U
    f/e6                     @   s.  d Z ddlmZ ddlm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ZddlmZ ddlmZ d	Zd
ZdZdZddddddddddddddddgZdZdZdZd Zd!e d"e d"e d"e d#	Zd$e d"e d%Zd&Zeed'd(d)Z ed*d+d,Z!d-d. Z"d/d0 Z#G d1d2 d2eej$Z%dS )3z
Read a SAS XPort format file into a Pandas DataFrame.

Based on code from Jack Cushman (github.com/jcushman/xport).

The file format is defined here:

https://support.sas.com/techsup/technote/ts140.pdf
    )abc)datetimeN)IOcast)Appender)
get_handle)
ReaderBasezPHEADER RECORD*******LIBRARY HEADER RECORD!!!!!!!000000000000000000000000000000  zKHEADER RECORD*******MEMBER  HEADER RECORD!!!!!!!000000000000000001600000000zPHEADER RECORD*******DSCRPTR HEADER RECORD!!!!!!!000000000000000000000000000000  zPHEADER RECORD*******OBS     HEADER RECORD!!!!!!!000000000000000000000000000000  ntypeZnhfunfield_lengthZnvar0namelabelZnformZnflZnum_decimalsZnfjZnfillZniformZniflZnifdZnpos_zParameters
----------
filepath_or_buffer : str or file-like object
    Path to SAS file or object implementing binary read method.zindex : identifier of index column
    Identifier of column that should be used as index of the DataFrame.
encoding : str
    Encoding for text data.
chunksize : int
    Read file `chunksize` lines at a time, returns iterator.zBformat : str
    File format, only `xport` is currently supported.z\iterator : bool, default False
    Return XportReader object for reading file incrementally.z#Read a SAS file into a DataFrame.


a  

Returns
-------
DataFrame or XportReader

Examples
--------
Read a SAS Xport file:

>>> df = pd.read_sas('filename.XPT')

Read a Xport file in 10,000 line chunks:

>>> itr = pd.read_sas('filename.XPT', chunksize=10000)
>>> for chunk in itr:
>>>     do_something(chunk)

z$Class for reading SAS Xport files.

z

Attributes
----------
member_info : list
    Contains information about the file
fields : list
    Contains information about the variables in the file
zRead observations from SAS Xport file, returning as data frame.

Parameters
----------
nrows : int
    Number of rows to read from data file; if None, read whole
    file.

Returns
-------
A DataFrame.
)datestrreturnc                 C   s.   zt | dW S  tk
r(   tj Y S X dS )z1Given a date in xport format, return Python date.z%d%b%y:%H:%M:%SN)r   strptime
ValueErrorpdZNaT)r    r   ;/tmp/pip-unpacked-wheel-tiezk1ph/pandas/io/sas/sas_xport.py_parse_date   s    r   )sc                 C   s@   i }d}|D ](\}}| |||    ||< ||7 }q|d= |S )a  
    Parameters
    ----------
    s: str
        Fixed-length string to split
    parts: list of (name, length) pairs
        Used to break up string, name '_' will be filtered from output.

    Returns
    -------
    Dict of name:contents of string at given location.
    r   r   )strip)r   partsoutstartr   lengthr   r   r   _split_line   s    
r   c                 C   sT   |dkrPt t| t d}t d| dd|  }|j|d}| |d< |S | S )N   ZS8Sz,Sdtypef0)npzeroslenr!   view)vecnbytesvec1r!   Zvec2r   r   r   _handle_truncated_float_vec   s    	r*   c           	      C   s  t d}| j|d}|d }|d }|d@ }t jt| t jd}d|t |d@ < d|t |d	@ < d
|t |d@ < ||L }||? |d@ dd
|  > B }|dM }||d? d@ d d> | d d> |d@ B O }t jt|fdd}||d< ||d< |jdd}|d}|S )zf
    Parse a vector of float values representing IBM 8 byte floats into
    native 8 byte floats.
    z>u4,>u4r    r"   f1i    i       i  @    i         l          A   i     l        z>f8Zf8)	r#   r!   r&   r$   r%   Zuint8whereemptyZastype)	r'   r!   r)   Zxport1Zxport2Zieee1shiftZieee2Zieeer   r   r   _parse_float_vec   s*    
		 
r8   c                   @   sl   e Zd ZeZdddZdd Zdd Zd	d
 Zdd Z	e
dddZdddZdd ZeedddZdS )XportReaderN
ISO-8859-1c                 C   sn   || _ d| _|| _|| _t|d|dd| _ttt | jj	| _
z|   W n tk
rh   |    Y nX d S )Nr   rbF)encodingZis_text)	_encoding_lines_read_index
_chunksizer   handlesr   r   byteshandlefilepath_or_buffer_read_header	Exceptionclose)selfrD   indexr<   	chunksizer   r   r   __init__   s        zXportReader.__init__c                 C   s   | j   d S )N)rA   rG   rH   r   r   r   rG     s    zXportReader.closec                 C   s   | j d S )NP   )rD   readdecoderL   r   r   r   _get_row  s    zXportReader._get_rowc              	   C   s2  | j d |  }|tkr$td|  }ddgddgddgddgd	d
gg}t||}|d dkrltdt|d	 |d	< || _|  }t|d d
 |d< |  }|  }|t	}|t
k}	|r|	stdt|dd }
ddgddgddgddgddgddgd	d
gg}t|  |}dd
gdd
gddgddgg}|t|  | t|d |d< t|d	 |d	< || _ddd}t|  dd }|
| }|d r|d|d  7 }| j |}g }d}t||
kr|d |
 ||
d   }}|d}td|}ttt|}|d= ||d  |d< |d }|d dkrf|d k sR|dkrfd!| d"}t|| D ]2\}}z| ||< W n tk
r   Y nX qn||d 7 }||g7 }q|  }|tkstd#|| _|| _| j  | _|  | _ d$d% | jD | _!d&d% t"| jD }t#$|}|| _%d S )'Nr   z#Header record is not an XPORT file.prefixr1   versionr   ZOSr   created   zSAS     SAS     SASLIBz!Header record has invalid prefix.modifiedzMember header not foundset_nameZsasdatar   (   typenumericchar)r,   r-   6   :   rM      z>hhhh8s40s8shhh2s8shhl52sr	   r
   r-   zFloating field width z is not between 2 and 8.zObservation header not found.c                 S   s   g | ]}|d    qS )r   )rO   ).0xr   r   r   
<listcomp>r  s     z,XportReader._read_header.<locals>.<listcomp>c                 S   s,   g | ]$\}}d t | dt |d  fqS )r   r   r
   )str)r`   ifieldr   r   r   rb   u  s   )&rD   seekrP   _correct_line1r   r   r   	file_info
startswith_correct_header1_correct_header2intupdatemember_inforN   r%   ljuststructunpackdictzip
_fieldkeys	TypeErroritemsr   AttributeError_correct_obs_headerfieldsrecord_lengthtellrecord_start_record_countnobscolumns	enumerater#   r!   _dtype)rH   Zline1Zline2Zfifrh   Zline3Zheader1Zheader2Z	headflag1Z	headflag2ZfieldnamelengthZmemrn   typesZ
fieldcountZ
datalengthZ	fielddatary   Z
obs_lengthZ
fieldbytesZfieldstructre   flmsgkvheaderZdtypelr!   r   r   r   rE     s    "

	




"



zXportReader._read_headerc                 C   s   | j | jpddS )Nr,   nrows)rN   r@   rL   r   r   r   __next__|  s    zXportReader.__next__)r   c                 C   s   | j dd | j  | j }|d dkr4td | jdkrV| j | j || j S | j dd | j d}tj	|tj
d}t|dk}t|dkrd}ndt| }| j | j || | j S )	z
        Get number of records in file.

        This is maybe suboptimal because we have to seek to the end of
        the file.

        Side effect: returns file position to record_start.
        r   r-   rM   zxport file may be corruptedir    l     @@  r   )rD   rf   r{   r|   warningswarnrz   rN   r#   
frombufferZuint64Zflatnonzeror%   )rH   Ztotal_records_lengthZlast_card_bytesZ	last_cardixZtail_padr   r   r   r}     s     	


zXportReader._record_countc                 C   s   |dkr| j }| j|dS )a  
        Reads lines from Xport file and returns as dataframe

        Parameters
        ----------
        size : int, defaults to None
            Number of lines to read.  If None, reads whole file.

        Returns
        -------
        DataFrame
        Nr   )r@   rN   )rH   sizer   r   r   	get_chunk  s    zXportReader.get_chunkc                 C   sl   |j dd}|d dk|d dk@ |d dk@ }|d dk|d d	k@ |d d
kB |d dkB }||M }|S )Nzu1,u1,u2,u4r    r+   r   f2Zf3r"   r3   Z   _   .   )r&   )rH   r'   r   missZmiss1r   r   r   _missing_double  s    $

zXportReader._missing_doublec                    sf  |d kr j }t| j  j }| j }|dkr>   t j|}tj	| j
|d}tjt|d}t jD ]\}}|dt|  }	 j| d }
|
dkrt|	 j| d }	 |	}t|	}tj||< n@ j| d dkrd	d
 |	D } jd k	r fdd
|D }|||< qv jd krHtt j j| |_n| j}  j|7  _|S )Nr   )r!   count)rI   r   r	   r[   r
   r\   c                 S   s   g | ]}|  qS r   )rstripr`   yr   r   r   rb     s     z$XportReader.read.<locals>.<listcomp>c                    s   g | ]}|  jqS r   )rO   r=   r   rL   r   r   rb     s     )r~   minr>   rz   rG   StopIterationrD   rN   r#   r   r   r   Z	DataFrameranger   r   rc   ry   r*   r   r8   nanr=   r?   ZIndexrI   Z	set_index)rH   r   
read_linesread_lenrawdataZdfjra   r'   r	   r   r   r   rL   r   rN     s8    


zXportReader.read)Nr:   N)N)N)__name__
__module____qualname___xport_reader_doc__doc__rK   rG   rP   rE   r   rl   r}   r   r   r   _read_method_docrN   r   r   r   r   r9      s        
h#
r9   )&r   collectionsr   r   rp   typingr   r   r   Znumpyr#   Zpandas.util._decoratorsr   Zpandasr   Zpandas.io.commonr   Zpandas.io.sas.sasreaderr   rg   rj   rk   rx   rt   Z_base_params_docZ_params2_docZ_format_params_docZ_iterator_docZ_read_sas_docr   r   rc   r   r   r*   r8   Iteratorr9   r   r   r   r   <module>   sv   		9