xapian-applications/omega/metaxmlparse.cc

   1 /* metaxmlparse.cc: subclass of HtmlParser for parsing OpenDocument's meta.xml.
   2  *
   3  * Copyright (C) 2006,2009,2010,2011,2013,2015 Olly Betts
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License
  16  * along with this program; if not, write to the Free Software
  17  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  18  */
  19
  20 #include <config.h>
  21
  22 #include "metaxmlparse.h"
  23
  24 #include "datetime.h"
  25
  26 using namespace std;
  27
  28 void
  29 MetaXmlParser::process_text(const string &text)
  30 {
  31     switch (field) {
  32         case KEYWORDS:
  33             if (!keywords.empty()) keywords += ' ';
  34             keywords += text;
  35             break;
  36         case TITLE:
  37             if (!title.empty()) title += ' ';
  38             title += text;
  39             break;
  40         case SAMPLE:
  41             if (!sample.empty()) sample += ' ';
  42             sample += text;
  43             break;
  44         case AUTHOR:
  45             if (!author.empty()) author += ' ';
  46             author += text;
  47             break;
  48         case TOPIC:
  49             if (!topic.empty()) topic += ' ';
  50             topic += text;
  51             break;
  52         case CREATED: {
  53             // E.g. 2013-03-04T22:57:00
  54             created = parse_datetime(text);
  55             break;
  56         }
  57         case NONE:
  58             // Ignore other fields.
  59             break;
  60     }
  61 }
  62
  63 bool
  64 MetaXmlParser::opening_tag(const string &tag)
  65 {
  66     if (tag.size() < 8) return true;
  67     if (tag[0] == 'd' && tag[1] == 'c') {
  68         if (tag == "dc:subject") {
  69             // dc:subject is "Subject and Keywords":
  70             // "Typically, Subject will be expressed as keywords, key phrases
  71             // or classification codes that describe a topic of the resource."
  72             // OpenOffice uses meta:keywords for keywords - dc:subject
  73             // comes from a text field labelled "Subject".  Let's just treat
  74             // it as more keywords.
  75             field = KEYWORDS;
  76         } else if (tag == "dc:title") {
  77             field = TITLE;
  78         } else if (tag == "dc:description") {
  79             field = SAMPLE;
  80         } else if (tag == "dc:creator") {
  81             field = AUTHOR;
  82         } else if (tag == "dc:subject") {
  83             field = TOPIC;
  84         }
  85     } else if (tag[0] == 'm') {
  86         if (tag == "meta:keyword") {
  87             // e.g.:
  88             // <meta:keywords>
  89             // <meta:keyword>information retrieval</meta:keyword>
  90             // </meta:keywords>
  91             field = KEYWORDS;
  92         } else if (tag == "meta:creation-date") {
  93             field = CREATED;
  94         }
  95     }
  96     return true;
  97 }
  98
  99 bool
 100 MetaXmlParser::closing_tag(const string &)
 101 {
 102     field = NONE;
 103     return true;
 104 }