.\" This is a wxWidgets manpage page generated from the XML docs
.TH wxHtmlParser 3wx 2005-02-15 "wxWidgets" "wxWidgets class documentation"
.SH NAME
wxHtmlParser \- 
  Generic HTML parser class
 
.SH DESCRIPTION

  


   Classes derived from this handle the
   
    generic
   
   parsing of HTML documents: it scans the document and divide it into blocks of
   tags (where one block consists of beginning and ending tag and of text
   between these two tags).
  
  


   It is independent from wxHtmlWindow and can be used as stand-alone parser
   (Julian Smart's idea of speech-only HTML viewer or wget-like utility - see
   InetGet sample for example).
  
  


   It uses system of tag handlers to parse the HTML document. Tag handlers are
   not statically shared by all instances but are created for each wxHtmlParser
   instance. The reason is that the handler may contain document-specific
   temporary data used during parsing (e.g. complicated structures like tables).
  
  


   Typically the user calls only the
   Parse
   method.
  
 
.SH "PARENTS"

  wxObject
 
.SH "INCLUDE FILES"
wx/html/htmlpars.h
.SH MEMBERS

  
.SS  wxHtmlParser ()

     


      Constructor.
     
    
   
  
.SS void AddTag (const wxHtmlTag& tag)

     


      This may (and may not) be overwritten in derived class.
     
     


      This method is called each time new tag is about to be added.
      
       tag
      
      contains information about the tag. (See
      wxHtmlTag
      for details.)
     
     


      Default (wxHtmlParser) behaviour is this: First it finds a handler capable
      of handling this tag and then it calls handler's HandleTag method.
     
    
   
  
.SS virtual void AddTagHandler (wxHtmlTagHandler *handler)

     


      Adds handler to the internal list (& hash table) of handlers. This
      method should not be called directly by user but rather by derived class'
      constructor.
     
     


      This adds the handler to this
      
       instance
      
      of wxHtmlParser, not to all objects of this class! (Static front-end to
      AddTagHandler is provided by wxHtmlWinParser).
     
     


      All handlers are deleted on object deletion.
     
    
   
  
.SS virtual void AddWord (const char* txt)

     


      Must be overwritten in derived class.
     
     


      This method is called by
      DoParsing
      each time a part of text is parsed.
      
       txt
      
      is NOT only one word, it is substring of input. It is not formatted or
      preprocessed (so white spaces are unmodified).
     
    
   
  
.SS void DoParsing (int begin_posint end_pos)

.SS void DoParsing ()

     


      Parses the m_Source from begin_pos to end_pos-1. (in noparams version it
      parses whole m_Source)
     
    
   
  
.SS virtual void DoneParser ()

     


      This must be called after DoParsing().
     
    
   
  
.SS wxFileSystem* GetFS ()

     


      Returns pointer to the file system. Because each tag handler has reference
      to it is parent parser it can easily request the file by calling
     
     
wxFSFile *f = m_Parser -> GetFS() -> OpenFile("image.jpg");

    
   
  
.SS virtual wxObject* GetProduct ()

     


      Returns product of parsing. Returned value is result of parsing of the
      document. The type of this result depends on internal representation in
      derived parser (but it must be derived from wxObject!).
     
     


      See wxHtmlWinParser for details.
     
    
   
  
.SS wxString* GetSource ()

     


      Returns pointer to the source being parsed.
     
    
   
  
.SS virtual void InitParser (const wxString& source)

     


      Setups the parser for parsing the
      
       source
      
      string. (Should be overridden in derived class)
     
    
   
  
.SS virtual wxFSFile* OpenURL (wxHtmlURLType typeconst wxString& url)

     


      Opens given URL and returns
      wxFSFile
      object that can be used to read data from it. This method may return NULL
      in one of two cases: either the URL doesn't point to any valid resource or
      the URL is blocked by overridden implementation of
      
       OpenURL
      
      in derived class.
     
    
   
  
.SS wxObject* Parse (const wxString& source)

     


      Proceeds parsing of the document. This is end-user method. You can simply
      call it when you need to obtain parsed output (which is parser-specific)
     
     


      The method does these things:
     
     


      
       calls
        InitParser(source)
        
       calls
        DoParsing
        
       calls
        GetProduct
        
       calls
        DoneParser
        
       returns value returned by GetProduct
      
     
     


      You shouldn't use InitParser, DoParsing, GetProduct or DoneParser
      directly.
     
    
   
  
.SS void PushTagHandler (wxHtmlTagHandler* handlerconst wxString& tags)

     


      Forces the handler to handle additional tags (not returned by
      GetSupportedTags
      ). The handler should already be added to this parser.
     
    
   
  
.SS void PopTagHandler ()

     


      Restores parser's state before last call to
      PushTagHandler
      .
     
    
   
  
.SS void SetFS (wxFileSystem *fs)

     


      Sets the virtual file system that will be used to request additional
      files. (For example
      <IMG>
      tag handler requests wxFSFile with the image data.)
     
    
   
  
.SS void StopParsing ()

     


      Call this function to interrupt parsing from a tag handler. No more tags
      will be parsed afterward. This function may only be called from
      wxHtmlParser::Parse
      or any function called by it (i.e. from tag handlers).
     
    
 
.SH "SEE ALSO"

  wxObject
 
  Cells Overview
  , 
  Tag Handlers Overview
  , 
  wxHtmlTag
 
.SH "AUTHORS"
Documentation content by Julian Smart, Robert Roebling, Vadim Zeitlin, Robin Dunn, et al

Conversion to manpage format by Arnout Engelen (http://bzzt.net), bugreports welcome.