xapian-applications/omega/svgparser.cc

   1 /** @file
   2  * @brief Extract text from an SVG file.
   3  */
   4 /* Copyright (C) 2010-2022 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 "svgparser.h"
  24 #include "stringutils.h"
  25
  26 using namespace std;
  27
  28 void
  29 SvgParser::process_content(const string& content)
  30 {
  31     string * target = NULL;
  32     switch (state) {
  33         case TEXT:
  34             target = &dump;
  35             break;
  36         case TITLE:
  37             target = &title;
  38             break;
  39         case DC_TITLE:
  40             // Prefer <title> to <dc:title>.
  41             if (!title.empty()) return;
  42             break;
  43         case KEYWORDS:
  44             target = &keywords;
  45             break;
  46         case AUTHOR:
  47             target = &author;
  48             break;
  49         case METADATA: case OTHER:
  50             // Ignore context in other places.
  51             return;
  52     }
  53     if (!target->empty())
  54         *target += ' ';
  55     *target += content;
  56 }
  57
  58 bool
  59 SvgParser::opening_tag(const string& tag)
  60 {
  61     switch (state) {
  62         case OTHER:
  63             if (tag == "text" || tag == "svg:text")
  64                 state = TEXT;
  65             else if (tag == "metadata" || tag == "svg:metadata")
  66                 state = METADATA;
  67             else if (tag == "title")
  68                 state = TITLE;
  69             break;
  70         case METADATA:
  71             // Ignore nested "dc:" tags - for example dc:title is also used to
  72             // specify the creator's name inside dc:creator.
  73             if (dc_tag.empty() && startswith(tag, "dc:")) {
  74                 dc_tag = tag;
  75                 if (tag == "dc:title")
  76                     state = DC_TITLE;
  77                 else if (tag == "dc:subject")
  78                     state = KEYWORDS;
  79                 else if (tag == "dc:creator")
  80                     state = AUTHOR;
  81             }
  82             break;
  83         case DC_TITLE: case KEYWORDS: case TEXT: case TITLE: case AUTHOR:
  84             // Avoid compiler warnings.
  85             break;
  86     }
  87     return true;
  88 }
  89
  90 bool
  91 SvgParser::closing_tag(const string& tag)
  92 {
  93     if (tag == "text" || tag == "svg:text" ||
  94         tag == "title" ||
  95         tag == "metadata" || tag == "svg:metadata") {
  96         state = OTHER;
  97     } else if (tag == dc_tag) {
  98         dc_tag.resize(0);
  99         state = METADATA;
 100     }
 101     return true;
 102 }