blob: b25ca2da03c194ed71e0b0eb771a120e28f8098f [file] [log] [blame]
{
"resources": {
"operations": {
"methods": {
"get": {
"response": {
"$ref": "Operation"
},
"parameterOrder": [
"name"
],
"httpMethod": "GET",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"name": {
"description": "The operation resource name.",
"required": true,
"type": "string",
"pattern": "^operations/.+$",
"location": "path"
}
},
"flatPath": "v1alpha1/operations/{operationsId}",
"path": "v1alpha1/{+name}",
"id": "dataproc.operations.get",
"description": "Gets the latest state of a long-running operation. Clients may use this method to poll the operation result at intervals as recommended by the API service."
},
"list": {
"description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.",
"httpMethod": "GET",
"parameterOrder": [
"name"
],
"response": {
"$ref": "ListOperationsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"pageSize": {
"description": "The standard List page size.",
"format": "int32",
"type": "integer",
"location": "query"
},
"filter": {
"description": "Required A JSON object that contains filters for the list operation, in the format {\"key1\":\"value1\",\"key2\":\"value2\", ..., }. Possible keys include project_id, cluster_name, and operation_state_matcher.If project_id is set, requests the list of operations that belong to the specified Google Cloud Platform project ID. This key is required.If cluster_name is set, requests the list of operations that were submitted to the specified cluster name. This key is optional.If operation_state_matcher is set, requests the list of operations that match one of the following status options: ALL, ACTIVE, or NON_ACTIVE.",
"type": "string",
"location": "query"
},
"name": {
"description": "The operation collection name.",
"required": true,
"type": "string",
"pattern": "^operations$",
"location": "path"
},
"pageToken": {
"description": "The standard List page token.",
"type": "string",
"location": "query"
}
},
"flatPath": "v1alpha1/operations",
"id": "dataproc.operations.list",
"path": "v1alpha1/{+name}"
},
"cancel": {
"request": {
"$ref": "CancelOperationRequest"
},
"description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED. Clients may use Operations.GetOperation or other methods to check whether the cancellation succeeded or the operation completed despite cancellation.",
"response": {
"$ref": "Empty"
},
"parameterOrder": [
"name"
],
"httpMethod": "POST",
"parameters": {
"name": {
"description": "The name of the operation resource to be cancelled.",
"required": true,
"type": "string",
"pattern": "^operations/.+$",
"location": "path"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1alpha1/operations/{operationsId}:cancel",
"path": "v1alpha1/{+name}:cancel",
"id": "dataproc.operations.cancel"
},
"delete": {
"flatPath": "v1alpha1/operations/{operationsId}",
"id": "dataproc.operations.delete",
"path": "v1alpha1/{+name}",
"description": "Deletes a long-running operation. It indicates the client is no longer interested in the operation result. It does not cancel the operation.",
"httpMethod": "DELETE",
"response": {
"$ref": "Empty"
},
"parameterOrder": [
"name"
],
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"name": {
"description": "The name of the operation resource to be deleted.",
"required": true,
"type": "string",
"pattern": "^operations/.+$",
"location": "path"
}
}
}
}
},
"projects": {
"resources": {
"regions": {
"resources": {
"clusters": {
"methods": {
"delete": {
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"path": "v1alpha1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"id": "dataproc.projects.regions.clusters.delete",
"description": "Request to delete a cluster in a project.",
"response": {
"$ref": "Operation"
},
"parameterOrder": [
"projectId",
"region",
"clusterName"
],
"httpMethod": "DELETE",
"parameters": {
"region": {
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string",
"location": "path"
},
"clusterName": {
"location": "path",
"description": "Required The cluster name.",
"required": true,
"type": "string"
},
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.",
"required": true,
"type": "string",
"location": "path"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"patch": {
"description": "Request to update a cluster in a project.",
"request": {
"$ref": "Cluster"
},
"httpMethod": "PATCH",
"parameterOrder": [
"projectId",
"region",
"clusterName"
],
"response": {
"$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"region": {
"location": "path",
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string"
},
"updateMask": {
"location": "query",
"description": "Required Specifies the path, relative to \u003ccode\u003eCluster\u003c/code\u003e, of the field to update. For example, to change the number of workers in a cluster to 5, the \u003ccode\u003eupdate_mask\u003c/code\u003e parameter would be specified as \u003ccode\u003e\"configuration.worker_configuration.num_instances,\"\u003c/code\u003e and the PATCH request body would specify the new value, as follows:\n{\n \"configuration\":{\n \"workerConfiguration\":{\n \"numInstances\":\"5\"\n }\n }\n}\n\u003cstrong\u003eNote:\u003c/strong\u003e Currently, \u003ccode\u003econfiguration.worker_configuration.num_instances\u003c/code\u003e is the only field that can be updated.",
"format": "google-fieldmask",
"type": "string"
},
"clusterName": {
"description": "Required The cluster name.",
"required": true,
"type": "string",
"location": "path"
},
"projectId": {
"location": "path",
"description": "Required The ID of the Google Cloud Platform project the cluster belongs to.",
"required": true,
"type": "string"
}
},
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"id": "dataproc.projects.regions.clusters.patch",
"path": "v1alpha1/projects/{projectId}/regions/{region}/clusters/{clusterName}"
},
"get": {
"description": "Request to get the resource representation for a cluster in a project.",
"response": {
"$ref": "Cluster"
},
"parameterOrder": [
"projectId",
"region",
"clusterName"
],
"httpMethod": "GET",
"parameters": {
"region": {
"location": "path",
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string"
},
"clusterName": {
"location": "path",
"description": "Required The cluster name.",
"required": true,
"type": "string"
},
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.",
"required": true,
"type": "string",
"location": "path"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"path": "v1alpha1/projects/{projectId}/regions/{region}/clusters/{clusterName}",
"id": "dataproc.projects.regions.clusters.get"
},
"list": {
"description": "Request a list of all regions/{region}/clusters in a project.",
"response": {
"$ref": "ListClustersResponse"
},
"parameterOrder": [
"projectId",
"region"
],
"httpMethod": "GET",
"parameters": {
"pageSize": {
"location": "query",
"description": "The standard List page size.",
"format": "int32",
"type": "integer"
},
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.",
"required": true,
"type": "string",
"location": "path"
},
"region": {
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string",
"location": "path"
},
"filter": {
"location": "query",
"description": "Optional A filter constraining which clusters to list. Valid filters contain label terms such as: labels.key1 = val1 AND (-labels.k2 = val2 OR labels.k3 = val3)",
"type": "string"
},
"pageToken": {
"description": "The standard List page token.",
"type": "string",
"location": "query"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/clusters",
"path": "v1alpha1/projects/{projectId}/regions/{region}/clusters",
"id": "dataproc.projects.regions.clusters.list"
},
"create": {
"response": {
"$ref": "Operation"
},
"parameterOrder": [
"projectId",
"region"
],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.",
"required": true,
"type": "string",
"location": "path"
},
"region": {
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string",
"location": "path"
}
},
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/clusters",
"path": "v1alpha1/projects/{projectId}/regions/{region}/clusters",
"id": "dataproc.projects.regions.clusters.create",
"description": "Request to create a cluster in a project.",
"request": {
"$ref": "Cluster"
}
}
}
},
"jobs": {
"methods": {
"patch": {
"description": "Updates a job in a project.",
"request": {
"$ref": "Job"
},
"httpMethod": "PATCH",
"parameterOrder": [
"projectId",
"region",
"jobId"
],
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"region": {
"location": "path",
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string"
},
"updateMask": {
"description": "Required Specifies the path, relative to \u003ccode\u003eJob\u003c/code\u003e, of the field to update. For example, to update the labels of a Job the \u003ccode\u003eupdate_mask\u003c/code\u003e parameter would be specified as \u003ccode\u003elabels\u003c/code\u003e, and the PATCH request body would specify the new value. \u003cstrong\u003eNote:\u003c/strong\u003e Currently, \u003ccode\u003elabels\u003c/code\u003e is the only field that can be updated.",
"format": "google-fieldmask",
"type": "string",
"location": "query"
},
"projectId": {
"location": "path",
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"required": true,
"type": "string"
},
"jobId": {
"description": "Required The job ID.",
"required": true,
"type": "string",
"location": "path"
}
},
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}",
"id": "dataproc.projects.regions.jobs.patch",
"path": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}"
},
"get": {
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}",
"path": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}",
"id": "dataproc.projects.regions.jobs.get",
"description": "Gets the resource representation for a job in a project.",
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId",
"region",
"jobId"
],
"httpMethod": "GET",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"projectId": {
"location": "path",
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"required": true,
"type": "string"
},
"jobId": {
"description": "Required The job ID.",
"required": true,
"type": "string",
"location": "path"
},
"region": {
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string",
"location": "path"
}
}
},
"submit": {
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId",
"region"
],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"region": {
"location": "path",
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string"
},
"projectId": {
"location": "path",
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"required": true,
"type": "string"
}
},
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/jobs:submit",
"path": "v1alpha1/projects/{projectId}/regions/{region}/jobs:submit",
"id": "dataproc.projects.regions.jobs.submit",
"description": "Submits a job to a cluster.",
"request": {
"$ref": "SubmitJobRequest"
}
},
"delete": {
"description": "Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.",
"httpMethod": "DELETE",
"parameterOrder": [
"projectId",
"region",
"jobId"
],
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"required": true,
"type": "string",
"location": "path"
},
"jobId": {
"description": "Required The job ID.",
"required": true,
"type": "string",
"location": "path"
},
"region": {
"location": "path",
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string"
}
},
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}",
"id": "dataproc.projects.regions.jobs.delete",
"path": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}"
},
"list": {
"request": {
"$ref": "ListJobsRequest"
},
"description": "Lists regions/{region}/jobs in a project.",
"response": {
"$ref": "ListJobsResponse"
},
"parameterOrder": [
"projectId",
"region"
],
"httpMethod": "POST",
"parameters": {
"region": {
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string",
"location": "path"
},
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"required": true,
"type": "string",
"location": "path"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/jobs:list",
"path": "v1alpha1/projects/{projectId}/regions/{region}/jobs:list",
"id": "dataproc.projects.regions.jobs.list"
},
"cancel": {
"request": {
"$ref": "CancelJobRequest"
},
"description": "Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs:list or regions/{region}/jobs:get.",
"response": {
"$ref": "Job"
},
"parameterOrder": [
"projectId",
"region",
"jobId"
],
"httpMethod": "POST",
"parameters": {
"region": {
"description": "Required The Dataproc region in which to handle the request.",
"required": true,
"type": "string",
"location": "path"
},
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"required": true,
"type": "string",
"location": "path"
},
"jobId": {
"description": "Required The job ID.",
"required": true,
"type": "string",
"location": "path"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}:cancel",
"path": "v1alpha1/projects/{projectId}/regions/{region}/jobs/{jobId}:cancel",
"id": "dataproc.projects.regions.jobs.cancel"
}
}
}
}
}
}
}
},
"parameters": {
"pp": {
"location": "query",
"description": "Pretty-print response.",
"type": "boolean",
"default": "true"
},
"bearer_token": {
"description": "OAuth bearer token.",
"type": "string",
"location": "query"
},
"oauth_token": {
"description": "OAuth 2.0 token for the current user.",
"type": "string",
"location": "query"
},
"upload_protocol": {
"location": "query",
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"type": "string"
},
"prettyPrint": {
"description": "Returns response with indentations and line breaks.",
"type": "boolean",
"default": "true",
"location": "query"
},
"fields": {
"description": "Selector specifying which fields to include in a partial response.",
"type": "string",
"location": "query"
},
"uploadType": {
"description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"type": "string",
"location": "query"
},
"callback": {
"description": "JSONP",
"type": "string",
"location": "query"
},
"$.xgafv": {
"enumDescriptions": [
"v1 error format",
"v2 error format"
],
"location": "query",
"enum": [
"1",
"2"
],
"description": "V1 error format.",
"type": "string"
},
"alt": {
"enumDescriptions": [
"Responses with Content-Type of application/json",
"Media download with context-dependent Content-Type",
"Responses with Content-Type of application/x-protobuf"
],
"location": "query",
"description": "Data format for response.",
"default": "json",
"enum": [
"json",
"media",
"proto"
],
"type": "string"
},
"key": {
"location": "query",
"description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
"type": "string"
},
"access_token": {
"location": "query",
"description": "OAuth access token.",
"type": "string"
},
"quotaUser": {
"description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
"type": "string",
"location": "query"
}
},
"schemas": {
"InstanceGroupConfiguration": {
"description": "The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group.",
"type": "object",
"properties": {
"numInstances": {
"description": "The number of VM instances in the instance group. For master instance groups, must be set to 1.",
"format": "int32",
"type": "integer"
},
"diskConfiguration": {
"$ref": "DiskConfiguration",
"description": "Disk option configuration settings."
},
"machineTypeUri": {
"description": "The Google Compute Engine machine type used for cluster instances. Example: \"compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2\".",
"type": "string"
},
"imageUri": {
"description": "Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version. Example: \"compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904\".",
"type": "string"
},
"isPreemptible": {
"description": "Specifies that this instance group contains Preemptible Instances.",
"type": "boolean"
},
"instanceNames": {
"description": "The list of instance names. Dataproc derives the names from cluster_name, num_instances, and the instance group if not set by user (recommended practice is to let Dataproc derive the name).",
"type": "array",
"items": {
"type": "string"
}
},
"managedGroupConfiguration": {
"$ref": "ManagedGroupConfiguration",
"description": "Output-only The configuration for Google Compute Engine Instance Group Manager that manages this group. This is only used for preemptible instance groups."
}
},
"id": "InstanceGroupConfiguration"
},
"GceClusterConfiguration": {
"description": "Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.",
"type": "object",
"properties": {
"internalIpOnly": {
"description": "If true, all instances in the cluser will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.",
"type": "boolean"
},
"metadata": {
"additionalProperties": {
"type": "string"
},
"description": "The Google Compute Engine metadata entries to add to all instances.",
"type": "object"
},
"serviceAccountScopes": {
"description": "The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example \"auth.googleapis.com/compute\" and \"auth.googleapis.com/devstorage.full_control\".",
"type": "array",
"items": {
"type": "string"
}
},
"tags": {
"description": "The Google Compute Engine tags to add to all instances.",
"type": "array",
"items": {
"type": "string"
}
},
"serviceAccount": {
"description": "Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles:\nroles/logging.logWriter\nroles/storage.objectAdmin(see https://cloud.google.com/compute/docs/access/service-accounts#custom_service_accounts for more information). Example: [account_id]@[project_id].iam.gserviceaccount.com",
"type": "string"
},
"subnetworkUri": {
"description": "The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: compute.googleapis.com/projects/[project_id]/regions/us-east1/sub0.",
"type": "string"
},
"networkUri": {
"description": "The Google 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 https://cloud.google.com/compute/docs/subnetworks for more information). Example: compute.googleapis.com/projects/[project_id]/regions/global/default.",
"type": "string"
},
"zoneUri": {
"description": "Required The zone where the Google Compute Engine cluster will be located. Example: \"compute.googleapis.com/projects/project_id /zones/us-east1-a\".",
"type": "string"
}
},
"id": "GceClusterConfiguration"
},
"CancelOperationRequest": {
"description": "The request message for Operations.CancelOperation.",
"type": "object",
"properties": {},
"id": "CancelOperationRequest"
},
"DiagnoseClusterOutputLocation": {
"description": "The location where output from diagnostic command can be found.",
"type": "object",
"properties": {
"outputUri": {
"description": "Output-only The Google Cloud Storage URI of the diagnostic output. This will be a plain text file with summary of collected diagnostics.",
"type": "string"
}
},
"id": "DiagnoseClusterOutputLocation"
},
"Operation": {
"description": "An asynchronous operation in a project that runs over a given cluster. Used to track the progress of a user request that is running asynchronously. Examples include creating a cluster, updating a cluster, and deleting a cluster.",
"type": "object",
"properties": {
"error": {
"$ref": "Status",
"description": "The error result of the operation in case of failure."
},
"metadata": {
"description": "Service-specific metadata associated with the operation.",
"type": "object",
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
}
},
"done": {
"description": "Indicates if the operation is done. If true, the operation is complete and the result is available. If false, the operation is still in progress.",
"type": "boolean"
},
"response": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "The operation response. If the called method returns no data on success, the response is google.protobuf.Empty. If the called method is Get,Create or Update, the response is the resource. For all other methods, the response type is a concatenation of the method name and \"Response\". For example, if the called method is TakeSnapshot(), the response type is TakeSnapshotResponse.",
"type": "object"
},
"name": {
"description": "The name of the operation resource, in the format projects/project_id/operations/operation_id",
"type": "string"
}
},
"id": "Operation"
},
"OperationStatus": {
"description": "The status of the operation.",
"type": "object",
"properties": {
"state": {
"enumDescriptions": [
"Unused.",
"The operation has been created.",
"The operation is running.",
"The operation is done; either cancelled or completed."
],
"enum": [
"UNKNOWN",
"PENDING",
"RUNNING",
"DONE"
],
"description": "A message containing the operation state.",
"type": "string"
},
"details": {
"description": "A message containing any operation metadata details.",
"type": "string"
},
"innerState": {
"description": "A message containing the detailed operation state.",
"type": "string"
},
"stateStartTime": {
"description": "The time this state was entered.",
"format": "google-datetime",
"type": "string"
}
},
"id": "OperationStatus"
},
"JobReference": {
"description": "Encapsulates the full scoping used to reference a job.",
"type": "object",
"properties": {
"projectId": {
"description": "Required The ID of the Google Cloud Platform project that the job belongs to.",
"type": "string"
},
"jobId": {
"description": "Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 512 characters.",
"type": "string"
}
},
"id": "JobReference"
},
"SubmitJobRequest": {
"description": "A job submission request.",
"type": "object",
"properties": {
"job": {
"description": "Required The job resource.",
"$ref": "Job"
}
},
"id": "SubmitJobRequest"
},
"Status": {
"description": "The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC (https://github.com/grpc). The error model is designed to be:\nSimple to use and understand for most users\nFlexible enough to meet unexpected needsOverviewThe Status message contains three pieces of data: error code, error message, and error details. The error code should be an enum value of google.rpc.Code, but it may accept additional error codes if needed. The error message should be a developer-facing English message that helps developers understand and resolve the error. If a localized user-facing error message is needed, put the localized message in the error details or localize it in the client. The optional error details may contain arbitrary information about the error. There is a predefined set of error detail types in the package google.rpc which can be used for common error conditions.Language mappingThe Status message is the logical representation of the error model, but it is not necessarily the actual wire format. When the Status message is exposed in different client libraries and different wire protocols, it can be mapped differently. For example, it will likely be mapped to some exceptions in Java, but more likely mapped to some error codes in C.Other usesThe error model and the Status message can be used in a variety of environments, either with or without APIs, to provide a consistent developer experience across different environments.Example uses of this error model include:\nPartial errors. If a service needs to return partial errors to the client, it may embed the Status in the normal response to indicate the partial errors.\nWorkflow errors. A typical workflow has multiple steps. Each step may have a Status message for error reporting purpose.\nBatch operations. If a client uses batch request and batch response, the Status message should be used directly inside batch response, one for each error sub-response.\nAsynchronous operations. If an API call embeds asynchronous operation results in its response, the status of those operations should be represented directly using the Status message.\nLogging. If some API errors are stored in logs, the message Status could be used directly after any stripping needed for security/privacy reasons.",
"type": "object",
"properties": {
"details": {
"description": "A list of messages that carry the error details. There will be a common set of message types for APIs to use.",
"type": "array",
"items": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"type": "object"
}
},
"code": {
"description": "The status code, which should be an enum value of google.rpc.Code.",
"format": "int32",
"type": "integer"
},
"message": {
"description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.",
"type": "string"
}
},
"id": "Status"
},
"JobScheduling": {
"description": "Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release.",
"type": "object",
"properties": {
"maxFailuresPerHour": {
"description": "Optional Maximum number of times per hour a driver may be restarted as a result of driver terminating with non-zero code before job is reported failed.A job may be reported as thrashing if driver exits with non-zero code 4 times within 10 minute window.Maximum value is 10.",
"format": "int32",
"type": "integer"
}
},
"id": "JobScheduling"
},
"NodeInitializationAction": {
"description": "Specifies an executable to run on a fully configured node and a timeout period for executable completion.",
"type": "object",
"properties": {
"executableFile": {
"description": "Required Google Cloud Storage URI of executable file.",
"type": "string"
},
"executionTimeout": {
"description": "Optional Amount of time executable has to complete. Default is 10 minutes. 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.",
"format": "google-duration",
"type": "string"
}
},
"id": "NodeInitializationAction"
},
"ListJobsResponse": {
"description": "A response to a request to list jobs in a project.",
"type": "object",
"properties": {
"nextPageToken": {
"description": "Optional This token is included in the response if there are more results to fetch. To fetch additional results, provide this value as the page_token in a subsequent \u003ccode\u003eListJobsRequest\u003c/code\u003e.",
"type": "string"
},
"jobs": {
"description": "Output-only Jobs list.",
"type": "array",
"items": {
"$ref": "Job"
}
}
},
"id": "ListJobsResponse"
},
"CancelJobRequest": {
"description": "A request to cancel a job.",
"type": "object",
"properties": {},
"id": "CancelJobRequest"
},
"SparkSqlJob": {
"description": "A Cloud Dataproc job for running Spark SQL queries.",
"type": "object",
"properties": {
"scriptVariables": {
"description": "Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name=\"value\";).",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"jarFileUris": {
"description": "Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.",
"type": "array",
"items": {
"type": "string"
}
},
"loggingConfiguration": {
"description": "Optional The runtime log configuration for job execution.",
"$ref": "LoggingConfiguration"
},
"properties": {
"description": "Optional A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"queryList": {
"description": "A list of queries.",
"$ref": "QueryList"
},
"queryFileUri": {
"description": "The HCFS URI of the script that contains SQL queries.",
"type": "string"
}
},
"id": "SparkSqlJob"
},
"Cluster": {
"description": "Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances.",
"type": "object",
"properties": {
"createTime": {
"description": "Output-only The timestamp of cluster creation.",
"format": "google-datetime",
"type": "string"
},
"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 64 labels can be associated with a given cluster.",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"metrics": {
"$ref": "ClusterMetrics",
"description": "Contains cluster daemon metrics such as HDFS and YARN stats."
},
"status": {
"description": "Output-only Cluster status.",
"$ref": "ClusterStatus"
},
"statusHistory": {
"description": "Output-only Previous cluster statuses.",
"type": "array",
"items": {
"$ref": "ClusterStatus"
}
},
"clusterName": {
"description": "Required The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused.",
"type": "string"
},
"clusterUuid": {
"description": "Output-only A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster.",
"type": "string"
},
"projectId": {
"description": "Required The Google Cloud Platform project ID that the cluster belongs to.",
"type": "string"
},
"configuration": {
"$ref": "ClusterConfiguration",
"description": "Required The cluster configuration. It may differ from a user's initial configuration due to Cloud Dataproc setting of default values and updating clusters."
}
},
"id": "Cluster"
},
"ListOperationsResponse": {
"description": "The response message for Operations.ListOperations.",
"type": "object",
"properties": {
"operations": {
"description": "A list of operations that match the specified filter in the request.",
"type": "array",
"items": {
"$ref": "Operation"
}
},
"nextPageToken": {
"description": "The standard List next-page token.",
"type": "string"
}
},
"id": "ListOperationsResponse"
},
"OperationMetadata": {
"description": "Metadata describing the operation.",
"type": "object",
"properties": {
"insertTime": {
"description": "The time that the operation was requested.",
"format": "google-datetime",
"type": "string"
},
"statusHistory": {
"description": "Output-only Previous operation status.",
"type": "array",
"items": {
"$ref": "OperationStatus"
}
},
"operationType": {
"description": "Output-only The operation type.",
"type": "string"
},
"description": {
"description": "Output-only Short description of operation.",
"type": "string"
},
"status": {
"description": "Output-only Current operation status.",
"$ref": "OperationStatus"
},
"state": {
"description": "A message containing the operation state.",
"type": "string",
"enumDescriptions": [
"Unused.",
"The operation has been created.",
"The operation is currently running.",
"The operation is done, either cancelled or completed."
],
"enum": [
"UNKNOWN",
"PENDING",
"RUNNING",
"DONE"
]
},
"details": {
"description": "A message containing any operation metadata details.",
"type": "string"
},
"clusterName": {
"description": "Name of the cluster for the operation.",
"type": "string"
},
"clusterUuid": {
"description": "Cluster UUId for the operation.",
"type": "string"
},
"innerState": {
"description": "A message containing the detailed operation state.",
"type": "string"
},
"endTime": {
"description": "The time that the operation completed.",
"format": "google-datetime",
"type": "string"
},
"startTime": {
"description": "The time that the operation was started by the server.",
"format": "google-datetime",
"type": "string"
},
"warnings": {
"description": "Output-only Errors encountered during operation execution.",
"type": "array",
"items": {
"type": "string"
}
}
},
"id": "OperationMetadata"
},
"JobPlacement": {
"description": "Cloud Dataproc job configuration.",
"type": "object",
"properties": {
"clusterName": {
"description": "Required The name of the cluster where the job will be submitted.",
"type": "string"
},
"clusterUuid": {
"description": "Output-only A cluster UUID generated by the Dataproc service when the job is submitted.",
"type": "string"
}
},
"id": "JobPlacement"
},
"PigJob": {
"description": "A Cloud Dataproc job for running Pig queries on YARN.",
"type": "object",
"properties": {
"jarFileUris": {
"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.",
"type": "array",
"items": {
"type": "string"
}
},
"scriptVariables": {
"description": "Optional Mapping of query variable names to values (equivalent to the Pig command: \"name=value\").",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"loggingConfiguration": {
"description": "Optional The runtime log configuration for job execution.",
"$ref": "LoggingConfiguration"
},
"properties": {
"additionalProperties": {
"type": "string"
},
"description": "Optional A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/pig/conf/pig.properties, and classes in user code.",
"type": "object"
},
"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"
},
"queryFileUri": {
"description": "The HCFS URI of the script that contains the Pig queries.",
"type": "string"
},
"queryList": {
"$ref": "QueryList",
"description": "A list of queries."
}
},
"id": "PigJob"
},
"ClusterStatus": {
"description": "The status of a cluster and its instances.",
"type": "object",
"properties": {
"detail": {
"description": "Optional details of cluster's state.",
"type": "string"
},
"state": {
"enumDescriptions": [
"The cluster state is unknown.",
"The cluster is being created and set up. It is not ready for use.",
"The cluster is currently running and healthy. It is ready for use.",
"The cluster encountered an error. It is not ready for use.",
"The cluster is being deleted. It cannot be used.",
"The cluster is being updated. It continues to accept and process jobs."
],
"enum": [
"UNKNOWN",
"CREATING",
"RUNNING",
"ERROR",
"DELETING",
"UPDATING"
],
"description": "The cluster's state.",
"type": "string"
},
"stateStartTime": {
"description": "Time when this state was entered.",
"format": "google-datetime",
"type": "string"
}
},
"id": "ClusterStatus"
},
"ListClustersResponse": {
"description": "The list of all clusters in a project.",
"type": "object",
"properties": {
"clusters": {
"description": "Output-only The clusters in the project.",
"type": "array",
"items": {
"$ref": "Cluster"
}
},
"nextPageToken": {
"description": "The standard List next-page token.",
"type": "string"
}
},
"id": "ListClustersResponse"
},
"ManagedGroupConfiguration": {
"description": "Specifies the resources used to actively manage an instance group.",
"type": "object",
"properties": {
"instanceGroupManagerName": {
"description": "Output-only The name of Instance Group Manager managing this group.",
"type": "string"
},
"instanceTemplateName": {
"description": "Output-only The name of Instance Template used for Managed Instance Group.",
"type": "string"
}
},
"id": "ManagedGroupConfiguration"
},
"SparkJob": {
"description": "A Cloud Dataproc job for running Spark applications on YARN.",
"type": "object",
"properties": {
"mainJarFileUri": {
"description": "The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.",
"type": "string"
},
"jarFileUris": {
"description": "Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.",
"type": "array",
"items": {
"type": "string"
}
},
"loggingConfiguration": {
"$ref": "LoggingConfiguration",
"description": "Optional The runtime log configuration for job execution."
},
"properties": {
"description": "Optional A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"args": {
"description": "Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.",
"type": "array",
"items": {
"type": "string"
}
},
"fileUris": {
"description": "Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.",
"type": "array",
"items": {
"type": "string"
}
},
"mainClass": {
"description": "The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.",
"type": "string"
},
"archiveUris": {
"description": "Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.",
"type": "array",
"items": {
"type": "string"
}
}
},
"id": "SparkJob"
},
"Job": {
"description": "A Cloud Dataproc job resource.",
"type": "object",
"properties": {
"reference": {
"$ref": "JobReference",
"description": "Optional The fully-qualified reference to the job, which can be used to obtain the equivalent REST path of the job resource. If this property is not specified when a job is created, the server generates a \u003ccode\u003ejob_id\u003c/code\u003e."
},
"interactive": {
"description": "Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.",
"type": "boolean"
},
"driverInputResourceUri": {
"description": "Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.",
"type": "string"
},
"hadoopJob": {
"description": "Job is a Hadoop job.",
"$ref": "HadoopJob"
},
"status": {
"description": "Output-only The job status. Additional application-specific status information may be contained in the \u003ccode\u003etype_job\u003c/code\u003e and \u003ccode\u003eyarn_applications\u003c/code\u003e fields.",
"$ref": "JobStatus"
},
"placement": {
"$ref": "JobPlacement",
"description": "Required Job information, including how, when, and where to run the job."
},
"driverControlFilesUri": {
"description": "Output-only If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri.",
"type": "string"
},
"submittedBy": {
"description": "Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is \u003ccode\u003eusername@hostname\u003c/code\u003e.",
"type": "string"
},
"scheduling": {
"description": "Optional Job scheduling configuration.",
"$ref": "JobScheduling"
},
"pigJob": {
"description": "Job is a Pig job.",
"$ref": "PigJob"
},
"driverOutputUri": {
"description": "Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program—for example, \u003ccode\u003egs://sysbucket123/foo-cluster/jobid-123/driver/output\u003c/code\u003e.",
"type": "string"
},
"hiveJob": {
"description": "Job is a Hive job.",
"$ref": "HiveJob"
},
"labels": {
"additionalProperties": {
"type": "string"
},
"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 64 labels can be associated with a given job.",
"type": "object"
},
"driverOutputResourceUri": {
"description": "Output-only A URI pointing to the location of the stdout of the job's driver program.",
"type": "string"
},
"sparkSqlJob": {
"description": "Job is a SparkSql job.",
"$ref": "SparkSqlJob"
},
"sparkJob": {
"$ref": "SparkJob",
"description": "Job is a Spark job."
},
"statusHistory": {
"description": "Output-only The previous job status.",
"type": "array",
"items": {
"$ref": "JobStatus"
}
},
"yarnApplications": {
"description": "Output-only The collection of Yarn applications spun up by this job.",
"type": "array",
"items": {
"$ref": "YarnApplication"
}
},
"pysparkJob": {
"$ref": "PySparkJob",
"description": "Job is a Pyspark job."
}
},
"id": "Job"
},
"DiskConfiguration": {
"description": "Specifies the configuration of disk options for a group of VM instances.",
"type": "object",
"properties": {
"bootDiskSizeGb": {
"description": "Optional Size in GB of the boot disk (default is 500GB).",
"format": "int32",
"type": "integer"
},
"numLocalSsds": {
"description": "Optional Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs, and HDFS data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries.",
"format": "int32",
"type": "integer"
}
},
"id": "DiskConfiguration"
},
"JobStatus": {
"description": "Cloud Dataproc job status.",
"type": "object",
"properties": {
"insertTime": {
"description": "The time of the job request.",
"format": "google-datetime",
"type": "string"
},
"state": {
"description": "Required A state message specifying the overall job state.",
"type": "string",
"enumDescriptions": [
"The job state is unknown.",
"The job is pending; it has been submitted, but is not yet running.",
"Job has been received by the service and completed initial setup; it will shortly be submitted to the cluster.",
"The job is running on the cluster.",
"A CancelJob request has been received, but is pending.",
"Transient in-flight resources have been canceled, and the request to cancel the running job has been issued to the cluster.",
"The job cancelation was successful.",
"The job has completed successfully.",
"The job has completed, but encountered an error.",
"Job attempt has failed. The detail field contains failure details for this attempt.Applies to restartable jobs only."
],
"enum": [
"STATE_UNSPECIFIED",
"PENDING",
"SETUP_DONE",
"RUNNING",
"CANCEL_PENDING",
"CANCEL_STARTED",
"CANCELLED",
"DONE",
"ERROR",
"ATTEMPT_FAILURE"
]
},
"details": {
"description": "Optional Job state details, such as an error description if the state is \u003ccode\u003eERROR\u003c/code\u003e.",
"type": "string"
},
"stateStartTime": {
"description": "Output-only The time when this state was entered.",
"format": "google-datetime",
"type": "string"
},
"endTime": {
"description": "The time when the job completed.",
"format": "google-datetime",
"type": "string"
},
"startTime": {
"description": "The time when the server started the job.",
"format": "google-datetime",
"type": "string"
}
},
"id": "JobStatus"
},
"ClusterOperationStatus": {
"description": "The status of the operation.",
"type": "object",
"properties": {
"state": {
"enumDescriptions": [
"Unused.",
"The operation has been created.",
"The operation is running.",
"The operation is done; either cancelled or completed."
],
"enum": [
"UNKNOWN",
"PENDING",
"RUNNING",
"DONE"
],
"description": "Output-only A message containing the operation state.",
"type": "string"
},
"details": {
"description": "Output-onlyA message containing any operation metadata details.",
"type": "string"
},
"innerState": {
"description": "Output-only A message containing the detailed operation state.",
"type": "string"
},
"stateStartTime": {
"description": "Output-only The time this state was entered.",
"format": "google-datetime",
"type": "string"
}
},
"id": "ClusterOperationStatus"
},
"HadoopJob": {
"description": "A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN.",
"type": "object",
"properties": {
"jarFileUris": {
"description": "Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.",
"type": "array",
"items": {
"type": "string"
}
},
"loggingConfiguration": {
"$ref": "LoggingConfiguration",
"description": "Optional The runtime log configuration for job execution."
},
"properties": {
"description": "Optional A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.",
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"args": {
"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 may occur that causes an incorrect job submission.",
"type": "array",
"items": {
"type": "string"
}
},
"fileUris": {
"description": "Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.",
"type": "array",
"items": {
"type": "string"
}
},
"mainClass": {
"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.",
"type": "string"
},
"archiveUris": {
"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.",
"type": "array",
"items": {
"type": "string"
}
},
"mainJarFileUri": {
"description": "The Hadoop Compatible Filesystem (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"
}
},
"id": "HadoopJob"
},
"YarnApplication": {
"description": "A YARN application created by a job. Application information is a subset of \u003ccode\u003eorg.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto\u003c/code\u003e.",
"type": "object",
"properties": {
"state": {
"description": "Required The application state.",
"type": "string",
"enumDescriptions": [
"Status is unspecified.",
"Status is NEW.",
"Status is NEW_SAVING.",
"Status is SUBMITTED.",
"Status is ACCEPTED.",
"Status is RUNNING.",
"Status is FINISHED.",
"Status is FAILED.",
"Status is KILLED."
],
"enum": [
"STATE_UNSPECIFIED",
"NEW",
"NEW_SAVING",
"SUBMITTED",
"ACCEPTED",
"RUNNING",
"FINISHED",
"FAILED",
"KILLED"
]
},
"name": {
"description": "Required The application name.",
"type": "string"
},
"trackingUrl": {
"description": "Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.",
"type": "string"
},
"progress": {
"description": "Required The numerical progress of the application, from 1 to 100.",
"format": "float",
"type": "number"
}
},
"id": "YarnApplication"
},
"QueryList": {
"description": "A list of queries to run on a cluster.",
"type": "object",
"properties": {
"queries": {
"description": "Required The queries to execute. You do not need to terminate a query with a semicolon. Multiple queries can be specified in one string by separating each with a semicolon. Here is an example of an Cloud Dataproc API snippet that uses a QueryList to specify a HiveJob:\n\"hiveJob\": {\n \"queryList\": {\n \"queries\": [\n \"query1\",\n \"query2\",\n \"query3;query4\",\n ]\n }\n}\n",
"type": "array",
"items": {
"type": "string"
}
}
},
"id": "QueryList"
},
"ClusterOperationMetadata": {
"description": "Metadata describing the operation.",
"type": "object",
"properties": {
"labels": {
"additionalProperties": {
"type": "string"
},
"description": "Output-only Labels associated with the operation",
"type": "object"
},
"status": {
"$ref": "ClusterOperationStatus",
"description": "Output-only Current operation status."
},
"statusHistory": {
"description": "Output-only The previous operation status.",
"type": "array",
"items": {
"$ref": "ClusterOperationStatus"
}
},
"clusterUuid": {
"description": "Output-only Cluster UUID for the operation.",
"type": "string"
},
"clusterName": {
"description": "Output-only Name of the cluster for the operation.",
"type": "string"
},
"operationType": {
"description": "Output-only The operation type.",
"type": "string"
},
"description": {
"description": "Output-only Short description of operation.",
"type": "string"
},
"warnings": {
"description": "Output-only Errors encountered during operation execution.",
"type": "array",
"items": {
"type": "string"
}
}
},
"id": "ClusterOperationMetadata"
},
"Empty": {
"description": "A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance:\nservice Foo {\n rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);\n}\nThe JSON representation for Empty is empty JSON object {}.",
"type": "object",
"properties": {},
"id": "Empty"
},
"HiveJob": {
"description": "A Cloud Dataproc job for running Hive queries on YARN.",
"type": "object",
"properties": {
"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.",
"type": "array",
"items": {
"type": "string"
}
},
"scriptVariables": {
"additionalProperties": {
"type": "string"
},
"description": "Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name=\"value\";').",
"type": "object"
},
"properties": {
"additionalProperties": {
"type": "string"
},
"description": "Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.",
"type": "object"
},
"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"
},
"queryFileUri": {
"description": "The HCFS URI of the script that contains Hive queries.",
"type": "string"
},
"queryList": {
"description": "A list of queries.",
"$ref": "QueryList"
}
},
"id": "HiveJob"
},
"ListJobsRequest": {
"description": "A request to list jobs in a project.",
"type": "object",
"properties": {
"pageSize": {
"description": "Optional The number of results to return in each response.",
"format": "int32",
"type": "integer"
},
"filter": {
"description": "Optional A filter constraining which jobs to list. Valid filters contain job state and label terms such as: labels.key1 = val1 AND (labels.k2 = val2 OR labels.k3 = val3)",
"type": "string"
},
"jobStateMatcher": {
"enumDescriptions": [
"Match all jobs, regardless of state.",
"Only match jobs in non-terminal states: PENDING, RUNNING, CANCEL_PENDING",
"Only match jobs in terminal states: CANCELLED, DONE, ERROR"
],
"enum": [
"ALL",
"ACTIVE",
"NON_ACTIVE"
],
"description": "Optional Specifies enumerated categories of jobs to list.",
"type": "string"
},
"pageToken": {
"description": "Optional The page token, returned by a previous call, to request the next page of results.",
"type": "string"
},
"clusterName": {
"description": "Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.",
"type": "string"
}
},
"id": "ListJobsRequest"
},
"DiagnoseClusterResults": {
"description": "The location of diagnostic output.",
"type": "object",
"properties": {
"outputUri": {
"description": "Output-only The Google Cloud Storage URI of the diagnostic output. The output report is a plain text file with a summary of collected diagnostics.",
"type": "string"
}
},
"id": "DiagnoseClusterResults"
},
"GceConfiguration": {
"description": "Deprecated Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.",
"type": "object",
"properties": {
"imageUri": {
"description": "Deprecated The Google Compute Engine image resource used for cluster instances. Example: \"compute.googleapis.com/projects/debian-cloud /global/images/backports-debian-7-wheezy-v20140904\".",
"type": "string"
},
"machineTypeUri": {
"description": "Deprecated The Google Compute Engine machine type used for cluster instances. Example: \"compute.googleapis.com/projects/project_id /zones/us-east1-a/machineTypes/n1-standard-2\".",
"type": "string"
},
"networkUri": {
"description": "Deprecated The Google Compute Engine network to be used for machine communications. Inbound SSH connections are necessary to complete cluster configuration. Example \"compute.googleapis.com/projects/project_id /zones/us-east1-a/default\".",
"type": "string"
},
"serviceAccountScopes": {
"description": "Deprecated The service account scopes included in Google Compute Engine instances. Must include devstorage.full_control to enable the Google Cloud Storage connector. Example \"auth.googleapis.com/compute\" and \"auth.googleapis.com/devstorage.full_control\".",
"type": "array",
"items": {
"type": "string"
}
},
"zoneUri": {
"description": "Deprecated The zone where the Google Compute Engine cluster will be located. Example: \"compute.googleapis.com/projects/project_id /zones/us-east1-a\".",
"type": "string"
}
},
"id": "GceConfiguration"
},
"SoftwareConfiguration": {
"description": "Specifies the selection and configuration of software inside the cluster.",
"type": "object",
"properties": {
"imageVersion": {
"description": "Optional The version of software inside the cluster. It must match the regular expression 0-9+.0-9+. If unspecified it will default to latest version.",
"type": "string"
},
"properties": {
"additionalProperties": {
"type": "string"
},
"description": "Optional The properties to set on daemon configuration files.Property keys are specified in \"prefix:property\" format, such as \"core:fs.defaultFS\". The following are supported prefixes and their mappings: core - core-site.xml hdfs - hdfs-site.xml mapred - mapred-site.xml yarn - yarn-site.xml hive - hive-site.xml pig - pig.properties spark - spark-defaults.conf",
"type": "object"
}
},
"id": "SoftwareConfiguration"
},
"PySparkJob": {
"description": "A Cloud Dataproc job for running PySpark applications on YARN.",
"type": "object",
"properties": {
"archiveUris": {
"description": "Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.",
"type": "array",
"items": {
"type": "string"
}
},
"jarFileUris": {
"description": "Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.",
"type": "array",
"items": {
"type": "string"
}
},
"loggingConfiguration": {
"$ref": "LoggingConfiguration",
"description": "Optional The runtime log configuration for job execution."
},
"properties": {
"additionalProperties": {
"type": "string"
},
"description": "Optional A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.",
"type": "object"
},
"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"
}
},
"fileUris": {
"description": "Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.",
"type": "array",
"items": {
"type": "string"
}
},
"pythonFileUris": {
"description": "Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.",
"type": "array",
"items": {
"type": "string"
}
},
"mainPythonFileUri": {
"description": "Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.",
"type": "string"
}
},
"id": "PySparkJob"
},
"ClusterConfiguration": {
"description": "The cluster configuration.",
"type": "object",
"properties": {
"masterDiskConfiguration": {
"description": "Deprecated The configuration settings of master node disk options.",
"$ref": "DiskConfiguration"
},
"gceConfiguration": {
"description": "Deprecated The Google Compute Engine configuration settings for cluster resources.",
"$ref": "GceConfiguration"
},
"workerDiskConfiguration": {
"$ref": "DiskConfiguration",
"description": "Deprecated The configuration settings of worker node disk options."
},
"masterConfiguration": {
"description": "Optional The Google Compute Engine configuration settings for the master instance in a cluster.",
"$ref": "InstanceGroupConfiguration"
},
"secondaryWorkerConfiguration": {
"$ref": "InstanceGroupConfiguration",
"description": "Optional The Google Compute Engine configuration settings for additional worker instances in a cluster."
},
"masterName": {
"description": "Deprecated The Master's hostname. Dataproc derives the name from cluster_name if not set by user (recommended practice is to let Dataproc derive the name). Derived master name example: hadoop-m.",
"type": "string"
},
"workers": {
"description": "Deprecated The list of worker node names. Dataproc derives the names from cluster_name and num_workers if not set by user (recommended practice is to let Dataproc derive the name). Derived worker node name example: hadoop-w-0.",
"type": "array",
"items": {
"type": "string"
}
},
"workerConfiguration": {
"$ref": "InstanceGroupConfiguration",
"description": "Optional The Google Compute Engine configuration settings for worker instances in a cluster."
},
"initializationActions": {
"description": "Optional Commands to execute on each node after configuration is completed. By default, executables are run on master and all worker nodes. You can test a node's \u003ccode\u003erole\u003c/code\u003e metadata to run an executable on a master or worker node, as shown below:\nROLE=$(/usr/share/google/get_metadata_value attributes/role)\nif [[ \"${ROLE}\" == 'Master' ]]; then\n ... master specific actions ...\nelse\n ... worker specific actions ...\nfi\n",
"type": "array",
"items": {
"$ref": "NodeInitializationAction"
}
},
"softwareConfiguration": {
"description": "Optional The configuration settings for software inside the cluster.",
"$ref": "SoftwareConfiguration"
},
"gceClusterConfiguration": {
"$ref": "GceClusterConfiguration",
"description": "Optional The shared Google Compute Engine configuration settings for all instances in a cluster."
},
"configurationBucket": {
"description": "Optional A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, then it will create and manage this project-level, per-location bucket for you.",
"type": "string"
},
"numWorkers": {
"description": "Deprecated The number of worker nodes in the cluster.",
"format": "int32",
"type": "integer"
}
},
"id": "ClusterConfiguration"
},
"ClusterMetrics": {
"description": "Contains cluster daemon metrics, such as HDFS and YARN stats.",
"type": "object",
"properties": {
"yarnMetrics": {
"additionalProperties": {
"format": "int64",
"type": "string"
},
"description": "The YARN metrics.",
"type": "object"
},
"hdfsMetrics": {
"additionalProperties": {
"format": "int64",
"type": "string"
},
"description": "The HDFS metrics.",
"type": "object"
}
},
"id": "ClusterMetrics"
},
"LoggingConfiguration": {
"description": "The runtime logging configuration of the job.",
"type": "object",
"properties": {
"driverLogLevels": {
"additionalProperties": {
"type": "string",
"enum": [
"LEVEL_UNSPECIFIED",
"ALL",
"TRACE",
"DEBUG",
"INFO",
"WARN",
"ERROR",
"FATAL",
"OFF"
]
},
"description": "The per-package log levels for the driver. This may include 'root' package name to configure rootLogger. Examples: com.google = FATAL, root = INFO, org.apache = DEBUG",
"type": "object"
}
},
"id": "LoggingConfiguration"
}
},
"icons": {
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
"protocol": "rest",
"version": "v1alpha1",
"baseUrl": "https://dataproc.googleapis.com/",
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
}
}
}
},
"servicePath": "",
"description": "Manages Hadoop-based clusters and jobs on Google Cloud Platform.",
"kind": "discovery#restDescription",
"rootUrl": "https://dataproc.googleapis.com/",
"basePath": "",
"ownerDomain": "google.com",
"name": "dataproc",
"batchPath": "batch",
"revision": "20170207",
"id": "dataproc:v1alpha1",
"documentationLink": "https://cloud.google.com/dataproc/",
"title": "Google Cloud Dataproc API",
"ownerName": "Google",
"discoveryVersion": "v1"
}