Method _get_data_buffer

pandas/core/interchange/column.py:309–382

Return the buffer containing the data and the buffer's associated dtype.

(
        self,
    )

        return buffers

    def _get_data_buffer(
        self,
    ) -> tuple[Buffer, tuple[DtypeKind, int, str, str]]:
        """
        Return the buffer containing the data and the buffer's associated dtype.
        """
        buffer: Buffer
        if self.dtype[0] == DtypeKind.DATETIME:
            # self.dtype[2] is an ArrowCTypes.TIMESTAMP where the tz will make
            # it longer than 4 characters
            if len(self.dtype[2]) > 4:
                np_arr = self._col.dt.tz_convert(None).to_numpy()
            else:
                np_arr = self._col.to_numpy()
            buffer = PandasBuffer(np_arr, allow_copy=self._allow_copy)
            dtype = (
                DtypeKind.INT,
                64,
                ArrowCTypes.INT64,
                Endianness.NATIVE,
            )
        elif self.dtype[0] in (
            DtypeKind.INT,
            DtypeKind.UINT,
            DtypeKind.FLOAT,
            DtypeKind.BOOL,
        ):
            dtype = self.dtype
            arr = self._col.array
            if isinstance(self._col.dtype, ArrowDtype):
                # We already rechunk (if necessary / allowed) upon initialization, so
                # this is already single-chunk by the time we get here.
                arr = arr._pa_array.chunks[0]  # type: ignore[attr-defined]
                buffer = PandasBufferPyarrow(
                    arr.buffers()[1],
                    length=len(arr),
                )
                return buffer, dtype
            if isinstance(self._col.dtype, BaseMaskedDtype):
                np_arr = arr._data  # type: ignore[attr-defined]
            else:
                np_arr = arr._ndarray  # type: ignore[attr-defined]
            buffer = PandasBuffer(np_arr, allow_copy=self._allow_copy)
        elif self.dtype[0] == DtypeKind.CATEGORICAL:
            codes = self._col.values._codes
            buffer = PandasBuffer(codes, allow_copy=self._allow_copy)
            dtype = self._dtype_from_pandasdtype(codes.dtype)
        elif self.dtype[0] == DtypeKind.STRING:
            # Marshal the strings from a NumPy object array into a byte array
            buf = self._col.to_numpy()
            b = bytearray()

            # TODO: this for-loop is slow; can be implemented in Cython/C/C++ later
            for obj in buf:
                if isinstance(obj, str):
                    b.extend(obj.encode(encoding="utf-8"))

            # Convert the byte array to a Pandas "buffer" using