From 0f85a04d615d56e962e3e10132cc911c06ab63bc Mon Sep 17 00:00:00 2001
From: Moritz Bunkus <moritz@bunkus.org>
Date: Wed, 5 Nov 2003 18:19:10 +0000
Subject: [PATCH] The charset used during subtitle extraction defaults to
 UTF-8.

---
 doc/mkvextract.1          | 2 +-
 src/mkvextract.cpp        | 8 ++++++--
 src/mkvextract.h          | 1 +
 src/mkvextract_tracks.cpp | 2 ++
 4 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/doc/mkvextract.1 b/doc/mkvextract.1
index 432beb37f..6e5c65716 100644
--- a/doc/mkvextract.1
+++ b/doc/mkvextract.1
@@ -35,7 +35,7 @@ Command line syntax for the \fBtracks\fR extraction mode:
 .TP
 \fB\-c\fR \fIcharset\fR
 Sets the charset to convert the next text subtitle track to. Only valid if the
-next track ID targets a text subtitle track.
+next track ID targets a text subtitle track. It defaults to UTF-8.
 .TP
 \fITID\fR:\fIoutname\fR
 Causes extraction of the track with the ID \fITID\fR into the file
diff --git a/src/mkvextract.cpp b/src/mkvextract.cpp
index 7480b9f5a..6ae771583 100644
--- a/src/mkvextract.cpp
+++ b/src/mkvextract.cpp
@@ -121,7 +121,7 @@ void usage() {
 " on the mode.\n"
 "\n"
 " First mode extracts some tracks to external files.\n"
-"  -c charset     Convert text subtitles to this charset.\n"
+"  -c charset     Convert text subtitles to this charset (default: UTF-8).\n"
 "  TID:out        Write track with the ID TID to the file 'out'.\n"
 "\n"
 " Second mode extracts the tags and converts them to XML. The output is\n"
@@ -195,7 +195,8 @@ void parse_args(int argc, char **argv, char *&file_name, int &mode) {
 
   file_name = argv[2];
 
-  conv_handle = 0;
+  conv_handle = conv_utf8;
+  sub_charset = "UTF-8";
 
   // Now process all the other options.
   for (i = 3; i < argc; i++)
@@ -244,6 +245,8 @@ void parse_args(int argc, char **argv, char *&file_name, int &mode) {
       track.sub_charset = safestrdup(sub_charset);
       tracks.push_back(track);
       safefree(copy);
+      conv_handle = conv_utf8;
+      sub_charset = "UTF-8";
     }
 
   if ((mode == MODE_TAGS) || (mode == MODE_CHAPTERS))
@@ -315,6 +318,7 @@ int main(int argc, char **argv) {
 #endif
 
   utf8_init(NULL);
+  conv_utf8 = utf8_init("UTF-8");
 
   parse_args(argc, argv, input_file, mode);
   if (mode == MODE_TRACKS) {
diff --git a/src/mkvextract.h b/src/mkvextract.h
index baa04987b..f789b989c 100644
--- a/src/mkvextract.h
+++ b/src/mkvextract.h
@@ -101,6 +101,7 @@ void show_error(const char *fmt, ...);
 kax_track_t *find_track(int tid);
 
 bool extract_tracks(const char *file_name);
+extern int conv_utf8;
 void extract_tags(const char *file_name);
 void extract_chapters(const char *file_name, bool chapter_format_simple);
 void extract_attachments(const char *file_name);
diff --git a/src/mkvextract_tracks.cpp b/src/mkvextract_tracks.cpp
index 73092de38..ce2021380 100644
--- a/src/mkvextract_tracks.cpp
+++ b/src/mkvextract_tracks.cpp
@@ -80,6 +80,8 @@ extern "C" {
 using namespace libmatroska;
 using namespace std;
 
+int conv_utf8;
+
 // }}}
 
 // {{{ FUNCTIONS flush_ogg_pages(), write_ogg_pages()