# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Unility functions for Transformer."""
__all__ = ["pad_sequence"]


def pad_sequence(sequences,
                 batch_first: bool = False,
                 padding_value: float = 0.0):
    r"""Pad a list of variable length Tensors with ``padding_value``

    ``pad_sequence`` stacks a list of Tensors along a new dimension,
    and pads them to equal length. For example, if the input is list of
    sequences with size ``L x *`` and if batch_first is False, and ``T x B x *``
    otherwise.

    `B` is batch size. It is equal to the number of elements in ``sequences``.
    `T` is length of the longest sequence.
    `L` is length of the sequence.
    `*` is any number of trailing dimensions, including none.

    Example:
        >>> from paddle.nn.utils.rnn import pad_sequence
        >>> a = paddle.ones(25, 300)
        >>> b = paddle.ones(22, 300)
        >>> c = paddle.ones(15, 300)
        >>> pad_sequence([a, b, c]).size()
        paddle.Tensor([25, 3, 300])

    Note:
        This function returns a Tensor of size ``T x B x *`` or ``B x T x *``
        where `T` is the length of the longest sequence. This function assumes
        trailing dimensions and type of all the Tensors in sequences are same.

    Args:
        sequences (list[Tensor]): list of variable length sequences.
        batch_first (bool, optional): output will be in ``B x T x *`` if True, or in
            ``T x B x *`` otherwise
        padding_value (float, optional): value for padded elements. Default: 0.

    Returns:
        Tensor of size ``T x B x *`` if :attr:`batch_first` is ``False``.
        Tensor of size ``B x T x *`` otherwise
    """

    # assuming trailing dimensions and type of all the Tensors
    # in sequences are same and fetching those from sequences[0]
    max_size = sequences[0].size()
    # (TODO Hui Zhang): slice not supprot `end==start`
    # trailing_dims = max_size[1:]
    trailing_dims = max_size[1:] if max_size.ndim >= 2 else ()
    max_len = max([s.shape[0] for s in sequences])
    if batch_first:
        out_dims = (len(sequences), max_len) + trailing_dims
    else:
        out_dims = (max_len, len(sequences)) + trailing_dims

    out_tensor = sequences[0].new_full(out_dims, padding_value)
    for i, tensor in enumerate(sequences):
        length = tensor.shape[0]
        # use index notation to prevent duplicate references to the tensor
        print(
            f"length {length}, out_tensor {out_tensor.shape}, tensor {tensor.shape}"
        )
        if batch_first:
            # TODO (Hui Zhang): set_value op not supprot `end==start`
            # TODO (Hui Zhang): set_value op not support int16
            # TODO (Hui Zhang): set_varbase 2 rank not support [0,0,...]
            # out_tensor[i, :length, ...] = tensor
            if length != 0:
                out_tensor[i, :length] = tensor
            else:
                out_tensor[i, length] = tensor
        else:
            # TODO (Hui Zhang): set_value op not supprot `end==start`
            # out_tensor[:length, i, ...] = tensor
            if length != 0:
                out_tensor[:length, i] = tensor
            else:
                out_tensor[length, i] = tensor

    return out_tensor