kzosabe commented on a change in pull request #18694:
URL: https://github.com/apache/superset/pull/18694#discussion_r807789432
##########
File path: superset/db_engine_specs/bigquery.py
##########
@@ -185,6 +185,60 @@ class BigQueryEngineSpec(BaseEngineSpec):
),
}
+ @classmethod
+ def get_allow_cost_estimate(cls, extra: Dict[str, Any]) -> bool:
+ return True
+
+ @classmethod
+ def estimate_statement_cost(
+ cls, statement: str, cursor: Any, engine: Engine
+ ) -> Dict[str, Any]:
+ try:
+ # pylint: disable=import-outside-toplevel
+ from google.cloud import bigquery
+ from google.oauth2 import service_account
+ except ImportError as ex:
+ raise Exception(
+ "Could not import libraries `google.cloud` or `google.oauth2`,
"
+ "which are required to be installed in your environment in
order "
+ "to estimate cost"
+ ) from ex
+
+ creds = engine.dialect.credentials_info
+ credentials =
service_account.Credentials.from_service_account_info(creds)
+ client = bigquery.Client(credentials=credentials)
+ dry_run_result = client.query(
+ statement, bigquery.job.QueryJobConfig(dry_run=True)
+ )
+
+ return {
+ "Total bytes processed": dry_run_result.total_bytes_processed,
+ }
+
+ @classmethod
+ def query_cost_formatter(
+ cls, raw_cost: List[Dict[str, Any]]
+ ) -> List[Dict[str, str]]:
+ def format_bytes_str(raw_bytes: int) -> str:
+ if not isinstance(raw_bytes, int):
+ return str(raw_bytes)
+ units = ["B", "KiB", "MiB", "GiB", "TiB", "PiB"]
+ index = 0
+ bytes = float(raw_bytes)
+ while bytes >= 1024 and index < len(units) - 1:
+ bytes /= 1024
+ index += 1
+
+ return "{:.1f}".format(bytes) + f" {units[index]}"
+
+ return [
+ {
+ k: format_bytes_str(v) if k == "Total bytes processed" else
str(v)
+ for k, v in row.items()
+ }
+ for row in raw_cost
+ ]
Review comment:
Does anyone have any suggestions?
I think the ability of estimating bytes is important, and the format is
relatively unimportant, so I'm not strongly concerned about how to handle it.
I think it would be better to refactor trino and presto to KiB notation, but
if there are some reasons not to do so, I'll make the BigQuery implementation
as KB notation.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
