Source code for airflow.providers.google.cloud.operators.dataplex
# Licensed to the Apache Software Foundation (ASF) under one# or more contributor license agreements. See the NOTICE file# distributed with this work for additional information# regarding copyright ownership. The ASF licenses this file# to you under the Apache License, Version 2.0 (the# "License"); you may not use this file except in compliance# with the License. You may obtain a copy of the License at## http://www.apache.org/licenses/LICENSE-2.0## Unless required by applicable law or agreed to in writing,# software distributed under the License is distributed on an# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY# KIND, either express or implied. See the License for the# specific language governing permissions and limitations# under the License."""This module contains Google Dataplex operators."""from__future__importannotationsimporttimefromtypingimportTYPE_CHECKING,Any,Sequencefromairflow.exceptionsimportAirflowExceptionfromairflow.providers.google.cloud.triggers.datapleximport(DataplexDataProfileJobTrigger,DataplexDataQualityJobTrigger,)ifTYPE_CHECKING:fromgoogle.protobuf.field_mask_pb2importFieldMaskfromairflow.utils.contextimportContextfromgoogle.api_core.exceptionsimportAlreadyExists,GoogleAPICallErrorfromgoogle.api_core.gapic_v1.methodimportDEFAULT,_MethodDefaultfromgoogle.api_core.retryimportRetry,exponential_sleep_generatorfromgoogle.cloud.dataplex_v1.typesimportAsset,DataScan,DataScanJob,Lake,Task,Zonefromgoogleapiclient.errorsimportHttpErrorfromairflow.configurationimportconffromairflow.providers.google.cloud.hooks.datapleximportAirflowDataQualityScanException,DataplexHookfromairflow.providers.google.cloud.links.datapleximport(DataplexLakeLink,DataplexTaskLink,DataplexTasksLink,)fromairflow.providers.google.cloud.operators.cloud_baseimportGoogleCloudBaseOperator
[docs]classDataplexCreateTaskOperator(GoogleCloudBaseOperator):""" Creates a task resource within a lake. :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 lake_id: Required. The ID of the Google Cloud lake that the task belongs to. :param body: Required. The Request body contains an instance of Task. :param dataplex_task_id: Required. Task identifier. :param validate_only: Optional. Only validate the request, but do not perform mutations. The default is false. :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 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 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 asynchronous: Flag informing should the Dataplex task be created asynchronously. This is useful for long running creating tasks and waiting on them asynchronously using the DataplexTaskSensor """
[docs]defexecute(self,context:Context)->dict:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Creating Dataplex task %s",self.dataplex_task_id)DataplexTaskLink.persist(context=context,task_instance=self)try:operation=hook.create_task(project_id=self.project_id,region=self.region,lake_id=self.lake_id,body=self.body,dataplex_task_id=self.dataplex_task_id,validate_only=self.validate_only,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)ifnotself.asynchronous:self.log.info("Waiting for Dataplex task %s to be created",self.dataplex_task_id)task=hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Task %s created successfully",self.dataplex_task_id)else:is_done=operation.done()self.log.info("Is operation done already? %s",is_done)returnis_doneexceptHttpErroraserr:iferr.resp.statusnotin(409,"409"):raiseself.log.info("Task %s already exists",self.dataplex_task_id)# Wait for task to be readyfortime_to_waitinexponential_sleep_generator(initial=10,maximum=120):task=hook.get_task(project_id=self.project_id,region=self.region,lake_id=self.lake_id,dataplex_task_id=self.dataplex_task_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)iftask["state"]!="CREATING":breaktime.sleep(time_to_wait)returnTask.to_dict(task)
[docs]classDataplexDeleteTaskOperator(GoogleCloudBaseOperator):""" Delete the task resource. :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 lake_id: Required. The ID of the Google Cloud lake that the task belongs to. :param dataplex_task_id: Required. Task identifier. :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 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 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). """
[docs]classDataplexListTasksOperator(GoogleCloudBaseOperator):""" Lists tasks under the given lake. :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 lake_id: Required. The ID of the Google Cloud lake that the task belongs to. :param page_size: Optional. Maximum number of tasks to return. The service may return fewer than this value. If unspecified, at most 10 tasks will be returned. The maximum value is 1000; values above 1000 will be coerced to 1000. :param page_token: Optional. Page token received from a previous ListZones call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to ListZones must match the call that provided the page token. :param filter: Optional. Filter request. :param order_by: Optional. Order by fields for the result. :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 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 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). """
[docs]defexecute(self,context:Context)->list[dict]:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Listing Dataplex tasks from lake %s",self.lake_id)DataplexTasksLink.persist(context=context,task_instance=self)tasks=hook.list_tasks(project_id=self.project_id,region=self.region,lake_id=self.lake_id,page_size=self.page_size,page_token=self.page_token,filter=self.filter,order_by=self.order_by,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)return[Task.to_dict(task)fortaskintasks]
[docs]classDataplexGetTaskOperator(GoogleCloudBaseOperator):""" Get task resource. :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 lake_id: Required. The ID of the Google Cloud lake that the task belongs to. :param dataplex_task_id: Required. Task identifier. :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 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 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). """
[docs]classDataplexCreateLakeOperator(GoogleCloudBaseOperator):""" Creates a lake resource within a lake. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param lake_id: Required. Lake identifier. :param body: Required. The Request body contains an instance of Lake. :param validate_only: Optional. Only validate the request, but do not perform mutations. The default is false. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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 asynchronous: Flag informing should the Dataplex lake be created asynchronously. This is useful for long-running creating lakes. """
[docs]defexecute(self,context:Context)->dict:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Creating Dataplex lake %s",self.lake_id)try:operation=hook.create_lake(project_id=self.project_id,region=self.region,lake_id=self.lake_id,body=self.body,validate_only=self.validate_only,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)ifnotself.asynchronous:self.log.info("Waiting for Dataplex lake %s to be created",self.lake_id)lake=hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Lake %s created successfully",self.lake_id)else:is_done=operation.done()self.log.info("Is operation done already? %s",is_done)returnis_doneexceptHttpErroraserr:iferr.resp.statusnotin(409,"409"):raiseself.log.info("Lake %s already exists",self.lake_id)# Wait for lake to be readyfortime_to_waitinexponential_sleep_generator(initial=10,maximum=120):lake=hook.get_lake(project_id=self.project_id,region=self.region,lake_id=self.lake_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)iflake["state"]!="CREATING":breaktime.sleep(time_to_wait)DataplexLakeLink.persist(context=context,task_instance=self,)returnLake.to_dict(lake)
[docs]classDataplexDeleteLakeOperator(GoogleCloudBaseOperator):""" Delete the lake resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param lake_id: Required. Lake identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). """
[docs]defexecute(self,context:Context)->None:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Deleting Dataplex lake %s",self.lake_id)operation=hook.delete_lake(project_id=self.project_id,region=self.region,lake_id=self.lake_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)DataplexLakeLink.persist(context=context,task_instance=self)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex lake %s deleted successfully!",self.lake_id)
[docs]classDataplexCreateOrUpdateDataQualityScanOperator(GoogleCloudBaseOperator):""" Creates a DataScan resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param body: Required. The Request body contains an instance of DataScan. :param data_scan_id: Required. Data Quality scan identifier. :param update_mask: Mask of fields to update. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). :return: Dataplex data scan id """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Creating Dataplex Data Quality scan %s",self.data_scan_id)try:operation=hook.create_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,body=self.body,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex Data Quality scan %s created successfully!",self.data_scan_id)exceptAlreadyExists:self.log.info("Dataplex Data Quality scan already exists: %s",{self.data_scan_id})operation=hook.update_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,body=self.body,update_mask=self.update_mask,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex Data Quality scan %s updated successfully!",self.data_scan_id)exceptGoogleAPICallErrorase:raiseAirflowException(f"Error creating Data Quality scan {self.data_scan_id}",e)returnself.data_scan_id
[docs]classDataplexGetDataQualityScanOperator(GoogleCloudBaseOperator):""" Gets a DataScan resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Quality scan identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). :return: Dataplex data scan """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Retrieving the details of Dataplex Data Quality scan %s",self.data_scan_id)data_quality_scan=hook.get_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)returnDataScan.to_dict(data_quality_scan)
[docs]classDataplexDeleteDataQualityScanOperator(GoogleCloudBaseOperator):""" Deletes a DataScan resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Quality scan identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). :return: None """
[docs]defexecute(self,context:Context)->None:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Deleting Dataplex Data Quality Scan: %s",self.data_scan_id)operation=hook.delete_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex Data Quality scan %s deleted successfully!",self.data_scan_id)
[docs]classDataplexRunDataQualityScanOperator(GoogleCloudBaseOperator):""" Runs an on-demand execution of a DataScan. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Quality scan identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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 asynchronous: Flag informing that the Dataplex job should be run asynchronously. This is useful for submitting long-running jobs and waiting on them asynchronously using the DataplexDataQualityJobStatusSensor :param fail_on_dq_failure: If set to true and not all Data Quality scan rules have been passed, an exception is thrown. If set to false and not all Data Quality scan rules have been passed, execution will finish with success. :param result_timeout: Value in seconds for which operator will wait for the Data Quality scan result when the flag `asynchronous = False`. Throws exception if there is no result found after specified amount of seconds. :param polling_interval_seconds: time in seconds between polling for job completion. The value is considered only when running in deferrable mode. Must be greater than 0. :param deferrable: Run operator in the deferrable mode. :return: Dataplex Data Quality scan job id. """
[docs]defexecute(self,context:Context)->str:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)result=hook.run_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)job_id=result.job.name.split("/")[-1]ifself.deferrable:ifself.asynchronous:raiseAirflowException("Both asynchronous and deferrable parameters were passed. Please, provide only one.")self.defer(trigger=DataplexDataQualityJobTrigger(job_id=job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,gcp_conn_id=self.gcp_conn_id,impersonation_chain=self.impersonation_chain,polling_interval_seconds=self.polling_interval_seconds,),method_name="execute_complete",)ifnotself.asynchronous:job=hook.wait_for_data_scan_job(job_id=job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,result_timeout=self.result_timeout,)ifjob.state==DataScanJob.State.FAILED:raiseAirflowException(f"Data Quality job failed: {job_id}")ifjob.state==DataScanJob.State.SUCCEEDED:ifnotjob.data_quality_result.passed:ifself.fail_on_dq_failure:raiseAirflowDataQualityScanException(f"Data Quality job {job_id} execution failed due to failure of its scanning "f"rules: {self.data_scan_id}")else:self.log.info("Data Quality job executed successfully.")else:self.log.info("Data Quality job execution returned status: %s",job.status)returnjob_id
[docs]defexecute_complete(self,context,event=None)->None:""" Act as a callback for when the trigger fires - returns immediately. Relies on trigger to throw an exception, otherwise it assumes execution was successful. """job_state=event["job_state"]job_id=event["job_id"]ifjob_state==DataScanJob.State.FAILED:raiseAirflowException(f"Job failed:\n{job_id}")ifjob_state==DataScanJob.State.CANCELLED:raiseAirflowException(f"Job was cancelled:\n{job_id}")ifjob_state==DataScanJob.State.SUCCEEDED:job=event["job"]ifnotjob["data_quality_result"]["passed"]:ifself.fail_on_dq_failure:raiseAirflowDataQualityScanException(f"Data Quality job {job_id} execution failed due to failure of its scanning "f"rules: {self.data_scan_id}")else:self.log.info("Data Quality job executed successfully.")returnjob_id
[docs]classDataplexGetDataQualityScanResultOperator(GoogleCloudBaseOperator):""" Gets a Data Scan Job resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Quality scan identifier. :param job_id: Optional. Data Quality scan job identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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 fail_on_dq_failure: If set to true and not all Data Quality scan rules have been passed, an exception is thrown. If set to false and not all Data Quality scan rules have been passed, execution will finish with success. :param wait_for_results: Flag indicating whether to wait for the result of a job execution or to return the job in its current state. :param result_timeout: Value in seconds for which operator will wait for the Data Quality scan result when the flag `wait_for_results = True`. Throws exception if there is no result found after specified amount of seconds. :param polling_interval_seconds: time in seconds between polling for job completion. The value is considered only when running in deferrable mode. Must be greater than 0. :param deferrable: Run operator in the deferrable mode. :return: Dict representing DataScanJob. When the job completes with a successful status, information about the Data Quality result is available. """
[docs]defexecute(self,context:Context)->dict:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)# fetch the last jobifnotself.job_id:jobs=hook.list_data_scan_jobs(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)job_ids=[DataScanJob.to_dict(job)forjobinjobs]ifnotjob_ids:raiseAirflowException("There are no jobs, you should create one before.")job_id=job_ids[0]["name"]self.job_id=job_id.split("/")[-1]ifself.wait_for_results:ifself.deferrable:self.defer(trigger=DataplexDataQualityJobTrigger(job_id=self.job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,gcp_conn_id=self.gcp_conn_id,impersonation_chain=self.impersonation_chain,polling_interval_seconds=self.polling_interval_seconds,),method_name="execute_complete",)else:job=hook.wait_for_data_scan_job(job_id=self.job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,result_timeout=self.result_timeout,)else:job=hook.get_data_scan_job(project_id=self.project_id,region=self.region,job_id=self.job_id,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)ifjob.state==DataScanJob.State.SUCCEEDED:ifnotjob.data_quality_result.passed:ifself.fail_on_dq_failure:raiseAirflowDataQualityScanException(f"Data Quality job {self.job_id} execution failed due to failure of its scanning "f"rules: {self.data_scan_id}")else:self.log.info("Data Quality job executed successfully")else:self.log.info("Data Quality job execution returned status: %s",job.state)result=DataScanJob.to_dict(job)result["state"]=DataScanJob.State(result["state"]).namereturnresult
[docs]defexecute_complete(self,context,event=None)->None:""" Act as a callback for when the trigger fires - returns immediately. Relies on trigger to throw an exception, otherwise it assumes execution was successful. """job_state=event["job_state"]job_id=event["job_id"]job=event["job"]ifjob_state==DataScanJob.State.FAILED:raiseAirflowException(f"Job failed:\n{job_id}")ifjob_state==DataScanJob.State.CANCELLED:raiseAirflowException(f"Job was cancelled:\n{job_id}")ifjob_state==DataScanJob.State.SUCCEEDED:ifnotjob["data_quality_result"]["passed"]:ifself.fail_on_dq_failure:raiseAirflowDataQualityScanException(f"Data Quality job {self.job_id} execution failed due to failure of its scanning "f"rules: {self.data_scan_id}")else:self.log.info("Data Quality job executed successfully")else:self.log.info("Data Quality job execution returned status: %s",job_state)returnjob
[docs]classDataplexCreateOrUpdateDataProfileScanOperator(GoogleCloudBaseOperator):""" Creates a DataScan Data Profile resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param body: Required. The Request body contains an instance of DataScan. :param data_scan_id: Required. Data Profile scan identifier. :param update_mask: Mask of fields to update. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). :return: Dataplex data profile id """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Creating Dataplex Data Profile scan %s",self.data_scan_id)try:operation=hook.create_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,body=self.body,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex Data Profile scan %s created successfully!",self.data_scan_id)exceptAlreadyExists:self.log.info("Dataplex Data Profile scan already exists: %s",{self.data_scan_id})operation=hook.update_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,body=self.body,update_mask=self.update_mask,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex Data Profile scan %s updated successfully!",self.data_scan_id)exceptGoogleAPICallErrorase:raiseAirflowException(f"Error creating Data Profile scan {self.data_scan_id}",e)returnself.data_scan_id
[docs]classDataplexGetDataProfileScanOperator(GoogleCloudBaseOperator):""" Gets a DataScan DataProfile resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Profile scan identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). :return: Dataplex data profile """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Retrieving the details of Dataplex Data Profile scan %s",self.data_scan_id)data_profile_scan=hook.get_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)returnDataScan.to_dict(data_profile_scan)
[docs]classDataplexDeleteDataProfileScanOperator(GoogleCloudBaseOperator):""" Deletes a DataScan DataProfile resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Profile scan identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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). :return: None """
[docs]defexecute(self,context:Context)->None:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Deleting Dataplex Data Profile Scan: %s",self.data_scan_id)operation=hook.delete_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex Data Profile scan %s deleted successfully!",self.data_scan_id)
[docs]classDataplexRunDataProfileScanOperator(GoogleCloudBaseOperator):""" Runs an on-demand execution of a DataScan Data Profile Scan. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Profile scan identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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 asynchronous: Flag informing that the Dataplex job should be run asynchronously. This is useful for submitting long-running jobs and waiting on them asynchronously using the DataplexDataProfileJobStatusSensor :param result_timeout: Value in seconds for which operator will wait for the Data Profile scan result when the flag `asynchronous = False`. Throws exception if there is no result found after specified amount of seconds. :param polling_interval_seconds: time in seconds between polling for job completion. The value is considered only when running in deferrable mode. Must be greater than 0. :param deferrable: Run operator in the deferrable mode. :return: Dataplex Data Profile scan job id. """
[docs]defexecute(self,context:Context)->dict:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)result=hook.run_data_scan(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)job_id=result.job.name.split("/")[-1]ifself.deferrable:ifself.asynchronous:raiseAirflowException("Both asynchronous and deferrable parameters were passed. Please, provide only one.")self.defer(trigger=DataplexDataProfileJobTrigger(job_id=job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,gcp_conn_id=self.gcp_conn_id,impersonation_chain=self.impersonation_chain,polling_interval_seconds=self.polling_interval_seconds,),method_name="execute_complete",)ifnotself.asynchronous:job=hook.wait_for_data_scan_job(job_id=job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,result_timeout=self.result_timeout,)ifjob.state==DataScanJob.State.FAILED:raiseAirflowException(f"Data Profile job failed: {job_id}")ifjob.state==DataScanJob.State.SUCCEEDED:self.log.info("Data Profile job executed successfully.")else:self.log.info("Data Profile job execution returned status: %s",job.status)returnjob_id
[docs]defexecute_complete(self,context,event=None)->None:""" Act as a callback for when the trigger fires - returns immediately. Relies on trigger to throw an exception, otherwise it assumes execution was successful. """job_state=event["job_state"]job_id=event["job_id"]ifjob_state==DataScanJob.State.FAILED:raiseAirflowException(f"Job failed:\n{job_id}")ifjob_state==DataScanJob.State.CANCELLED:raiseAirflowException(f"Job was cancelled:\n{job_id}")ifjob_state==DataScanJob.State.SUCCEEDED:self.log.info("Data Profile job executed successfully.")returnjob_id
[docs]classDataplexGetDataProfileScanResultOperator(GoogleCloudBaseOperator):""" Gets a DataScan Data Profile Job resource. :param project_id: Required. The ID of the Google Cloud project that the lake belongs to. :param region: Required. The ID of the Google Cloud region that the lake belongs to. :param data_scan_id: Required. Data Profile scan identifier. :param job_id: Optional. Data Profile scan job identifier. :param api_version: The version of the api that will be requested for example 'v1'. :param retry: A retry object used to retry requests. If `None` is specified, requests will not be retried. :param 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 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_for_results: Flag indicating whether to wait for the result of a job execution or to return the job in its current state. :param result_timeout: Value in seconds for which operator will wait for the Data Profile scan result when the flag `wait_for_results = True`. Throws exception if there is no result found after specified amount of seconds. :return: Dict representing DataScanJob. When the job completes with a successful status, information about the Data Profile result is available. """
[docs]defexecute(self,context:Context)->dict:hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)# fetch the last jobifnotself.job_id:jobs=hook.list_data_scan_jobs(project_id=self.project_id,region=self.region,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)job_ids=[DataScanJob.to_dict(job)forjobinjobs]ifnotjob_ids:raiseAirflowException("There are no jobs, you should create one before.")job_id=job_ids[0]["name"]self.job_id=job_id.split("/")[-1]ifself.wait_for_results:job=hook.wait_for_data_scan_job(job_id=self.job_id,data_scan_id=self.data_scan_id,project_id=self.project_id,region=self.region,result_timeout=self.result_timeout,)else:job=hook.get_data_scan_job(project_id=self.project_id,region=self.region,job_id=self.job_id,data_scan_id=self.data_scan_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)ifjob.state==DataScanJob.State.SUCCEEDED:self.log.info("Data Profile job executed successfully")else:self.log.info("Data Profile job execution returned status: %s",job.state)result=DataScanJob.to_dict(job)result["state"]=DataScanJob.State(result["state"]).namereturnresult
[docs]defexecute_complete(self,context,event=None)->None:""" Act as a callback for when the trigger fires - returns immediately. Relies on trigger to throw an exception, otherwise it assumes execution was successful. """job_state=event["job_state"]job_id=event["job_id"]job=event["job"]ifjob_state==DataScanJob.State.FAILED:raiseAirflowException(f"Job failed:\n{job_id}")ifjob_state==DataScanJob.State.CANCELLED:raiseAirflowException(f"Job was cancelled:\n{job_id}")ifjob_state==DataScanJob.State.SUCCEEDED:self.log.info("Data Profile job executed successfully")else:self.log.info("Data Profile job execution returned status: %s",job_state)returnjob
[docs]classDataplexCreateZoneOperator(GoogleCloudBaseOperator):""" Creates a Zone resource within a Lake. :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 lake_id: Required. The ID of the Google Cloud lake that the task belongs to. :param body: Required. The Request body contains an instance of Zone. :param zone_id: Required. Task identifier. :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 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 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). :return: Zone """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Creating Dataplex zone %s",self.zone_id)try:operation=hook.create_zone(project_id=self.project_id,region=self.region,lake_id=self.lake_id,body=self.body,zone_id=self.zone_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)zone=hook.wait_for_operation(timeout=self.timeout,operation=operation)exceptGoogleAPICallErrorase:raiseAirflowException(f"Error occurred when creating zone {self.zone_id}",e)self.log.info("Dataplex zone %s created successfully!",self.zone_id)returnZone.to_dict(zone)
[docs]classDataplexDeleteZoneOperator(GoogleCloudBaseOperator):""" Deletes a Zone resource. All assets within a zone must be deleted before the zone can be deleted. :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 lake_id: Required. The ID of the Google Cloud lake that the task belongs to. :param zone_id: Required. Zone identifier. :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 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 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). :return: None """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Deleting Dataplex zone %s",self.zone_id)operation=hook.delete_zone(project_id=self.project_id,region=self.region,lake_id=self.lake_id,zone_id=self.zone_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)hook.wait_for_operation(timeout=self.timeout,operation=operation)self.log.info("Dataplex zone %s deleted successfully!",self.zone_id)
[docs]classDataplexCreateAssetOperator(GoogleCloudBaseOperator):""" Creates an Asset resource. :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 lake_id: Required. The ID of the Google Cloud lake that the lake belongs to. :param zone_id: Required. Zone identifier. :param asset_id: Required. Asset identifier. :param body: Required. The Request body contains an instance of Asset. :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 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 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). :return: Asset """
[docs]defexecute(self,context:Context):hook=DataplexHook(gcp_conn_id=self.gcp_conn_id,api_version=self.api_version,impersonation_chain=self.impersonation_chain,)self.log.info("Creating Dataplex asset %s",self.zone_id)try:operation=hook.create_asset(project_id=self.project_id,region=self.region,lake_id=self.lake_id,body=self.body,zone_id=self.zone_id,asset_id=self.asset_id,retry=self.retry,timeout=self.timeout,metadata=self.metadata,)result=hook.wait_for_operation(timeout=self.timeout,operation=operation)exceptGoogleAPICallErrorase:raiseAirflowException(f"Error occurred when creating asset {self.asset_id}",e)self.log.info("Dataplex asset %s created successfully!",self.asset_id)returnAsset.to_dict(result)
[docs]classDataplexDeleteAssetOperator(GoogleCloudBaseOperator):""" Deletes an asset resource. :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 lake_id: Required. The ID of the Google Cloud lake that the asset belongs to. :param zone_id: Required. Zone identifier. :param asset_id: Required. Asset identifier. :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 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 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). :return: None """