GH-51043: [Python] Reject null required Arrow objects

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()))

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`.

python/pyarrow/array.pxi

@@ -4293,8 +4293,9 @@ 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.
 

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),

python/pyarrow/tests/test_array.py

@@ -928,6 +928,13 @@ 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():

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,