darcy-shen commented on a change in pull request #32332:
URL: https://github.com/apache/spark/pull/32332#discussion_r679585610
##########
File path: python/pyspark/sql/session.py
##########
@@ -483,13 +483,22 @@ def _inferSchema(self, rdd, samplingRatio=None,
names=None):
row, names,
infer_dict_as_struct=infer_dict_as_struct)).reduce(_merge_type)
return schema
- def _createFromRDD(self, rdd, schema, samplingRatio):
+ def _create_verified_converter(self, schema, verifySchema):
+ converter = _create_converter(schema)
+ verify_func = _make_type_verifier(schema) if verifySchema else lambda
_: True
+
+ def verify_and_convert(obj):
+ verify_func(obj)
+ return converter(obj)
+ return verify_and_convert
Review comment:
simplified now
--
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]
