o
    g7$                     @   s^  d dl mZ d dlmZ d dlZd dlZd dlmZmZ d dl	m
Z d dlmZ ejdd Zdd	 Zd
d Zdd Zdd Zejdddgdd Zdd Zdd Zdd Zdd Zejdddgdd Zejdg dd d! Zejdg d"d#d$ Zd%d& Zejd'dd(gd)d* Zejd+d,d-gd.d/ Z d0d1 Z!d2d3 Z"d4d5 Z#dS )6    )StringIO)PathN)	DataFrame	read_json)
JsonReaderc                  C   s$   t g dg dd} | jdddS )N                  ABTrecordslinesorient)r   to_json)df r   a/home/ubuntu/cloudmapper/venv/lib/python3.10/site-packages/pandas/tests/io/json/test_readlines.pylines_json_df   s   r   c                  C   s8   t ddd} tddgddggddgd}t| | d S )	Nz!{"a": 1, "b": 2}
{"b":2, "a" :1}
Tr   r   r	   abcolumns)r   r   tmassert_frame_equal)resultexpectedr   r   r   test_read_jsonl   s   r$   c                  C   s|   d} t | } t| dd}tddgddggddgd	}t|| d} t| dd}tddgddggddgd	}t|| d S )
Nu5   {"a": "foo”", "b": "bar"}
{"a": "foo", "b": "bar"}
Tr   u   foo”barfoor   r   r   )r   r   r   r    r!   )jsonr"   r#   r   r   r   test_read_jsonl_unicode_chars   s   r(   c                  C   s   t ddgddggddgd} | jddd}d	}||ksJ t d
dgddggddgd} | jddd}d}||ks:J tt|dd|  t ddgddggddgd} | jddd}d}||ksaJ tt|dd|  d S )Nr   r	   r   r   r   r   Tr   r   z{"a":1,"b":2}
{"a":1,"b":2}
zfoo}r%   zfoo"z/{"a":"foo}","b":"bar"}
{"a":"foo\"","b":"bar"}
r   zfoo\za\z4{"a\\":"foo\\","b":"bar"}
{"a\\":"foo\"","b":"bar"}
)r   r   r    r!   r   )r   r"   r#   r   r   r   test_to_jsonl/   s   r*   c                  C   sD   t ddgddggddgd} | jdddd	}d}||ks J d S )
Nr   r	   r   r   r   r   Tr)   
)r   r   count)r   actual_new_lines_countexpected_new_lines_countr   r   r   test_to_jsonl_count_new_linesD   s   r/   	chunksizer   g      ?c                 C   s\   t t| dd}t t| d|d}t|}W d    n1 s!w   Y  t|| d S )NTr   r   r0   )r   r   pdconcatr    r!   )r   r0   	unchunkedreaderchunkedr   r   r   test_readjson_chunksL   s
   r7   c              	   C   sz   d}t jt|d* tt| ddd}W d    n1 sw   Y  W d    d S W d    d S 1 s6w   Y  d S )Nz*chunksize can only be passed if lines=TruematchFr	   r1   pytestraises
ValueErrorr   r   )r   msg_r   r   r   &test_readjson_chunksize_requires_linesY   s   "r@   c                  C   s   t ddd} t| jddd}t|ddd}t| jddd}t|dddd	}t |}W d    n1 s9w   Y  t|| d S )
Nr   r	   r   Tr   r   Series)r   typ)r   rB   r0   )r2   rA   r   r   r   r3   r    assert_series_equal)sstrior4   r5   r6   r   r   r   test_readjson_chunks_series`   s   rF   c                 C   sb   t t| ddd}t|}W d    n1 sw   Y  |d jdks&J |d jdks/J d S )NTr	   r1   r   r	   r	   r   )r   r	   )r   r   listshape)r   r5   chunksr   r   r   test_readjson_each_chunkn   s
   
rK   c               	   C   s   t dD} tg dg dd}|j| ddd t| ddd	}t|}W d    n1 s0w   Y  t| dd
}t || W d    d S 1 sLw   Y  d S )N	test.jsonr   r   r   Tr   r   r   r1   r   )r    ensure_cleanr   r   r   r2   r3   r!   )pathr   r5   r6   r4   r   r   r   test_readjson_chunks_from_filew   s   "rO   c                 C   s   t dQ}tg dg dd}|j|ddd t|d dddddd	d	d d d| d d d
}| |  W d    n1 s=w   Y  |jjjsNJ d|  W d    d S 1 sYw   Y  d S )NrL   r   r   r   Tr   r   frameF)r   rB   dtypeconvert_axesconvert_dateskeep_default_datesnumpyprecise_float	date_unitencodingr   r0   compressionnrowsz%didn't close stream with chunksize = )	r    rM   r   r   r   readhandleshandleclosed)r0   rN   r   r5   r   r   r   test_readjson_chunks_closes   s8   
"r_   )r   g@r&   c              	   C   sz   d}t jt|d* tt| d|d}W d    n1 sw   Y  W d    d S W d    d S 1 s6w   Y  d S )Nz"'chunksize' must be an integer >=1r8   Tr1   r:   )r   r0   r>   r?   r   r   r   test_readjson_invalid_chunksize   s   "ra   )Nr   r	   c                 C   sx   d}t g dg dd}t|d| d}| d ur/| t|}W d    n1 s*w   Y  tj||d|  d d S )	NzF

    {"A":1,"B":4}



    {"A":2,"B":5}







    {"A":3,"B":6}
    r   r   r   Tr1   zchunksize: )obj)r   r   r2   r3   r    r!   )r0   jorigtestr   r   r   )test_readjson_chunks_multiple_empty_lines   s   rf   c              	   C   s   t d>}| ddd  t|ddd}|d W d    n1 s%w   Y  t|}td	d
gi}t || W d    d S 1 sFw   Y  d S )NrL   zlocale.getpreferredencodingc                 S   s   dS )Ncp949r   )lr   r   r   <lambda>   s    z'test_readjson_unicode.<locals>.<lambda>wzutf-8)rX   u6   {"£©µÀÆÖÞßéöÿ":["АБВГДабвгд가"]}u   £©µÀÆÖÞßéöÿu   АБВГДабвгд가)r    rM   setattropenwriter   r   r!   )monkeypatchrN   fr"   r#   r   r   r   test_readjson_unicode   s   "rp   rZ   r	   c                 C   sB   d}t |d| d}tg dg ddjd |  }t|| d S )N[{"a": 1, "b": 2}
        {"a": 3, "b": 4}
        {"a": 5, "b": 6}
        {"a": 7, "b": 8}Tr   rZ   r   r
   r      r	   r   r      r   r   )r   r   ilocr    r!   )rZ   jsonlr"   r#   r   r   r   test_readjson_nrows   s    rz   znrows,chunksizerG   )r   r	   c                 C   sn   d}t |d| |d}t|}W d    n1 sw   Y  tg dg ddjd |  }t|| d S )Nrq   T)r   rZ   r0   rs   ru   rw   )r   r2   r3   r   rx   r    r!   )rZ   r0   ry   r5   r6   r#   r   r   r   test_readjson_nrows_chunks   s    r{   c                  C   sJ   d} d}t jt|d t| ddd W d    d S 1 sw   Y  d S )Nrq   z&nrows can only be passed if lines=Truer8   Fr	   rr   )r;   r<   r=   r   )ry   r>   r   r   r   "test_readjson_nrows_requires_lines   s
   "r|   c                 C   s   t ddggddgdgdt ddggddgdgdt d	d
ggddgdgdg}| dddd}t| }t|ddd}t|D ]\}}t|||  q?W d    d S 1 sWw   Y  d S )Nr   r	   r   r   r   )r   indexr
   r   r   r   ior'   datazline_delimited.jsonTr1   )r   r   as_urir   	enumerater    r!   )datapathdf_list_expectedos_pathfile_url
url_readerr}   chuckr   r   r   "test_readjson_lines_chunks_fileurl   s   "r   c                  C   sN   dd } G dd d}|| }t tt|ddddksJ |jd	ks%J d S )
Nz\{"a": 1, "b": 2}
        {"a": 3, "b": 4}
        {"a": 5, "b": 6}
        {"a": 7, "b": 8}
i  c                   @   s$   e Zd Zdd Zdd Zdd ZdS )z/test_chunksize_is_incremental.<locals>.MyReaderc                 S   s   d| _ t|| _d S )Nr   )
read_countr   stringio)selfcontentsr   r   r   __init__  s   z8test_chunksize_is_incremental.<locals>.MyReader.__init__c                 W   s   |  j d7  _ | jj| S Nr   )r   r   r[   )r   argsr   r   r   r[     s   z4test_chunksize_is_incremental.<locals>.MyReader.readc                 S   s   |  j d7  _ t| jS r   )r   iterr   )r   r   r   r   __iter__  s   
z8test_chunksize_is_incremental.<locals>.MyReader.__iter__N)__name__
__module____qualname__r   r[   r   r   r   r   r   MyReader  s    r   Td   r1   r   
   )lenrH   r   r   )ry   r   r5   r   r   r   test_chunksize_is_incremental  s   r   )$r~   r   pathlibr   r;   pandasr2   r   r   pandas._testing_testingr    pandas.io.json._jsonr   fixturer   r$   r(   r*   r/   markparametrizer7   r@   rF   rK   rO   r_   ra   rf   rp   rz   r{   r|   r   r   r   r   r   r   <module>   sB    

	





