o
    tf                     @   s  d Z dZddl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
mZ ddlZddlZddlZddlZddlZddlZddlZddlZdd	 Zd#ddZG dd deZdd ZdZdZd$ddZd%ddZd&ddZd'ddZd(d d!Zed"kreej   dS dS ))z=Diagnostic functions, mainly for use when doing tech support.MIT    N)BytesIO)
HTMLParser)BeautifulSoup__version__)builder_registryc           
      C   s  t dt  t dtj  g d}|D ]}tjD ]	}||jv r! nq|| t d|  qd|v rc|d zddl	m
} t d	d
tt|j  W n tyb } z
t d W Y d}~nd}~ww d|v rzddl}t d|j  W n ty } z
t d W Y d}~nd}~ww t| dr|  } |D ]C}t d|  d}z
t| |d}	d}W n ty } zt d|  t  W Y d}~nd}~ww |rt d|  t |	  t d qdS )zDiagnostic suite for isolating common problems.

    :param data: A string containing markup that needs to be explained.
    :return: None; diagnostics are printed to standard output.
    z'Diagnostic running on Beautiful Soup %szPython version %s)html.parserhtml5liblxmlz;I noticed that %s is not installed. Installing it may help.r
   zlxml-xmlr   etreezFound lxml version %s.z.lxml is not installed or couldn't be imported.Nr	   zFound html5lib version %sz2html5lib is not installed or couldn't be imported.readz#Trying to parse your markup with %sF)featuresT%s could not parse the markup.z#Here's what %s did with the markup:zP--------------------------------------------------------------------------------)printr   sysversionr   Zbuildersr   removeappendr
   r   joinmapstrZLXML_VERSIONImportErrorr	   hasattrr   r   	Exception	traceback	print_excZprettify)
dataZbasic_parsersnamebuilderr   er	   parsersuccesssoup r%   U/var/www/html/software/conda/envs/catlas/lib/python3.10/site-packages/bs4/diagnose.pydiagnose   sl   





r'   Tc                 K   sp   ddl m} |dd}t| tr| d} t| }|j|f||d|D ]\}}td||j	|j
f  q&dS )	a  Print out the lxml events that occur during parsing.

    This lets you see how lxml parses a document when no Beautiful
    Soup code is running. You can use this to determine whether
    an lxml-specific problem is in Beautiful Soup's lxml tree builders
    or in lxml itself.

    :param data: Some markup.
    :param html: If True, markup will be parsed with lxml's HTML parser.
       if False, lxml's XML parser will be used.
    r   r   recoverTutf8)htmlr(   z%s, %4s, %sN)r
   r   pop
isinstancer   encoder   Z	iterparser   tagtext)r   r*   kwargsr   r(   readereventelementr%   r%   r&   
lxml_traceN   s   

r4   c                   @   s`   e Zd ZdZdd Zdd Zdd Zdd	 Zd
d Zdd Z	dd Z
dd Zdd Zdd ZdS )AnnouncingParserzSubclass of HTMLParser that announces parse events, without doing
    anything else.

    You can use this to get a picture of how html.parser sees a given
    document. The easiest way to do this is to call `htmlparser_trace`.
    c                 C   s   t | d S )N)r   )selfsr%   r%   r&   _pl   s   zAnnouncingParser._pc                 C      |  d|  d S )Nz%s STARTr8   )r6   r   attrsr%   r%   r&   handle_starttago      z AnnouncingParser.handle_starttagc                 C   r9   )Nz%s ENDr:   r6   r   r%   r%   r&   handle_endtagr   r=   zAnnouncingParser.handle_endtagc                 C   r9   )Nz%s DATAr:   r6   r   r%   r%   r&   handle_datau   r=   zAnnouncingParser.handle_datac                 C   r9   )Nz
%s CHARREFr:   r>   r%   r%   r&   handle_charrefx   r=   zAnnouncingParser.handle_charrefc                 C   r9   )Nz%s ENTITYREFr:   r>   r%   r%   r&   handle_entityref{   r=   z!AnnouncingParser.handle_entityrefc                 C   r9   )Nz
%s COMMENTr:   r@   r%   r%   r&   handle_comment~   r=   zAnnouncingParser.handle_commentc                 C   r9   )Nz%s DECLr:   r@   r%   r%   r&   handle_decl   r=   zAnnouncingParser.handle_declc                 C   r9   )Nz%s UNKNOWN-DECLr:   r@   r%   r%   r&   unknown_decl   r=   zAnnouncingParser.unknown_declc                 C   r9   )Nz%s PIr:   r@   r%   r%   r&   	handle_pi   r=   zAnnouncingParser.handle_piN)__name__
__module____qualname____doc__r8   r<   r?   rA   rB   rC   rD   rE   rF   rG   r%   r%   r%   r&   r5   d   s    r5   c                 C   s   t  }||  dS )zPrint out the HTMLParser events that occur during parsing.

    This lets you see how HTMLParser parses a document when no
    Beautiful Soup code is running.

    :param data: Some markup.
    N)r5   feed)r   r"   r%   r%   r&   htmlparser_trace   s   rM   ZaeiouZbcdfghjklmnpqrstvwxyz   c                 C   s:   d}t | D ]}|d dkrt}nt}|t|7 }q|S )z#Generate a random word-like string.    r   )range_consonants_vowelsrandomchoice)lengthr7   itr%   r%   r&   rword   s   rY      c                 C   s   d dd t| D S )z'Generate a random sentence-like string. c                 s   s     | ]}t td dV  qdS )rZ   	   N)rY   rT   randint).0rW   r%   r%   r&   	<genexpr>   s    zrsentence.<locals>.<genexpr>)r   rQ   )rV   r%   r%   r&   	rsentence   s   r`     c                 C   s   g d}g }t | D ]9}tdd}|dkr#t|}|d|  q
|dkr3|ttdd q
|dkrCt|}|d|  q
d	d
| d S )z+Randomly generate an invalid HTML document.)pdivspanrW   bscripttabler      z<%s>   rZ   rP   z</%s>z<html>
z</html>)rQ   rT   r]   rU   r   r`   r   )num_elementsZ	tag_nameselementsrW   rU   Ztag_namer%   r%   r&   rdoc   s   

rm   順 c           
      C   s&  t dt  t| }t dt|  dddgddfD ]>}d}zt }t||}t }d}W n tyK } zt d	|  t  W Y d
}~nd
}~ww |rXt d||| f  qddl	m
} t }|| t }t d||   dd
l}	|	 }t }|| t }t d||   d
S )z.Very basic head-to-head performance benchmark.z1Comparative parser benchmark on Beautiful Soup %sz3Generated a large invalid HTML document (%d bytes).r
   r*   r	   r   FTr   Nz"BS4+%s parsed the markup in %.2fs.r   r   z$Raw lxml parsed the markup in %.2fs.z(Raw html5lib parsed the markup in %.2fs.)r   r   rm   lentimer   r   r   r   r
   r   HTMLr	   r   parse)
rk   r   r"   r#   ar$   re   r!   r   r	   r%   r%   r&   benchmark_parsers   s:   


rt   r
   c                 C   sX   t  }|j}t| }tt||d}td||| t	|}|
d |dd dS )z7Use Python's profiler on a randomly generated document.)bs4r   r"   zbs4.BeautifulSoup(data, parser)Z
cumulativez_html5lib|bs42   N)tempfileNamedTemporaryFiler   rm   dictru   cProfileZrunctxpstatsZStatsZ
sort_statsZprint_stats)rk   r"   Z
filehandlefilenamer   varsstatsr%   r%   r&   profile   s   

r   __main__)T)rN   )rZ   )ra   )rn   )rn   r
   )!rK   __license__rz   ior   html.parserr   ru   r   r   Zbs4.builderr   osr{   rT   rw   rp   r   r   r'   r4   r5   rM   rS   rR   rY   r`   rm   rt   r   rH   stdinr   r%   r%   r%   r&   <module>   s<    
8&




 