in jobs/socorro_import_crash_data.py [0:0]
def parse_args():
parser = argparse.ArgumentParser(
description="Write json socorro crash reports to parquet."
)
parser.add_argument(
"--date",
"-d",
required=True,
help="Date (ds_nodash in airflow) of data to process. E.g. 20190801.",
)
parser.add_argument(
"--source-gcs-path",
required=True,
help="The source gcs path, without the date folder prefix. E.g. gs://moz-fx-data-prod-socorro/v1/crash_report",
)
parser.add_argument(
"--dest-gcs-path",
required=True,
help="The destination gcs path, without version and date folder prefixes. E.g. gs://moz-fx-data-prod-socorro/socorro_crash_parquet",
)
parser.add_argument(
"--num-partitions",
type=int,
default=10,
help="Number of partitions to use when rewriting json to parquet.",
)
return parser.parse_args()