def test_create_bq_dataset(self, mock_dataset, mock_client): mock_client.dataset.return_value = 'dataset_ref' mock_dataset.return_value = 'dataset_obj' utils.create_bq_dataset('project', 'dataset_base_name') mock_client.return_value.create_dataset.assert_called_with( 'dataset_obj')
def setUp(self): self.test_pipeline = TestPipeline(is_integration_test=True) self.project = self.test_pipeline.get_option('project') # Set up BigQuery environment self.dataset_ref = utils.create_bq_dataset(self.project, self.OUTPUT_DATASET)
def setUp(self): self.test_pipeline = TestPipeline(is_integration_test=True) self.project = self.test_pipeline.get_option('project') # Set up PubSub environment. from google.cloud import pubsub self.pub_client = pubsub.PublisherClient() self.pubsub_setup_client = PubSubSetupClient(project=self.project) self.input_topic = self.pubsub_setup_client.create_topic(INPUT_TOPIC) self.output_topic = self.pubsub_setup_client.create_topic(OUTPUT_TOPIC) self.input_sub = self.pubsub_setup_client.create_subscription( self.input_topic, INPUT_SUB) self.output_sub = self.pubsub_setup_client.create_subscription( self.output_topic, OUTPUT_SUB) # Set up BigQuery tables self.dataset_ref = utils.create_bq_dataset(self.project, OUTPUT_DATASET) self.bq_wrapper = BigQueryWrapper() table_schema = parse_table_schema_from_json(schemas.get_test_schema()) def _create_table(table_id, schema): return self.bq_wrapper.get_or_create_table( project_id=self.project, dataset_id=self.dataset_ref.dataset_id, table_id=table_id, schema=schema, create_disposition='CREATE_IF_NEEDED', write_disposition='WRITE_APPEND') self.table_ref = _create_table(OUTPUT_TABLE, table_schema)
def setUp(self): # Set up PubSub self.test_pipeline = TestPipeline(is_integration_test=True) self.runner_name = type(self.test_pipeline.runner).__name__ self.project = self.test_pipeline.get_option('project') self.uuid = str(uuid.uuid4()) from google.cloud import pubsub self.pub_client = pubsub.PublisherClient() self.input_topic = self.pub_client.create_topic( self.pub_client.topic_path(self.project, self.INPUT_TOPIC + self.uuid)) self.sub_client = pubsub.SubscriberClient() self.input_sub = self.sub_client.create_subscription( self.sub_client.subscription_path( self.project, self.INPUT_SUB + self.uuid), self.input_topic.name) # Set up BQ self.dataset_ref = utils.create_bq_dataset( self.project, self.BIG_QUERY_DATASET_ID) self.output_table = "%s.output_table" % (self.dataset_ref.dataset_id)
def setUp(self): self.test_pipeline = TestPipeline(is_integration_test=True) self.project = self.test_pipeline.get_option('project') _unique_id = str(uuid.uuid4()) # Set up PubSub environment. from google.cloud import pubsub self.pub_client = pubsub.PublisherClient() self.input_topic = self.pub_client.create_topic( self.pub_client.topic_path(self.project, self.INPUT_TOPIC + _unique_id)) self.sub_client = pubsub.SubscriberClient() self.input_sub = self.sub_client.create_subscription( self.sub_client.subscription_path( self.project, self.INPUT_SUB + _unique_id), self.input_topic.name) # Set up BigQuery environment self.dataset_ref = utils.create_bq_dataset( self.project, self.OUTPUT_DATASET) self._test_timestamp = int(time.time() * 1000)
def setUp(self): self.test_pipeline = TestPipeline(is_integration_test=True) self.project = self.test_pipeline.get_option('project') _unique_id = str(uuid.uuid4()) # Set up PubSub environment. from google.cloud import pubsub self.pub_client = pubsub.PublisherClient() self.input_topic = self.pub_client.create_topic( self.pub_client.topic_path(self.project, self.INPUT_TOPIC + _unique_id)) self.sub_client = pubsub.SubscriberClient() self.input_sub = self.sub_client.create_subscription( self.sub_client.subscription_path(self.project, self.INPUT_SUB + _unique_id), self.input_topic.name) # Set up BigQuery environment self.dataset_ref = utils.create_bq_dataset(self.project, self.OUTPUT_DATASET) self._test_timestamp = int(time.time() * 1000)