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 Dataflow Beam Pipeline Operator with Python.
from __future__ import annotations

import os
from datetime import datetime
from pathlib import Path

from airflow.models.dag import DAG
from airflow.providers.apache.beam.hooks.beam import BeamRunnerType
from airflow.providers.apache.beam.operators.beam import BeamRunPythonPipelineOperator
from import DataflowStopJobOperator
from import GCSCreateBucketOperator, GCSDeleteBucketOperator
from import LocalFilesystemToGCSOperator
from airflow.utils.trigger_rule import TriggerRule

[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID")
[docs]DAG_ID = "dataflow_native_python"
[docs]BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}"
[docs]GCS_TMP = f"gs://{BUCKET_NAME}/temp/"
[docs]GCS_STAGING = f"gs://{BUCKET_NAME}/staging/"
[docs]GCS_OUTPUT = f"gs://{BUCKET_NAME}/output"
[docs]PYTHON_FILE_LOCAL_PATH = str(Path(__file__).parent / "resources" / PYTHON_FILE_NAME)
[docs]LOCATION = "europe-west3"
[docs]default_args = { "dataflow_default_options": { "tempLocation": GCS_TMP, "stagingLocation": GCS_STAGING, } }
with DAG( DAG_ID, default_args=default_args, schedule="@once", start_date=datetime(2021, 1, 1), catchup=False, tags=["example", "dataflow"], ) as dag:
[docs] create_bucket = GCSCreateBucketOperator(task_id="create_bucket", bucket_name=BUCKET_NAME)
upload_file = LocalFilesystemToGCSOperator( task_id="upload_file_to_bucket", src=PYTHON_FILE_LOCAL_PATH, dst=PYTHON_FILE_NAME, bucket=BUCKET_NAME, ) # [START howto_operator_start_python_job] start_python_job = BeamRunPythonPipelineOperator( runner=BeamRunnerType.DataflowRunner, task_id="start_python_job", py_file=GCS_PYTHON_SCRIPT, py_options=[], pipeline_options={ "output": GCS_OUTPUT, }, py_requirements=["apache-beam[gcp]==2.46.0"], py_interpreter="python3", py_system_site_packages=False, dataflow_config={"location": LOCATION}, ) # [END howto_operator_start_python_job] start_python_job_local = BeamRunPythonPipelineOperator( task_id="start_python_job_local", py_file="apache_beam.examples.wordcount", py_options=["-m"], pipeline_options={ "output": GCS_OUTPUT, }, py_requirements=["apache-beam[gcp]==2.46.0"], py_interpreter="python3", py_system_site_packages=False, ) # [START howto_operator_stop_dataflow_job] stop_dataflow_job = DataflowStopJobOperator( task_id="stop_dataflow_job", location=LOCATION, job_name_prefix="start-python-pipeline", ) # [END howto_operator_stop_dataflow_job] delete_bucket = GCSDeleteBucketOperator( task_id="delete_bucket", bucket_name=BUCKET_NAME, trigger_rule=TriggerRule.ALL_DONE ) ( # TEST SETUP create_bucket >> upload_file # TEST BODY >> start_python_job >> start_python_job_local >> stop_dataflow_job # TEST TEARDOWN >> 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() 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?