o
    pi0                     @  s   d dl mZ d dlmZ d dlZd dlmZ d dlmZ d dlm	Z	 d dl
mZ d dlmZ er<d d	lmZ d d
lmZ g Z			ddddZ			ddddZdS )    )annotations)TYPE_CHECKINGN)_C_ops)check_variable_and_dtype)Variable)LayerHelper)in_dynamic_or_pir_mode)Sequence)Tensorxr
   	neighborscountvalue_bufferTensor | Noneindex_buffername
str | Nonereturntuple[Tensor, Tensor, Tensor]c                 C  s  |dur
|dur
dnd}t  r t| ||||\}}}	|||	fS t| ddd t|ddd t|dd	d |rEt|d
d	d t|dd	d tdi t }
|
j| jd}|
j| jd}|
j| jd}	|
jd| |||rl|nd|rq|ndd|||	dd |||	fS )a  

    Reindex Graph API.

    This API is mainly used in Graph Learning domain, which should be used
    in conjunction with `paddle.geometric.sample_neighbors` API. And the main purpose
    is to reindex the ids information of the input nodes, and return the
    corresponding graph edges after reindex.

    Take input nodes x = [0, 1, 2] as an example. If we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2],
    then we know that the neighbors of 0 is [8, 9], the neighbors of 1 is [0, 4, 7], and the neighbors of 2 is [6, 7].
    Then after graph_reindex, we will have 3 different outputs: reindex_src: [3, 4, 0, 5, 6, 7, 6], reindex_dst: [0, 0, 1, 1, 1, 2, 2]
    and out_nodes: [0, 1, 2, 8, 9, 4, 7, 6]. We can see that the numbers in `reindex_src` and `reindex_dst` is the corresponding index
    of nodes in `out_nodes`.

    Note:
        The number in x should be unique, otherwise it would cause potential errors. We will reindex all the nodes from 0.

    Args:
        x (Tensor): The input nodes which we sample neighbors for. The available
                    data type is int32, int64.
        neighbors (Tensor): The neighbors of the input nodes `x`. The data type
                            should be the same with `x`.
        count (Tensor): The neighbor count of the input nodes `x`. And the
                        data type should be int32.
        value_buffer (Tensor, optional): Value buffer for hashtable. The data type should be int32,
                                    and should be filled with -1. Only useful for gpu version. Default is None.
        index_buffer (Tensor, optional): Index buffer for hashtable. The data type should be int32,
                                    and should be filled with -1. Only useful for gpu version.
                                    `value_buffer` and `index_buffer` should be both not None
                                    if you want to speed up by using hashtable buffer. Default is None.
        name (str, optional): Name for the operation (optional, default is None).
                              For more information, please refer to :ref:`api_guide_Name`.

    Returns:
        - reindex_src (Tensor), the source node index of graph edges after reindex.

        - reindex_dst (Tensor), the destination node index of graph edges after reindex.

        - out_nodes (Tensor), the index of unique input nodes and neighbors before reindex, where we put the input nodes `x` in the front, and put neighbor nodes in the back.

    Examples:
        .. code-block:: python

            >>> import paddle

            >>> x = [0, 1, 2]
            >>> neighbors = [8, 9, 0, 4, 7, 6, 7]
            >>> count = [2, 3, 2]
            >>> x = paddle.to_tensor(x, dtype="int64")
            >>> neighbors = paddle.to_tensor(neighbors, dtype="int64")
            >>> count = paddle.to_tensor(count, dtype="int32")
            >>> reindex_src, reindex_dst, out_nodes = paddle.geometric.reindex_graph(x, neighbors, count)
            >>> print(reindex_src.numpy())
            [3 4 0 5 6 7 6]
            >>> print(reindex_dst.numpy())
            [0 0 1 1 1 2 2]
            >>> print(out_nodes.numpy())
            [0 1 2 8 9 4 7 6]

    NTFXint32Zint64graph_reindex	NeighborsCountr   HashTable_ValueHashTable_Indexreindex_graphdtyper   r   r   r   r   ZReindex_SrcZReindex_DstZ	Out_NodestypeZinputsZoutputs)r   )	r   r   r   r   r   locals"create_variable_for_type_inferencer   	append_opr   r   r   r   r   r   Zuse_buffer_hashtableZreindex_srcZreindex_dstZ	out_nodeshelper r)   _/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/paddle/geometric/reindex.pyr   "   sR   F




r   Sequence[Tensor]c                 C  sv  |dur
|dur
dnd}t  r.tj|dd}tj|dd}t| ||||\}}}	|||	fS t|tr6|g}t|tr>|g}tj|dd}tj|dd}t| ddd t|d	dd
 t|ddd
 |rqt|ddd
 t|ddd
 tdi t	 }
|
j
| jd}|
j
| jd}|
j
| jd}	tj|dd}tj|dd}|
jd
| |||r|nd|r|ndd|||	dd |||	fS )a5  

    Reindex HeterGraph API.

    This API is mainly used in Graph Learning domain, which should be used
    in conjunction with `paddle.geometric.sample_neighbors` API. And the main purpose
    is to reindex the ids information of the input nodes, and return the
    corresponding graph edges after reindex.

    Take input nodes x = [0, 1, 2] as an example. For graph A, suppose we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2],
    then we know that the neighbors of 0 is [8, 9], the neighbors of 1 is [0, 4, 7], and the neighbors of 2 is [6, 7]. For graph B,
    suppose we have neighbors = [0, 2, 3, 5, 1], and count = [1, 3, 1], then we know that the neighbors of 0 is [0], the neighbors of 1 is [2, 3, 5],
    and the neighbors of 3 is [1]. We will get following outputs: reindex_src: [3, 4, 0, 5, 6, 7, 6, 0, 2, 8, 9, 1], reindex_dst: [0, 0, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2]
    and out_nodes: [0, 1, 2, 8, 9, 4, 7, 6, 3, 5].

    Note:
        The number in x should be unique, otherwise it would cause potential errors. We support multi-edge-types neighbors reindexing in reindex_heter_graph api. We will reindex all the nodes from 0.

    Args:
        x (Tensor): The input nodes which we sample neighbors for. The available
                    data type is int32, int64.
        neighbors (list|tuple): The neighbors of the input nodes `x` from different graphs.
                                The data type should be the same with `x`.
        count (list|tuple): The neighbor counts of the input nodes `x` from different graphs.
                            And the data type should be int32.
        value_buffer (Tensor, optional): Value buffer for hashtable. The data type should be int32,
                                    and should be filled with -1. Only useful for gpu version. Default is None.
        index_buffer (Tensor, optional): Index buffer for hashtable. The data type should be int32,
                                    and should be filled with -1. Only useful for gpu version.
                                    `value_buffer` and `index_buffer` should be both not None
                                    if you want to speed up by using hashtable buffer. Default is None.
        name (str, optional): Name for the operation (optional, default is None).
                              For more information, please refer to :ref:`api_guide_Name`.

    Returns:
        - reindex_src (Tensor), the source node index of graph edges after reindex.

        - reindex_dst (Tensor), the destination node index of graph edges after reindex.

        - out_nodes (Tensor), the index of unique input nodes and neighbors before reindex,
                              where we put the input nodes `x` in the front, and put neighbor
                              nodes in the back.

    Examples:
        .. code-block:: python

            >>> import paddle

            >>> x = [0, 1, 2]
            >>> neighbors_a = [8, 9, 0, 4, 7, 6, 7]
            >>> count_a = [2, 3, 2]
            >>> x = paddle.to_tensor(x, dtype="int64")
            >>> neighbors_a = paddle.to_tensor(neighbors_a, dtype="int64")
            >>> count_a = paddle.to_tensor(count_a, dtype="int32")
            >>> neighbors_b = [0, 2, 3, 5, 1]
            >>> count_b = [1, 3, 1]
            >>> neighbors_b = paddle.to_tensor(neighbors_b, dtype="int64")
            >>> count_b = paddle.to_tensor(count_b, dtype="int32")
            >>> neighbors = [neighbors_a, neighbors_b]
            >>> count = [count_a, count_b]
            >>> reindex_src, reindex_dst, out_nodes = paddle.geometric.reindex_heter_graph(x, neighbors, count)
            >>> print(reindex_src.numpy())
            [3 4 0 5 6 7 6 0 2 8 9 1]
            >>> print(reindex_dst.numpy())
            [0 0 1 1 1 2 2 0 1 1 1 2]
            >>> print(out_nodes.numpy())
            [0 1 2 8 9 4 7 6 3 5]

    NTFr   )Zaxisr   r   Zheter_graph_reindexr   r   r   r   r   r   reindex_heter_graphr   r    r!   r"   )r,   )r   paddleconcatr   r   
isinstancer   r   r   r$   r%   r   r&   r'   r)   r)   r*   r,      sf   N






r,   )NNN)r   r
   r   r
   r   r
   r   r   r   r   r   r   r   r   )r   r
   r   r+   r   r+   r   r   r   r   r   r   r   r   )
__future__r   typingr   r-   r   Zpaddle.base.data_feederr   Zpaddle.base.frameworkr   Zpaddle.base.layer_helperr   Zpaddle.frameworkr   collections.abcr	   r
   __all__r   r,   r)   r)   r)   r*   <module>   s(   {