jorisvandenbossche commented on a change in pull request #11724:
URL: https://github.com/apache/arrow/pull/11724#discussion_r759143705
##########
File path: python/pyarrow/tests/parquet/test_basic.py
##########
@@ -352,6 +352,101 @@ def test_byte_stream_split(use_legacy_dataset):
use_legacy_dataset=use_legacy_dataset)
+@parametrize_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'])
+
+ # Check "BYTE_STREAM_SPLIT" for column 'a' and "PLAIN" column_encoding for
+ # column 'b'.
+ _check_roundtrip(mixed_table, expected=mixed_table, use_dictionary=False,
+ column_encoding={'a': "BYTE_STREAM_SPLIT", 'b': "PLAIN"},
+ use_legacy_dataset=use_legacy_dataset)
+
+ # Check "PLAIN" for all columns.
+ _check_roundtrip(mixed_table, expected=mixed_table,
+ use_dictionary=False,
+ column_encoding="PLAIN",
+ use_legacy_dataset=use_legacy_dataset)
+
+ # Try to pass "BYTE_STREAM_SPLIT" column encoding for integer column 'b'.
+ # This should throw an error as it is only supports FLOAT and DOUBLE.
+ with pytest.raises(IOError,
+ match="BYTE_STREAM_SPLIT only supports FLOAT and
DOUBLE"):
+ _check_roundtrip(mixed_table, expected=mixed_table,
+ use_dictionary=False,
+ column_encoding={'b': "BYTE_STREAM_SPLIT"},
+ use_legacy_dataset=use_legacy_dataset)
+
+ # Try to pass "DELTA_BINARY_PACKED".
+ # This should throw an error as it is only supported for reading.
+ with pytest.raises(IOError,
+ match="Not yet implemented: Selected encoding is not
supported."):
+ _check_roundtrip(mixed_table, expected=mixed_table,
+ use_dictionary=False,
+ column_encoding={'b': "DELTA_BINARY_PACKED"},
+ use_legacy_dataset=use_legacy_dataset)
+
+ # Try to pass "RLE_DICTIONARY".
Review comment:
```suggestion
# Try to pass "RLE_DICTIONARY".
# This should throw an error as dictionary encoding is already used by
default
# and not supported to be specified as "fallback" 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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
