Fokko commented on code in PR #3461:
URL: https://github.com/apache/iceberg-python/pull/3461#discussion_r3383052734
##########
pyiceberg/io/pyarrow.py:
##########
@@ -1756,6 +1764,7 @@ def __init__(
self._case_sensitive = case_sensitive
self._limit = limit
self._downcast_ns_timestamp_to_us =
Config().get_bool(DOWNCAST_NS_TIMESTAMP_TO_US_ON_WRITE)
+ self._dictionary_columns = frozenset(dictionary_columns)
Review Comment:
Why not keep it a tuple here?
##########
pyiceberg/io/pyarrow.py:
##########
@@ -1625,8 +1625,12 @@ def _task_to_record_batches(
partition_spec: PartitionSpec | None = None,
format_version: TableVersion = TableProperties.DEFAULT_FORMAT_VERSION,
downcast_ns_timestamp_to_us: bool | None = None,
+ dictionary_columns: frozenset[str] = frozenset(),
) -> Iterator[pa.RecordBatch]:
- arrow_format = _get_file_format(task.file.file_format, pre_buffer=True,
buffer_size=(ONE_MEGABYTE * 8))
+ format_kwargs: dict[str, Any] = {"pre_buffer": True, "buffer_size":
ONE_MEGABYTE * 8}
+ if dictionary_columns and task.file.file_format == FileFormat.PARQUET:
+ format_kwargs["dictionary_columns"] = tuple(dictionary_columns)
Review Comment:
Here we convert the frozenset back to a tuple
--
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]
