src/stl_binary_reader.cc

   1 /*
   2     Copyright (C) 2014 Carl Hetherington <cth@carlh.net>
   3
   4     This program is free software; you can redistribute it and/or modify
   5     it under the terms of the GNU General Public License as published by
   6     the Free Software Foundation; either version 2 of the License, or
   7     (at your option) any later version.
   8
   9     This program is distributed in the hope that it will be useful,
  10     but WITHOUT ANY WARRANTY; without even the implied warranty of
  11     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12     GNU General Public License for more details.
  13
  14     You should have received a copy of the GNU General Public License
  15     along with this program; if not, write to the Free Software
  16     Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  17
  18 */
  19
  20 #include <boost/lexical_cast.hpp>
  21 #include <boost/algorithm/string.hpp>
  22 #include <boost/locale.hpp>
  23 #include "stl_binary_reader.h"
  24 #include "exceptions.h"
  25 #include "iso6937.h"
  26 #include "compose.hpp"
  27
  28 using std::map;
  29 using std::cout;
  30 using std::string;
  31 using std::istream;
  32 using boost::lexical_cast;
  33 using boost::algorithm::replace_all;
  34 using boost::locale::conv::utf_to_utf;
  35 using namespace sub;
  36
  37 template <class E, class F>
  38 E
  39 file_to_enum (F k, map<F, STLCode<E> > m, string name)
  40 {
  41         typename map<F, STLCode<E> >::const_iterator i = m.find (k);
  42         if (i == m.end ()) {
  43                 throw STLError (String::compose ("Unknown %1 %2 in binary STL file", name, k));
  44         }
  45
  46         return i->second.value;
  47 }
  48
  49 template <class E, class F>
  50 string
  51 enum_to_description (E v, map<F, STLCode<E> > const & m)
  52 {
  53         for (typename map<F, STLCode<E> >::const_iterator i = m.begin(); i != m.end(); ++i) {
  54                 if (i->second.value == v) {
  55                         return i->second.description;
  56                 }
  57         }
  58
  59         return "";
  60 }
  61
  62 template <class E, class F>
  63 void
  64 code (map<F, STLCode<E> >& m, F k, E v, string d)
  65 {
  66         m[k] = STLCode<E> (v, d);
  67 }
  68
  69
  70 STLBinaryReader::STLBinaryReader (istream& in)
  71         : _buffer (new unsigned char[1024])
  72 {
  73         create_tables ();
  74
  75         in.read ((char *) _buffer, 1024);
  76         if (in.gcount() != 1024) {
  77                 throw STLError ("Could not read GSI block from binary STL file");
  78         }
  79
  80         code_page_number = atoi (get_string (0, 3).c_str ());
  81
  82         string const dfc = get_string (3, 8);
  83         if (dfc == "STL24.01") {
  84                 frame_rate = 24;
  85         } else if (dfc == "STL25.01") {
  86                 frame_rate = 25;
  87         } else if (dfc == "STL30.01") {
  88                 frame_rate = 30;
  89         } else {
  90                 throw STLError (String::compose ("Unknown disk format code %1 in binary STL file", dfc));
  91         }
  92
  93         display_standard = file_to_enum (get_string (11, 1), _display_standard_map, "display standard code");
  94         language_group = file_to_enum (get_string (12, 2), _language_group_map, "character code");
  95         language = file_to_enum (get_string (14, 2), _language_map, "language code");
  96         original_programme_title = get_string (16, 32);
  97         original_episode_title = get_string (48, 32);
  98         translated_programme_title = get_string (80, 32);
  99         translated_episode_title = get_string (112, 32);
 100         translator_name = get_string (144, 32);
 101         translator_contact_details = get_string (176, 32);
 102         subtitle_list_reference_code = get_string (208, 32);
 103         creation_date = get_string (224, 6);
 104         revision_date = get_string (230, 6);
 105         revision_number = get_string (236, 2);
 106
 107         tti_blocks = atoi (get_string (238, 5).c_str ());
 108         number_of_subtitles = atoi (get_string (243, 5).c_str ());
 109         subtitle_groups = atoi (get_string (248, 3).c_str ());
 110         maximum_characters = atoi (get_string (251, 2).c_str ());
 111         maximum_rows = atoi (get_string (253, 2).c_str ());
 112         timecode_status = file_to_enum (get_string (255, 1), _timecode_status_map, "timecode status code");
 113         start_of_programme = get_string (256, 8);
 114         first_in_cue = get_string (256, 8);
 115         disks = atoi (get_string (272, 1).c_str ());
 116         disk_sequence_number = atoi (get_string (273, 1).c_str ());
 117         country_of_origin = get_string (274, 3);
 118         publisher = get_string (277, 32);
 119         editor_name = get_string (309, 32);
 120         editor_contact_details = get_string (341, 32);
 121
 122         for (int i = 0; i < tti_blocks; ++i) {
 123                 Subtitle sub;
 124
 125                 in.read ((char *) _buffer, 128);
 126                 if (in.gcount() != 128) {
 127                         throw STLError ("Could not read TTI block from binary STL file");
 128                 }
 129
 130                 if (file_to_enum (get_int (15, 1), _comment_map, "comment flag") == COMMENT_YES) {
 131                         continue;
 132                 }
 133
 134                 sub.from.frame = get_timecode (5);
 135                 sub.to.frame = get_timecode (9);
 136                 sub.line = get_int (13, 1);
 137
 138                 /* XXX: justification, effects */
 139
 140                 string s = get_string (16, 112);
 141
 142                 /* 8Ah is a new line */
 143                 replace_all (s, "\x8a", "\n");
 144
 145                 /* 8Fh is unused space, so trim the string to the first instance of that */
 146                 size_t unused = s.find_first_of ('\x8f');
 147                 if (unused != string::npos) {
 148                         s = s.substr (0, unused);
 149                 }
 150
 151                 sub.text = utf_to_utf<char> (iso6937_to_utf16 (s.c_str()));
 152
 153                 _subs.push_back (sub);
 154         }
 155 }
 156
 157 STLBinaryReader::~STLBinaryReader ()
 158 {
 159         delete[] _buffer;
 160 }
 161
 162 string
 163 STLBinaryReader::get_string (int offset, int length) const
 164 {
 165         string s;
 166         for (int i = 0; i < length; ++i) {
 167                 s += _buffer[offset + i];
 168         }
 169
 170         return s;
 171 }
 172
 173 int
 174 STLBinaryReader::get_int (int offset, int length) const
 175 {
 176         int v = 0;
 177         for (int i = 0; i < length; ++i) {
 178                 v |= _buffer[offset + i] << (8 * i);
 179         }
 180
 181         return v;
 182 }
 183
 184 FrameTime
 185 STLBinaryReader::get_timecode (int offset) const
 186 {
 187         return FrameTime (_buffer[offset], _buffer[offset + 1], _buffer[offset + 2], _buffer[offset + 3]);
 188 }
 189
 190 map<string, string>
 191 STLBinaryReader::metadata () const
 192 {
 193         map<string, string> m;
 194
 195         m["Code page number"] = lexical_cast<string> (code_page_number);
 196         m["Frame rate"] = lexical_cast<string> (frame_rate);
 197         m["Display standard"] = enum_to_description (display_standard, _display_standard_map);
 198         m["Language group"] = enum_to_description (language_group, _language_group_map);
 199         m["Language"] = enum_to_description (language, _language_map);
 200         m["Original programme title"] = original_programme_title;
 201         m["Original episode title"] = original_episode_title;
 202         m["Translated programme title"] = translated_programme_title;
 203         m["Translated episode title"] = translated_episode_title;
 204         m["Translator name"] = translator_name;
 205         m["Translator contact details"] = translator_contact_details;
 206         m["Subtitle list reference code"] = subtitle_list_reference_code;
 207         m["Creation date"] = creation_date;
 208         m["Revision date"] = revision_date;
 209         m["Revision number"] = revision_number;
 210         m["TTI blocks"] = lexical_cast<string> (tti_blocks);
 211         m["Number of subtitles"] = lexical_cast<string> (number_of_subtitles);
 212         m["Subtitle groups"] = lexical_cast<string> (subtitle_groups);
 213         m["Maximum characters"] = lexical_cast<string> (maximum_characters);
 214         m["Maximum rows"] = lexical_cast<string> (maximum_rows);
 215         m["Timecode status"] = enum_to_description (timecode_status, _timecode_status_map);
 216         m["Start of programme"] = start_of_programme;
 217         m["First in cue"] = first_in_cue;
 218         m["Disks"] = lexical_cast<string> (disks);
 219         m["Disk sequence number"] = lexical_cast<string> (disk_sequence_number);
 220         m["Country of origin"] = country_of_origin;
 221         m["Publisher"] = publisher;
 222         m["Editor name"] = editor_name;
 223         m["Editor contact details"] = editor_contact_details;
 224
 225         return m;
 226 }
 227
 228 void
 229 STLBinaryReader::create_tables ()
 230 {
 231         code<DisplayStandard, string> (_display_standard_map, " ", DISPLAY_STANDARD_UNDEFINED, "Undefined");
 232         code<DisplayStandard, string> (_display_standard_map, "0", DISPLAY_STANDARD_OPEN_SUBTITLING, "Open subtitling");
 233         code<DisplayStandard, string> (_display_standard_map, "1", DISPLAY_STANDARD_LEVEL_1_TELETEXT, "Level 1 teletext");
 234         code<DisplayStandard, string> (_display_standard_map, "2", DISPLAY_STANDARD_LEVEL_2_TELETEXT, "Level 2 teletext");
 235
 236         code<LanguageGroup, string> (_language_group_map, "00", LANGUAGE_GROUP_LATIN, "Latin");
 237         code<LanguageGroup, string> (_language_group_map, "01", LANGUAGE_GROUP_LATIN_CYRILLIC, "Latin/Cyrillic");
 238         code<LanguageGroup, string> (_language_group_map, "02", LANGUAGE_GROUP_LATIN_ARABIC, "Latin/Arabic");
 239         code<LanguageGroup, string> (_language_group_map, "03", LANGUAGE_GROUP_LATIN_GREEK, "Latin/Greek");
 240         code<LanguageGroup, string> (_language_group_map, "04", LANGUAGE_GROUP_LATIN_HEBREW, "Latin/Hebrew");
 241
 242         code<Language, string> (_language_map, "00", LANGUAGE_UNKNOWN, "Unknown");
 243         code<Language, string> (_language_map, "01", LANGUAGE_ALBANIAN, "Albanian");
 244         code<Language, string> (_language_map, "02", LANGUAGE_BRETON, "Breton");
 245         code<Language, string> (_language_map, "03", LANGUAGE_CATALAN, "Catalan");
 246         code<Language, string> (_language_map, "04", LANGUAGE_CROATIAN, "Croatian");
 247         code<Language, string> (_language_map, "05", LANGUAGE_WELSH, "Welsh");
 248         code<Language, string> (_language_map, "06", LANGUAGE_CZECH, "Czech");
 249         code<Language, string> (_language_map, "07", LANGUAGE_DANISH, "Danish");
 250         code<Language, string> (_language_map, "08", LANGUAGE_GERMAN, "German");
 251         code<Language, string> (_language_map, "09", LANGUAGE_ENGLISH, "English");
 252         code<Language, string> (_language_map, "0A", LANGUAGE_SPANISH, "Spanish");
 253         code<Language, string> (_language_map, "0B", LANGUAGE_ESPERANTO, "Esperanto");
 254         code<Language, string> (_language_map, "0C", LANGUAGE_ESTONIAN, "Estonian");
 255         code<Language, string> (_language_map, "0D", LANGUAGE_BASQUE, "Basque");
 256         code<Language, string> (_language_map, "0E", LANGUAGE_FAROESE, "Faroese");
 257         code<Language, string> (_language_map, "0F", LANGUAGE_FRENCH, "French");
 258         code<Language, string> (_language_map, "10", LANGUAGE_FRISIAN, "Frisian");
 259         code<Language, string> (_language_map, "11", LANGUAGE_IRISH, "Irish");
 260         code<Language, string> (_language_map, "12", LANGUAGE_GAELIC, "Gaelic");
 261         code<Language, string> (_language_map, "13", LANGUAGE_GALACIAN, "Galacian");
 262         code<Language, string> (_language_map, "14", LANGUAGE_ICELANDIC, "Icelandic");
 263         code<Language, string> (_language_map, "15", LANGUAGE_ITALIAN, "Italian");
 264         code<Language, string> (_language_map, "16", LANGUAGE_LAPPISH, "Lappish");
 265         code<Language, string> (_language_map, "17", LANGUAGE_LATIN, "Latin");
 266         code<Language, string> (_language_map, "18", LANGUAGE_LATVIAN, "Latvian");
 267         code<Language, string> (_language_map, "19", LANGUAGE_LUXEMBORGIAN, "Luxemborgian");
 268         code<Language, string> (_language_map, "1A", LANGUAGE_LITHUANIAN, "Lithuanian");
 269         code<Language, string> (_language_map, "1B", LANGUAGE_HUNGARIAN, "Hungarian");
 270         code<Language, string> (_language_map, "1C", LANGUAGE_MALTESE, "Maltese");
 271         code<Language, string> (_language_map, "1D", LANGUAGE_DUTCH, "Dutch");
 272         code<Language, string> (_language_map, "1E", LANGUAGE_NORWEGIAN, "Norwegian");
 273         code<Language, string> (_language_map, "1F", LANGUAGE_OCCITAN, "Occitan");
 274         code<Language, string> (_language_map, "20", LANGUAGE_POLISH, "Polish");
 275         code<Language, string> (_language_map, "21", LANGUAGE_PORTUGESE, "Portugese");
 276         code<Language, string> (_language_map, "22", LANGUAGE_ROMANIAN, "Romanian");
 277         code<Language, string> (_language_map, "23", LANGUAGE_ROMANSH, "Romansh");
 278         code<Language, string> (_language_map, "24", LANGUAGE_SERBIAN, "Serbian");
 279         code<Language, string> (_language_map, "25", LANGUAGE_SLOVAK, "Slovak");
 280         code<Language, string> (_language_map, "26", LANGUAGE_SLOVENIAN, "Slovenian");
 281         code<Language, string> (_language_map, "27", LANGUAGE_FINNISH, "Finnish");
 282         code<Language, string> (_language_map, "28", LANGUAGE_SWEDISH, "Swedish");
 283         code<Language, string> (_language_map, "29", LANGUAGE_TURKISH, "Turkish");
 284         code<Language, string> (_language_map, "2A", LANGUAGE_FLEMISH, "Flemish");
 285         code<Language, string> (_language_map, "2B", LANGUAGE_WALLON, "Wallon");
 286         code<Language, string> (_language_map, "7F", LANGUAGE_AMHARIC, "Amharic");
 287         code<Language, string> (_language_map, "7E", LANGUAGE_ARABIC, "Arabic");
 288         code<Language, string> (_language_map, "7D", LANGUAGE_ARMENIAN, "Armenian");
 289         code<Language, string> (_language_map, "7C", LANGUAGE_ASSAMESE, "Assamese");
 290         code<Language, string> (_language_map, "7B", LANGUAGE_AZERBAIJANI, "Azerbaijani");
 291         code<Language, string> (_language_map, "7A", LANGUAGE_BAMBORA, "Bambora");
 292         code<Language, string> (_language_map, "79", LANGUAGE_BIELORUSSIAN, "Bielorussian");
 293         code<Language, string> (_language_map, "78", LANGUAGE_BENGALI, "Bengali");
 294         code<Language, string> (_language_map, "77", LANGUAGE_BULGARIAN, "Bulgarian");
 295         code<Language, string> (_language_map, "76", LANGUAGE_BURMESE, "Burmese");
 296         code<Language, string> (_language_map, "75", LANGUAGE_CHINESE, "Chinese");
 297         code<Language, string> (_language_map, "74", LANGUAGE_CHURASH, "Churash");
 298         code<Language, string> (_language_map, "73", LANGUAGE_DARI, "Dari");
 299         code<Language, string> (_language_map, "72", LANGUAGE_FULANI, "Fulani");
 300         code<Language, string> (_language_map, "71", LANGUAGE_GEORGIAN, "Georgian");
 301         code<Language, string> (_language_map, "70", LANGUAGE_GREEK, "Greek");
 302         code<Language, string> (_language_map, "6F", LANGUAGE_GUJURATI, "Gujarati");
 303         code<Language, string> (_language_map, "6E", LANGUAGE_GURANI, "Gurani");
 304         code<Language, string> (_language_map, "6D", LANGUAGE_HAUSA, "Hausa");
 305         code<Language, string> (_language_map, "6C", LANGUAGE_HEBREW, "Hebrew");
 306         code<Language, string> (_language_map, "6B", LANGUAGE_HINDI, "Hindi");
 307         code<Language, string> (_language_map, "6A", LANGUAGE_INDONESIAN, "Indonesian");
 308         code<Language, string> (_language_map, "69", LANGUAGE_JAPANESE, "Japanese");
 309         code<Language, string> (_language_map, "68", LANGUAGE_KANNADA, "Kannada");
 310         code<Language, string> (_language_map, "67", LANGUAGE_KAZAKH, "Kazakh");
 311         code<Language, string> (_language_map, "66", LANGUAGE_KHMER, "Khmer");
 312         code<Language, string> (_language_map, "65", LANGUAGE_KOREAN, "Korean");
 313         code<Language, string> (_language_map, "64", LANGUAGE_LAOTIAN, "Laotian");
 314         code<Language, string> (_language_map, "63", LANGUAGE_MACEDONIAN, "Macedonian");
 315         code<Language, string> (_language_map, "62", LANGUAGE_MALAGASAY, "Malagasay");
 316         code<Language, string> (_language_map, "61", LANGUAGE_MALAYSIAN, "Malaysian");
 317         code<Language, string> (_language_map, "60", LANGUAGE_MOLDAVIAN, "Moldavian");
 318         code<Language, string> (_language_map, "5F", LANGUAGE_MARATHI, "Marathi");
 319         code<Language, string> (_language_map, "5E", LANGUAGE_NDEBELE, "Ndebele");
 320         code<Language, string> (_language_map, "5D", LANGUAGE_NEPALI, "Nepali");
 321         code<Language, string> (_language_map, "5C", LANGUAGE_ORIYA, "Oriya");
 322         code<Language, string> (_language_map, "5B", LANGUAGE_PAPAMIENTO, "Papamiento");
 323         code<Language, string> (_language_map, "5A", LANGUAGE_PERSIAN, "Persian");
 324         code<Language, string> (_language_map, "59", LANGUAGE_PUNJABI, "Punjabi");
 325         code<Language, string> (_language_map, "58", LANGUAGE_PUSHTU, "Pushtu");
 326         code<Language, string> (_language_map, "57", LANGUAGE_QUECHUA, "Quechua");
 327         code<Language, string> (_language_map, "56", LANGUAGE_RUSSIAN, "Russian");
 328         code<Language, string> (_language_map, "55", LANGUAGE_RUTHENIAN, "Ruthenian");
 329         code<Language, string> (_language_map, "54", LANGUAGE_SERBO_CROAT, "Serbo Croat");
 330         code<Language, string> (_language_map, "53", LANGUAGE_SHONA, "Shona");
 331         code<Language, string> (_language_map, "52", LANGUAGE_SINHALESE, "Sinhalese");
 332         code<Language, string> (_language_map, "51", LANGUAGE_SOMALI, "Somali");
 333         code<Language, string> (_language_map, "50", LANGUAGE_SRANAN_TONGO, "Sranan Tongo");
 334         code<Language, string> (_language_map, "4F", LANGUAGE_SWAHILI, "Swahili");
 335         code<Language, string> (_language_map, "4E", LANGUAGE_TADZHIK, "Tadzhik");
 336         code<Language, string> (_language_map, "4D", LANGUAGE_TAMIL, "Tamil");
 337         code<Language, string> (_language_map, "4C", LANGUAGE_TATAR, "Tatar");
 338         code<Language, string> (_language_map, "4B", LANGUAGE_TELUGU, "Telugu");
 339         code<Language, string> (_language_map, "4A", LANGUAGE_THAI, "Thai");
 340         code<Language, string> (_language_map, "49", LANGUAGE_UKRANIAN, "Ukranian");
 341         code<Language, string> (_language_map, "48", LANGUAGE_URDU, "Urdu");
 342         code<Language, string> (_language_map, "47", LANGUAGE_UZBEK, "Uzbek");
 343         code<Language, string> (_language_map, "46", LANGUAGE_VIETNAMESE, "Vietnamese");
 344         code<Language, string> (_language_map, "45", LANGUAGE_ZULU, "Zulu");
 345
 346         code<TimecodeStatus, string> (_timecode_status_map, "0", TIMECODE_STATUS_NOT_INTENDED_FOR_USE, "Not intended for use");
 347         code<TimecodeStatus, string> (_timecode_status_map, "1", TIMECODE_STATUS_INTENDED_FOR_USE, "Intended for use");
 348
 349         code<CumulativeStatus, int> (_cumulative_status_map, 0, CUMULATIVE_STATUS_NOT_CUMULATIVE, "Not part of a cumulative set");
 350         code<CumulativeStatus, int> (_cumulative_status_map, 1, CUMULATIVE_STATUS_FIRST, "First subtitle of a cumulative set");
 351         code<CumulativeStatus, int> (_cumulative_status_map, 2, CUMULATIVE_STATUS_INTERMEDIATE, "Intermediate subtitle of a cumulative set");
 352         code<CumulativeStatus, int> (_cumulative_status_map, 3, CUMULATIVE_STATUS_LAST, "Last subtitle of a cumulative set");
 353
 354         code<Justification, int> (_justification_map, 0, JUSTIFICATION_NONE, "No justification");
 355         code<Justification, int> (_justification_map, 1, JUSTIFICATION_LEFT, "Left justification");
 356         code<Justification, int> (_justification_map, 2, JUSTIFICATION_CENTRE, "Centre justification");
 357         code<Justification, int> (_justification_map, 3, JUSTIFICATION_CENTRE, "Right justification");
 358
 359         code<Comment, int> (_comment_map, 0, COMMENT_NO, "Not a comment");
 360         code<Comment, int> (_comment_map, 1, COMMENT_YES, "Is a comment");
 361 }