cloud-fan commented on code in PR #38301: URL: https://github.com/apache/spark/pull/38301#discussion_r1002886025
########## python/pyspark/sql/connect/client.py: ########## @@ -151,7 +151,44 @@ def _to_pandas(self, plan: pb2.Plan) -> Optional[pandas.DataFrame]: req.plan.CopyFrom(plan) return self._execute_and_fetch(req) - def analyze(self, plan: pb2.Plan) -> AnalyzeResult: + def _proto_schema_to_pyspark_schema(self, schema: pb2.DataType) -> DataType: + if schema.HasField("struct"): + structFields = [] + for proto_field in schema.struct.fields: + structFields.append( + StructField( + proto_field.name, + self._proto_schema_to_pyspark_schema(proto_field.type), + proto_field.nullable, + ) + ) + return StructType(structFields) + elif schema.HasField("i64"): Review Comment: I think the returned schema should always be a StructType? -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org