Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(678)

Issues Search
    My Issues | Starred     Open | Closed | All

Unified Diff: discovery/googleapis_beta/dataflow__v1b3.json

Issue 2779563003: Api-roll 47: 2017-03-27 (Closed)
Patch Set: Created 3 years, 9 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « discovery/googleapis_beta/cloudresourcemanager__v1beta1.json ('k') | discovery/googleapis_beta/dataproc__v1beta1.json » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: discovery/googleapis_beta/dataflow__v1b3.json
diff --git a/discovery/googleapis_beta/dataflow__v1b3.json b/discovery/googleapis_beta/dataflow__v1b3.json
index c5e51a9215b7d46ef188321376b117bd14cf14f1..8b85330315746e324f5056e22a34a70520ade87a 100644
--- a/discovery/googleapis_beta/dataflow__v1b3.json
+++ b/discovery/googleapis_beta/dataflow__v1b3.json
@@ -27,22 +27,16 @@
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
- "prettyPrint": {
- "default": "true",
- "description": "Returns response with indentations and line breaks.",
+ "uploadType": {
+ "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"location": "query",
- "type": "boolean"
+ "type": "string"
},
"fields": {
"description": "Selector specifying which fields to include in a partial response.",
"location": "query",
"type": "string"
},
- "uploadType": {
- "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
- "location": "query",
- "type": "string"
- },
"$.xgafv": {
"description": "V1 error format.",
"enum": [
@@ -112,6 +106,12 @@
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"location": "query",
"type": "string"
+ },
+ "prettyPrint": {
+ "default": "true",
+ "description": "Returns response with indentations and line breaks.",
+ "location": "query",
+ "type": "boolean"
}
},
"protocol": "rest",
@@ -161,12 +161,6 @@
"jobId"
],
"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",
@@ -189,6 +183,12 @@
],
"location": "query",
"type": "string"
+ },
+ "location": {
+ "description": "The location that contains this job.",
+ "location": "path",
+ "required": true,
+ "type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}",
@@ -209,6 +209,23 @@
"location"
],
"parameters": {
+ "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"
+ },
+ "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"
+ },
"projectId": {
"description": "The project which owns the jobs.",
"location": "path",
@@ -236,23 +253,6 @@
"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"
- },
- "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"
- },
- "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",
@@ -314,11 +314,6 @@
"location"
],
"parameters": {
- "replaceJobId": {
- "description": "Deprecated. This field is now in the Job message.",
- "location": "query",
- "type": "string"
- },
"projectId": {
"description": "The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
@@ -341,6 +336,11 @@
"location": "path",
"required": true,
"type": "string"
+ },
+ "replaceJobId": {
+ "description": "Deprecated. This field is now in the Job message.",
+ "location": "query",
+ "type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs",
@@ -365,18 +365,6 @@
"jobId"
],
"parameters": {
- "projectId": {
- "description": "A project id.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "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",
@@ -388,6 +376,18 @@
"format": "google-datetime",
"location": "query",
"type": "string"
+ },
+ "projectId": {
+ "description": "A project id.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "jobId": {
+ "description": "The job to get messages for.",
+ "location": "path",
+ "required": true,
+ "type": "string"
}
},
"path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics",
@@ -401,12 +401,12 @@
}
},
"resources": {
- "messages": {
+ "workItems": {
"methods": {
- "list": {
- "description": "Request the job status.",
- "httpMethod": "GET",
- "id": "dataflow.projects.locations.jobs.messages.list",
+ "reportStatus": {
+ "description": "Reports the status of dataflow WorkItems leased by a worker.",
+ "httpMethod": "POST",
+ "id": "dataflow.projects.locations.jobs.workItems.reportStatus",
"parameterOrder": [
"projectId",
"location",
@@ -414,73 +414,36 @@
],
"parameters": {
"projectId": {
- "description": "A project id.",
+ "description": "The project which owns the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
},
"jobId": {
- "description": "The job to get messages about.",
+ "description": "The job which the WorkItem is part of.",
"location": "path",
"required": true,
"type": "string"
},
"location": {
- "description": "The location which contains the job specified by job_id.",
+ "description": "The location which contains the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
- },
- "endTime": {
- "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).",
- "format": "google-datetime",
- "location": "query",
- "type": "string"
- },
- "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"
- },
- "startTime": {
- "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
- "format": "google-datetime",
- "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"
- },
- "minimumImportance": {
- "description": "Filter to only get messages with importance >= 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"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
+ "request": {
+ "$ref": "ReportWorkItemStatusRequest"
+ },
"response": {
- "$ref": "ListJobMessagesResponse"
+ "$ref": "ReportWorkItemStatusResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/userinfo.email"
]
- }
- }
- },
- "workItems": {
- "methods": {
+ },
"lease": {
"description": "Leases a dataflow WorkItem to run.",
"httpMethod": "POST",
@@ -491,20 +454,20 @@
"jobId"
],
"parameters": {
- "projectId": {
- "description": "Identifies the project this worker belongs to.",
+ "location": {
+ "description": "The location which contains the WorkItem's job.",
"location": "path",
"required": true,
"type": "string"
},
- "jobId": {
- "description": "Identifies the workflow job this worker belongs to.",
+ "projectId": {
+ "description": "Identifies the project this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
},
- "location": {
- "description": "The location which contains the WorkItem's job.",
+ "jobId": {
+ "description": "Identifies the workflow job this worker belongs to.",
"location": "path",
"required": true,
"type": "string"
@@ -521,42 +484,79 @@
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/userinfo.email"
]
- },
- "reportStatus": {
- "description": "Reports the status of dataflow WorkItems leased by a worker.",
- "httpMethod": "POST",
- "id": "dataflow.projects.locations.jobs.workItems.reportStatus",
+ }
+ }
+ },
+ "messages": {
+ "methods": {
+ "list": {
+ "description": "Request the job status.",
+ "httpMethod": "GET",
+ "id": "dataflow.projects.locations.jobs.messages.list",
"parameterOrder": [
"projectId",
"location",
"jobId"
],
"parameters": {
- "location": {
- "description": "The location which contains the WorkItem's job.",
+ "projectId": {
+ "description": "A project id.",
"location": "path",
"required": true,
"type": "string"
},
- "projectId": {
- "description": "The project which owns the WorkItem's job.",
+ "jobId": {
+ "description": "The job to get messages about.",
"location": "path",
"required": true,
"type": "string"
},
- "jobId": {
- "description": "The job which the WorkItem is part of.",
+ "location": {
+ "description": "The location which contains the job specified by job_id.",
"location": "path",
"required": true,
"type": "string"
+ },
+ "endTime": {
+ "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).",
+ "format": "google-datetime",
+ "location": "query",
+ "type": "string"
+ },
+ "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"
+ },
+ "startTime": {
+ "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
+ "format": "google-datetime",
+ "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"
+ },
+ "minimumImportance": {
+ "description": "Filter to only get messages with importance >= 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"
}
},
- "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus",
- "request": {
- "$ref": "ReportWorkItemStatusRequest"
- },
+ "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages",
"response": {
- "$ref": "ReportWorkItemStatusResponse"
+ "$ref": "ListJobMessagesResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -571,10 +571,10 @@
},
"templates": {
"methods": {
- "get": {
- "description": "Get the template associated with a template.",
- "httpMethod": "GET",
- "id": "dataflow.projects.templates.get",
+ "launch": {
+ "description": "Launch a template.",
+ "httpMethod": "POST",
+ "id": "dataflow.projects.templates.launch",
"parameterOrder": [
"projectId"
],
@@ -585,33 +585,33 @@
"required": true,
"type": "string"
},
- "view": {
- "description": "The view to retrieve. Defaults to METADATA_ONLY.",
- "enum": [
- "METADATA_ONLY"
- ],
+ "gcsPath": {
+ "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
"location": "query",
"type": "string"
},
- "gcsPath": {
- "description": "Required. A Cloud Storage path to the template from which to\ncreate the job.\nMust be a valid Cloud Storage URL, beginning with `gs://`.",
+ "dryRun": {
+ "description": "Whether or not the job should actually be executed after\nvalidating parameters. Defaults to false. Validation errors do\nnot cause the HTTP request to fail if true.",
"location": "query",
- "type": "string"
+ "type": "boolean"
}
},
- "path": "v1b3/projects/{projectId}/templates:get",
+ "path": "v1b3/projects/{projectId}/templates:launch",
+ "request": {
+ "$ref": "LaunchTemplateParameters"
+ },
"response": {
- "$ref": "GetTemplateResponse"
+ "$ref": "LaunchTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "create": {
- "description": "Creates a Cloud Dataflow job from a template.",
- "httpMethod": "POST",
- "id": "dataflow.projects.templates.create",
+ "get": {
+ "description": "Get the template associated with a template.",
+ "httpMethod": "GET",
+ "id": "dataflow.projects.templates.get",
"parameterOrder": [
"projectId"
],
@@ -621,51 +621,51 @@
"location": "path",
"required": true,
"type": "string"
+ },
+ "view": {
+ "description": "The view to retrieve. Defaults to METADATA_ONLY.",
+ "enum": [
+ "METADATA_ONLY"
+ ],
+ "location": "query",
+ "type": "string"
+ },
+ "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://`.",
+ "location": "query",
+ "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/templates",
- "request": {
- "$ref": "CreateJobFromTemplateRequest"
- },
+ "path": "v1b3/projects/{projectId}/templates:get",
"response": {
- "$ref": "Job"
+ "$ref": "GetTemplateResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/userinfo.email"
]
},
- "launch": {
- "description": "Launch a template.",
+ "create": {
+ "description": "Creates a Cloud Dataflow job from a template.",
"httpMethod": "POST",
- "id": "dataflow.projects.templates.launch",
+ "id": "dataflow.projects.templates.create",
"parameterOrder": [
"projectId"
],
"parameters": {
- "dryRun": {
- "description": "Whether or not the job should actually be executed after\nvalidating parameters. Defaults to false. Validation errors do\nnot cause the HTTP request to fail if true.",
- "location": "query",
- "type": "boolean"
- },
"projectId": {
"description": "Required. The ID of the Cloud Platform project that the job belongs to.",
"location": "path",
"required": true,
"type": "string"
- },
- "gcsPath": {
- "description": "Required. A Cloud Storage path to the template from which to create\nthe job.\nMust be valid Cloud Storage URL, beginning with 'gs://'.",
- "location": "query",
- "type": "string"
}
},
- "path": "v1b3/projects/{projectId}/templates:launch",
+ "path": "v1b3/projects/{projectId}/templates",
"request": {
- "$ref": "LaunchTemplateParameters"
+ "$ref": "CreateJobFromTemplateRequest"
},
"response": {
- "$ref": "LaunchTemplateResponse"
+ "$ref": "Job"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform",
@@ -685,17 +685,6 @@
"jobId"
],
"parameters": {
- "location": {
- "description": "The location which contains the job specified by job_id.",
- "location": "query",
- "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"
- },
"projectId": {
"description": "A project id.",
"location": "path",
@@ -707,6 +696,17 @@
"location": "path",
"required": true,
"type": "string"
+ },
+ "location": {
+ "description": "The location which contains the job specified by job_id.",
+ "location": "query",
+ "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",
@@ -727,11 +727,6 @@
"jobId"
],
"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",
@@ -754,6 +749,11 @@
],
"location": "query",
"type": "string"
+ },
+ "location": {
+ "description": "The location that contains this job.",
+ "location": "query",
+ "type": "string"
}
},
"path": "v1b3/projects/{projectId}/jobs/{jobId}",
@@ -916,82 +916,6 @@
}
},
"resources": {
- "messages": {
- "methods": {
- "list": {
- "description": "Request the job status.",
- "httpMethod": "GET",
- "id": "dataflow.projects.jobs.messages.list",
- "parameterOrder": [
- "projectId",
- "jobId"
- ],
- "parameters": {
- "startTime": {
- "description": "If specified, return only messages with timestamps >= start_time.\nThe default is the job creation time (i.e. beginning of messages).",
- "format": "google-datetime",
- "location": "query",
- "type": "string"
- },
- "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"
- },
- "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"
- },
- "minimumImportance": {
- "description": "Filter to only get messages with importance >= 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"
- },
- "jobId": {
- "description": "The job to get messages about.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "projectId": {
- "description": "A project id.",
- "location": "path",
- "required": true,
- "type": "string"
- },
- "location": {
- "description": "The location which contains the job specified by job_id.",
- "location": "query",
- "type": "string"
- },
- "endTime": {
- "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).",
- "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/userinfo.email"
- ]
- }
- }
- },
"debug": {
"methods": {
"getConfig": {
@@ -1135,254 +1059,107 @@
]
}
}
+ },
+ "messages": {
+ "methods": {
+ "list": {
+ "description": "Request the job status.",
+ "httpMethod": "GET",
+ "id": "dataflow.projects.jobs.messages.list",
+ "parameterOrder": [
+ "projectId",
+ "jobId"
+ ],
+ "parameters": {
+ "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"
+ },
+ "minimumImportance": {
+ "description": "Filter to only get messages with importance >= 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"
+ },
+ "projectId": {
+ "description": "A project id.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "jobId": {
+ "description": "The job to get messages about.",
+ "location": "path",
+ "required": true,
+ "type": "string"
+ },
+ "endTime": {
+ "description": "Return only messages with timestamps < end_time. The default is now\n(i.e. return up to the latest messages available).",
+ "format": "google-datetime",
+ "location": "query",
+ "type": "string"
+ },
+ "location": {
+ "description": "The location which contains the job specified by job_id.",
+ "location": "query",
+ "type": "string"
+ },
+ "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"
+ },
+ "startTime": {
+ "description": "If specified, return only messages with timestamps >= 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": {
+ "$ref": "ListJobMessagesResponse"
+ },
+ "scopes": [
+ "https://www.googleapis.com/auth/cloud-platform",
+ "https://www.googleapis.com/auth/userinfo.email"
+ ]
+ }
+ }
}
}
}
}
}
},
- "revision": "20170303",
+ "revision": "20170318",
"rootUrl": "https://dataflow.googleapis.com/",
"schemas": {
- "SeqMapTaskOutputInfo": {
- "description": "Information about an output of a SeqMapTask.",
- "id": "SeqMapTaskOutputInfo",
+ "InstructionOutput": {
+ "description": "An output of an instruction.",
+ "id": "InstructionOutput",
"properties": {
- "sink": {
- "$ref": "Sink",
- "description": "The sink to write the output value to."
- },
- "tag": {
- "description": "The id of the TupleTag the user code will tag the output value by.",
- "type": "string"
- }
- },
- "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"
- },
- "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": {
- "deliveryEndpoint": {
- "description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
- "type": "string"
- },
- "start": {
- "description": "The start (inclusive) of the key range.",
- "type": "string"
- },
- "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"
- },
- "persistentDirectory": {
- "description": "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"
- }
- },
- "type": "object"
- },
- "SourceGetMetadataRequest": {
- "description": "A request to compute the SourceMetadata of a Source.",
- "id": "SourceGetMetadataRequest",
- "properties": {
- "source": {
- "$ref": "Source",
- "description": "Specification of the source whose metadata should be computed."
- }
- },
- "type": "object"
- },
- "NameAndKind": {
- "description": "Basic metadata about a counter.",
- "id": "NameAndKind",
- "properties": {
- "name": {
- "description": "Name of the counter.",
- "type": "string"
- },
- "kind": {
- "description": "Counter aggregation kind.",
- "enum": [
- "INVALID",
- "SUM",
- "MAX",
- "MIN",
- "MEAN",
- "OR",
- "AND",
- "SET",
- "DISTRIBUTION"
- ],
- "enumDescriptions": [
- "Counter aggregation kind was not set.",
- "Aggregated value is the sum of all contributed values.",
- "Aggregated value is the max of all contributed values.",
- "Aggregated value is the min of all contributed values.",
- "Aggregated value is the mean of all contributed values.",
- "Aggregated value represents the logical 'or' of all contributed values.",
- "Aggregated value represents the logical 'and' of all contributed values.",
- "Aggregated value is a set of unique contributed values.",
- "Aggregated value captures statistics about a distribution."
- ],
- "type": "string"
- }
- },
- "type": "object"
- },
- "SeqMapTask": {
- "description": "Describes a particular function to invoke.",
- "id": "SeqMapTask",
- "properties": {
- "inputs": {
- "description": "Information about each of the inputs.",
- "items": {
- "$ref": "SideInputInfo"
- },
- "type": "array"
- },
- "systemName": {
- "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
- "type": "string"
- },
- "stageName": {
- "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
- "type": "string"
- },
- "userFn": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "description": "The user function to invoke.",
- "type": "object"
- },
- "name": {
- "description": "The user-provided name of the SeqDo operation.",
- "type": "string"
- },
- "outputInfos": {
- "description": "Information about each of the outputs.",
- "items": {
- "$ref": "SeqMapTaskOutputInfo"
- },
- "type": "array"
- }
- },
- "type": "object"
- },
- "WorkerMessageCode": {
- "description": "A message code is used to report status and error messages to the service.\nThe message codes are intended to be machine readable. The service will\ntake care of translating these into user understandable messages if\nnecessary.\n\nExample use cases:\n 1. Worker processes reporting successful startup.\n 2. Worker processes reporting specific errors (e.g. package staging\n failure).",
- "id": "WorkerMessageCode",
- "properties": {
- "code": {
- "description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change.",
+ "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"
},
- "parameters": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "description": "Parameters contains specific information about the code.\n\nThis is a struct to allow parameters of different types.\n\nExamples:\n 1. For a \"HARNESS_STARTED\" message parameters might provide the name\n of the worker and additional data like timing information.\n 2. For a \"GCS_DOWNLOAD_ERROR\" parameters might contain fields listing\n the GCS objects being downloaded and fields containing errors.\n\nIn general complex data structures should be avoided. If a worker\nneeds to send a specific and complicated data structure then please\nconsider defining a new proto and adding it to the data oneof in\nWorkerMessageResponse.\n\nConventions:\n Parameters should only be used for information that isn't typically passed\n as a label.\n hostname and other worker identifiers should almost always be passed\n as labels since they will be included on most messages.",
- "type": "object"
- }
- },
- "type": "object"
- },
- "CustomSourceLocation": {
- "description": "Identifies the location of a custom souce.",
- "id": "CustomSourceLocation",
- "properties": {
- "stateful": {
- "description": "Whether this source is stateful.",
+ "onlyCountKeyBytes": {
+ "description": "For system-generated byte and mean byte metrics, certain instructions\nshould only report the key size.",
"type": "boolean"
- }
- },
- "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": {
- "systemName": {
- "description": "System-defined name of this MapTask.\nUnique across the workflow.",
- "type": "string"
- },
- "stageName": {
- "description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
- "type": "string"
- },
- "instructions": {
- "description": "The instructions in the MapTask.",
- "items": {
- "$ref": "ParallelInstruction"
- },
- "type": "array"
- }
- },
- "type": "object"
- },
- "FloatingPointMean": {
- "description": "A representation of a floating point mean metric contribution.",
- "id": "FloatingPointMean",
- "properties": {
- "count": {
- "$ref": "SplitInt64",
- "description": "The number of values being aggregated."
},
- "sum": {
- "description": "The sum of all values being aggregated.",
- "format": "double",
- "type": "number"
- }
- },
- "type": "object"
- },
- "ReportWorkItemStatusResponse": {
- "description": "Response from a request to report the status of WorkItems.",
- "id": "ReportWorkItemStatusResponse",
- "properties": {
- "workItemServiceStates": {
- "description": "A set of messages indicating the service-side state for each\nWorkItem whose status was reported, in the same order as the\nWorkItemStatus messages in the ReportWorkItemStatusRequest which\nresulting in this response.",
- "items": {
- "$ref": "WorkItemServiceState"
- },
- "type": "array"
- }
- },
- "type": "object"
- },
- "InstructionOutput": {
- "description": "An output of an instruction.",
- "id": "InstructionOutput",
- "properties": {
"systemName": {
"description": "System-defined name of this output.\nUnique across the workflow.",
"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"
@@ -1398,10 +1175,6 @@
"name": {
"description": "The user-provided name of this output.",
"type": "string"
- },
- "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"
}
},
"type": "object"
@@ -1410,6 +1183,10 @@
"description": "A request to create a Cloud Dataflow job from a template.",
"id": "CreateJobFromTemplateRequest",
"properties": {
+ "jobName": {
+ "description": "Required. The job name to use for the created job.",
+ "type": "string"
+ },
"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"
@@ -1424,10 +1201,6 @@
},
"description": "The runtime parameters to pass to the job.",
"type": "object"
- },
- "jobName": {
- "description": "Required. The job name to use for the created job.",
- "type": "string"
}
},
"type": "object"
@@ -1436,13 +1209,13 @@
"description": "A representation of an integer mean metric contribution.",
"id": "IntegerMean",
"properties": {
- "sum": {
- "$ref": "SplitInt64",
- "description": "The sum of all values being aggregated."
- },
"count": {
"$ref": "SplitInt64",
"description": "The number of values being aggregated."
+ },
+ "sum": {
+ "$ref": "SplitInt64",
+ "description": "The sum of all values being aggregated."
}
},
"type": "object"
@@ -1451,13 +1224,6 @@
"description": "Response to a request to list Cloud Dataflow jobs. This may be a partial\nresponse, depending on the page size in the ListJobsRequest.",
"id": "ListJobsResponse",
"properties": {
- "jobs": {
- "description": "A subset of the requested job information.",
- "items": {
- "$ref": "Job"
- },
- "type": "array"
- },
"nextPageToken": {
"description": "Set if there may be more results than fit in this response.",
"type": "string"
@@ -1468,6 +1234,13 @@
"$ref": "FailedLocation"
},
"type": "array"
+ },
+ "jobs": {
+ "description": "A subset of the requested job information.",
+ "items": {
+ "$ref": "Job"
+ },
+ "type": "array"
}
},
"type": "object"
@@ -1476,43 +1249,43 @@
"description": "All configuration data for a particular Computation.",
"id": "ComputationTopology",
"properties": {
- "systemStageName": {
- "description": "The system stage name.",
+ "userStageName": {
+ "description": "The user stage name.",
"type": "string"
},
- "inputs": {
- "description": "The inputs to the computation.",
+ "outputs": {
+ "description": "The outputs from the computation.",
"items": {
"$ref": "StreamLocation"
},
"type": "array"
},
- "computationId": {
- "description": "The ID of the computation.",
- "type": "string"
- },
- "keyRanges": {
- "description": "The key ranges processed by the computation.",
+ "stateFamilies": {
+ "description": "The state family values.",
"items": {
- "$ref": "KeyRangeLocation"
+ "$ref": "StateFamilyConfig"
},
"type": "array"
},
- "userStageName": {
- "description": "The user stage name.",
+ "systemStageName": {
+ "description": "The system stage name.",
"type": "string"
},
- "outputs": {
- "description": "The outputs from the computation.",
+ "computationId": {
+ "description": "The ID of the computation.",
+ "type": "string"
+ },
+ "inputs": {
+ "description": "The inputs to the computation.",
"items": {
"$ref": "StreamLocation"
},
"type": "array"
},
- "stateFamilies": {
- "description": "The state family values.",
+ "keyRanges": {
+ "description": "The key ranges processed by the computation.",
"items": {
- "$ref": "StateFamilyConfig"
+ "$ref": "KeyRangeLocation"
},
"type": "array"
}
@@ -1523,15 +1296,6 @@
"description": "The environment values to set at runtime.",
"id": "RuntimeEnvironment",
"properties": {
- "maxWorkers": {
- "description": "The maximum number of Google Compute Engine instances to be made\navailable to your pipeline during execution, from 1 to 1000.",
- "format": "int32",
- "type": "integer"
- },
- "zone": {
- "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
- "type": "string"
- },
"serviceAccountEmail": {
"description": "The email address of the service account to run the job as.",
"type": "string"
@@ -1543,20 +1307,14 @@
"bypassTempDirValidation": {
"description": "Whether to bypass the safety checks for the job's temporary directory.\nUse with caution.",
"type": "boolean"
- }
- },
- "type": "object"
- },
- "StreamingSideInputLocation": {
- "description": "Identifies the location of a streaming side input.",
- "id": "StreamingSideInputLocation",
- "properties": {
- "stateFamily": {
- "description": "Identifies the state family where this side input is stored.",
- "type": "string"
},
- "tag": {
- "description": "Identifies the particular side input within the streaming Dataflow job.",
+ "maxWorkers": {
+ "description": "The maximum number of Google Compute Engine instances to be made\navailable to your pipeline during execution, from 1 to 1000.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "zone": {
+ "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)\nfor launching worker instances to run your pipeline.",
"type": "string"
}
},
@@ -1573,14 +1331,25 @@
},
"type": "object"
},
+ "StreamingSideInputLocation": {
+ "description": "Identifies the location of a streaming side input.",
+ "id": "StreamingSideInputLocation",
+ "properties": {
+ "tag": {
+ "description": "Identifies the particular side input within the streaming Dataflow job.",
+ "type": "string"
+ },
+ "stateFamily": {
+ "description": "Identifies the state family where this side input is stored.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
"LaunchTemplateResponse": {
"description": "Response to the request to launch a template.",
"id": "LaunchTemplateResponse",
"properties": {
- "status": {
- "$ref": "Status",
- "description": "The status of the launch template request. Any problems with the request\nwill be indicated in the error_details."
- },
"job": {
"$ref": "Job",
"description": "The job that was launched, if the request was not a dry run and\nthe job was successfully launched."
@@ -1634,67 +1403,6 @@
"description": "Defines a job to be run by the Cloud Dataflow service.",
"id": "Job",
"properties": {
- "steps": {
- "description": "The top-level steps that constitute the entire job.",
- "items": {
- "$ref": "Step"
- },
- "type": "array"
- },
- "replacedByJobId": {
- "description": "If another job is an update of this job (and thus, this job is in\n`JOB_STATE_UPDATED`), this field contains the ID of that job.",
- "type": "string"
- },
- "executionInfo": {
- "$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"
- },
- "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"
- ],
- "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`."
- ],
- "type": "string"
- },
- "location": {
- "description": "The location that contains this job.",
- "type": "string"
- },
- "currentStateTime": {
- "description": "The timestamp associated with the current state.",
- "format": "google-datetime",
- "type": "string"
- },
- "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"
- },
"labels": {
"additionalProperties": {
"type": "string"
@@ -1711,6 +1419,10 @@
"format": "google-datetime",
"type": "string"
},
+ "projectId": {
+ "description": "The ID of the Cloud Platform project that the job belongs to.",
+ "type": "string"
+ },
"type": {
"description": "The type of Cloud Dataflow job.",
"enum": [
@@ -1725,10 +1437,6 @@
],
"type": "string"
},
- "projectId": {
- "description": "The ID of the Cloud Platform project that the job belongs to.",
- "type": "string"
- },
"pipelineDescription": {
"$ref": "PipelineDescription",
"description": "Preliminary field: The format of this data may change at any time.\nA description of the user pipeline and stages through which it is executed.\nCreated by Cloud Dataflow service. Only retrieved with\nJOB_VIEW_DESCRIPTION or JOB_VIEW_ALL."
@@ -1777,6 +1485,67 @@
"name": {
"description": "The user-specified Cloud Dataflow job name.\n\nOnly one Job with a given name may exist in a project at any\ngiven time. If a caller attempts to create a Job with the same\nname as an already-existing Job, the attempt returns the\nexisting Job.\n\nThe name must match the regular expression\n`[a-z]([-a-z0-9]{0,38}[a-z0-9])?`",
"type": "string"
+ },
+ "steps": {
+ "description": "The top-level steps that constitute the entire job.",
+ "items": {
+ "$ref": "Step"
+ },
+ "type": "array"
+ },
+ "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"
+ },
+ "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"
+ },
+ "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"
+ ],
+ "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`."
+ ],
+ "type": "string"
+ },
+ "location": {
+ "description": "The location that contains this job.",
+ "type": "string"
+ },
+ "currentStateTime": {
+ "description": "The timestamp associated with the current state.",
+ "format": "google-datetime",
+ "type": "string"
+ },
+ "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": "object"
@@ -1785,17 +1554,23 @@
"description": "The result of a SourceOperationRequest, specified in\nReportWorkItemStatusRequest.source_operation when the work item\nis completed.",
"id": "SourceOperationResponse",
"properties": {
- "split": {
- "$ref": "SourceSplitResponse",
- "description": "A response to a request to split a source."
- },
"getMetadata": {
"$ref": "SourceGetMetadataResponse",
"description": "A response to a request to get metadata about a source."
+ },
+ "split": {
+ "$ref": "SourceSplitResponse",
+ "description": "A response to a request to split a source."
}
},
"type": "object"
},
+ "SendDebugCaptureResponse": {
+ "description": "Response to a send capture request.\nnothing",
+ "id": "SendDebugCaptureResponse",
+ "properties": {},
+ "type": "object"
+ },
"SideInputInfo": {
"description": "Information about a side input of a DoFn or an input of a SeqDoFn.",
"id": "SideInputInfo",
@@ -1822,12 +1597,6 @@
},
"type": "object"
},
- "SendDebugCaptureResponse": {
- "description": "Response to a send capture request.\nnothing",
- "id": "SendDebugCaptureResponse",
- "properties": {},
- "type": "object"
- },
"WriteInstruction": {
"description": "An instruction that writes records.\nTakes one input, produces no outputs.",
"id": "WriteInstruction",
@@ -1843,6 +1612,21 @@
},
"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"
+ },
"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",
@@ -1859,21 +1643,6 @@
},
"type": "object"
},
- "CounterStructuredNameAndMetadata": {
- "description": "A single message which encapsulates structured name and metadata for a given\ncounter.",
- "id": "CounterStructuredNameAndMetadata",
- "properties": {
- "name": {
- "$ref": "CounterStructuredName",
- "description": "Structured name of the counter."
- },
- "metadata": {
- "$ref": "CounterMetadata",
- "description": "Metadata associated with a counter"
- }
- },
- "type": "object"
- },
"AutoscalingSettings": {
"description": "Settings for WorkerPool autoscaling.",
"id": "AutoscalingSettings",
@@ -1904,16 +1673,16 @@
"description": "Describes full or partial data disk assignment information of the computation\nranges.",
"id": "StreamingComputationRanges",
"properties": {
+ "computationId": {
+ "description": "The ID of the computation.",
+ "type": "string"
+ },
"rangeAssignments": {
"description": "Data disk assignments for ranges from this computation.",
"items": {
"$ref": "KeyRangeDataDiskAssignment"
},
"type": "array"
- },
- "computationId": {
- "description": "The ID of the computation.",
- "type": "string"
}
},
"type": "object"
@@ -1922,6 +1691,32 @@
"description": "Description of the composing transforms, names/ids, and input/outputs of a\nstage of execution. Some composing transforms and sources may have been\ngenerated by the Dataflow service during execution planning.",
"id": "ExecutionStageSummary",
"properties": {
+ "kind": {
+ "description": "Type of tranform this stage is executing.",
+ "enum": [
+ "UNKNOWN_KIND",
+ "PAR_DO_KIND",
+ "GROUP_BY_KEY_KIND",
+ "FLATTEN_KIND",
+ "READ_KIND",
+ "WRITE_KIND",
+ "CONSTANT_KIND",
+ "SINGLETON_KIND",
+ "SHUFFLE_KIND"
+ ],
+ "enumDescriptions": [
+ "Unrecognized transform type.",
+ "ParDo transform.",
+ "Group By Key transform.",
+ "Flatten transform.",
+ "Read transform.",
+ "Write transform.",
+ "Constructs from a constant value, such as with Create.of.",
+ "Creates a Singleton view of a collection.",
+ "Opening or closing a shuffle session, often as part of a GroupByKey."
+ ],
+ "type": "string"
+ },
"outputSource": {
"description": "Output sources for this stage.",
"items": {
@@ -1957,32 +1752,6 @@
"$ref": "ComponentSource"
},
"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"
}
},
"type": "object"
@@ -2032,11 +1801,6 @@
"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",
@@ -2046,6 +1810,11 @@
"description": "Total active CPU time across all cores (ie., non-idle) in milliseconds\nsince start-up.",
"format": "uint64",
"type": "string"
+ },
+ "rate": {
+ "description": "Average CPU utilization rate (% non-idle cpu / second) since previous\nsample.",
+ "format": "double",
+ "type": "number"
}
},
"type": "object"
@@ -2054,6 +1823,33 @@
"description": "Describes the environment in which a Dataflow Job runs.",
"id": "Environment",
"properties": {
+ "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"
+ },
+ "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"
+ },
+ "internalExperiments": {
+ "additionalProperties": {
+ "description": "Properties of the object. Contains field @type with type URL.",
+ "type": "any"
+ },
+ "description": "Experimental settings.",
+ "type": "object"
+ },
"serviceAccountEmail": {
"description": "Identity to run virtual machines as. Defaults to the default account.",
"type": "string"
@@ -2088,33 +1884,6 @@
"$ref": "WorkerPool"
},
"type": "array"
- },
- "dataset": {
- "description": "The dataset for the current project where various workflow\nrelated tables are stored.\n\nThe supported resource type is:\n\nGoogle BigQuery:\n bigquery.googleapis.com/{dataset}",
- "type": "string"
- },
- "experiments": {
- "description": "The list of experiments to enable.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "version": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "description": "A structure describing which components and their versions of the service\nare required in order to run the job.",
- "type": "object"
- },
- "internalExperiments": {
- "additionalProperties": {
- "description": "Properties of the object. Contains field @type with type URL.",
- "type": "any"
- },
- "description": "Experimental settings.",
- "type": "object"
}
},
"type": "object"
@@ -2123,6 +1892,13 @@
"description": "A task which describes what action should be performed for the specified\nstreaming computation ranges.",
"id": "StreamingComputationTask",
"properties": {
+ "dataDisks": {
+ "description": "Describes the set of data disks this task should apply to.",
+ "items": {
+ "$ref": "MountedDataDisk"
+ },
+ "type": "array"
+ },
"taskType": {
"description": "A type of streaming computation task.",
"enum": [
@@ -2143,13 +1919,6 @@
"$ref": "StreamingComputationRanges"
},
"type": "array"
- },
- "dataDisks": {
- "description": "Describes the set of data disks this task should apply to.",
- "items": {
- "$ref": "MountedDataDisk"
- },
- "type": "array"
}
},
"type": "object"
@@ -2158,10 +1927,6 @@
"description": "Request to send encoded debug information.",
"id": "SendDebugCaptureRequest",
"properties": {
- "data": {
- "description": "The encoded debug information.",
- "type": "string"
- },
"componentId": {
"description": "The internal component id for which debug information is sent.",
"type": "string"
@@ -2169,6 +1934,10 @@
"workerId": {
"description": "The worker id, i.e., VM hostname.",
"type": "string"
+ },
+ "data": {
+ "description": "The encoded debug information.",
+ "type": "string"
}
},
"type": "object"
@@ -2188,10 +1957,6 @@
"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"
- },
"userName": {
"description": "Human-readable name for this transform; may be user or system generated.",
"type": "string"
@@ -2199,6 +1964,10 @@
"originalTransform": {
"description": "User name for the original user transform with which this transform is\nmost closely associated.",
"type": "string"
+ },
+ "name": {
+ "description": "Dataflow service generated name for this source.",
+ "type": "string"
}
},
"type": "object"
@@ -2232,22 +2001,14 @@
"description": "Identifies a pubsub location to use for transferring data into or\nout of a streaming Dataflow job.",
"id": "PubsubLocation",
"properties": {
- "withAttributes": {
- "description": "If true, then the client has requested to get pubsub attributes.",
- "type": "boolean"
- },
- "idLabel": {
- "description": "If set, contains a pubsub label from which to extract record ids.\nIf left empty, record deduplication will be strictly best effort.",
+ "topic": {
+ "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"",
"type": "string"
},
"timestampLabel": {
"description": "If set, contains a pubsub label from which to extract record timestamps.\nIf left empty, record timestamps will be generated upon arrival.",
"type": "string"
},
- "topic": {
- "description": "A pubsub topic, in the form of\n\"pubsub.googleapis.com/topics/<project-id>/<topic-name>\"",
- "type": "string"
- },
"subscription": {
"description": "A pubsub subscription, in the form of\n\"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>\"",
"type": "string"
@@ -2259,6 +2020,14 @@
"trackingSubscription": {
"description": "If set, specifies the pubsub subscription that will be used for tracking\ncustom time timestamps for watermark estimation.",
"type": "string"
+ },
+ "withAttributes": {
+ "description": "If true, then the client has requested to get pubsub attributes.",
+ "type": "boolean"
+ },
+ "idLabel": {
+ "description": "If set, contains a pubsub label from which to extract record ids.\nIf left empty, record deduplication will be strictly best effort.",
+ "type": "string"
}
},
"type": "object"
@@ -2299,6 +2068,11 @@
"description": "A particular message pertaining to a Dataflow job.",
"id": "JobMessage",
"properties": {
+ "time": {
+ "description": "The timestamp of the message.",
+ "format": "google-datetime",
+ "type": "string"
+ },
"id": {
"description": "Identifies the message. This is automatically generated by the\nservice; the caller should treat it as an opaque string.",
"type": "string"
@@ -2326,11 +2100,6 @@
"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"
- },
- "time": {
- "description": "The timestamp of the message.",
- "format": "google-datetime",
- "type": "string"
}
},
"type": "object"
@@ -2339,6 +2108,13 @@
"description": "Metadata for a specific parameter.",
"id": "ParameterMetadata",
"properties": {
+ "regexes": {
+ "description": "Optional. Regexes that the parameter must match.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
"label": {
"description": "Required. The label to display for the parameter.",
"type": "string"
@@ -2354,13 +2130,6 @@
"name": {
"description": "Required. The name of the parameter.",
"type": "string"
- },
- "regexes": {
- "description": "Optional. Regexes that the parameter must match.",
- "items": {
- "type": "string"
- },
- "type": "array"
}
},
"type": "object"
@@ -2482,14 +2251,14 @@
"description": "The location on the worker for task-specific subdirectories.",
"type": "string"
},
- "languageHint": {
- "description": "The suggested backend language.",
- "type": "string"
- },
"commandlinesFileName": {
"description": "The file to store preprocessing commands in.",
"type": "string"
},
+ "languageHint": {
+ "description": "The suggested backend language.",
+ "type": "string"
+ },
"baseUrl": {
"description": "The base URL for the taskrunner to use when accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
"type": "string"
@@ -2534,15 +2303,15 @@
"description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED\nsharding).",
"type": "string"
},
- "concatPosition": {
- "$ref": "ConcatPosition",
- "description": "CloudPosition is a concat position."
- },
"byteOffset": {
"description": "Position is a byte offset.",
"format": "int64",
"type": "string"
},
+ "concatPosition": {
+ "$ref": "ConcatPosition",
+ "description": "CloudPosition is a concat position."
+ },
"end": {
"description": "Position is past all other positions. Also useful for the end\nposition of an unbounded range.",
"type": "boolean"
@@ -2575,21 +2344,6 @@
"description": "A source that records can be read and decoded from.",
"id": "Source",
"properties": {
- "metadata": {
- "$ref": "SourceMetadata",
- "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
- },
- "baseSpecs": {
- "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).",
- "items": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "type": "object"
- },
- "type": "array"
- },
"codec": {
"additionalProperties": {
"description": "Properties of the object.",
@@ -2609,32 +2363,29 @@
},
"description": "The source to read from, plus its parameters.",
"type": "object"
- }
- },
- "type": "object"
- },
- "WorkerPool": {
- "description": "Describes one particular pool of Cloud Dataflow workers to be\ninstantiated by the Cloud Dataflow service in order to perform the\ncomputations required by a job. Note that a workflow job may use\nmultiple pools, in order to match the various computational\nrequirements of the various stages of the job.",
- "id": "WorkerPool",
- "properties": {
- "numThreadsPerWorker": {
- "description": "The number of threads per worker harness. If empty or unspecified, the\nservice will choose a number of threads (according to the number of cores\non the selected machine type for batch, or 1 by convention for streaming).",
- "format": "int32",
- "type": "integer"
},
- "zone": {
- "description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
- "type": "string"
- },
- "numWorkers": {
- "description": "Number of Google Compute Engine workers in this pool needed to\nexecute the job. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
- "format": "int32",
- "type": "integer"
- },
- "diskSourceImage": {
- "description": "Fully qualified source image for disks.",
- "type": "string"
+ "metadata": {
+ "$ref": "SourceMetadata",
+ "description": "Optionally, metadata for this source can be supplied right away,\navoiding a SourceGetMetadataOperation roundtrip\n(see SourceOperationRequest).\n\nThis field is meaningful only in the Source objects populated\nby the user (e.g. when filling in a DerivedSource).\nSource objects supplied by the framework to the user don't have\nthis field populated."
},
+ "baseSpecs": {
+ "description": "While splitting, sources may specify the produced bundles\nas differences against another source, in order to save backend-side\nmemory and allow bigger jobs. For details, see SourceSplitRequest.\nTo support this use case, the full set of parameters of the source\nis logically obtained by taking the latest explicitly specified value\nof each parameter in the order:\nbase_specs (later items win), spec (overrides anything in base_specs).",
+ "items": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "WorkerPool": {
+ "description": "Describes one particular pool of Cloud Dataflow workers to be\ninstantiated by the Cloud Dataflow service in order to perform the\ncomputations required by a job. Note that a workflow job may use\nmultiple pools, in order to match the various computational\nrequirements of the various stages of the job.",
+ "id": "WorkerPool",
+ "properties": {
"packages": {
"description": "Packages to be installed on workers.",
"items": {
@@ -2679,14 +2430,14 @@
"description": "Required. Docker container image that executes the Cloud Dataflow worker\nharness, residing in Google Container Registry.",
"type": "string"
},
- "machineType": {
- "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
- "type": "string"
- },
"diskType": {
"description": "Type of root disk for VMs. If empty or unspecified, the service will\nattempt to choose a reasonable default.",
"type": "string"
},
+ "machineType": {
+ "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the\nservice will attempt to choose a reasonable default.",
+ "type": "string"
+ },
"kind": {
"description": "The kind of the worker pool; currently only `harness` and `shuffle`\nare supported.",
"type": "string"
@@ -2716,14 +2467,14 @@
],
"type": "string"
},
- "autoscalingSettings": {
- "$ref": "AutoscalingSettings",
- "description": "Settings for autoscaling of this WorkerPool."
- },
"taskrunnerSettings": {
"$ref": "TaskRunnerSettings",
"description": "Settings passed through to Google Compute Engine workers when\nusing the standard Dataflow task runner. Users should ignore\nthis field."
},
+ "autoscalingSettings": {
+ "$ref": "AutoscalingSettings",
+ "description": "Settings for autoscaling of this WorkerPool."
+ },
"metadata": {
"additionalProperties": {
"type": "string"
@@ -2750,6 +2501,24 @@
"network": {
"description": "Network to which VMs will be assigned. If empty or unspecified,\nthe service will use the network \"default\".",
"type": "string"
+ },
+ "zone": {
+ "description": "Zone to run the worker pools in. If empty or unspecified, the service\nwill attempt to choose a reasonable default.",
+ "type": "string"
+ },
+ "numWorkers": {
+ "description": "Number of Google Compute Engine workers in this pool needed to\nexecute the job. If zero or unspecified, the service will\nattempt to choose a reasonable default.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "numThreadsPerWorker": {
+ "description": "The number of threads per worker harness. If empty or unspecified, the\nservice will choose a number of threads (according to the number of cores\non the selected machine type for batch, or 1 by convention for streaming).",
+ "format": "int32",
+ "type": "integer"
+ },
+ "diskSourceImage": {
+ "description": "Fully qualified source image for disks.",
+ "type": "string"
}
},
"type": "object"
@@ -2773,14 +2542,45 @@
"description": "WorkItem represents basic information about a WorkItem to be executed\nin the cloud.",
"id": "WorkItem",
"properties": {
- "shellTask": {
- "$ref": "ShellTask",
- "description": "Additional information for ShellTask WorkItems."
+ "projectId": {
+ "description": "Identifies the cloud project this WorkItem belongs to.",
+ "type": "string"
+ },
+ "reportStatusInterval": {
+ "description": "Recommended reporting interval.",
+ "format": "google-duration",
+ "type": "string"
+ },
+ "sourceOperationTask": {
+ "$ref": "SourceOperationRequest",
+ "description": "Additional information for source operation WorkItems."
+ },
+ "streamingSetupTask": {
+ "$ref": "StreamingSetupTask",
+ "description": "Additional information for StreamingSetupTask WorkItems."
+ },
+ "streamingConfigTask": {
+ "$ref": "StreamingConfigTask",
+ "description": "Additional information for StreamingConfigTask WorkItems."
+ },
+ "leaseExpireTime": {
+ "description": "Time when the lease on this Work will expire.",
+ "format": "google-datetime",
+ "type": "string"
+ },
+ "initialReportIndex": {
+ "description": "The initial index to use when reporting the status of the WorkItem.",
+ "format": "int64",
+ "type": "string"
},
"streamingComputationTask": {
"$ref": "StreamingComputationTask",
"description": "Additional information for StreamingComputationTask WorkItems."
},
+ "shellTask": {
+ "$ref": "ShellTask",
+ "description": "Additional information for ShellTask WorkItems."
+ },
"jobId": {
"description": "Identifies the workflow job this WorkItem belongs to.",
"type": "string"
@@ -2808,53 +2608,6 @@
"$ref": "Package"
},
"type": "array"
- },
- "projectId": {
- "description": "Identifies the cloud project this WorkItem belongs to.",
- "type": "string"
- },
- "sourceOperationTask": {
- "$ref": "SourceOperationRequest",
- "description": "Additional information for source operation WorkItems."
- },
- "streamingSetupTask": {
- "$ref": "StreamingSetupTask",
- "description": "Additional information for StreamingSetupTask WorkItems."
- },
- "reportStatusInterval": {
- "description": "Recommended reporting interval.",
- "format": "google-duration",
- "type": "string"
- },
- "streamingConfigTask": {
- "$ref": "StreamingConfigTask",
- "description": "Additional information for StreamingConfigTask WorkItems."
- },
- "leaseExpireTime": {
- "description": "Time when the lease on this Work will expire.",
- "format": "google-datetime",
- "type": "string"
- },
- "initialReportIndex": {
- "description": "The initial index to use when reporting the status of the WorkItem.",
- "format": "int64",
- "type": "string"
- }
- },
- "type": "object"
- },
- "ReportedParallelism": {
- "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.",
- "id": "ReportedParallelism",
- "properties": {
- "value": {
- "description": "Specifies the level of parallelism in case it is finite.",
- "format": "double",
- "type": "number"
- },
- "isInfinite": {
- "description": "Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack.",
- "type": "boolean"
}
},
"type": "object"
@@ -2873,10 +2626,38 @@
},
"type": "object"
},
+ "ReportedParallelism": {
+ "description": "Represents the level of parallelism in a WorkItem's input,\nreported by the worker.",
+ "id": "ReportedParallelism",
+ "properties": {
+ "isInfinite": {
+ "description": "Specifies whether the parallelism is infinite. If true, \"value\" is\nignored.\nInfinite parallelism means the service will assume that the work item\ncan always be split into more non-empty work items by dynamic splitting.\nThis is a work-around for lack of support for infinity by the current\nJSON-based Java RPC stack.",
+ "type": "boolean"
+ },
+ "value": {
+ "description": "Specifies the level of parallelism in case it is finite.",
+ "format": "double",
+ "type": "number"
+ }
+ },
+ "type": "object"
+ },
"TopologyConfig": {
"description": "Global topology of the streaming Dataflow job, including all\ncomputations and their sharded locations.",
"id": "TopologyConfig",
"properties": {
+ "forwardingKeyBits": {
+ "description": "The size (in bits) of keys that will be assigned to source messages.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "userStageToComputationNameMap": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Maps user stage names to stable computation names.",
+ "type": "object"
+ },
"computations": {
"description": "The computations associated with a streaming Dataflow job.",
"items": {
@@ -2895,18 +2676,6 @@
"description": "Version number for persistent state.",
"format": "int32",
"type": "integer"
- },
- "forwardingKeyBits": {
- "description": "The size (in bits) of keys that will be assigned to source messages.",
- "format": "int32",
- "type": "integer"
- },
- "userStageToComputationNameMap": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "Maps user stage names to stable computation names.",
- "type": "object"
}
},
"type": "object"
@@ -2943,18 +2712,6 @@
"description": "Provides data to pass through to the worker harness.",
"id": "WorkerSettings",
"properties": {
- "tempStoragePrefix": {
- "description": "The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
- "type": "string"
- },
- "baseUrl": {
- "description": "The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
- "type": "string"
- },
- "reportingEnabled": {
- "description": "Whether to send work progress updates to the service.",
- "type": "boolean"
- },
"servicePath": {
"description": "The Cloud Dataflow service path relative to the root URL, for example,\n\"dataflow/v1b3/projects\".",
"type": "string"
@@ -2966,17 +2723,18 @@
"workerId": {
"description": "The ID of the worker running this pipeline.",
"type": "string"
- }
- },
- "type": "object"
- },
- "StreamingStageLocation": {
- "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.",
- "id": "StreamingStageLocation",
- "properties": {
- "streamId": {
- "description": "Identifies the particular stream within the streaming Dataflow\njob.",
+ },
+ "tempStoragePrefix": {
+ "description": "The prefix of the resources the system should use for temporary\nstorage.\n\nThe supported resource type is:\n\nGoogle Cloud Storage:\n\n storage.googleapis.com/{bucket}/{object}\n bucket.storage.googleapis.com/{object}",
+ "type": "string"
+ },
+ "baseUrl": {
+ "description": "The base URL for accessing Google Cloud APIs.\n\nWhen workers access Google Cloud APIs, they logically do so via\nrelative URLs. If this field is specified, it supplies the base\nURL to use for resolving these relative URLs. The normative\nalgorithm used is defined by RFC 1808, \"Relative Uniform Resource\nLocators\".\n\nIf not specified, the default value is \"http://www.googleapis.com/\"",
"type": "string"
+ },
+ "reportingEnabled": {
+ "description": "Whether to send work progress updates to the service.",
+ "type": "boolean"
}
},
"type": "object"
@@ -2985,16 +2743,27 @@
"description": "Data disk assignment for a given VM instance.",
"id": "DataDiskAssignment",
"properties": {
- "vmInstance": {
- "description": "VM instance name the data disks mounted to, for example\n\"myproject-1014-104817-4c2-harness-0\".",
- "type": "string"
- },
"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"
+ },
+ "StreamingStageLocation": {
+ "description": "Identifies the location of a streaming computation stage, for\nstage-to-stage communication.",
+ "id": "StreamingStageLocation",
+ "properties": {
+ "streamId": {
+ "description": "Identifies the particular stream within the streaming Dataflow\njob.",
+ "type": "string"
}
},
"type": "object"
@@ -3019,6 +2788,15 @@
"description": "The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` which can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting purpose.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons.",
"id": "Status",
"properties": {
+ "code": {
+ "description": "The status code, which should be an enum value of google.rpc.Code.",
+ "format": "int32",
+ "type": "integer"
+ },
+ "message": {
+ "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
+ "type": "string"
+ },
"details": {
"description": "A list of messages that carry the error details. There will be a\ncommon set of message types for APIs to use.",
"items": {
@@ -3029,15 +2807,6 @@
"type": "object"
},
"type": "array"
- },
- "code": {
- "description": "The status code, which should be an enum value of google.rpc.Code.",
- "format": "int32",
- "type": "integer"
- },
- "message": {
- "description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
- "type": "string"
}
},
"type": "object"
@@ -3079,14 +2848,26 @@
},
"type": "object"
},
- "LeaseWorkItemResponse": {
- "description": "Response to a request to lease WorkItems.",
- "id": "LeaseWorkItemResponse",
+ "StreamingComputationConfig": {
+ "description": "Configuration information for a single streaming computation.",
+ "id": "StreamingComputationConfig",
"properties": {
- "workItems": {
- "description": "A list of the leased WorkItems.",
+ "computationId": {
+ "description": "Unique identifier for this computation.",
+ "type": "string"
+ },
+ "systemName": {
+ "description": "System defined name for this computation.",
+ "type": "string"
+ },
+ "stageName": {
+ "description": "Stage name of this computation.",
+ "type": "string"
+ },
+ "instructions": {
+ "description": "Instructions that comprise the computation.",
"items": {
- "$ref": "WorkItem"
+ "$ref": "ParallelInstruction"
},
"type": "array"
}
@@ -3097,25 +2878,21 @@
"description": "Description of the type, names/ids, and input/outputs for a transform.",
"id": "TransformSummary",
"properties": {
- "name": {
- "description": "User provided name for this transform instance.",
- "type": "string"
- },
"id": {
"description": "SDK generated id of this transform instance.",
"type": "string"
},
- "displayData": {
- "description": "Transform-specific display data.",
+ "outputCollectionName": {
+ "description": "User names for all collection outputs to this transform.",
"items": {
- "$ref": "DisplayData"
+ "type": "string"
},
"type": "array"
},
- "outputCollectionName": {
- "description": "User names for all collection outputs to this transform.",
+ "displayData": {
+ "description": "Transform-specific display data.",
"items": {
- "type": "string"
+ "$ref": "DisplayData"
},
"type": "array"
},
@@ -3151,32 +2928,46 @@
"type": "string"
},
"type": "array"
+ },
+ "name": {
+ "description": "User provided name for this transform instance.",
+ "type": "string"
}
},
"type": "object"
},
- "StreamingComputationConfig": {
- "description": "Configuration information for a single streaming computation.",
- "id": "StreamingComputationConfig",
+ "LeaseWorkItemResponse": {
+ "description": "Response to a request to lease WorkItems.",
+ "id": "LeaseWorkItemResponse",
"properties": {
- "computationId": {
- "description": "Unique identifier for this computation.",
- "type": "string"
- },
- "systemName": {
- "description": "System defined name for this computation.",
+ "workItems": {
+ "description": "A list of the leased WorkItems.",
+ "items": {
+ "$ref": "WorkItem"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "LaunchTemplateParameters": {
+ "description": "Parameters to provide to the template being launched.",
+ "id": "LaunchTemplateParameters",
+ "properties": {
+ "jobName": {
+ "description": "Required. The job name to use for the created job.",
"type": "string"
},
- "stageName": {
- "description": "Stage name of this computation.",
- "type": "string"
+ "environment": {
+ "$ref": "RuntimeEnvironment",
+ "description": "The runtime environment for the job."
},
- "instructions": {
- "description": "Instructions that comprise the computation.",
- "items": {
- "$ref": "ParallelInstruction"
+ "parameters": {
+ "additionalProperties": {
+ "type": "string"
},
- "type": "array"
+ "description": "The runtime parameters to pass to the job.",
+ "type": "object"
}
},
"type": "object"
@@ -3204,28 +2995,6 @@
},
"type": "object"
},
- "LaunchTemplateParameters": {
- "description": "Parameters to provide to the template being launched.",
- "id": "LaunchTemplateParameters",
- "properties": {
- "environment": {
- "$ref": "RuntimeEnvironment",
- "description": "The runtime environment for the job."
- },
- "parameters": {
- "additionalProperties": {
- "type": "string"
- },
- "description": "The runtime parameters to pass to the job.",
- "type": "object"
- },
- "jobName": {
- "description": "Required. The job name to use for the created job.",
- "type": "string"
- }
- },
- "type": "object"
- },
"FlattenInstruction": {
"description": "An instruction that copies its inputs (zero or more) to its (single) output.",
"id": "FlattenInstruction",
@@ -3244,26 +3013,14 @@
"description": "An instruction that does a partial group-by-key.\nOne input and one output.",
"id": "PartialGroupByKeyInstruction",
"properties": {
- "valueCombiningFn": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "description": "The value combining function to invoke.",
- "type": "object"
- },
- "inputElementCodec": {
- "additionalProperties": {
- "description": "Properties of the object.",
- "type": "any"
- },
- "description": "The codec to use for interpreting an element in the input PTable.",
- "type": "object"
- },
"originalCombineValuesInputStoreName": {
"description": "If this instruction includes a combining function this is the name of the\nintermediate store between the GBK and the CombineValues.",
"type": "string"
},
+ "originalCombineValuesStepName": {
+ "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
+ "type": "string"
+ },
"sideInputs": {
"description": "Zero or more side inputs.",
"items": {
@@ -3271,13 +3028,25 @@
},
"type": "array"
},
- "originalCombineValuesStepName": {
- "description": "If this instruction includes a combining function, this is the name of the\nCombineValues instruction lifted into this instruction.",
- "type": "string"
- },
"input": {
"$ref": "InstructionInput",
"description": "Describes the input to the partial group-by-key instruction."
+ },
+ "inputElementCodec": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "description": "The codec to use for interpreting an element in the input PTable.",
+ "type": "object"
+ },
+ "valueCombiningFn": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "description": "The value combining function to invoke.",
+ "type": "object"
}
},
"type": "object"
@@ -3303,10 +3072,6 @@
"description": "Description of an input or output of an execution stage.",
"id": "StageSource",
"properties": {
- "originalTransformOrCollection": {
- "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
- "type": "string"
- },
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
@@ -3319,6 +3084,10 @@
"userName": {
"description": "Human-readable name for this source; may be user or system generated.",
"type": "string"
+ },
+ "originalTransformOrCollection": {
+ "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
+ "type": "string"
}
},
"type": "object"
@@ -3341,6 +3110,10 @@
"description": "Data provided with a pipeline or transform to provide descriptive info.",
"id": "DisplayData",
"properties": {
+ "strValue": {
+ "description": "Contains value if the data is of string type.",
+ "type": "string"
+ },
"durationValue": {
"description": "Contains value if the data is of duration type.",
"format": "google-duration",
@@ -3381,40 +3154,37 @@
"format": "google-datetime",
"type": "string"
},
- "javaClassValue": {
- "description": "Contains value if the data is of java class type.",
- "type": "string"
- },
"boolValue": {
"description": "Contains value if the data is of a boolean type.",
"type": "boolean"
},
- "strValue": {
- "description": "Contains value if the data is of string type.",
+ "javaClassValue": {
+ "description": "Contains value if the data is of java class type.",
"type": "string"
}
},
"type": "object"
},
- "GetDebugConfigRequest": {
- "description": "Request to get updated debug configuration for component.",
- "id": "GetDebugConfigRequest",
+ "LeaseWorkItemRequest": {
+ "description": "Request to lease WorkItems.",
+ "id": "LeaseWorkItemRequest",
"properties": {
+ "workerCapabilities": {
+ "description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
"workerId": {
- "description": "The worker id, i.e., VM hostname.",
+ "description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
"type": "string"
},
- "componentId": {
- "description": "The internal component id for which debug configuration is\nrequested.",
+ "requestedLeaseDuration": {
+ "description": "The initial lease period.",
+ "format": "google-duration",
"type": "string"
- }
- },
- "type": "object"
- },
- "LeaseWorkItemRequest": {
- "description": "Request to lease WorkItems.",
- "id": "LeaseWorkItemRequest",
- "properties": {
+ },
"currentWorkerTime": {
"description": "The current timestamp at the worker.",
"format": "google-datetime",
@@ -3430,21 +3200,20 @@
"type": "string"
},
"type": "array"
- },
- "workerCapabilities": {
- "description": "Worker capabilities. WorkItems might be limited to workers with specific\ncapabilities.",
- "items": {
- "type": "string"
- },
- "type": "array"
- },
+ }
+ },
+ "type": "object"
+ },
+ "GetDebugConfigRequest": {
+ "description": "Request to get updated debug configuration for component.",
+ "id": "GetDebugConfigRequest",
+ "properties": {
"workerId": {
- "description": "Identifies the worker leasing work -- typically the ID of the\nvirtual machine running the worker.",
+ "description": "The worker id, i.e., VM hostname.",
"type": "string"
},
- "requestedLeaseDuration": {
- "description": "The initial lease period.",
- "format": "google-duration",
+ "componentId": {
+ "description": "The internal component id for which debug configuration is\nrequested.",
"type": "string"
}
},
@@ -3454,13 +3223,13 @@
"description": "The response to a GetTemplate request.",
"id": "GetTemplateResponse",
"properties": {
- "status": {
- "$ref": "Status",
- "description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
- },
"metadata": {
"$ref": "TemplateMetadata",
"description": "The template metadata describing the template name, available\nparameters, etc."
+ },
+ "status": {
+ "$ref": "Status",
+ "description": "The status of the get template request. Any problems with the\nrequest will be indicated in the error_details."
}
},
"type": "object"
@@ -3492,51 +3261,65 @@
},
"type": "object"
},
- "StreamingConfigTask": {
- "description": "A task that carries configuration information for streaming computations.",
- "id": "StreamingConfigTask",
+ "PipelineDescription": {
+ "description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.",
+ "id": "PipelineDescription",
"properties": {
- "streamingComputationConfigs": {
- "description": "Set of computation configuration information.",
+ "displayData": {
+ "description": "Pipeline level display data.",
"items": {
- "$ref": "StreamingComputationConfig"
+ "$ref": "DisplayData"
},
"type": "array"
},
- "userStepToStateFamilyNameMap": {
- "additionalProperties": {
- "type": "string"
+ "executionPipelineStage": {
+ "description": "Description of each stage of execution of the pipeline.",
+ "items": {
+ "$ref": "ExecutionStageSummary"
},
- "description": "Map from user step names to state families.",
- "type": "object"
- }
- },
- "type": "object"
- },
- "PipelineDescription": {
- "description": "A descriptive representation of submitted pipeline as well as the executed\nform. This data is provided by the Dataflow service for ease of visualizing\nthe pipeline and interpretting Dataflow provided metrics.",
- "id": "PipelineDescription",
- "properties": {
+ "type": "array"
+ },
"originalPipelineTransform": {
"description": "Description of each transform in the pipeline and collections between them.",
"items": {
"$ref": "TransformSummary"
},
"type": "array"
- },
- "displayData": {
- "description": "Pipeline level display data.",
+ }
+ },
+ "type": "object"
+ },
+ "StreamingConfigTask": {
+ "description": "A task that carries configuration information for streaming computations.",
+ "id": "StreamingConfigTask",
+ "properties": {
+ "streamingComputationConfigs": {
+ "description": "Set of computation configuration information.",
"items": {
- "$ref": "DisplayData"
+ "$ref": "StreamingComputationConfig"
},
"type": "array"
},
- "executionPipelineStage": {
- "description": "Description of each stage of execution of the pipeline.",
- "items": {
- "$ref": "ExecutionStageSummary"
+ "userStepToStateFamilyNameMap": {
+ "additionalProperties": {
+ "type": "string"
},
- "type": "array"
+ "description": "Map from user step names to state families.",
+ "type": "object"
+ }
+ },
+ "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": {
+ "$ref": "JobExecutionStageInfo"
+ },
+ "description": "A mapping from each stage to the information about that stage.",
+ "type": "object"
}
},
"type": "object"
@@ -3564,20 +3347,6 @@
},
"type": "object"
},
- "JobExecutionInfo": {
- "description": "Additional information about how a Cloud Dataflow job will be executed that\nisn't contained in the submitted job.",
- "id": "JobExecutionInfo",
- "properties": {
- "stages": {
- "additionalProperties": {
- "$ref": "JobExecutionStageInfo"
- },
- "description": "A mapping from each stage to the information about that stage.",
- "type": "object"
- }
- },
- "type": "object"
- },
"FailedLocation": {
"description": "Indicates which location failed to respond to a request for data.",
"id": "FailedLocation",
@@ -3613,34 +3382,6 @@
"description": "CounterMetadata includes all static non-name non-value counter attributes.",
"id": "CounterMetadata",
"properties": {
- "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"
- },
- "otherUnits": {
- "description": "A string referring to the unit type.",
- "type": "string"
- },
"kind": {
"description": "Counter aggregation kind.",
"enum": [
@@ -3670,6 +3411,34 @@
"description": {
"description": "Human-readable description of the counter semantics.",
"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"
+ },
+ "otherUnits": {
+ "description": "A string referring to the unit type.",
+ "type": "string"
}
},
"type": "object"
@@ -3696,15 +3465,6 @@
"description": "A progress measurement of a WorkItem by a worker.",
"id": "ApproximateReportedProgress",
"properties": {
- "position": {
- "$ref": "Position",
- "description": "A Position within the work to represent a progress."
- },
- "fractionConsumed": {
- "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing\nconsumed), to 1.0 (end of the input, entire input consumed).",
- "format": "double",
- "type": "number"
- },
"consumedParallelism": {
"$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."
@@ -3712,21 +3472,15 @@
"remainingParallelism": {
"$ref": "ReportedParallelism",
"description": "Total amount of parallelism in the input of this task that remains,\n(i.e. can be delegated to this task and any new tasks via dynamic\nsplitting). Always at least 1 for non-finished work items and 0 for\nfinished.\n\n\"Amount of parallelism\" refers to how many non-empty parts of the input\ncan be read in parallel. This does not necessarily equal number\nof records. An input that can be read in parallel down to the\nindividual records is called \"perfectly splittable\".\nAn example of non-perfectly parallelizable input is a block-compressed\nfile format where a block of records has to be read as a whole,\nbut different blocks can be read in parallel.\n\nExamples:\n* If we are processing record #30 (starting at 1) out of 50 in a perfectly\n splittable 50-record input, this value should be 21 (20 remaining + 1\n current).\n* If we are reading through block 3 in a block-compressed file consisting\n of 5 blocks, this value should be 3 (since blocks 4 and 5 can be\n processed in parallel by new tasks via dynamic splitting and the current\n task remains processing block 3).\n* If we are reading through the last block in a block-compressed file,\n or reading or processing the last record in a perfectly splittable\n input, this value should be 1, because apart from the current task, no\n additional remainder can be split off."
- }
- },
- "type": "object"
- },
- "StateFamilyConfig": {
- "description": "State family configuration.",
- "id": "StateFamilyConfig",
- "properties": {
- "stateFamily": {
- "description": "The state family value.",
- "type": "string"
},
- "isRead": {
- "description": "If true, this family corresponds to a read operation.",
- "type": "boolean"
+ "position": {
+ "$ref": "Position",
+ "description": "A Position within the work to represent a progress."
+ },
+ "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"
}
},
"type": "object"
@@ -3745,6 +3499,21 @@
},
"type": "object"
},
+ "StateFamilyConfig": {
+ "description": "State family configuration.",
+ "id": "StateFamilyConfig",
+ "properties": {
+ "isRead": {
+ "description": "If true, this family corresponds to a read operation.",
+ "type": "boolean"
+ },
+ "stateFamily": {
+ "description": "The state family value.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
"ResourceUtilizationReportResponse": {
"description": "Service-side response to WorkerMessage reporting resource utilization.",
"id": "ResourceUtilizationReportResponse",
@@ -3755,6 +3524,13 @@
"description": "The response to a SourceSplitRequest.",
"id": "SourceSplitResponse",
"properties": {
+ "shards": {
+ "description": "DEPRECATED in favor of bundles.",
+ "items": {
+ "$ref": "SourceSplitShard"
+ },
+ "type": "array"
+ },
"outcome": {
"description": "Indicates whether splitting happened and produced a list of bundles.\nIf this is USE_CURRENT_SOURCE_AS_IS, the current source should\nbe processed \"as is\" without splitting. \"bundles\" is ignored in this case.\nIf this is SPLITTING_HAPPENED, then \"bundles\" contains a list of\nbundles into which the source was split.",
"enum": [
@@ -3775,13 +3551,6 @@
"$ref": "DerivedSource"
},
"type": "array"
- },
- "shards": {
- "description": "DEPRECATED in favor of bundles.",
- "items": {
- "$ref": "SourceSplitShard"
- },
- "type": "array"
}
},
"type": "object"
@@ -3790,22 +3559,6 @@
"description": "Describes a particular operation comprising a MapTask.",
"id": "ParallelInstruction",
"properties": {
- "flatten": {
- "$ref": "FlattenInstruction",
- "description": "Additional information for Flatten instructions."
- },
- "originalName": {
- "description": "System-defined name for the operation in the original workflow graph.",
- "type": "string"
- },
- "write": {
- "$ref": "WriteInstruction",
- "description": "Additional information for Write instructions."
- },
- "systemName": {
- "description": "System-defined name of this operation.\nUnique across the workflow.",
- "type": "string"
- },
"partialGroupByKey": {
"$ref": "PartialGroupByKeyInstruction",
"description": "Additional information for PartialGroupByKey instructions."
@@ -3821,13 +3574,29 @@
"description": "User-provided name of this operation.",
"type": "string"
},
+ "read": {
+ "$ref": "ReadInstruction",
+ "description": "Additional information for Read instructions."
+ },
"parDo": {
"$ref": "ParDoInstruction",
"description": "Additional information for ParDo instructions."
},
- "read": {
- "$ref": "ReadInstruction",
- "description": "Additional information for Read instructions."
+ "originalName": {
+ "description": "System-defined name for the operation in the original workflow graph.",
+ "type": "string"
+ },
+ "flatten": {
+ "$ref": "FlattenInstruction",
+ "description": "Additional information for Flatten instructions."
+ },
+ "systemName": {
+ "description": "System-defined name of this operation.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "write": {
+ "$ref": "WriteInstruction",
+ "description": "Additional information for Write instructions."
}
},
"type": "object"
@@ -3965,6 +3734,18 @@
"description": "Describes the state of a metric.",
"id": "MetricUpdate",
"properties": {
+ "set": {
+ "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.",
+ "type": "any"
+ },
+ "internal": {
+ "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
+ "type": "any"
+ },
+ "cumulative": {
+ "description": "True if this metric is reported as the total cumulative aggregate\nvalue accumulated since the worker started working on this WorkItem.\nBy default this is false, indicating that this metric is reported\nas a delta that is not associated with any WorkItem.",
+ "type": "boolean"
+ },
"kind": {
"description": "Metric aggregation kind. The possible metric aggregation kinds are\n\"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", and \"Or\".\nThe specified aggregation kind is case-insensitive.\n\nIf omitted, this is not an aggregated value but instead\na single metric sample value.",
"type": "string"
@@ -3989,18 +3770,6 @@
"name": {
"$ref": "MetricStructuredName",
"description": "Name of the metric."
- },
- "set": {
- "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only\npossible value type is a list of Values whose type can be Long, Double,\nor String, according to the metric's type. All Values in the list must\nbe of the same type.",
- "type": "any"
- },
- "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"
- },
- "internal": {
- "description": "Worker-computed aggregate value for internal use by the Dataflow\nservice.",
- "type": "any"
}
},
"type": "object"
@@ -4009,10 +3778,6 @@
"description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest.",
"id": "ApproximateProgress",
"properties": {
- "position": {
- "$ref": "Position",
- "description": "Obsolete."
- },
"percentComplete": {
"description": "Obsolete.",
"format": "float",
@@ -4022,6 +3787,10 @@
"description": "Obsolete.",
"format": "google-duration",
"type": "string"
+ },
+ "position": {
+ "$ref": "Position",
+ "description": "Obsolete."
}
},
"type": "object"
@@ -4045,6 +3814,10 @@
"description": "Metadata describing a template.",
"id": "TemplateMetadata",
"properties": {
+ "bypassTempDirValidation": {
+ "description": "If true, will bypass the validation that the temp directory is\nwritable. This should only be used with templates for pipelines\nthat are guaranteed not to need to write to the temp directory,\nwhich is subject to change based on the optimizer.",
+ "type": "boolean"
+ },
"name": {
"description": "Required. The name of the template.",
"type": "string"
@@ -4059,10 +3832,6 @@
"description": {
"description": "Optional. A description of the template.",
"type": "string"
- },
- "bypassTempDirValidation": {
- "description": "If true, will bypass the validation that the temp directory is\nwritable. This should only be used with templates for pipelines\nthat are guaranteed not to need to write to the temp directory,\nwhich is subject to change based on the optimizer.",
- "type": "boolean"
}
},
"type": "object"
@@ -4071,14 +3840,6 @@
"description": "WorkerMessage provides information to the backend about a worker.",
"id": "WorkerMessage",
"properties": {
- "workerMessageCode": {
- "$ref": "WorkerMessageCode",
- "description": "A worker message code."
- },
- "workerMetrics": {
- "$ref": "ResourceUtilizationReport",
- "description": "Resource metrics reported by workers."
- },
"labels": {
"additionalProperties": {
"type": "string"
@@ -4094,6 +3855,14 @@
"workerHealthReport": {
"$ref": "WorkerHealthReport",
"description": "The health of a worker."
+ },
+ "workerMessageCode": {
+ "$ref": "WorkerMessageCode",
+ "description": "A worker message code."
+ },
+ "workerMetrics": {
+ "$ref": "ResourceUtilizationReport",
+ "description": "Resource metrics reported by workers."
}
},
"type": "object"
@@ -4136,14 +3905,6 @@
"description": "An update to a Counter sent from a worker.",
"id": "CounterUpdate",
"properties": {
- "structuredNameAndMetadata": {
- "$ref": "CounterStructuredNameAndMetadata",
- "description": "Counter structured name and metadata."
- },
- "integerList": {
- "$ref": "IntegerList",
- "description": "List of integers, for Set."
- },
"floatingPoint": {
"description": "Floating point value for Sum, Max, Min.",
"format": "double",
@@ -4193,6 +3954,14 @@
"integer": {
"$ref": "SplitInt64",
"description": "Integer value for Sum, Max, Min."
+ },
+ "structuredNameAndMetadata": {
+ "$ref": "CounterStructuredNameAndMetadata",
+ "description": "Counter structured name and metadata."
+ },
+ "integerList": {
+ "$ref": "IntegerList",
+ "description": "List of integers, for Set."
}
},
"type": "object"
@@ -4284,10 +4053,6 @@
"description": "Conveys a worker's progress through the work described by a WorkItem.",
"id": "WorkItemStatus",
"properties": {
- "sourceFork": {
- "$ref": "SourceFork",
- "description": "DEPRECATED in favor of dynamic_source_split."
- },
"counterUpdates": {
"description": "Worker output counters for this WorkItem.",
"items": {
@@ -4346,6 +4111,10 @@
"reportedProgress": {
"$ref": "ApproximateReportedProgress",
"description": "The worker's progress through this WorkItem."
+ },
+ "sourceFork": {
+ "$ref": "SourceFork",
+ "description": "DEPRECATED in favor of dynamic_source_split."
}
},
"type": "object"
@@ -4354,10 +4123,6 @@
"description": "Description of an interstitial value between transforms in an execution\nstage.",
"id": "ComponentSource",
"properties": {
- "originalTransformOrCollection": {
- "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
- "type": "string"
- },
"name": {
"description": "Dataflow service generated name for this source.",
"type": "string"
@@ -4365,6 +4130,10 @@
"userName": {
"description": "Human-readable name for this transform; may be user or system generated.",
"type": "string"
+ },
+ "originalTransformOrCollection": {
+ "description": "User name for the original user transform or collection with which this\nsource is most closely associated.",
+ "type": "string"
}
},
"type": "object"
@@ -4373,6 +4142,19 @@
"description": "The Dataflow service's idea of the current state of a WorkItem\nbeing processed by a worker.",
"id": "WorkItemServiceState",
"properties": {
+ "nextReportIndex": {
+ "description": "The index value to use for the next report sent by the worker.\nNote: If the report call fails for whatever reason, the worker should\nreuse this index for subsequent report attempts.",
+ "format": "int64",
+ "type": "string"
+ },
+ "suggestedStopPoint": {
+ "$ref": "ApproximateProgress",
+ "description": "DEPRECATED in favor of split_request."
+ },
+ "splitRequest": {
+ "$ref": "ApproximateSplitRequest",
+ "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
+ },
"suggestedStopPosition": {
"$ref": "Position",
"description": "Obsolete, always empty."
@@ -4401,19 +4183,6 @@
"$ref": "MetricShortId"
},
"type": "array"
- },
- "nextReportIndex": {
- "description": "The index value to use for the next report sent by the worker.\nNote: If the report call fails for whatever reason, the worker should\nreuse this index for subsequent report attempts.",
- "format": "int64",
- "type": "string"
- },
- "suggestedStopPoint": {
- "$ref": "ApproximateProgress",
- "description": "DEPRECATED in favor of split_request."
- },
- "splitRequest": {
- "$ref": "ApproximateSplitRequest",
- "description": "The progress point in the WorkItem where the Dataflow service\nsuggests that the worker truncate the task."
}
},
"type": "object"
@@ -4439,6 +4208,233 @@
}
},
"type": "object"
+ },
+ "SeqMapTaskOutputInfo": {
+ "description": "Information about an output of a SeqMapTask.",
+ "id": "SeqMapTaskOutputInfo",
+ "properties": {
+ "tag": {
+ "description": "The id of the TupleTag the user code will tag the output value by.",
+ "type": "string"
+ },
+ "sink": {
+ "$ref": "Sink",
+ "description": "The sink to write the output value to."
+ }
+ },
+ "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"
+ },
+ "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": {
+ "deliveryEndpoint": {
+ "description": "The physical location of this range assignment to be used for\nstreaming computation cross-worker message delivery.",
+ "type": "string"
+ },
+ "start": {
+ "description": "The start (inclusive) of the key range.",
+ "type": "string"
+ },
+ "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"
+ },
+ "deprecatedPersistentDirectory": {
+ "description": "DEPRECATED. The location of the persistent state for this range, as a\npersistent directory in the worker local filesystem.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "SourceGetMetadataRequest": {
+ "description": "A request to compute the SourceMetadata of a Source.",
+ "id": "SourceGetMetadataRequest",
+ "properties": {
+ "source": {
+ "$ref": "Source",
+ "description": "Specification of the source whose metadata should be computed."
+ }
+ },
+ "type": "object"
+ },
+ "NameAndKind": {
+ "description": "Basic metadata about a counter.",
+ "id": "NameAndKind",
+ "properties": {
+ "kind": {
+ "description": "Counter aggregation kind.",
+ "enum": [
+ "INVALID",
+ "SUM",
+ "MAX",
+ "MIN",
+ "MEAN",
+ "OR",
+ "AND",
+ "SET",
+ "DISTRIBUTION"
+ ],
+ "enumDescriptions": [
+ "Counter aggregation kind was not set.",
+ "Aggregated value is the sum of all contributed values.",
+ "Aggregated value is the max of all contributed values.",
+ "Aggregated value is the min of all contributed values.",
+ "Aggregated value is the mean of all contributed values.",
+ "Aggregated value represents the logical 'or' of all contributed values.",
+ "Aggregated value represents the logical 'and' of all contributed values.",
+ "Aggregated value is a set of unique contributed values.",
+ "Aggregated value captures statistics about a distribution."
+ ],
+ "type": "string"
+ },
+ "name": {
+ "description": "Name of the counter.",
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "SeqMapTask": {
+ "description": "Describes a particular function to invoke.",
+ "id": "SeqMapTask",
+ "properties": {
+ "inputs": {
+ "description": "Information about each of the inputs.",
+ "items": {
+ "$ref": "SideInputInfo"
+ },
+ "type": "array"
+ },
+ "systemName": {
+ "description": "System-defined name of the SeqDo operation.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "stageName": {
+ "description": "System-defined name of the stage containing the SeqDo operation.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "userFn": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "description": "The user function to invoke.",
+ "type": "object"
+ },
+ "name": {
+ "description": "The user-provided name of the SeqDo operation.",
+ "type": "string"
+ },
+ "outputInfos": {
+ "description": "Information about each of the outputs.",
+ "items": {
+ "$ref": "SeqMapTaskOutputInfo"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "WorkerMessageCode": {
+ "description": "A message code is used to report status and error messages to the service.\nThe message codes are intended to be machine readable. The service will\ntake care of translating these into user understandable messages if\nnecessary.\n\nExample use cases:\n 1. Worker processes reporting successful startup.\n 2. Worker processes reporting specific errors (e.g. package staging\n failure).",
+ "id": "WorkerMessageCode",
+ "properties": {
+ "code": {
+ "description": "The code is a string intended for consumption by a machine that identifies\nthe type of message being sent.\nExamples:\n 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has\n started.\n 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading\n a GCS file as part of the boot process of one of the worker containers.\n\nThis is a string and not an enum to make it easy to add new codes without\nwaiting for an API change.",
+ "type": "string"
+ },
+ "parameters": {
+ "additionalProperties": {
+ "description": "Properties of the object.",
+ "type": "any"
+ },
+ "description": "Parameters contains specific information about the code.\n\nThis is a struct to allow parameters of different types.\n\nExamples:\n 1. For a \"HARNESS_STARTED\" message parameters might provide the name\n of the worker and additional data like timing information.\n 2. For a \"GCS_DOWNLOAD_ERROR\" parameters might contain fields listing\n the GCS objects being downloaded and fields containing errors.\n\nIn general complex data structures should be avoided. If a worker\nneeds to send a specific and complicated data structure then please\nconsider defining a new proto and adding it to the data oneof in\nWorkerMessageResponse.\n\nConventions:\n Parameters should only be used for information that isn't typically passed\n as a label.\n hostname and other worker identifiers should almost always be passed\n as labels since they will be included on most messages.",
+ "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"
+ },
+ "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": {
+ "systemName": {
+ "description": "System-defined name of this MapTask.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "stageName": {
+ "description": "System-defined name of the stage containing this MapTask.\nUnique across the workflow.",
+ "type": "string"
+ },
+ "instructions": {
+ "description": "The instructions in the MapTask.",
+ "items": {
+ "$ref": "ParallelInstruction"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ },
+ "FloatingPointMean": {
+ "description": "A representation of a floating point mean metric contribution.",
+ "id": "FloatingPointMean",
+ "properties": {
+ "count": {
+ "$ref": "SplitInt64",
+ "description": "The number of values being aggregated."
+ },
+ "sum": {
+ "description": "The sum of all values being aggregated.",
+ "format": "double",
+ "type": "number"
+ }
+ },
+ "type": "object"
+ },
+ "ReportWorkItemStatusResponse": {
+ "description": "Response from a request to report the status of WorkItems.",
+ "id": "ReportWorkItemStatusResponse",
+ "properties": {
+ "workItemServiceStates": {
+ "description": "A set of messages indicating the service-side state for each\nWorkItem whose status was reported, in the same order as the\nWorkItemStatus messages in the ReportWorkItemStatusRequest which\nresulting in this response.",
+ "items": {
+ "$ref": "WorkItemServiceState"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
}
},
"servicePath": "",
« no previous file with comments | « discovery/googleapis_beta/cloudresourcemanager__v1beta1.json ('k') | discovery/googleapis_beta/dataproc__v1beta1.json » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698