
    j
i                    X    d Z ddlmZ ddlZddlZddlmZ ddlmZ  G d d          Z	dS )zJSON text splitter.    )annotationsN)Any)Documentc                       e Zd ZU dZdZded<   	 dZded<   	 	 d)d* fdZed+d            Z	ed,d            Z
d-dZ	 	 d.d/dZ	 d0d1d Z	 	 d2d3d#Z	 	 	 d4d5d(Z xZS )6RecursiveJsonSplittera  Splits JSON data into smaller, structured chunks while preserving hierarchy.

    This class provides methods to split JSON data into smaller dictionaries or
    JSON-formatted strings based on configurable maximum and minimum chunk sizes.
    It supports nested JSON structures, optionally converts lists into dictionaries
    for better chunking, and allows the creation of document objects for further use.
      intmax_chunk_sizei  min_chunk_sizeN
int | NonereturnNonec                    t                                                       || _        ||nt          |dz
  d          | _        dS )a  Initialize the chunk size configuration for text processing.

        This constructor sets up the maximum and minimum chunk sizes, ensuring that
        the `min_chunk_size` defaults to a value slightly smaller than the
        `max_chunk_size` if not explicitly provided.

        Args:
            max_chunk_size: The maximum size for a chunk.
            min_chunk_size: The minimum size for a chunk.

                If `None`, defaults to the maximum chunk size minus 200, with a lower
                bound of 50.
        N   2   )super__init__r
   maxr   )selfr
   r   	__class__s      C:\Users\Dell Inspiron 16\Desktop\tws\AgrotaPowerBi\back-agrota-powerbi\mcp-client-agrota\venv\Lib\site-packages\langchain_text_splitters/json.pyr   zRecursiveJsonSplitter.__init__   sR      	, ) N^c)2.. 	    datadict[str, Any]c                D    t          t          j        |                     S )z1Calculate the size of the serialized JSON object.)lenjsondumps)r   s    r   
_json_sizez RecursiveJsonSplitter._json_size5   s     4:d##$$$r   dpath	list[str]valuer   c                b    |dd         D ]}|                      |i           } || |d         <   dS )z;Set a value in a nested dictionary based on the given path.N)
setdefault)r    r!   r#   keys       r   _set_nested_dictz&RecursiveJsonSplitter._set_nested_dict:   sA     9 	& 	&CS"%%AA$r(r   c                     t          |t                    r  fd|                                D             S t          |t                    r fdt	          |          D             S |S )Nc                B    i | ]\  }}|                     |          S  )_list_to_dict_preprocessing).0kvr   s      r   
<dictcomp>zERecursiveJsonSplitter._list_to_dict_preprocessing.<locals>.<dictcomp>K   s-    TTTtq!At77::TTTr   c                \    i | ](\  }}t          |                              |          )S r+   )strr,   )r-   iitemr   s      r   r0   zERecursiveJsonSplitter._list_to_dict_preprocessing.<locals>.<dictcomp>N   sC       At A88>>  r   )
isinstancedictitemslist	enumerate)r   r   s   ` r   r,   z1RecursiveJsonSplitter._list_to_dict_preprocessingE   s     dD!! 	UTTTTtzz||TTTTdD!! 	   (   
 r   current_pathlist[str] | Nonechunkslist[dict[str, Any]] | Nonelist[dict[str, Any]]c                   |pg }||ni g}t          |t                    r|                                D ]\  }}g ||}|                     |d                   }|                     ||i          }| j        |z
  }	||	k     r|                     |d         ||           k|| j        k    r|                    i            |                     |||           n|                     |d         ||           |S )zESplit json into maximum size dictionaries while preserving structure.Nr%   )	r5   r6   r7   r   r
   r(   r   append_json_split)
r   r   r:   r<   r'   r#   new_path
chunk_sizesize	remainings
             r   rA   z!RecursiveJsonSplitter._json_splitU   s!    $)r!-B4dD!! 	B"jjll > >
U/\/3/!__VBZ88
U|44 /*<	)##))&*hFFFF!T%888b))) $$UHf====>$ !!&*lDAAAr   F	json_dataconvert_listsboolc                    |r)|                      |                     |                    }n|                      |          }|d         s|                                 |S )a  Splits JSON into a list of JSON chunks.

        Args:
            json_data: The JSON data to be split.
            convert_lists: Whether to convert lists in the JSON to dictionaries
                before splitting.

        Returns:
            A list of JSON chunks.
        r%   )rA   r,   pop)r   rF   rG   r<   s       r   
split_jsonz RecursiveJsonSplitter.split_jsont   sb      	1%%d&F&Fy&Q&QRRFF%%i00F bz 	JJLLLr   Tensure_asciic                N    |                      ||          }fd|D             S )a~  Splits JSON into a list of JSON formatted strings.

        Args:
            json_data: The JSON data to be split.
            convert_lists: Whether to convert lists in the JSON to dictionaries
                before splitting.
            ensure_ascii: Whether to ensure ASCII encoding in the JSON strings.

        Returns:
            A list of JSON formatted strings.
        )rF   rG   c                <    g | ]}t          j        |           S ))rL   )r   r   )r-   chunkrL   s     r   
<listcomp>z4RecursiveJsonSplitter.split_text.<locals>.<listcomp>   s(    QQQ
5|<<<QQQr   )rK   )r   rF   rG   rL   r<   s      ` r   
split_textz RecursiveJsonSplitter.split_text   s7    " 9MRR RQQQ&QQQQr   texts	metadataslist[dict[Any, Any]] | Nonelist[Document]c                   |pi gt          |          z  }g }t          |          D ]`\  }}|                     |||          D ]B}	t          j        ||                   }
t          |	|
          }|                    |           Ca|S )a  Create a list of `Document` objects from a list of json objects (`dict`).

        Args:
            texts: A list of JSON data to be split and converted into documents.
            convert_lists: Whether to convert lists to dictionaries before splitting.
            ensure_ascii: Whether to ensure ASCII encoding in the JSON strings.
            metadatas: Optional list of metadata to associate with each document.

        Returns:
            A list of `Document` objects.
        )rF   rG   rL   )page_contentmetadata)r   r9   rQ   copydeepcopyr   r@   )r   rR   rG   rL   rS   
metadatas_	documentsr3   textrO   rX   new_docs               r   create_documentsz&RecursiveJsonSplitter.create_documents   s    $ 32$U"3
	 '' 	* 	*GAtm, )   * *  =A77"III  ))))* r   )r   N)r
   r	   r   r   r   r   )r   r   r   r	   )r    r   r!   r"   r#   r   r   r   )r   r   r   r   )NN)r   r   r:   r;   r<   r=   r   r>   )F)rF   r   rG   rH   r   r>   )FT)rF   r   rG   rH   rL   rH   r   r"   )FTN)
rR   r>   rG   rH   rL   rH   rS   rT   r   rU   )__name__
__module____qualname____doc__r
   __annotations__r   r   staticmethodr   r(   r,   rA   rK   rQ   r_   __classcell__)r   s   @r   r   r      s_          N*N
 HL
 
 
 
 
 
 
0 % % % \%    \   & *..2	    D $    8 $!	R R R R R2 $!15        r   r   )
rc   
__future__r   rY   r   typingr   langchain_core.documentsr   r   r+   r   r   <module>rj      s      " " " " " "         - - - - - -r r r r r r r r r rr   