blob: 5f49ecbbd7e0b72b98ba799a8cf47ba9e24d45f1 [file] [log] [blame]
{
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
},
"https://www.googleapis.com/auth/compute": {
"description": "View and manage your Google Compute Engine resources"
},
"https://www.googleapis.com/auth/compute.readonly": {
"description": "View your Google Compute Engine resources"
},
"https://www.googleapis.com/auth/userinfo.email": {
"description": "View your email address"
}
}
}
},
"basePath": "",
"baseUrl": "https://dataflow.googleapis.com/",
"batchPath": "batch",
"description": "Manages Google Cloud Dataflow projects on Google Cloud Platform.",
"discoveryVersion": "v1",
"documentationLink": "https://cloud.google.com/dataflow",
"icons": {
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
"id": "dataflow:v1b3",
"kind": "discovery#restDescription",
"name": "dataflow",
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
"$.xgafv": {
"description": "V1 error format.",
"enum": [
"1",
"2"
],
"enumDescriptions": [
"v1 error format",
"v2 error format"
],
"location": "query",
"type": "string"
},
"access_token": {
"description": "OAuth access token.",
"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"
},
"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"
},
"prettyPrint": {
"default": "true",
"description": "Returns response with indentations and line breaks.",
"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.",
"location": "query",
"type": "string"
},
"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\").",
"location": "query",
"type": "string"
}
},
"protocol": "rest",
"resources": {
"projects": {
"methods": {
"workerMessages": {
"description": "Send a worker_message to the service.",
"flatPath": "v1b3/projects/{projectId}/WorkerMessages",
"httpMethod": "POST",
"id": "dataflow.projects.workerMessages",
"parameterOrder": [
"projectId"
],
"parameters": {
"projectId": {
"description": "The project to send the WorkerMessages to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/WorkerMessages",
"request": {
"$ref": "SendWorkerMessagesRequest"
},
"response": {
"$ref": "SendWorkerMessagesResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
},
"resources": {
"jobs": {
"methods": {
"aggregated": {
"description": "List the jobs of a project across all regions.",
"flatPath": "v1b3/projects/{projectId}/jobs:aggregated",
"httpMethod": "GET",
"id": "dataflow.projects.jobs.aggregated",
"parameterOrder": [
"projectId"
],
"parameters": {
"filter": {
"description": "The kind of filter to use.",
"enum": [
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"location": "query",
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "query",
"type": "string"
},
"pageSize": {
"description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "The project which owns the jobs.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs:aggregated",
"response": {
"$ref": "ListJobsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"create": {
"description": "Creates a Cloud Dataflow job.",
"flatPath": "v1b3/projects/{projectId}/jobs",
"httpMethod": "POST",
"id": "dataflow.projects.jobs.create",
"parameterOrder": [
"projectId"
],
"parameters": {
"location": {
"description": "The location that contains this job.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"replaceJobId": {
"description": "Deprecated. This field is now in the Job message.",
"location": "query",
"type": "string"
},
"view": {
"description": "The level of information requested in response.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs",
"request": {
"$ref": "Job"
},
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"get": {
"description": "Gets the state of the specified Cloud Dataflow job.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}",
"httpMethod": "GET",
"id": "dataflow.projects.jobs.get",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job ID.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "The level of information requested in response.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}",
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"getMetrics": {
"description": "Request the job status.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
"httpMethod": "GET",
"id": "dataflow.projects.jobs.getMetrics",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job to get messages for.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "A project id.",
"location": "path",
"required": true,
"type": "string"
},
"startTime": {
"description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
"format": "google-datetime",
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics",
"response": {
"$ref": "JobMetrics"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"list": {
"description": "List the jobs of a project in a given region.",
"flatPath": "v1b3/projects/{projectId}/jobs",
"httpMethod": "GET",
"id": "dataflow.projects.jobs.list",
"parameterOrder": [
"projectId"
],
"parameters": {
"filter": {
"description": "The kind of filter to use.",
"enum": [
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"location": "query",
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "query",
"type": "string"
},
"pageSize": {
"description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "The project which owns the jobs.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs",
"response": {
"$ref": "ListJobsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"snapshot": {
"description": "Snapshot the state of a streaming job.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}:snapshot",
"httpMethod": "POST",
"id": "dataflow.projects.jobs.snapshot",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job to be snapshotted.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project which owns the job to be snapshotted.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}:snapshot",
"request": {
"$ref": "SnapshotJobRequest"
},
"response": {
"$ref": "Snapshot"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"update": {
"description": "Updates the state of an existing Cloud Dataflow job.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}",
"httpMethod": "PUT",
"id": "dataflow.projects.jobs.update",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job ID.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}",
"request": {
"$ref": "Job"
},
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
},
"resources": {
"debug": {
"methods": {
"getConfig": {
"description": "Get encoded debug configuration for component. Not cacheable.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
"httpMethod": "POST",
"id": "dataflow.projects.jobs.debug.getConfig",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job id.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project id.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig",
"request": {
"$ref": "GetDebugConfigRequest"
},
"response": {
"$ref": "GetDebugConfigResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"sendCapture": {
"description": "Send encoded debug capture data for component.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
"httpMethod": "POST",
"id": "dataflow.projects.jobs.debug.sendCapture",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job id.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project id.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture",
"request": {
"$ref": "SendDebugCaptureRequest"
},
"response": {
"$ref": "SendDebugCaptureResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
},
"messages": {
"methods": {
"list": {
"description": "Request the job status.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
"httpMethod": "GET",
"id": "dataflow.projects.jobs.messages.list",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"endTime": {
"description": "Return only messages with timestamps \u003c end_time. The default is now\n(i.e. return up to the latest messages available).",
"format": "google-datetime",
"location": "query",
"type": "string"
},
"jobId": {
"description": "The job to get messages about.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"location": "query",
"type": "string"
},
"minimumImportance": {
"description": "Filter to only get messages with importance \u003e= level",
"enum": [
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"location": "query",
"type": "string"
},
"pageSize": {
"description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "A project id.",
"location": "path",
"required": true,
"type": "string"
},
"startTime": {
"description": "If specified, return only messages with timestamps \u003e= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
"format": "google-datetime",
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/messages",
"response": {
"$ref": "ListJobMessagesResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
},
"workItems": {
"methods": {
"lease": {
"description": "Leases a dataflow WorkItem to run.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
"httpMethod": "POST",
"id": "dataflow.projects.jobs.workItems.lease",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "Identifies the workflow job this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "Identifies the project this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease",
"request": {
"$ref": "LeaseWorkItemRequest"
},
"response": {
"$ref": "LeaseWorkItemResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"reportStatus": {
"description": "Reports the status of dataflow WorkItems leased by a worker.",
"flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus",
"httpMethod": "POST",
"id": "dataflow.projects.jobs.workItems.reportStatus",
"parameterOrder": [
"projectId",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job which the WorkItem is part of.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project which owns the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus",
"request": {
"$ref": "ReportWorkItemStatusRequest"
},
"response": {
"$ref": "ReportWorkItemStatusResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
}
}
},
"locations": {
"methods": {
"workerMessages": {
"description": "Send a worker_message to the service.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/WorkerMessages",
"httpMethod": "POST",
"id": "dataflow.projects.locations.workerMessages",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"location": {
"description": "The location which contains the job",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project to send the WorkerMessages to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/WorkerMessages",
"request": {
"$ref": "SendWorkerMessagesRequest"
},
"response": {
"$ref": "SendWorkerMessagesResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
},
"resources": {
"jobs": {
"methods": {
"create": {
"description": "Creates a Cloud Dataflow job.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs",
"httpMethod": "POST",
"id": "dataflow.projects.locations.jobs.create",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"location": {
"description": "The location that contains this job.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"replaceJobId": {
"description": "Deprecated. This field is now in the Job message.",
"location": "query",
"type": "string"
},
"view": {
"description": "The level of information requested in response.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs",
"request": {
"$ref": "Job"
},
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"get": {
"description": "Gets the state of the specified Cloud Dataflow job.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"httpMethod": "GET",
"id": "dataflow.projects.locations.jobs.get",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job ID.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "The level of information requested in response.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"getMetrics": {
"description": "Request the job status.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
"httpMethod": "GET",
"id": "dataflow.projects.locations.jobs.getMetrics",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job to get messages for.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "A project id.",
"location": "path",
"required": true,
"type": "string"
},
"startTime": {
"description": "Return only metric data that has changed since this time.\nDefault is to return all information about all metrics for the job.",
"format": "google-datetime",
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
"response": {
"$ref": "JobMetrics"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"list": {
"description": "List the jobs of a project in a given region.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs",
"httpMethod": "GET",
"id": "dataflow.projects.locations.jobs.list",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"filter": {
"description": "The kind of filter to use.",
"enum": [
"UNKNOWN",
"ALL",
"TERMINATED",
"ACTIVE"
],
"location": "query",
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "path",
"required": true,
"type": "string"
},
"pageSize": {
"description": "If there are many jobs, limit response to at most this many.\nThe actual number of jobs returned will be the lesser of max_responses\nand an unspecified server-defined limit.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "Set this to the 'next_page_token' field of a previous response\nto request additional results in a long list.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "The project which owns the jobs.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "Level of information requested in response. Default is `JOB_VIEW_SUMMARY`.",
"enum": [
"JOB_VIEW_UNKNOWN",
"JOB_VIEW_SUMMARY",
"JOB_VIEW_ALL",
"JOB_VIEW_DESCRIPTION"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs",
"response": {
"$ref": "ListJobsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"snapshot": {
"description": "Snapshot the state of a streaming job.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}:snapshot",
"httpMethod": "POST",
"id": "dataflow.projects.locations.jobs.snapshot",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job to be snapshotted.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project which owns the job to be snapshotted.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}:snapshot",
"request": {
"$ref": "SnapshotJobRequest"
},
"response": {
"$ref": "Snapshot"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"update": {
"description": "Updates the state of an existing Cloud Dataflow job.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"httpMethod": "PUT",
"id": "dataflow.projects.locations.jobs.update",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job ID.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location that contains this job.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
"request": {
"$ref": "Job"
},
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
},
"resources": {
"debug": {
"methods": {
"getConfig": {
"description": "Get encoded debug configuration for component. Not cacheable.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getConfig",
"httpMethod": "POST",
"id": "dataflow.projects.locations.jobs.debug.getConfig",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job id.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project id.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getConfig",
"request": {
"$ref": "GetDebugConfigRequest"
},
"response": {
"$ref": "GetDebugConfigResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"sendCapture": {
"description": "Send encoded debug capture data for component.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/sendCapture",
"httpMethod": "POST",
"id": "dataflow.projects.locations.jobs.debug.sendCapture",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job id.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project id.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/sendCapture",
"request": {
"$ref": "SendDebugCaptureRequest"
},
"response": {
"$ref": "SendDebugCaptureResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
},
"messages": {
"methods": {
"list": {
"description": "Request the job status.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
"httpMethod": "GET",
"id": "dataflow.projects.locations.jobs.messages.list",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"endTime": {
"description": "Return only messages with timestamps \u003c end_time. The default is now\n(i.e. return up to the latest messages available).",
"format": "google-datetime",
"location": "query",
"type": "string"
},
"jobId": {
"description": "The job to get messages about.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"location": "path",
"required": true,
"type": "string"
},
"minimumImportance": {
"description": "Filter to only get messages with importance \u003e= level",
"enum": [
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"location": "query",
"type": "string"
},
"pageSize": {
"description": "If specified, determines the maximum number of messages to\nreturn. If unspecified, the service may choose an appropriate\ndefault, or may return an arbitrarily large number of results.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "If supplied, this should be the value of next_page_token returned\nby an earlier call. This will cause the next page of results to\nbe returned.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "A project id.",
"location": "path",
"required": true,
"type": "string"
},
"startTime": {
"description": "If specified, return only messages with timestamps \u003e= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
"format": "google-datetime",
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
"response": {
"$ref": "ListJobMessagesResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
},
"workItems": {
"methods": {
"lease": {
"description": "Leases a dataflow WorkItem to run.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
"httpMethod": "POST",
"id": "dataflow.projects.locations.jobs.workItems.lease",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "Identifies the workflow job this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "Identifies the project this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease",
"request": {
"$ref": "LeaseWorkItemRequest"
},
"response": {
"$ref": "LeaseWorkItemResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"reportStatus": {
"description": "Reports the status of dataflow WorkItems leased by a worker.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
"httpMethod": "POST",
"id": "dataflow.projects.locations.jobs.workItems.reportStatus",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
"jobId": {
"description": "The job which the WorkItem is part of.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
"description": "The location which contains the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "The project which owns the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
"request": {
"$ref": "ReportWorkItemStatusRequest"
},
"response": {
"$ref": "ReportWorkItemStatusResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
}
}
},
"templates": {
"methods": {
"create": {
"description": "Creates a Cloud Dataflow job from a template.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/templates",
"httpMethod": "POST",
"id": "dataflow.projects.locations.templates.create",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"location": {
"description": "The location to which to direct the request.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/templates",
"request": {
"$ref": "CreateJobFromTemplateRequest"
},
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"get": {
"description": "Get the template associated with a template.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/templates:get",
"httpMethod": "GET",
"id": "dataflow.projects.locations.templates.get",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"gcsPath": {
"description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"location": "query",
"type": "string"
},
"location": {
"description": "The location to which to direct the request.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "The view to retrieve. Defaults to METADATA_ONLY.",
"enum": [
"METADATA_ONLY"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/templates:get",
"response": {
"$ref": "GetTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"launch": {
"description": "Launch a template.",
"flatPath": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
"httpMethod": "POST",
"id": "dataflow.projects.locations.templates.launch",
"parameterOrder": [
"projectId",
"location"
],
"parameters": {
"dynamicTemplate.gcsPath": {
"description": "Path to dynamic template spec file on GCS.\nThe file must be a Json serialized DynamicTemplateFieSpec object.",
"location": "query",
"type": "string"
},
"dynamicTemplate.stagingLocation": {
"description": "Cloud Storage path for staging dependencies.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"location": "query",
"type": "string"
},
"gcsPath": {
"description": "A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"location": "query",
"type": "string"
},
"location": {
"description": "The location to which to direct the request.",
"location": "path",
"required": true,
"type": "string"
},
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"validateOnly": {
"description": "If true, the request is validated but not actually executed.\nDefaults to false.",
"location": "query",
"type": "boolean"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/templates:launch",
"request": {
"$ref": "LaunchTemplateParameters"
},
"response": {
"$ref": "LaunchTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
}
}
},
"templates": {
"methods": {
"create": {
"description": "Creates a Cloud Dataflow job from a template.",
"flatPath": "v1b3/projects/{projectId}/templates",
"httpMethod": "POST",
"id": "dataflow.projects.templates.create",
"parameterOrder": [
"projectId"
],
"parameters": {
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/templates",
"request": {
"$ref": "CreateJobFromTemplateRequest"
},
"response": {
"$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"get": {
"description": "Get the template associated with a template.",
"flatPath": "v1b3/projects/{projectId}/templates:get",
"httpMethod": "GET",
"id": "dataflow.projects.templates.get",
"parameterOrder": [
"projectId"
],
"parameters": {
"gcsPath": {
"description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"location": "query",
"type": "string"
},
"location": {
"description": "The location to which to direct the request.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"view": {
"description": "The view to retrieve. Defaults to METADATA_ONLY.",
"enum": [
"METADATA_ONLY"
],
"location": "query",
"type": "string"
}
},
"path": "v1b3/projects/{projectId}/templates:get",
"response": {
"$ref": "GetTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
},
"launch": {
"description": "Launch a template.",
"flatPath": "v1b3/projects/{projectId}/templates:launch",
"httpMethod": "POST",
"id": "dataflow.projects.templates.launch",
"parameterOrder": [
"projectId"
],
"parameters": {
"dynamicTemplate.gcsPath": {
"description": "Path to dynamic template spec file on GCS.\nThe file must be a Json serialized DynamicTemplateFieSpec object.",
"location": "query",
"type": "string"
},
"dynamicTemplate.stagingLocation": {
"description": "Cloud Storage path for staging dependencies.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"location": "query",
"type": "string"
},
"gcsPath": {
"description": "A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"location": "query",
"type": "string"
},
"location": {
"description": "The location to which to direct the request.",
"location": "query",
"type": "string"
},
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
},
"validateOnly": {
"description": "If true, the request is validated but not actually executed.\nDefaults to false.",
"location": "query",
"type": "boolean"
}
},
"path": "v1b3/projects/{projectId}/templates:launch",
"request": {
"$ref": "LaunchTemplateParameters"
},
"response": {
"$ref": "LaunchTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/compute.readonly",
"https://www.googleapis.com/auth/userinfo.email"
]
}
}
}
}
}
},
"revision": "20181116",
"rootUrl": "https://dataflow.googleapis.com/",
"schemas": {
"ApproximateProgress": {
"description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
"id": "ApproximateProgress",
"properties": {
"percentComplete": {
"description": "Obsolete.",
"format": "float",
"type": "number"
},
"position": {
"$ref": "Position",
"description": "Obsolete."
},
"remainingTime": {
"description": "Obsolete.",
"format": "google-duration",
"type": "string"
}
},
"type": "object"
},
"ApproximateReportedProgress": {
"description": "A progress measurement of a WorkItem by a worker.",
"id": "ApproximateReportedProgress",
"properties": {
"consumedParallelism": {
"$ref": "ReportedParallelism",
"description": "Total amount of parallelism in the portion of input of this task that has\nalready been consumed and is no longer active. In the first two examples\nabove (see remaining_parallelism), the value should be 29 or 2\nrespectively. The sum of remaining_parallelism and consumed_parallelism\nshould equal the total amount of parallelism in this work item. If\nspecified, must be finite."
},
"fractionConsumed": {
"description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
"format": "double",
"type": "number"
},
"position": {
"$ref": "Position",
"description": "A Position within the work to represent a progress."
},
"remainingParallelism": {
"$ref": "ReportedParallelism",
"description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
}
},
"type": "object"
},
"ApproximateSplitRequest": {
"description": "A suggestion by the service to the worker to dynamically split the WorkItem.",
"id": "ApproximateSplitRequest",
"properties": {
"fractionConsumed": {
"description": "A fraction at which to split the work item, from 0.0 (beginning of the\ninput) to 1.0 (end of the input).",
"format": "double",
"type": "number"
},
"position": {
"$ref": "Position",
"description": "A Position at which to split the work item."
}
},
"type": "object"
},
"AutoscalingEvent": {
"description": "A structured message reporting an autoscaling decision made by the Dataflow\nservice.",
"id": "AutoscalingEvent",
"properties": {
"currentNumWorkers": {
"description": "The current number of workers the job has.",
"format": "int64",
"type": "string"
},
"description": {
"$ref": "StructuredMessage",
"description": "A message describing why the system decided to adjust the current\nnumber of workers, why it failed, or why the system decided to\nnot make any changes to the number of workers."
},
"eventType": {
"description": "The type of autoscaling event to report.",
"enum": [
"TYPE_UNKNOWN",
"TARGET_NUM_WORKERS_CHANGED",
"CURRENT_NUM_WORKERS_CHANGED",
"ACTUATION_FAILURE",
"NO_CHANGE"
],
"enumDescriptions": [
"Default type for the enum. Value should never be returned.",
"The TARGET_NUM_WORKERS_CHANGED type should be used when the target\nworker pool size has changed at the start of an actuation. An event\nshould always be specified as TARGET_NUM_WORKERS_CHANGED if it reflects\na change in the target_num_workers.",
"The CURRENT_NUM_WORKERS_CHANGED type should be used when actual worker\npool size has been changed, but the target_num_workers has not changed.",
"The ACTUATION_FAILURE type should be used when we want to report\nan error to the user indicating why the current number of workers\nin the pool could not be changed.\nDisplayed in the current status and history widgets.",
"Used when we want to report to the user a reason why we are\nnot currently adjusting the number of workers.\nShould specify both target_num_workers, current_num_workers and a\ndecision_message."
],
"type": "string"
},
"targetNumWorkers": {
"description": "The target number of workers the worker pool wants to resize to use.",
"format": "int64",
"type": "string"
},
"time": {
"description": "The time this event was emitted to indicate a new target or current\nnum_workers value.",
"format": "google-datetime",
"type": "string"
},
"workerPool": {
"description": "A short and friendly name for the worker pool this event refers to,\npopulated from the value of PoolStageRelation::user_pool_name.",
"type": "string"
}
},
"type": "object"
},
"AutoscalingSettings": {
"description": "Settings for WorkerPool autoscaling.",
"id": "AutoscalingSettings",
"properties": {
"algorithm": {
"description": "The algorithm to use for autoscaling.",
"enum": [
"AUTOSCALING_ALGORITHM_UNKNOWN",
"AUTOSCALING_ALGORITHM_NONE",
"AUTOSCALING_ALGORITHM_BASIC"
],
"enumDescriptions": [
"The algorithm is unknown, or unspecified.",
"Disable autoscaling.",
"Increase worker count over time to reduce job execution time."
],
"type": "string"
},
"maxNumWorkers": {
"description": "The maximum number of workers to cap scaling at.",
"format": "int32",
"type": "integer"
}
},
"type": "object"
},
"BigQueryIODetails": {
"description": "Metadata for a BigQuery connector used by the job.",
"id": "BigQueryIODetails",
"properties": {
"dataset": {
"description": "Dataset accessed in the connection.",
"type": "string"
},
"projectId": {
"description": "Project accessed in the connection.",
"type": "string"
},
"query": {
"description": "Query used to access data in the connection.",
"type": "string"
},
"table": {
"description": "Table accessed in the connection.",
"type": "string"
}
},
"type": "object"
},
"BigTableIODetails": {
"description": "Metadata for a BigTable connector used by the job.",
"id": "BigTableIODetails",
"properties": {
"instanceId": {
"description": "InstanceId accessed in the connection.",
"type": "string"
},
"projectId": {
"description": "ProjectId accessed in the connection.",
"type": "string"
},
"tableId": {
"description": "TableId accessed in the connection.",
"type": "string"
}
},
"type": "object"
},
"CPUTime": {
"description": "Modeled after information exposed by /proc/stat.",
"id": "CPUTime",
"properties": {
"rate": {
"description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
"format": "double",
"type": "number"
},
"timestamp": {
"description": "Timestamp of the measurement.",
"format": "google-datetime",
"type": "string"
},
"totalMs": {
"description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
"format": "uint64",
"type": "string"
}
},
"type": "object"
},
"ComponentSource": {
"description": "Description of an interstitial value between transforms in an execution\nstage.",
"id": "ComponentSource",
"properties": {
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
},
"originalTransformOrCollection": {
"description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
"type": "string"
},
"userName": {
"description": "Human-readable name for this transform; may be user or system generated.",
"type": "string"
}
},
"type": "object"
},
"ComponentTransform": {
"description": "Description of a transform executed as part of an execution stage.",
"id": "ComponentTransform",
"properties": {
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
},
"originalTransform": {
"description": "User name for the original user transform with which this transform is\nmost closely associated.",
"type": "string"
},
"userName": {
"description": "Human-readable name for this transform; may be user or system generated.",
"type": "string"
}
},
"type": "object"
},
"ComputationTopology": {
"description": "All configuration data for a particular Computation.",
"id": "ComputationTopology",
"properties": {
"computationId": {
"description": "The ID of the computation.",
"type": "string"
},
"inputs": {
"description": "The inputs to the computation.",
"items": {
"$ref": "StreamLocation"
},
"type": "array"
},
"keyRanges": {
"description": "The key ranges processed by the computation.",
"items": {
"$ref": "KeyRangeLocation"
},
"type": "array"
},
"outputs": {
"description": "The outputs from the computation.",
"items": {
"$ref": "StreamLocation"
},
"type": "array"
},
"stateFamilies": {
"description": "The state family values.",
"items": {
"$ref": "StateFamilyConfig"
},
"type": "array"
},
"systemStageName": {
"description": "The system stage name.",
"type": "string"
}
},
"type": "object"
},
"ConcatPosition": {
"description": "A position that encapsulates an inner position and an index for the inner\nposition. A ConcatPosition can be used by a reader of a source that\nencapsulates a set of other sources.",
"id": "ConcatPosition",
"properties": {
"index": {
"description": "Index of the inner source.",
"format": "int32",
"type": "integer"
},
"position": {
"$ref": "Position",
"description": "Position within the inner source."
}
},
"type": "object"
},
"CounterMetadata": {
"description": "CounterMetadata includes all static non-name non-value counter attributes.",
"id": "CounterMetadata",
"properties": {
"description": {
"description": "Human-readable description of the counter semantics.",
"type": "string"
},
"kind": {
"description": "Counter aggregation kind.",
"enum": [
"INVALID",
"SUM",
"MAX",
"MIN",
"MEAN",
"OR",
"AND",
"SET",
"DISTRIBUTION",
"LATEST_VALUE"
],
"enumDescriptions": [
"Counter aggregation kind was not set.",
"Aggregated value is the sum of all contributed values.",
"Aggregated value is the max of all contributed values.",
"Aggregated value is the min of all contributed values.",
"Aggregated value is the mean of all contributed values.",
"Aggregated value represents the logical 'or' of all contributed values.",
"Aggregated value represents the logical 'and' of all contributed values.",
"Aggregated value is a set of unique contributed values.",
"Aggregated value captures statistics about a distribution.",
"Aggregated value tracks the latest value of a variable."
],
"type": "string"
},
"otherUnits": {
"description": "A string referring to the unit type.",
"type": "string"
},
"standardUnits": {
"description": "System defined Units, see above enum.",
"enum": [
"BYTES",
"BYTES_PER_SEC",
"MILLISECONDS",
"MICROSECONDS",
"NANOSECONDS",
"TIMESTAMP_MSEC",
"TIMESTAMP_USEC",
"TIMESTAMP_NSEC"
],
"enumDescriptions": [
"Counter returns a value in bytes.",
"Counter returns a value in bytes per second.",
"Counter returns a value in milliseconds.",
"Counter returns a value in microseconds.",
"Counter returns a value in nanoseconds.",
"Counter returns a timestamp in milliseconds.",
"Counter returns a timestamp in microseconds.",
"Counter returns a timestamp in nanoseconds."
],
"type": "string"
}
},
"type": "object"
},
"CounterStructuredName": {
"description": "Identifies a counter within a per-job namespace. Counters whose structured\nnames are the same get merged into a single value for the job.",
"id": "CounterStructuredName",
"properties": {
"componentStepName": {
"description": "Name of the optimized step being executed by the workers.",
"type": "string"
},
"executionStepName": {
"description": "Name of the stage. An execution step contains multiple component steps.",
"type": "string"
},
"inputIndex": {
"description": "Index of an input collection that's being read from/written to as a side\ninput.\nThe index identifies a step's side inputs starting by 1 (e.g. the first\nside input has input_index 1, the third has input_index 3).\nSide inputs are identified by a pair of (original_step_name, input_index).\nThis field helps uniquely identify them.",
"format": "int32",
"type": "integer"
},
"name": {
"description": "Counter name. Not necessarily globally-unique, but unique within the\ncontext of the other fields.\nRequired.",
"type": "string"
},
"origin": {
"description": "One of the standard Origins defined above.",
"enum": [
"SYSTEM",
"USER"
],
"enumDescriptions": [
"Counter was created by the Dataflow system.",
"Counter was created by the user."
],
"type": "string"
},
"originNamespace": {
"description": "A string containing a more specific namespace of the counter's origin.",
"type": "string"
},
"originalRequestingStepName": {
"description": "The step name requesting an operation, such as GBK.\nI.e. the ParDo causing a read/write from shuffle to occur, or a\nread from side inputs.",
"type": "string"
},
"originalStepName": {
"description": "System generated name of the original step in the user's graph, before\noptimization.",
"type": "string"
},
"portion": {
"description": "Portion of this counter, either key or value.",
"enum": [
"ALL",
"KEY",
"VALUE"
],
"enumDescriptions": [
"Counter portion has not been set.",
"Counter reports a key.",
"Counter reports a value."
],
"type": "string"
},
"workerId": {
"description": "ID of a particular worker.",
"type": "string"
}
},
"type": "object"
},
"CounterStructuredNameAndMetadata": {
"description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
"id": "CounterStructuredNameAndMetadata",
"properties": {
"metadata": {
"$ref": "CounterMetadata",
"description": "Metadata associated with a counter"
},
"name": {
"$ref": "CounterStructuredName",
"description": "Structured name of the counter."
}
},
"type": "object"
},
"CounterUpdate": {
"description": "An update to a Counter sent from a worker.",
"id": "CounterUpdate",
"properties": {
"boolean": {
"description": "Boolean value for And, Or.",
"type": "boolean"
},
"cumulative": {
"description": "True if this counter is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this counter is reported\nas a delta.",
"type": "boolean"
},
"distribution": {
"$ref": "DistributionUpdate",
"description": "Distribution data"
},
"floatingPoint": {
"description": "Floating point value for Sum, Max, Min.",
"format": "double",
"type": "number"
},
"floatingPointList": {
"$ref": "FloatingPointList",
"description": "List of floating point numbers, for Set."
},
"floatingPointMean": {
"$ref": "FloatingPointMean",
"description": "Floating point mean aggregation value for Mean."
},
"integer": {
"$ref": "SplitInt64",
"description": "Integer value for Sum, Max, Min."
},
"integerGauge": {
"$ref": "IntegerGauge",
"description": "Gauge data"
},
"integerList": {
"$ref": "IntegerList",
"description": "List of integers, for Set."
},
"integerMean": {
"$ref": "IntegerMean",
"description": "Integer mean aggregation value for Mean."
},
"internal": {
"description": "Value for internally-defined counters used by the Dataflow service.",
"type": "any"
},
"nameAndKind": {
"$ref": "NameAndKind",
"description": "Counter name and aggregation type."
},
"shortId": {
"description": "The service-generated short identifier for this counter.\nThe short_id -\u003e (name, metadata) mapping is constant for the lifetime of\na job.",
"format": "int64",
"type": "string"
},
"stringList": {
"$ref": "StringList",
"description": "List of strings, for Set."
},
"structuredNameAndMetadata": {
"$ref": "CounterStructuredNameAndMetadata",
"description": "Counter structured name and metadata."
}
},
"type": "object"
},
"CreateJobFromTemplateRequest": {
"description": "A request to create a Cloud Dataflow job from a template.",
"id": "CreateJobFromTemplateRequest",
"properties": {
"environment": {
"$ref": "RuntimeEnvironment",
"description": "The runtime environment for the job."
},
"gcsPath": {
"description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
"type": "string"
},
"jobName": {
"description": "Required. The job name to use for the created job.",
"type": "string"
},
"location": {
"description": "The location to which to direct the request.",
"type": "string"
},
"parameters": {
"additionalProperties": {
"type": "string"
},
"description": "The runtime parameters to pass to the job.",
"type": "object"
}
},
"type": "object"
},
"CustomSourceLocation": {
"description": "Identifies the location of a custom souce.",
"id": "CustomSourceLocation",
"properties": {
"stateful": {
"description": "Whether this source is stateful.",
"type": "boolean"
}
},
"type": "object"
},
"DataDiskAssignment": {
"description": "Data disk assignment for a given VM instance.",
"id": "DataDiskAssignment",
"properties": {
"dataDisks": {
"description": "Mounted data disks. The order is important a data disk's 0-based index in\nthis list defines which persistent directory the disk is mounted to, for\nexample the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" },\n{ \"myproject-1014-104817-4c2-harness-0-disk-1\" }.",
"items": {
"type": "string"
},
"type": "array"
},
"vmInstance": {
"description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
"type": "string"
}
},
"type": "object"
},
"DatastoreIODetails": {
"description": "Metadata for a Datastore connector used by the job.",
"id": "DatastoreIODetails",
"properties": {
"namespace": {
"description": "Namespace used in the connection.",
"type": "string"
},
"projectId": {
"description": "ProjectId accessed in the connection.",
"type": "string"
}
},
"type": "object"
},
"DerivedSource": {
"description": "Specification of one of the bundles produced as a result of splitting\na Source (e.g. when executing a SourceSplitRequest, or when\nsplitting an active task using WorkItemStatus.dynamic_source_split),\nrelative to the source being split.",
"id": "DerivedSource",
"properties": {
"derivationMode": {
"description": "What source to base the produced source on (if any).",
"enum": [
"SOURCE_DERIVATION_MODE_UNKNOWN",
"SOURCE_DERIVATION_MODE_INDEPENDENT",
"SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT",
"SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT"
],
"enumDescriptions": [
"The source derivation is unknown, or unspecified.",
"Produce a completely independent Source with no base.",
"Produce a Source based on the Source being split.",
"Produce a Source based on the base of the Source being split."
],
"type": "string"
},
"source": {
"$ref": "Source",
"description": "Specification of the source."
}
},
"type": "object"
},
"Disk": {
"description": "Describes the data disk used by a workflow job.",
"id": "Disk",
"properties": {
"diskType": {
"description": "Disk storage type, as defined by Google Compute Engine. This\nmust be a disk type appropriate to the project and zone in which\nthe workers will run. If unknown or unspecified, the service\nwill attempt to choose a reasonable default.\n\nFor example, the standard persistent disk type is a resource name\ntypically ending in \"pd-standard\". If SSD persistent disks are\navailable, the resource name typically ends with \"pd-ssd\". The\nactual valid values are defined the Google Compute Engine API,\nnot by the Cloud Dataflow API; consult the Google Compute Engine\ndocumentation for more information about determining the set of\navailable disk types for a particular project and zone.\n\nGoogle Compute Engine Disk types are local to a particular\nproject in a particular zone, and so the resource name will\ntypically look something like this:\n\ncompute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard",
"type": "string"
},
"mountPoint": {
"description": "Directory in a VM where disk is mounted.",
"type": "string"
},
"sizeGb": {
"description": "Size of disk in GB. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
"format": "int32",
"type": "integer"
}
},
"type": "object"
},
"DisplayData": {
"description": "Data provided with a pipeline or transform to provide descriptive info.",
"id": "DisplayData",
"properties": {
"boolValue": {
"description": "Contains value if the data is of a boolean type.",
"type": "boolean"
},
"durationValue": {
"description": "Contains value if the data is of duration type.",
"format": "google-duration",
"type": "string"
},
"floatValue": {
"description": "Contains value if the data is of float type.",
"format": "float",
"type": "number"
},
"int64Value": {
"description": "Contains value if the data is of int64 type.",
"format": "int64",
"type": "string"
},
"javaClassValue": {
"description": "Contains value if the data is of java class type.",
"type": "string"
},
"key": {
"description": "The key identifying the display data.\nThis is intended to be used as a label for the display data\nwhen viewed in a dax monitoring system.",
"type": "string"
},
"label": {
"description": "An optional label to display in a dax UI for the element.",
"type": "string"
},
"namespace": {
"description": "The namespace for the key. This is usually a class name or programming\nlanguage namespace (i.e. python module) which defines the display data.\nThis allows a dax monitoring system to specially handle the data\nand perform custom rendering.",
"type": "string"
},
"shortStrValue": {
"description": "A possible additional shorter value to display.\nFor example a java_class_name_value of com.mypackage.MyDoFn\nwill be stored with MyDoFn as the short_str_value and\ncom.mypackage.MyDoFn as the java_class_name value.\nshort_str_value can be displayed and java_class_name_value\nwill be displayed as a tooltip.",
"type": "string"
},
"strValue": {
"description": "Contains value if the data is of string type.",
"type": "string"
},
"timestampValue": {
"description": "Contains value if the data is of timestamp type.",
"format": "google-datetime",
"type": "string"
},
"url": {
"description": "An optional full URL.",
"type": "string"
}
},
"type": "object"
},
"DistributionUpdate": {
"description": "A metric value representing a distribution.",
"id": "DistributionUpdate",
"properties": {
"count": {
"$ref": "SplitInt64",
"description": "The count of the number of elements present in the distribution."
},
"histogram": {
"$ref": "Histogram",
"description": "(Optional) Histogram of value counts for the distribution."
},
"max": {
"$ref": "SplitInt64",
"description": "The maximum value present in the distribution."
},
"min": {
"$ref": "SplitInt64",
"description": "The minimum value present in the distribution."
},
"sum": {
"$ref": "SplitInt64",
"description": "Use an int64 since we'd prefer the added precision. If overflow is a common\nproblem we can detect it and use an additional int64 or a double."
},
"sumOfSquares": {
"description": "Use a double since the sum of squares is likely to overflow int64.",
"format": "double",
"type": "number"
}
},
"type": "object"
},
"DynamicSourceSplit": {
"description": "When a task splits using WorkItemStatus.dynamic_source_split, this\nmessage describes the two parts of the split relative to the\ndescription of the current task's input.",
"id": "DynamicSourceSplit",
"properties": {
"primary": {
"$ref": "DerivedSource",
"description": "Primary part (continued to be processed by worker).\nSpecified relative to the previously-current source.\nBecomes current."
},
"residual": {
"$ref": "DerivedSource",
"description": "Residual part (returned to the pool of work).\nSpecified relative to the previously-current source."
}
},
"type": "object"
},
"Environment": {
"description": "Describes the environment in which a Dataflow Job runs.",
"id": "Environment",
"properties": {
"clusterManagerApiService": {
"description": "The type of cluster manager API to use. If unknown or\nunspecified, the service will attempt to choose a reasonable\ndefault. This should be in the form of the API service name,\ne.g. \"compute.googleapis.com\".",
"type": "string"
},
"dataset": {
"description": "The dataset for the current project where various workflow\nrelated tables are stored.\n\nThe supported resource type is:\n\nGoogle BigQuery:\n bigquery.googleapis.com/{dataset}",
"type": "string"
},
"experiments": {
"description": "The list of experiments to enable.",
"items": {
"type": "string"
},
"type": "array"
},
"internalExperiments": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "Experimental settings.",
"type": "object"
},
"sdkPipelineOptions": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The Cloud Dataflow SDK pipeline options specified by the user. These\noptions are passed through the service and are used to recreate the\nSDK pipeline options on the worker in a language agnostic and platform\nindependent way.",
"type": "object"
},
"serviceAccountEmail": {
"description": "Identity to run virtual machines as. Defaults to the default account.",
"type": "string"
},
"tempStoragePrefix": {
"description": "The prefix of the resources the system should use for temporary\nstorage. The system will append the suffix \"/temp-{JOBNAME} to\nthis resource prefix, where {JOBNAME} is the value of the\njob_name field. The resulting bucket and object prefix is used\nas the prefix of the resources used to store temporary data\nneeded during the job execution. NOTE: This will override the\nvalue in taskrunner_settings.\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"type": "string"
},
"userAgent": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "A description of the process that generated the request.",
"type": "object"
},
"version": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "A structure describing which components and their versions of the service\nare required in order to run the job.",
"type": "object"
},
"workerPools": {
"description": "The worker pools. At least one \"harness\" worker pool must be\nspecified in order for the job to have workers.",
"items": {
"$ref": "WorkerPool"
},
"type": "array"
}
},
"type": "object"
},
"ExecutionStageState": {
"description": "A message describing the state of a particular execution stage.",
"id": "ExecutionStageState",
"properties": {
"currentStateTime": {
"description": "The time at which the stage transitioned to this state.",
"format": "google-datetime",
"type": "string"
},
"executionStageName": {
"description": "The name of the execution stage.",
"type": "string"
},
"executionStageState": {
"description": "Executions stage states allow the same set of values as JobState.",
"enum": [
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING",
"JOB_STATE_QUEUED"
],
"enumDescriptions": [
"The job's run state isn't specified.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"`JOB_STATE_PENDING` indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"`JOB_STATE_CANCELLING` indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to `JOB_STATE_CANCELLED` or `JOB_STATE_FAILED`.",
"`JOB_STATE_QUEUED` indicates that the job has been created but is being\ndelayed until launch. Jobs that are queued may only transition to\n`JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`."
],
"type": "string"
}
},
"type": "object"
},
"ExecutionStageSummary": {
"description": "Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning.",
"id": "ExecutionStageSummary",
"properties": {
"componentSource": {
"description": "Collections produced and consumed by component transforms of this stage.",
"items": {
"$ref": "ComponentSource"
},
"type": "array"
},
"componentTransform": {
"description": "Transforms that comprise this execution stage.",
"items": {
"$ref": "ComponentTransform"
},
"type": "array"
},
"id": {
"description": "Dataflow service generated id for this stage.",
"type": "string"
},
"inputSource": {
"description": "Input sources for this stage.",
"items": {
"$ref": "StageSource"
},
"type": "array"
},
"kind": {
"description": "Type of tranform this stage is executing.",
"enum": [
"UNKNOWN_KIND",
"PAR_DO_KIND",
"GROUP_BY_KEY_KIND",
"FLATTEN_KIND",
"READ_KIND",
"WRITE_KIND",
"CONSTANT_KIND",
"SINGLETON_KIND",
"SHUFFLE_KIND"
],
"enumDescriptions": [
"Unrecognized transform type.",
"ParDo transform.",
"Group By Key transform.",
"Flatten transform.",
"Read transform.",
"Write transform.",
"Constructs from a constant value, such as with Create.of.",
"Creates a Singleton view of a collection.",
"Opening or closing a shuffle session, often as part of a GroupByKey."
],
"type": "string"
},
"name": {
"description": "Dataflow service generated name for this stage.",
"type": "string"
},
"outputSource": {
"description": "Output sources for this stage.",
"items": {
"$ref": "StageSource"
},
"type": "array"
}
},
"type": "object"
},
"FailedLocation": {
"description": "Indicates which location failed to respond to a request for data.",
"id": "FailedLocation",
"properties": {
"name": {
"description": "The name of the failed location.",
"type": "string"
}
},
"type": "object"
},
"FileIODetails": {
"description": "Metadata for a File connector used by the job.",
"id": "FileIODetails",
"properties": {
"filePattern": {
"description": "File Pattern used to access files by the connector.",
"type": "string"
}
},
"type": "object"
},
"FlattenInstruction": {
"description": "An instruction that copies its inputs (zero or more) to its (single) output.",
"id": "FlattenInstruction",
"properties": {
"inputs": {
"description": "Describes the inputs to the flatten instruction.",
"items": {
"$ref": "InstructionInput"
},
"type": "array"
}
},
"type": "object"
},
"FloatingPointList": {
"description": "A metric value representing a list of floating point numbers.",
"id": "FloatingPointList",
"properties": {
"elements": {
"description": "Elements of the list.",
"items": {
"format": "double",
"type": "number"
},
"type": "array"
}
},
"type": "object"
},
"FloatingPointMean": {
"description": "A representation of a floating point mean metric contribution.",
"id": "FloatingPointMean",
"properties": {
"count": {
"$ref": "SplitInt64",
"description": "The number of values being aggregated."
},
"sum": {
"description": "The sum of all values being aggregated.",
"format": "double",
"type": "number"
}
},
"type": "object"
},
"GetDebugConfigRequest": {
"description": "Request to get updated debug configuration for component.",
"id": "GetDebugConfigRequest",
"properties": {
"componentId": {
"description": "The internal component id for which debug configuration is\nrequested.",
"type": "string"
},
"location": {
"description": "The location which contains the job specified by job_id.",
"type": "string"
},
"workerId": {
"description": "The worker id, i.e., VM hostname.",
"type": "string"
}
},
"type": "object"
},
"GetDebugConfigResponse": {
"description": "Response to a get debug configuration request.",
"id": "GetDebugConfigResponse",
"properties": {
"config": {
"description": "The encoded debug configuration for the requested component.",
"type": "string"
}
},
"type": "object"
},
"GetTemplateResponse": {
"description": "The response to a GetTemplate request.",
"id": "GetTemplateResponse",
"properties": {
"metadata": {
"$ref": "TemplateMetadata",
"description": "The template metadata describing the template name, available\nparameters, etc."
},
"status": {
"$ref": "Status",
"description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
}
},
"type": "object"
},
"Histogram": {
"description": "Histogram of value counts for a distribution.\n\nBuckets have an inclusive lower bound and exclusive upper bound and use\n\"1,2,5 bucketing\": The first bucket range is from [0,1) and all subsequent\nbucket boundaries are powers of ten multiplied by 1, 2, or 5. Thus, bucket\nboundaries are 0, 1, 2, 5, 10, 20, 50, 100, 200, 500, 1000, ...\nNegative values are not supported.",
"id": "Histogram",
"properties": {
"bucketCounts": {
"description": "Counts of values in each bucket. For efficiency, prefix and trailing\nbuckets with count = 0 are elided. Buckets can store the full range of\nvalues of an unsigned long, with ULLONG_MAX falling into the 59th bucket\nwith range [1e19, 2e19).",
"items": {
"format": "int64",
"type": "string"
},
"type": "array"
},
"firstBucketOffset": {
"description": "Starting index of first stored bucket. The non-inclusive upper-bound of\nthe ith bucket is given by:\n pow(10,(i-first_bucket_offset)/3) * (1,2,5)[(i-first_bucket_offset)%3]",
"format": "int32",
"type": "integer"
}
},
"type": "object"
},
"InstructionInput": {
"description": "An input of an instruction, as a reference to an output of a\nproducer instruction.",
"id": "InstructionInput",
"properties": {
"outputNum": {
"description": "The output index (origin zero) within the producer.",
"format": "int32",
"type": "integer"
},
"producerInstructionIndex": {
"description": "The index (origin zero) of the parallel instruction that produces\nthe output to be consumed by this input. This index is relative\nto the list of instructions in this input's instruction's\ncontaining MapTask.",
"format": "int32",
"type": "integer"
}
},
"type": "object"
},
"InstructionOutput": {
"description": "An output of an instruction.",
"id": "InstructionOutput",
"properties": {
"codec": {
"additionalProperties": {
"description": "Properties of the object.",
"type": "any"
},
"description": "The codec to use to encode data being written via this output.",
"type": "object"
},
"name": {
"description": "The user-provided name of this output.",
"type": "string"
},
"onlyCountKeyBytes": {
"description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
"type": "boolean"
},
"onlyCountValueBytes": {
"description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the value size.",
"type": "boolean"
},
"originalName": {
"description": "System-defined name for this output in the original workflow graph.\nOutputs that do not contribute to an original instruction do not set this.",
"type": "string"
},
"systemName": {
"description": "System-defined name of this output.\nUnique across the workflow.",
"type": "string"
}
},
"type": "object"
},
"IntegerGauge": {
"description": "A metric value representing temporal values of a variable.",
"id": "IntegerGauge",
"properties": {
"timestamp": {
"description": "The time at which this value was measured. Measured as msecs from epoch.",
"format": "google-datetime",
"type": "string"
},
"value": {
"$ref": "SplitInt64",
"description": "The value of the variable represented by this gauge."
}
},
"type": "object"
},
"IntegerList": {
"description": "A metric value representing a list of integers.",
"id": "IntegerList",
"properties": {
"elements": {
"description": "Elements of the list.",
"items": {
"$ref": "SplitInt64"
},
"type": "array"
}
},
"type": "object"
},
"IntegerMean": {
"description": "A representation of an integer mean metric contribution.",
"id": "IntegerMean",
"properties": {
"count": {
"$ref": "SplitInt64",
"description": "The number of values being aggregated."
},
"sum": {
"$ref": "SplitInt64",
"description": "The sum of all values being aggregated."
}
},
"type": "object"
},
"Job": {
"description": "Defines a job to be run by the Cloud Dataflow service.",
"id": "Job",
"properties": {
"clientRequestId": {
"description": "The client's unique identifier of the job, re-used across retried attempts.\nIf this field is set, the service will ensure its uniqueness.\nThe request to create a job will fail if the service has knowledge of a\npreviously submitted job with the same client's ID and job name.\nThe caller may use this field to ensure idempotence of job\ncreation across retried attempts to create a job.\nBy default, the field is empty and, in that case, the service ignores it.",
"type": "string"
},
"createTime": {
"description": "The timestamp when the job was initially created. Immutable and set by the\nCloud Dataflow service.",
"format": "google-datetime",
"type": "string"
},
"createdFromSnapshotId": {
"description": "If this is specified, the job's initial state is populated from the given\nsnapshot.",
"type": "string"
},
"currentState": {
"description": "The current state of the job.\n\nJobs are created in the `JOB_STATE_STOPPED` state unless otherwise\nspecified.\n\nA job in the `JOB_STATE_RUNNING` state may asynchronously enter a\nterminal state. After a job has reached a terminal state, no\nfurther state updates may be made.\n\nThis field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
"enum": [
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING",
"JOB_STATE_QUEUED"
],
"enumDescriptions": [
"The job's run state isn't specified.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"`JOB_STATE_PENDING` indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"`JOB_STATE_CANCELLING` indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to `JOB_STATE_CANCELLED` or `JOB_STATE_FAILED`.",
"`JOB_STATE_QUEUED` indicates that the job has been created but is being\ndelayed until launch. Jobs that are queued may only transition to\n`JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`."
],
"type": "string"
},
"currentStateTime": {
"description": "The timestamp associated with the current state.",
"format": "google-datetime",
"type": "string"
},
"environment": {
"$ref": "Environment",
"description": "The environment for the job."
},
"executionInfo": {
"$ref": "JobExecutionInfo",
"description": "Deprecated."
},
"id": {
"description": "The unique ID of this job.\n\nThis field is set by the Cloud Dataflow service when the Job is\ncreated, and is immutable for the life of the job.",
"type": "string"
},
"jobMetadata": {
"$ref": "JobMetadata",
"description": "This field is populated by the Dataflow service to support filtering jobs\nby the metadata values provided here. Populated for ListJobs and all GetJob\nviews SUMMARY and higher."
},
"labels": {
"additionalProperties": {
"type": "string"
},
"description": "User-defined labels for this job.\n\nThe labels map can contain no more than 64 entries. Entries of the labels\nmap are UTF8 strings that comply with the following restrictions:\n\n* Keys must conform to regexp: \\p{Ll}\\p{Lo}{0,62}\n* Values must conform to regexp: [\\p{Ll}\\p{Lo}\\p{N}_-]{0,63}\n* Both keys and values are additionally constrained to be \u003c= 128 bytes in\nsize.",
"type": "object"
},
"location": {
"description": "The location that contains this job.",
"type": "string"
},
"name": {
"description": "The user-specified Cloud Dataflow job name.\n\nOnly one Job with a given name may exist in a project at any\ngiven time. If a caller attempts to create a Job with the same\nname as an already-existing Job, the attempt returns the\nexisting Job.\n\nThe name must match the regular expression\n`[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
"type": "string"
},
"pipelineDescription": {
"$ref": "PipelineDescription",
"description": "Preliminary field: The format of this data may change at any time.\nA description of the user pipeline and stages through which it is executed.\nCreated by Cloud Dataflow service. Only retrieved with\nJOB_VIEW_DESCRIPTION or JOB_VIEW_ALL."
},
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"type": "string"
},
"replaceJobId": {
"description": "If this job is an update of an existing job, this field is the job ID\nof the job it replaced.\n\nWhen sending a `CreateJobRequest`, you can update a job by specifying it\nhere. The job named here is stopped, and its intermediate state is\ntransferred to this job.",
"type": "string"
},
"replacedByJobId": {
"description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
"type": "string"
},
"requestedState": {
"description": "The job's requested state.\n\n`UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and\n`JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may\nalso be used to directly set a job's requested state to\n`JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the\njob if it has not already reached a terminal state.",
"enum": [
"JOB_STATE_UNKNOWN",
"JOB_STATE_STOPPED",
"JOB_STATE_RUNNING",
"JOB_STATE_DONE",
"JOB_STATE_FAILED",
"JOB_STATE_CANCELLED",
"JOB_STATE_UPDATED",
"JOB_STATE_DRAINING",
"JOB_STATE_DRAINED",
"JOB_STATE_PENDING",
"JOB_STATE_CANCELLING",
"JOB_STATE_QUEUED"
],
"enumDescriptions": [
"The job's run state isn't specified.",
"`JOB_STATE_STOPPED` indicates that the job has not\nyet started to run.",
"`JOB_STATE_RUNNING` indicates that the job is currently running.",
"`JOB_STATE_DONE` indicates that the job has successfully completed.\nThis is a terminal job state. This state may be set by the Cloud Dataflow\nservice, as a transition from `JOB_STATE_RUNNING`. It may also be set via a\nCloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal\nstate.",
"`JOB_STATE_FAILED` indicates that the job has failed. This is a\nterminal job state. This state may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_RUNNING`.",
"`JOB_STATE_CANCELLED` indicates that the job has been explicitly\ncancelled. This is a terminal job state. This state may only be\nset via a Cloud Dataflow `UpdateJob` call, and only if the job has not\nyet reached another terminal state.",
"`JOB_STATE_UPDATED` indicates that the job was successfully updated,\nmeaning that this job was stopped and another job was started, inheriting\nstate from this one. This is a terminal job state. This state may only be\nset by the Cloud Dataflow service, and only as a transition from\n`JOB_STATE_RUNNING`.",
"`JOB_STATE_DRAINING` indicates that the job is in the process of draining.\nA draining job has stopped pulling from its input sources and is processing\nany data that remains in-flight. This state may be set via a Cloud Dataflow\n`UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs\nthat are draining may only transition to `JOB_STATE_DRAINED`,\n`JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.",
"`JOB_STATE_DRAINED` indicates that the job has been drained.\nA drained job terminated by stopping pulling from its input sources and\nprocessing any data that remained in-flight when draining was requested.\nThis state is a terminal state, may only be set by the Cloud Dataflow\nservice, and only as a transition from `JOB_STATE_DRAINING`.",
"`JOB_STATE_PENDING` indicates that the job has been created but is not yet\nrunning. Jobs that are pending may only transition to `JOB_STATE_RUNNING`,\nor `JOB_STATE_FAILED`.",
"`JOB_STATE_CANCELLING` indicates that the job has been explicitly cancelled\nand is in the process of stopping. Jobs that are cancelling may only\ntransition to `JOB_STATE_CANCELLED` or `JOB_STATE_FAILED`.",
"`JOB_STATE_QUEUED` indicates that the job has been created but is being\ndelayed until launch. Jobs that are queued may only transition to\n`JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`."
],
"type": "string"
},
"stageStates": {
"description": "This field may be mutated by the Cloud Dataflow service;\ncallers cannot mutate it.",
"items": {
"$ref": "ExecutionStageState"
},
"type": "array"
},
"startTime": {
"description": "The timestamp when the job was started (transitioned to JOB_STATE_PENDING).\nFlexible resource scheduling jobs are started with some delay after job\ncreation, so start_time is unset before start and is updated when the\njob is started by the Cloud Dataflow service. For other jobs, start_time\nalways equals to create_time and is immutable and set by the Cloud Dataflow\nservice.",
"format": "google-datetime",
"type": "string"
},
"steps": {
"description": "Exactly one of step or steps_location should be specified.\n\nThe top-level steps that constitute the entire job.",
"items": {
"$ref": "Step"
},
"type": "array"
},
"stepsLocation": {
"description": "The GCS location where the steps are stored.",
"type": "string"
},
"tempFiles": {
"description": "A set of files the system should be aware of that are used\nfor temporary storage. These temporary files will be\nremoved on job completion.\nNo duplicates are allowed.\nNo file patterns are supported.\n\nThe supported files are:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
"items": {
"type": "string"
},
"type": "array"
},
"transformNameMapping": {
"additionalProperties": {
"type": "string"
},
"description": "The map of transform name prefixes of the job to be replaced to the\ncorresponding name prefixes of the new job.",
"type": "object"
},
"type": {
"description": "The type of Cloud Dataflow job.",
"enum": [
"JOB_TYPE_UNKNOWN",
"JOB_TYPE_BATCH",
"JOB_TYPE_STREAMING"
],
"enumDescriptions": [
"The type of the job is unspecified, or unknown.",
"A batch job with a well-defined end point: data is read, data is\nprocessed, data is written, and the job is done.",
"A continuously streaming job with no end: data is read,\nprocessed, and written continuously."
],
"type": "string"
}
},
"type": "object"
},
"JobExecutionInfo": {
"description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.",
"id": "JobExecutionInfo",
"properties": {
"stages": {
"additionalProperties": {
"$ref": "JobExecutionStageInfo"
},
"description": "A mapping from each stage to the information about that stage.",
"type": "object"
}
},
"type": "object"
},
"JobExecutionStageInfo": {
"description": "Contains information about how a particular\ngoogle.dataflow.v1beta3.Step will be executed.",
"id": "JobExecutionStageInfo",
"properties": {
"stepName": {
"description": "The steps associated with the execution stage.\nNote that stages may have several steps, and that a given step\nmight be run by more than one stage.",
"items": {
"type": "string"
},
"type": "array"
}
},
"type": "object"
},
"JobMessage": {
"description": "A particular message pertaining to a Dataflow job.",
"id": "JobMessage",
"properties": {
"id": {
"description": "Deprecated.",
"type": "string"
},
"messageImportance": {
"description": "Importance level of the message.",
"enum": [
"JOB_MESSAGE_IMPORTANCE_UNKNOWN",
"JOB_MESSAGE_DEBUG",
"JOB_MESSAGE_DETAILED",
"JOB_MESSAGE_BASIC",
"JOB_MESSAGE_WARNING",
"JOB_MESSAGE_ERROR"
],
"enumDescriptions": [
"The message importance isn't specified, or is unknown.",
"The message is at the 'debug' level: typically only useful for\nsoftware engineers working on the code the job is running.\nTypically, Dataflow pipeline runners do not display log messages\nat this level by default.",
"The message is at the 'detailed' level: somewhat verbose, but\npotentially useful to users. Typically, Dataflow pipeline\nrunners do not display log messages at this level by default.\nThese messages are displayed by default in the Dataflow\nmonitoring UI.",
"The message is at the 'basic' level: useful for keeping\ntrack of the execution of a Dataflow pipeline. Typically,\nDataflow pipeline runners display log messages at this level by\ndefault, and these messages are displayed by default in the\nDataflow monitoring UI.",
"The message is at the 'warning' level: indicating a condition\npertaining to a job which may require human intervention.\nTypically, Dataflow pipeline runners display log messages at this\nlevel by default, and these messages are displayed by default in\nthe Dataflow monitoring UI.",
"The message is at the 'error' level: indicating a condition\npreventing a job from succeeding. Typically, Dataflow pipeline\nrunners display log messages at this level by default, and these\nmessages are displayed by default in the Dataflow monitoring UI."
],
"type": "string"
},
"messageText": {
"description": "The text of the message.",
"type": "string"
},
"time": {
"description": "The timestamp of the message.",
"format": "google-datetime",
"type": "string"
}
},
"type": "object"
},
"JobMetadata": {
"description": "Metadata available primarily for filtering jobs. Will be included in the\nListJob response and Job SUMMARY view+.",
"id": "JobMetadata",
"properties": {
"bigTableDetails": {
"description": "Identification of a BigTable source used in the Dataflow job.",
"items": {
"$ref": "BigTableIODetails"
},
"type": "array"
},
"bigqueryDetails": {
"description": "Identification of a BigQuery source used in the Dataflow job.",
"items": {
"$ref": "BigQueryIODetails"
},
"type": "array"
},
"datastoreDetails": {
"description": "Identification of a Datastore source used in the Dataflow job.",
"items": {
"$ref": "DatastoreIODetails"
},
"type": "array"
},
"fileDetails": {
"description": "Identification of a File source used in the Dataflow job.",
"items": {
"$ref": "FileIODetails"
},
"type": "array"
},
"pubsubDetails": {
"description": "Identification of a PubSub source used in the Dataflow job.",
"items": {
"$ref": "PubSubIODetails"
},
"type": "array"
},
"sdkVersion": {
"$ref": "SdkVersion",
"description": "The SDK version used to run the job."
},
"spannerDetails": {
"description": "Identification of a Spanner source used in the Dataflow job.",
"items": {
"$ref": "SpannerIODetails"
},
"type": "array"
}
},
"type": "object"
},
"JobMetrics": {
"description": "JobMetrics contains a collection of metrics descibing the detailed progress\nof a Dataflow job. Metrics correspond to user-defined and system-defined\nmetrics in the job.\n\nThis resource captures only the most recent values of each metric;\ntime-series data can be queried for them (under the same metric names)\nfrom Cloud Monitoring.",
"id": "JobMetrics",
"properties": {
"metricTime": {
"description": "Timestamp as of which metric values are current.",
"format": "google-datetime",
"type": "string"
},
"metrics": {
"description": "All metrics for this job.",
"items": {
"$ref": "MetricUpdate"
},
"type": "array"
}
},
"type": "object"
},
"KeyRangeDataDiskAssignment": {
"description": "Data disk assignment information for a specific key-range of a sharded\ncomputation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
"id": "KeyRangeDataDiskAssignment",
"properties": {
"dataDisk": {
"description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
"type": "string"
},
"end": {
"description": "The end (exclusive) of the key range.",
"type": "string"
},
"start": {
"description": "The start (inclusive) of the key range.",
"type": "string"
}
},
"type": "object"
},
"KeyRangeLocation": {
"description": "Location information for a specific key-range of a sharded computation.\nCurrently we only support UTF-8 character splits to simplify encoding into\nJSON.",
"id": "KeyRangeLocation",
"properties": {
"dataDisk": {
"description": "The name of the data disk where data for this range is stored.\nThis name is local to the Google Cloud Platform project and uniquely\nidentifies the disk within that project, for example\n\"myproject-1014-104817-4c2-harness-0-disk-1\".",
"type": "string"
},
"deliveryEndpoint": {
"description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
"type": "string"
},
"deprecatedPersistentDirectory": {
"description": "DEPRECATED. The location of the persistent state for this range, as a\npersistent directory in the worker local filesystem.",
"type": "string"
},
"end": {
"description": "The end (exclusive) of the key range.",
"type": "string"
},
"start": {
"description": "The start (inclusive) of the key range.",
"type": "string"
}
},
"type": "object"
},
"LaunchTemplateParameters": {
"description": "Parameters to provide to the template being launched.",
"id": "LaunchTemplateParameters",
"properties": {
"environment": {
"$ref": "RuntimeEnvironment",
"description": "The runtime environment for the job."
},
"jobName": {
"description": "Required. The job name to use for the created job.",
"type": "string"
},
"parameters": {
"additionalProperties": {
"type": "string"
},
"description": "The runtime parameters to pass to the job.",
"type": "object"
}
},
"type": "object"
},
"LaunchTemplateResponse": {
"description": "Response to the request to launch a template.",
"id": "LaunchTemplateResponse",
"properties": {
"job": {
"$ref": "Job",
"description": "The job that was launched, if the request was not a dry run and\nthe job was successfully launched."
}
},
"type": "object"
},
"LeaseWorkItemRequest": {
"description": "Request to lease WorkItems.",
"id": "LeaseWorkItemRequest",
"properties": {
"currentWorkerTime": {
"description": "The current timestamp at the worker.",
"format": "google-datetime",
"type": "string"
},
"location": {
"description": "The location which contains the WorkItem's job.",
"type": "string"
},
"requestedLeaseDuration": {
"description": "The initial lease period.",
"format": "google-duration",
"type": "string"
},
"workItemTypes": {
"description": "Filter for WorkItem type.",
"items": {
"type": "string"
},
"type": "array"
},
"workerCapabilities": {
"description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
"items": {
"type": "string"
},
"type": "array"
},
"workerId": {
"description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
"type": "string"
}
},
"type": "object"
},
"LeaseWorkItemResponse": {
"description": "Response to a request to lease WorkItems.",
"id": "LeaseWorkItemResponse",
"properties": {
"workItems": {
"description": "A list of the leased WorkItems.",
"items": {
"$ref": "WorkItem"
},
"type": "array"
}
},
"type": "object"
},
"ListJobMessagesResponse": {
"description": "Response to a request to list job messages.",
"id": "ListJobMessagesResponse",
"properties": {
"autoscalingEvents": {
"description": "Autoscaling events in ascending timestamp order.",
"items": {
"$ref": "AutoscalingEvent"
},
"type": "array"
},
"jobMessages": {
"description": "Messages in ascending timestamp order.",
"items": {
"$ref": "JobMessage"
},
"type": "array"
},
"nextPageToken": {
"description": "The token to obtain the next page of results if there are more.",
"type": "string"
}
},
"type": "object"
},
"ListJobsResponse": {
"description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
"id": "ListJobsResponse",
"properties": {
"failedLocation": {
"description": "Zero or more messages describing locations that failed to respond.",
"items": {
"$ref": "FailedLocation"
},
"type": "array"
},
"jobs": {
"description": "A subset of the requested job information.",
"items": {
"$ref": "Job"
},
"type": "array"
},
"nextPageToken": {
"description": "Set if there may be more results than fit in this response.",
"type": "string"
}
},
"type": "object"
},
"MapTask": {
"description": "MapTask consists of an ordered set of instructions, each of which\ndescribes one particular low-level operation for the worker to\nperform in order to accomplish the MapTask's WorkItem.\n\nEach instruction must appear in the list before any instructions which\ndepends on its output.",
"id": "MapTask",
"properties": {
"counterPrefix": {
"description": "Counter prefix that can be used to prefix counters. Not currently used in\nDataflow.",
"type": "string"
},
"instructions": {
"description": "The instructions in the MapTask.",
"items": {
"$ref": "ParallelInstruction"
},
"type": "array"
},
"stageName": {
"description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
"type": "string"
},
"systemName": {
"description": "System-defined name of this MapTask.\nUnique across the workflow.",
"type": "string"
}
},
"type": "object"
},
"MetricShortId": {
"description": "The metric short id is returned to the user alongside an offset into\nReportWorkItemStatusRequest",
"id": "MetricShortId",
"properties": {
"metricIndex": {
"description": "The index of the corresponding metric in\nthe ReportWorkItemStatusRequest. Required.",
"format": "int32",
"type": "integer"
},
"shortId": {
"description": "The service-generated short identifier for the metric.",
"format": "int64",
"type": "string"
}
},
"type": "object"
},
"MetricStructuredName": {
"description": "Identifies a metric, by describing the source which generated the\nmetric.",
"id": "MetricStructuredName",
"properties": {
"context": {
"additionalProperties": {
"type": "string"
},
"description": "Zero or more labeled fields which identify the part of the job this\nmetric is associated with, such as the name of a step or collection.\n\nFor example, built-in counters associated with steps will have\ncontext['step'] = \u003cstep-name\u003e. Counters associated with PCollections\nin the SDK will have context['pcollection'] = \u003cpcollection-name\u003e.",
"type": "object"
},
"name": {
"description": "Worker-defined metric name.",
"type": "string"
},
"origin": {
"description": "Origin (namespace) of metric name. May be blank for user-define metrics;\nwill be \"dataflow\" for metrics defined by the Dataflow service or SDK.",
"type": "string"
}
},
"type": "object"
},
"MetricUpdate": {
"description": "Describes the state of a metric.",
"id": "MetricUpdate",
"properties": {
"cumulative": {
"description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.",
"type": "boolean"
},
"distribution": {
"description": "A struct value describing properties of a distribution of numeric values.",
"type": "any"
},
"gauge": {
"description": "A struct value describing properties of a Gauge.\nMetrics of gauge type show the value of a metric across time, and is\naggregated based on the newest value.",
"type": "any"
},
"internal": {
"description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
"type": "any"
},
"kind": {
"description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", \"Or\", and \"Distribution\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
"type": "string"
},
"meanCount": {
"description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the count of the aggregated values and is used in combination\nwith mean_sum above to obtain the actual mean aggregate value.\nThe only possible value type is Long.",
"type": "any"
},
"meanSum": {
"description": "Worker-computed aggregate value for the \"Mean\" aggregation kind.\nThis holds the sum of the aggregated values and is used in combination\nwith mean_count below to obtain the actual mean aggregate value.\nThe only possible value types are Long and Double.",