xapian-applications/omega/svgparse.cc

   1 /** @file svgparse.cc
   2  * @brief Extract text from an SVG file.
   3  */
   4 /* Copyright (C) 2010,2011 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 "svgparse.h"
  24 #include "stringutils.h"
  25
  26 using namespace std;
  27
  28 void
  29 SvgParser::process_text(const string &text)
  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 KEYWORDS:
  40             target = &keywords;
  41             break;
  42         case AUTHOR:
  43             target = &author;
  44             break;
  45         case METADATA: case OTHER:
  46             // Ignore context in other places.
  47             return;
  48     }
  49     if (!target->empty())
  50         *target += ' ';
  51     *target += text;
  52 }
  53
  54 bool
  55 SvgParser::opening_tag(const string &tag)
  56 {
  57     switch (state) {
  58         case OTHER:
  59             if (tag == "text")
  60                 state = TEXT;
  61             else if (tag == "metadata")
  62                 state = METADATA;
  63             break;
  64         case METADATA:
  65             // Ignore nested "dc:" tags - for example dc:title is also used to
  66             // specify the creator's name inside dc:creator.
  67             if (dc_tag.empty() && startswith(tag, "dc:")) {
  68                 dc_tag = tag;
  69                 if (tag == "dc:title")
  70                     state = TITLE;
  71                 else if (tag == "dc:subject")
  72                     state = KEYWORDS;
  73                 else if (tag == "dc:creator")
  74                     state = AUTHOR;
  75             }
  76             break;
  77         case KEYWORDS: case TEXT: case TITLE: case AUTHOR:
  78             // Avoid compiler warnings.
  79             break;
  80     }
  81     return true;
  82 }
  83
  84 bool
  85 SvgParser::closing_tag(const string &tag)
  86 {
  87     if (tag == "text" || tag == "metadata") {
  88         state = OTHER;
  89     } else if (tag == dc_tag) {
  90         dc_tag.resize(0);
  91         state = METADATA;
  92     }
  93     return true;
  94 }