fix: add mains to samples (#3284)

Added mains to two samples: create_cluster and instantiate_inline_workflow_templates.

Fixed their associated tests to accommodate this.

Removed subprocess from quickstart/quickstart_test.py to fix [2873](#2873)

fixes #2873

Author: bradmiro

dataproc/create_cluster.py

@@ -16,6 +16,12 @@
 
 # This sample walks a user through creating a Cloud Dataproc cluster using
 # the Python client library.
+#
+# This script can be run on its own:
+#   python create_cluster.py ${PROJECT_ID} ${REGION} ${CLUSTER_NAME}
+
+
+import sys
 
 # [START dataproc_create_cluster]
 from google.cloud import dataproc_v1 as dataproc
@@ -33,7 +39,7 @@ def create_cluster(project_id, region, cluster_name):
 
     # Create a client with the endpoint set to the desired cluster region.
     cluster_client = dataproc.ClusterControllerClient(client_options={
-        'api_endpoint': '{}-dataproc.googleapis.com:443'.format(region)
+        'api_endpoint': f'{region}-dataproc.googleapis.com:443',
     })
 
     # Create the cluster config.
@@ -57,5 +63,15 @@ def create_cluster(project_id, region, cluster_name):
     result = operation.result()
 
     # Output a success message.
-    print('Cluster created successfully: {}'.format(result.cluster_name))
+    print(f'Cluster created successfully: {result.cluster_name}')
     # [END dataproc_create_cluster]
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 4:
+        sys.exit('python create_cluster.py project_id region cluster_name')
+
+    project_id = sys.argv[1]
+    region = sys.argv[2]
+    cluster_name = sys.argv[3]
+    create_cluster(project_id, region, cluster_name)

dataproc/create_cluster_test.py

@@ -31,7 +31,7 @@ def teardown():
     yield
 
     cluster_client = dataproc.ClusterControllerClient(client_options={
-        'api_endpoint': '{}-dataproc.googleapis.com:443'.format(REGION)
+        'api_endpoint': f'{REGION}-dataproc.googleapis.com:443'
     })
     # Client library function
     operation = cluster_client.delete_cluster(PROJECT_ID, REGION, CLUSTER_NAME)

dataproc/instantiate_inline_workflow_template.py

@@ -16,9 +16,11 @@
 # workflow for Cloud Dataproc using the Python client library.
 #
 # This script can be run on its own:
-#   python workflows.py ${PROJECT_ID} ${REGION}
+#   python instantiate_inline_workflow_template.py ${PROJECT_ID} ${REGION}
+
 
 import sys
+
 # [START dataproc_instantiate_inline_workflow_template]
 from google.cloud import dataproc_v1 as dataproc
 
@@ -35,7 +37,8 @@ def instantiate_inline_workflow_template(project_id, region):
     # Create a client with the endpoint set to the desired region.
     workflow_template_client = dataproc.WorkflowTemplateServiceClient(
         client_options={
-            'api_endpoint': '{}-dataproc.googleapis.com:443'.format(region)}
+            'api_endpoint': f'{region}-dataproc.googleapis.com:443'
+        }
     )
 
     parent = workflow_template_client.region_path(project_id, region)
@@ -91,8 +94,14 @@ def instantiate_inline_workflow_template(project_id, region):
 
     # Output a success message.
     print('Workflow ran successfully.')
-# [END dataproc_instantiate_inline_workflow_template]
+    # [END dataproc_instantiate_inline_workflow_template]
 
 
 if __name__ == "__main__":
-    instantiate_inline_workflow_template(sys.argv[1], sys.argv[2])
+    if len(sys.argv) < 3:
+        sys.exit('python instantiate_inline_workflow_template.py '
+                 + 'project_id region')
+
+    project_id = sys.argv[1]
+    region = sys.argv[2]
+    instantiate_inline_workflow_template(project_id, region)

dataproc/quickstart/quickstart_test.py

@@ -15,11 +15,12 @@
 import os
 import uuid
 import pytest
-import subprocess
 
 from google.cloud import dataproc_v1 as dataproc
 from google.cloud import storage
 
+import quickstart
+
 
 PROJECT_ID = os.environ['GCLOUD_PROJECT']
 REGION = 'us-central1'
@@ -60,15 +61,9 @@ def setup_teardown():
     bucket.delete()
 
 
-def test_quickstart():
-    command = [
-        'python', 'quickstart/quickstart.py',
-        '--project_id', PROJECT_ID,
-        '--region', REGION,
-        '--cluster_name', CLUSTER_NAME,
-        '--job_file_path', JOB_FILE_PATH
-    ]
-    out = subprocess.check_output(command).decode("utf-8")
+def test_quickstart(capsys):
+    quickstart.quickstart(PROJECT_ID, REGION, CLUSTER_NAME, JOB_FILE_PATH)
+    out, _ = capsys.readouterr()
 
     assert 'Cluster created successfully' in out
     assert 'Submitted job' in out