def parse_args()

in python/dataproc_templates/bigquery/bigquery_to_gcs.py [0:0]
54 lines of code
1 McCabe index (conditional complexity)

    def parse_args(args: Optional[Sequence[str]] = None) -> Dict[str, Any]:
        parser: argparse.ArgumentParser = argparse.ArgumentParser()

        parser.add_argument(
            f'--{constants.BQ_GCS_INPUT_TABLE}',
            dest=constants.BQ_GCS_INPUT_TABLE,
            required=True,
            help='BigQuery Input table name'
        )
        parser.add_argument(
            f'--{constants.BQ_GCS_OUTPUT_FORMAT}',
            dest=constants.BQ_GCS_OUTPUT_FORMAT,
            required=True,
            help='Output file format (one of: avro,parquet,csv,json)',
            choices=[
                constants.FORMAT_AVRO,
                constants.FORMAT_PRQT,
                constants.FORMAT_CSV,
                constants.FORMAT_JSON
            ]
        )
        parser.add_argument(
            f'--{constants.BQ_GCS_OUTPUT_LOCATION}',
            dest=constants.BQ_GCS_OUTPUT_LOCATION,
            required=True,
            help='Cloud Storage location for output files'
        )
        parser.add_argument(
            f'--{constants.BQ_GCS_OUTPUT_PARTITION_COLUMN}',
            dest=constants.BQ_GCS_OUTPUT_PARTITION_COLUMN,
            required=False,
            default="",
            help='Partition column name to partition the final output in destination bucket'
        )
        parser.add_argument(
            f'--{constants.BQ_GCS_OUTPUT_MODE}',
            dest=constants.BQ_GCS_OUTPUT_MODE,
            required=False,
            default=constants.OUTPUT_MODE_APPEND,
            help=(
                'Output write mode '
                '(one of: append,overwrite,ignore,errorifexists) '
                '(Defaults to append)'
            ),
            choices=[
                constants.OUTPUT_MODE_OVERWRITE,
                constants.OUTPUT_MODE_APPEND,
                constants.OUTPUT_MODE_IGNORE,
                constants.OUTPUT_MODE_ERRORIFEXISTS
            ]
        )
        add_spark_options(parser, constants.get_csv_output_spark_options("bigquery.gcs.output."))

        known_args: argparse.Namespace
        known_args, _ = parser.parse_known_args(args)

        return vars(known_args)