def main()

in courses/understanding_spanner/dataflow/spanner-to-bq.py [0:0]

• 28 lines of code
• 1 McCabe index (conditional complexity)

def main(argv=None, save_main_session=True):
    """Main entry point."""
    projectid = os.environ.get('GOOGLE_CLOUD_PROJECT')
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '--instance',
        dest='instance',
        default='test-spanner-instance',
        help='Spanner instance ID.')
    parser.add_argument(
        '--database',
        dest='database',
        default = 'pets-db',      
        help='Spanner database.')
    known_args, pipeline_args = parser.parse_known_args(argv)

    pipeline_options = PipelineOptions(pipeline_args)
    pipeline_options.view_as(SetupOptions).save_main_session = save_main_session

    with beam.Pipeline(options=pipeline_options) as p:
        owner_pets = p | ReadFromSpanner(
                            project_id=projectid,
                            instance_id=known_args.instance,
                            database_id=known_args.database,
                            row_type=PetRow,
                            sql = "SELECT OwnerID, PetName, PetType, Breed FROM Pets"
                            ).with_output_types(PetRow)
                            
        ( owner_pets | beam.Map(lambda x : x._asdict())
                     | beam.io.WriteToBigQuery('Pets', dataset = 'petsdb', project = projectid, method = 'STREAMING_INSERTS')
        )
        owner_pets | beam.Map(print)