示例#1
0
                "name": "emp_name",
                "type": "STRING",
                "mode": "REQUIRED"
            },
            {
                "name": "salary",
                "type": "INTEGER",
                "mode": "NULLABLE"
            },
        ],
    )
    # [END howto_operator_bigquery_create_table]

    # [START howto_operator_bigquery_delete_table]
    delete_table = BigQueryDeleteTableOperator(
        task_id="delete_table",
        deletion_dataset_table=f"{PROJECT_ID}.{DATASET_NAME}.test_table",
    )
    # [END howto_operator_bigquery_delete_table]

    # [START howto_operator_bigquery_create_view]
    create_view = BigQueryCreateEmptyTableOperator(
        task_id="create_view",
        dataset_id=DATASET_NAME,
        table_id="test_view",
        view={
            "query": f"SELECT * FROM `{PROJECT_ID}.{DATASET_NAME}.test_table`",
            "useLegacySql": False,
        },
    )
    # [END howto_operator_bigquery_create_view]
示例#2
0
        task_id="create_view",
        dataset_id=LOCATION_DATASET_NAME,
        table_id="test_view",
        view={
            "query": "SELECT * FROM `{}.test_table`".format(DATASET_NAME),
            "useLegacySql": False
        })

    get_empty_dataset_tables = BigQueryGetDatasetTablesOperator(
        task_id="get_empty_dataset_tables", dataset_id=DATASET_NAME)

    get_dataset_tables = BigQueryGetDatasetTablesOperator(
        task_id="get_dataset_tables", dataset_id=DATASET_NAME)

    delete_view = BigQueryDeleteTableOperator(
        task_id="delete_view",
        deletion_dataset_table="{}.test_view".format(DATASET_NAME))

    delete_table = BigQueryDeleteTableOperator(
        task_id="delete_table",
        deletion_dataset_table="{}.test_table".format(DATASET_NAME))

    get_dataset = BigQueryGetDatasetOperator(task_id="get-dataset",
                                             dataset_id=DATASET_NAME)

    get_dataset_result = BashOperator(
        task_id="get_dataset_result",
        bash_command=
        "echo \"{{ task_instance.xcom_pull('get-dataset')['id'] }}\"",
    )
示例#3
0
        project_id=os.environ['GCP_PROJECT_ID'],
        region=os.environ['GCP_REGION'],
        parameters={
            'PATH_TO_ETL_FILE':
            f"gs://{os.environ['GCP_GCS_BUCKET_ROUTINE']}/etl/etl.py",
            'CLUSTER_NAME': 'goodreads-etl',
            'ARG_SOURCE_BUCKET': os.environ['GCP_GCS_BUCKET_WORKING'],
            'ARG_DESTINATION_BUCKET': os.environ['GCP_GCS_BUCKET_PROCESSED'],
            'ARG_OBJECT_PREFIX': '{{ run_id }}',
        },
        gcp_conn_id='gr_dataproc_conn',
    )

    drop_stage_user_data = BigQueryDeleteTableOperator(
        task_id="drop_stage_user_data",
        deletion_dataset_table=
        f"{GCP_PROJECT_ID}.{GCP_BQ_DATASET_STAGE}.{GCP_BQ_TABLE_USERS}",
        gcp_conn_id='gr_bigquery_conn',
        ignore_if_missing=True)

    drop_stage_authors_data = BigQueryDeleteTableOperator(
        task_id="drop_stage_authors_data",
        deletion_dataset_table=
        f"{GCP_PROJECT_ID}.{GCP_BQ_DATASET_STAGE}.{GCP_BQ_TABLE_AUTHORS}",
        gcp_conn_id='gr_bigquery_conn',
        ignore_if_missing=True)

    drop_stage_books_data = BigQueryDeleteTableOperator(
        task_id="drop_stage_books_data",
        deletion_dataset_table=
        f"{GCP_PROJECT_ID}.{GCP_BQ_DATASET_STAGE}.{GCP_BQ_TABLE_BOOKS}",
        gcp_conn_id='gr_bigquery_conn',