bhirsz commented on a change in pull request #22311: URL: https://github.com/apache/airflow/pull/22311#discussion_r829885457
########## File path: tests/system/providers/google/bigquery/example_bigquery_operations.py ########## @@ -0,0 +1,106 @@ +# +# 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 local file upload and external table creation. +""" +import os +from datetime import datetime +from pathlib import Path + +from airflow import models +from airflow.providers.google.cloud.operators.bigquery import ( + BigQueryCreateEmptyDatasetOperator, + BigQueryCreateExternalTableOperator, + BigQueryDeleteDatasetOperator, +) +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 +from tests.system.utils.watcher import watcher + +ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID") +DAG_ID = "bigquery_operations" + +DATASET_NAME = f"dataset_{DAG_ID}_{ENV_ID}" +DATA_SAMPLE_GCS_BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}" +DATA_SAMPLE_GCS_OBJECT_NAME = "bigquery/us-states/us-states.csv" +CSV_FILE_LOCAL_PATH = str(Path(__file__).parent / "resources" / "us-states.csv") + + +with models.DAG( + DAG_ID, + schedule_interval="@once", + start_date=datetime(2021, 1, 1), + catchup=False, + tags=["example", "bigquery"], +) as dag: + create_bucket = GCSCreateBucketOperator(task_id="create_bucket", bucket_name=DATA_SAMPLE_GCS_BUCKET_NAME) + + create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET_NAME) + + upload_file = LocalFilesystemToGCSOperator( + task_id="upload_file_to_bucket", + src=CSV_FILE_LOCAL_PATH, + dst=DATA_SAMPLE_GCS_OBJECT_NAME, + bucket=DATA_SAMPLE_GCS_BUCKET_NAME, + ) + + # [START howto_operator_bigquery_create_external_table] + create_external_table = BigQueryCreateExternalTableOperator( + task_id="create_external_table", + destination_project_dataset_table=f"{DATASET_NAME}.external_table", + bucket=DATA_SAMPLE_GCS_BUCKET_NAME, + source_objects=[DATA_SAMPLE_GCS_OBJECT_NAME], + schema_fields=[ + {"name": "emp_name", "type": "STRING", "mode": "REQUIRED"}, + {"name": "salary", "type": "INTEGER", "mode": "NULLABLE"}, + ], + ) + # [END howto_operator_bigquery_create_external_table] + + 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=DATA_SAMPLE_GCS_BUCKET_NAME, trigger_rule=TriggerRule.ALL_DONE + ) + + ( + # TEST SETUP + [create_bucket, create_dataset] + # TEST BODY + >> upload_file + >> create_external_table + # TEST TEARDOWN + >> delete_dataset + >> delete_bucket + ) + + list(dag.tasks) >> watcher() Review comment: > Writing the same line in hundreds of files just feels wrong I fully agree with you and it was actually the reason for the redesign - where we had dozens of lines repeated for every test only to trigger other file with the DAG. And we always welcome any suggestions and discussion. We changed the design several times over the time thanks for the input from the others. I agree with Jarek here - the goal is to have an example dag that can be used by other Airflow users as reference and it would be best to avoid any code specific only to system test. Proposed local import of the watcher looks like a good idea for me for this reason alone ########## File path: tests/system/providers/google/bigquery/example_bigquery_operations.py ########## @@ -0,0 +1,106 @@ +# +# 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 local file upload and external table creation. +""" +import os +from datetime import datetime +from pathlib import Path + +from airflow import models +from airflow.providers.google.cloud.operators.bigquery import ( + BigQueryCreateEmptyDatasetOperator, + BigQueryCreateExternalTableOperator, + BigQueryDeleteDatasetOperator, +) +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 +from tests.system.utils.watcher import watcher + +ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID") +DAG_ID = "bigquery_operations" + +DATASET_NAME = f"dataset_{DAG_ID}_{ENV_ID}" +DATA_SAMPLE_GCS_BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}" +DATA_SAMPLE_GCS_OBJECT_NAME = "bigquery/us-states/us-states.csv" +CSV_FILE_LOCAL_PATH = str(Path(__file__).parent / "resources" / "us-states.csv") + + +with models.DAG( + DAG_ID, + schedule_interval="@once", + start_date=datetime(2021, 1, 1), + catchup=False, + tags=["example", "bigquery"], +) as dag: + create_bucket = GCSCreateBucketOperator(task_id="create_bucket", bucket_name=DATA_SAMPLE_GCS_BUCKET_NAME) + + create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET_NAME) + + upload_file = LocalFilesystemToGCSOperator( + task_id="upload_file_to_bucket", + src=CSV_FILE_LOCAL_PATH, + dst=DATA_SAMPLE_GCS_OBJECT_NAME, + bucket=DATA_SAMPLE_GCS_BUCKET_NAME, + ) + + # [START howto_operator_bigquery_create_external_table] + create_external_table = BigQueryCreateExternalTableOperator( + task_id="create_external_table", + destination_project_dataset_table=f"{DATASET_NAME}.external_table", + bucket=DATA_SAMPLE_GCS_BUCKET_NAME, + source_objects=[DATA_SAMPLE_GCS_OBJECT_NAME], + schema_fields=[ + {"name": "emp_name", "type": "STRING", "mode": "REQUIRED"}, + {"name": "salary", "type": "INTEGER", "mode": "NULLABLE"}, + ], + ) + # [END howto_operator_bigquery_create_external_table] + + 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=DATA_SAMPLE_GCS_BUCKET_NAME, trigger_rule=TriggerRule.ALL_DONE + ) + + ( + # TEST SETUP + [create_bucket, create_dataset] + # TEST BODY + >> upload_file + >> create_external_table + # TEST TEARDOWN + >> delete_dataset + >> delete_bucket + ) + + list(dag.tasks) >> watcher() Review comment: > Writing the same line in hundreds of files just feels wrong I fully agree with you and it was actually the reason for the redesign - where we had dozens of lines repeated for every test only to trigger other file with the DAG. And we always welcome any suggestions and discussion. We changed the design several times over the time thanks for the input from the others. I agree with Jarek here - the goal is to have an example dag that can be used by other Airflow users as reference and it would be best to avoid any code specific only to system test. Proposed local import of the watcher looks like a good idea for me for this reason alone -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
