def task_6(task: tasks.Task, job: tasks.Job) -> str:
"""task06: a simple task creating a BigQuery asynchronous job."""
del job
logging.info('Running task_6.')
_, project = google.auth.default()
dst_table_id = f'{project}.{task.task_args["dest_table"]}'
client = bigquery.Client()
job_config = bigquery.QueryJobConfig(
destination=dst_table_id,
use_legacy_sql=False,
write_disposition=bigquery.job.WriteDisposition.WRITE_TRUNCATE)
sql = """
SELECT * FROM bigquery-public-data.samples.shakespeare
WHERE corpus = 'hamlet'
ORDER BY word_count DESC
LIMIT 10
"""
# The `shakespeare` sample dataset is located in the US region. If you get an
# error about the dataset not being available in your location,
# try using a different dataset, or one of your own. For example, for EU
# region you can use this query:
#
# sql = """
# SELECT rental_id, duration, end_station_name
# FROM `bigquery-public-data.london_bicycles.cycle_hire`
# ORDER BY start_date DESC
# LIMIT 10;
# """
query_job = client.query(sql, job_config=job_config)
bq_job_id = query_job.job_id
logging.info('Launched bq job %s.', bq_job_id)
return futures.BigQueryFuture(bq_job_id)
def task1(job, task):
mark_unused(job, task)
return futures.BigQueryFuture(trigger_id='test-bq-job-id')