U
    }g(                     @  sH  U d dl mZ d dlmZmZmZmZmZmZm	Z	m
Z
 d dlmZ d dlmZ e	r^d dlmZ G dd deZG dd	 d	eZG d
d deZeejdejd< eejdddejd< eejdddejd< eejdejd< eddejd< eejdejd< eejdejd< eddejd< eegef Zded< e
eef ZdS )    )annotations)CallableDictIterableOptionalSetTupleTYPE_CHECKINGUnion)	TypeAlias)EntitySubstitution)_AttributeValuec                   @  s   e Zd ZU dZdZded< dZded< eeddgd	Z	d
ed< ded< ded< ded< ded< ded< ded< dddddddZ
d-dddddddd d!Zddd"d#d$Zddd%d&d'Zd(d)d*d+d,ZdS ).	Formattera  Describes a strategy to use when outputting a parse tree to a string.

    Some parts of this strategy come from the distinction between
    HTML4, HTML5, and XML. Others are configurable by the user.

    Formatters are passed in as the `formatter` argument to methods
    like `bs4.element.Tag.encode`. Most people won't need to
    think about formatters, and most people who need to think about
    them can pass in one of these predefined strings as `formatter`
    rather than making a new Formatter object:

    For HTML documents:
     * 'html' - HTML entity substitution for generic HTML documents. (default)
     * 'html5' - HTML entity substitution for HTML5 documents, as
                 well as some optimizations in the way tags are rendered.
     * 'html5-4.12.0' - The version of the 'html5' formatter used prior to
                        Beautiful Soup 4.13.0.
     * 'minimal' - Only make the substitutions necessary to guarantee
                   valid HTML.
     * None - Do not perform any substitution. This will be faster
              but may result in invalid markup.

    For XML documents:
     * 'html' - Entity substitution for XHTML documents.
     * 'minimal' - Only make the substitutions necessary to guarantee
                   valid XML. (default)
     * None - Do not perform any substitution. This will be faster
              but may result in invalid markup.

    htmlstrHTMLxmlXMLscriptstyle)cdata_containing_tagszDict[str, Set[str]]HTML_DEFAULTSzOptional[str]language%Optional[_EntitySubstitutionFunction]entity_substitutionvoid_element_close_prefixzSet[str]r   indentboolempty_attributes_are_booleansOptional[Set[str]])r   valuekwargreturnc                 C  s&   |d k	r|S || j krt S | j| S )N)r   setr   )selfr   r    r!    r%   1/tmp/pip-unpacked-wheel-kgiupv3k/bs4/formatter.py_defaultB   s
    
zFormatter._defaultN/F   Union[int, str])r   r   r   r   r   r   c                 C  sz   |p| j | _|| _|| _| | j|d| _|| _|dkr<d}t|tr\|dk rRd}d| }nt|t	rl|}nd}|| _
dS )a  Constructor.

        :param language: This should be `Formatter.XML` if you are formatting
           XML markup and `Formatter.HTML` if you are formatting HTML markup.

        :param entity_substitution: A function to call to replace special
           characters with XML/HTML entities. For examples, see
           bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
        :param void_element_close_prefix: By default, void elements
           are represented as <tag/> (XML rules) rather than <tag>
           (HTML rules). To get <tag>, pass in the empty string.
        :param cdata_containing_tags: The set of tags that are defined
           as containing CDATA in this dialect. For example, in HTML,
           <script> and <style> tags are defined as containing CDATA,
           and their contents should not be formatted.
        :param empty_attributes_are_booleans: If this is set to true,
          then attributes whose values are sent to the empty string
          will be treated as `HTML boolean
          attributes<https://dev.w3.org/html5/spec-LC/common-microsyntaxes.html#boolean-attributes>`_. (Attributes
          whose value is None are always rendered this way.)
        :param indent: If indent is a non-negative integer or string,
            then the contents of elements will be indented
            appropriately when pretty-printing. An indent level of 0,
            negative, or "" will only insert newlines. Using a
            positive integer indent indents that many spaces per
            level. If indent is a string (such as "\t"), that string
            is used to indent each level. The default behavior is to
            indent one space per level.

        r   Nr    )r   r   r   r   r'   r   r   
isinstanceintr   r   )r$   r   r   r   r   r   r   Z
indent_strr%   r%   r&   __init__O   s&    '  


zFormatter.__init__)nsr"   c                 C  sF   | j s
|S ddlm} t||r<|jdk	r<|jj| jkr<|S |  |S )a$  Process a string that needs to undergo entity substitution.
        This may be a string encountered in an attribute value or as
        text.

        :param ns: A string.
        :return: The same string but with certain characters replaced by named
           or numeric entities.
        r)   )NavigableStringN)r   elementr0   r,   parentnamer   )r$   r/   r0   r%   r%   r&   
substitute   s    	zFormatter.substitute)r    r"   c                 C  s
   |  |S )zProcess the value of an attribute.

        :param ns: A string.
        :return: A string with certain characters replaced by named
           or numeric entities.
        )r4   )r$   r    r%   r%   r&   attribute_value   s    zFormatter.attribute_valuezbs4.element.Tagz/Iterable[Tuple[str, Optional[_AttributeValue]]])tagr"   c                   s2   |j dkrg S t|j  }t fdd|D S )a  Reorder a tag's attributes however you want.

        By default, attributes are sorted alphabetically. This makes
        behavior consistent between Python 2 and Python 3, and preserves
        backwards compatibility with older versions of Beautiful Soup.

        If `empty_attributes_are_booleans` is True, then
        attributes whose values are set to the empty string will be
        treated as boolean attributes.
        Nc                 3  s,   | ]$\}}| j r|d krdn|fV  qdS ) N)r   ).0kvr$   r%   r&   	<genexpr>   s   z'Formatter.attributes.<locals>.<genexpr>)attrslistitemssorted)r$   r6   r?   r%   r;   r&   
attributes   s    
zFormatter.attributes)NNr(   NFr)   )__name__
__module____qualname____doc__r   __annotations__r   dictr#   r   r'   r.   r4   r5   rA   r%   r%   r%   r&   r   
   s.   
 
      ;	r   c                      s>   e Zd ZU dZi Zded< ddd	d
ddd fddZ  ZS )HTMLFormatterzA generic Formatter for HTML.z"Dict[Optional[str], HTMLFormatter]REGISTRYNr(   Fr)   r   r   r   r   r*   r   r   r   r   r   c                   s"   t t| j| j|||||d d S N)r   )superrH   r.   r   r$   r   r   r   r   r   	__class__r%   r&   r.      s    
zHTMLFormatter.__init__)Nr(   NFr)   rB   rC   rD   rE   rI   rF   r.   __classcell__r%   r%   rN   r&   rH      s   
     rH   c                      s>   e Zd ZU dZi Zded< ddd	d
ddd fddZ  ZS )XMLFormatterzA generic Formatter for XML.z!Dict[Optional[str], XMLFormatter]rI   Nr(   Fr)   r   r   r   r   r*   rJ   c                   s"   t t| j| j|||||d d S rK   )rL   rR   r.   r   rM   rN   r%   r&   r.      s    
zXMLFormatter.__init__)Nr(   NFr)   rP   r%   r%   rN   r&   rR      s   
     rR   )r   r   r7   T)r   r   r   html5z
html5-4.12ZminimalNr   _EntitySubstitutionFunction)
__future__r   typingr   r   r   r   r   r   r	   r
   Ztyping_extensionsr   Z
bs4.dammitr   Zbs4._typingr   r   rH   rR   Zsubstitute_htmlrI   Zsubstitute_html5Zsubstitute_xmlr   rT   rF   Z_FormatterOrNamer%   r%   r%   r&   <module>   sH    ( 8