xapian-applications/omega/metaxmlparse.cc

   1 /** @file
   2  * @brief Parser for OpenDocument's meta.xml.
   3  */
   4 /* Copyright (C) 2006,2009,2010,2011,2013,2015,2020 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 #include <config.h>
  22
  23 #include "metaxmlparse.h"
  24
  25 #include "datetime.h"
  26
  27 using namespace std;
  28
  29 void
  30 MetaXmlParser::process_text(const string &text)
  31 {
  32     switch (field) {
  33         case KEYWORDS:
  34             if (!keywords.empty()) keywords += ' ';
  35             keywords += text;
  36             break;
  37         case TITLE:
  38             if (!title.empty()) title += ' ';
  39             title += text;
  40             break;
  41         case SAMPLE:
  42             if (!sample.empty()) sample += ' ';
  43             sample += text;
  44             break;
  45         case AUTHOR:
  46             if (!author.empty()) author += ' ';
  47             author += text;
  48             break;
  49         case TOPIC:
  50             if (!topic.empty()) topic += ' ';
  51             topic += text;
  52             break;
  53         case CREATED: {
  54             // E.g. 2013-03-04T22:57:00
  55             created = parse_datetime(text);
  56             break;
  57         }
  58         case NONE:
  59             // Ignore other fields.
  60             break;
  61     }
  62 }
  63
  64 bool
  65 MetaXmlParser::opening_tag(const string &tag)
  66 {
  67     if (tag.size() < 8) return true;
  68     if (tag[0] == 'd' && tag[1] == 'c') {
  69         if (tag == "dc:subject") {
  70             // dc:subject is "Subject and Keywords":
  71             // "Typically, Subject will be expressed as keywords, key phrases
  72             // or classification codes that describe a topic of the resource."
  73             // OpenOffice uses meta:keywords for keywords - dc:subject
  74             // comes from a text field labelled "Subject".  Let's just treat
  75             // it as more keywords.
  76             field = KEYWORDS;
  77         } else if (tag == "dc:title") {
  78             field = TITLE;
  79         } else if (tag == "dc:description") {
  80             field = SAMPLE;
  81         } else if (tag == "dc:creator") {
  82             field = AUTHOR;
  83         } else if (tag == "dc:subject") {
  84             field = TOPIC;
  85         }
  86     } else if (tag[0] == 'm') {
  87         if (tag == "meta:keyword") {
  88             // e.g.:
  89             // <meta:keywords>
  90             // <meta:keyword>information retrieval</meta:keyword>
  91             // </meta:keywords>
  92             field = KEYWORDS;
  93         } else if (tag == "meta:creation-date") {
  94             field = CREATED;
  95         }
  96     }
  97     return true;
  98 }
  99
 100 bool
 101 MetaXmlParser::closing_tag(const string &)
 102 {
 103     field = NONE;
 104     return true;
 105 }