2 Copyright (C) 2014-2020 Carl Hetherington <cth@carlh.net>
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.
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.
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.
20 #include "stl_binary_reader.h"
21 #include "exceptions.h"
24 #include "compose.hpp"
25 #include <boost/lexical_cast.hpp>
26 #include <boost/algorithm/string.hpp>
27 #include <boost/locale.hpp>
35 using boost::lexical_cast;
36 using boost::algorithm::replace_all;
37 using boost::is_any_of;
38 using boost::locale::conv::utf_to_utf;
41 class InputReader : public boost::noncopyable
45 : _buffer (new unsigned char[1024])
50 virtual ~InputReader ()
55 virtual void read (int size, string what) = 0;
57 string get_string (int offset, int length) const
60 for (int i = 0; i < length; ++i) {
61 s += _buffer[offset + i];
67 int get_int (int offset, int length) const
70 for (int i = 0; i < length; ++i) {
71 v |= _buffer[offset + i] << (8 * i);
77 Time get_timecode (int offset, int frame_rate) const
79 return Time::from_hmsf (_buffer[offset], _buffer[offset + 1], _buffer[offset + 2], _buffer[offset + 3], Rational (frame_rate, 1));
83 unsigned char* _buffer;
87 class StreamInputReader : public InputReader
90 StreamInputReader (istream& in)
96 void read (int size, string what)
98 _in.read (reinterpret_cast<char *>(_buffer), size);
99 if (_in.gcount() != size) {
100 throw STLError (String::compose("Could not read %1 block from binary STL file", what));
108 STLBinaryReader::STLBinaryReader (istream& in)
110 StreamInputReader reader (in);
111 reader.read (1024, "GSI");
113 code_page_number = atoi (reader.get_string(0, 3).c_str());
114 frame_rate = stl_dfc_to_frame_rate (reader.get_string(3, 8));
115 display_standard = _tables.display_standard_file_to_enum (reader.get_string(11, 1));
116 language_group = _tables.language_group_file_to_enum (reader.get_string(12, 2));
117 language = _tables.language_file_to_enum (reader.get_string(14, 2));
118 original_programme_title = reader.get_string(16, 32);
119 original_episode_title = reader.get_string(48, 32);
120 translated_programme_title = reader.get_string(80, 32);
121 translated_episode_title = reader.get_string(112, 32);
122 translator_name = reader.get_string(144, 32);
123 translator_contact_details = reader.get_string(176, 32);
124 subtitle_list_reference_code = reader.get_string(208, 16);
125 creation_date = reader.get_string(224, 6);
126 revision_date = reader.get_string(230, 6);
127 revision_number = reader.get_string(236, 2);
129 tti_blocks = atoi (reader.get_string(238, 5).c_str());
130 number_of_subtitles = atoi (reader.get_string(243, 5).c_str());
131 subtitle_groups = atoi (reader.get_string(248, 3).c_str());
132 maximum_characters = atoi (reader.get_string(251, 2).c_str());
133 maximum_rows = atoi (reader.get_string(253, 2).c_str());
134 timecode_status = _tables.timecode_status_file_to_enum (reader.get_string(255, 1));
135 start_of_programme = reader.get_string(256, 8);
136 first_in_cue = reader.get_string(264, 8);
137 disks = atoi (reader.get_string(272, 1).c_str());
138 disk_sequence_number = atoi (reader.get_string(273, 1).c_str());
139 country_of_origin = reader.get_string(274, 3);
140 publisher = reader.get_string(277, 32);
141 editor_name = reader.get_string(309, 32);
142 editor_contact_details = reader.get_string(341, 32);
144 for (int i = 0; i < tti_blocks; ++i) {
146 reader.read (128, "TTI");
148 if (_tables.comment_file_to_enum (reader.get_int(15, 1)) == COMMENT_YES) {
152 string const whole = reader.get_string(16, 112);
154 /* Split the text up into lines (8Ah is a new line) */
155 vector<string> lines;
156 split (lines, whole, is_any_of ("\x8a"));
158 /* Italic / underline specifications can span lines, so we need to track them
159 outside the lines loop.
162 bool underline = false;
164 for (size_t i = 0; i < lines.size(); ++i) {
166 sub.from = reader.get_timecode(5, frame_rate);
167 sub.to = reader.get_timecode(9, frame_rate);
168 sub.vertical_position.line = reader.get_int(13, 1) + i;
169 sub.vertical_position.lines = maximum_rows;
170 sub.vertical_position.reference = TOP_OF_SCREEN;
172 sub.underline = underline;
174 /* XXX: not sure what to do with JC = 0, "unchanged presentation" */
175 int const h = reader.get_int(14, 1);
179 sub.horizontal_position.reference = HORIZONTAL_CENTRE_OF_SCREEN;
182 sub.horizontal_position.reference = LEFT_OF_SCREEN;
185 sub.horizontal_position.reference = RIGHT_OF_SCREEN;
189 /* Loop over characters */
191 for (size_t j = 0; j < lines[i].size(); ++j) {
193 unsigned char const c = static_cast<unsigned char> (lines[i][j]);
196 /* Unused space i.e. end of line */
200 if (c >= 0x80 && c <= 0x83) {
201 /* Italic or underline control code */
202 sub.text = utf_to_utf<char> (iso6937_to_utf16 (text.c_str()));
203 _subs.push_back (sub);
226 sub.underline = underline;
229 if (!text.empty ()) {
230 sub.text = utf_to_utf<char> (iso6937_to_utf16 (text.c_str()));
231 _subs.push_back (sub);
234 /* XXX: justification */
240 STLBinaryReader::metadata () const
242 map<string, string> m;
244 m["Code page number"] = lexical_cast<string> (code_page_number);
245 m["Frame rate"] = lexical_cast<string> (frame_rate);
246 m["Display standard"] = _tables.display_standard_enum_to_description (display_standard);
247 m["Language group"] = _tables.language_group_enum_to_description (language_group);
248 m["Language"] = _tables.language_enum_to_description (language);
249 m["Original programme title"] = original_programme_title;
250 m["Original episode title"] = original_episode_title;
251 m["Translated programme title"] = translated_programme_title;
252 m["Translated episode title"] = translated_episode_title;
253 m["Translator name"] = translator_name;
254 m["Translator contact details"] = translator_contact_details;
255 m["Subtitle list reference code"] = subtitle_list_reference_code;
256 m["Creation date"] = creation_date;
257 m["Revision date"] = revision_date;
258 m["Revision number"] = revision_number;
259 m["TTI blocks"] = lexical_cast<string> (tti_blocks);
260 m["Number of subtitles"] = lexical_cast<string> (number_of_subtitles);
261 m["Subtitle groups"] = lexical_cast<string> (subtitle_groups);
262 m["Maximum characters"] = lexical_cast<string> (maximum_characters);
263 m["Maximum rows"] = lexical_cast<string> (maximum_rows);
264 m["Timecode status"] = _tables.timecode_status_enum_to_description (timecode_status);
265 m["Start of programme"] = start_of_programme;
266 m["First in cue"] = first_in_cue;
267 m["Disks"] = lexical_cast<string> (disks);
268 m["Disk sequence number"] = lexical_cast<string> (disk_sequence_number);
269 m["Country of origin"] = country_of_origin;
270 m["Publisher"] = publisher;
271 m["Editor name"] = editor_name;
272 m["Editor contact details"] = editor_contact_details;