2 Copyright (C) 2014-2015 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 STLBinaryReader::STLBinaryReader (istream& in)
42 : _buffer (new unsigned char[1024])
44 in.read ((char *) _buffer, 1024);
45 if (in.gcount() != 1024) {
46 throw STLError ("Could not read GSI block from binary STL file");
49 code_page_number = atoi (get_string (0, 3).c_str ());
50 frame_rate = stl_dfc_to_frame_rate (get_string (3, 8));
51 display_standard = _tables.display_standard_file_to_enum (get_string (11, 1));
52 language_group = _tables.language_group_file_to_enum (get_string (12, 2));
53 language = _tables.language_file_to_enum (get_string (14, 2));
54 original_programme_title = get_string (16, 32);
55 original_episode_title = get_string (48, 32);
56 translated_programme_title = get_string (80, 32);
57 translated_episode_title = get_string (112, 32);
58 translator_name = get_string (144, 32);
59 translator_contact_details = get_string (176, 32);
60 subtitle_list_reference_code = get_string (208, 16);
61 creation_date = get_string (224, 6);
62 revision_date = get_string (230, 6);
63 revision_number = get_string (236, 2);
65 tti_blocks = atoi (get_string (238, 5).c_str ());
66 number_of_subtitles = atoi (get_string (243, 5).c_str ());
67 subtitle_groups = atoi (get_string (248, 3).c_str ());
68 maximum_characters = atoi (get_string (251, 2).c_str ());
69 maximum_rows = atoi (get_string (253, 2).c_str ());
70 timecode_status = _tables.timecode_status_file_to_enum (get_string (255, 1));
71 start_of_programme = get_string (256, 8);
72 first_in_cue = get_string (264, 8);
73 disks = atoi (get_string (272, 1).c_str ());
74 disk_sequence_number = atoi (get_string (273, 1).c_str ());
75 country_of_origin = get_string (274, 3);
76 publisher = get_string (277, 32);
77 editor_name = get_string (309, 32);
78 editor_contact_details = get_string (341, 32);
80 for (int i = 0; i < tti_blocks; ++i) {
82 in.read ((char *) _buffer, 128);
83 if (in.gcount() != 128) {
84 throw STLError ("Could not read TTI block from binary STL file");
87 if (_tables.comment_file_to_enum (get_int (15, 1)) == COMMENT_YES) {
91 string const whole = get_string (16, 112);
93 /* Split the text up into lines (8Ah is a new line) */
95 split (lines, whole, is_any_of ("\x8a"));
97 /* Italic / underline specifications can span lines, so we need to track them
98 outside the lines loop.
101 bool underline = false;
103 for (size_t i = 0; i < lines.size(); ++i) {
105 sub.from = get_timecode (5);
106 sub.to = get_timecode (9);
107 sub.vertical_position.line = get_int (13, 1) + i;
108 sub.vertical_position.lines = maximum_rows;
109 sub.vertical_position.reference = TOP_OF_SCREEN;
111 sub.underline = underline;
113 /* XXX: not sure what to do with JC = 0, "unchanged presentation" */
114 int const h = get_int (14, 1);
118 sub.horizontal_position.reference = HORIZONTAL_CENTRE_OF_SCREEN;
121 sub.horizontal_position.reference = LEFT_OF_SCREEN;
124 sub.horizontal_position.reference = RIGHT_OF_SCREEN;
128 /* Loop over characters */
130 for (size_t j = 0; j < lines[i].size(); ++j) {
132 unsigned char const c = static_cast<unsigned char> (lines[i][j]);
135 /* Unused space i.e. end of line */
139 if (c >= 0x80 && c <= 0x83) {
140 /* Italic or underline control code */
141 sub.text = utf_to_utf<char> (iso6937_to_utf16 (text.c_str()));
142 _subs.push_back (sub);
165 sub.underline = underline;
168 if (!text.empty ()) {
169 sub.text = utf_to_utf<char> (iso6937_to_utf16 (text.c_str()));
170 _subs.push_back (sub);
173 /* XXX: justification */
178 STLBinaryReader::~STLBinaryReader ()
184 STLBinaryReader::get_string (int offset, int length) const
187 for (int i = 0; i < length; ++i) {
188 s += _buffer[offset + i];
195 STLBinaryReader::get_int (int offset, int length) const
198 for (int i = 0; i < length; ++i) {
199 v |= _buffer[offset + i] << (8 * i);
206 STLBinaryReader::get_timecode (int offset) const
208 return Time::from_hmsf (_buffer[offset], _buffer[offset + 1], _buffer[offset + 2], _buffer[offset + 3], Rational (frame_rate, 1));
212 STLBinaryReader::metadata () const
214 map<string, string> m;
216 m["Code page number"] = lexical_cast<string> (code_page_number);
217 m["Frame rate"] = lexical_cast<string> (frame_rate);
218 m["Display standard"] = _tables.display_standard_enum_to_description (display_standard);
219 m["Language group"] = _tables.language_group_enum_to_description (language_group);
220 m["Language"] = _tables.language_enum_to_description (language);
221 m["Original programme title"] = original_programme_title;
222 m["Original episode title"] = original_episode_title;
223 m["Translated programme title"] = translated_programme_title;
224 m["Translated episode title"] = translated_episode_title;
225 m["Translator name"] = translator_name;
226 m["Translator contact details"] = translator_contact_details;
227 m["Subtitle list reference code"] = subtitle_list_reference_code;
228 m["Creation date"] = creation_date;
229 m["Revision date"] = revision_date;
230 m["Revision number"] = revision_number;
231 m["TTI blocks"] = lexical_cast<string> (tti_blocks);
232 m["Number of subtitles"] = lexical_cast<string> (number_of_subtitles);
233 m["Subtitle groups"] = lexical_cast<string> (subtitle_groups);
234 m["Maximum characters"] = lexical_cast<string> (maximum_characters);
235 m["Maximum rows"] = lexical_cast<string> (maximum_rows);
236 m["Timecode status"] = _tables.timecode_status_enum_to_description (timecode_status);
237 m["Start of programme"] = start_of_programme;
238 m["First in cue"] = first_in_cue;
239 m["Disks"] = lexical_cast<string> (disks);
240 m["Disk sequence number"] = lexical_cast<string> (disk_sequence_number);
241 m["Country of origin"] = country_of_origin;
242 m["Publisher"] = publisher;
243 m["Editor name"] = editor_name;
244 m["Editor contact details"] = editor_contact_details;