xapian-applications/omega/opendocparse.cc

   1 /** @file opendocparse.cc
   2  * @brief Extract text from XML from an OpenDocument document.
   3  */
   4 /* Copyright (C) 2012 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 #include <config.h>
  22
  23 #include "opendocparse.h"
  24
  25 using namespace std;
  26
  27 bool
  28 OpenDocParser::opening_tag(const string &tag)
  29 {
  30     if (tag == "office:body") {
  31         indexing = true;
  32     } else if (tag == "style:style") {
  33         (void)get_parameter("style:master-page-name", master_page_name);
  34     } else if (tag == "style:master-page") {
  35         string n;
  36         if (get_parameter("style:name", n) && n == master_page_name)
  37             indexing = true;
  38     }
  39     return true;
  40 }
  41
  42 bool
  43 OpenDocParser::closing_tag(const string &tag)
  44 {
  45     if (!indexing)
  46         return true;
  47
  48     if (tag == "text:p") {
  49         pending_space = true;
  50     } else if (tag == "office:body" || tag == "style:style") {
  51         indexing = false;
  52     }
  53     return true;
  54 }
  55
  56 void
  57 OpenDocParser::process_text(const string &text)
  58 {
  59     if (indexing && !text.empty()) {
  60         if (pending_space) {
  61             pending_space = false;
  62             dump += ' ';
  63         }
  64         dump += text;
  65     }
  66 }