/* Copyright (C) 2014-2020 Carl Hetherington This file is part of DCP-o-matic. DCP-o-matic is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. DCP-o-matic is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with DCP-o-matic. If not, see . */ #include "cross.h" #include "exceptions.h" #include "string_text_file.h" #include "string_text_file_content.h" #include #include #include #include #include #include #include #include #include #include #include "i18n.h" using std::cout; using std::shared_ptr; using std::string; using std::vector; using boost::scoped_array; using boost::optional; using dcp::ArrayData; using namespace dcpomatic; StringTextFile::StringTextFile (shared_ptr content) { string ext = content->path(0).extension().string(); transform (ext.begin(), ext.end(), ext.begin(), ::tolower); std::unique_ptr reader; if (ext == ".stl") { dcp::File f(content->path(0), "rb"); if (!f) { throw OpenFileError (f.path(), errno, OpenFileError::READ); } try { reader.reset(new sub::STLBinaryReader(f.get())); } catch (...) { throw; } } else { /* Text-based file; sort out its character encoding before we try to parse it */ ArrayData in (content->path (0)); UErrorCode status = U_ZERO_ERROR; UCharsetDetector* detector = ucsdet_open (&status); ucsdet_setText (detector, reinterpret_cast(in.data()), in.size(), &status); UCharsetMatch const * match = ucsdet_detect (detector, &status); char const * in_charset = ucsdet_getName (match, &status); UConverter* to_utf16 = ucnv_open (in_charset, &status); /* This is a guess; I think we should be able to encode any input in 4 times its input size */ scoped_array utf16 (new uint16_t[in.size() * 2]); int const utf16_len = ucnv_toUChars ( to_utf16, reinterpret_cast(utf16.get()), in.size() * 2, reinterpret_cast(in.data()), in.size(), &status ); UConverter* to_utf8 = ucnv_open ("UTF-8", &status); /* Another guess */ scoped_array utf8 (new char[utf16_len * 2]); ucnv_fromUChars (to_utf8, utf8.get(), utf16_len * 2, reinterpret_cast(utf16.get()), utf16_len, &status); /* Fix OS X line endings */ size_t utf8_len = strlen (utf8.get ()); for (size_t i = 0; i < utf8_len; ++i) { if (utf8[i] == '\r' && ((i == utf8_len - 1) || utf8[i + 1] != '\n')) { utf8[i] = '\n'; } } ucsdet_close (detector); ucnv_close (to_utf16); ucnv_close (to_utf8); if (ext == ".srt") { try { reader.reset(new sub::SubripReader(utf8.get())); } catch (sub::SubripError& subrip_error) { /* Sometimes files are have the .srt extension but are really WEBVTT... */ try { reader.reset(new sub::WebVTTReader(utf8.get())); } catch (sub::WebVTTHeaderError&) { /* ...but in this case there isn't even a WebVTT error */ throw subrip_error; } } } else if (ext == ".ssa" || ext == ".ass") { reader.reset(new sub::SSAReader(utf8.get())); } else if (ext == ".vtt") { reader.reset(new sub::WebVTTReader(utf8.get())); } } if (reader) { _subtitles = sub::collect>(reader->subtitles()); } } /** @return time of first subtitle, if there is one */ optional StringTextFile::first () const { if (_subtitles.empty()) { return {}; } return ContentTime::from_seconds(_subtitles[0].from.all_as_seconds()); } ContentTime StringTextFile::length () const { if (_subtitles.empty ()) { return {}; } return ContentTime::from_seconds (_subtitles.back().to.all_as_seconds ()); }