def parse_args()

in python/dataproc_templates/jdbc/jdbc_to_gcs.py [0:0]
142 lines of code
5 McCabe index (conditional complexity)

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

        group = parser.add_mutually_exclusive_group(required=True)
        group.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_URL}',
            dest=constants.JDBCTOGCS_INPUT_URL,
            required=False,
            default="",
            help='JDBC input URL'
        )
        group.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_URL_SECRET}',
            dest=constants.JDBCTOGCS_INPUT_URL_SECRET,
            required=False,
            default="",
            help='JDBC input URL secret name'
        )    
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_DRIVER}',
            dest=constants.JDBCTOGCS_INPUT_DRIVER,
            required=True,
            help='JDBC input driver name'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_TABLE}',
            dest=constants.JDBCTOGCS_INPUT_TABLE,
            required=False,
            help='JDBC input table name'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_SQL_QUERY}',
            dest=constants.JDBCTOGCS_INPUT_SQL_QUERY,
            required=False,
            help='JDBC input SQL query'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_PARTITIONCOLUMN}',
            dest=constants.JDBCTOGCS_INPUT_PARTITIONCOLUMN,
            required=False,
            default="",
            help='JDBC input table partition column name'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_LOWERBOUND}',
            dest=constants.JDBCTOGCS_INPUT_LOWERBOUND,
            required=False,
            default="",
            help='JDBC input table partition column lower bound which is used to decide the partition stride'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_UPPERBOUND}',
            dest=constants.JDBCTOGCS_INPUT_UPPERBOUND,
            required=False,
            default="",
            help='JDBC input table partition column upper bound which is used to decide the partition stride'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_NUMPARTITIONS}',
            dest=constants.JDBCTOGCS_NUMPARTITIONS,
            required=False,
            default="10",
            help='The maximum number of partitions that can be used for parallelism in table reading and writing. Default set to 10'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_INPUT_FETCHSIZE}',
            dest=constants.JDBCTOGCS_INPUT_FETCHSIZE,
            required=False,
            default=0,
            type=int,
            help='Determines how many rows to fetch per round trip'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_SESSIONINITSTATEMENT}',
            dest=constants.JDBCTOGCS_SESSIONINITSTATEMENT,
            required=False,
            default="",
            help='Custom SQL statement to execute in each reader database session'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_OUTPUT_LOCATION}',
            dest=constants.JDBCTOGCS_OUTPUT_LOCATION,
            required=True,
            help='Cloud Storage location for output files'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_OUTPUT_FORMAT}',
            dest=constants.JDBCTOGCS_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.JDBCTOGCS_OUTPUT_MODE}',
            dest=constants.JDBCTOGCS_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
            ]
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_OUTPUT_PARTITIONCOLUMN}',
            dest=constants.JDBCTOGCS_OUTPUT_PARTITIONCOLUMN,
            required=False,
            default="",
            help='Cloud Storage partition column name'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_TEMP_VIEW_NAME}',
            dest=constants.JDBCTOGCS_TEMP_VIEW_NAME,
            required=False,
            default="",
            help='Temp view name for creating a spark sql view on source data. This name has to match with the table name that will be used in the SQL query'
        )
        parser.add_argument(
            f'--{constants.JDBCTOGCS_TEMP_SQL_QUERY}',
            dest=constants.JDBCTOGCS_TEMP_SQL_QUERY,
            required=False,
            default="",
            help='SQL query for data transformation. This must use the temp view name as the table to query from.'
        )
        add_spark_options(parser, constants.get_csv_output_spark_options("jdbc.gcs.output."))

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

        if getattr(known_args, constants.JDBCTOGCS_INPUT_TABLE) and getattr(known_args, constants.JDBCTOGCS_INPUT_SQL_QUERY):
            sys.exit('ArgumentParser Error: Arguments cannot have both input table and sql query, use either one.')

        if getattr(known_args, constants.JDBCTOGCS_TEMP_SQL_QUERY) and not getattr(known_args, constants.JDBCTOGCS_TEMP_VIEW_NAME):
            sys.exit('ArgumentParser Error: Temp view name cannot be null if you want to do data transformations with query')

        return vars(known_args)