Source code for tests.system.providers.google.cloud.dataflow.example_dataflow_native_python
#
# 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 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 import models
from airflow.providers.apache.beam.operators.beam import BeamRunPythonPipelineOperator
from airflow.providers.google.cloud.operators.gcs import GCSCreateBucketOperator, GCSDeleteBucketOperator
from airflow.providers.google.cloud.transfers.local_to_gcs 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]PYTHON_FILE_NAME = "wordcount_debugging.txt"
[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]GCS_PYTHON_SCRIPT = f"gs://{BUCKET_NAME}/{PYTHON_FILE_NAME}"
[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 models.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(
task_id="start_python_job",
py_file=GCS_PYTHON_SCRIPT,
py_options=[],
pipeline_options={
"output": GCS_OUTPUT,
},
py_requirements=["apache-beam[gcp]==2.36.0"],
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]==2.36.0"],
py_interpreter="python3",
py_system_site_packages=False,
)
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
# 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/README.md#run_via_pytest)
[docs]test_run = get_test_run(dag)