bkief commented on a change in pull request #11724:
URL: https://github.com/apache/arrow/pull/11724#discussion_r752172753
##########
File path: python/pyarrow/tests/parquet/test_basic.py
##########
@@ -352,6 +352,37 @@ def test_byte_stream_split(use_legacy_dataset):
use_legacy_dataset=use_legacy_dataset)
+@parametrize_legacy_dataset
+def test_col_encoding(use_legacy_dataset):
+ arr_float = pa.array(list(map(float, range(100))))
+ arr_int = pa.array(list(map(int, range(100))))
+ mixed_table = pa.Table.from_arrays([arr_float, arr_int],
+ names=['a', 'b'])
+
+ # Check NONE col_encoding.
+ _check_roundtrip(mixed_table, expected=mixed_table, use_dictionary=False,
+ col_encoding=None, use_legacy_dataset=use_legacy_dataset)
+
+ # Check "BYTE_STREAM_SPLIT" for column 'a' and "PLAIN" col_encoding for
+ # column 'b'.
+ _check_roundtrip(mixed_table, expected=mixed_table, use_dictionary=False,
+ col_encoding={'a': "BYTE_STREAM_SPLIT", 'b': "PLAIN"},
+ use_legacy_dataset=use_legacy_dataset)
+
+ # Check "RLE" for column 'a' and "BYTE_STREAM_SPLIT" col_encoding for
+ # column 'b'.
+ _check_roundtrip(mixed_table, expected=mixed_table,
+ use_byte_stream_split=['a'],
+ col_encoding={'a': "RLE", 'b': "BYTE_STREAM_SPLIT"},
+ use_legacy_dataset=use_legacy_dataset)
+
+ # Check "DELTA_BINARY_PACKED" col_encoding for column 'b'.
+ _check_roundtrip(mixed_table, expected=mixed_table,
+ use_dictionary=['b'],
+ col_encoding={'b': "DELTA_BINARY_PACKED"},
Review comment:
Long term, should `use_byte_stream_split` be deprecated (or at least put
on that path) and `use_dictionary` become a boolean just to set the default
encoding?
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
