xapian-applications/omega/xmlparser.h

   1 /** @file
   2  * @brief XML (and HTML) parser
   3  */
   4 /* Copyright 1999,2000,2001 BrightStation PLC
   5  * Copyright 2002,2006,2008,2009,2011,2016,2020,2023 Olly Betts
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  20  * USA
  21  */
  22
  23 #ifndef OMEGA_INCLUDED_XMLPARSER_H
  24 #define OMEGA_INCLUDED_XMLPARSER_H
  25
  26 #include <string>
  27 #include <string_view>
  28
  29 class XmlParser {
  30     const char* attribute_data;
  31     mutable size_t attribute_len;
  32
  33   protected:
  34     /** Control HTML-specific handling.
  35      *
  36      *  Defaults to XML, which means no HTML-specific handling.
  37      *
  38      *  The HtmlParser subclass overrides this to HTML at construction time,
  39      *  and then it can change to HTML_IN_SCRIPT and back to HTML as we
  40      *  move in and out of parsing script elements.
  41      */
  42     enum { XML, HTML, HTML_IN_SCRIPT } state = XML;
  43
  44     std::string charset;
  45
  46     /// Protected constructor for HtmlParser subclass.
  47     explicit XmlParser(bool) : state(HTML) { }
  48
  49     static void decode_entities(std::string& s);
  50
  51     bool get_attribute(const std::string& name, std::string& value) const;
  52
  53     /** Process an opening tag.
  54      *
  55      *  Return false to stop parsing of the rest of the document.
  56      */
  57     virtual bool opening_tag(const std::string& tag) {
  58         (void)tag;
  59         return true;
  60     }
  61
  62     /** Process a closing tag.
  63      *
  64      *  Return false to stop parsing of the rest of the document.
  65      */
  66     virtual bool closing_tag(const std::string& tag) {
  67         (void)tag;
  68         return true;
  69     }
  70
  71     /// Process text between tags.
  72     virtual void process_content(const std::string& content) {
  73         (void)content;
  74     }
  75
  76   public:
  77     XmlParser() { }
  78
  79     XmlParser(const XmlParser&) = delete;
  80
  81     XmlParser& operator=(const XmlParser&) = delete;
  82
  83     virtual ~XmlParser() { }
  84
  85     void parse(std::string_view text);
  86 };
  87
  88 #endif // OMEGA_INCLUDED_XMLPARSER_H