def test_construct_from_invalid_sources_raise(multisourcefs): child1 = ds.FileSystemDatasetFactory( multisourcefs, fs.FileSelector('/plain'), format=ds.ParquetFileFormat() ) child2 = ds.FileSystemDatasetFactory( multisourcefs, fs.FileSelector('/schema'), format=ds.ParquetFileFormat() ) with pytest.raises(TypeError, match='Expected.*FileSystemDatasetFactory'): ds.dataset([child1, child2]) expected = ( "Expected a list of path-like or dataset objects. The given list " "contains the following types: int" ) with pytest.raises(TypeError, match=expected): ds.dataset([1, 2, 3]) expected = ( "Expected a path-like, list of path-likes or a list of Datasets " "instead of the given type: NoneType" ) with pytest.raises(TypeError, match=expected): ds.dataset(None)
def test_open_dataset_from_source_additional_kwargs(multisourcefs): child = ds.FileSystemDatasetFactory( multisourcefs, fs.FileSelector('/plain'), format=ds.ParquetFileFormat() ) with pytest.raises(ValueError, match="cannot pass any additional"): ds.dataset(child, format="parquet")
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_dataset_union(multisourcefs): child = ds.FileSystemDatasetFactory( multisourcefs, fs.FileSelector('/plain'), format=ds.ParquetFileFormat() ) factory = ds.UnionDatasetFactory([child]) # TODO(bkietz) reintroduce factory.children property assert len(factory.inspect_schemas()) == 1 assert all(isinstance(s, pa.Schema) for s in factory.inspect_schemas()) assert factory.inspect_schemas()[0].equals(child.inspect()) assert factory.inspect().equals(child.inspect()) assert isinstance(factory.finish(), ds.Dataset)