OpenMetadata/ingestion/tests/unit/resources/datasets/databricks_pipeline_resource.json
Suman Maharana 2477bbc9ca
Fixes #16574 : Fix Databricks pipeline task status ingestion (#16802)
* Fixed Databricks pipeline task issue

* updated test cases

* addressed review
2024-06-27 12:07:04 +05:30

226 lines
5.9 KiB
JSON

[
{
"job_id": 11223344,
"creator_user_name": "user.name@databricks.com",
"settings": {
"name": "OpenMetadata Databricks Workflow",
"description": "This job contain multiple tasks that are required to produce the weekly shark sightings report.",
"email_notifications": {
"on_start": [
"user.name@databricks.com"
],
"on_success": [
"user.name@databricks.com"
],
"on_failure": [
"user.name@databricks.com"
],
"on_duration_warning_threshold_exceeded": [
"user.name@databricks.com"
],
"no_alert_for_skipped_runs": false
},
"webhook_notifications": {
"on_start": [
[
{
"id": "0481e838-0a59-4eff-9541-a4ca6f149574"
}
]
],
"on_success": [
[
{
"id": "0481e838-0a59-4eff-9541-a4ca6f149574"
}
]
],
"on_failure": [
[
{
"id": "0481e838-0a59-4eff-9541-a4ca6f149574"
}
]
],
"on_duration_warning_threshold_exceeded": [
[
{
"id": "0481e838-0a59-4eff-9541-a4ca6f149574"
}
]
]
},
"notification_settings": {
"no_alert_for_skipped_runs": false,
"no_alert_for_canceled_runs": false
},
"timeout_seconds": 86400,
"health": {
"rules": [
{
"metric": "RUN_DURATION_SECONDS",
"op": "GREATER_THAN",
"value": 10
}
]
},
"schedule": {
"quartz_cron_expression": "20 30 * * * ?",
"timezone_id": "Europe/London",
"pause_status": "UNPAUSED"
},
"trigger": {
"pause_status": "UNPAUSED",
"file_arrival": {
"url": "string",
"min_time_between_triggers_seconds": 0,
"wait_after_last_change_seconds": 0
}
},
"continuous": {
"pause_status": "UNPAUSED"
},
"max_concurrent_runs": 10,
"tasks": [
{
"max_retries": 3,
"task_key": "Sessionize",
"description": "Extracts session data from events",
"min_retry_interval_millis": 2000,
"depends_on": [],
"timeout_seconds": 86400,
"spark_jar_task": {
"main_class_name": "com.databricks.Sessionize",
"parameters": [
"--data",
"dbfs:/path/to/data.json"
]
},
"libraries": [
{
"jar": "dbfs:/mnt/databricks/Sessionize.jar"
}
],
"retry_on_timeout": false,
"existing_cluster_id": "0923-164208-meows279"
},
{
"max_retries": 3,
"task_key": "Orders_Ingest",
"description": "Ingests order data",
"job_cluster_key": "auto_scaling_cluster",
"min_retry_interval_millis": 2000,
"depends_on": [],
"timeout_seconds": 86400,
"spark_jar_task": {
"main_class_name": "com.databricks.OrdersIngest",
"parameters": [
"--data",
"dbfs:/path/to/order-data.json"
]
},
"libraries": [
{
"jar": "dbfs:/mnt/databricks/OrderIngest.jar"
}
],
"retry_on_timeout": false
},
{
"max_retries": 3,
"task_key": "Matched_Changed",
"description": "Matches orders with user sessions",
"notebook_task": {
"base_parameters": {
"age": "35",
"name": "John Doe"
},
"notebook_path": "/Users/user.name@databricks.com/Match"
},
"min_retry_interval_millis": 2000,
"depends_on": [
{
"task_key": "Orders_Ingest"
},
{
"task_key": "Sessionize"
},
{
"task_key": "Sessionize_duplicated"
}
],
"new_cluster": {
"autoscale": {
"max_workers": 16,
"min_workers": 2
},
"node_type_id": null,
"spark_conf": {
"spark.speculation": true
},
"spark_version": "7.3.x-scala2.12"
},
"timeout_seconds": 86400,
"retry_on_timeout": false,
"run_if": "ALL_SUCCESS"
}
],
"job_clusters": [
{
"job_cluster_key": "auto_scaling_cluster",
"new_cluster": {
"autoscale": {
"max_workers": 16,
"min_workers": 2
},
"node_type_id": null,
"spark_conf": {
"spark.speculation": true
},
"spark_version": "7.3.x-scala2.12"
}
}
],
"git_source": {
"git_branch": "main",
"git_provider": "gitHub",
"git_url": "https://github.com/databricks/databricks-cli"
},
"tags": {
"cost-center": "engineering",
"team": "jobs"
},
"format": "SINGLE_TASK",
"queue": {
"enabled": true
},
"parameters": [
{
"default": "users",
"name": "table"
}
],
"run_as": {
"user_name": "user@databricks.com",
"service_principal_name": "692bc6d0-ffa3-11ed-be56-0242ac120002"
},
"edit_mode": "UI_LOCKED",
"deployment": {
"kind": "BUNDLE",
"metadata_file_path": "string"
},
"environments": [
{
"environment_key": "string",
"spec": {
"client": "1",
"dependencies": [
"string"
]
}
}
]
},
"created_time": 1601370337343
}
]