pitrou commented on code in PR #14293:
URL: https://github.com/apache/arrow/pull/14293#discussion_r1053562365
##########
python/pyarrow/tests/parquet/test_basic.py:
##########
@@ -390,13 +390,17 @@ def test_byte_stream_split(use_legacy_dataset):
def test_column_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'])
+ arr_bin = pa.array(list(map(
+ lambda x: bytes(str(x).zfill(8), "utf-8"), range(100))), pa.binary())
+ mixed_table = pa.Table.from_arrays([arr_float, arr_int, arr_bin],
+ names=['a', 'b', 'c'])
# Check "BYTE_STREAM_SPLIT" for column 'a' and "PLAIN" column_encoding for
- # column 'b'.
+ # column 'b' and 'c'.
_check_roundtrip(mixed_table, expected=mixed_table, use_dictionary=False,
- column_encoding={'a': "BYTE_STREAM_SPLIT", 'b': "PLAIN"},
+ column_encoding={'a': "BYTE_STREAM_SPLIT",
Review Comment:
(to expand a bit on the previous reply, the "shortcuts" may take place where
zero-copy reads are possible, which is only the case for trivial encodings such
as PLAIN)
--
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]
