HyukjinKwon commented on code in PR #41980:
URL: https://github.com/apache/spark/pull/41980#discussion_r1261978208
##########
python/pyspark/sql/connect/session.py:
##########
@@ -489,13 +489,31 @@ def createDataFrame(
createDataFrame.__doc__ = PySparkSession.createDataFrame.__doc__
- def sql(self, sqlQuery: str, args: Optional[Union[Dict[str, Any], List]] =
None) -> "DataFrame":
- cmd = SQL(sqlQuery, args)
- data, properties =
self.client.execute_command(cmd.command(self._client))
- if "sql_command_result" in properties:
- return
DataFrame.withPlan(CachedRelation(properties["sql_command_result"]), self)
- else:
- return DataFrame.withPlan(SQL(sqlQuery, args), self)
+ def sql(
+ self,
+ sqlQuery: str,
+ args: Optional[Union[Dict[str, Any], List]] = None,
+ **kwargs: Any,
+ ) -> "DataFrame":
+
+ if len(kwargs) > 0:
+ from pyspark.sql.connect.sql_formatter import SQLStringFormatter
+
+ formatter = SQLStringFormatter(self)
+ sqlQuery = formatter.format(sqlQuery, **kwargs)
+
+ try:
+ cmd = SQL(sqlQuery, args)
+ data, properties =
self.client.execute_command(cmd.command(self._client))
+ if "sql_command_result" in properties:
+ return
DataFrame.withPlan(CachedRelation(properties["sql_command_result"]), self)
+ else:
+ return DataFrame.withPlan(SQL(sqlQuery, args), self)
+ finally:
+ if len(kwargs) > 0:
Review Comment:
Can we call `cache` or `persist` on the DataFrame, and drop the table for
now? If that doesn't work, I am fine as is too but we would have to at least
clean the temp views ..
--
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]
