zhengruifeng commented on code in PR #52295:
URL: https://github.com/apache/spark/pull/52295#discussion_r2357868532
##########
python/pyspark/sql/connect/dataframe.py:
##########
@@ -443,6 +443,51 @@ def repartitionByRange( # type: ignore[misc]
res._cached_schema = self._cached_schema
return res
+ def repartitionById(
+ self, numPartitions: int, partitionIdCol: "ColumnOrName"
+ ) -> ParentDataFrame:
+ if not isinstance(numPartitions, int) or isinstance(numPartitions,
bool):
+ raise PySparkTypeError(
+ errorClass="NOT_INT",
+ messageParameters={
+ "arg_name": "numPartitions",
+ "arg_type": type(numPartitions).__name__,
+ },
+ )
+ if numPartitions <= 0:
+ raise PySparkValueError(
+ errorClass="VALUE_NOT_POSITIVE",
+ messageParameters={
+ "arg_name": "numPartitions",
+ "arg_value": str(numPartitions),
+ },
+ )
+
+ from pyspark.sql.connect.expressions import DirectShufflePartitionID,
Expression
Review Comment:
`DirectShufflePartitionID` should be imported at the top of this file
--
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
