Implement Buffer Protocol for PandasBuffer

pandas/_libs/buffer.pyx

@@ -0,0 +1,29 @@
+from cpython cimport Py_buffer
+from libc.stdint cimport (
+    uint8_t,
+    uintptr_t,
+)
+
+
+cdef class CBuffer:
+    def __getbuffer__(self, Py_buffer *buffer, int flags):
+        cdef Py_ssize_t itemsize = sizeof(uint8_t)
+        cdef uintptr_t ptr = self.ptr
+        cdef Py_ssize_t[1] shape = tuple((self.bufsize // itemsize,))
+        cdef Py_ssize_t[1] strides = tuple((itemsize,))
+
+        buffer.buf = <void*>ptr
+        # assumes sizeof(unsigned char) == sizeof(uint8_t)
+        # TODO: use C11 static_assert macro in Cython
+        buffer.format = "@B"
+        buffer.itemsize = itemsize
+        buffer.len = self.bufsize
+        buffer.ndim = 1
+        buffer.obj = self
+        buffer.readonly = 1
+        buffer.shape = shape
+        buffer.strides = strides
+        buffer.suboffsets = NULL
+
+    def __releasebuffer__(self, Py_buffer *buffer):
+        pass

pandas/_libs/meson.build

@@ -63,6 +63,7 @@ libs_sources = {
     # numpy include dir is implicitly included
     'algos': {'sources': ['algos.pyx', _algos_common_helper, _algos_take_helper, _khash_primitive_helper]},
     'arrays': {'sources': ['arrays.pyx']},
+    'buffer': {'sources': ['buffer.pyx']},
     'groupby': {'sources': ['groupby.pyx']},
     'hashing': {'sources': ['hashing.pyx']},
     'hashtable': {'sources': ['hashtable.pyx', _khash_primitive_helper, _hashtable_class_helper, _hashtable_func_helper]},

pandas/core/interchange/dataframe_protocol.py

@@ -21,6 +21,8 @@
         Sequence,
     )
 
+from pandas._libs.buffer import CBuffer
+
 
 class DlpackDeviceType(enum.IntEnum):
     """Integer enum for device type codes matching DLPack."""
@@ -118,7 +120,7 @@ class CategoricalDescription(TypedDict):
     categories: Column | None
 
 
-class Buffer(ABC):
+class Buffer(ABC, CBuffer):
     """
     Data in the buffer is guaranteed to be contiguous in memory.
 

pandas/tests/interchange/test_impl.py

@@ -1,4 +1,5 @@
 from datetime import datetime
+import sys
 
 import numpy as np
 import pytest
@@ -340,3 +341,30 @@ def test_interchange_from_non_pandas_tz_aware(request):
         dtype="datetime64[us, Asia/Kathmandu]",
     )
     tm.assert_frame_equal(expected, result)
+
+
+@pytest.mark.parametrize(
+    "data,dtype,expected",
+    [
+        ([True, False, True], np.bool_, bytearray(b"\x01\x00\x01")),
+        ([0, 1, 42], np.uint8, bytearray(b"\x00\x01\x2a")),
+        ([-42, 0, 42], np.int8, bytearray(b"\xd6\x00\x2a")),
+        (
+            [-42, 0, 42],
+            np.int32,
+            bytearray(b"\xd6\xff\xff\xff\x00\x00\x00\x00\x2a\x00\x00\x00")
+            if sys.byteorder == "little"
+            else bytearray(b"\xff\xff\xff\xd6\x00\x00\x00\x00\x00\x00\x00\x2a"),
+        ),
+        (
+            ["foo", "bar", "baz"],
+            "string",
+            bytearray(b"\x66\x6f\x6f\x62\x61\x72\x62\x61\x7a"),
+        ),
+    ],
+)
+def test_buffer_buffer_protocol(data, dtype, expected):
+    df = pd.DataFrame({"col": data}, dtype=dtype)
+    col = df.__dataframe__().get_column_by_name("col")
+    result = bytearray(memoryview(col.get_buffers()["data"][0]))
+    assert result == expected