xapian-applications/omega/xlsxparser.h

   1 /** @file
   2  * @brief Extract fields from XLSX sheet*.xml.
   3  */
   4 /* Copyright (C) 2012,2013,2019 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_XLSXPARSER_H
  22 #define OMEGA_INCLUDED_XLSXPARSER_H
  23
  24 #include "xmlparser.h"
  25
  26 #include <vector>
  27 #include <set>
  28 #include <string>
  29
  30 class XlsxParser : public XmlParser {
  31     std::vector<std::string> sst;
  32     std::set<unsigned> date_style;
  33     std::set<unsigned long> date_format;
  34
  35     enum {
  36         MODE_NONE,
  37         MODE_SI,
  38         MODE_C_STRING,
  39         MODE_V_STRING,
  40         MODE_C_LITERAL,
  41         MODE_V_LITERAL,
  42         MODE_C_DATE,
  43         MODE_V_DATE,
  44         MODE_CELLXFS
  45     } mode = MODE_NONE;
  46
  47     bool date1904 = false;
  48
  49     unsigned style_index = 0;
  50
  51     void append_field(const std::string& text) {
  52         if (!text.empty()) {
  53             if (!dump.empty()) dump += ' ';
  54             dump += text;
  55         }
  56     }
  57
  58   public:
  59     std::string dump;
  60
  61     XlsxParser() { }
  62     bool opening_tag(const std::string& tag);
  63     void process_content(const std::string& content);
  64 };
  65
  66 #endif // OMEGA_INCLUDED_XLSXPARSER_H