Revonzy Mini Shell

a

�DOg�C�@s�dZd
dl
Z
d
dlZd
dlmZ
dg
Ze
�d�
Ze
�d�
Ze
�d�
Z	e
�d�
Z
e
�d	�
Ze
�d
�
Ze
�d�
Z
e
�d�
Ze
�d
�
Ze
�de
j�Ze
�d
�
Ze
�d�
ZGdd�dej�ZdS)zA parser for HTML and XHTML.�N)
�unescape�
HTMLParserz[&<]z
&[a-zA-Z#]z%&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]z)&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]z	<[a-zA-Z]�
>z--\s*>z+([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*z]((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*aF
  <[a-zA-Z][^\t\n\r\f />\x00]*       # tag name
  (?:[\s/]*                          # optional whitespace before attribute name
    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
      (?:\s*=+\s*                    # value indicator
        (?:'[^']*'                   # LITA-enclosed value
          |"[^"]*"                   # LIT-enclosed value
          |(?!['"])[^>\s]*           # bare value
         )
        \s*                          # possibly followed by a space
       )?(?:\s|/(?!>))*
     )*
   )?
  \s*                                # trailing whitespace
z#</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>c@s�eZ
dZd
ZdZdd�
dd�Zdd�Zd	d
�Zdd�Zd
Z	dd�Z
dd�Zdd�Zdd�Z
dd�Zd7dd�
Zdd�Zdd�Zdd �Zd!d"�Zd#d$�Zd%d&�Zd'd(�Zd)d*�Zd+d,�Zd-d.�Zd/d0�Zd1d2�Zd3d4�Zd5d6�Zd
S)8raEFind tags and other markup and call handler functions.

    Usage:
        p = HTMLParser()
        p.feed(data)
        ...
        p.close()

    Start tags are handled by calling self.handle_starttag() or
    self.handle_startendtag(); end tags by self.handle_endtag().  The
    data between tags is passed from the parser to the derived class
    by calling self.handle_data() with the data as argument (the data
    may be split up in arbitrary chunks).  If convert_charrefs is
    True the character references are converted automatically to the
    corresponding Unicode character (and self.handle_data() is no
    longer split in chunks), otherwise they are passed by calling
    self.handle_entityref() or self.handle_charref() with the string
    containing respectively the named or numeric reference as the
    argument.
    )Zscript�styleT)
�convert_charrefsc

Cs|
|_|�
�
d
S)z�Initialize and reset this instance.

        If convert_charrefs is True (the default), all character references
        are automatically converted to the corresponding Unicode characters.
        N)r�reset)�selfr�r	�#/usr/lib64/python3.9/html/parser.py�__init__Vs
zHTMLParser.__init__c

Cs(d
|_d|_
t|_d|_tj�|�

dS)z1Reset this instance.  Loses all unprocessed data.�z???N)�rawdata�lasttag�interesting_normal�interesting�
cdata_elem�_markupbase�
ParserBaser�
rr	r	r
r_s




zHTMLParser.resetcCs|j|
|_|�
d
�

dS)z�Feed data to the parser.

        Call this as often as you want, with as little or as much text
        as you want (may include '\n').
        r
N)r
�goahead�r�datar	r	r
�feedgs
zHTMLParser.feedc

Cs|�d
�

dS)zHandle any buffered data.�
N)
rrr	r	r
�closepszHTMLParser.closeNc


Cs|jS)
z)Return full source of start tag: '<...>'.)
�_HTMLParser__starttag_textrr	r	r
�get_starttag_textvszHTMLParser.get_starttag_textcCs$|
��|_
t�d
|j
tj�|_dS)Nz</\s*%s\s*>)�lowerr�re�compile�
Ir)r�elemr	r	r
�set_cdata_modezs


zHTMLParser.set_cdata_modec

Cst|_
d|_dS�
N)rrrrr	r	r
�clear_cdata_mode~s

zHTMLParser.clear_cdata_modecCsJ|j}d
}t
|�
}||k�r�|jrv|jsv|�d|�}|d
kr�|�dt||d��}|d
krpt�d�
�	||�sp�q�|}n*|j
�	||�}|r�|��}n|jr��q�|}||kr�|jr�|js�|�t
|||��
�

n|�|||��

|�||�}||kr��q�|j}|d|��rJt�||��
r"|�|�
}	n�|d|��
r:|�|�
}	nn|d|��
rR|�|�
}	nV|d|��
rj|�|�
}	n>|d	|��
r�|�|�
}	n&|d
|k�r�|�d�

|d
}	n�q�|	d
k�r<|
�
s��q�|�d|d
�}	|	d
k�
r�|�d|d
�}	|	d
k�r|d
}	n|	d
7}	|j�r*|j�s*|�t
|||	��
�

n|�|||	��

|�||	�}q|d|��r�t�||�}|�r�|��d
d�}
|�|
�

|��}	|d|	d
��s�|	d
}	|�||	�}qn<d||d�v�r�|�|||d
��

|�||d
�}�q�q|d|�rt�||�}|�rN|�d
�
}
|�|
�

|��}	|d|	d
��s@|	d
}	|�||	�}qt�||�}|�r�|
�r�|��||d�k�r�|��}	|	|k
�r�|}	|�||d
�}�q�n.|d
|k�r�|�d�

|�||d
�}n�q�qq|
�r8||k�r8|j�s8|j�r|j�s|�t
|||��
�

n|�|||��

|�||�}||d�|_dS)Nr
�
<�
&�"z[\s;]z</�<!--z<?z<!rrz&#�����
;)r
�lenrr�find�rfind�maxrr�searchr�start�handle_datarZ	updatepos�
startswith�starttagopen�match�parse_starttag�parse_endtag�
parse_comment�parse_pi�parse_html_declaration�charref�group�handle_charref�end�	entityref�handle_entityref�
incomplete)rr>r
�
i�
n�
jZampposr5r3�
k�namer	r	r
r�s�









�



















































































zHTMLParser.goaheadcCs�|j}||
|
d
�dkr$|�
|
�
S||
|
d�dkrB|�|
�
S||
|
d���dkr�|�d|
d�}|dkrvdS|�||
d	|��

|d
S|�|
�
SdS)N�r(�z<![�	z	<!doctyperr*r)r)r
r8Zparse_marked_sectionrr-�handle_decl�parse_bogus_comment)rrBr
�gtposr	r	r
r:�s









z!HTMLParser.parse_html_declarationrcCsD|j}|�
d
|
d�}|dkr"dS|r<|�||
d|��

|dS)Nrr)r*r)r
r-�handle_comment)rrB�reportr
�posr	r	r
rK
s





zHTMLParser.parse_bogus_commentcCsH|j}t
�||
d
�}|sdS|��}|�||
d
|��

|��}|S)Nr)r*)r
�picloser0r1�	handle_pir>)rrBr
r5rDr	r	r
r9 
s






zHTMLParser.parse_picCs�
d|_|�
|
�
}|d
kr|S|j}||
|�|_g}t�||
d�}|��}|�d�
��|_}||k�
r t	�||�}|s~�
q |�ddd�\}	}
}|
s�d}nZ|dd�dkr�|dd�ks�n
|dd�dkr�|dd�kr�n
n|dd�}|�
rt
|�
}|�|	��|f�

|��}q`|||���}|dv
�
r�|�
�\}
}d	|jv�
rz|
|j�d	�
}
t|j�
|j�d	�
}n|t|j�
}|�||
|��

|S|�d
�
�
r�|�||�
n"|�||�
||jv�
r�|�|�

|S)Nr
rr)rH�
'r*�
")r�/>�

rT)r�check_for_whole_start_tagr
�tagfind_tolerantr5r>r<rr�attrfind_tolerantr�append�stripZgetpos�countr,r.r2�endswith�handle_startendtag�handle_starttag�CDATA_CONTENT_ELEMENTSr")rrB�endposr
�attrsr5rE�tag�
m�attrname�restZ	attrvaluer>�lineno�offsetr	r	r
r6,
sX

















&
�

�













�






zHTMLParser.parse_starttagcCs�|j}t
�||
�}|r�|��}|||d
�}|dkr>|d
S|dkr~|�d|�rZ|dS|�d|�rjdS||
krv|S|
d
S|dkr�dS|dvr�dS||
kr�|S|
d
Std	�
�
dS)
Nrr�
/rTr)r*rz6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r
�locatestarttagend_tolerantr5r>r3�AssertionError)rrBr
rcrD�nextr	r	r
rV_
s.
















z$HTMLParser.check_for_whole_start_tagcCs
|j}t
�||
d
�}|sdS|��}t�||
�}|s�|jdu
rV|�||
|��

|St�||
d�}|s�||
|
d�dkr�|
dS|�	|
�
S|�
d
�
��}|�d|���}|�
|�

|d
S|�
d
�
��}|jdu
r�||jkr�|�||
|��

|S|�
|�

|��
|S)Nrr*r)rHz</>r)r
�	endendtagr0r>�
endtagfindr5rr2rWrKr<rr-�
handle_endtagr$)rrBr
r5rLZ	namematchZtagnamer!r	r	r
r7�
s6

























zHTMLParser.parse_endtagcCs|�|
|�
|�
|
�

dSr#)r^rn�rrbrar	r	r
r]�
s

zHTMLParser.handle_startendtagc
CsdSr#r	ror	r	r
r^�
s
zHTMLParser.handle_starttagc
CsdSr#r	)rrbr	r	r
rn�
s
zHTMLParser.handle_endtagc
CsdSr#r	�rrFr	r	r
r=�
s
zHTMLParser.handle_charrefc
CsdSr#r	rpr	r	r
r@�
s
zHTMLParser.handle_entityrefc
CsdSr#r	rr	r	r
r2�
s
zHTMLParser.handle_datac
CsdSr#r	rr	r	r
rM�
s
zHTMLParser.handle_commentc
CsdSr#r	)rZdeclr	r	r
rJ�
s
zHTMLParser.handle_declc
CsdSr#r	rr	r	r
rQ�
s
zHTMLParser.handle_pic
CsdSr#r	rr	r	r
�unknown_decl�
s
zHTMLParser.unknown_decl)
r)�__name__�
__module__�__qualname__�__doc__r_rrrrrrr"r$rr:rKr9r6rVr7r]r^rnr=r@r2rMrJrQrqr	r	r	r
r>s6
		z
3"()rurrZhtmlr�__all__rrrAr?r;r4rPZcommentcloserWrX�VERBOSErirlrmrrr	r	r	r
�<module>
s*















��