feat: add optional parameters (tarball_gcs_dir, diagnosis_interval, jobs, yarn_application_ids) in DiagnoseClusterRequest

google/cloud/dataproc_v1/types/clusters.py

@@ -20,6 +20,7 @@
 from google.protobuf import duration_pb2  # type: ignore
 from google.protobuf import field_mask_pb2  # type: ignore
 from google.protobuf import timestamp_pb2  # type: ignore
+from google.type import interval_pb2  # type: ignore
 import proto  # type: ignore
 
 from google.cloud.dataproc_v1.types import shared
@@ -837,26 +838,20 @@ class InstanceGroupConfig(proto.Message):
             Instance Group. See `Dataproc -> Minimum CPU
             Platform <https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu>`__.
         min_num_instances (int):
-            Optional. The minimum number of instances to create. If
-            min_num_instances is set, min_num_instances is used for a
-            criteria to decide the cluster. Cluster creation will be
-            failed by being an error state if the total number of
-            instances created is less than the min_num_instances. For
-            example, given that num_instances = 5 and min_num_instances
-            = 3,
-
-            -  if 4 instances are created and then registered
-               successfully but one instance is failed, the failed VM
-               will be deleted and the cluster will be resized to 4
-               instances in running state.
-            -  if 2 instances are created successfully and 3 instances
-               are failed, the cluster will be in an error state and
-               does not delete failed VMs for debugging.
-            -  if 2 instance are created and then registered
-               successfully but 3 instances are failed to initialize,
-               the cluster will be in an error state and does not delete
-               failed VMs for debugging. NB: This can only be set for
-               primary workers now.
+            Optional. The minimum number of primary worker instances to
+            create. If ``min_num_instances`` is set, cluster creation
+            will succeed if the number of primary workers created is at
+            least equal to the ``min_num_instances`` number.
+
+            Example: Cluster creation request with ``num_instances`` =
+            ``5`` and ``min_num_instances`` = ``3``:
+
+            -  If 4 VMs are created and 1 instance fails, the failed VM
+               is deleted. The cluster is resized to 4 instances and
+               placed in a ``RUNNING`` state.
+            -  If 2 instances are created and 3 instances fail, the
+               cluster in placed in an ``ERROR`` state. The failed VMs
+               are not deleted.
         instance_flexibility_policy (google.cloud.dataproc_v1.types.InstanceFlexibilityPolicy):
             Optional. Instance flexibility Policy
             allowing a mixture of VM shapes and provisioning
@@ -1251,13 +1246,13 @@ class NodeGroup(proto.Message):
     """
 
     class Role(proto.Enum):
-        r"""Node group roles.
+        r"""Node pool roles.
 
         Values:
             ROLE_UNSPECIFIED (0):
                 Required unspecified role.
             DRIVER (1):
-                Job drivers run on the node group.
+                Job drivers run on the node pool.
         """
         ROLE_UNSPECIFIED = 0
         DRIVER = 1
@@ -2359,6 +2354,22 @@ class DiagnoseClusterRequest(proto.Message):
             handle the request.
         cluster_name (str):
             Required. The cluster name.
+        tarball_gcs_dir (str):
+            Optional. The output Cloud Storage directory
+            for the diagnostic tarball. If not specified, a
+            task-specific directory in the cluster's staging
+            bucket will be used.
+        diagnosis_interval (google.type.interval_pb2.Interval):
+            Optional. Time interval in which diagnosis
+            should be carried out on the cluster.
+        jobs (MutableSequence[str]):
+            Optional. Specifies a list of jobs on which
+            diagnosis is to be performed. Format:
+            projects/{project}/regions/{region}/jobs/{job}
+        yarn_application_ids (MutableSequence[str]):
+            Optional. Specifies a list of yarn
+            applications on which diagnosis is to be
+            performed.
     """
 
     project_id: str = proto.Field(
@@ -2373,6 +2384,23 @@ class DiagnoseClusterRequest(proto.Message):
         proto.STRING,
         number=2,
     )
+    tarball_gcs_dir: str = proto.Field(
+        proto.STRING,
+        number=4,
+    )
+    diagnosis_interval: interval_pb2.Interval = proto.Field(
+        proto.MESSAGE,
+        number=6,
+        message=interval_pb2.Interval,
+    )
+    jobs: MutableSequence[str] = proto.RepeatedField(
+        proto.STRING,
+        number=10,
+    )
+    yarn_application_ids: MutableSequence[str] = proto.RepeatedField(
+        proto.STRING,
+        number=11,
+    )
 
 
 class DiagnoseClusterResults(proto.Message):

samples/generated_samples/snippet_metadata_google.cloud.dataproc.v1.json

@@ -8,7 +8,7 @@
     ],
     "language": "PYTHON",
     "name": "google-cloud-dataproc",
-    "version": "5.5.1"
+    "version": "0.1.0"
   },
   "snippets": [
     {

scripts/fixup_dataproc_v1_keywords.py

@@ -50,7 +50,7 @@ class dataprocCallTransformer(cst.CSTTransformer):
         'delete_cluster': ('project_id', 'region', 'cluster_name', 'cluster_uuid', 'request_id', ),
         'delete_job': ('project_id', 'region', 'job_id', ),
         'delete_workflow_template': ('name', 'version', ),
-        'diagnose_cluster': ('project_id', 'region', 'cluster_name', ),
+        'diagnose_cluster': ('project_id', 'region', 'cluster_name', 'tarball_gcs_dir', 'diagnosis_interval', 'jobs', 'yarn_application_ids', ),
         'get_autoscaling_policy': ('name', ),
         'get_batch': ('name', ),
         'get_cluster': ('project_id', 'region', 'cluster_name', ),

tests/unit/gapic/dataproc_v1/test_cluster_controller.py

@@ -51,6 +51,7 @@
 from google.protobuf import field_mask_pb2  # type: ignore
 from google.protobuf import json_format
 from google.protobuf import timestamp_pb2  # type: ignore
+from google.type import interval_pb2  # type: ignore
 import grpc
 from grpc.experimental import aio
 from proto.marshal.rules import wrappers