xapian-applications/omega/handler_libgepub.cc

   1 /** @file
   2  * @brief Extract text and metadata using libgepub
   3  */
   4 /* Copyright (C) 2023 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU General Public License as
   8  * published by the Free Software Foundation; either version 2 of the
   9  * License, or (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
  19  * USA
  20  */
  21
  22 #include <config.h>
  23
  24 #include "handler.h"
  25
  26 #include "htmlparser.h"
  27
  28 #include <gepub-doc.h>
  29
  30 #include <string_view>
  31
  32 using namespace std;
  33
  34 static void
  35 send_glib_field(Field field, gchar* data)
  36 {
  37     if (data) {
  38         send_field(field, data);
  39         g_free(data);
  40     }
  41 }
  42
  43 bool
  44 initialise()
  45 {
  46     return true;
  47 }
  48
  49 void
  50 extract(const string& filename, const string&)
  51 {
  52     GError* e = nullptr;
  53     GepubDoc* doc = gepub_doc_new(filename.c_str(), &e);
  54     if (!doc) {
  55         send_field(FIELD_ERROR, "gepub_doc_new() failed: ");
  56         send_field(FIELD_ERROR, e->message);
  57         g_error_free(e);
  58         return;
  59     }
  60
  61     int chapters = gepub_doc_get_n_chapters(doc);
  62     // "Page count" is not a concept which seems to perfectly fit with an EPUB
  63     // so (at least for now) we report the number of chapters.
  64     send_field_page_count(chapters);
  65     for (int i = 0; i < chapters; ++i) {
  66         gepub_doc_set_chapter(doc, i);
  67         GBytes* html = gepub_doc_get_current(doc);
  68         gsize size;
  69         auto data = static_cast<const char*>(g_bytes_get_data(html, &size));
  70         HtmlParser parser;
  71         try {
  72             parser.parse(string_view(data, size), "utf-8", false);
  73         } catch (const string& newcharset) {
  74             parser.parse(string_view(data, size), newcharset, true);
  75         }
  76         send_field(FIELD_BODY, parser.dump);
  77         g_bytes_unref(html);
  78     }
  79
  80     // Extract metadata.
  81     send_glib_field(FIELD_AUTHOR,
  82                     gepub_doc_get_metadata(doc, GEPUB_META_AUTHOR));
  83     send_glib_field(FIELD_KEYWORDS,
  84                     gepub_doc_get_metadata(doc, GEPUB_META_DESC));
  85     send_glib_field(FIELD_TITLE,
  86                     gepub_doc_get_metadata(doc, GEPUB_META_TITLE));
  87
  88     g_object_unref(doc);
  89 }