xapian-applications/omega/htmlparse.h

   1 /* htmlparse.h: simple HTML parser for omega indexer
   2  *
   3  * Copyright 1999,2000,2001 BrightStation PLC
   4  * Copyright 2002,2006,2008,2009,2011 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU General Public License as
   8  * published by the Free Software Foundation; either version 2 of the
   9  * License, or (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  19  * USA
  20  */
  21
  22 #ifndef OMEGA_INCLUDED_HTMLPARSE_H
  23 #define OMEGA_INCLUDED_HTMLPARSE_H
  24
  25 #include <string>
  26 #include <map>
  27
  28 using std::string;
  29 using std::map;
  30
  31 class HtmlParser {
  32         map<string, string> parameters;
  33     protected:
  34         void decode_entities(string &s);
  35         bool in_script;
  36         string charset;
  37         static map<string, unsigned int> named_ents;
  38
  39         bool get_parameter(const string & param, string & value) const;
  40     public:
  41         virtual void process_text(const string &/*text*/) { }
  42         virtual bool opening_tag(const string &/*tag*/) { return true; }
  43         virtual bool closing_tag(const string &/*tag*/) { return true; }
  44         virtual void parse(const string &text);
  45         HtmlParser();
  46         virtual ~HtmlParser() { }
  47 };
  48
  49 #endif // OMEGA_INCLUDED_HTMLPARSE_H