in python/dataproc_templates/s3/s3_to_bigquery.py [0:0]
def parse_args(args: Optional[Sequence[str]] = None) -> Dict[str, Any]:
parser: argparse.ArgumentParser = argparse.ArgumentParser()
parser.add_argument(
f'--{constants.S3_BQ_INPUT_LOCATION}',
dest=constants.S3_BQ_INPUT_LOCATION,
required=True,
help='Amazon S3 input location. Input location must begin with s3a://'
)
parser.add_argument(
f'--{constants.S3_BQ_ACCESS_KEY}',
dest=constants.S3_BQ_ACCESS_KEY,
required=True,
help='Access key to access Amazon S3 bucket'
)
parser.add_argument(
f'--{constants.S3_BQ_SECRET_KEY}',
dest=constants.S3_BQ_SECRET_KEY,
required=True,
help='Secret key to access Amazon S3 bucket'
)
parser.add_argument(
f'--{constants.S3_BQ_INPUT_FORMAT}',
dest=constants.S3_BQ_INPUT_FORMAT,
required=True,
help='Input file format in Amazon S3 bucket (one of : avro, parquet, csv, json)',
choices=[
constants.FORMAT_AVRO,
constants.FORMAT_PRQT,
constants.FORMAT_CSV,
constants.FORMAT_JSON
]
)
parser.add_argument(
f'--{constants.S3_BQ_OUTPUT_DATASET_NAME}',
dest=constants.S3_BQ_OUTPUT_DATASET_NAME,
required=True,
help='BigQuery dataset for the output table'
)
parser.add_argument(
f'--{constants.S3_BQ_OUTPUT_TABLE_NAME}',
dest=constants.S3_BQ_OUTPUT_TABLE_NAME,
required=True,
help='BigQuery output table name'
)
parser.add_argument(
f'--{constants.S3_BQ_TEMP_BUCKET_NAME}',
dest=constants.S3_BQ_TEMP_BUCKET_NAME,
required=True,
help='Pre existing GCS bucket name where temporary files are staged'
)
parser.add_argument(
f'--{constants.S3_BQ_OUTPUT_MODE}',
dest=constants.S3_BQ_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
]
)
known_args: argparse.Namespace
known_args, _ = parser.parse_known_args(args)
return vars(known_args)