xapian-applications/omega/handler_libextractor.cc

   1 /** @file
   2  * @brief Extract metadata using libextractor.
   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 #include "parseint.h"
  25
  26 #include <extractor.h>
  27
  28 using namespace std;
  29
  30 /** Store metadata in its corresponding variable.
  31  *
  32  *  @param cls                  last parameter from EXTRACTOR_extract (unused)
  33  *  @param plugin_name          name of the plugin (unused)
  34  *  @param type                 mime-type of file according to libextractor
  35  *  @param format               format information about data
  36  *  @param data_mime_type       mimetype according to libextractor (unused)
  37  *  @param data                 actual meta-data found
  38  *  @param data_len             number of bytes in data
  39  */
  40 static int
  41 process_metadata(void*,
  42                  const char*,
  43                  enum EXTRACTOR_MetaType type,
  44                  enum EXTRACTOR_MetaFormat format,
  45                  const char*,
  46                  const char* data,
  47                  size_t data_len)
  48 {
  49     switch (format) {
  50         case EXTRACTOR_METAFORMAT_UTF8:
  51             break;
  52
  53         default:
  54             // specific encoding unknown
  55             // EXTRACTOR_METAFORMAT_UNKNOWN
  56             // EXTRACTOR_METAFORMAT_BINARY
  57             // EXTRACTOR_METAFORMAT_C_STRING
  58             return 0;
  59     }
  60
  61     // "data_len is strlen (data)+1"!
  62     --data_len;
  63
  64     switch (type) {
  65         case EXTRACTOR_METATYPE_BOOK_TITLE:
  66         case EXTRACTOR_METATYPE_JOURNAL_NAME:
  67         case EXTRACTOR_METATYPE_ORIGINAL_TITLE:
  68         case EXTRACTOR_METATYPE_SUBJECT:
  69         case EXTRACTOR_METATYPE_SUBTITLE:
  70         case EXTRACTOR_METATYPE_TITLE:
  71             send_field(FIELD_TITLE, data, data_len);
  72             break;
  73
  74         case EXTRACTOR_METATYPE_PAGE_COUNT: {
  75             unsigned p;
  76             if (parse_unsigned(data, p)) {
  77                 send_field_page_count(int(p));
  78             }
  79             break;
  80         }
  81
  82         case EXTRACTOR_METATYPE_ARTIST:
  83         case EXTRACTOR_METATYPE_AUTHOR_NAME:
  84         case EXTRACTOR_METATYPE_COMPOSER:
  85         case EXTRACTOR_METATYPE_CONDUCTOR:
  86         case EXTRACTOR_METATYPE_CREATOR:
  87         case EXTRACTOR_METATYPE_MOVIE_DIRECTOR:
  88         case EXTRACTOR_METATYPE_ORIGINAL_ARTIST:
  89         case EXTRACTOR_METATYPE_ORIGINAL_PERFORMER:
  90         case EXTRACTOR_METATYPE_ORIGINAL_WRITER:
  91         case EXTRACTOR_METATYPE_PERFORMER:
  92         case EXTRACTOR_METATYPE_WRITER:
  93             send_field(FIELD_AUTHOR, data, data_len);
  94             break;
  95
  96         case EXTRACTOR_METATYPE_KEYWORDS:
  97             send_field(FIELD_KEYWORDS, data, data_len);
  98             break;
  99
 100         case EXTRACTOR_METATYPE_ABSTRACT:
 101         case EXTRACTOR_METATYPE_COMMENT:
 102         case EXTRACTOR_METATYPE_DESCRIPTION:
 103         case EXTRACTOR_METATYPE_LYRICS:
 104         case EXTRACTOR_METATYPE_SUMMARY:
 105             send_field(FIELD_BODY, data, data_len);
 106             break;
 107
 108         default:
 109             // Ignore other metadata.
 110             break;
 111     }
 112     return 0;
 113 }
 114
 115 static struct EXTRACTOR_PluginList* plugins;
 116
 117 bool
 118 initialise()
 119 {
 120     // Add all default plugins.
 121     plugins = EXTRACTOR_plugin_add_defaults(EXTRACTOR_OPTION_DEFAULT_POLICY);
 122     return plugins != nullptr;
 123 }
 124
 125 void
 126 extract(const string& filename, const string&)
 127 {
 128     // If plugin not found/ File format not recognised/ corrupt file
 129     // no data is extracted, rather than reporting an error.
 130     EXTRACTOR_extract(plugins, filename.c_str(),
 131                       nullptr, 0,
 132                       &process_metadata, nullptr);
 133 }