def test_filesystem_factory(mockfs, paths_or_selector):
format = ds.ParquetFileFormat(read_options=ds.ParquetReadOptions(
dictionary_columns={"str"}))
options = ds.FileSystemFactoryOptions('subdir')
options.partitioning = ds.DirectoryPartitioning(
pa.schema(
[pa.field('group', pa.int32()),
pa.field('key', pa.string())]))
assert options.partition_base_dir == 'subdir'
assert options.ignore_prefixes == ['.', '_']
assert options.exclude_invalid_files is False
factory = ds.FileSystemDatasetFactory(mockfs, paths_or_selector, format,
options)
inspected_schema = factory.inspect()
assert factory.inspect().equals(pa.schema([
pa.field('i64', pa.int64()),
pa.field('f64', pa.float64()),
pa.field('str', pa.dictionary(pa.int32(), pa.string())),
pa.field('const', pa.int64()),
pa.field('group', pa.int32()),
pa.field('key', pa.string()),
]),
check_metadata=False)
assert isinstance(factory.inspect_schemas(), list)
assert isinstance(factory.finish(inspected_schema), ds.FileSystemDataset)
assert factory.root_partition.equals(ds.ScalarExpression(True))
dataset = factory.finish()
assert isinstance(dataset, ds.FileSystemDataset)
assert len(list(dataset.scan())) == 2
scanner = ds.Scanner(dataset)
expected_i64 = pa.array([0, 1, 2, 3, 4], type=pa.int64())
expected_f64 = pa.array([0, 1, 2, 3, 4], type=pa.float64())
expected_str = pa.DictionaryArray.from_arrays(
pa.array([0, 1, 2, 3, 4], type=pa.int32()),
pa.array("0 1 2 3 4".split(), type=pa.string()))
for task, group, key in zip(scanner.scan(), [1, 2], ['xxx', 'yyy']):
expected_group = pa.array([group] * 5, type=pa.int32())
expected_key = pa.array([key] * 5, type=pa.string())
expected_const = pa.array([group - 1] * 5, type=pa.int64())
for batch in task.execute():
assert batch.num_columns == 6
assert batch[0].equals(expected_i64)
assert batch[1].equals(expected_f64)
assert batch[2].equals(expected_str)
assert batch[3].equals(expected_const)
assert batch[4].equals(expected_group)
assert batch[5].equals(expected_key)
table = dataset.to_table()
assert isinstance(table, pa.Table)
assert len(table) == 10
assert table.num_columns == 6
def test_file_format_pickling():
formats = [
ds.IpcFileFormat(),
ds.ParquetFileFormat(),
ds.ParquetFileFormat(read_options=ds.ParquetReadOptions(
use_buffered_stream=True)),
ds.ParquetFileFormat(read_options={
'use_buffered_stream': True,
'buffer_size': 4096,
})
]
for file_format in formats:
assert pickle.loads(pickle.dumps(file_format)) == file_format
def test_parquet_read_options():
opts1 = ds.ParquetReadOptions()
opts2 = ds.ParquetReadOptions(buffer_size=4096,
dictionary_columns=['a', 'b'])
opts3 = ds.ParquetReadOptions(buffer_size=2**13, use_buffered_stream=True,
dictionary_columns={'a', 'b'})
assert opts1.use_buffered_stream is False
assert opts1.buffer_size == 2**13
assert opts1.dictionary_columns == set()
assert opts2.use_buffered_stream is False
assert opts2.buffer_size == 2**12
assert opts2.dictionary_columns == {'a', 'b'}
assert opts3.use_buffered_stream is True
assert opts3.buffer_size == 2**13
assert opts3.dictionary_columns == {'a', 'b'}
assert opts1 == opts1
assert opts1 != opts2
assert opts2 != opts3
def test_file_format_pickling():
formats = [
ds.IpcFileFormat(),
ds.CsvFileFormat(),
ds.CsvFileFormat(pa.csv.ParseOptions(delimiter='\t',
ignore_empty_lines=True)),
ds.ParquetFileFormat(),
ds.ParquetFileFormat(
read_options=ds.ParquetReadOptions(use_buffered_stream=True)
),
ds.ParquetFileFormat(
read_options={
'use_buffered_stream': True,
'buffer_size': 4096,
}
)
]
for file_format in formats:
assert pickle.loads(pickle.dumps(file_format)) == file_format