You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by "dtenedor (via GitHub)" <gi...@apache.org> on 2023/09/28 00:04:45 UTC
[GitHub] [spark] dtenedor commented on a diff in pull request #43156: [SPARK-45362][PYTHON] Project out PARTITION BY expressions before Python UDTF 'eval' method consumes them
dtenedor commented on code in PR #43156:
URL: https://github.com/apache/spark/pull/43156#discussion_r1339357062
##########
python/pyspark/worker.py:
##########
@@ -752,17 +757,28 @@ def _check_partition_boundaries(self, arguments: list) -> bool:
prev_table_arg = self._get_table_arg(self._prev_arguments)
cur_partitions_args = []
prev_partitions_args = []
- for i in partition_child_indexes:
+ for i in self._partition_child_indexes:
cur_partitions_args.append(cur_table_arg[i])
prev_partitions_args.append(prev_table_arg[i])
- self._prev_arguments = arguments
result = any(k != v for k, v in zip(cur_partitions_args, prev_partitions_args))
self._prev_arguments = arguments
return result
def _get_table_arg(self, inputs: list) -> Row:
return [x for x in inputs if type(x) is Row][0]
+ def _remove_partition_by_exprs(self, arg: Any) -> Any:
+ if type(arg) is Row:
Review Comment:
Done!
--
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-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org