Index: discovery/googleapis_beta/dataproc__v1beta1.json |
diff --git a/discovery/googleapis_beta/dataproc__v1beta1.json b/discovery/googleapis_beta/dataproc__v1beta1.json |
index e6466a2dd6d896492910443e1ad5242ba197c1ad..4db858738a6f9ee84eda2e9c6d2ce2880125f097 100644 |
--- a/discovery/googleapis_beta/dataproc__v1beta1.json |
+++ b/discovery/googleapis_beta/dataproc__v1beta1.json |
@@ -11,10 +11,9 @@ |
"basePath": "", |
"baseUrl": "https://dataproc.googleapis.com/", |
"batchPath": "batch", |
- "description": "An API for managing Hadoop-based clusters and jobs on Google Cloud Platform.", |
+ "description": "Manages Hadoop-based clusters and jobs on Google Cloud Platform.", |
"discoveryVersion": "v1", |
"documentationLink": "https://cloud.google.com/dataproc/", |
- "etag": "\"tbys6C40o18GZwyMen5GMkdK-3s/cZQ-6vqHhMM0YELMHYWsiSzNXAM\"", |
"icons": { |
"x16": "http://www.google.com/images/icons/product/search-16.gif", |
"x32": "http://www.google.com/images/icons/product/search-32.gif" |
@@ -25,52 +24,26 @@ |
"ownerDomain": "google.com", |
"ownerName": "Google", |
"parameters": { |
- "access_token": { |
- "description": "OAuth access token.", |
- "location": "query", |
- "type": "string" |
- }, |
- "alt": { |
- "default": "json", |
- "description": "Data format for response.", |
- "enumDescriptions": [ |
- "Responses with Content-Type of application/json", |
- "Media download with context-dependent Content-Type", |
- "Responses with Content-Type of application/x-protobuf" |
- ], |
+ "pp": { |
+ "default": "true", |
+ "description": "Pretty-print response.", |
"location": "query", |
- "type": "string" |
+ "type": "boolean" |
}, |
"bearer_token": { |
"description": "OAuth bearer token.", |
"location": "query", |
"type": "string" |
}, |
- "callback": { |
- "description": "JSONP", |
- "location": "query", |
- "type": "string" |
- }, |
- "fields": { |
- "description": "Selector specifying which fields to include in a partial response.", |
- "location": "query", |
- "type": "string" |
- }, |
- "key": { |
- "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.", |
- "location": "query", |
- "type": "string" |
- }, |
"oauth_token": { |
"description": "OAuth 2.0 token for the current user.", |
"location": "query", |
"type": "string" |
}, |
- "pp": { |
- "default": "true", |
- "description": "Pretty-print response.", |
+ "upload_protocol": { |
+ "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
"location": "query", |
- "type": "boolean" |
+ "type": "string" |
}, |
"prettyPrint": { |
"default": "true", |
@@ -78,33 +51,187 @@ |
"location": "query", |
"type": "boolean" |
}, |
- "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.", |
+ "uploadType": { |
+ "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
"location": "query", |
"type": "string" |
}, |
- "upload_protocol": { |
- "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
+ "fields": { |
+ "description": "Selector specifying which fields to include in a partial response.", |
"location": "query", |
"type": "string" |
}, |
- "uploadType": { |
- "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
+ "callback": { |
+ "description": "JSONP", |
"location": "query", |
"type": "string" |
}, |
"$.xgafv": { |
"description": "V1 error format.", |
+ "enum": [ |
+ "1", |
+ "2" |
+ ], |
"enumDescriptions": [ |
"v1 error format", |
"v2 error format" |
], |
"location": "query", |
"type": "string" |
+ }, |
+ "alt": { |
+ "default": "json", |
+ "description": "Data format for response.", |
+ "enum": [ |
+ "json", |
+ "media", |
+ "proto" |
+ ], |
+ "enumDescriptions": [ |
+ "Responses with Content-Type of application/json", |
+ "Media download with context-dependent Content-Type", |
+ "Responses with Content-Type of application/x-protobuf" |
+ ], |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "access_token": { |
+ "description": "OAuth access token.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "key": { |
+ "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "quotaUser": { |
+ "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", |
+ "location": "query", |
+ "type": "string" |
} |
}, |
"protocol": "rest", |
"resources": { |
+ "operations": { |
+ "methods": { |
+ "cancel": { |
+ "description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED. Clients can use operations.get or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation.", |
+ "httpMethod": "POST", |
+ "id": "dataproc.operations.cancel", |
+ "parameterOrder": [ |
+ "name" |
+ ], |
+ "parameters": { |
+ "name": { |
+ "description": "The name of the operation resource to be cancelled.", |
+ "location": "path", |
+ "pattern": "^operations/.+$", |
+ "required": true, |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1beta1/{+name}:cancel", |
+ "request": { |
+ "$ref": "CancelOperationRequest" |
+ }, |
+ "response": { |
+ "$ref": "Empty" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ }, |
+ "delete": { |
+ "description": "Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.", |
+ "httpMethod": "DELETE", |
+ "id": "dataproc.operations.delete", |
+ "parameterOrder": [ |
+ "name" |
+ ], |
+ "parameters": { |
+ "name": { |
+ "description": "The name of the operation resource to be deleted.", |
+ "location": "path", |
+ "pattern": "^operations/.+$", |
+ "required": true, |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1beta1/{+name}", |
+ "response": { |
+ "$ref": "Empty" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ }, |
+ "get": { |
+ "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.", |
+ "httpMethod": "GET", |
+ "id": "dataproc.operations.get", |
+ "parameterOrder": [ |
+ "name" |
+ ], |
+ "parameters": { |
+ "name": { |
+ "description": "The name of the operation resource.", |
+ "location": "path", |
+ "pattern": "^operations/.+$", |
+ "required": true, |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1beta1/{+name}", |
+ "response": { |
+ "$ref": "Operation" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ }, |
+ "list": { |
+ "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns UNIMPLEMENTED.NOTE: the name binding below allows API services to override the binding to use different resource name schemes, such as users/*/operations.", |
+ "httpMethod": "GET", |
+ "id": "dataproc.operations.list", |
+ "parameterOrder": [ |
+ "name" |
+ ], |
+ "parameters": { |
+ "name": { |
+ "description": "The name of the operation collection.", |
+ "location": "path", |
+ "pattern": "^operations$", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "pageToken": { |
+ "description": "The standard list page token.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "pageSize": { |
+ "description": "The standard list page size.", |
+ "format": "int32", |
+ "location": "query", |
+ "type": "integer" |
+ }, |
+ "filter": { |
+ "description": "The standard list filter.", |
+ "location": "query", |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1beta1/{+name}", |
+ "response": { |
+ "$ref": "ListOperationsResponse" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ } |
+ } |
+ }, |
"projects": { |
"resources": { |
"clusters": { |
@@ -118,7 +245,7 @@ |
], |
"parameters": { |
"projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
@@ -144,20 +271,21 @@ |
"clusterName" |
], |
"parameters": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project the cluster belongs to.", |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "clusterName": { |
- "description": "[Required] The cluster name.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
"updateMask": { |
- "description": "[Required] Specifies the path, relative to Cluster, of the field to update. For example, to change the number of workers in a cluster to 5, the update_mask parameter would be specified as configuration.worker_configuration.num_instances, and the `PATCH` request body would specify the new value, as follows: { \"configuration\":{ \"workerConfiguration\":{ \"numInstances\":\"5\" } } } Similarly, to change the number of preemptible workers in a cluster to 5, the update_mask parameter would be config.secondary_worker_config.num_instances, and the `PATCH` request body would be set as follows: { \"config\":{ \"secondaryWorkerConfig\":{ \"numInstances\":\"5\" } } } Note: Currently, config.worker_config.num_instances and config.secondary_worker_config.num_instances are the only fields that can be updated.", |
+ "description": "Required Specifies the path, relative to <code>Cluster</code>, of the field to update. For example, to change the number of workers in a cluster to 5, the <code>update_mask</code> parameter would be specified as <code>configuration.worker_configuration.num_instances</code>, and the PATCH request body would specify the new value, as follows:\n{\n \"configuration\":{\n \"workerConfiguration\":{\n \"numInstances\":\"5\"\n }\n }\n}\nSimilarly, to change the number of preemptible workers in a cluster to 5, the <code>update_mask</code> parameter would be <code>config.secondary_worker_config.num_instances</code>, and the PATCH request body would be set as follows:\n{\n \"config\":{\n \"secondaryWorkerConfig\":{\n \"numInstances\":\"5\"\n }\n }\n}\n<strong>Note:</strong> Currently, <code>config.worker_config.num_instances</code> and <code>config.secondary_worker_config.num_instances</code> are the only fields that can be updated.", |
+ "format": "google-fieldmask", |
"location": "query", |
"type": "string" |
} |
@@ -173,6 +301,36 @@ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
+ "get": { |
+ "description": "Gets the resource representation for a cluster in a project.", |
+ "httpMethod": "GET", |
+ "id": "dataproc.projects.clusters.get", |
+ "parameterOrder": [ |
+ "projectId", |
+ "clusterName" |
+ ], |
+ "parameters": { |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
+ "response": { |
+ "$ref": "Cluster" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ }, |
"delete": { |
"description": "Deletes a cluster in a project.", |
"httpMethod": "DELETE", |
@@ -182,14 +340,14 @@ |
"clusterName" |
], |
"parameters": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "clusterName": { |
- "description": "[Required] The cluster name.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
@@ -203,31 +361,34 @@ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "get": { |
- "description": "Gets the resource representation for a cluster in a project.", |
- "httpMethod": "GET", |
- "id": "dataproc.projects.clusters.get", |
+ "diagnose": { |
+ "description": "Gets cluster diagnostic information. After the operation completes, the Operation.response field contains DiagnoseClusterOutputLocation.", |
+ "httpMethod": "POST", |
+ "id": "dataproc.projects.clusters.diagnose", |
"parameterOrder": [ |
"projectId", |
"clusterName" |
], |
"parameters": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "clusterName": { |
+ "description": "Required The cluster name.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "clusterName": { |
- "description": "[Required] The cluster name.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters/{clusterName}", |
+ "path": "v1beta1/projects/{projectId}/clusters/{clusterName}:diagnose", |
+ "request": { |
+ "$ref": "DiagnoseClusterRequest" |
+ }, |
"response": { |
- "$ref": "Cluster" |
+ "$ref": "Operation" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
@@ -241,26 +402,26 @@ |
"projectId" |
], |
"parameters": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the cluster belongs to.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- }, |
"filter": { |
- "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)", |
+ "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)", |
"location": "query", |
"type": "string" |
}, |
- "pageSize": { |
+ "pageToken": { |
+ "description": "The standard List page token.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "pageSize": { |
"description": "The standard List page size.", |
"format": "int32", |
"location": "query", |
"type": "integer" |
}, |
- "pageToken": { |
- "description": "The standard List page token.", |
- "location": "query", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "location": "path", |
+ "required": true, |
"type": "string" |
} |
}, |
@@ -271,44 +432,80 @@ |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
+ } |
+ } |
+ }, |
+ "jobs": { |
+ "methods": { |
+ "get": { |
+ "description": "Gets the resource representation for a job in a project.", |
+ "httpMethod": "GET", |
+ "id": "dataproc.projects.jobs.get", |
+ "parameterOrder": [ |
+ "projectId", |
+ "jobId" |
+ ], |
+ "parameters": { |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "jobId": { |
+ "description": "Required The job ID.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ } |
+ }, |
+ "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
+ "response": { |
+ "$ref": "Job" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
}, |
- "diagnose": { |
- "description": "Gets cluster diagnostic information. After the operation completes, the Operation.response field contains `DiagnoseClusterOutputLocation`.", |
- "httpMethod": "POST", |
- "id": "dataproc.projects.clusters.diagnose", |
+ "patch": { |
+ "description": "Updates a job in a project.", |
+ "httpMethod": "PATCH", |
+ "id": "dataproc.projects.jobs.patch", |
"parameterOrder": [ |
"projectId", |
- "clusterName" |
+ "jobId" |
], |
"parameters": { |
+ "updateMask": { |
+ "description": "Required Specifies the path, relative to <code>Job</code>, of the field to update. For example, to update the labels of a Job the <code>update_mask</code> parameter would be specified as <code>labels</code>, and the PATCH request body would specify the new value. <strong>Note:</strong> Currently, <code>labels</code> is the only field that can be updated.", |
+ "format": "google-fieldmask", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the cluster belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
- "clusterName": { |
- "description": "[Required] The cluster name.", |
+ "jobId": { |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
} |
}, |
- "path": "v1beta1/projects/{projectId}/clusters/{clusterName}:diagnose", |
+ "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
"request": { |
- "$ref": "DiagnoseClusterRequest" |
+ "$ref": "Job" |
}, |
"response": { |
- "$ref": "Operation" |
+ "$ref": "Job" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
- } |
- } |
- }, |
- "jobs": { |
- "methods": { |
+ }, |
"submit": { |
"description": "Submits a job to a cluster.", |
"httpMethod": "POST", |
@@ -318,7 +515,7 @@ |
], |
"parameters": { |
"projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the job belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
@@ -335,23 +532,23 @@ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
}, |
- "get": { |
- "description": "Gets the resource representation for a job in a project.", |
- "httpMethod": "GET", |
- "id": "dataproc.projects.jobs.get", |
+ "delete": { |
+ "description": "Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.", |
+ "httpMethod": "DELETE", |
+ "id": "dataproc.projects.jobs.delete", |
"parameterOrder": [ |
"projectId", |
"jobId" |
], |
"parameters": { |
"projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the job belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
"jobId": { |
- "description": "[Required] The job ID.", |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
@@ -359,7 +556,7 @@ |
}, |
"path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
"response": { |
- "$ref": "Job" |
+ "$ref": "Empty" |
}, |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
@@ -373,30 +570,35 @@ |
"projectId" |
], |
"parameters": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the job belongs to.", |
- "location": "path", |
- "required": true, |
+ "pageToken": { |
+ "description": "Optional The page token, returned by a previous call, to request the next page of results.", |
+ "location": "query", |
"type": "string" |
}, |
"pageSize": { |
- "description": "[Optional] The number of results to return in each response.", |
+ "description": "Optional The number of results to return in each response.", |
"format": "int32", |
"location": "query", |
"type": "integer" |
}, |
- "pageToken": { |
- "description": "[Optional] The page token, returned by a previous call, to request the next page of results.", |
+ "clusterName": { |
+ "description": "Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.", |
"location": "query", |
"type": "string" |
}, |
- "clusterName": { |
- "description": "[Optional] If set, the returned jobs list includes only jobs that were submitted to the named cluster.", |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "location": "path", |
+ "required": true, |
+ "type": "string" |
+ }, |
+ "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)", |
"location": "query", |
"type": "string" |
}, |
"jobStateMatcher": { |
- "description": "[Optional] Specifies enumerated categories of jobs to list.", |
+ "description": "Optional Specifies enumerated categories of jobs to list.", |
"enum": [ |
"ALL", |
"ACTIVE", |
@@ -404,11 +606,6 @@ |
], |
"location": "query", |
"type": "string" |
- }, |
- "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)", |
- "location": "query", |
- "type": "string" |
} |
}, |
"path": "v1beta1/projects/{projectId}/jobs", |
@@ -420,7 +617,7 @@ |
] |
}, |
"cancel": { |
- "description": "Starts a job cancellation request. To access the job resource after cancellation, call [jobs.list](/dataproc/reference/rest/v1beta1/projects.jobs/list) or [jobs.get](/dataproc/reference/rest/v1beta1/projects.jobs/get).", |
+ "description": "Starts a job cancellation request. To access the job resource after cancellation, call jobs.list or jobs.get.", |
"httpMethod": "POST", |
"id": "dataproc.projects.jobs.cancel", |
"parameterOrder": [ |
@@ -429,13 +626,13 @@ |
], |
"parameters": { |
"projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the job belongs to.", |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
"location": "path", |
"required": true, |
"type": "string" |
}, |
"jobId": { |
- "description": "[Required] The job ID.", |
+ "description": "Required The job ID.", |
"location": "path", |
"required": true, |
"type": "string" |
@@ -451,376 +648,212 @@ |
"scopes": [ |
"https://www.googleapis.com/auth/cloud-platform" |
] |
- }, |
- "delete": { |
- "description": "Deletes the job from the project. If the job is active, the delete fails, and the response returns `FAILED_PRECONDITION`.", |
- "httpMethod": "DELETE", |
- "id": "dataproc.projects.jobs.delete", |
- "parameterOrder": [ |
- "projectId", |
- "jobId" |
- ], |
- "parameters": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the job belongs to.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- }, |
- "jobId": { |
- "description": "[Required] The job ID.", |
- "location": "path", |
- "required": true, |
- "type": "string" |
- } |
- }, |
- "path": "v1beta1/projects/{projectId}/jobs/{jobId}", |
- "response": { |
- "$ref": "Empty" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
} |
} |
} |
} |
- }, |
- "operations": { |
- "methods": { |
- "get": { |
- "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.", |
- "httpMethod": "GET", |
- "id": "dataproc.operations.get", |
- "parameterOrder": [ |
- "name" |
- ], |
- "parameters": { |
- "name": { |
- "description": "The name of the operation resource.", |
- "location": "path", |
- "pattern": "^operations/.+$", |
- "required": true, |
- "type": "string" |
- } |
- }, |
- "path": "v1beta1/{+name}", |
- "response": { |
- "$ref": "Operation" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
- }, |
- "list": { |
- "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`. NOTE: the `name` binding below allows API services to override the binding to use different resource name schemes, such as `users/*/operations`.", |
- "httpMethod": "GET", |
- "id": "dataproc.operations.list", |
- "parameterOrder": [ |
- "name" |
- ], |
- "parameters": { |
- "name": { |
- "description": "The name of the operation collection.", |
- "location": "path", |
- "pattern": "^operations$", |
- "required": true, |
- "type": "string" |
- }, |
- "filter": { |
- "description": "The standard list filter.", |
- "location": "query", |
- "type": "string" |
- }, |
- "pageSize": { |
- "description": "The standard list page size.", |
- "format": "int32", |
- "location": "query", |
- "type": "integer" |
- }, |
- "pageToken": { |
- "description": "The standard list page token.", |
- "location": "query", |
- "type": "string" |
- } |
- }, |
- "path": "v1beta1/{+name}", |
- "response": { |
- "$ref": "ListOperationsResponse" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
- }, |
- "cancel": { |
- "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 can use [operations.get](/dataproc/reference/rest/v1beta1/operations/get) or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation.", |
- "httpMethod": "POST", |
- "id": "dataproc.operations.cancel", |
- "parameterOrder": [ |
- "name" |
- ], |
- "parameters": { |
- "name": { |
- "description": "The name of the operation resource to be cancelled.", |
- "location": "path", |
- "pattern": "^operations/.+$", |
- "required": true, |
- "type": "string" |
- } |
- }, |
- "path": "v1beta1/{+name}:cancel", |
- "request": { |
- "$ref": "CancelOperationRequest" |
- }, |
- "response": { |
- "$ref": "Empty" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
- }, |
- "delete": { |
- "description": "Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`.", |
- "httpMethod": "DELETE", |
- "id": "dataproc.operations.delete", |
- "parameterOrder": [ |
- "name" |
- ], |
- "parameters": { |
- "name": { |
- "description": "The name of the operation resource to be deleted.", |
- "location": "path", |
- "pattern": "^operations/.+$", |
- "required": true, |
- "type": "string" |
- } |
- }, |
- "path": "v1beta1/{+name}", |
- "response": { |
- "$ref": "Empty" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
- } |
- } |
} |
}, |
- "revision": "20161102", |
+ "revision": "20170207", |
"rootUrl": "https://dataproc.googleapis.com/", |
"schemas": { |
- "Cluster": { |
- "description": "Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances.", |
- "id": "Cluster", |
+ "GceClusterConfiguration": { |
+ "description": "Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.", |
+ "id": "GceClusterConfiguration", |
"properties": { |
- "projectId": { |
- "description": "[Required] The Google Cloud Platform project ID that the cluster belongs to.", |
+ "tags": { |
+ "description": "The Google Compute Engine tags to add to all instances.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "serviceAccount": { |
+ "description": "Optional The service account of the instances. Defaults to the default Google Compute Engine service account. Custom service accounts need permissions equivalent to the folloing IAM roles:\nroles/logging.logWriter\nroles/storage.objectAdmin(see https://cloud.google.com/compute/docs/access/service-accounts#custom_service_accounts for more information). Example: [account_id]@[project_id].iam.gserviceaccount.com", |
"type": "string" |
}, |
- "clusterName": { |
- "description": "[Required] The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused.", |
+ "subnetworkUri": { |
+ "description": "The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/sub0.", |
"type": "string" |
}, |
- "configuration": { |
- "$ref": "ClusterConfiguration", |
- "description": "[Required] The cluster configuration. Note that Cloud Dataproc may set default values, and values may change when clusters are updated." |
+ "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: https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default.", |
+ "type": "string" |
}, |
- "labels": { |
+ "zoneUri": { |
+ "description": "Required The zone where the Google Compute Engine cluster will be located. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone].", |
+ "type": "string" |
+ }, |
+ "metadata": { |
"additionalProperties": { |
"type": "string" |
}, |
- "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.", |
+ "description": "The Google Compute Engine metadata entries to add to all instances.", |
"type": "object" |
}, |
- "status": { |
- "$ref": "ClusterStatus", |
- "description": "[Output-only] Cluster status." |
+ "internalIpOnly": { |
+ "description": "If true, all instances in the cluser will only have internal IP addresses. By default, clusters are not restricted to internal IP addresses, and will have ephemeral external IP addresses assigned to each instance. This restriction can only be enabled for subnetwork enabled networks, and all off-cluster dependencies must be configured to be accessible without external IP addresses.", |
+ "type": "boolean" |
}, |
- "statusHistory": { |
- "description": "[Output-only] Previous cluster statuses.", |
+ "serviceAccountScopes": { |
+ "description": "The URIs of service account scopes to be included in Google Compute Engine instances. The following base set of scopes is always included: - https://www.googleapis.com/auth/cloud.useraccounts.readonly - https://www.googleapis.com/auth/devstorage.read_write - https://www.googleapis.com/auth/logging.write If no scopes are specfied, the following defaults are also provided: - https://www.googleapis.com/auth/bigquery - https://www.googleapis.com/auth/bigtable.admin.table - https://www.googleapis.com/auth/bigtable.data - https://www.googleapis.com/auth/devstorage.full_control", |
"items": { |
- "$ref": "ClusterStatus" |
+ "type": "string" |
}, |
"type": "array" |
- }, |
- "clusterUuid": { |
- "description": "[Output-only] A cluster UUID (Unique Universal Identifier). Cloud Dataproc generates this value when it creates the cluster.", |
- "type": "string" |
- }, |
- "metrics": { |
- "$ref": "ClusterMetrics", |
- "description": "Contains cluster daemon metrics such as HDFS and YARN stats." |
} |
}, |
"type": "object" |
}, |
- "ClusterConfiguration": { |
- "description": "The cluster configuration.", |
- "id": "ClusterConfiguration", |
+ "CancelOperationRequest": { |
+ "description": "The request message for Operations.CancelOperation.", |
+ "id": "CancelOperationRequest", |
+ "properties": {}, |
+ "type": "object" |
+ }, |
+ "DiagnoseClusterOutputLocation": { |
+ "description": "The location where output from diagnostic command can be found.", |
+ "id": "DiagnoseClusterOutputLocation", |
"properties": { |
- "configurationBucket": { |
- "description": "[Optional] A Google Cloud Storage staging bucket used for sharing generated SSH keys and configuration. If you do not specify a staging bucket, Cloud Dataproc will determine an appropriate Cloud Storage location (US, ASIA, or EU) for your cluster's staging bucket according to the Google Compute Engine zone where your cluster is deployed, and then it will create and manage this project-level, per-location bucket for you.", |
+ "outputUri": { |
+ "description": "Output-only The Google Cloud Storage URI of the diagnostic output. This will be a plain text file with summary of collected diagnostics.", |
"type": "string" |
- }, |
- "gceClusterConfiguration": { |
- "$ref": "GceClusterConfiguration", |
- "description": "[Required] The shared Google Compute Engine configuration settings for all instances in a cluster." |
- }, |
- "masterConfiguration": { |
- "$ref": "InstanceGroupConfiguration", |
- "description": "[Optional] The Google Compute Engine configuration settings for the master instance in a cluster." |
- }, |
- "workerConfiguration": { |
- "$ref": "InstanceGroupConfiguration", |
- "description": "[Optional] The Google Compute Engine configuration settings for worker instances in a cluster." |
- }, |
- "secondaryWorkerConfiguration": { |
- "$ref": "InstanceGroupConfiguration", |
- "description": "[Optional] The Google Compute Engine configuration settings for additional worker instances in a cluster." |
- }, |
- "softwareConfiguration": { |
- "$ref": "SoftwareConfiguration", |
- "description": "[Optional] The configuration settings for software inside the 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 role metadata to run an executable on a master or worker node, as shown below: ROLE=$(/usr/share/google/get_metadata_value attributes/role) if [[ \"${ROLE}\" == 'Master' ]]; then ... master specific actions ... else ... worker specific actions ... fi", |
- "items": { |
- "$ref": "NodeInitializationAction" |
- }, |
- "type": "array" |
} |
}, |
"type": "object" |
}, |
- "GceClusterConfiguration": { |
- "description": "Common configuration settings for resources of Google Compute Engine cluster instances, applicable to all instances in the cluster.", |
- "id": "GceClusterConfiguration", |
+ "Operation": { |
+ "description": "This resource represents a long-running operation that is the result of a network API call.", |
+ "id": "Operation", |
"properties": { |
- "zoneUri": { |
- "description": "[Required] The zone where the Google Compute Engine cluster will be located. Example: `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/[zone]`.", |
- "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: `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/global/default`.", |
- "type": "string" |
+ "response": { |
+ "additionalProperties": { |
+ "description": "Properties of the object. Contains field @type with type URL.", |
+ "type": "any" |
+ }, |
+ "description": "The normal response of the operation in case of success. If the original method returns no data on success, such as Delete, the response is google.protobuf.Empty. If the original method is standard Get/Create/Update, the response should be the resource. For other methods, the response should have the type XxxResponse, where Xxx is the original method name. For example, if the original method name is TakeSnapshot(), the inferred response type is TakeSnapshotResponse.", |
+ "type": "object" |
}, |
- "subnetworkUri": { |
- "description": "The Google Compute Engine subnetwork to be used for machine communications. Cannot be specified with network_uri. Example: `https://www.googleapis.com/compute/v1/projects/[project_id]/regions/us-east1/sub0`.", |
+ "name": { |
+ "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the name should have the format of operations/some/unique/name.", |
"type": "string" |
}, |
- "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" |
- }, |
- "serviceAccountScopes": { |
- "description": "The URIs of service account scopes to be included in Google 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.write If no scopes are specfied, 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", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "tags": { |
- "description": "The Google Compute Engine tags to add to all instances.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
+ "error": { |
+ "$ref": "Status", |
+ "description": "The error result of the operation in case of failure or cancellation." |
}, |
"metadata": { |
"additionalProperties": { |
- "type": "string" |
+ "description": "Properties of the object. Contains field @type with type URL.", |
+ "type": "any" |
}, |
- "description": "The Google Compute Engine metadata entries to add to all instances.", |
+ "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", |
"type": "object" |
+ }, |
+ "done": { |
+ "description": "If the value is false, it means the operation is still in progress. If true, the operation is completed, and either error or response is available.", |
+ "type": "boolean" |
} |
}, |
"type": "object" |
}, |
- "InstanceGroupConfiguration": { |
- "description": "The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group.", |
- "id": "InstanceGroupConfiguration", |
+ "OperationStatus": { |
+ "description": "The status of the operation.", |
+ "id": "OperationStatus", |
"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" |
- }, |
- "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).", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "imageUri": { |
- "description": "[Output-only] The Google Compute Engine image resource used for cluster instances. Inferred from `SoftwareConfiguration.image_version`.", |
+ "innerState": { |
+ "description": "A message containing the detailed operation state.", |
"type": "string" |
}, |
- "machineTypeUri": { |
- "description": "The Google Compute Engine machine type used for cluster instances. Example: `https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2`.", |
+ "stateStartTime": { |
+ "description": "The time this state was entered.", |
+ "format": "google-datetime", |
"type": "string" |
}, |
- "diskConfiguration": { |
- "$ref": "DiskConfiguration", |
- "description": "Disk option configuration settings." |
- }, |
- "isPreemptible": { |
- "description": "Specifies that this instance group contains Preemptible Instances.", |
- "type": "boolean" |
+ "state": { |
+ "description": "A message containing the operation state.", |
+ "enum": [ |
+ "UNKNOWN", |
+ "PENDING", |
+ "RUNNING", |
+ "DONE" |
+ ], |
+ "enumDescriptions": [ |
+ "Unused.", |
+ "The operation has been created.", |
+ "The operation is running.", |
+ "The operation is done; either cancelled or completed." |
+ ], |
+ "type": "string" |
}, |
- "managedGroupConfiguration": { |
- "$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." |
+ "details": { |
+ "description": "A message containing any operation metadata details.", |
+ "type": "string" |
} |
}, |
"type": "object" |
}, |
- "DiskConfiguration": { |
- "description": "Specifies the configuration of disk options for a group of VM instances.", |
- "id": "DiskConfiguration", |
+ "JobReference": { |
+ "description": "Encapsulates the full scoping used to reference a job.", |
+ "id": "JobReference", |
"properties": { |
- "bootDiskSizeGb": { |
- "description": "[Optional] Size in GB of the boot disk (default is 500GB).", |
- "format": "int32", |
- "type": "integer" |
+ "projectId": { |
+ "description": "Required The ID of the Google Cloud Platform project that the job belongs to.", |
+ "type": "string" |
}, |
- "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" |
+ "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 hyphens (-). The maximum length is 512 characters.", |
+ "type": "string" |
} |
}, |
"type": "object" |
}, |
- "ManagedGroupConfiguration": { |
- "description": "Specifies the resources used to actively manage an instance group.", |
- "id": "ManagedGroupConfiguration", |
+ "SubmitJobRequest": { |
+ "description": "A request to submit a job.", |
+ "id": "SubmitJobRequest", |
"properties": { |
- "instanceTemplateName": { |
- "description": "[Output-only] The name of the Instance Template used for the Managed Instance Group.", |
- "type": "string" |
- }, |
- "instanceGroupManagerName": { |
- "description": "[Output-only] The name of the Instance Group Manager for this group.", |
- "type": "string" |
+ "job": { |
+ "$ref": "Job", |
+ "description": "Required The job resource." |
} |
}, |
"type": "object" |
}, |
- "SoftwareConfiguration": { |
- "description": "Specifies the selection and configuration of software inside the cluster.", |
- "id": "SoftwareConfiguration", |
+ "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.", |
+ "id": "Status", |
"properties": { |
- "imageVersion": { |
- "description": "[Optional] The version of software inside the cluster. It must match the regular expression `[0-9]+\\.[0-9]+`. If unspecified, it defaults to the latest version (see [Cloud Dataproc Versioning](/dataproc/versioning)).", |
+ "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" |
}, |
- "properties": { |
- "additionalProperties": { |
- "type": "string" |
+ "details": { |
+ "description": "A list of messages that carry the error details. There will be a common set of message types for APIs to use.", |
+ "items": { |
+ "additionalProperties": { |
+ "description": "Properties of the object. Contains field @type with type URL.", |
+ "type": "any" |
+ }, |
+ "type": "object" |
}, |
- "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" |
+ "type": "array" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "JobScheduling": { |
+ "description": "Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release.", |
+ "id": "JobScheduling", |
+ "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" |
} |
}, |
"type": "object" |
@@ -830,257 +863,220 @@ |
"id": "NodeInitializationAction", |
"properties": { |
"executableFile": { |
- "description": "[Required] Google Cloud Storage URI of executable file.", |
+ "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.", |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "ClusterStatus": { |
- "description": "The status of a cluster and its instances.", |
- "id": "ClusterStatus", |
+ "ListJobsResponse": { |
+ "description": "A list of jobs in a project.", |
+ "id": "ListJobsResponse", |
"properties": { |
- "state": { |
- "description": "The cluster's state.", |
- "enum": [ |
- "UNKNOWN", |
- "CREATING", |
- "RUNNING", |
- "ERROR", |
- "DELETING", |
- "UPDATING" |
- ], |
- "type": "string" |
- }, |
- "detail": { |
- "description": "Optional details of cluster's state.", |
+ "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 <code>ListJobsRequest</code>.", |
"type": "string" |
}, |
- "stateStartTime": { |
- "description": "Time when this state was entered.", |
- "type": "string" |
+ "jobs": { |
+ "description": "Output-only Jobs list.", |
+ "items": { |
+ "$ref": "Job" |
+ }, |
+ "type": "array" |
} |
}, |
"type": "object" |
}, |
- "ClusterMetrics": { |
- "description": "Contains cluster daemon metrics, such as HDFS and YARN stats.", |
- "id": "ClusterMetrics", |
+ "CancelJobRequest": { |
+ "description": "A request to cancel a job.", |
+ "id": "CancelJobRequest", |
+ "properties": {}, |
+ "type": "object" |
+ }, |
+ "SparkSqlJob": { |
+ "description": "A Cloud Dataproc job for running Spark SQL queries.", |
+ "id": "SparkSqlJob", |
"properties": { |
- "hdfsMetrics": { |
- "additionalProperties": { |
- "format": "int64", |
+ "queryList": { |
+ "$ref": "QueryList", |
+ "description": "A list of queries." |
+ }, |
+ "queryFileUri": { |
+ "description": "The HCFS URI of the script that contains SQL queries.", |
+ "type": "string" |
+ }, |
+ "scriptVariables": { |
+ "additionalProperties": { |
"type": "string" |
}, |
- "description": "The HDFS metrics.", |
+ "description": "Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name=\"value\";).", |
"type": "object" |
}, |
- "yarnMetrics": { |
+ "jarFileUris": { |
+ "description": "Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "loggingConfiguration": { |
+ "$ref": "LoggingConfiguration", |
+ "description": "Optional The runtime log configuration for job execution." |
+ }, |
+ "properties": { |
"additionalProperties": { |
- "format": "int64", |
"type": "string" |
}, |
- "description": "The YARN metrics.", |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "Operation": { |
- "description": "This resource represents a long-running operation that is the result of a network API call.", |
- "id": "Operation", |
+ "Cluster": { |
+ "description": "Describes the identifying information, configuration, and status of a cluster of Google Compute Engine instances.", |
+ "id": "Cluster", |
"properties": { |
- "name": { |
- "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should have the format of `operations/some/unique/name`.", |
- "type": "string" |
+ "configuration": { |
+ "$ref": "ClusterConfiguration", |
+ "description": "Required The cluster configuration. Note that Cloud Dataproc may set default values, and values may change when clusters are updated." |
}, |
- "metadata": { |
+ "labels": { |
"additionalProperties": { |
- "description": "Properties of the object. Contains field @type with type URL.", |
- "type": "any" |
+ "type": "string" |
}, |
- "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", |
+ "description": "Optional The labels to associate with this cluster.Label keys must be between 1 and 63 characters long, and must conform to the following PCRE regular expression: \\p{Ll}\\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following PCRE regular expression: \\p{Ll}\\p{Lo}\\p{N}_-{0,63}No more than 64 labels can be associated with a given cluster.", |
"type": "object" |
}, |
- "done": { |
- "description": "If the value is `false`, it means the operation is still in progress. If true, the operation is completed, and either `error` or `response` is available.", |
- "type": "boolean" |
+ "metrics": { |
+ "$ref": "ClusterMetrics", |
+ "description": "Contains cluster daemon metrics such as HDFS and YARN stats." |
}, |
- "error": { |
- "$ref": "Status", |
- "description": "The error result of the operation in case of failure or cancellation." |
+ "status": { |
+ "$ref": "ClusterStatus", |
+ "description": "Output-only Cluster status." |
}, |
- "response": { |
- "additionalProperties": { |
- "description": "Properties of the object. Contains field @type with type URL.", |
- "type": "any" |
+ "statusHistory": { |
+ "description": "Output-only Previous cluster statuses.", |
+ "items": { |
+ "$ref": "ClusterStatus" |
}, |
- "description": "The normal response of the operation in case of success. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.", |
- "type": "object" |
- } |
- }, |
- "type": "object" |
- }, |
- "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: - Simple to use and understand for most users - Flexible enough to meet unexpected needs # Overview The `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 mapping The `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 uses The 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: - Partial 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. - Workflow errors. A typical workflow has multiple steps. Each step may have a `Status` message for error reporting purpose. - Batch 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. - Asynchronous 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. - Logging. If some API errors are stored in logs, the message `Status` could be used directly after any stripping needed for security/privacy reasons.", |
- "id": "Status", |
- "properties": { |
- "code": { |
- "description": "The status code, which should be an enum value of google.rpc.Code.", |
- "format": "int32", |
- "type": "integer" |
+ "type": "array" |
}, |
- "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.", |
+ "clusterName": { |
+ "description": "Required The cluster name. Cluster names within a project must be unique. Names from deleted clusters can be reused.", |
"type": "string" |
}, |
- "details": { |
- "description": "A list of messages that carry the error details. There will be a common set of message types for APIs to use.", |
- "items": { |
- "additionalProperties": { |
- "description": "Properties of the object. Contains field @type with type URL.", |
- "type": "any" |
- }, |
- "type": "object" |
- }, |
- "type": "array" |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "ListClustersResponse": { |
- "description": "The list of all clusters in a project.", |
- "id": "ListClustersResponse", |
+ "ListOperationsResponse": { |
+ "description": "The response message for Operations.ListOperations.", |
+ "id": "ListOperationsResponse", |
"properties": { |
- "clusters": { |
- "description": "[Output-only] The clusters in the project.", |
- "items": { |
- "$ref": "Cluster" |
- }, |
- "type": "array" |
- }, |
"nextPageToken": { |
"description": "The standard List next-page token.", |
"type": "string" |
+ }, |
+ "operations": { |
+ "description": "A list of operations that matches the specified filter in the request.", |
+ "items": { |
+ "$ref": "Operation" |
+ }, |
+ "type": "array" |
} |
}, |
"type": "object" |
}, |
- "DiagnoseClusterRequest": { |
- "description": "A request to collect cluster diagnostic information.", |
- "id": "DiagnoseClusterRequest", |
- "type": "object" |
- }, |
- "SubmitJobRequest": { |
- "description": "A request to submit a job.", |
- "id": "SubmitJobRequest", |
- "properties": { |
- "job": { |
- "$ref": "Job", |
- "description": "[Required] The job resource." |
- } |
- }, |
- "type": "object" |
- }, |
- "Job": { |
- "description": "A Cloud Dataproc job resource.", |
- "id": "Job", |
+ "OperationMetadata": { |
+ "description": "Metadata describing the operation.", |
+ "id": "OperationMetadata", |
"properties": { |
- "reference": { |
- "$ref": "JobReference", |
- "description": "[Optional] The fully qualified reference to the job, which can be used to obtain the equivalent REST path of the job resource. If this property is not specified when a job is created, the server generates a job_id." |
- }, |
- "placement": { |
- "$ref": "JobPlacement", |
- "description": "[Required] Job information, including how, when, and where to run the job." |
- }, |
- "hadoopJob": { |
- "$ref": "HadoopJob", |
- "description": "Job is a Hadoop job." |
- }, |
- "sparkJob": { |
- "$ref": "SparkJob", |
- "description": "Job is a Spark job." |
- }, |
- "pysparkJob": { |
- "$ref": "PySparkJob", |
- "description": "Job is a Pyspark job." |
- }, |
- "hiveJob": { |
- "$ref": "HiveJob", |
- "description": "Job is a Hive job." |
- }, |
- "pigJob": { |
- "$ref": "PigJob", |
- "description": "Job is a Pig job." |
+ "operationType": { |
+ "description": "Output-only The operation type.", |
+ "type": "string" |
}, |
- "sparkSqlJob": { |
- "$ref": "SparkSqlJob", |
- "description": "Job is a SparkSql job." |
+ "description": { |
+ "description": "Output-only Short description of operation.", |
+ "type": "string" |
}, |
"status": { |
- "$ref": "JobStatus", |
- "description": "[Output-only] The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields." |
+ "$ref": "OperationStatus", |
+ "description": "Output-only Current operation status." |
}, |
- "statusHistory": { |
- "description": "[Output-only] The previous job status.", |
- "items": { |
- "$ref": "JobStatus" |
- }, |
- "type": "array" |
+ "state": { |
+ "description": "A message containing the operation state.", |
+ "enum": [ |
+ "UNKNOWN", |
+ "PENDING", |
+ "RUNNING", |
+ "DONE" |
+ ], |
+ "enumDescriptions": [ |
+ "Unused.", |
+ "The operation has been created.", |
+ "The operation is currently running.", |
+ "The operation is done, either cancelled or completed." |
+ ], |
+ "type": "string" |
}, |
- "yarnApplications": { |
- "description": "[Output-only] The collection of YARN applications spun up by this job.", |
- "items": { |
- "$ref": "YarnApplication" |
- }, |
- "type": "array" |
+ "details": { |
+ "description": "A message containing any operation metadata details.", |
+ "type": "string" |
}, |
- "submittedBy": { |
- "description": "[Output-only] The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.", |
+ "clusterName": { |
+ "description": "Name of the cluster for the operation.", |
"type": "string" |
}, |
- "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.", |
+ "clusterUuid": { |
+ "description": "Cluster UUId for the operation.", |
"type": "string" |
}, |
- "driverOutputResourceUri": { |
- "description": "[Output-only] A URI pointing to the location of the stdout of the job's driver program.", |
+ "innerState": { |
+ "description": "A message containing the detailed operation state.", |
"type": "string" |
}, |
- "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`.", |
+ "endTime": { |
+ "description": "The time that the operation completed.", |
+ "format": "google-datetime", |
"type": "string" |
}, |
- "interactive": { |
- "description": "[Optional] If set to `true`, 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" |
+ "startTime": { |
+ "description": "The time that the operation was started by the server.", |
+ "format": "google-datetime", |
+ "type": "string" |
}, |
- "labels": { |
- "additionalProperties": { |
+ "warnings": { |
+ "description": "Output-only Errors encountered during operation execution.", |
+ "items": { |
"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" |
- } |
- }, |
- "type": "object" |
- }, |
- "JobReference": { |
- "description": "Encapsulates the full scoping used to reference a job.", |
- "id": "JobReference", |
- "properties": { |
- "projectId": { |
- "description": "[Required] The ID of the Google Cloud Platform project that the job belongs to.", |
- "type": "string" |
+ "type": "array" |
}, |
- "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 hyphens (-). The maximum length is 512 characters.", |
+ "insertTime": { |
+ "description": "The time that the operation was requested.", |
+ "format": "google-datetime", |
"type": "string" |
+ }, |
+ "statusHistory": { |
+ "description": "Output-only Previous operation status.", |
+ "items": { |
+ "$ref": "OperationStatus" |
+ }, |
+ "type": "array" |
} |
}, |
"type": "object" |
@@ -1090,384 +1086,447 @@ |
"id": "JobPlacement", |
"properties": { |
"clusterName": { |
- "description": "[Required] The name of the cluster where the job will be submitted.", |
+ "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.", |
+ "description": "Output-only A cluster UUID generated by the Dataproc service when the job is submitted.", |
"type": "string" |
} |
}, |
"type": "object" |
}, |
- "HadoopJob": { |
- "description": "A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN.", |
- "id": "HadoopJob", |
+ "ClusterStatus": { |
+ "description": "The status of a cluster and its instances.", |
+ "id": "ClusterStatus", |
"properties": { |
- "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'", |
+ "stateStartTime": { |
+ "description": "Time when this state was entered.", |
+ "format": "google-datetime", |
"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`.", |
+ "detail": { |
+ "description": "Optional details of cluster's state.", |
"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.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "jarFileUris": { |
- "description": "[Optional] Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
- }, |
- "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.", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
+ "state": { |
+ "description": "The cluster's state.", |
+ "enum": [ |
+ "UNKNOWN", |
+ "CREATING", |
+ "RUNNING", |
+ "ERROR", |
+ "DELETING", |
+ "UPDATING" |
+ ], |
+ "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." |
+ ], |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "PigJob": { |
+ "description": "A Cloud Dataproc job for running Pig queries on YARN.", |
+ "id": "PigJob", |
+ "properties": { |
+ "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" |
}, |
- "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.", |
+ "queryList": { |
+ "$ref": "QueryList", |
+ "description": "A list of queries." |
+ }, |
+ "queryFileUri": { |
+ "description": "The HCFS URI of the script that contains the Pig queries.", |
+ "type": "string" |
+ }, |
+ "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.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
- "properties": { |
+ "scriptVariables": { |
"additionalProperties": { |
"type": "string" |
}, |
- "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.", |
+ "description": "Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).", |
"type": "object" |
}, |
"loggingConfiguration": { |
"$ref": "LoggingConfiguration", |
- "description": "[Optional] The runtime log configuration for job execution." |
- } |
- }, |
- "type": "object" |
- }, |
- "LoggingConfiguration": { |
- "description": "The runtime logging configuration of the job.", |
- "id": "LoggingConfiguration", |
- "properties": { |
- "driverLogLevels": { |
+ "description": "Optional The runtime log configuration for job execution." |
+ }, |
+ "properties": { |
"additionalProperties": { |
- "enum": [ |
- "LEVEL_UNSPECIFIED", |
- "ALL", |
- "TRACE", |
- "DEBUG", |
- "INFO", |
- "WARN", |
- "ERROR", |
- "FATAL", |
- "OFF" |
- ], |
"type": "string" |
}, |
- "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'", |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "SparkJob": { |
- "description": "A Cloud Dataproc job for running Spark applications on YARN.", |
- "id": "SparkJob", |
+ "ManagedGroupConfiguration": { |
+ "description": "Specifies the resources used to actively manage an instance group.", |
+ "id": "ManagedGroupConfiguration", |
"properties": { |
- "mainJarFileUri": { |
- "description": "The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.", |
+ "instanceGroupManagerName": { |
+ "description": "Output-only The name of the Instance Group Manager for this group.", |
"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`.", |
+ "instanceTemplateName": { |
+ "description": "Output-only The name of the Instance Template used for the Managed Instance Group.", |
"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": "object" |
+ }, |
+ "ListClustersResponse": { |
+ "description": "The list of all clusters in a project.", |
+ "id": "ListClustersResponse", |
+ "properties": { |
+ "clusters": { |
+ "description": "Output-only The clusters in the project.", |
"items": { |
- "type": "string" |
+ "$ref": "Cluster" |
}, |
"type": "array" |
}, |
- "jarFileUris": { |
- "description": "[Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.", |
- "items": { |
+ "nextPageToken": { |
+ "description": "The standard List next-page token.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "Job": { |
+ "description": "A Cloud Dataproc job resource.", |
+ "id": "Job", |
+ "properties": { |
+ "interactive": { |
+ "description": "Optional If set to true, 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": { |
+ "$ref": "HadoopJob", |
+ "description": "Job is a Hadoop job." |
+ }, |
+ "status": { |
+ "$ref": "JobStatus", |
+ "description": "Output-only The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields." |
+ }, |
+ "placement": { |
+ "$ref": "JobPlacement", |
+ "description": "Required Job information, including how, when, and where to run the job." |
+ }, |
+ "driverControlFilesUri": { |
+ "description": "Output-only If present, the location of miscellaneous control files which may be used as part of job setup and handling. If not present, control files may be placed in the same location as driver_output_uri.", |
+ "type": "string" |
+ }, |
+ "submittedBy": { |
+ "description": "Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.", |
+ "type": "string" |
+ }, |
+ "scheduling": { |
+ "$ref": "JobScheduling", |
+ "description": "Optional Job scheduling configuration." |
+ }, |
+ "pigJob": { |
+ "$ref": "PigJob", |
+ "description": "Job is a Pig job." |
+ }, |
+ "hiveJob": { |
+ "$ref": "HiveJob", |
+ "description": "Job is a Hive job." |
+ }, |
+ "labels": { |
+ "additionalProperties": { |
"type": "string" |
}, |
- "type": "array" |
+ "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" |
}, |
- "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.", |
+ "driverOutputResourceUri": { |
+ "description": "Output-only A URI pointing to the location of the stdout of the job's driver program.", |
+ "type": "string" |
+ }, |
+ "sparkSqlJob": { |
+ "$ref": "SparkSqlJob", |
+ "description": "Job is a SparkSql job." |
+ }, |
+ "statusHistory": { |
+ "description": "Output-only The previous job status.", |
"items": { |
- "type": "string" |
+ "$ref": "JobStatus" |
}, |
"type": "array" |
}, |
- "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.", |
+ "sparkJob": { |
+ "$ref": "SparkJob", |
+ "description": "Job is a Spark job." |
+ }, |
+ "yarnApplications": { |
+ "description": "Output-only The collection of YARN applications spun up by this job.", |
"items": { |
- "type": "string" |
+ "$ref": "YarnApplication" |
}, |
"type": "array" |
}, |
- "properties": { |
- "additionalProperties": { |
- "type": "string" |
- }, |
- "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" |
+ "pysparkJob": { |
+ "$ref": "PySparkJob", |
+ "description": "Job is a Pyspark job." |
}, |
- "loggingConfiguration": { |
- "$ref": "LoggingConfiguration", |
- "description": "[Optional] The runtime log configuration for job execution." |
+ "reference": { |
+ "$ref": "JobReference", |
+ "description": "Optional The fully qualified reference to the job, which can be used to obtain the equivalent REST path of the job resource. If this property is not specified when a job is created, the server generates a <code>job_id</code>." |
} |
}, |
"type": "object" |
}, |
- "PySparkJob": { |
- "description": "A Cloud Dataproc job for running PySpark applications on YARN.", |
- "id": "PySparkJob", |
+ "SparkJob": { |
+ "description": "A Cloud Dataproc job for running Spark applications on YARN.", |
+ "id": "SparkJob", |
"properties": { |
- "mainPythonFileUri": { |
- "description": "[Required] The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.", |
- "type": "string" |
- }, |
- "args": { |
- "description": "[Optional] The arguments to pass to the driver. Do not include arguments, such as `--conf`, that can be set as job properties, since a collision may occur that causes an incorrect job submission.", |
+ "jarFileUris": { |
+ "description": "Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
- "pythonFileUris": { |
- "description": "[Optional] HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.", |
- "items": { |
+ "loggingConfiguration": { |
+ "$ref": "LoggingConfiguration", |
+ "description": "Optional The runtime log configuration for job execution." |
+ }, |
+ "properties": { |
+ "additionalProperties": { |
"type": "string" |
}, |
- "type": "array" |
+ "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" |
}, |
- "jarFileUris": { |
- "description": "[Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.", |
+ "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.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
"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.", |
+ "description": "Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
+ "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 .jar, .tar, .tar.gz, .tgz, and .zip.", |
+ "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.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
- "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" |
+ "mainJarFileUri": { |
+ "description": "The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "DiskConfiguration": { |
+ "description": "Specifies the configuration of disk options for a group of VM instances.", |
+ "id": "DiskConfiguration", |
+ "properties": { |
+ "bootDiskSizeGb": { |
+ "description": "Optional Size in GB of the boot disk (default is 500GB).", |
+ "format": "int32", |
+ "type": "integer" |
}, |
- "loggingConfiguration": { |
- "$ref": "LoggingConfiguration", |
- "description": "[Optional] The runtime log configuration for job execution." |
+ "numLocalSsds": { |
+ "description": "Optional Number of attached SSDs, from 0 to 4 (default is 0). If SSDs are not attached, the boot disk is used to store runtime logs and HDFS data. If one or more SSDs are attached, this runtime bulk data is spread across them, and the boot disk contains only basic configuration and installed binaries.", |
+ "format": "int32", |
+ "type": "integer" |
} |
}, |
"type": "object" |
}, |
- "HiveJob": { |
- "description": "A Cloud Dataproc job for running Hive queries on YARN.", |
- "id": "HiveJob", |
+ "JobStatus": { |
+ "description": "Cloud Dataproc job status.", |
+ "id": "JobStatus", |
"properties": { |
- "queryFileUri": { |
- "description": "The HCFS URI of the script that contains Hive queries.", |
+ "state": { |
+ "description": "Required A state message specifying the overall job state.", |
+ "enum": [ |
+ "STATE_UNSPECIFIED", |
+ "PENDING", |
+ "SETUP_DONE", |
+ "RUNNING", |
+ "CANCEL_PENDING", |
+ "CANCEL_STARTED", |
+ "CANCELLED", |
+ "DONE", |
+ "ERROR", |
+ "ATTEMPT_FAILURE" |
+ ], |
+ "enumDescriptions": [ |
+ "The job state is unknown.", |
+ "The job is pending; it has been submitted, but is not yet running.", |
+ "Job has been received by the service and completed initial setup; it will shortly be submitted to the cluster.", |
+ "The job is running on the cluster.", |
+ "A CancelJob request has been received, but is pending.", |
+ "Transient in-flight resources have been canceled, and the request to cancel the running job has been issued to the cluster.", |
+ "The job cancelation was successful.", |
+ "The job has completed successfully.", |
+ "The job has completed, but encountered an error.", |
+ "Job attempt has failed. The detail field contains failure details for this attempt.Applies to restartable jobs only." |
+ ], |
"type": "string" |
}, |
- "queryList": { |
- "$ref": "QueryList", |
- "description": "A list of queries." |
- }, |
- "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" |
- }, |
- "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" |
+ "details": { |
+ "description": "Optional Job state details, such as an error description if the state is <code>ERROR</code>.", |
+ "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" |
+ "stateStartTime": { |
+ "description": "Output-only The time when this state was entered.", |
+ "format": "google-datetime", |
+ "type": "string" |
} |
}, |
"type": "object" |
}, |
- "QueryList": { |
- "description": "A list of queries to run on a cluster.", |
- "id": "QueryList", |
+ "ClusterOperationStatus": { |
+ "description": "The status of the operation.", |
+ "id": "ClusterOperationStatus", |
"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: \"hiveJob\": { \"queryList\": { \"queries\": [ \"query1\", \"query2\", \"query3;query4\", ] } }", |
- "items": { |
- "type": "string" |
- }, |
- "type": "array" |
+ "state": { |
+ "description": "Output-only A message containing the operation state.", |
+ "enum": [ |
+ "UNKNOWN", |
+ "PENDING", |
+ "RUNNING", |
+ "DONE" |
+ ], |
+ "enumDescriptions": [ |
+ "Unused.", |
+ "The operation has been created.", |
+ "The operation is running.", |
+ "The operation is done; either cancelled or completed." |
+ ], |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "PigJob": { |
- "description": "A Cloud Dataproc job for running Pig queries on YARN.", |
- "id": "PigJob", |
+ "HadoopJob": { |
+ "description": "A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN.", |
+ "id": "HadoopJob", |
"properties": { |
- "queryFileUri": { |
- "description": "The HCFS URI of the script that contains the Pig queries.", |
- "type": "string" |
- }, |
- "queryList": { |
- "$ref": "QueryList", |
- "description": "A list of queries." |
- }, |
- "continueOnFailure": { |
- "description": "[Optional] Whether to continue executing queries if a query fails. The default value is `false`. Setting to `true` can be useful when executing independent parallel queries.", |
- "type": "boolean" |
- }, |
- "scriptVariables": { |
- "additionalProperties": { |
+ "jarFileUris": { |
+ "description": "Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.", |
+ "items": { |
"type": "string" |
}, |
- "description": "[Optional] Mapping of query variable names to values (equivalent to the Pig command: `name=[value]`).", |
- "type": "object" |
+ "type": "array" |
+ }, |
+ "loggingConfiguration": { |
+ "$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 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.", |
+ "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" |
}, |
- "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.", |
+ "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.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
- "loggingConfiguration": { |
- "$ref": "LoggingConfiguration", |
- "description": "[Optional] The runtime log configuration for job execution." |
- } |
- }, |
- "type": "object" |
- }, |
- "SparkSqlJob": { |
- "description": "A Cloud Dataproc job for running Spark SQL queries.", |
- "id": "SparkSqlJob", |
- "properties": { |
- "queryFileUri": { |
- "description": "The HCFS URI of the script that contains SQL queries.", |
- "type": "string" |
- }, |
- "queryList": { |
- "$ref": "QueryList", |
- "description": "A list of queries." |
- }, |
- "scriptVariables": { |
- "additionalProperties": { |
+ "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.", |
+ "items": { |
"type": "string" |
}, |
- "description": "[Optional] Mapping of query variable names to values (equivalent to the Spark SQL command: SET `name=\"value\";`).", |
- "type": "object" |
+ "type": "array" |
}, |
- "properties": { |
- "additionalProperties": { |
- "type": "string" |
- }, |
- "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" |
+ "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" |
}, |
- "jarFileUris": { |
- "description": "[Optional] HCFS URIs of jar files to be added to the Spark CLASSPATH.", |
+ "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.", |
"items": { |
"type": "string" |
}, |
"type": "array" |
}, |
- "loggingConfiguration": { |
- "$ref": "LoggingConfiguration", |
- "description": "[Optional] The runtime log configuration for job execution." |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "JobStatus": { |
- "description": "Cloud Dataproc job status.", |
- "id": "JobStatus", |
+ "QueryList": { |
+ "description": "A list of queries to run on a cluster.", |
+ "id": "QueryList", |
"properties": { |
- "state": { |
- "description": "[Required] A state message specifying the overall job state.", |
- "enum": [ |
- "STATE_UNSPECIFIED", |
- "PENDING", |
- "SETUP_DONE", |
- "RUNNING", |
- "CANCEL_PENDING", |
- "CANCEL_STARTED", |
- "CANCELLED", |
- "DONE", |
- "ERROR" |
- ], |
- "type": "string" |
- }, |
- "details": { |
- "description": "[Optional] Job state details, such as an error description if the state is ERROR.", |
- "type": "string" |
- }, |
- "stateStartTime": { |
- "description": "[Output-only] The time when this state was entered.", |
- "type": "string" |
+ "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", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
} |
}, |
"type": "object" |
}, |
"YarnApplication": { |
- "description": "A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto.", |
+ "description": "A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.", |
"id": "YarnApplication", |
"properties": { |
- "name": { |
- "description": "[Required] The application name.", |
- "type": "string" |
+ "progress": { |
+ "description": "Required The numerical progress of the application, from 1 to 100.", |
+ "format": "float", |
+ "type": "number" |
}, |
"state": { |
- "description": "[Required] The application state.", |
+ "description": "Required The application state.", |
"enum": [ |
"STATE_UNSPECIFIED", |
"NEW", |
@@ -1479,252 +1538,337 @@ |
"FAILED", |
"KILLED" |
], |
+ "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." |
+ ], |
"type": "string" |
}, |
- "progress": { |
- "description": "[Required] The numerical progress of the application, from 1 to 100.", |
- "format": "float", |
- "type": "number" |
+ "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.", |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "ListJobsResponse": { |
- "description": "A list of jobs in a project.", |
- "id": "ListJobsResponse", |
+ "DiagnoseClusterRequest": { |
+ "description": "A request to collect cluster diagnostic information.", |
+ "id": "DiagnoseClusterRequest", |
+ "properties": {}, |
+ "type": "object" |
+ }, |
+ "ClusterOperationMetadata": { |
+ "description": "Metadata describing the operation.", |
+ "id": "ClusterOperationMetadata", |
"properties": { |
- "jobs": { |
- "description": "[Output-only] Jobs list.", |
+ "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.", |
"items": { |
- "$ref": "Job" |
+ "type": "string" |
}, |
"type": "array" |
}, |
- "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 ListJobsRequest.", |
+ "labels": { |
+ "additionalProperties": { |
+ "type": "string" |
+ }, |
+ "description": "Output-only Labels associated with the operation", |
+ "type": "object" |
+ }, |
+ "status": { |
+ "$ref": "ClusterOperationStatus", |
+ "description": "Output-only Current operation status." |
+ }, |
+ "statusHistory": { |
+ "description": "Output-only The previous operation status.", |
+ "items": { |
+ "$ref": "ClusterOperationStatus" |
+ }, |
+ "type": "array" |
+ }, |
+ "clusterUuid": { |
+ "description": "Output-only Cluster UUID for the operation.", |
+ "type": "string" |
+ }, |
+ "clusterName": { |
+ "description": "Output-only Name of the cluster for the operation.", |
"type": "string" |
} |
}, |
"type": "object" |
}, |
- "CancelJobRequest": { |
- "description": "A request to cancel a job.", |
- "id": "CancelJobRequest", |
- "type": "object" |
- }, |
"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: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } The JSON representation for `Empty` is empty JSON object `{}`.", |
+ "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 {}.", |
"id": "Empty", |
+ "properties": {}, |
"type": "object" |
}, |
- "ListOperationsResponse": { |
- "description": "The response message for Operations.ListOperations.", |
- "id": "ListOperationsResponse", |
+ "HiveJob": { |
+ "description": "A Cloud Dataproc job for running Hive queries on YARN.", |
+ "id": "HiveJob", |
"properties": { |
- "operations": { |
- "description": "A list of operations that matches the specified filter in the request.", |
+ "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": { |
+ "$ref": "QueryList", |
+ "description": "A list of queries." |
+ }, |
+ "jarFileUris": { |
+ "description": "Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.", |
"items": { |
- "$ref": "Operation" |
+ "type": "string" |
}, |
"type": "array" |
}, |
- "nextPageToken": { |
- "description": "The standard List next-page token.", |
- "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" |
} |
}, |
"type": "object" |
}, |
- "CancelOperationRequest": { |
- "description": "The request message for Operations.CancelOperation.", |
- "id": "CancelOperationRequest", |
- "type": "object" |
- }, |
"DiagnoseClusterResults": { |
"description": "The location of diagnostic output.", |
"id": "DiagnoseClusterResults", |
"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.", |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "ClusterOperationMetadata": { |
- "description": "Metadata describing the operation.", |
- "id": "ClusterOperationMetadata", |
+ "SoftwareConfiguration": { |
+ "description": "Specifies the selection and configuration of software inside the cluster.", |
+ "id": "SoftwareConfiguration", |
"properties": { |
- "clusterName": { |
- "description": "[Output-only] Name of the cluster for the operation.", |
+ "imageVersion": { |
+ "description": "Optional The version of software inside the cluster. It must match the regular expression [0-9]+\\.[0-9]+. If unspecified, it defaults to the latest version (see Cloud Dataproc Versioning).", |
"type": "string" |
}, |
- "clusterUuid": { |
- "description": "[Output-only] Cluster UUID for the operation.", |
+ "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" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "PySparkJob": { |
+ "description": "A Cloud Dataproc job for running PySpark applications on YARN.", |
+ "id": "PySparkJob", |
+ "properties": { |
+ "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.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "pythonFileUris": { |
+ "description": "Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ }, |
+ "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" |
}, |
- "status": { |
- "$ref": "ClusterOperationStatus", |
- "description": "[Output-only] Current operation status." |
+ "archiveUris": { |
+ "description": "Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
}, |
- "statusHistory": { |
- "description": "[Output-only] The previous operation status.", |
+ "jarFileUris": { |
+ "description": "Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.", |
"items": { |
- "$ref": "ClusterOperationStatus" |
+ "type": "string" |
}, |
"type": "array" |
}, |
- "operationType": { |
- "description": "[Output-only] The operation type.", |
- "type": "string" |
+ "loggingConfiguration": { |
+ "$ref": "LoggingConfiguration", |
+ "description": "Optional The runtime log configuration for job execution." |
}, |
- "description": { |
- "description": "[Output-only] Short description of operation.", |
- "type": "string" |
+ "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" |
}, |
- "labels": { |
+ "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.", |
+ "items": { |
+ "type": "string" |
+ }, |
+ "type": "array" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "ClusterMetrics": { |
+ "description": "Contains cluster daemon metrics, such as HDFS and YARN stats.", |
+ "id": "ClusterMetrics", |
+ "properties": { |
+ "hdfsMetrics": { |
"additionalProperties": { |
+ "format": "int64", |
"type": "string" |
}, |
- "description": "[Output-only] labels associated with the operation", |
+ "description": "The HDFS metrics.", |
+ "type": "object" |
+ }, |
+ "yarnMetrics": { |
+ "additionalProperties": { |
+ "format": "int64", |
+ "type": "string" |
+ }, |
+ "description": "The YARN metrics.", |
"type": "object" |
} |
}, |
"type": "object" |
}, |
- "ClusterOperationStatus": { |
- "description": "The status of the operation.", |
- "id": "ClusterOperationStatus", |
+ "ClusterConfiguration": { |
+ "description": "The cluster configuration.", |
+ "id": "ClusterConfiguration", |
"properties": { |
- "state": { |
- "description": "[Output-only] A message containing the operation state.", |
- "enum": [ |
- "UNKNOWN", |
- "PENDING", |
- "RUNNING", |
- "DONE" |
- ], |
- "type": "string" |
+ "secondaryWorkerConfiguration": { |
+ "$ref": "InstanceGroupConfiguration", |
+ "description": "Optional The Google Compute Engine configuration settings for additional worker instances in a cluster." |
}, |
- "innerState": { |
- "description": "[Output-only] A message containing the detailed operation state.", |
- "type": "string" |
+ "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 <code>role</code> 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", |
+ "items": { |
+ "$ref": "NodeInitializationAction" |
+ }, |
+ "type": "array" |
}, |
- "details": { |
- "description": "[Output-only]A message containing any operation metadata details.", |
- "type": "string" |
+ "workerConfiguration": { |
+ "$ref": "InstanceGroupConfiguration", |
+ "description": "Optional The Google Compute Engine configuration settings for worker instances in a cluster." |
}, |
- "stateStartTime": { |
- "description": "[Output-only] The time this state was entered.", |
+ "softwareConfiguration": { |
+ "$ref": "SoftwareConfiguration", |
+ "description": "Optional The configuration settings for software inside the cluster." |
+ }, |
+ "gceClusterConfiguration": { |
+ "$ref": "GceClusterConfiguration", |
+ "description": "Required 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, and then it will create and manage this project-level, per-location bucket for you.", |
"type": "string" |
+ }, |
+ "masterConfiguration": { |
+ "$ref": "InstanceGroupConfiguration", |
+ "description": "Optional The Google Compute Engine configuration settings for the master instance in a cluster." |
} |
}, |
"type": "object" |
}, |
- "DiagnoseClusterOutputLocation": { |
- "description": "The location where output from diagnostic command can be found.", |
- "id": "DiagnoseClusterOutputLocation", |
+ "LoggingConfiguration": { |
+ "description": "The runtime logging configuration of the job.", |
+ "id": "LoggingConfiguration", |
"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" |
+ "driverLogLevels": { |
+ "additionalProperties": { |
+ "enum": [ |
+ "LEVEL_UNSPECIFIED", |
+ "ALL", |
+ "TRACE", |
+ "DEBUG", |
+ "INFO", |
+ "WARN", |
+ "ERROR", |
+ "FATAL", |
+ "OFF" |
+ ], |
+ "type": "string" |
+ }, |
+ "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" |
} |
}, |
"type": "object" |
}, |
- "OperationMetadata": { |
- "description": "Metadata describing the operation.", |
- "id": "OperationMetadata", |
+ "InstanceGroupConfiguration": { |
+ "description": "The configuration settings for Google Compute Engine resources in an instance group, such as a master or worker group.", |
+ "id": "InstanceGroupConfiguration", |
"properties": { |
- "state": { |
- "description": "A message containing the operation state.", |
- "enum": [ |
- "UNKNOWN", |
- "PENDING", |
- "RUNNING", |
- "DONE" |
- ], |
- "type": "string" |
- }, |
- "innerState": { |
- "description": "A message containing the detailed operation state.", |
- "type": "string" |
- }, |
- "details": { |
- "description": "A message containing any operation metadata details.", |
- "type": "string" |
- }, |
- "insertTime": { |
- "description": "The time that the operation was requested.", |
- "type": "string" |
- }, |
- "startTime": { |
- "description": "The time that the operation was started by the server.", |
- "type": "string" |
+ "diskConfiguration": { |
+ "$ref": "DiskConfiguration", |
+ "description": "Disk option configuration settings." |
}, |
- "endTime": { |
- "description": "The time that the operation completed.", |
- "type": "string" |
+ "isPreemptible": { |
+ "description": "Specifies that this instance group contains Preemptible Instances.", |
+ "type": "boolean" |
}, |
- "clusterName": { |
- "description": "Name of the cluster for the operation.", |
+ "imageUri": { |
+ "description": "Output-only The Google Compute Engine image resource used for cluster instances. Inferred from SoftwareConfiguration.image_version.", |
"type": "string" |
}, |
- "clusterUuid": { |
- "description": "Cluster UUId for the operation.", |
+ "machineTypeUri": { |
+ "description": "The Google Compute Engine machine type used for cluster instances. Example: https://www.googleapis.com/compute/v1/projects/[project_id]/zones/us-east1-a/machineTypes/n1-standard-2.", |
"type": "string" |
}, |
- "status": { |
- "$ref": "OperationStatus", |
- "description": "[Output-only] Current operation status." |
+ "managedGroupConfiguration": { |
+ "$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." |
}, |
- "statusHistory": { |
- "description": "[Output-only] Previous operation status.", |
+ "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).", |
"items": { |
- "$ref": "OperationStatus" |
+ "type": "string" |
}, |
"type": "array" |
}, |
- "operationType": { |
- "description": "[Output-only] The operation type.", |
- "type": "string" |
- }, |
- "description": { |
- "description": "[Output-only] Short description of operation.", |
- "type": "string" |
- } |
- }, |
- "type": "object" |
- }, |
- "OperationStatus": { |
- "description": "The status of the operation.", |
- "id": "OperationStatus", |
- "properties": { |
- "state": { |
- "description": "A message containing the operation state.", |
- "enum": [ |
- "UNKNOWN", |
- "PENDING", |
- "RUNNING", |
- "DONE" |
- ], |
- "type": "string" |
- }, |
- "innerState": { |
- "description": "A message containing the detailed operation state.", |
- "type": "string" |
- }, |
- "details": { |
- "description": "A message containing any operation metadata details.", |
- "type": "string" |
- }, |
- "stateStartTime": { |
- "description": "The time this state was entered.", |
- "type": "string" |
+ "numInstances": { |
+ "description": "The number of VM instances in the instance group. For master instance groups, must be set to 1.", |
+ "format": "int32", |
+ "type": "integer" |
} |
}, |
"type": "object" |