiple_jobs)
def setUp(self):
with mock.patch(BASE_STRING.format('GoogleCloudBaseHook.__init__'),
new=mock_init):
self.dataflow_hook = DataFlowHook(gcp_conn_id='test')
