Function test_compression_level

python/pyarrow/tests/parquet/test_basic.py:588–630

()

def test_compression_level():
    arr = pa.array(list(map(int, range(1000))))
    data = [arr, arr]
    table = pa.Table.from_arrays(data, names=['a', 'b'])

    # Check one compression level.
    _check_roundtrip(table, expected=table, compression="gzip",
                     compression_level=1)

    # Check another one to make sure that compression_level=1 does not
    # coincide with the default one in Arrow.
    _check_roundtrip(table, expected=table, compression="gzip",
                     compression_level=5)

    # Check that the user can provide a compression per column
    _check_roundtrip(table, expected=table,
                     compression={'a': "gzip", 'b': "snappy"})

    # Check that the user can provide a compression level per column
    _check_roundtrip(table, expected=table, compression="gzip",
                     compression_level={'a': 2, 'b': 3})

    # Check if both LZ4 compressors are working
    # (level < 3 -> fast, level >= 3 -> HC)
    _check_roundtrip(table, expected=table, compression="lz4",
                     compression_level=1)

    _check_roundtrip(table, expected=table, compression="lz4",
                     compression_level=9)

    # Check that specifying a compression level for a codec which does allow
    # specifying one, results into an error.
    # Uncompressed, snappy and lzo do not support specifying a compression
    # level.
    # GZIP (zlib) allows for specifying a compression level but as of up
    # to version 1.2.11 the valid range is [-1, 9].
    invalid_combinations = [("snappy", 4), ("gzip", -1337),
                            ("None", 444), ("lzo", 14)]
    buf = io.BytesIO()
    for (codec, level) in invalid_combinations:
        with pytest.raises((ValueError, OSError)):
            _write_table(table, buf, compression=codec,
                         compression_level=level)


def test_lz4_raw_compression_alias():