diff --git a/python/pyarrow/_acero.pyx b/python/pyarrow/_acero.pyx index e27509469ef5..0a5285056931 100644 --- a/python/pyarrow/_acero.pyx +++ b/python/pyarrow/_acero.pyx @@ -141,6 +141,8 @@ cdef class _ProjectNodeOptions(ExecNodeOptions): vector[c_string] c_names for expr in expressions: + if expr is None: + raise TypeError("Expression must not be None") c_expressions.push_back(expr.unwrap()) if names is not None: diff --git a/python/pyarrow/_dataset.pyx b/python/pyarrow/_dataset.pyx index 8889090801c8..b2b400d9f3ba 100644 --- a/python/pyarrow/_dataset.pyx +++ b/python/pyarrow/_dataset.pyx @@ -1121,7 +1121,8 @@ cdef class FileSystemDataset(Dataset): cdef: CFileSystemDataset* filesystem_dataset - def __init__(self, fragments, Schema schema, FileFormat format, + def __init__(self, fragments, Schema schema not None, + FileFormat format not None, FileSystem filesystem=None, root_partition=None): cdef: FileFragment fragment=None @@ -1138,6 +1139,8 @@ cdef class FileSystemDataset(Dataset): ) for fragment in fragments: + if fragment is None: + raise TypeError("Fragment must not be None") c_fragments.push_back( static_pointer_cast[CFileFragment, CFragment]( fragment.unwrap())) @@ -4236,5 +4239,5 @@ class ScanNodeOptions(_ScanNodeOptions): Preserve implicit ordering of data. """ - def __init__(self, Dataset dataset, **kwargs): + def __init__(self, Dataset dataset not None, **kwargs): self._set_options(dataset, kwargs) diff --git a/python/pyarrow/_fs.pyx b/python/pyarrow/_fs.pyx index 0739b6acba32..10b6ac52dd55 100644 --- a/python/pyarrow/_fs.pyx +++ b/python/pyarrow/_fs.pyx @@ -1205,7 +1205,7 @@ cdef class SubTreeFileSystem(FileSystem): For usage of the methods see examples for :func:`~pyarrow.fs.LocalFileSystem`. """ - def __init__(self, base_path, FileSystem base_fs): + def __init__(self, base_path, FileSystem base_fs not None): cdef: c_string pathstr shared_ptr[CSubTreeFileSystem] wrapped diff --git a/python/pyarrow/_parquet.pyx b/python/pyarrow/_parquet.pyx index afe6ee994507..fb963f313684 100644 --- a/python/pyarrow/_parquet.pyx +++ b/python/pyarrow/_parquet.pyx @@ -755,7 +755,8 @@ cdef class SortingColumn: self.nulls_first = nulls_first @classmethod - def from_ordering(cls, Schema schema, sort_keys, null_placement='at_end'): + def from_ordering(cls, Schema schema not None, sort_keys, + null_placement='at_end'): """ Create a tuple of SortingColumn objects from the same arguments as :class:`pyarrow.compute.SortOptions`. @@ -816,7 +817,7 @@ cdef class SortingColumn: return tuple(sorting_columns) @staticmethod - def to_ordering(Schema schema, sorting_columns): + def to_ordering(Schema schema not None, sorting_columns): """ Convert a tuple of SortingColumn objects to the same format as :class:`pyarrow.compute.SortOptions`. @@ -1247,7 +1248,7 @@ cdef class FileMetaData(_Weakrefable): cdef class ParquetSchema(_Weakrefable): """A Parquet schema.""" - def __cinit__(self, FileMetaData container): + def __cinit__(self, FileMetaData container not None): self.parent = container self.schema = container._metadata.schema() @@ -1336,7 +1337,7 @@ cdef class ColumnSchema(_Weakrefable): ParquetSchema parent const ColumnDescriptor* descr - def __cinit__(self, ParquetSchema schema, int index): + def __cinit__(self, ParquetSchema schema not None, int index): self.parent = schema self.index = index # for pickling support self.descr = schema.schema.Column(index) diff --git a/python/pyarrow/array.pxi b/python/pyarrow/array.pxi index e090b1d0b3db..239d968f69ef 100644 --- a/python/pyarrow/array.pxi +++ b/python/pyarrow/array.pxi @@ -1329,8 +1329,8 @@ cdef class Array(_PandasConvertible): (_reduce_array_data(self.sp_array.get().data().get()),) @staticmethod - def from_buffers(DataType type, length, buffers, null_count=-1, offset=0, - children=None): + def from_buffers(DataType type not None, length, buffers, null_count=-1, + offset=0, children=None): """ Construct an Array from a sequence of buffers. @@ -1386,6 +1386,8 @@ cdef class Array(_PandasConvertible): c_buffers.push_back(pyarrow_unwrap_buffer(buf)) for child in children: + if child is None: + raise TypeError("Array child must not be None") c_child_data.push_back(child.ap.data()) array_data = CArrayData.MakeWithChildren(type.sp_type, length, @@ -4328,8 +4330,9 @@ cdef class DictionaryArray(Array): return self._indices @staticmethod - def from_buffers(DataType type, int64_t length, buffers, Array dictionary, - int64_t null_count=-1, int64_t offset=0): + def from_buffers(DataType type not None, int64_t length, buffers, + Array dictionary not None, int64_t null_count=-1, + int64_t offset=0): """ Construct a DictionaryArray from buffers. @@ -4745,8 +4748,8 @@ cdef class RunEndEncodedArray(Array): run_ends, values, 0) @staticmethod - def from_buffers(DataType type, length, buffers, null_count=-1, offset=0, - children=None): + def from_buffers(DataType type not None, length, buffers, null_count=-1, + offset=0, children=None): """ Construct a RunEndEncodedArray from all the parameters that make up an Array. diff --git a/python/pyarrow/tests/parquet/test_metadata.py b/python/pyarrow/tests/parquet/test_metadata.py index 817566125feb..8e9c6c403f17 100644 --- a/python/pyarrow/tests/parquet/test_metadata.py +++ b/python/pyarrow/tests/parquet/test_metadata.py @@ -351,6 +351,12 @@ def test_parquet_sorting_column(): with pytest.raises(ValueError): pq.SortingColumn.from_ordering(schema, (("a", "not a valid sort order"))) + with pytest.raises(TypeError, match="Argument 'schema' has incorrect type"): + pq.SortingColumn.from_ordering(None, ()) + + with pytest.raises(TypeError, match="Argument 'schema' has incorrect type"): + pq.SortingColumn.to_ordering(None, ()) + with pytest.raises(ValueError, match="inconsistent null placement"): sorting_cols = ( pq.SortingColumn(1, nulls_first=True), @@ -871,6 +877,12 @@ def msg(c): with pytest.raises(TypeError, match=msg("FileMetaData")): pq.FileMetaData() + with pytest.raises(TypeError, match="Argument 'container'"): + pq.ParquetSchema(None) + + with pytest.raises(TypeError, match="Argument 'schema'"): + pq.ColumnSchema(None, 0) + def test_read_schema_uuid_extension_type(tmp_path): # These are the raw 16-byte payloads for diff --git a/python/pyarrow/tests/test_acero.py b/python/pyarrow/tests/test_acero.py index 6e471d61199f..bbda3abee19c 100644 --- a/python/pyarrow/tests/test_acero.py +++ b/python/pyarrow/tests/test_acero.py @@ -247,6 +247,8 @@ def test_project(table_source): # input validation with pytest.raises(ValueError): ProjectNodeOptions([pc.multiply(field("a"), 2)], ["a2", "b2"]) + with pytest.raises(TypeError, match="Expression must not be None"): + ProjectNodeOptions([None]) # no scalar expression decl = Declaration.from_sequence([ @@ -597,3 +599,6 @@ def test_scan(tempdir): assert result["a"].to_pylist() == [1, 2, 3] # "b" is still included, but without data as it will be removed by the projection assert pc.all(result["b"].is_null()).as_py() + + with pytest.raises(TypeError, match="Argument 'dataset'"): + ScanNodeOptions(None) diff --git a/python/pyarrow/tests/test_array.py b/python/pyarrow/tests/test_array.py index 63c0eb0bea4e..6e19fbd95836 100644 --- a/python/pyarrow/tests/test_array.py +++ b/python/pyarrow/tests/test_array.py @@ -784,6 +784,9 @@ def test_array_from_buffers(): with pytest.raises(TypeError): pa.Array.from_buffers(pa.int16(), 3, ['', ''], offset=1) + with pytest.raises(TypeError, match="Argument 'type' has incorrect type"): + pa.Array.from_buffers(type=None, length=0, buffers=[]) + def test_string_binary_from_buffers(): array = pa.array(["a", None, "b", "c"]) @@ -868,6 +871,10 @@ def test_list_from_buffers(list_type_factory): pa.Array.from_buffers(ty, 4, buffers[:ty.num_buffers], children=[child, child]) + with pytest.raises(TypeError, match="Array child must not be None"): + pa.Array.from_buffers( + type=ty, length=4, buffers=buffers[:ty.num_buffers], children=[None]) + def test_struct_from_buffers(): ty = pa.struct([pa.field('a', pa.int16()), pa.field('b', pa.utf8())]) @@ -987,6 +994,13 @@ def test_dictionary_from_buffers(offset): offset=offset) assert a[offset:] == b + with pytest.raises(TypeError, match="Argument 'type' has incorrect type"): + pa.DictionaryArray.from_buffers( + None, len(a), a.indices.buffers(), a.dictionary) + with pytest.raises(TypeError, match="Argument 'dictionary' has incorrect type"): + pa.DictionaryArray.from_buffers( + a.type, len(a), a.indices.buffers(), None) + @pytest.mark.numpy def test_dictionary_from_numpy(): @@ -4275,6 +4289,9 @@ def test_run_end_encoded_from_buffers(): pa.RunEndEncodedArray.from_buffers(ree_type, length, buffers, 1, offset, children) + with pytest.raises(TypeError, match="Argument 'type' has incorrect type"): + pa.RunEndEncodedArray.from_buffers(type=None, length=0, buffers=[]) + @pytest.mark.numpy def test_run_end_encoded_from_array_with_type(): diff --git a/python/pyarrow/tests/test_dataset.py b/python/pyarrow/tests/test_dataset.py index 3b575e24d5e1..e80786cb94f0 100644 --- a/python/pyarrow/tests/test_dataset.py +++ b/python/pyarrow/tests/test_dataset.py @@ -396,6 +396,12 @@ def test_filesystem_dataset(mockfs): # validation of required arguments with pytest.raises(TypeError, match="incorrect type"): ds.FileSystemDataset(fragments, file_format, schema) + with pytest.raises(TypeError, match="Fragment must not be None"): + ds.FileSystemDataset([None], schema=schema, format=file_format) + with pytest.raises(TypeError, match="Argument 'schema' has incorrect type"): + ds.FileSystemDataset(fragments, schema=None, format=file_format) + with pytest.raises(TypeError, match="Argument 'format' has incorrect type"): + ds.FileSystemDataset(fragments, schema=schema, format=None) # validation of root_partition with pytest.raises(TypeError, match="incorrect type"): ds.FileSystemDataset(fragments, schema=schema, diff --git a/python/pyarrow/tests/test_fs.py b/python/pyarrow/tests/test_fs.py index 5bf1950c0654..416c75bccd2b 100644 --- a/python/pyarrow/tests/test_fs.py +++ b/python/pyarrow/tests/test_fs.py @@ -635,6 +635,9 @@ def test_subtree_filesystem(): assert repr(subfs).startswith('SubTreeFileSystem(base_path=/another/base/,' ' base_fs=