a
    Gb                     @   s  d Z ddlmZ ddlZddlmZ ddlmZ ej	
dZeej	di ddigd	d
 Zedd Zdd Zeej	ddeg dgg ddfdeg dgg ddfdeg dgg ddfgdd Zeej	ddg deg dg d gg d!dfd"g d#eg d$g d%gg d&dfd'g d(eg d)g d*gg d+dfgd,d- Zed.d/ Zed0d1 Zed2d3 ZdS )4z
Tests that duplicate columns are handled appropriately when parsed by the
CSV engine. In general, the expected result is that they are either thoroughly
de-duplicated (if mangling requested) or ignored otherwise.
    )StringION)	DataFrameZpyarrow_skipkwargsZmangle_dupe_colsTc                 C   sH   | }d}|j t|fddi|}tg dgg dd}t|| d S )Nza,a,b,b,b
1,2,3,4,5sep,)               )aa.1bzb.1zb.2columnsread_csvr   r   tmassert_frame_equal)all_parsersr   parserdataresultexpected r   Glib/python3.9/site-packages/pandas/tests/io/parser/test_mangle_dupes.py
test_basic   s
    r   c                 C   sB   | }d}t g dg dgg dd}|t|}t|| d S )Nza,b,a
0,1,2
3,4,5r   r   r   )r	   r
   r   )r   r   r   r   )r   r   r   r   r   )r   r   r   r   r   r   r   r   test_basic_names   s
    r   c                 C   sP   | }d}t jtdd& |jt|g dd W d    n1 sB0    Y  d S )Nz0,1,2
3,4,5Duplicate namesmatch)r   r   r   namespytestZraises
ValueErrorr   r   )r   r   r   r   r   r   test_basic_names_raise*   s    r'   zdata,expectedza,a,a.1
1,2,3r   r   r	   )r   a.2r   r   z+a,a,a.1,a.1.1,a.1.1.1,a.1.1.1.1
1,2,3,4,5,6)r   r   r	   r
   r      )r   r)   r   a.1.1a.1.1.1	a.1.1.1.1z!a,a,a.3,a.1,a.2,a,a
1,2,3,4,5,6,7r   r   r	   r
   r   r*      )r   a.4a.3r   r)   za.5za.6c                 C   s"   | }| t|}t|| d S )N)r   r   r   r   )r   r   r   r   r   r   r   r   test_thorough_mangle_columns3   s    r2   zdata,names,expectedza,b,b
1,2,3)r   r   r+   )r   r   r   )123)r   r+   r,   za,b,c,d,e,f
1,2,3,4,5,6)r   r   r   r+   r,   r-   )r   r   cdef)r3   r4   r5   456)r   r   r+   r,   r-   za.1.1.1.1.1za,b,c,d,e,f,g
1,2,3,4,5,6,7)r   r   r1   r   r)   r   r   )r   r   r6   r7   r8   r9   g)r3   r4   r5   r:   r;   r<   7)r   r   r1   r+   r)   za.2.1za.3.1c                 C   sH   | }t jtdd" |jt||d W d    n1 s:0    Y  d S )Nr   r    r"   r$   )r   r   r#   r   r   r   r   r   test_thorough_mangle_namesP   s    "r?   c           	      C   s   d}| }g d}t ||i}tdD ]r}t  }t|d D ]4}ddd|  t|d  }|jd|g dd	 q:|||< |t| }t|| q$d S )
N0r(   r	   r   
Unnamed: 0.r   r   )Zloccolumnvalue)	r   rangemininsertr   r   Zto_csvr   r   )	r   Zorig_keyr   Z
orig_valueZdfir   jZcol_namer   r   r   !test_mangled_unnamed_placeholdersx   s    rJ   c                 C   s<   | }d}| t|}tg dgg dd}t|| d S )Nz%a,a,a.1,a,a.3,a.1,a.1.1
1,2,3,4,5,6,7r.   )r   r)   r   r0   r1   za.1.2r+   r   r   r   r   r   r   r   r   r   r   $test_mangle_dupe_cols_already_exists   s    rL   c                 C   s<   | }d}| t|}tg dgg dd}t|| d S )Nz,Unnamed: 0,,Unnamed: 2
1,2,3,4)r   r   r	   r
   )zUnnamed: 0.1rA   zUnnamed: 2.1z
Unnamed: 2r   r   rK   r   r   r   0test_mangle_dupe_cols_already_exists_unnamed_col   s    rM   )__doc__ior   r%   Zpandasr   Zpandas._testingZ_testingr   ZmarkZusefixturesZskip_pyarrowZparametrizer   r   r'   r2   r?   rJ   rL   rM   r   r   r   r   <module>   s   
		

