xapian-applications/omega/xlsxparse.h

   1 /** @file
   2  * @brief Extract fields from XLSX sheet*.xml.
   3  */
   4 /* Copyright (C) 2012,2013 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_XLSXPARSE_H
  22 #define OMEGA_INCLUDED_XLSXPARSE_H
  23
  24 #include "htmlparse.h"
  25
  26 #include <vector>
  27 #include <set>
  28
  29 class XlsxParser : public HtmlParser {
  30     std::vector<std::string> sst;
  31     std::set<unsigned> date_style;
  32     std::set<unsigned long> date_format;
  33
  34     enum {
  35         MODE_NONE,
  36         MODE_SI,
  37         MODE_C_STRING,
  38         MODE_V_STRING,
  39         MODE_C_LITERAL,
  40         MODE_V_LITERAL,
  41         MODE_C_DATE,
  42         MODE_V_DATE,
  43         MODE_CELLXFS
  44     } mode;
  45
  46     bool date1904;
  47     unsigned style_index;
  48
  49     void append_field(const std::string &text) {
  50         if (!text.empty()) {
  51             if (!dump.empty()) dump += ' ';
  52             dump += text;
  53         }
  54     }
  55
  56   public:
  57     std::string dump;
  58
  59     XlsxParser()
  60         : HtmlParser(), mode(MODE_NONE), date1904(false), style_index(0) { }
  61     bool opening_tag(const std::string &tag);
  62     void process_text(const std::string &text);
  63 };
  64
  65 #endif // OMEGA_INCLUDED_XLSXPARSE_H