forked from OpenLineage/OpenLineage
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Spec] gcp dataproc facet (OpenLineage#2987)
* gcp dataproc facet Signed-off-by: tnazarew <[email protected]> * change filenames Signed-off-by: tnazarew <[email protected]> --------- Signed-off-by: tnazarew <[email protected]>
- Loading branch information
Showing
11 changed files
with
120 additions
and
39 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
75 changes: 75 additions & 0 deletions
75
spec/registry/gcp/dataproc/facets/GcpDataprocSparkRunFacet.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,75 @@ | ||
| { | ||
| "$schema": "https://json-schema.org/draft/2020-12/schema", | ||
| "$id": "https://openlineage.io/spec/facets/1-0-0/GcpDataprocSparkRunFacet.json", | ||
| "$defs": { | ||
| "GcpDataprocSparkRunFacet": { | ||
| "allOf": [ | ||
| { | ||
| "$ref": "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunFacet" | ||
| }, | ||
| { | ||
| "type": "object", | ||
| "properties": { | ||
| "appId": { | ||
| "description": "Application ID set in the spark configuration of the current context. Its format depends on the resource manager.", | ||
| "type": "string" | ||
| }, | ||
| "appName": { | ||
| "description": "App name set in the spark configuration of the current context. It may be provided by the user.", | ||
| "type": "string" | ||
| }, | ||
| "batchId": { | ||
| "description": "Populated only for Dataproc serverless batches. The resource id of the batch.", | ||
| "type": "string" | ||
| }, | ||
| "batchUuid": { | ||
| "description": "Populated only for Dataproc serverless batches. A UUID generated by the service when it creates the batch.", | ||
| "type": "string" | ||
| }, | ||
| "clusterName": { | ||
| "description": "Populated only for Dataproc GCE workloads. The cluster name is unique within a GCP project.", | ||
| "type": "string" | ||
| }, | ||
| "clusterUuid": { | ||
| "description": "Populated only for Dataproc GCE workloads. A UUID generated by the service at the time of cluster creation.", | ||
| "type": "string" | ||
| }, | ||
| "jobId": { | ||
| "description": "Populated only for Dataproc GCE workloads. If not specified by the user, the job ID will be provided by the service.", | ||
| "type": "string" | ||
| }, | ||
| "jobUuid": { | ||
| "description": "Populated only for Dataproc GCE workloads. A UUID that uniquely identifies a job within the project over time.", | ||
| "type": "string" | ||
| }, | ||
| "projectId": { | ||
| "description": "The GCP project ID that the resource belongs to.", | ||
| "type": "string" | ||
| }, | ||
| "queryNodeName": { | ||
| "description": "The name of the query node in the executed Spark Plan. Often used to describe the command being executed.", | ||
| "type": "string" | ||
| }, | ||
| "sessionId": { | ||
| "description": "Populated only for Dataproc serverless interactive sessions. The resource id of the session, used for URL generation.", | ||
| "type": "string" | ||
| }, | ||
| "sessionUuid": { | ||
| "description": "Populated only for Dataproc serverless interactive sessions. A UUID generated by the service when it creates the session.", | ||
| "type": "string" | ||
| } | ||
| }, | ||
| "required": ["appId", "appName", "projectId"], | ||
| "additionalProperties": true | ||
| } | ||
| ], | ||
| "type": "object" | ||
| } | ||
| }, | ||
| "type": "object", | ||
| "properties": { | ||
| "gcp_dataproc_spark": { | ||
| "$ref": "#/$defs/GcpDataprocSparkRunFacet" | ||
| } | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| { | ||
| "producer": { | ||
| "root_doc_URL": "https://cloud.google.com/dataproc/docs/guides/lineage", | ||
| "produced_facets": ["ol:gcp:dataproc:GcpDataprocSparkRunFacet.json"] | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
2 changes: 1 addition & 1 deletion
2
spec/registry/gcp/registry.json → spec/registry/gcp/lineage/registry.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,6 +1,6 @@ | ||
| { | ||
| "consumer": { | ||
| "root_doc_URL": "https://cloud.google.com/data-catalog/docs/reference/data-lineage/rpc/google.cloud.datacatalog.lineage.v1#google.cloud.datacatalog.lineage.v1.Lineage.ProcessOpenLineageRunEvent", | ||
| "produced_facets": ["ol:gcp:GcpCommonJobFacet.json"] | ||
| "consumed_facets": ["ol:gcp:lineage:GcpLineageJobFacet.json", "ol:gcp:dataproc:GcpDataprocSparkRunFacet.json"] | ||
| } | ||
| } |