def run()

in python/dataproc_templates/jdbc/jdbc_to_bigquery.py [0:0]
50 lines of code
9 McCabe index (conditional complexity)

    def run(self, spark: SparkSession, args: Dict[str, Any]) -> None:

        logger: Logger = self.get_logger(spark=spark)

        # Arguments
        big_query_dataset: str = args[constants.JDBC_BQ_OUTPUT_DATASET]
        big_query_table: str = args[constants.JDBC_BQ_OUTPUT_TABLE]
        bq_temp_bucket: str = args[constants.JDBC_BQ_LD_TEMP_BUCKET_NAME]
        
        #check if secret is passed or the connection string in the agruments
        if str(args[constants.JDBC_BQ_INPUT_URL])=="":
            input_jdbc_url: str = secret_manager.access_secret_version(args[constants.JDBC_BQ_INPUT_URL_SECRET])
        else:
            input_jdbc_url: str = args[constants.JDBC_BQ_INPUT_URL]

        input_jdbc_driver: str = args[constants.JDBC_BQ_INPUT_DRIVER]
        input_jdbc_table: str = args[constants.JDBC_BQ_INPUT_TABLE]
        input_jdbc_partitioncolumn: str = args[constants.JDBC_BQ_INPUT_PARTITIONCOLUMN]
        input_jdbc_lowerbound: str = args[constants.JDBC_BQ_INPUT_LOWERBOUND]
        input_jdbc_upperbound: str = args[constants.JDBC_BQ_INPUT_UPPERBOUND]
        jdbc_numpartitions: str = args[constants.JDBC_BQ_NUMPARTITIONS]
        input_jdbc_fetchsize: int = args[constants.JDBC_BQ_INPUT_FETCHSIZE]
        input_jdbc_sessioninitstatement: str = args[constants.JDBC_BQ_SESSIONINITSTATEMENT]
        output_mode: str = args[constants.JDBC_BQ_OUTPUT_MODE]

        ignore_keys = {constants.JDBC_BQ_INPUT_URL}
        filtered_args = {key:val for key,val in args.items() if key not in ignore_keys}
        logger.info(
            "Starting JDBC to BigQuery Spark job with parameters:\n"
            f"{pprint.pformat(filtered_args)}"
        )

        # Read
        input_data: DataFrame

        partition_parameters = str(input_jdbc_partitioncolumn) + str(input_jdbc_lowerbound) + str(input_jdbc_upperbound)
        if ((partition_parameters != "") & ((input_jdbc_partitioncolumn == "") | (input_jdbc_lowerbound == "") | (input_jdbc_upperbound == ""))):
            logger.error("Set all the sql partitioning parameters together-jdbctogcs.input.partitioncolumn,jdbctogcs.input.lowerbound,jdbctogcs.input.upperbound. Refer to README.md for more instructions.")
            exit (1)

        properties = {constants.JDBC_URL: input_jdbc_url,
                      constants.JDBC_DRIVER: input_jdbc_driver,
                      constants.JDBC_TABLE: input_jdbc_table,
                      constants.JDBC_NUMPARTITIONS: jdbc_numpartitions,
                      constants.JDBC_FETCHSIZE: input_jdbc_fetchsize}
        if input_jdbc_sessioninitstatement:
            properties[constants.JDBC_SESSIONINITSTATEMENT] = input_jdbc_sessioninitstatement
        if partition_parameters:
            properties.update({constants.JDBC_PARTITIONCOLUMN: input_jdbc_partitioncolumn,
                               constants.JDBC_LOWERBOUND: input_jdbc_lowerbound,
                               constants.JDBC_UPPERBOUND: input_jdbc_upperbound})

        input_data = spark.read \
            .format(constants.FORMAT_JDBC) \
            .options(**properties) \
            .load()

        # Write
        input_data.write \
                .format(constants.FORMAT_BIGQUERY) \
                .option(constants.TABLE, big_query_dataset + "." + big_query_table) \
                .option(constants.GCS_BQ_TEMP_BUCKET, bq_temp_bucket) \
                .mode(output_mode) \
                .save()