#
# 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 DataprocSubmitJobOperator with sparkr job.
"""
from __future__ import annotations
import os
from datetime import datetime
from pathlib import Path
from airflow import models
from airflow.providers.google.cloud.operators.dataproc import (
DataprocCreateClusterOperator,
DataprocDeleteClusterOperator,
DataprocSubmitJobOperator,
)
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 = "dataproc_sparkr"
[docs]PROJECT_ID = os.environ.get("SYSTEM_TESTS_GCP_PROJECT", "")
[docs]BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}"
[docs]CLUSTER_NAME = f"dataproc-sparkr-{ENV_ID}"
[docs]SPARKR_SRC = str(Path(__file__).parent / "resources" / "hello_world.R")
[docs]SPARKR_FILE = "hello_world.R"
# Cluster definition
[docs]CLUSTER_CONFIG = {
"master_config": {
"num_instances": 1,
"machine_type_uri": "n1-standard-4",
"disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 1024},
},
"worker_config": {
"num_instances": 2,
"machine_type_uri": "n1-standard-4",
"disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 1024},
},
}
[docs]TIMEOUT = {"seconds": 1 * 24 * 60 * 60}
# Jobs definitions
# [START how_to_cloud_dataproc_sparkr_config]
[docs]SPARKR_JOB = {
"reference": {"project_id": PROJECT_ID},
"placement": {"cluster_name": CLUSTER_NAME},
"spark_r_job": {"main_r_file_uri": f"gs://{BUCKET_NAME}/{SPARKR_FILE}"},
}
# [END how_to_cloud_dataproc_sparkr_config]
with models.DAG(
DAG_ID,
schedule="@once",
start_date=datetime(2021, 1, 1),
catchup=False,
tags=["example", "dataproc"],
) as dag:
[docs] create_bucket = GCSCreateBucketOperator(
task_id="create_bucket", bucket_name=BUCKET_NAME, project_id=PROJECT_ID
)
upload_file = LocalFilesystemToGCSOperator(
task_id="upload_file",
src=SPARKR_SRC,
dst=SPARKR_FILE,
bucket=BUCKET_NAME,
)
create_cluster = DataprocCreateClusterOperator(
task_id="create_cluster",
project_id=PROJECT_ID,
cluster_config=CLUSTER_CONFIG,
region=REGION,
cluster_name=CLUSTER_NAME,
)
sparkr_task = DataprocSubmitJobOperator(
task_id="sparkr_task", job=SPARKR_JOB, region=REGION, project_id=PROJECT_ID
)
delete_cluster = DataprocDeleteClusterOperator(
task_id="delete_cluster",
project_id=PROJECT_ID,
cluster_name=CLUSTER_NAME,
region=REGION,
trigger_rule=TriggerRule.ALL_DONE,
)
delete_bucket = GCSDeleteBucketOperator(
task_id="delete_bucket", bucket_name=BUCKET_NAME, trigger_rule=TriggerRule.ALL_DONE
)
# TEST SETUP
create_bucket >> [upload_file, create_cluster]
# TEST BODY
[upload_file, create_cluster] >> sparkr_task
# TEST TEARDOWN
sparkr_task >> [delete_cluster, 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)
