{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/google-cloud-dataproc/json-schema/google-cloud-dataproc-workflow-template-schema.json",
  "title": "WorkflowTemplate",
  "description": "A Dataproc workflow template resource.",
  "x-generated": "2026-11-11",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/google-cloud-dataproc-dataproc-projects-api-openapi.yml#/components/schemas/WorkflowTemplate",
  "properties": {
    "parameters": {
      "description": "Optional. Template parameters whose values are substituted into the template. Values for parameters must be provided when the template is instantiated.",
      "type": "array",
      "items": {
        "$ref": "#/$defs/TemplateParameter"
      }
    },
    "version": {
      "format": "int32",
      "description": "Optional. Used to perform a consistent read-modify-write.This field should be left blank for a CreateWorkflowTemplate request. It is required for an UpdateWorkflowTemplate request, and must match the current server version. A typical update template flow would fetch the current template with a GetWorkflowTemplate request, which will return the current template with the version field filled in with the current server version. The user updates other fields in the template, then returns it as part of the UpdateWorkflowTemplate request.",
      "type": "integer"
    },
    "placement": {
      "$ref": "#/$defs/WorkflowTemplatePlacement",
      "description": "Required. WorkflowTemplate scheduling information."
    },
    "encryptionConfig": {
      "$ref": "#/$defs/GoogleCloudDataprocV1WorkflowTemplateEncryptionConfig",
      "description": "Optional. Encryption settings for encrypting workflow template job arguments."
    },
    "name": {
      "type": "string",
      "description": "Output only. The resource name of the workflow template, as described in https://cloud.google.com/apis/design/resource_names. For projects.regions.workflowTemplates, the resource name of the template has the following format: projects/{project_id}/regions/{region}/workflowTemplates/{template_id} For projects.locations.workflowTemplates, the resource name of the template has the following format: projects/{project_id}/locations/{location}/workflowTemplates/{template_id}",
      "readOnly": true
    },
    "createTime": {
      "description": "Output only. The time template was created.",
      "readOnly": true,
      "type": "string",
      "format": "google-datetime"
    },
    "labels": {
      "additionalProperties": {
        "type": "string"
      },
      "description": "Optional. The labels to associate with this template. These labels will be propagated to all jobs and clusters created by the workflow instance.Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt).Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt).No more than 32 labels can be associated with a template.",
      "type": "object"
    },
    "dagTimeout": {
      "description": "Optional. Timeout duration for the DAG of jobs, expressed in seconds (see JSON representation of duration (https://developers.google.com/protocol-buffers/docs/proto3#json)). The timeout duration must be from 10 minutes (\"600s\") to 24 hours (\"86400s\"). The timer begins when the first job is submitted. If the workflow is running at the end of the timeout period, any remaining jobs are cancelled, the workflow is ended, and if the workflow was running on a managed cluster, the cluster is deleted.",
      "format": "google-duration",
      "type": "string"
    },
    "id": {
      "type": "string"
    },
    "updateTime": {
      "format": "google-datetime",
      "type": "string",
      "description": "Output only. The time template was last updated.",
      "readOnly": true
    },
    "jobs": {
      "description": "Required. The Directed Acyclic Graph of Jobs to submit.",
      "type": "array",
      "items": {
        "$ref": "#/$defs/OrderedJob"
      }
    }
  },
  "type": "object",
  "$defs": {
    "AcceleratorConfig": {
      "properties": {
        "acceleratorTypeUri": {
          "description": "Full URL, partial URI, or short name of the accelerator type resource to expose to this instance. See Compute Engine AcceleratorTypes (https://cloud.google.com/compute/docs/reference/v1/acceleratorTypes).Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/acceleratorTypes/nvidia-tesla-t4 projects/[project_id]/zones/[zone]/acceleratorTypes/nvidia-tesla-t4 nvidia-tesla-t4Auto Zone Exception: If you are using Auto Zone Placement (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement), you must use the short name of the accelerator type resource, for example, nvidia-tesla-t4.",
          "type": "string"
        },
        "acceleratorCount": {
          "type": "integer",
          "description": "The number of the accelerator cards of this type exposed to this instance.",
          "format": "int32"
        }
      },
      "description": "Specifies the type and number of accelerator cards attached to the instances of an instance. See GPUs on Compute Engine (https://cloud.google.com/compute/docs/gpus/).",
      "type": "object"
    },
    "AttachedDiskConfig": {
      "properties": {
        "provisionedIops": {
          "format": "int64",
          "description": "Optional. Indicates how many IOPS to provision for the attached disk. This sets the number of I/O operations per second that the disk can handle. See https://cloud.google.com/compute/docs/disks/hyperdisks#hyperdisk-features",
          "type": "string"
        },
        "diskSizeGb": {
          "description": "Optional. Disk size in GB.",
          "format": "int32",
          "type": "integer"
        },
        "diskType": {
          "description": "Optional. Deprecated: Use type instead.",
          "type": "string",
          "enum": [
            "DISK_TYPE_UNSPECIFIED",
            "HYPERDISK_BALANCED",
            "HYPERDISK_EXTREME",
            "HYPERDISK_ML",
            "HYPERDISK_THROUGHPUT"
          ],
          "deprecated": true
        },
        "provisionedThroughput": {
          "format": "int64",
          "type": "string",
          "description": "Optional. Indicates how much throughput to provision for the attached disk. This sets the number of throughput mb per second that the disk can handle. See https://cloud.google.com/compute/docs/disks/hyperdisks#hyperdisk-features"
        },
        "type": {
          "description": "Optional. Attached disk type. Currently only supports Hyperdisks. See https://cloud.google.com/compute/docs/disks/hyperdisks. Note: Hyperdisk Balanced High Availability is not supported.Allowed values are: hyperdisk-balanced hyperdisk-extreme hyperdisk-ml hyperdisk-throughput",
          "type": "string"
        }
      },
      "description": "Specifies the config of attached disk options for single VM instance.",
      "type": "object"
    },
    "AutoscalingConfig": {
      "type": "object",
      "description": "Autoscaling Policy config associated with the cluster.",
      "properties": {
        "policyUri": {
          "type": "string",
          "description": "Optional. The autoscaling policy used by the cluster.Only resource names including projectid and location (region) are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id] projects/[project_id]/locations/[dataproc_region]/autoscalingPolicies/[policy_id]Note that the policy must be in the same project and region."
        }
      }
    },
    "AuxiliaryNodeGroup": {
      "properties": {
        "nodeGroup": {
          "$ref": "#/$defs/NodeGroup",
          "description": "Required. Node group configuration."
        },
        "nodeGroupId": {
          "type": "string",
          "description": "Optional. A node group ID. Generated if not specified.The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). Cannot begin or end with underscore or hyphen. Must consist of from 3 to 33 characters."
        }
      },
      "type": "object",
      "description": "Node group identification and configuration information."
    },
    "ClusterConfig": {
      "properties": {
        "diagnosticBucket": {
          "type": "string",
          "description": "Optional. A Cloud Storage bucket used to collect checkpoint diagnostic data (https://cloud.google.com/dataproc/docs/support/diagnose-clusters#checkpoint_diagnostic_data). If you do not specify a diagnostic bucket, The service will use the temp bucket to collect the checkpoint diagnostic data. This field requires a Cloud Storage bucket name, not a gs://... URI to a Cloud Storage bucket."
        },
        "securityConfig": {
          "$ref": "#/$defs/SecurityConfig",
          "description": "Optional. Security settings for the cluster."
        },
        "softwareConfig": {
          "$ref": "#/$defs/SoftwareConfig",
          "description": "Optional. The config settings for cluster software."
        },
        "workerFlexibleConfig": {
          "$ref": "#/$defs/FlexibleInstanceGroupConfig",
          "description": "Optional. The High Obtainability (HO) config settings for the cluster's worker instances.In High Obtainability (HO) mode, flexible configs are the single source of truth for desired cluster configuration. num_instances represents the desired capacity of the worker group and is mutable via cluster updates and autoscaling.Only one of worker_config or worker_flexible_config can be set.In High Obtainability (HO) mode, for multi-node (standard) clusters, both master_flexible_config and worker_flexible_config must be specified. Mixing standard and flexible configs across node groups is not allowed. Single-node clusters do not specify worker configs."
        },
        "tempBucket": {
          "description": "Optional. A Cloud Storage bucket used to store ephemeral cluster and jobs data, such as Spark and MapReduce history files. If you do not specify a temp bucket, the service will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's temp bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket. The default bucket has a TTL of 90 days, but you can use any TTL (or none) if you specify a bucket (see staging and temp buckets (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a gs://... URI to a Cloud Storage bucket.",
          "type": "string"
        },
        "masterFlexibleConfig": {
          "$ref": "#/$defs/FlexibleInstanceGroupConfig",
          "description": "Optional. The High Obtainability (HO) config settings for the cluster's master instances.In High Obtainability (HO) mode, flexible configs are the single source of truth for desired cluster configuration across node groups: * For single-node clusters: master_flexible_config must be specified, and no worker configs should be set. * For multi-node (standard) clusters: both master_flexible_config and worker_flexible_config must be specified. Mixing standard and flexible configs across node groups is not allowed.Only one of master_config or master_flexible_config can be set."
        },
        "encryptionConfig": {
          "$ref": "#/$defs/EncryptionConfig",
          "description": "Optional. Encryption settings for the cluster."
        },
        "schedulingConfig": {
          "$ref": "#/$defs/SchedulingConfig",
          "description": "Optional. Config for scheduling the resources to be allocated when available."
        },
        "lifecycleConfig": {
          "$ref": "#/$defs/LifecycleConfig",
          "description": "Optional. Lifecycle setting for the cluster."
        },
        "autoscalingConfig": {
          "$ref": "#/$defs/AutoscalingConfig",
          "description": "Optional. Autoscaling config for the policy associated with the cluster. Cluster does not autoscale if this field is unset."
        },
        "clusterTier": {
          "type": "string",
          "enum": [
            "CLUSTER_TIER_UNSPECIFIED",
            "CLUSTER_TIER_STANDARD",
            "CLUSTER_TIER_PREMIUM"
          ],
          "description": "Optional. The cluster tier."
        },
        "gkeClusterConfig": {
          "$ref": "#/$defs/GkeClusterConfig",
          "description": "Optional. BETA. The Kubernetes Engine config for clusters deployed to Kubernetes. These config settings are mutually exclusive with Compute Engine-based options, such as gce_cluster_config, master_config, worker_config, secondary_worker_config, and autoscaling_config."
        },
        "gceClusterConfig": {
          "$ref": "#/$defs/GceClusterConfig",
          "description": "Optional. The shared Compute Engine config settings for all instances in a cluster."
        },
        "secondaryWorkerFlexibleConfig": {
          "$ref": "#/$defs/FlexibleInstanceGroupConfig",
          "description": "Optional. The High Obtainability (HO) config settings for a cluster's secondary worker instances.In High Obtainability (HO) mode, flexible configs are the single source of truth for desired cluster configuration. num_instances represents the desired capacity of the secondary worker group and is mutable via cluster updates and autoscaling.Only one of secondary_worker_config or secondary_worker_flexible_config can be set.In High Obtainability (HO) mode, secondary workers are optional. If secondary workers are used in an HO cluster, they must be configured using secondary_worker_flexible_config (not secondary_worker_config)."
        },
        "masterConfig": {
          "$ref": "#/$defs/InstanceGroupConfig",
          "description": "Optional. The Compute Engine config settings for the cluster's master instance."
        },
        "engine": {
          "type": "string",
          "enum": [
            "ENGINE_UNSPECIFIED",
            "DEFAULT",
            "LIGHTNING"
          ],
          "description": "Optional. The cluster engine."
        },
        "configBucket": {
          "type": "string",
          "description": "Optional. A Cloud Storage bucket used to stage job dependencies, config files, and job driver console output. If you do not specify a staging bucket, the service will determine a Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Compute Engine zone where your cluster is deployed, and then create and manage this project-level, per-location bucket (see staging and temp buckets (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/staging-bucket)). This field requires a Cloud Storage bucket name, not a gs://... URI to a Cloud Storage bucket."
        },
        "workerConfig": {
          "$ref": "#/$defs/InstanceGroupConfig",
          "description": "Optional. The Compute Engine config settings for the cluster's worker instances."
        },
        "dataprocMetricConfig": {
          "$ref": "#/$defs/DataprocMetricConfig",
          "description": "Optional. The config for metrics."
        },
        "initializationActions": {
          "items": {
            "$ref": "#/$defs/NodeInitializationAction"
          },
          "description": "Optional. Commands to execute on each node after config is completed. By default, executables are run on master and all worker nodes. You can test a node's role metadata to run an executable on a master or worker node, as shown below using curl (you can also use wget): ROLE=$(curl -H Metadata-Flavor:Google http://metadata/computeMetadata/v1/instance/attributes/dataproc-role) if [[ \"${ROLE}\" == 'Master' ]]; then ... master specific actions ... else ... worker specific actions ... fi ",
          "type": "array"
        },
        "clusterType": {
          "type": "string",
          "enum": [
            "CLUSTER_TYPE_UNSPECIFIED",
            "STANDARD",
            "SINGLE_NODE",
            "ZERO_SCALE"
          ],
          "description": "Optional. The type of the cluster."
        },
        "auxiliaryNodeGroups": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/AuxiliaryNodeGroup"
          },
          "description": "Optional. The node group settings."
        },
        "secondaryWorkerConfig": {
          "$ref": "#/$defs/InstanceGroupConfig",
          "description": "Optional. The Compute Engine config settings for a cluster's secondary worker instances"
        },
        "metastoreConfig": {
          "$ref": "#/$defs/MetastoreConfig",
          "description": "Optional. Metastore configuration."
        },
        "endpointConfig": {
          "$ref": "#/$defs/EndpointConfig",
          "description": "Optional. Port/endpoint configuration for this cluster"
        }
      },
      "type": "object",
      "description": "The cluster config."
    },
    "ClusterSelector": {
      "properties": {
        "zone": {
          "description": "Optional. The zone where workflow process executes. This parameter does not affect the selection of the cluster.If unspecified, the zone of the first cluster matching the selector is used.",
          "type": "string"
        },
        "clusterLabels": {
          "type": "object",
          "description": "Required. The cluster labels. Cluster must have all labels to match.",
          "additionalProperties": {
            "type": "string"
          }
        }
      },
      "description": "A selector that chooses target cluster for jobs based on metadata.",
      "type": "object"
    },
    "ConfidentialInstanceConfig": {
      "type": "object",
      "description": "Confidential Instance Config for clusters using Confidential VMs (https://cloud.google.com/confidential-computing/confidential-vm/docs)",
      "properties": {
        "confidentialInstanceType": {
          "description": "Optional. Defines the type of Confidential Compute technology to use.",
          "type": "string",
          "enum": [
            "CONFIDENTIAL_INSTANCE_TYPE_UNSPECIFIED",
            "SEV",
            "SEV_SNP",
            "TDX"
          ]
        },
        "enableConfidentialCompute": {
          "type": "boolean",
          "description": "Optional. Deprecated: Use 'confidential_instance_type' instead. Defines whether the instance should have confidential compute enabled.",
          "deprecated": true
        }
      }
    },
    "DataprocMetricConfig": {
      "properties": {
        "metrics": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/Metric"
          },
          "description": "Required. Metrics sources to enable."
        }
      },
      "type": "object",
      "description": "Metric config."
    },
    "DiskConfig": {
      "type": "object",
      "properties": {
        "bootDiskSizeGb": {
          "format": "int32",
          "type": "integer",
          "description": "Optional. Size in GB of the boot disk (default is 500GB)."
        },
        "bootDiskProvisionedIops": {
          "description": "Optional. Indicates how many IOPS to provision for the disk. This sets the number of I/O operations per second that the disk can handle. This field is supported only if boot_disk_type is hyperdisk-balanced.",
          "type": "string",
          "format": "int64"
        },
        "bootDiskType": {
          "type": "string",
          "description": "Optional. Type of the boot disk (default is pd-standard). Valid values: pd-balanced (Persistent Disk Balanced Solid State Drive), pd-ssd (Persistent Disk Solid State Drive), or pd-standard (Persistent Disk Hard Disk Drive). See Disk types (https://cloud.google.com/compute/docs/disks#disk-types)."
        },
        "numLocalSsds": {
          "format": "int32",
          "type": "integer",
          "description": "Optional. Number of attached SSDs, from 0 to 8 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and HDFS (https://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html) data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic config and installed binaries.Note: Local SSD options may vary by machine type and number of vCPUs selected."
        },
        "bootDiskProvisionedThroughput": {
          "format": "int64",
          "description": "Optional. Indicates how much throughput to provision for the disk. This sets the number of throughput mb per second that the disk can handle. Values must be greater than or equal to 1. This field is supported only if boot_disk_type is hyperdisk-balanced.",
          "type": "string"
        },
        "attachedDiskConfigs": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/AttachedDiskConfig"
          },
          "description": "Optional. A list of attached disk configs for a group of VM instances."
        },
        "localSsdInterface": {
          "description": "Optional. Interface type of local SSDs (default is scsi). Valid values: scsi (Small Computer System Interface), nvme (Non-Volatile Memory Express). See local SSD performance (https://cloud.google.com/compute/docs/disks/local-ssd#performance).",
          "type": "string"
        }
      },
      "description": "Specifies the config of boot disk and attached disk options for a group of VM instances."
    },
    "EncryptionConfig": {
      "properties": {
        "kmsKey": {
          "description": "Optional. The Cloud KMS key resource name to use for cluster persistent disk and job argument encryption. See Use CMEK with cluster data (https://cloud.google.com//dataproc/docs/concepts/configuring-clusters/customer-managed-encryption#use_cmek_with_cluster_data) for more information.When this key resource name is provided, the following job arguments of the following job types submitted to the cluster are encrypted using CMEK: FlinkJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/FlinkJob) HadoopJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/HadoopJob) SparkJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/SparkJob) SparkRJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/SparkRJob) PySparkJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/PySparkJob) SparkSqlJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/SparkSqlJob) scriptVariables and queryList.queries HiveJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/HiveJob) scriptVariables and queryList.queries PigJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/PigJob) scriptVariables and queryList.queries PrestoJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/PrestoJob) scriptVariables and queryList.queries",
          "type": "string"
        },
        "gcePdKmsKeyName": {
          "type": "string",
          "description": "Optional. The Cloud KMS key resource name to use for persistent disk encryption for all instances in the cluster. See Use CMEK with cluster data (https://cloud.google.com//dataproc/docs/concepts/configuring-clusters/customer-managed-encryption#use_cmek_with_cluster_data) for more information."
        }
      },
      "description": "Encryption settings for the cluster.",
      "type": "object"
    },
    "EndpointConfig": {
      "type": "object",
      "properties": {
        "httpPorts": {
          "readOnly": true,
          "description": "Output only. The map of port descriptions to URLs. Will only be populated if enable_http_port_access is true.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "enableHttpPortAccess": {
          "type": "boolean",
          "description": "Optional. If true, enable http access to specific ports on the cluster from external sources. Defaults to false."
        }
      },
      "description": "Endpoint config for this cluster"
    },
    "FlexibleInstanceGroupConfig": {
      "description": "The configuration for High Obtainability (HO) flexible instance groups. Flexible instance group configs serve as the single source of truth for desired state.",
      "type": "object",
      "properties": {
        "bootDiskSizeGb": {
          "description": "Optional. The boot disk size in GB. This is a create-time specification and is not currently mutable via update masks.",
          "type": "integer",
          "format": "int32"
        },
        "coreCount": {
          "type": "integer",
          "description": "Optional. The number of vCPUs per instance. Must be a power of 2 (2, 4, 8, 16, 32). This is a create-time specification and is not currently mutable via update masks.",
          "format": "int32"
        },
        "hardwareClass": {
          "description": "Optional. The hardware class of the instances. This is a create-time specification and is not currently mutable via update masks.",
          "type": "string",
          "enum": [
            "HARDWARE_CLASS_UNSPECIFIED",
            "STANDARD",
            "PERFORMANCE"
          ]
        },
        "numInstances": {
          "format": "int32",
          "description": "Optional. The number of VM instances requested.For master instances, this must be 1. For worker and secondary worker instances, this represents the desired capacity of the group and is mutable via cluster update operations and autoscaling.",
          "type": "integer"
        }
      }
    },
    "FlinkJob": {
      "properties": {
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "mainClass": {
          "description": "The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jarFileUris.",
          "type": "string"
        },
        "mainJarFileUri": {
          "description": "The HCFS URI of the jar file that contains the main class.",
          "type": "string"
        },
        "savepointUri": {
          "description": "Optional. HCFS URI of the savepoint, which contains the last saved progress for starting the current job.",
          "type": "string"
        },
        "jarFileUris": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Flink driver and tasks."
        },
        "properties": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "Optional. A mapping of property names to values, used to configure Flink. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/flink/conf/flink-defaults.conf and classes in user code.",
          "type": "object"
        },
        "args": {
          "items": {
            "type": "string"
          },
          "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision might occur that causes an incorrect job submission.",
          "type": "array"
        }
      },
      "description": "A Dataproc job for running Apache Flink applications on YARN.",
      "type": "object"
    },
    "GceClusterConfig": {
      "type": "object",
      "description": "Common config settings for resources of Compute Engine cluster instances, applicable to all instances in the cluster.",
      "properties": {
        "zoneUri": {
          "description": "Optional. The Compute Engine zone where the cluster will be located. If omitted, the service will pick a zone in the cluster's Compute Engine region. On a get request, zone will always be present.A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone] projects/[project_id]/zones/[zone] [zone]",
          "type": "string"
        },
        "serviceAccountScopes": {
          "items": {
            "type": "string"
          },
          "description": "Optional. The URIs of service account scopes to be included in Compute Engine instances. The following base set of scopes is always included: https://www.googleapis.com/auth/cloud.useraccounts.readonly https://www.googleapis.com/auth/devstorage.read_write https://www.googleapis.com/auth/logging.writeIf no scopes are specified, the following defaults are also provided: https://www.googleapis.com/auth/bigquery https://www.googleapis.com/auth/bigtable.admin.table https://www.googleapis.com/auth/bigtable.data https://www.googleapis.com/auth/devstorage.full_control",
          "type": "array"
        },
        "confidentialInstanceConfig": {
          "$ref": "#/$defs/ConfidentialInstanceConfig",
          "description": "Optional. Confidential Instance Config for clusters using Confidential VMs (https://cloud.google.com/confidential-computing/confidential-vm/docs)."
        },
        "networkUri": {
          "type": "string",
          "description": "Optional. The Compute Engine network to be used for machine communications. Cannot be specified with subnetwork_uri. If neither network_uri nor subnetwork_uri is specified, the \"default\" network of the project is used, if it exists. Cannot be a Custom Subnet Network (see Using Subnetworks (https://cloud.google.com/compute/docs/subnetworks) for more information).A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/global/networks/default projects/[project_id]/global/networks/default default"
        },
        "tags": {
          "description": "The Compute Engine network tags to add to all instances (see Tagging instances (https://cloud.google.com/vpc/docs/add-remove-network-tags)).",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "nodeGroupAffinity": {
          "$ref": "#/$defs/NodeGroupAffinity",
          "description": "Optional. Node Group Affinity for sole-tenant clusters."
        },
        "multiZoneConfig": {
          "$ref": "#/$defs/MultiZoneConfig",
          "description": "Optional. Controls how instances within this Cluster are allowed to exist in multiple Zones within the Region. Only one of zone_uri or multi_zone_config must be set."
        },
        "shieldedInstanceConfig": {
          "$ref": "#/$defs/ShieldedInstanceConfig",
          "description": "Optional. Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm)."
        },
        "serviceAccount": {
          "description": "Optional. The VM service account (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/service-accounts#service_accounts_in_dataproc) (also see VM Data Plane identity (https://cloud.google.com/dataproc/docs/concepts/iam/dataproc-principals#vm_service_account_data_plane_identity)) used by cluster VM instances to access Google Cloud Platform services.If not specified, the Compute Engine default service account (https://cloud.google.com/compute/docs/access/service-accounts#default_service_account) is used.",
          "type": "string"
        },
        "subnetworkUri": {
          "description": "Optional. The Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri.A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/[region]/subnetworks/sub0 projects/[project_id]/regions/[region]/subnetworks/sub0 sub0",
          "type": "string"
        },
        "reservationAffinity": {
          "$ref": "#/$defs/ReservationAffinity",
          "description": "Optional. Reservation Affinity for consuming Zonal reservation."
        },
        "resourceManagerTags": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "Optional. Resource manager tags (https://cloud.google.com/resource-manager/docs/tags/tags-creating-and-managing) to add to all instances (see Use secure tags (https://cloud.google.com/dataproc/docs/guides/use-secure-tags)).",
          "type": "object"
        },
        "metadata": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          },
          "description": "Optional. The Compute Engine metadata entries to add to all instances (see Project and instance metadata (https://cloud.google.com/compute/docs/storing-retrieving-metadata#project_and_instance_metadata))."
        },
        "autoZoneExcludeZoneUris": {
          "items": {
            "type": "string"
          },
          "description": "Optional. An optional list of Compute Engine zones where the cluster will not be located when Auto Zone is enabled. Only one of zone_uri or auto_zone_exclude_zone_uris can be set. If both are omitted, the service will pick a zone in the cluster Compute Engine region. If auto_zone_exclude_zone_uris is set and there is more than one non-excluded zone, the service will pick one of the non-excluded zones. Otherwise, cluster creation will fail with INVALID_ARGUMENT error.A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone] projects/[project_id]/zones/[zone] [zone]",
          "type": "array"
        },
        "internalIpOnly": {
          "description": "Optional. This setting applies to subnetwork-enabled networks. It is set to true by default in clusters created with image versions 2.2.x.When set to true: All cluster VMs have internal IP addresses. Google Private Access (https://cloud.google.com/vpc/docs/private-google-access) must be enabled to access the Dataproc API and other Google Cloud APIs. Off-cluster dependencies must be configured to be accessible without external IP addresses.When set to false: Cluster VMs are not restricted to internal IP addresses. Ephemeral external IP addresses are assigned to each cluster VM.",
          "type": "boolean"
        },
        "privateIpv6GoogleAccess": {
          "type": "string",
          "enum": [
            "PRIVATE_IPV6_GOOGLE_ACCESS_UNSPECIFIED",
            "INHERIT_FROM_SUBNETWORK",
            "OUTBOUND",
            "BIDIRECTIONAL"
          ],
          "description": "Optional. The type of IPv6 access for a cluster."
        }
      }
    },
    "GkeClusterConfig": {
      "type": "object",
      "properties": {
        "namespacedGkeDeploymentTarget": {
          "$ref": "#/$defs/NamespacedGkeDeploymentTarget",
          "description": "Optional. Deprecated. Use gkeClusterTarget. Used only for the deprecated beta. A target for the deployment."
        },
        "gkeClusterTarget": {
          "type": "string",
          "description": "Optional. A target GKE cluster to deploy to. It must be in the same project and region as the Dataproc cluster (the GKE cluster can be zonal or regional). Format: 'projects/{project}/locations/{location}/clusters/{cluster_id}'"
        },
        "nodePoolTarget": {
          "type": "array",
          "description": "Optional. GKE node pools where workloads will be scheduled. At least one node pool must be assigned the DEFAULT GkeNodePoolTarget.Role. If a GkeNodePoolTarget is not specified, Dataproc constructs a DEFAULT GkeNodePoolTarget. Each role can be given to only one GkeNodePoolTarget. All node pools must have the same location settings.",
          "items": {
            "$ref": "#/$defs/GkeNodePoolTarget"
          }
        }
      },
      "description": "The cluster's GKE config."
    },
    "GkeNodeConfig": {
      "description": "Parameters that describe cluster nodes.",
      "type": "object",
      "properties": {
        "localSsdCount": {
          "type": "integer",
          "format": "int32",
          "description": "Optional. The number of local SSD disks to attach to the node, which is limited by the maximum number of disks allowable per zone (see Adding Local SSDs (https://cloud.google.com/compute/docs/disks/local-ssd))."
        },
        "bootDiskKmsKey": {
          "type": "string",
          "description": "Optional. The Customer Managed Encryption Key (CMEK) (https://cloud.google.com/kubernetes-engine/docs/how-to/using-cmek) used to encrypt the boot disk attached to each node in the node pool. Specify the key using the following format: projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}"
        },
        "serviceAccount": {
          "type": "string",
          "description": "Optional. Specifies the service account (https://cloud.google.com/dataproc/docs/guides/dpgke/dataproc-gke-iam) to be used by the node pools. Specify the email address of the service account or its full resource name.Format: projects/{project}/serviceAccounts/{service_account_email} or {service_account_email}."
        },
        "accelerators": {
          "description": "Optional. A list of hardware accelerators (https://cloud.google.com/compute/docs/gpus) to attach to each node.",
          "items": {
            "$ref": "#/$defs/GkeNodePoolAcceleratorConfig"
          },
          "type": "array"
        },
        "preemptible": {
          "description": "Optional. Whether the nodes are created as legacy preemptible VM instances (https://cloud.google.com/compute/docs/instances/preemptible). Also see Spot VMs, preemptible VM instances without a maximum lifetime. Legacy and Spot preemptible nodes cannot be used in a node pool with the CONTROLLER role or in the DEFAULT node pool if the CONTROLLER role is not assigned (the DEFAULT node pool will assume the CONTROLLER role).",
          "type": "boolean"
        },
        "spot": {
          "description": "Optional. Whether the nodes are created as Spot VM instances (https://cloud.google.com/compute/docs/instances/spot). Spot VMs are the latest update to legacy preemptible VMs. Spot VMs do not have a maximum lifetime. Legacy and Spot preemptible nodes cannot be used in a node pool with the CONTROLLER role or in the DEFAULT node pool if the CONTROLLER role is not assigned (the DEFAULT node pool will assume the CONTROLLER role).",
          "type": "boolean"
        },
        "minCpuPlatform": {
          "type": "string",
          "description": "Optional. Minimum CPU platform (https://cloud.google.com/compute/docs/instances/specify-min-cpu-platform) to be used by this instance. The instance may be scheduled on the specified or a newer CPU platform. Specify the friendly names of CPU platforms, such as \"Intel Haswell\"` or Intel Sandy Bridge\"."
        },
        "machineType": {
          "description": "Optional. The name of a Compute Engine machine type (https://cloud.google.com/compute/docs/machine-types).",
          "type": "string"
        }
      }
    },
    "GkeNodePoolAcceleratorConfig": {
      "type": "object",
      "description": "A GkeNodeConfigAcceleratorConfig represents a Hardware Accelerator request for a node pool.",
      "properties": {
        "acceleratorCount": {
          "format": "int64",
          "description": "The number of accelerator cards exposed to an instance.",
          "type": "string"
        },
        "acceleratorType": {
          "type": "string",
          "description": "The accelerator type resource namename (see GPUs on Compute Engine)."
        },
        "gpuPartitionSize": {
          "description": "Size of partitions to create on the GPU. Valid values are described in the NVIDIA mig user guide (https://docs.nvidia.com/datacenter/tesla/mig-user-guide/#partitioning).",
          "type": "string"
        }
      }
    },
    "GkeNodePoolAutoscalingConfig": {
      "properties": {
        "minNodeCount": {
          "description": "The minimum number of nodes in the node pool. Must be >= 0 and <= max_node_count.",
          "type": "integer",
          "format": "int32"
        },
        "maxNodeCount": {
          "format": "int32",
          "type": "integer",
          "description": "The maximum number of nodes in the node pool. Must be >= min_node_count, and must be > 0. Note: Quota must be sufficient to scale up the cluster."
        }
      },
      "description": "GkeNodePoolAutoscaling contains information the cluster autoscaler needs to adjust the size of the node pool to the current cluster usage.",
      "type": "object"
    },
    "GkeNodePoolConfig": {
      "type": "object",
      "properties": {
        "autoscaling": {
          "$ref": "#/$defs/GkeNodePoolAutoscalingConfig",
          "description": "Optional. The autoscaler configuration for this node pool. The autoscaler is enabled only when a valid configuration is present."
        },
        "config": {
          "$ref": "#/$defs/GkeNodeConfig",
          "description": "Optional. The node pool configuration."
        },
        "locations": {
          "items": {
            "type": "string"
          },
          "description": "Optional. The list of Compute Engine zones (https://cloud.google.com/compute/docs/zones#available) where node pool nodes associated with a Dataproc on GKE virtual cluster will be located.Note: All node pools associated with a virtual cluster must be located in the same region as the virtual cluster, and they must be located in the same zone within that region.If a location is not specified during node pool creation, Dataproc on GKE will choose the zone.",
          "type": "array"
        }
      },
      "description": "The configuration of a GKE node pool used by a Dataproc-on-GKE cluster (https://cloud.google.com/dataproc/docs/concepts/jobs/dataproc-gke#create-a-dataproc-on-gke-cluster)."
    },
    "GkeNodePoolTarget": {
      "type": "object",
      "description": "GKE node pools that Dataproc workloads run on.",
      "properties": {
        "nodePoolConfig": {
          "$ref": "#/$defs/GkeNodePoolConfig",
          "description": "Input only. The configuration for the GKE node pool.If specified, Dataproc attempts to create a node pool with the specified shape. If one with the same name already exists, it is verified against all specified fields. If a field differs, the virtual cluster creation will fail.If omitted, any node pool with the specified name is used. If a node pool with the specified name does not exist, Dataproc create a node pool with default values.This is an input only field. It will not be returned by the API."
        },
        "nodePool": {
          "type": "string",
          "description": "Required. The target GKE node pool. Format: 'projects/{project}/locations/{location}/clusters/{cluster}/nodePools/{node_pool}'"
        },
        "roles": {
          "description": "Required. The roles associated with the GKE node pool.",
          "items": {
            "type": "string",
            "enum": [
              "ROLE_UNSPECIFIED",
              "DEFAULT",
              "CONTROLLER",
              "SPARK_DRIVER",
              "SPARK_EXECUTOR"
            ]
          },
          "type": "array"
        }
      }
    },
    "GoogleCloudDataprocV1WorkflowTemplateEncryptionConfig": {
      "properties": {
        "kmsKey": {
          "type": "string",
          "description": "Optional. The Cloud KMS key name to use for encrypting workflow template job arguments.When this this key is provided, the following workflow template job arguments (https://cloud.google.com/dataproc/docs/concepts/workflows/use-workflows#adding_jobs_to_a_template), if present, are CMEK encrypted (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/customer-managed-encryption#use_cmek_with_workflow_template_data): FlinkJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/FlinkJob) HadoopJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/HadoopJob) SparkJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/SparkJob) SparkRJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/SparkRJob) PySparkJob args (https://cloud.google.com/dataproc/docs/reference/rest/v1/PySparkJob) SparkSqlJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/SparkSqlJob) scriptVariables and queryList.queries HiveJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/HiveJob) scriptVariables and queryList.queries PigJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/PigJob) scriptVariables and queryList.queries PrestoJob (https://cloud.google.com/dataproc/docs/reference/rest/v1/PrestoJob) scriptVariables and queryList.queries"
        }
      },
      "type": "object",
      "description": "Encryption settings for encrypting workflow template job arguments."
    },
    "HadoopJob": {
      "properties": {
        "mainJarFileUri": {
          "description": "The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'",
          "type": "string"
        },
        "fileUris": {
          "items": {
            "type": "string"
          },
          "description": "Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.",
          "type": "array"
        },
        "mainClass": {
          "type": "string",
          "description": "The name of the driver's main class. The jar file containing the class must be in the default CLASSPATH or specified in jar_file_uris."
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "jarFileUris": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks."
        },
        "archiveUris": {
          "type": "array",
          "description": "Optional. HCFS URIs of archives to be extracted in the working directory of Hadoop drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, or .zip.",
          "items": {
            "type": "string"
          }
        },
        "args": {
          "items": {
            "type": "string"
          },
          "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as -libjars or -Dfoo=bar, that can be set as job properties, since a collision might occur that causes an incorrect job submission.",
          "type": "array"
        },
        "properties": {
          "type": "object",
          "description": "Optional. A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.",
          "additionalProperties": {
            "type": "string"
          }
        }
      },
      "type": "object",
      "description": "A Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html)."
    },
    "HiveJob": {
      "description": "A Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN.",
      "properties": {
        "queryFileUri": {
          "type": "string",
          "description": "The HCFS URI of the script that contains Hive queries."
        },
        "queryList": {
          "$ref": "#/$defs/QueryList",
          "description": "A list of queries."
        },
        "continueOnFailure": {
          "type": "boolean",
          "description": "Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries."
        },
        "properties": {
          "description": "Optional. A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "scriptVariables": {
          "description": "Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name=\"value\";).",
          "type": "object",
          "additionalProperties": {
            "type": "string"
          }
        },
        "jarFileUris": {
          "description": "Optional. HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.",
          "items": {
            "type": "string"
          },
          "type": "array"
        }
      },
      "type": "object"
    },
    "IdentityConfig": {
      "type": "object",
      "properties": {
        "userServiceAccountMapping": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "Required. Map of user to service account.",
          "type": "object"
        },
        "enableSsh": {
          "description": "Optional. Whether to enable SSH access for the cluster. The default is true for image versions prior to 3.1 and false for image versions 3.1 and later. The default behavior can be changed when creating clusters using image versions 2.3.30 and later.",
          "type": "boolean"
        }
      },
      "description": "Identity related configuration, including service account based secure multi-tenancy user mappings."
    },
    "InstanceFlexibilityPolicy": {
      "type": "object",
      "properties": {
        "provisioningModelMix": {
          "$ref": "#/$defs/ProvisioningModelMix",
          "description": "Optional. Defines how the Group selects the provisioning model to ensure required reliability."
        },
        "instanceMachineTypes": {
          "readOnly": true,
          "description": "Output only. A map of instance short name to machine type. The key is the short name of the Compute Engine instance, and the value is the full machine-type name (e.g., 'n1-standard-16'). See Machine types for more information on valid machine type strings.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "instanceSelectionList": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/InstanceSelection"
          },
          "description": "Optional. List of instance selection options that the group will use when creating new VMs."
        },
        "instanceSelectionResults": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/InstanceSelectionResult"
          },
          "description": "Output only. A list of instance selection results in the group.",
          "readOnly": true
        }
      },
      "description": "Instance flexibility Policy allowing a mixture of VM shapes and provisioning models."
    },
    "InstanceGroupConfig": {
      "description": "The config settings for Compute Engine resources in an instance group, such as a master or worker group.",
      "properties": {
        "diskConfig": {
          "$ref": "#/$defs/DiskConfig",
          "description": "Optional. Disk option config settings."
        },
        "isPreemptible": {
          "readOnly": true,
          "description": "Output only. Specifies that this instance group contains preemptible instances.",
          "type": "boolean"
        },
        "instanceFlexibilityPolicy": {
          "$ref": "#/$defs/InstanceFlexibilityPolicy",
          "description": "Optional. Instance flexibility Policy allowing a mixture of VM shapes and provisioning models."
        },
        "minNumInstances": {
          "type": "integer",
          "description": "Optional. The minimum number of primary worker instances to create. If min_num_instances is set, cluster creation will succeed if the number of primary workers created is at least equal to the min_num_instances number.Example: Cluster creation request with num_instances = 5 and min_num_instances = 3: If 4 VMs are created and 1 instance fails, the failed VM is deleted. The cluster is resized to 4 instances and placed in a RUNNING state. If 2 instances are created and 3 instances fail, the cluster in placed in an ERROR state. The failed VMs are not deleted.",
          "format": "int32"
        },
        "preemptibility": {
          "type": "string",
          "enum": [
            "PREEMPTIBILITY_UNSPECIFIED",
            "NON_PREEMPTIBLE",
            "PREEMPTIBLE",
            "SPOT"
          ],
          "description": "Optional. Specifies the preemptibility of the instance group.The default value for master and worker groups is NON_PREEMPTIBLE. This default cannot be changed.The default value for secondary instances is PREEMPTIBLE."
        },
        "minCpuPlatform": {
          "description": "Optional. Specifies the minimum cpu platform for the Instance Group. See Minimum CPU Platform (https://cloud.google.com/dataproc/docs/concepts/compute/dataproc-min-cpu).",
          "type": "string"
        },
        "accelerators": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/AcceleratorConfig"
          },
          "description": "Optional. The Compute Engine accelerator configuration for these instances."
        },
        "machineTypeUri": {
          "type": "string",
          "description": "Optional. The Compute Engine machine type used for cluster instances.A full URL, partial URI, or short name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/machineTypes/n1-standard-2 projects/[project_id]/zones/[zone]/machineTypes/n1-standard-2 n1-standard-2Auto Zone Exception: If you are using Auto Zone Placement (https://cloud.google.com/dataproc/docs/concepts/configuring-clusters/auto-zone#using_auto_zone_placement), you must use the short name of the machine type resource, for example, n1-standard-2."
        },
        "managedGroupConfig": {
          "$ref": "#/$defs/ManagedGroupConfig",
          "description": "Output only. The config for Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups."
        },
        "instanceReferences": {
          "readOnly": true,
          "type": "array",
          "description": "Output only. List of references to Compute Engine instances.",
          "items": {
            "$ref": "#/$defs/InstanceReference"
          }
        },
        "numInstances": {
          "type": "integer",
          "description": "Optional. The number of VM instances in the instance group. For HA cluster master_config groups, must be set to 3. For standard cluster master_config groups, must be set to 1.",
          "format": "int32"
        },
        "imageUri": {
          "type": "string",
          "description": "Optional. The Compute Engine image resource used for cluster instances.The URI can represent an image or image family.Image examples: https://www.googleapis.com/compute/v1/projects/[project_id]/global/images/[image-id] projects/[project_id]/global/images/[image-id] image-idImage family examples. The service will use the most recent image from the family: https://www.googleapis.com/compute/v1/projects/[project_id]/global/images/family/[custom-image-family-name] projects/[project_id]/global/images/family/[custom-image-family-name]If the URI is unspecified, it will be inferred from SoftwareConfig.image_version or the system default."
        },
        "startupConfig": {
          "$ref": "#/$defs/StartupConfig",
          "description": "Optional. Configuration to handle the startup of instances during cluster create and update process."
        },
        "instanceNames": {
          "description": "Output only. The list of instance names, derived from cluster_name, num_instances, and the instance group.",
          "items": {
            "type": "string"
          },
          "type": "array",
          "readOnly": true
        }
      },
      "type": "object"
    },
    "InstanceReference": {
      "type": "object",
      "properties": {
        "instanceName": {
          "description": "The user-friendly name of the Compute Engine instance.",
          "type": "string"
        },
        "instanceId": {
          "type": "string",
          "description": "The unique identifier of the Compute Engine instance."
        },
        "publicEciesKey": {
          "description": "The public ECIES key used for sharing data with this instance.",
          "type": "string"
        },
        "publicKey": {
          "type": "string",
          "description": "The public RSA key used for sharing data with this instance."
        }
      },
      "description": "A reference to a Compute Engine instance."
    },
    "InstanceSelection": {
      "properties": {
        "machineTypes": {
          "items": {
            "type": "string"
          },
          "description": "Optional. Full machine-type names, e.g. \"n1-standard-16\".",
          "type": "array"
        },
        "diskConfig": {
          "$ref": "#/$defs/DiskConfig",
          "description": "Optional. Disk configuration to apply to the instances in this instance selection. If specified on any entry in instanceSelectionList, then it must be specified on every entry in instanceSelectionList and the instanceGroupConfig must not specify any diskConfig."
        },
        "rank": {
          "type": "integer",
          "description": "Optional. Preference of this instance selection. Lower number means higher preference. The service will first try to create a VM based on the machine-type with priority rank and fallback to next rank based on availability. Machine types and instance selections with the same priority have the same preference.",
          "format": "int32"
        }
      },
      "type": "object",
      "description": "Defines machines types and a rank to which the machines types belong."
    },
    "InstanceSelectionResult": {
      "properties": {
        "machineType": {
          "type": "string",
          "description": "Output only. Full machine-type names, e.g. \"n1-standard-16\".",
          "readOnly": true
        },
        "vmCount": {
          "description": "Output only. Number of VM provisioned with the machine_type.",
          "readOnly": true,
          "type": "integer",
          "format": "int32"
        }
      },
      "description": "Defines a mapping from machine types to the number of VMs that are created with each machine type.",
      "type": "object"
    },
    "JobScheduling": {
      "description": "Job scheduling options.",
      "properties": {
        "maxFailuresTotal": {
          "format": "int32",
          "description": "Optional. Maximum total number of times a driver can be restarted as a result of the driver exiting with a non-zero code. After the maximum number is reached, the job will be reported as failed.Maximum value is 240.Note: Currently, this restartable job option is not supported in Dataproc workflow templates (https://cloud.google.com/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template).",
          "type": "integer"
        },
        "maxFailuresPerHour": {
          "type": "integer",
          "description": "Optional. Maximum number of times per hour a driver can be restarted as a result of driver exiting with non-zero code before job is reported failed.A job might be reported as thrashing if the driver exits with a non-zero code four times within a 10-minute window.Maximum value is 10.Note: This restartable job option is not supported in Dataproc workflow templates (https://cloud.google.com/dataproc/docs/concepts/workflows/using-workflows#adding_jobs_to_a_template).",
          "format": "int32"
        }
      },
      "type": "object"
    },
    "KerberosConfig": {
      "properties": {
        "truststoreUri": {
          "type": "string",
          "description": "Optional. The Cloud Storage URI of the truststore file used for SSL encryption. If not provided, the service will provide a self-signed certificate."
        },
        "crossRealmTrustRealm": {
          "description": "Optional. The remote realm the on-cluster KDC will trust, should the user enable cross realm trust.",
          "type": "string"
        },
        "keystorePasswordUri": {
          "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided keystore. For the self-signed certificate, this password is generated by the service.",
          "type": "string"
        },
        "kdcDbKeyUri": {
          "type": "string",
          "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the master key of the KDC database."
        },
        "tgtLifetimeHours": {
          "format": "int32",
          "description": "Optional. The lifetime of the ticket granting ticket, in hours. If not specified, or user specifies 0, then default value 10 will be used.",
          "type": "integer"
        },
        "keyPasswordUri": {
          "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided key. For the self-signed certificate, this password is generated by the service.",
          "type": "string"
        },
        "crossRealmTrustKdc": {
          "description": "Optional. The KDC (IP or hostname) for the remote trusted realm in a cross realm trust relationship.",
          "type": "string"
        },
        "rootPrincipalPasswordUri": {
          "type": "string",
          "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the root principal password."
        },
        "keystoreUri": {
          "description": "Optional. The Cloud Storage URI of the keystore file used for SSL encryption. If not provided, the service will provide a self-signed certificate.",
          "type": "string"
        },
        "truststorePasswordUri": {
          "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the password to the user provided truststore. For the self-signed certificate, this password is generated by the service.",
          "type": "string"
        },
        "realm": {
          "type": "string",
          "description": "Optional. The name of the on-cluster Kerberos realm. If not specified, the uppercased domain of hostnames will be the realm."
        },
        "crossRealmTrustSharedPasswordUri": {
          "type": "string",
          "description": "Optional. The Cloud Storage URI of a KMS encrypted file containing the shared password between the on-cluster Kerberos realm and the remote trusted realm, in a cross realm trust relationship."
        },
        "kmsKeyUri": {
          "description": "Optional. The URI of the KMS key used to encrypt sensitive files.",
          "type": "string"
        },
        "crossRealmTrustAdminServer": {
          "description": "Optional. The admin server (IP or hostname) for the remote trusted realm in a cross realm trust relationship.",
          "type": "string"
        },
        "enableKerberos": {
          "type": "boolean",
          "description": "Optional. Flag to indicate whether to Kerberize the cluster (default: false). Set this field to true to enable Kerberos on a cluster."
        }
      },
      "description": "Specifies Kerberos related configuration.",
      "type": "object"
    },
    "LifecycleConfig": {
      "type": "object",
      "properties": {
        "idleDeleteTtl": {
          "description": "Optional. The duration to keep the cluster alive while idling (when no jobs are running). Passing this threshold will cause the cluster to be deleted. Minimum value is 5 minutes; maximum value is 14 days (see JSON representation of Duration (https://developers.google.com/protocol-buffers/docs/proto3#json)).",
          "type": "string",
          "format": "google-duration"
        },
        "idleStopTtl": {
          "format": "google-duration",
          "description": "Optional. The duration to keep the cluster started while idling (when no jobs are running). Passing this threshold will cause the cluster to be stopped. Minimum value is 5 minutes; maximum value is 14 days (see JSON representation of Duration (https://developers.google.com/protocol-buffers/docs/proto3#json)).",
          "type": "string"
        },
        "autoStopTtl": {
          "description": "Optional. The lifetime duration of the cluster. The cluster will be auto-stopped at the end of this period, calculated from the time of submission of the create or update cluster request. Minimum value is 10 minutes; maximum value is 14 days (see JSON representation of Duration (https://developers.google.com/protocol-buffers/docs/proto3#json)).",
          "format": "google-duration",
          "type": "string"
        },
        "autoDeleteTime": {
          "description": "Optional. The time when cluster will be auto-deleted (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).",
          "format": "google-datetime",
          "type": "string"
        },
        "autoDeleteTtl": {
          "format": "google-duration",
          "type": "string",
          "description": "Optional. The lifetime duration of cluster. The cluster will be auto-deleted at the end of this period. Minimum value is 10 minutes; maximum value is 14 days (see JSON representation of Duration (https://developers.google.com/protocol-buffers/docs/proto3#json))."
        },
        "idleStartTime": {
          "readOnly": true,
          "format": "google-datetime",
          "description": "Output only. The time when cluster became idle (most recent job finished) and became eligible for deletion due to idleness (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).",
          "type": "string"
        },
        "autoStopTime": {
          "format": "google-datetime",
          "description": "Optional. The time when cluster will be auto-stopped (see JSON representation of Timestamp (https://developers.google.com/protocol-buffers/docs/proto3#json)).",
          "type": "string"
        }
      },
      "description": "Specifies the cluster auto-delete schedule configuration."
    },
    "LoggingConfig": {
      "properties": {
        "driverLogLevels": {
          "description": "The per-package log levels for the driver. This can include \"root\" package name to configure rootLogger. Examples: - 'com.google = FATAL' - 'root = INFO' - 'org.apache = DEBUG'",
          "additionalProperties": {
            "type": "string",
            "enum": [
              "LEVEL_UNSPECIFIED",
              "ALL",
              "TRACE",
              "DEBUG",
              "INFO",
              "WARN",
              "ERROR",
              "FATAL",
              "OFF"
            ]
          },
          "type": "object"
        }
      },
      "description": "The runtime logging config of the job.",
      "type": "object"
    },
    "ManagedCluster": {
      "properties": {
        "labels": {
          "description": "Optional. The labels to associate with this cluster.Label keys must be between 1 and 63 characters long, and must conform to the following PCRE regular expression: \\p{Ll}\\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following PCRE regular expression: \\p{Ll}\\p{Lo}\\p{N}_-{0,63}No more than 32 labels can be associated with a given cluster.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "clusterName": {
          "type": "string",
          "description": "Required. The cluster name prefix. A unique cluster name will be formed by appending a random suffix.The name must contain only lower-case letters (a-z), numbers (0-9), and hyphens (-). Must begin with a letter. Cannot begin or end with hyphen. Must consist of between 2 and 35 characters."
        },
        "config": {
          "$ref": "#/$defs/ClusterConfig",
          "description": "Required. The cluster configuration."
        }
      },
      "type": "object",
      "description": "Cluster that is managed by the workflow."
    },
    "ManagedGroupConfig": {
      "description": "Specifies the resources used to actively manage an instance group.",
      "type": "object",
      "properties": {
        "instanceTemplateName": {
          "type": "string",
          "readOnly": true,
          "description": "Output only. The name of the Instance Template used for the Managed Instance Group."
        },
        "instanceGroupManagerName": {
          "readOnly": true,
          "type": "string",
          "description": "Output only. The name of the Instance Group Manager for this group."
        },
        "instanceGroupManagerUri": {
          "description": "Output only. The partial URI to the instance group manager for this group. E.g. projects/my-project/regions/us-central1/instanceGroupManagers/my-igm.",
          "type": "string",
          "readOnly": true
        }
      }
    },
    "MetastoreConfig": {
      "type": "object",
      "properties": {
        "dataprocMetastoreService": {
          "type": "string",
          "description": "Required. Resource name of an existing Metastore service.Example: projects/[project_id]/locations/[dataproc_region]/services/[service-name]"
        }
      },
      "description": "Specifies a Metastore configuration."
    },
    "Metric": {
      "type": "object",
      "properties": {
        "metricOverrides": {
          "type": "array",
          "description": "Optional. Specify one or more Custom metrics (https://cloud.google.com/dataproc/docs/guides/dataproc-metrics#custom_metrics) to collect for the metric course (for the SPARK metric source (any Spark metric (https://spark.apache.org/docs/latest/monitoring.html#metrics) can be specified).Provide metrics in the following format:METRIC_SOURCE:INSTANCE :GROUP:METRIC Use camelcase as appropriate.Examples: yarn:ResourceManager:QueueMetrics:AppsCompleted spark:driver:DAGScheduler:job.allJobs sparkHistoryServer:JVM:Memory:NonHeapMemoryUsage.committed hiveserver2:JVM:Memory:NonHeapMemoryUsage.used Notes: Only the specified overridden metrics are collected for the metric source. For example, if one or more spark:executive metrics are listed as metric overrides, other SPARK metrics are not collected. The collection of the metrics for other enabled custom metric sources is unaffected. For example, if both SPARK and YARN metric sources are enabled, and overrides are provided for Spark metrics only, all YARN metrics are collected.",
          "items": {
            "type": "string"
          }
        },
        "metricSource": {
          "type": "string",
          "enum": [
            "METRIC_SOURCE_UNSPECIFIED",
            "MONITORING_AGENT_DEFAULTS",
            "HDFS",
            "SPARK",
            "YARN",
            "SPARK_HISTORY_SERVER",
            "HIVESERVER2",
            "HIVEMETASTORE",
            "FLINK"
          ],
          "description": "Required. A standard set of metrics is collected unless metricOverrides are specified for the metric source (see Custom metrics (https://cloud.google.com/dataproc/docs/guides/dataproc-metrics#custom_metrics) for more information)."
        }
      },
      "description": "A custom metric."
    },
    "MultiZoneConfig": {
      "type": "object",
      "properties": {
        "targetShape": {
          "description": "Optional. The distribution shape of the nodes in the multi-zonal cluster.",
          "type": "string",
          "enum": [
            "TARGET_SHAPE_UNSPECIFIED",
            "ANY"
          ]
        }
      },
      "description": "Configuration for multi-zonal clusters that can create instances across multiple Zones within the Region."
    },
    "NamespacedGkeDeploymentTarget": {
      "type": "object",
      "properties": {
        "targetGkeCluster": {
          "description": "Optional. The target GKE cluster to deploy to. Format: 'projects/{project}/locations/{location}/clusters/{cluster_id}'",
          "type": "string"
        },
        "clusterNamespace": {
          "description": "Optional. A namespace within the GKE cluster to deploy into.",
          "type": "string"
        }
      },
      "description": "Deprecated. Used only for the deprecated beta. A full, namespace-isolated deployment target for an existing GKE cluster.",
      "deprecated": true
    },
    "NodeGroup": {
      "properties": {
        "name": {
          "type": "string",
          "description": "The Node group resource name (https://aip.dev/122)."
        },
        "roles": {
          "items": {
            "type": "string",
            "enum": [
              "ROLE_UNSPECIFIED",
              "DRIVER"
            ]
          },
          "description": "Required. Node group roles.",
          "type": "array"
        },
        "labels": {
          "description": "Optional. Node group labels. Label keys must consist of from 1 to 63 characters and conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values can be empty. If specified, they must consist of from 1 to 63 characters and conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). The node group must have no more than 32 labels.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "nodeGroupConfig": {
          "$ref": "#/$defs/InstanceGroupConfig",
          "description": "Optional. The node group instance group configuration."
        }
      },
      "description": "Node Group. The NodeGroup resource is not related to the NodeGroupAffinity resource.",
      "type": "object"
    },
    "NodeGroupAffinity": {
      "properties": {
        "nodeGroupUri": {
          "type": "string",
          "description": "Required. The URI of a sole-tenant node group resource (https://cloud.google.com/compute/docs/reference/rest/v1/nodeGroups) that the cluster will be created on.A full URL, partial URI, or node group name are valid. Examples: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]/nodeGroups/node-group-1 projects/[project_id]/zones/[zone]/nodeGroups/node-group-1 node-group-1"
        }
      },
      "type": "object",
      "description": "Node Group Affinity for clusters using sole-tenant node groups. The NodeGroupAffinity resource is not related to the NodeGroup resource."
    },
    "NodeInitializationAction": {
      "properties": {
        "executionTimeout": {
          "description": "Optional. Amount of time executable has to complete. Default is 10 minutes (see JSON representation of Duration (https://developers.google.com/protocol-buffers/docs/proto3#json)).Cluster creation fails with an explanatory error message (the name of the executable that caused the error and the exceeded timeout period) if the executable is not completed at end of the timeout period.",
          "type": "string",
          "format": "google-duration"
        },
        "executableFile": {
          "type": "string",
          "description": "Required. Cloud Storage URI of executable file."
        }
      },
      "type": "object",
      "description": "Specifies an executable to run on a fully configured node and a timeout period for executable completion."
    },
    "OrderedJob": {
      "properties": {
        "pigJob": {
          "$ref": "#/$defs/PigJob",
          "description": "Optional. Job is a Pig job."
        },
        "trinoJob": {
          "$ref": "#/$defs/TrinoJob",
          "description": "Optional. Job is a Trino job."
        },
        "labels": {
          "type": "object",
          "description": "Optional. The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \\p{Ll}\\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \\p{Ll}\\p{Lo}\\p{N}_-{0,63}No more than 32 labels can be associated with a given job.",
          "additionalProperties": {
            "type": "string"
          }
        },
        "sparkSqlJob": {
          "$ref": "#/$defs/SparkSqlJob",
          "description": "Optional. Job is a SparkSql job."
        },
        "prerequisiteStepIds": {
          "items": {
            "type": "string"
          },
          "description": "Optional. The optional list of prerequisite job step_ids. If not specified, the job will start at the beginning of workflow.",
          "type": "array"
        },
        "hiveJob": {
          "$ref": "#/$defs/HiveJob",
          "description": "Optional. Job is a Hive job."
        },
        "prestoJob": {
          "$ref": "#/$defs/PrestoJob",
          "description": "Optional. Job is a Presto job."
        },
        "hadoopJob": {
          "$ref": "#/$defs/HadoopJob",
          "description": "Optional. Job is a Hadoop job."
        },
        "stepId": {
          "description": "Required. The step id. The id must be unique among all jobs within the template.The step id is used as prefix for job id, as job goog-dataproc-workflow-step-id label, and in prerequisiteStepIds field from other steps.The id must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), and hyphens (-). Cannot begin or end with underscore or hyphen. Must consist of between 3 and 50 characters.",
          "type": "string"
        },
        "flinkJob": {
          "$ref": "#/$defs/FlinkJob",
          "description": "Optional. Job is a Flink job."
        },
        "scheduling": {
          "$ref": "#/$defs/JobScheduling",
          "description": "Optional. Job scheduling configuration."
        },
        "sparkJob": {
          "$ref": "#/$defs/SparkJob",
          "description": "Optional. Job is a Spark job."
        },
        "sparkRJob": {
          "$ref": "#/$defs/SparkRJob",
          "description": "Optional. Job is a SparkR job."
        },
        "pysparkJob": {
          "$ref": "#/$defs/PySparkJob",
          "description": "Optional. Job is a PySpark job."
        }
      },
      "type": "object",
      "description": "A job executed by the workflow."
    },
    "ParameterValidation": {
      "type": "object",
      "description": "Configuration for parameter validation.",
      "properties": {
        "values": {
          "$ref": "#/$defs/ValueValidation",
          "description": "Validation based on a list of allowed values."
        },
        "regex": {
          "$ref": "#/$defs/RegexValidation",
          "description": "Validation based on regular expressions."
        }
      }
    },
    "PigJob": {
      "type": "object",
      "description": "A Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN.",
      "properties": {
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "scriptVariables": {
          "type": "object",
          "description": "Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).",
          "additionalProperties": {
            "type": "string"
          }
        },
        "queryList": {
          "$ref": "#/$defs/QueryList",
          "description": "A list of queries."
        },
        "queryFileUri": {
          "description": "The HCFS URI of the script that contains the Pig queries.",
          "type": "string"
        },
        "properties": {
          "description": "Optional. A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/pig/conf/pig.properties, and classes in user code.",
          "type": "object",
          "additionalProperties": {
            "type": "string"
          }
        },
        "continueOnFailure": {
          "description": "Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.",
          "type": "boolean"
        },
        "jarFileUris": {
          "items": {
            "type": "string"
          },
          "type": "array",
          "description": "Optional. HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs."
        }
      }
    },
    "PrestoJob": {
      "properties": {
        "properties": {
          "additionalProperties": {
            "type": "string"
          },
          "type": "object",
          "description": "Optional. A mapping of property names to values. Used to set Presto session properties (https://prestodb.io/docs/current/sql/set-session.html) Equivalent to using the --session flag in the Presto CLI"
        },
        "queryList": {
          "$ref": "#/$defs/QueryList",
          "description": "A list of queries."
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "continueOnFailure": {
          "description": "Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries.",
          "type": "boolean"
        },
        "clientTags": {
          "type": "array",
          "description": "Optional. Presto client tags to attach to this query",
          "items": {
            "type": "string"
          }
        },
        "queryFileUri": {
          "type": "string",
          "description": "The HCFS URI of the script that contains SQL queries."
        },
        "outputFormat": {
          "description": "Optional. The format in which query output will be displayed. See the Presto documentation for supported output formats",
          "type": "string"
        }
      },
      "description": "A Dataproc job for running Presto (https://prestosql.io/) queries. IMPORTANT: The Dataproc Presto Optional Component (https://cloud.google.com/dataproc/docs/concepts/components/presto) must be enabled when the cluster is created to submit a Presto job to the cluster.",
      "type": "object"
    },
    "ProvisioningModelMix": {
      "properties": {
        "standardCapacityPercentAboveBase": {
          "description": "Optional. The percentage of target capacity that should use Standard VM. The remaining percentage will use Spot VMs. The percentage applies only to the capacity above standard_capacity_base. eg. If 15 instances are requested and standard_capacity_base is 5 and standard_capacity_percent_above_base is 30, the service will create 5 standard VMs and then start mixing spot and standard VMs for remaining 10 instances. The mix will be 30% standard and 70% spot.",
          "type": "integer",
          "format": "int32"
        },
        "standardCapacityBase": {
          "format": "int32",
          "description": "Optional. The base capacity that will always use Standard VMs to avoid risk of more preemption than the minimum capacity you need. The service will create only standard VMs until it reaches standard_capacity_base, then it will start using standard_capacity_percent_above_base to mix Spot with Standard VMs. eg. If 15 instances are requested and standard_capacity_base is 5, the service will create 5 standard VMs and thenstart mixing spot and standard VMs for remaining 10 instances.",
          "type": "integer"
        }
      },
      "description": "Defines how to create VMs with a mixture of provisioning models.",
      "type": "object"
    },
    "PySparkJob": {
      "properties": {
        "properties": {
          "type": "object",
          "description": "Optional. A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
          "additionalProperties": {
            "type": "string"
          }
        },
        "mainPythonFileUri": {
          "description": "Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.",
          "type": "string"
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "args": {
          "items": {
            "type": "string"
          },
          "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
          "type": "array"
        },
        "fileUris": {
          "items": {
            "type": "string"
          },
          "type": "array",
          "description": "Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks."
        },
        "pythonFileUris": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip."
        },
        "jarFileUris": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks."
        },
        "archiveUris": {
          "items": {
            "type": "string"
          },
          "description": "Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.Note: Spark applications must be deployed in cluster mode (https://spark.apache.org/docs/latest/cluster-overview.html) for correct environment propagation.",
          "type": "array"
        }
      },
      "description": "A Dataproc job for running Apache PySpark (https://spark.apache.org/docs/latest/api/python/index.html#pyspark-overview) applications on YARN.",
      "type": "object"
    },
    "QueryList": {
      "description": "A list of queries to run on a cluster.",
      "type": "object",
      "properties": {
        "queries": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Required. The queries to execute. You do not need to end a query expression with a semicolon. Multiple queries can be specified in one string by separating each with a semicolon. Here is an example of a Dataproc API snippet that uses a QueryList to specify a HiveJob: \"hiveJob\": { \"queryList\": { \"queries\": [ \"query1\", \"query2\", \"query3;query4\", ] } } "
        }
      }
    },
    "RegexValidation": {
      "properties": {
        "regexes": {
          "items": {
            "type": "string"
          },
          "description": "Required. RE2 regular expressions used to validate the parameter's value. The value must match the regex in its entirety (substring matches are not sufficient).",
          "type": "array"
        }
      },
      "description": "Validation based on regular expressions.",
      "type": "object"
    },
    "ReservationAffinity": {
      "type": "object",
      "properties": {
        "values": {
          "description": "Optional. Corresponds to the label values of reservation resource.",
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "key": {
          "description": "Optional. Corresponds to the label key of reservation resource.",
          "type": "string"
        },
        "consumeReservationType": {
          "description": "Optional. Type of reservation to consume",
          "type": "string",
          "enum": [
            "TYPE_UNSPECIFIED",
            "NO_RESERVATION",
            "ANY_RESERVATION",
            "SPECIFIC_RESERVATION"
          ]
        }
      },
      "description": "Reservation Affinity for consuming Zonal reservation."
    },
    "SchedulingConfig": {
      "description": "Config for scheduling the request to create Compute Engine resources for the cluster, when available.",
      "properties": {
        "requestedRunDuration": {
          "type": "string",
          "format": "google-duration",
          "description": "Optional. Required lifetime of the resources, once provisioned. Min 10 mins, Max/Default 7 days . Note that the cluster can still be deleted before reaching this time. This time is a maximum amount of time before the cluster is forcibly deleted. Lower times are more likely to start running sooner."
        },
        "schedulingTimeout": {
          "description": "Optional. How long to wait for worker resources to be allocated before failing the cluster creation request. Max/Default value: 13 days",
          "format": "google-duration",
          "type": "string"
        }
      },
      "type": "object"
    },
    "SecurityConfig": {
      "properties": {
        "identityConfig": {
          "$ref": "#/$defs/IdentityConfig",
          "description": "Optional. Identity related configuration, including service account based secure multi-tenancy user mappings."
        },
        "kerberosConfig": {
          "$ref": "#/$defs/KerberosConfig",
          "description": "Optional. Kerberos related configuration."
        }
      },
      "type": "object",
      "description": "Security related configuration, including encryption, Kerberos, etc."
    },
    "ShieldedInstanceConfig": {
      "description": "Shielded Instance Config for clusters using Compute Engine Shielded VMs (https://cloud.google.com/security/shielded-cloud/shielded-vm).",
      "type": "object",
      "properties": {
        "enableSecureBoot": {
          "description": "Optional. Defines whether instances have Secure Boot enabled.",
          "type": "boolean"
        },
        "enableVtpm": {
          "description": "Optional. Defines whether instances have the vTPM enabled.",
          "type": "boolean"
        },
        "enableIntegrityMonitoring": {
          "description": "Optional. Defines whether instances have integrity monitoring enabled.",
          "type": "boolean"
        }
      }
    },
    "SoftwareConfig": {
      "description": "Specifies the selection and config of software inside the cluster.",
      "type": "object",
      "properties": {
        "optionalComponents": {
          "description": "Optional. The set of components to activate on the cluster.",
          "type": "array",
          "items": {
            "type": "string",
            "enum": [
              "COMPONENT_UNSPECIFIED",
              "ALLOYDB_CONNECTOR",
              "ANACONDA",
              "DELTA",
              "DOCKER",
              "DRUID",
              "FLINK",
              "HBASE",
              "HIVE_WEBHCAT",
              "HUDI",
              "ICEBERG",
              "JUPYTER",
              "PIG",
              "PRESTO",
              "TRINO",
              "RANGER",
              "SOLR",
              "ZEPPELIN",
              "ZOOKEEPER",
              "JUPYTER_KERNEL_GATEWAY"
            ]
          }
        },
        "imageVersion": {
          "description": "Optional. The version of software inside the cluster. It must be one of the supported Image Versions (https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#supported-dataproc-image-versions), such as \"1.2\" (including a subminor version, such as \"1.2.29\"), or the \"preview\" version (https://cloud.google.com/dataproc/docs/concepts/versioning/dataproc-versions#other_versions). If unspecified, it defaults to the latest Debian version.",
          "type": "string"
        },
        "properties": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "Optional. The properties to set on daemon config files.Property keys are specified in prefix:property format, for example core:hadoop.tmp.dir. The following are supported prefixes and their mappings: capacity-scheduler: capacity-scheduler.xml core: core-site.xml distcp: distcp-default.xml hdfs: hdfs-site.xml hive: hive-site.xml mapred: mapred-site.xml pig: pig.properties spark: spark-defaults.conf yarn: yarn-site.xmlFor more information, see Cluster properties (https://cloud.google.com/dataproc/docs/concepts/cluster-properties).",
          "type": "object"
        }
      }
    },
    "SparkJob": {
      "description": "A Dataproc job for running Apache Spark (https://spark.apache.org/) applications on YARN.",
      "properties": {
        "fileUris": {
          "items": {
            "type": "string"
          },
          "type": "array",
          "description": "Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks."
        },
        "jarFileUris": {
          "description": "Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.",
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "archiveUris": {
          "description": "Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.",
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "mainClass": {
          "description": "The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in SparkJob.jar_file_uris.",
          "type": "string"
        },
        "args": {
          "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "mainJarFileUri": {
          "type": "string",
          "description": "The HCFS URI of the jar file that contains the main class."
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "properties": {
          "description": "Optional. A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
          "type": "object",
          "additionalProperties": {
            "type": "string"
          }
        }
      },
      "type": "object"
    },
    "SparkRJob": {
      "type": "object",
      "properties": {
        "args": {
          "type": "array",
          "description": "Optional. The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
          "items": {
            "type": "string"
          }
        },
        "archiveUris": {
          "description": "Optional. HCFS URIs of archives to be extracted into the working directory of each executor. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "fileUris": {
          "type": "array",
          "description": "Optional. HCFS URIs of files to be placed in the working directory of each executor. Useful for naively parallel tasks.",
          "items": {
            "type": "string"
          }
        },
        "mainRFileUri": {
          "type": "string",
          "description": "Required. The HCFS URI of the main R file to use as the driver. Must be a .R file."
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "properties": {
          "description": "Optional. A mapping of property names to values, used to configure SparkR. Properties that conflict with values set by the Dataproc API might be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        }
      },
      "description": "A Dataproc job for running Apache SparkR (https://spark.apache.org/docs/latest/sparkr.html) applications on YARN."
    },
    "SparkSqlJob": {
      "type": "object",
      "properties": {
        "scriptVariables": {
          "type": "object",
          "description": "Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name=\"value\";).",
          "additionalProperties": {
            "type": "string"
          }
        },
        "jarFileUris": {
          "description": "Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.",
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "properties": {
          "description": "Optional. A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Dataproc API might be overwritten.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "queryList": {
          "$ref": "#/$defs/QueryList",
          "description": "A list of queries."
        },
        "queryFileUri": {
          "description": "The HCFS URI of the script that contains SQL queries.",
          "type": "string"
        }
      },
      "description": "A Dataproc job for running Apache Spark SQL (https://spark.apache.org/sql/) queries."
    },
    "StartupConfig": {
      "properties": {
        "requiredRegistrationFraction": {
          "format": "double",
          "type": "number",
          "description": "Optional. The config setting to enable cluster creation/ updation to be successful only after required_registration_fraction of instances are up and running. This configuration is applicable to only secondary workers for now. The cluster will fail if required_registration_fraction of instances are not available. This will include instance creation, agent registration, and service registration (if enabled)."
        }
      },
      "type": "object",
      "description": "Configuration to handle the startup of instances during cluster create and update process."
    },
    "TemplateParameter": {
      "properties": {
        "description": {
          "type": "string",
          "description": "Optional. Brief description of the parameter. Must not exceed 1024 characters."
        },
        "fields": {
          "description": "Required. Paths to all fields that the parameter replaces. A field is allowed to appear in at most one parameter's list of field paths.A field path is similar in syntax to a google.protobuf.FieldMask. For example, a field path that references the zone field of a workflow template's cluster selector would be specified as placement.clusterSelector.zone.Also, field paths can reference fields using the following syntax: Values in maps can be referenced by key: labels'key' placement.clusterSelector.clusterLabels'key' placement.managedCluster.labels'key' placement.clusterSelector.clusterLabels'key' jobs'step-id'.labels'key' Jobs in the jobs list can be referenced by step-id: jobs'step-id'.hadoopJob.mainJarFileUri jobs'step-id'.hiveJob.queryFileUri jobs'step-id'.pySparkJob.mainPythonFileUri jobs'step-id'.hadoopJob.jarFileUris0 jobs'step-id'.hadoopJob.archiveUris0 jobs'step-id'.hadoopJob.fileUris0 jobs'step-id'.pySparkJob.pythonFileUris0 Items in repeated fields can be referenced by a zero-based index: jobs'step-id'.sparkJob.args0 Other examples: jobs'step-id'.hadoopJob.properties'key' jobs'step-id'.hadoopJob.args0 jobs'step-id'.hiveJob.scriptVariables'key' jobs'step-id'.hadoopJob.mainJarFileUri placement.clusterSelector.zoneIt may not be possible to parameterize maps and repeated fields in their entirety since only individual map values and individual items in repeated fields can be referenced. For example, the following field paths are invalid: placement.clusterSelector.clusterLabels jobs'step-id'.sparkJob.args",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "name": {
          "description": "Required. Parameter name. The parameter name is used as the key, and paired with the parameter value, which are passed to the template when the template is instantiated. The name must contain only capital letters (A-Z), numbers (0-9), and underscores (_), and must not start with a number. The maximum length is 40 characters.",
          "type": "string"
        },
        "validation": {
          "$ref": "#/$defs/ParameterValidation",
          "description": "Optional. Validation rules to be applied to this parameter's value."
        }
      },
      "type": "object",
      "description": "A configurable parameter that replaces one or more fields in the template. Parameterizable fields: - Labels - File uris - Job properties - Job arguments - Script variables - Main class (in HadoopJob and SparkJob) - Zone (in ClusterSelector)"
    },
    "TrinoJob": {
      "properties": {
        "queryFileUri": {
          "type": "string",
          "description": "The HCFS URI of the script that contains SQL queries."
        },
        "continueOnFailure": {
          "type": "boolean",
          "description": "Optional. Whether to continue executing queries if a query fails. The default value is false. Setting to true can be useful when executing independent parallel queries."
        },
        "outputFormat": {
          "description": "Optional. The format in which query output will be displayed. See the Trino documentation for supported output formats",
          "type": "string"
        },
        "clientTags": {
          "items": {
            "type": "string"
          },
          "description": "Optional. Trino client tags to attach to this query",
          "type": "array"
        },
        "queryList": {
          "$ref": "#/$defs/QueryList",
          "description": "A list of queries."
        },
        "loggingConfig": {
          "$ref": "#/$defs/LoggingConfig",
          "description": "Optional. The runtime log config for job execution."
        },
        "properties": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          },
          "description": "Optional. A mapping of property names to values. Used to set Trino session properties (https://trino.io/docs/current/sql/set-session.html) Equivalent to using the --session flag in the Trino CLI"
        }
      },
      "type": "object",
      "description": "A Dataproc job for running Trino (https://trino.io/) queries. IMPORTANT: The Dataproc Trino Optional Component (https://cloud.google.com/dataproc/docs/concepts/components/trino) must be enabled when the cluster is created to submit a Trino job to the cluster."
    },
    "ValueValidation": {
      "description": "Validation based on a list of allowed values.",
      "type": "object",
      "properties": {
        "values": {
          "items": {
            "type": "string"
          },
          "description": "Required. List of allowed values for the parameter.",
          "type": "array"
        }
      }
    },
    "WorkflowTemplatePlacement": {
      "properties": {
        "clusterSelector": {
          "$ref": "#/$defs/ClusterSelector",
          "description": "Optional. A selector that chooses target cluster for jobs based on metadata.The selector is evaluated at the time each job is submitted."
        },
        "managedCluster": {
          "$ref": "#/$defs/ManagedCluster",
          "description": "A cluster that is managed by the workflow."
        }
      },
      "description": "Specifies workflow execution target.Either managed_cluster or cluster_selector is required.",
      "type": "object"
    }
  }
}