def test_partitioning_factory(mockfs):
paths_or_selector = fs.FileSelector('subdir', recursive=True)
format = ds.ParquetFileFormat()
options = ds.FileSystemFactoryOptions('subdir')
partitioning_factory = ds.DirectoryPartitioning.discover(['group', 'key'])
assert isinstance(partitioning_factory, ds.PartitioningFactory)
options.partitioning_factory = partitioning_factory
factory = ds.FileSystemDatasetFactory(
mockfs, paths_or_selector, format, options
)
inspected_schema = factory.inspect()
# i64/f64 from data, group/key from "/1/xxx" and "/2/yyy" paths
expected_schema = pa.schema([
("i64", pa.int64()),
("f64", pa.float64()),
("str", pa.string()),
("group", pa.int32()),
("key", pa.string()),
])
assert inspected_schema.equals(expected_schema)
hive_partitioning_factory = ds.HivePartitioning.discover()
assert isinstance(hive_partitioning_factory, ds.PartitioningFactory)
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 dataset(mockfs):
format = ds.ParquetFileFormat()
selector = fs.FileSelector('subdir', recursive=True)
options = ds.FileSystemFactoryOptions('subdir')
options.partitioning = ds.DirectoryPartitioning(
pa.schema(
[pa.field('group', pa.int32()),
pa.field('key', pa.string())]))
factory = ds.FileSystemDatasetFactory(mockfs, selector, format, options)
return factory.finish()
def test_file_system_factory(mockfs, paths_or_selector):
format = ds.ParquetFileFormat()
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 True
factory = ds.FileSystemSourceFactory(
mockfs, paths_or_selector, format, options
)
inspected_schema = factory.inspect()
assert isinstance(factory.inspect(), pa.Schema)
assert isinstance(factory.inspect_schemas(), list)
assert isinstance(factory.finish(inspected_schema),
ds.FileSystemSource)
assert factory.root_partition.equals(ds.ScalarExpression(True))
source = factory.finish()
assert isinstance(source, ds.Source)
dataset = ds.Dataset([source], inspected_schema)
scanner = dataset.new_scan().finish()
assert len(list(scanner.scan())) == 2
expected_i64 = pa.array([0, 1, 2, 3, 4], type=pa.int64())
expected_f64 = pa.array([0, 1, 2, 3, 4], type=pa.float64())
for task, group, key in zip(scanner.scan(), [1, 2], ['xxx', 'yyy']):
expected_group_column = pa.array([group] * 5, type=pa.int32())
expected_key_column = pa.array([key] * 5, type=pa.string())
for batch in task.execute():
assert batch.num_columns == 4
assert batch[0].equals(expected_i64)
assert batch[1].equals(expected_f64)
assert batch[2].equals(expected_group_column)
assert batch[3].equals(expected_key_column)
table = scanner.to_table()
assert isinstance(table, pa.Table)
assert len(table) == 10
assert table.num_columns == 4
