ConeyLiu commented on code in PR #1427:
URL: https://github.com/apache/iceberg-python/pull/1427#discussion_r1887950445
##########
pyiceberg/table/__init__.py:
##########
@@ -1423,6 +1451,66 @@ def plan_files(self) -> Iterable[FileScanTask]:
for data_entry in data_entries
]
+ def _target_split_size(self) -> int:
+ table_value = property_as_int(
+ self.table_metadata.properties, TableProperties.READ_SPLIT_SIZE,
TableProperties.READ_SPLIT_SIZE_DEFAULT
+ )
+ return property_as_int(self.options, TableProperties.READ_SPLIT_SIZE,
table_value) # type: ignore
+
+ def _loop_back(self) -> int:
+ table_value = property_as_int(
+ self.table_metadata.properties,
TableProperties.READ_SPLIT_LOOKBACK, TableProperties.READ_SPLIT_LOOKBACK_DEFAULT
+ )
+ return property_as_int(self.options,
TableProperties.READ_SPLIT_LOOKBACK, table_value) # type: ignore
+
+ def _split_open_file_cost(self) -> int:
+ table_value = property_as_int(
+ self.table_metadata.properties,
+ TableProperties.READ_SPLIT_OPEN_FILE_COST,
+ TableProperties.READ_SPLIT_OPEN_FILE_COST_DEFAULT,
+ )
+ return property_as_int(self.options,
TableProperties.READ_SPLIT_OPEN_FILE_COST, table_value) # type: ignore
+
+ def plan_task(self) -> Iterable[CombinedFileScanTask]:
Review Comment:
Yes, both ray and daft are using plan_files. daft maybe done split by
itself, but ray it is not.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
