xapian-applications/omega/handler_libcdr.cc

   1 /** @file
   2  * @brief Extract text using libcdr.
   3  */
   4 /* Copyright (C) 2020 Parth Kapadia
   5  * Copyright (C) 2022,2023 Olly Betts
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  20  * USA
  21  */
  22 #include <config.h>
  23 #include "handler.h"
  24
  25 #include <librevenge-generators/librevenge-generators.h>
  26 #include <librevenge-stream/librevenge-stream.h>
  27 #include <libcdr/libcdr.h>
  28
  29 using namespace librevenge;
  30 using namespace std;
  31
  32 bool
  33 initialise()
  34 {
  35     return true;
  36 }
  37
  38 void
  39 extract(const string& filename, const string&)
  40 {
  41     RVNGFileStream input(filename.c_str());
  42     RVNGStringVector pages;
  43     RVNGTextDrawingGenerator content(pages);
  44
  45     // There's also support in libcdr for CMX files, which is an exchange
  46     // format used by CorelDraw which seems to be mostly used for brushes
  47     // and clip art, neither of which are likely to contain extractable
  48     // text, so currently we don't attempt to handle CMX files here.
  49     //
  50     // There don't seem to be many freely available sample files either - the
  51     // only one I found easily was NEWSFLASH.CMX in the EDRM dataset, which
  52     // doesn't contain any extractable text.
  53
  54     // check if cdr file supported
  55     if (!libcdr::CDRDocument::isSupported(&input)) {
  56         send_field(FIELD_ERROR, "Format not supported");
  57         return;
  58     }
  59
  60     if (!libcdr::CDRDocument::parse(&input, &content)) {
  61         send_field(FIELD_ERROR, "Failed to parse file");
  62         return;
  63     }
  64
  65     int page_count = pages.size();
  66     send_field_page_count(page_count);
  67     for (auto i = 0; i < page_count; ++i) {
  68         const RVNGString& page = pages[i];
  69         send_field(FIELD_BODY, page.cstr(), page.size());
  70     }
  71 }