allisonwang-db commented on code in PR #43360:
URL: https://github.com/apache/spark/pull/43360#discussion_r1362627217
##########
python/pyspark/sql/readwriter.py:
##########
@@ -69,20 +83,26 @@ class DataFrameReader(OptionUtils):
def __init__(self, spark: "SparkSession"):
self._jreader = spark._jsparkSession.read()
self._spark = spark
+ self._format: Optional[Union[str, Type[DataSource]]] = None
+ self._schema: Optional[Union[str, StructType]] = None
+ self._options: Dict[str, "OptionalPrimitiveType"] = dict()
def _df(self, jdf: JavaObject) -> "DataFrame":
from pyspark.sql.dataframe import DataFrame
return DataFrame(jdf, self._spark)
- def format(self, source: str) -> "DataFrameReader":
+ def format(self, source: Union[str, Type[DataSource]]) ->
"DataFrameReader":
Review Comment:
Yes we should also support using short names. But we need to support
registering the data source first. This is a TODO in the PR description: `4.
Register a Python data source and use its name to reference it in .format()`
--
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]
