summaryrefslogtreecommitdiff
path: root/src/lib/text_file.cc
diff options
context:
space:
mode:
authorCarl Hetherington <cth@carlh.net>2018-06-11 23:50:59 +0100
committerCarl Hetherington <cth@carlh.net>2018-07-19 23:36:56 +0100
commitd7ac100c0eb1b5efdcfbec59be870fd869252840 (patch)
tree74643ed748e14ea25948c2f68ae2799ebae9d62b /src/lib/text_file.cc
parent00ae2c28501bb757a6a45ba47ad4ecbe32412933 (diff)
Rename Subtitle -> Text
sed -i "s/SubtitleContent/TextContent/g" src/lib/*.cc src/lib/*.h src/wx/*.cc src/wx/*.h src/tools/*.cc test/*.cc sed -i "s/SubtitleDecoder/TextDecoder/g" src/lib/*.cc src/lib/*.h src/wx/*.cc src/wx/*.h src/tools/*.cc test/*.cc sed -i "s/subtitle_content/text_content/g" src/lib/*.cc src/lib/*.h src/wx/*.cc src/wx/*.h src/tools/*.cc test/*.cc src/lib/wscript src/wx/wscript sed -i "s/subtitle_decoder/text_decoder/g" src/lib/*.cc src/lib/*.h src/wx/*.cc src/wx/*.h src/tools/*.cc test/*.cc src/lib/wscript mv src/lib/subtitle_decoder.cc src/lib/text_decoder.cc mv src/lib/subtitle_decoder.h src/lib/text_decoder.h mv src/lib/subtitle_content.cc src/lib/text_content.cc mv src/lib/subtitle_content.h src/lib/text_content.h mv src/lib/dcp_subtitle_decoder.cc src/lib/dcp_text_decoder.cc mv src/lib/dcp_subtitle_decoder.h src/lib/dcp_text_decoder.h mv src/lib/dcp_subtitle_content.cc src/lib/dcp_text_content.cc mv src/lib/dcp_subtitle_content.h src/lib/dcp_text_content.h mv src/lib/text_subtitle_content.cc src/lib/text_text_content.cc mv src/lib/text_subtitle_content.h src/lib/text_text_content.h mv src/lib/text_subtitle_decoder.cc src/lib/text_text_decoder.cc mv src/lib/text_subtitle_decoder.h src/lib/text_text_decoder.h mv src/wx/timeline_subtitle_content_view.cc src/wx/timeline_text_content_view.cc mv src/wx/timeline_subtitle_content_view.h src/wx/timeline_text_content_view.h
Diffstat (limited to 'src/lib/text_file.cc')
-rw-r--r--src/lib/text_file.cc96
1 files changed, 96 insertions, 0 deletions
diff --git a/src/lib/text_file.cc b/src/lib/text_file.cc
new file mode 100644
index 000000000..b6a07574b
--- /dev/null
+++ b/src/lib/text_file.cc
@@ -0,0 +1,96 @@
+/*
+ Copyright (C) 2014-2016 Carl Hetherington <cth@carlh.net>
+
+ 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 <http://www.gnu.org/licenses/>.
+
+*/
+
+#include "text_file.h"
+#include "cross.h"
+#include "exceptions.h"
+#include "text_file_content.h"
+#include <sub/subrip_reader.h>
+#include <sub/ssa_reader.h>
+#include <sub/collect.h>
+#include <unicode/ucsdet.h>
+#include <unicode/ucnv.h>
+#include <iostream>
+
+#include "i18n.h"
+
+using std::vector;
+using std::cout;
+using std::string;
+using boost::shared_ptr;
+using boost::scoped_array;
+using dcp::Data;
+
+TextFile::TextFile (shared_ptr<const TextFileContent> content)
+{
+ Data in (content->path (0));
+
+ UErrorCode status = U_ZERO_ERROR;
+ UCharsetDetector* detector = ucsdet_open (&status);
+ ucsdet_setText (detector, reinterpret_cast<const char *> (in.data().get()), 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<uint16_t> utf16 (new uint16_t[in.size() * 2]);
+ int const utf16_len = ucnv_toUChars (
+ to_utf16, reinterpret_cast<UChar*>(utf16.get()), in.size() * 2,
+ reinterpret_cast<const char *> (in.data().get()), in.size(),
+ &status
+ );
+
+ UConverter* to_utf8 = ucnv_open ("UTF-8", &status);
+ /* Another guess */
+ scoped_array<char> utf8 (new char[utf16_len * 2]);
+ ucnv_fromUChars (to_utf8, utf8.get(), utf16_len * 2, reinterpret_cast<UChar*>(utf16.get()), utf16_len, &status);
+
+ ucsdet_close (detector);
+ ucnv_close (to_utf16);
+ ucnv_close (to_utf8);
+
+ sub::Reader* reader = 0;
+
+ string ext = content->path(0).extension().string();
+ transform (ext.begin(), ext.end(), ext.begin(), ::tolower);
+
+ if (ext == ".srt") {
+ reader = new sub::SubripReader (utf8.get());
+ } else if (ext == ".ssa" || ext == ".ass") {
+ reader = new sub::SSAReader (utf8.get());
+ }
+
+ if (reader) {
+ _subtitles = sub::collect<vector<sub::Subtitle> > (reader->subtitles ());
+ }
+
+ delete reader;
+}
+
+ContentTime
+TextFile::length () const
+{
+ if (_subtitles.empty ()) {
+ return ContentTime ();
+ }
+
+ return ContentTime::from_seconds (_subtitles.back().to.all_as_seconds ());
+}