# 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.
"""
Example Airflow DAG that shows how to use DataFusion.
"""
from __future__ import annotations
import os
from datetime import datetime
from airflow import models
from airflow.providers.google.cloud.operators.datafusion import (
CloudDataFusionCreateInstanceOperator,
CloudDataFusionCreatePipelineOperator,
CloudDataFusionDeleteInstanceOperator,
CloudDataFusionDeletePipelineOperator,
CloudDataFusionGetInstanceOperator,
CloudDataFusionListPipelinesOperator,
CloudDataFusionRestartInstanceOperator,
CloudDataFusionStartPipelineOperator,
CloudDataFusionStopPipelineOperator,
CloudDataFusionUpdateInstanceOperator,
)
from airflow.providers.google.cloud.operators.gcs import GCSCreateBucketOperator, GCSDeleteBucketOperator
from airflow.utils.trigger_rule import TriggerRule
# [START howto_data_fusion_env_variables]
[docs]SERVICE_ACCOUNT = os.environ.get("GCP_DATAFUSION_SERVICE_ACCOUNT")
[docs]PROJECT_ID = os.environ.get("SYSTEM_TESTS_GCP_PROJECT")
[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID")
[docs]DAG_ID = "example_datafusion_async"
[docs]LOCATION = "europe-north1"
[docs]INSTANCE_NAME = f"async-df-{ENV_ID}".replace("_", "-")
[docs]INSTANCE = {
"type": "BASIC",
"displayName": INSTANCE_NAME,
"dataprocServiceAccount": SERVICE_ACCOUNT,
}
[docs]BUCKET_NAME_1 = f"a-bucket1-{DAG_ID}-{ENV_ID}".replace("_", "-")
[docs]BUCKET_NAME_2 = f"a-bucket2-{DAG_ID}-{ENV_ID}".replace("_", "-")
[docs]BUCKET_NAME_1_URI = f"gs://{BUCKET_NAME_1}"
[docs]BUCKET_NAME_2_URI = f"gs://{BUCKET_NAME_2}"
[docs]PIPELINE_NAME = f"pipe-{ENV_ID}".replace("_", "-")
[docs]PIPELINE = {
"artifact": {
"name": "cdap-data-pipeline",
"version": "6.8.3",
"scope": "SYSTEM",
},
"description": "Data Pipeline Application",
"name": PIPELINE_NAME,
"config": {
"resources": {"memoryMB": 2048, "virtualCores": 1},
"driverResources": {"memoryMB": 2048, "virtualCores": 1},
"connections": [{"from": "GCS", "to": "GCS2"}],
"comments": [],
"postActions": [],
"properties": {},
"processTimingEnabled": "true",
"stageLoggingEnabled": "false",
"stages": [
{
"name": "GCS",
"plugin": {
"name": "GCSFile",
"type": "batchsource",
"label": "GCS",
"artifact": {"name": "google-cloud", "version": "0.21.2", "scope": "SYSTEM"},
"properties": {
"project": "auto-detect",
"format": "text",
"skipHeader": "false",
"serviceFilePath": "auto-detect",
"filenameOnly": "false",
"recursive": "false",
"encrypted": "false",
"schema": '{"type":"record","name":"textfile","fields":[{"name"\
:"offset","type":"long"},{"name":"body","type":"string"}]}',
"path": BUCKET_NAME_1_URI,
"referenceName": "foo_bucket",
"useConnection": "false",
"serviceAccountType": "filePath",
"sampleSize": "1000",
"fileEncoding": "UTF-8",
},
},
"outputSchema": '{"type":"record","name":"textfile","fields"\
:[{"name":"offset","type":"long"},{"name":"body","type":"string"}]}',
"id": "GCS",
},
{
"name": "GCS2",
"plugin": {
"name": "GCS",
"type": "batchsink",
"label": "GCS2",
"artifact": {"name": "google-cloud", "version": "0.21.2", "scope": "SYSTEM"},
"properties": {
"project": "auto-detect",
"suffix": "yyyy-MM-dd-HH-mm",
"format": "json",
"serviceFilePath": "auto-detect",
"location": "us",
"schema": '{"type":"record","name":"textfile","fields":[{"name"\
:"offset","type":"long"},{"name":"body","type":"string"}]}',
"referenceName": "bar",
"path": BUCKET_NAME_2_URI,
"serviceAccountType": "filePath",
"contentType": "application/octet-stream",
},
},
"outputSchema": '{"type":"record","name":"textfile","fields"\
:[{"name":"offset","type":"long"},{"name":"body","type":"string"}]}',
"inputSchema": [
{
"name": "GCS",
"schema": '{"type":"record","name":"textfile","fields":[{"name"\
:"offset","type":"long"},{"name":"body","type":"string"}]}',
}
],
"id": "GCS2",
},
],
"schedule": "0 * * * *",
"engine": "spark",
"numOfRecordsPreview": 100,
"description": "Data Pipeline Application",
"maxConcurrentRuns": 1,
},
}
# [END howto_data_fusion_env_variables]
with models.DAG(
DAG_ID,
start_date=datetime(2021, 1, 1),
catchup=False,
tags=["example", "datafusion", "deferrable"],
) as dag:
[docs] create_bucket1 = GCSCreateBucketOperator(
task_id="create_bucket1",
bucket_name=BUCKET_NAME_1,
project_id=PROJECT_ID,
)
create_bucket2 = GCSCreateBucketOperator(
task_id="create_bucket2",
bucket_name=BUCKET_NAME_2,
project_id=PROJECT_ID,
)
# [START howto_cloud_data_fusion_create_instance_operator]
create_instance = CloudDataFusionCreateInstanceOperator(
location=LOCATION,
instance_name=INSTANCE_NAME,
instance=INSTANCE,
task_id="create_instance",
)
# [END howto_cloud_data_fusion_create_instance_operator]
# [START howto_cloud_data_fusion_get_instance_operator]
get_instance = CloudDataFusionGetInstanceOperator(
location=LOCATION, instance_name=INSTANCE_NAME, task_id="get_instance"
)
# [END howto_cloud_data_fusion_get_instance_operator]
# [START howto_cloud_data_fusion_restart_instance_operator]
restart_instance = CloudDataFusionRestartInstanceOperator(
location=LOCATION, instance_name=INSTANCE_NAME, task_id="restart_instance"
)
# [END howto_cloud_data_fusion_restart_instance_operator]
# [START howto_cloud_data_fusion_update_instance_operator]
update_instance = CloudDataFusionUpdateInstanceOperator(
location=LOCATION,
instance_name=INSTANCE_NAME,
instance=INSTANCE,
update_mask="",
task_id="update_instance",
)
# [END howto_cloud_data_fusion_update_instance_operator]
# [START howto_cloud_data_fusion_create_pipeline]
create_pipeline = CloudDataFusionCreatePipelineOperator(
location=LOCATION,
pipeline_name=PIPELINE_NAME,
pipeline=PIPELINE,
instance_name=INSTANCE_NAME,
task_id="create_pipeline",
)
# [END howto_cloud_data_fusion_create_pipeline]
# [START howto_cloud_data_fusion_list_pipelines]
list_pipelines = CloudDataFusionListPipelinesOperator(
location=LOCATION, instance_name=INSTANCE_NAME, task_id="list_pipelines"
)
# [END howto_cloud_data_fusion_list_pipelines]
# [START howto_cloud_data_fusion_start_pipeline_def]
start_pipeline_def = CloudDataFusionStartPipelineOperator(
location=LOCATION,
pipeline_name=PIPELINE_NAME,
instance_name=INSTANCE_NAME,
deferrable=True,
task_id="start_pipeline_def",
)
# [END howto_cloud_data_fusion_start_pipeline_def]
# [START howto_cloud_data_fusion_stop_pipeline]
stop_pipeline = CloudDataFusionStopPipelineOperator(
location=LOCATION,
pipeline_name=PIPELINE_NAME,
instance_name=INSTANCE_NAME,
task_id="stop_pipeline",
)
# [END howto_cloud_data_fusion_stop_pipeline]
# [START howto_cloud_data_fusion_delete_pipeline]
delete_pipeline = CloudDataFusionDeletePipelineOperator(
location=LOCATION,
pipeline_name=PIPELINE_NAME,
instance_name=INSTANCE_NAME,
task_id="delete_pipeline",
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_cloud_data_fusion_delete_pipeline]
# [START howto_cloud_data_fusion_delete_instance_operator]
delete_instance = CloudDataFusionDeleteInstanceOperator(
location=LOCATION,
instance_name=INSTANCE_NAME,
task_id="delete_instance",
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_cloud_data_fusion_delete_instance_operator]
delete_bucket1 = GCSDeleteBucketOperator(
task_id="delete_bucket1", bucket_name=BUCKET_NAME_1, trigger_rule=TriggerRule.ALL_DONE
)
delete_bucket2 = GCSDeleteBucketOperator(
task_id="delete_bucket2", bucket_name=BUCKET_NAME_1, trigger_rule=TriggerRule.ALL_DONE
)
(
# TEST SETUP
[create_bucket1, create_bucket2]
# TEST BODY
>> create_instance
>> get_instance
>> restart_instance
>> update_instance
>> create_pipeline
>> list_pipelines
>> start_pipeline_def
>> stop_pipeline
>> delete_pipeline
>> delete_instance
# TEST TEARDOWN
>> [delete_bucket1, delete_bucket2]
)
from tests.system.utils.watcher import watcher
# This test needs watcher in order to properly mark success/failure
# when "tearDown" task with trigger rule is part of the DAG
list(dag.tasks) >> watcher()
from tests.system.utils import get_test_run # noqa: E402
# Needed to run the example DAG with pytest (see: tests/system/README.md#run_via_pytest)
[docs]test_run = get_test_run(dag)
