bkossakowska commented on code in PR #32256:
URL: https://github.com/apache/airflow/pull/32256#discussion_r1281543277
##########
airflow/providers/google/cloud/sensors/dataplex.py:
##########
@@ -114,3 +115,98 @@ def poke(self, context: Context) -> bool:
self.log.info("Current status of the Dataplex task %s => %s",
self.dataplex_task_id, task_status)
return task_status == TaskState.ACTIVE
+
+
+class DataplexDataQualityJobStatusSensor(BaseSensorOperator):
+ """
+ Check the status of the Dataplex data scan job is SUCCEEDED.
+
+ :param project_id: Required. The ID of the Google Cloud project that the
task belongs to.
+ :param region: Required. The ID of the Google Cloud region that the task
belongs to.
+ :param data_scan_id: Required. DataScan identifier.
+ :param job_id: Required. Job ID.
+ :param api_version: The version of the api that will be requested for
example 'v3'.
+ :param retry: A retry object used to retry requests. If `None` is
specified, requests
+ will not be retried.
+ :param metadata: Additional metadata that is provided to the method.
+ :param gcp_conn_id: The connection ID to use when fetching connection info.
+ :param impersonation_chain: Optional service account to impersonate using
short-term
+ credentials, or chained list of accounts required to get the
access_token
+ of the last account in the list, which will be impersonated in the
request.
+ If set as a string, the account must grant the originating account
+ the Service Account Token Creator IAM role.
+ If set as a sequence, the identities from the list must grant
+ Service Account Token Creator IAM role to the directly preceding
identity, with first
+ account from the list granting this role to the originating account
(templated).
+ :param wait_timeout: The amount of time, in seconds, to wait for the
request to complete.
+ Note that if `retry` is specified, the timeout applies to each
individual attempt.
+ :param fail_on_dq_failure: If set to true, sensor throws exception if Data
Quality fails.
+ :return: Boolean indicating if the job run has reached the
``DataScanJob.State.SUCCEEDED``.
+ """
+
+ template_fields = ["job_id"]
+
+ def __init__(
+ self,
+ project_id: str,
+ region: str,
+ data_scan_id: str,
+ job_id: str,
+ api_version: str = "v1",
+ retry: Retry | _MethodDefault = DEFAULT,
+ metadata: Sequence[tuple[str, str]] = (),
+ gcp_conn_id: str = "google_cloud_default",
+ impersonation_chain: str | Sequence[str] | None = None,
+ fail_on_dq_failure: bool = False,
+ wait_timeout: float | None = None,
+ *args,
+ **kwargs,
+ ) -> None:
+ super().__init__(*args, **kwargs)
+ self.project_id = project_id
+ self.region = region
+ self.data_scan_id = data_scan_id
+ self.job_id = job_id
+ self.api_version = api_version
+ self.retry = retry
+ self.metadata = metadata
+ self.gcp_conn_id = gcp_conn_id
+ self.impersonation_chain = impersonation_chain
+ self.fail_on_dq_failure = fail_on_dq_failure
+ self.wait_timeout = wait_timeout
+
+ def poke(self, context: Context) -> bool:
+ self.log.info("Waiting for job %s to be %s", self.job_id,
DataScanJob.State.SUCCEEDED)
+
+ hook = DataplexHook(
+ gcp_conn_id=self.gcp_conn_id,
+ api_version=self.api_version,
+ impersonation_chain=self.impersonation_chain,
+ )
+ try:
+ job = hook.get_data_scan_job(
+ project_id=self.project_id,
+ region=self.region,
+ data_scan_id=self.data_scan_id,
+ job_id=self.job_id,
+ timeout=self.wait_timeout,
+ retry=self.retry,
+ metadata=self.metadata,
+ )
+ except GoogleAPICallError as e:
+ raise AirflowException(f"Error getting data scan job:
{self.data_scan_id}", e)
Review Comment:
changed
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
