2 Copyright (C) 2014-2016 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 "text_subtitle.h"
22 #include "exceptions.h"
23 #include "text_subtitle_content.h"
24 #include <sub/subrip_reader.h>
25 #include <sub/ssa_reader.h>
26 #include <sub/collect.h>
27 #include <unicode/ucsdet.h>
28 #include <unicode/ucnv.h>
36 using boost::shared_ptr;
37 using boost::scoped_array;
40 TextSubtitle::TextSubtitle (shared_ptr<const TextSubtitleContent> content)
42 Data in (content->path (0));
44 UErrorCode status = U_ZERO_ERROR;
45 UCharsetDetector* detector = ucsdet_open (&status);
46 ucsdet_setText (detector, reinterpret_cast<const char *> (in.data().get()), in.size(), &status);
48 UCharsetMatch const * match = ucsdet_detect (detector, &status);
49 char const * in_charset = ucsdet_getName (match, &status);
51 UConverter* to_utf16 = ucnv_open (in_charset, &status);
52 /* This is a guess; I think we should be able to encode any input in 4 times its input size */
53 scoped_array<uint16_t> utf16 (new uint16_t[in.size() * 2]);
54 int const utf16_len = ucnv_toUChars (
55 to_utf16, reinterpret_cast<UChar*>(utf16.get()), in.size() * 2,
56 reinterpret_cast<const char *> (in.data().get()), in.size(),
60 UConverter* to_utf8 = ucnv_open ("UTF-8", &status);
62 scoped_array<char> utf8 (new char[utf16_len * 2]);
63 ucnv_fromUChars (to_utf8, utf8.get(), utf16_len * 2, reinterpret_cast<UChar*>(utf16.get()), utf16_len, &status);
65 ucsdet_close (detector);
66 ucnv_close (to_utf16);
69 sub::Reader* reader = 0;
71 if (content->path(0).extension() == ".srt" || content->path(0).extension() == ".SRT") {
72 reader = new sub::SubripReader (utf8.get());
73 } else if (content->path(0).extension() == ".ssa" || content->path(0).extension() == ".SSA") {
74 reader = new sub::SSAReader (utf8.get());
78 _subtitles = sub::collect<vector<sub::Subtitle> > (reader->subtitles ());
83 TextSubtitle::length () const
85 if (_subtitles.empty ()) {
86 return ContentTime ();
89 return ContentTime::from_seconds (_subtitles.back().to.all_as_seconds ());