o
    mqi#                     @  s   d Z ddlmZ ddlmZmZ ddlZddlZddlZddl	Z	ddl
mZmZ ddlZddlZddlmZ ddlmZ ddlmZmZmZ ddlZdd	lmZmZ dd
lmZ erfddlm Z  ddl!m"Z" G dd deZ#G dd deZ$dd Z%dS )a  
Test extension array for storing nested data in a pandas container.

The JSONArray stores lists of dictionaries. The storage mechanism is a list,
not an ndarray.

Note
----
We currently store lists of UserDicts. Pandas has a few places
internally that specifically check for dicts, and does non-scalar things
in that case. We *want* the dictionaries to be treated as scalars, so we
hack around pandas by using UserDicts.
    )annotations)UserDictabcN)TYPE_CHECKINGAny)find_stack_level'construct_1d_object_array_from_listlike)is_bool_dtypeis_list_likepandas_dtype)ExtensionArrayExtensionDtype)unpack_tuple_and_ellipses)Mapping)type_tc                   @  s4   e Zd ZU ejZdZe Zde	d< e
d	ddZdS )
	JSONDtypejsonzMapping[str, Any]na_valuereturntype_t[JSONArray]c                 C     t S )zq
        Return the array type associated with this dtype.

        Returns
        -------
        type
        )	JSONArray)cls r   h/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/pandas/tests/extension/json/array.pyconstruct_array_type;   s   	zJSONDtype.construct_array_typeN)r   r   )__name__
__module____qualname__r   r   typenamer   r   __annotations__classmethodr   r   r   r   r   r   6   s   
 r   c                      s   e Zd Ze ZdZd0d1ddZedddd	d
Zedd Z	dd Z
d1ddZd2ddZdd Zdd Zd3ddZed2ddZdd Zd4ddZd d! Zd5d#d$Zd%d& Zed'd( Zd)d* Zd+d, Zdd"d- fd.d/
Z  ZS )6r   i  NFr   Nonec                 C  sD   |D ]}t || jjstdt| jj q|| _| j | _| _d S )NzAll values must be of type )
isinstancedtyper    	TypeErrorstrdataZ_items_data)selfvaluesr&   copyvalr   r   r   __init__K   s   zJSONArray.__init__r&   r-   c                C  s   | |S Nr   )r   Zscalarsr&   r-   r   r   r   _from_sequenceX   s   zJSONArray._from_sequencec                 C  s   | dd |D S )Nc                 S  s   g | ]
}|d krt |qS )r   )r   .0xr   r   r   
<listcomp>^   s    z.JSONArray._from_factorized.<locals>.<listcomp>r   )r   r,   originalr   r   r   _from_factorized\      zJSONArray._from_factorizedc                   s   t |tr	t|}t |tjr j| S t |tr&|td kr&t  jS t |tr4t  j| S t|s<t	dt
jj |}t|jr[t jdd t |D  jdS t  fdd|D S )Nzuonly integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indicesc                 S  s   g | ]\}}|r|qS r   r   )r4   r5   mr   r   r   r6   w       z)JSONArray.__getitem__.<locals>.<listcomp>r&   c                      g | ]} j | qS r   r)   )r4   ir+   r   r   r6   z       )r%   tupler   numbersIntegralr)   slicer    r   
IndexErrorpdapiZindexersZcheck_array_indexerr
   r&   r2   zip)r+   itemr   r@   r   __getitem__`   s$   



zJSONArray.__getitem__c                 C  s   t |tjr|| j|< d S t |t| tjfst|g}t |t	j
rH|jdkrHtt||D ]\}\}}|rEt || jjs@J || j|< q/d S t||D ]\}}t || jjsZJ || j|< qMd S )Nbool)r%   rC   rD   r)   r    r   Sequence	itertoolscyclenpZndarrayr&   	enumeraterI   )r+   keyvaluer?   kvr   r   r   __setitem__|   s   
zJSONArray.__setitem__intc                 C  s
   t | jS r1   )lenr)   r@   r   r   r   __len__   s   
zJSONArray.__len__c                 C  r   r1   NotImplementedr+   otherr   r   r   __eq__      zJSONArray.__eq__c                 C  r   r1   rZ   r\   r   r   r   __ne__   r_   zJSONArray.__ne__c                 C  sd   |du rt jdtt d |d u rt}|tkrtt| S |d u r)tj| j	|dS tj| j	||dS )NFaS  Starting with NumPy 2.0, the behavior of the 'copy' keyword has changed and passing 'copy=False' raises an error when returning a zero-copy NumPy array is not possible. pandas will follow this behavior starting with pandas 3.0.
This conversion to NumPy requires a copy, but 'copy=False' was passed. Consider using 'np.asarray(..)' instead.)
stacklevelr<   r0   )
warningswarnFutureWarningr   objectr	   listrP   asarrayr)   )r+   r&   r-   r   r   r   	__array__   s   zJSONArray.__array__c                 C  s   t | jS r1   )sys	getsizeofr)   r@   r   r   r   nbytes   s   zJSONArray.nbytesc                   s   t j fdd jD tdS )Nc                   s   g | ]}| j jkqS r   )r&   r   r3   r@   r   r   r6      r;   z"JSONArray.isna.<locals>.<listcomp>r<   )rP   arrayr)   rL   r@   r   r@   r   isna   s   zJSONArray.isnac              
     s   t |}d}|r7 d u rjj |dk  rtz fdd|D }W n. ty6 } zt||d }~ww zfdd|D }W n tyS } zt||d }~ww tj|jdS )NzIIndex is out of bounds or cannot do a non-empty take from an empty array.c                   s"   g | ]}|d krj | n qS )rn   r>   r4   loc
fill_valuer+   r   r   r6      s    z"JSONArray.take.<locals>.<listcomp>c                   r=   r   r>   ro   r@   r   r   r6      rA   r<   )	rP   rg   r&   r   any
ValueErrorrF   r    r2   )r+   ZindexerZ
allow_fillrr   msgoutputerrr   rq   r   take   s.   



zJSONArray.takec                 C  s   t | | jd d  S r1   r    r)   r@   r   r   r   r-      s   zJSONArray.copyTc                 C  s   ddl m} t|}t|t| jr|| jkr|r|  S | S t||r0| }|j| |ddS |s>t	j
dd | D |dS t	jdd | D ||dS )	Nr   )StringDtypeFr0   c                 S     g | ]}t |qS r   dictr3   r   r   r   r6          z$JSONArray.astype.<locals>.<listcomp>r<   c                 S  r{   r   r|   r3   r   r   r   r6      r~   )Zpandas.core.arrays.string_rz   r   r%   r    r&   r-   r   r2   rP   rg   rl   )r+   r&   r-   rz   Zarr_clsr   r   r   astype   s   
zJSONArray.astypec                 C  s"   t | dd dd | jD D S )Nc                 S  r{   r   r|   r3   r   r   r   r6      r~   z$JSONArray.unique.<locals>.<listcomp>c                 S  s   h | ]}t | qS r   rB   items)r4   dr   r   r   	<setcomp>   r;   z#JSONArray.unique.<locals>.<setcomp>ry   r@   r   r   r   unique   s   "zJSONArray.uniquec                 C  s"   t tjdd |D }| |S )Nc                 s  s    | ]}|j V  qd S r1   r>   r3   r   r   r   	<genexpr>   s    z.JSONArray._concat_same_type.<locals>.<genexpr>)rf   rN   chainfrom_iterable)r   Z	to_concatr)   r   r   r   _concat_same_type   s   zJSONArray._concat_same_typec                 C  s$   |   }t|dkr| }|dfS )Nr   r   )_values_for_argsortrX   Zravelr+   frozenr   r   r   _values_for_factorize   s   zJSONArray._values_for_factorizec                 C  s   dd | D }t |S )Nc                 S  s   g | ]}t | qS r   r   r3   r   r   r   r6      r;   z1JSONArray._values_for_argsort.<locals>.<listcomp>r   r   r   r   r   r      s   zJSONArray._values_for_argsort)limitr-   c                  s   t  j|||dS )N)methodr   r-   )super_pad_or_backfill)r+   r   r   r-   	__class__r   r   r     r9   zJSONArray._pad_or_backfill)NF)r   r$   )r   rW   )NN)FN)T)r   r   r   r   r&   Z__array_priority__r/   r#   r2   r8   rK   rV   rY   r^   r`   rh   propertyrk   rm   rx   r-   r   r   r   r   r   r   __classcell__r   r   r   r   r   G   s4    






r   c                     s"   t jd  fddtdD S )N   c              	     s.   g | ]}t  fd dt ddD qS )c                   s(   g | ]}  ttj d dfqS )r   d   )choicerf   stringascii_lettersintegersr4   _rngr   r   r6     s    z(make_data.<locals>.<listcomp>.<listcomp>r   
   )r   ranger   r   r   r   r   r6   	  s    
zmake_data.<locals>.<listcomp>r   )rP   randomZdefault_rngr   r   r   r   r   	make_data  s   
r   )&__doc__
__future__r   collectionsr   r   rN   rC   r   ri   typingr   r   rb   numpyrP   Zpandas.util._exceptionsr   Zpandas.core.dtypes.castr	   Zpandas.core.dtypes.commonr
   r   r   ZpandasrG   Zpandas.api.extensionsr   r   Zpandas.core.indexersr   collections.abcr   Zpandas._typingr   r   r   r   r   r   r   r   <module>   s.     @