Source code for

# 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
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

Example Airflow DAG for testing Google DataPipelines Create Data Pipeline Operator.
from __future__ import annotations

import os
from datetime import datetime
from pathlib import Path

from airflow.models.dag import DAG
from import (
from import GCSCreateBucketOperator, GCSDeleteBucketOperator
from import LocalFilesystemToGCSOperator
from airflow.utils.trigger_rule import TriggerRule

[docs]DAG_ID = "google-datapipeline"
[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID")
[docs]GCP_LOCATION = os.environ.get("location", "us-central1")
[docs]PIPELINE_NAME = os.environ.get("DATA_PIPELINE_NAME", "defualt-pipeline-name")
[docs]BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}"
[docs]FILE_NAME = "kinglear.txt"
[docs]TEMPLATE_FILE = "word-count.json"
[docs]DATAPIPELINES_JOB_NAME = "test-job-name"
[docs]TEMP_LOCATION = f"gs://{BUCKET_NAME}/temp"
[docs]GCS_PATH = f"gs://{BUCKET_NAME}/templates/{TEMPLATE_FILE}"
[docs]INPUT_FILE = f"gs://{BUCKET_NAME}/examples/{FILE_NAME}"
[docs]OUTPUT = f"gs://{BUCKET_NAME}/results/hello"
[docs]FILE_LOCAL_PATH = str(Path(__file__).parent / "resources" / FILE_NAME)
[docs]TEMPLATE_LOCAL_PATH = str(Path(__file__).parent / "resources" / TEMPLATE_FILE)
with DAG( DAG_ID, schedule="@once", start_date=datetime(2021, 1, 1), catchup=False, tags=["example", "datapipeline"], ) as dag:
[docs] create_bucket = GCSCreateBucketOperator(task_id="create_bucket", bucket_name=BUCKET_NAME)
upload_file = LocalFilesystemToGCSOperator( task_id="upload_file_to_bucket", src=FILE_LOCAL_PATH, dst=FILE_NAME, bucket=BUCKET_NAME, ) upload_template = LocalFilesystemToGCSOperator( task_id="upload_template_to_bucket", src=TEMPLATE_LOCAL_PATH, dst=TEMPLATE_FILE, bucket=BUCKET_NAME, ) # [START howto_operator_create_data_pipeline] create_data_pipeline = CreateDataPipelineOperator( task_id="create_data_pipeline", project_id=GCP_PROJECT_ID, location=GCP_LOCATION, body={ "name": f"projects/{GCP_PROJECT_ID}/locations/{GCP_LOCATION}/pipelines/{PIPELINE_NAME}", "type": PIPELINE_TYPE, "workload": { "dataflowFlexTemplateRequest": { "launchParameter": { "containerSpecGcsPath": GCS_PATH, "jobName": DATAPIPELINES_JOB_NAME, "environment": {"tempLocation": TEMP_LOCATION}, "parameters": { "inputFile": INPUT_FILE, "output": OUTPUT, }, }, "projectId": GCP_PROJECT_ID, "location": GCP_LOCATION, } }, }, ) # [END howto_operator_create_data_pipeline] delete_bucket = GCSDeleteBucketOperator( task_id="delete_bucket", bucket_name=BUCKET_NAME, trigger_rule=TriggerRule.ALL_DONE ) (create_bucket >> upload_file >> upload_template >> create_data_pipeline >> delete_bucket) 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() # [START howto_operator_run_data_pipeline] run_data_pipeline = RunDataPipelineOperator( task_id="run_data_pipeline", data_pipeline_name=PIPELINE_NAME, project_id=GCP_PROJECT_ID, ) # [END howto_operator_run_data_pipeline] from tests.system.utils import get_test_run # noqa: E402 # Needed to run the example DAG with pytest (see: tests/system/
[docs]test_run = get_test_run(dag)

Was this entry helpful?