Function test_csv_format_compressed

python/pyarrow/tests/test_dataset.py:3507–3524

(tempdir, compression, dataset_reader)

    "zstd",
])
def test_csv_format_compressed(tempdir, compression, dataset_reader):
    if not pyarrow.Codec.is_available(compression):
        pytest.skip(f"{compression} support is not built")
    table = pa.table({'a': pa.array([1, 2, 3], type="int64"),
                      'b': pa.array([.1, .2, .3], type="float64")})
    filesystem = fs.LocalFileSystem()
    suffix = compression if compression != 'gzip' else 'gz'
    path = str(tempdir / f'test.csv.{suffix}')
    with filesystem.open_output_stream(path, compression=compression) as sink:
        # https://github.com/pandas-dev/pandas/issues/23854
        # With CI version of Pandas (anything < 1.2), Pandas tries to write
        # str to the sink
        csv_str = table.to_pandas().to_csv(index=False)
        sink.write(csv_str.encode('utf-8'))

    dataset = ds.dataset(path, format=ds.CsvFileFormat())
    result = dataset_reader.to_table(dataset)
    assert result.equals(table)


def test_csv_format_options(tempdir, dataset_reader):