xapian-applications/omega/xmlparse.h

   1 /** @file
   2  * @brief Extract text from Abiword documents.
   3  */
   4 /* Copyright (C) 2020 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (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 USA
  19  */
  20
  21 #ifndef OMEGA_INCLUDED_XMLPARSE_H
  22 #define OMEGA_INCLUDED_XMLPARSE_H
  23
  24 #include "myhtmlparse.h"
  25
  26 class XmlParser : public MyHtmlParser {
  27   public:
  28     XmlParser() : MyHtmlParser() { }
  29     bool opening_tag(const string &tag);
  30     bool closing_tag(const string &tag);
  31     void parse_xml(const string &text) {
  32         // Ignore overriding charsets in meta tags.
  33         MyHtmlParser::parse_html(text, "utf-8", true);
  34     }
  35 };
  36
  37 #endif // OMEGA_INCLUDED_XMLPARSE_H