o
    Ehe'                     @  sH  d Z ddlmZ ddlZddlmZ ddlZddlZ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 ddlmZ dd Zejddgddd Zejdd Zejdd Z ejdd Z!ejdd Z"ejdd Z#ejdd Z$G dd  d ej%Z&G d!d" d"ej'Z(d#d$ Z)d%d& Z*dS )'aj  
This file contains a minimal set of tests for compliance with the extension
array interface test suite, and should contain no other tests.
The test suite for the full functionality of the array is located in
`pandas/tests/arrays/`.

The tests in this file are inherited from the BaseExtensionTests, and only
minimal tweaks should be applied to get the tests passing (by overwriting a
parent method).

Additional tests should either be added to one of the BaseExtensionTests
classes (if they are relevant for the extension interface for all dtypes), or
be added to the array-specific tests in `pandas/tests/arrays/`.

    )annotationsN)cast)HAS_PYARROW)StorageExtensionDtypeis_string_dtype)ArrowStringArrayStringDtype)string_dtype_highest_priority)basec                 C  st   |s| S | j jdkr| S td}| j}t|d }|g |d | j||d  j}|jdks4J t	| |S )Npyarrow   )
dtypestoragepytestZimportorskipZ	_pa_arraylenZchunked_arraychunksZ
num_chunkstype)arrchunkedpaZarrow_arraysplit r   Blib/python3.10/site-packages/pandas/tests/extension/test_string.pymaybe_split_array%   s   
r   TF)paramsc                 C  s   | j S N)Zparam)requestr   r   r   r   6   s   r   c                 C  s   | \}}t ||dS )N)r   na_valuer	   )Zstring_dtype_argumentsr   r   r   r   r   r   ;   s   r   c                 C  st   t jdjttjdd}|d |d kr,t jdjttjdd}|d |d ks|  j|| d}t	||S )Nr   d   )sizer      r   )
npZrandomZdefault_rngchoiceliststringZascii_lettersconstruct_array_type_from_sequencer   )r   r   stringsr   r   r   r   dataA   s   
r+   c                 C  s"   |   jtjdg| d}t||S )zLength 2 array with [NA, Valid]Ar#   r(   r)   pdNAr   r   r   r   r   r   r   data_missingK   s   
r1   c                 C  s    |   jg d| d}t||S )N)BCr,   r#   )r(   r)   r   r0   r   r   r   data_for_sortingR   s   
r4   c                 C  s$   |   jdtjdg| d}t||S )Nr2   r,   r#   r-   r0   r   r   r   data_missing_for_sortingX   s   
r5   c              	   C  s0   |   jddtjtjddddg| d}t||S )Nr2   r,   r3   r#   r-   r0   r   r   r   data_for_grouping^   s   
r6   c                      s   e Zd Z fddZdd Z fddZ fddZ fd	d
Zdd Z fddZ	 fddZ
dd Zdd Zd*ddZd+ddZd+d d!Zd,d"d#Zd$d% Z fd&d'Z fd(d)Z  ZS )-TestStringArrayc                   s|   t  | |jtju r|d|j dksJ d S |jdkr<tt |dks*J W d    d S 1 s5w   Y  d S d S )Nzstring[]r   zstring[pyarrow_numpy])	supertest_eq_with_strr   r.   r/   r   tmZassert_produces_warningFutureWarningselfr   	__class__r   r   r:   g   s   
"z TestStringArray.test_eq_with_strc                 C  s   t |sJ d S r   r   r=   r   r   r   test_is_not_string_typeq   s   z'TestStringArray.test_is_not_string_typec                   s@   |j tju r|st||j}|du sJ d S t | d S )NF)r   r$   nanr   Zis_dtypenamer9   test_is_dtype_from_name)r>   r   using_infer_stringresultr?   r   r   rD   v   s   z'TestStringArray.test_is_dtype_from_namec                   s`   |j tju r(|s(tjtdd ||j W d    d S 1 s!w   Y  d S t 	| d S )Nz Cannot construct a 'StringDtype'match)
r   r$   rB   r   raises	TypeErrorZconstruct_from_stringrC   r9   #test_construct_from_string_own_name)r>   r   rE   r?   r   r   rK   }   s
   "z3TestStringArray.test_construct_from_string_own_namec                   (   |j jdkrtjdd t | d S Nr   /2D support not implemented for ArrowStringArrayreason)r   r   r   skipr9   	test_viewr>   r+   r?   r   r   rR         zTestStringArray.test_viewc                 C  s   d S r   r   rS   r   r   r   test_from_dtype   s   zTestStringArray.test_from_dtypec                   rL   rM   )r   r   r   rQ   r9   test_transposerS   r?   r   r   rV      rT   zTestStringArray.test_transposec                   rL   rM   )r   r   r   rQ   r9   test_setitem_preserves_viewsrS   r?   r   r   rW      rT   z,TestStringArray.test_setitem_preserves_viewsc                 C  s"   |  }|dg }t|| d S )Nr"   )Zdropnar;   assert_extension_array_equal)r>   r1   rF   expectedr   r   r   test_dropna_array   s   
z!TestStringArray.test_dropna_arrayc                 C  s`   ||    }|d }||}||usJ t|| |jdd}||us(J t|| d S )Nr   Zbackfill)method)ZisnaZfillnar;   rX   )r>   r+   ZvalidrF   r   r   r   test_fillna_no_op_returns_copy   s   
z.TestStringArray.test_fillna_no_op_returns_copyop_namestrreturn4type[Exception] | tuple[type[Exception], ...] | Nonec                 C  s(   |dv rt S |dv rt S |dv rt S d S )N)__mod____rmod__
__divmod____rdivmod____pow____rpow__)__mul____rmul__)__truediv____rtruediv____floordiv____rfloordiv____sub____rsub__)rJ   )r>   r]   objotherr   r   r   _get_expected_exception   s   z'TestStringArray._get_expected_exceptionser	pd.Seriesboolc                 C  s   |dv p|j jtju o|dv S )N)minmaxsum)anyall)r   r   r$   rB   r>   rr   r]   r   r   r   _supports_reduction   s   z#TestStringArray._supports_reductionc                 C  s   t |jtsJ |dv S )N)ZcumminZcummaxZcumsum)
isinstancer   r   rz   r   r   r   _supports_accumulation   s   z&TestStringArray._supports_accumulationc                 C  s|   t tt|}|dv r%|}t|tst|nd }t|tr$t||}n|jtj	u r/tj
}n
|jdkr7d}nd}||S )N)__add____radd__r   bool[pyarrow]boolean)r   r
   r;   Z	get_dtyper|   r^   r   r   r$   rB   Zbool_r   astype)r>   r]   ro   rp   Zpointwise_resultr   Zcast_toZdtype_otherr   r   r   _cast_pointwise_result   s   



z&TestStringArray._cast_pointwise_resultc                 C  s   t |}| |||d d S )Nabc)r.   SeriesZ_compare_other)r>   r+   Zcomparison_oprr   r   r   r   test_compare_scalar   s   
z#TestStringArray.test_compare_scalarc                   sP   t |dj}|r |jtju r |jdkr tjjdd}|	| t
 | d S )Nr"   pythonmThe pointwise operation result will be inferred to string[nan, pyarrow], which does not match the input dtyperO   )nextr   r   r.   r/   r   r   markxfailapplymarkerr9   test_combine_add)r>   Zdata_repeatedrE   r   r   r   r?   r   r   r      s   
z TestStringArray.test_combine_addc                   sV   |j }|r"|dkr"|jtju r"ts|jdkr"tjjdd}|	| t
 || d S )Nr   r   r   rO   )r   r   r.   r/   r   r   r   r   r   r   r9   test_arith_series_with_array)r>   r+   Zall_arithmetic_operatorsrE   r   r   r   r?   r   r   r      s   

z,TestStringArray.test_arith_series_with_array)r]   r^   r_   r`   )rr   rs   r]   r^   r_   rt   )r]   r^   )__name__
__module____qualname__r:   rA   rD   rK   rR   rU   rV   rW   rZ   r\   rq   r{   r}   r   r   r   r   __classcell__r   r   r?   r   r7   f   s$    




r7   c                   @  s    e Zd Zejdddd ZdS )Test2DCompatT)Zautousec                 C  s   t |trtjdd d S d S )NrN   rO   )r|   r   r   rQ   rS   r   r   r   arrow_not_supported  s   
z Test2DCompat.arrow_not_supportedN)r   r   r   r   fixturer   r   r   r   r   r      s    
r   c                 C  sr   | \}}}|  g d}tj|d< |rt|}d}tjt|d || W d    d S 1 s2w   Y  d S )N)r   r   r"   zOsearchsorted requires array to be sorted, which is impossible with NAs present.rG   )Ztaker.   r/   r   r   rI   
ValueErrorZsearchsorted)r4   Z	as_seriesbcar   msgr   r   r    test_searchsorted_with_na_raises  s   


"r   c                 C  s   t jddg| d}t jddgtd}||k}t jddgtd}| jdkr0| jt ju r0|d}n| jd	kr@| jt ju r@|d
}t	|| d S )Nr   r   r#   r"   FTr   r   r   r   )
r.   r   objectrt   r   r   r/   r   r;   Zassert_series_equal)r   rr   ZmixedrF   rY   r   r   r   test_mixed_object_comparison  s   
r   )+__doc__Z
__future__r   r'   typingr   Znumpyr$   r   Zpandas.compatr   Zpandas.core.dtypes.baser   Zpandasr.   Zpandas._testingZ_testingr;   Zpandas.api.typesr   Zpandas.core.arraysr   Zpandas.core.arrays.string_r
   Z'pandas.tests.arrays.string_.test_stringr   Zpandas.tests.extensionr   r   r   r   r   r+   r1   r4   r5   r6   ZExtensionTestsr7   ZDim2CompatTestsr   r   r   r   r   r   r   <module>   sF    


	



 