#
# 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 Google BigQuery service.
"""
import os
from datetime import datetime
from airflow import models
from airflow.providers.google.cloud.operators.bigquery import (
BigQueryCreateEmptyDatasetOperator,
BigQueryCreateEmptyTableOperator,
BigQueryDeleteDatasetOperator,
)
from airflow.providers.google.cloud.operators.gcs import GCSCreateBucketOperator, GCSDeleteBucketOperator
from airflow.providers.google.cloud.transfers.bigquery_to_bigquery import BigQueryToBigQueryOperator
from airflow.providers.google.cloud.transfers.bigquery_to_gcs import BigQueryToGCSOperator
from airflow.utils.trigger_rule import TriggerRule
[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID")
[docs]PROJECT_ID = os.environ.get("SYSTEM_TESTS_GCP_PROJECT")
[docs]DAG_ID = "example_bigquery_transfer"
[docs]DATASET_NAME = f"dataset_{DAG_ID}_{ENV_ID}"
[docs]BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}"
with models.DAG(
DAG_ID,
schedule_interval='@once', # Override to match your needs
start_date=datetime(2021, 1, 1),
catchup=False,
tags=["example", "bigquery"],
) as dag:
[docs] create_bucket = GCSCreateBucketOperator(
task_id="create_bucket", bucket_name=BUCKET_NAME, project_id=PROJECT_ID
)
create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET_NAME)
create_origin_table = BigQueryCreateEmptyTableOperator(
task_id=f"create_{ORIGIN}_table",
dataset_id=DATASET_NAME,
table_id=ORIGIN,
schema_fields=[
{"name": "emp_name", "type": "STRING", "mode": "REQUIRED"},
{"name": "salary", "type": "INTEGER", "mode": "NULLABLE"},
],
)
create_target_table = BigQueryCreateEmptyTableOperator(
task_id=f"create_{TARGET}_table",
dataset_id=DATASET_NAME,
table_id=TARGET,
schema_fields=[
{"name": "emp_name", "type": "STRING", "mode": "REQUIRED"},
{"name": "salary", "type": "INTEGER", "mode": "NULLABLE"},
],
)
copy_selected_data = BigQueryToBigQueryOperator(
task_id="copy_selected_data",
source_project_dataset_tables=f"{DATASET_NAME}.{ORIGIN}",
destination_project_dataset_table=f"{DATASET_NAME}.{TARGET}",
)
bigquery_to_gcs = BigQueryToGCSOperator(
task_id="bigquery_to_gcs",
source_project_dataset_table=f"{DATASET_NAME}.{ORIGIN}",
destination_cloud_storage_uris=[f"gs://{BUCKET_NAME}/export-bigquery.csv"],
)
delete_dataset = BigQueryDeleteDatasetOperator(
task_id="delete_dataset",
dataset_id=DATASET_NAME,
delete_contents=True,
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
>> create_dataset
>> create_origin_table
>> create_target_table
# TEST BODY
>> copy_selected_data
>> bigquery_to_gcs
# TEST TEARDOWN
>> delete_dataset
>> 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)
