def get_argument_parser(description):
"""Get the argument parser for the shared glean usage queries."""
parser = ArgumentParser(description=description)
parser.add_argument(
"--project_id",
"--project-id",
default="moz-fx-data-shar-nonprod-efed",
help="ID of the project in which to find tables",
)
parser.add_argument(
"--date",
required=True,
type=lambda d: datetime.strptime(d, "%Y-%m-%d").date(),
help="Date partition to process, in format 2019-01-01",
)
parser.add_argument(
"--output_dir",
"--output-dir",
help="Also write the query text underneath the given sql dir",
)
parser.add_argument(
"--output_only",
"--output-only",
"--views_only", # Deprecated name
"--views-only", # Deprecated name
action="store_true",
help=(
"If set, we only write out sql to --output-dir and we skip"
" running the queries"
),
)
standard_args.add_parallelism(parser)
standard_args.add_dry_run(parser, debug_log_queries=False)
standard_args.add_log_level(parser)
standard_args.add_priority(parser)
standard_args.add_billing_projects(parser)
standard_args.add_table_filter(parser)
return parser
"--project-id",
default="moz-fx-data-shar-nonprod-efed",
help="ID of the project in which to find tables",
)
parser.add_argument(
"--dates",
"--date",
nargs="+",
required=True,
type=lambda d: datetime.strptime(d, "%Y-%m-%d").date(),
help="One or more days of data to copy, in format 2019-01-01",
)
standard_args.add_parallelism(parser)
standard_args.add_dry_run(parser, debug_log_queries=False)
standard_args.add_log_level(parser)
standard_args.add_priority(parser)
standard_args.add_temp_dataset(parser)
parser.add_argument(
"--slices",
type=int,
default=1,
help=
("Number of queries to split deduplicate over, each handling an equal-size time "
"slice of the date; avoids memory overflow at the cost of less effective "
"clustering; recommended only for tables failing due to memory overflow"),
)
parser.add_argument(
"--hourly",
action="store_const",
dest="slices",
const=24,