U
    f/e7$                     @   sd  d dl mZ d dlmZ d dlZd dlZd dlmZmZ d dl	m
Z d dlmZ ejdd Zdd	 Zd
d Zdd Zdd Zejdddgdd Zdd Zdd Zdd Zdd Zejdddgdd Zejdd dd d!gd"d# Zejdddd$gd%d& Zd'd( Zejd)dd$gd*d+ Zejd,d-d.gd/d0 Z d1d2 Z!d3d4 Z"d5d6 Z#dS )7    )StringIO)PathN)	DataFrame	read_json)
JsonReaderc                  C   s(   t dddgdddgd} | jdd	d
S )N                  ABTrecordslinesorient)r   to_json)df r   G/tmp/pip-unpacked-wheel-tiezk1ph/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:tt d
dgddggddgd} | jddd}d}||kstttt|dd|  t ddgddggddgd} | jddd}d}||kst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   AssertionErrorr   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@td S )
Nr   r   r   r   r   r   Tr'   
)r   r   countr(   )r   Zactual_new_lines_countZexpected_new_lines_countr   r   r   test_to_jsonl_count_new_linesD   s    r,   	chunksizer   g      ?c              	   C   sH   t t| dd}t t| d|d}t|}W 5 Q R X t|| d S )NTr   r   r-   )r   r   pdconcatr   r   )r   r-   	unchunkedreaderchunkedr   r   r   test_readjson_chunksL   s    r4   c              
   C   s@   d}t jt|d$ tt| ddd}W 5 Q R X W 5 Q R X d S )Nz*chunksize can only be passed if lines=TruematchFr   r.   pytestraises
ValueErrorr   r   )r   msg_r   r   r   &test_readjson_chunksize_requires_linesY   s    r=   c               	   C   sx   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 5 Q R X t|| d S )
Nr   r   r   Tr   r   Series)r   typ)r   r?   r-   )r/   r>   r   r   r   r0   r   Zassert_series_equal)sZstrior1   r2   r3   r   r   r   test_readjson_chunks_series`   s    rA   c              	   C   sN   t t| ddd}t|}W 5 Q R X |d jdks8t|d jdksJtd S )NTr   r.   r   r   r   r   )r   r   )r   r   listshaper(   )r   r2   chunksr   r   r   test_readjson_each_chunkn   s    rF   c               
   C   s   t dl} tdddgdddgd}|j| d	d
d t| d	dd}t|}W 5 Q R X t| d	d}t || W 5 Q R X d S )N	test.jsonr   r   r	   r
   r   r   r   Tr   r   r.   r   )r   ensure_cleanr   r   r   r/   r0   r   )pathr   r2   r3   r1   r   r   r   test_readjson_chunks_from_filew   s    rJ   c                 C   s   t d}tdddgdddgd}|j|d	d
d t|d dd	d	d	d	ddd d d	| d d d}| |  W 5 Q R X |jjjst	d|  W 5 Q R X d S )NrG   r   r   r	   r
   r   r   r   Tr   r   frameF)r   r?   ZdtypeZconvert_axesZconvert_datesZkeep_default_datesZnumpyZprecise_floatZ	date_unitencodingr   r-   compressionnrowsz%didn't close stream with chunksize = )
r   rH   r   r   r   readZhandleshandleclosedr(   )r-   rI   r   r2   r   r   r   test_readjson_chunks_closes   s4    rR   g@r$   c              
   C   s@   d}t jt|d$ tt| d|d}W 5 Q R X W 5 Q R X d S )Nz"'chunksize' must be an integer >=1r5   Tr.   r7   )r   r-   r;   r<   r   r   r   test_readjson_invalid_chunksize   s    rT   r   c              	   C   sh   d}t dddgdddgd}t|d	| d
}| d k	rN| t|}W 5 Q R X tj||d|  d d S )NzF

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



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







    {"A":3,"B":6}
    r   r   r	   r
   r   r   r   Tr.   zchunksize: )obj)r   r   r/   r0   r   r   )r-   jorigtestr   r   r   )test_readjson_chunks_multiple_empty_lines   s    rY   c              
   C   sp   t d\}| ddd  t|ddd}|d W 5 Q R X t|}td	d
gi}t || W 5 Q R X d S )NrG   zlocale.getpreferredencodingc                 S   s   dS )Ncp949r   )lr   r   r   <lambda>       z'test_readjson_unicode.<locals>.<lambda>wzutf-8)rL   u6   {"£©µÀÆÖÞßéöÿ":["АБВГДабвгд가"]}u   £©µÀÆÖÞßéöÿu   АБВГДабвгд가)r   rH   setattropenwriter   r   r   )ZmonkeypatchrI   fr    r!   r   r   r   test_readjson_unicode   s    rc   rN   c                 C   sJ   d}t |d| d}tddddgdd	d
dg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   rN   r   r	   r      r   r
   r      r   r   )r   r   ilocr   r   )rN   jsonlr    r!   r   r   r   test_readjson_nrows   s    (rk   znrows,chunksizerB   )r
   r   c              	   C   sb   d}t |d| |d}t|}W 5 Q R X tddddgdd	d
dgdjd |  }t|| d S )Nrd   T)r   rN   r-   r   r	   r   rf   r   r
   r   rg   rh   )r   r/   r0   r   ri   r   r   )rN   r-   rj   r2   r3   r!   r   r   r   test_readjson_nrows_chunks   s
    (rl   c               	   C   s4   d} d}t jt|d t| ddd W 5 Q R X d S )Nrd   z&nrows can only be passed if lines=Truer5   Fr   re   )r8   r9   r:   r   )rj   r;   r   r   r   "test_readjson_nrows_requires_lines   s    rm   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 5 Q R X d S )Nr   r   r   r   r   )r   indexr	   r
   r   r   ior%   datazline_delimited.jsonTr.   )r   r   as_urir   	enumerater   r   )datapathZdf_list_expectedZos_pathZfile_urlZ
url_readerrn   Zchuckr   r   r   "test_readjson_lines_chunks_fileurl   s    rt   c                  C   sN   dd } G dd d}|| }t tt|ddddks<t|jd	ksJtd S )
Nz\{"a": 1, "b": 2}
        {"a": 3, "b": 4}
        {"a": 5, "b": 6}
        {"a": 7, "b": 8}
i  c                   @   s$   e Zd Zdd Zdd Zdd ZdS )z/test_chunksize_is_incremental.<locals>.MyReaderc                 S   s   d| _ t|| _d S )Nr   )
read_countr   stringio)selfcontentsr   r   r   __init__  s    z8test_chunksize_is_incremental.<locals>.MyReader.__init__c                 W   s   |  j d7  _ | jj| S Nr   )ru   rv   rO   )rw   argsr   r   r   rO     s    z4test_chunksize_is_incremental.<locals>.MyReader.readc                 S   s   |  j d7  _ t| jS rz   )ru   iterrv   )rw   r   r   r   __iter__  s    z8test_chunksize_is_incremental.<locals>.MyReader.__iter__N)__name__
__module____qualname__ry   rO   r}   r   r   r   r   MyReader  s   r   Td   r.   r   
   )lenrC   r   r(   ru   )rj   r   r2   r   r   r   test_chunksize_is_incremental  s    r   )$ro   r   pathlibr   r8   Zpandasr/   r   r   Zpandas._testingZ_testingr   Zpandas.io.json._jsonr   Zfixturer   r"   r&   r)   r,   markZparametrizer4   r=   rA   rF   rJ   rR   rT   rY   rc   rk   rl   rm   rt   r   r   r   r   r   <module>   s@   

	





