htmlparse.h

   1 /* htmlparse.cc: simple HTML parser for omega indexer
   2  *
   3  * ----START-LICENCE----
   4  * Copyright 1999,2000,2001 BrightStation PLC
   5  * Copyright 2002 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307
  20  * USA
  21  * -----END-LICENCE-----
  22  */
  23
  24 #include <string>
  25 #include <map>
  26
  27 using std::string;
  28 using std::map;
  29
  30 class HtmlParser {
  31     protected:
  32         void decode_entities(string &s);
  33         static map<string, unsigned int> named_ents;
  34     public:
  35         virtual void process_text(const string &/*text*/) { }
  36         virtual void opening_tag(const string &/*tag*/,
  37                                  const map<string,string> &/*p*/) { }
  38         virtual void closing_tag(const string &/*tag*/) { }
  39         virtual void parse_html(const string &text);
  40         HtmlParser();
  41         virtual ~HtmlParser() { }
  42 };