Added support for attaching files to the output file(s).

ChangeLog

@@ -1,5 +1,8 @@
 2003-07-14  Moritz Bunkus  <moritz@bunkus.org>
 
+        * mkvmerge: Added support for attaching files to the output
+        file(s).
+
         * mkvinfo: Support for the elements dealing with attachments
         (KaxAttachments, KaxAttached, KaxFileDescription, KaxFileName,
         KaxMimeType, KaxFileData).

doc/mkvmerge.1

@@ -1,18 +1,23 @@
 .TH MKVMERGE "1" "June 2003" "mkvmerge v0.5.0" "User Commands"
 
+
 .SH NAME
 mkvmerge \- Merge multimedia streams into a Matroska file
 
+
 .SH SYNOPSIS
 .B mkvmerge
 [\fIglobal options\fR] \-o \fIout\fR [\fIoptions\fR] <file1> [[\fIoptions\fR] <file2> ...] [@optionsfile]
 
+
 .SH DESCRIPTION
 .LP
 This program takes the input from several media files and joins
 their streams (all of them or just a selection) into a Matroska file.
 .UR http://www.matroska.org/
 .UE
+
+
 .LP
 Global options:
 .TP
@@ -87,6 +92,35 @@ section \fBFILE LINKING\fR below for details.
 \fB\-\-link\-to\-next\fR <\fIUID\fR>
 Links the last output file to the segment with the given \fIUID\fR. See the
 section \fBFILE LINKING\fR below for details.
+.TP
+\fB\-\-attachment\-description\fR <\fIdescription\fR>
+Plain text description of the following attachment. Applies to the next
+\fB\-\-attach\-file\fR or \fB\-\-attach\-file\-once\fR command.
+.TP
+\fB\-\-attachment\-mime\-type\fR <\fIMIME type\fR>
+MIME type of the following attachment. Applies to the next
+\fB\-\-attach\-file\fR or \fB\-\-attach\-file\-once\fR command.
+A list of officially recognized MIME types can be found e.g. at
+.URL
+ftp://ftp.isi.edu/in-notes/iana/assignments/media-types/media-types
+The MIME type is mandatory for an attachment.
+.TP
+\fB\-\-attach\-file\fR <\fIfile name\fR>
+.TP
+\fB\-\-attach\-file\-once\fR <\fIfile name\fR>
+Creates a file attachment inside the Matroska file. The MIME type must have
+been set before this option can used. The difference between the two forms
+is that during splitting the files attached with \fB\-\-attach\-file\fR are
+attached to all output files while the ones attached with
+\fB\-\-attach\-file\-once\fR are only attached to the first file created.
+If splitting is not used then both do the same.
+.br
+\fBmkvextract\fR can be used to extract attached files from a Matroska file.
+.br
+\fBNote:\fR If an input file is a Matroska file then the attached files will
+not be copied to the output file(s). This may change in the future.
+
+
 .LP
 Options that can be used for each input file:
 .TP
@@ -167,6 +201,8 @@ listed with the \fB\-\-list\-languages\fR option.
 .br
 This option can be used multiple times for an input file applying to several
 tracks by selecting different track IDs each time.
+
+
 .LP
 Options that only apply to video tracks:
 .TP
@@ -358,6 +394,7 @@ If you do not see the language or default track flags that you've specified
 in \fBmkvinfo\fR's output then please read the section about \fBDEFAULT
 VALUES\fR.
 
+
 .SH SUBTITLES
 .LP
 There are several text subtitle formats that can be embedded into Matroska.
@@ -382,6 +419,7 @@ limitations: 1) Files saved with more than one byte per character (e.g.
 all UTF-16 formats) are not supported, UTF-8/ASCII only; 2) The \fB\\fe\fR
 markup is not supported correctly.
 
+
 .SH FILE LINKING
 .LP
 Matroska supports file linking which simply says that a specific file is the
@@ -419,6 +457,7 @@ If splitting is used then the first file is linked to the UID given with
 with \'\fB\-\-link\-to\-next\fR\'. If splitting is not used then the one
 output file will be linked to both of the two UIDs.
 
+
 .SH TRACK IDS
 .LP
 Some of the options for \fBmkvmerge\fR need a track ID to specify which track
@@ -448,6 +487,7 @@ The options that use the track IDs are: \fB\-\-atracks\fR, \fB\-\-vtracks\fR,
 \fB\-\-stracks\fR, \fB\-\-sync\fR, \fB\-\-default-track\fR, \fB\-\-cues\fR
 and \fB\-\-language\fR.
 
+
 .SH DEFAULT VALUES
 .LP
 The Matroska specs say that some elements have a default value. Usually an
@@ -459,6 +499,27 @@ and the default value for the \fIdefault track flag\fR is \fItrue\fR. Therefore
 if you used \fB--language 0:eng\fR for a track then it will not show up
 in \fBmkvinfo\fR's output.
 
+
+.SH ATTACHMENTS
+.LP
+Maybe you also want to keep some photos along with your Matroska file, or
+you're using SSA subtitles and need a special TrueType font that's really
+rare. In these cases you can attach those files to the Matroska file. They
+will not be just appended to the file but embedded in it. A player can then
+show those files (the 'photos' case) or use them to render the subtitles
+(the 'TrueType fonts' case).
+.LP
+Here's an example how to attach a photo and a TrueType font to the output
+file:
+.br
+$ \fBmkvmerge -o output.mkv -A video.avi sound.ogg \-\-attachment\-description
+"Me and the band behind the stage in a small get-together"
+\-\-attachment\-mime\-type image/jpeg \-\-attach\-file me_and_the_band.jpg
+\-\-attachment\-description "The real rare and unbelievably good looking font"
+\-\-attachment\-type application/octet\-stream
+\-\-attach\-file really_cool_font.ttf
+
+
 .SH NOTES
 .LP
 What works:
@@ -487,6 +548,9 @@ DTS audio files
 MP3 audio files
 .TP
 *
+RealVideo and RealAudio from RealMedia files
+.TP
+*
 Track selection
 .TP
 *

src/mkvmerge.cpp

@@ -45,6 +45,8 @@
 #include <ebml/EbmlVoid.h>
 
 #include <matroska/FileKax.h>
+#include <matroska/KaxAttached.h>
+#include <matroska/KaxAttachements.h>
 #include <matroska/KaxBlock.h>
 #include <matroska/KaxCluster.h>
 #include <matroska/KaxClusterData.h>
@@ -110,8 +112,16 @@ typedef struct {
   generic_packetizer_c *packetizer;
 } packetizer_t;
 
+typedef struct {
+  char *name, *mime_type, *description;
+  int64_t size;
+  bool to_all_files;
+} attachment_t;
+
 vector<packetizer_t *> packetizers;
 vector<filelist_t *> files;
+vector<attachment_t *> attachments;
+int64_t attachment_sizes_first = 0, attachment_sizes_others = 0;
 
 // Variables set by the command line parser.
 char *outfile = NULL;
@@ -207,6 +217,15 @@ static void usage(void) {
     "  --dont-link              Don't link splitted files.\n"
     "  --link-to-previous <UID> Link the first file to the given UID.\n"
     "  --link-to-next <UID>     Link the last file to the given UID.\n"
+    "  --attachment-description <desc>\n"
+    "                           Description for the following attachment.\n"
+    "  --attachment-mime-type <mime type>\n"
+    "                           Mime type for the following attachment.\n"
+    "  --attach-file <file>     Creates a file attachment inside the\n"
+    "                           Matroska file.\n"
+    "  --attach-file-once <file>\n"
+    "                           Creates a file attachment inside the\n"
+    "                           firsts Matroska file written.\n"
     "\n Options for each input file:\n"
     "  -a, --atracks <n,m,...>  Copy audio tracks n,m etc. Default: copy all\n"
     "                           audio tracks.\n"
@@ -426,6 +445,8 @@ static float parse_aspect_ratio(char *s) {
   float w, h;
 
   div = strchr(s, '/');
+  if (div == NULL)
+    div = strchr(s, ':');
   if (div == NULL)
     return strtod(s, NULL);
 
@@ -703,6 +724,76 @@ static void render_headers(mm_io_c *out, bool last_file, bool first_file) {
   }
 }
 
+static void render_attachments(IOCallback *out) {
+  KaxAttachements *kax_as;
+  KaxAttached *kax_a;
+  KaxFileData *fdata;
+  attachment_t *attch;
+  int i;
+  char *name;
+  binary *buffer;
+  int64_t size;
+  mm_io_c *io;
+
+  if (!(((file_num == 1) && (attachment_sizes_first > 0)) ||
+        (attachment_sizes_others > 0)))
+    return;
+
+  kax_as = new KaxAttachements();
+  kax_a = NULL;
+  for (i = 0; i < attachments.size(); i++) {
+    attch = attachments[i];
+
+    if ((file_num == 1) || attch->to_all_files) {
+      if (kax_a == NULL)
+        kax_a = &GetChild<KaxAttached>(*kax_as);
+      else
+        kax_a = &GetNextChild<KaxAttached>(*kax_as, *kax_a);
+
+      if (attch->description != NULL)
+        *static_cast<EbmlUnicodeString *>
+          (&GetChild<KaxFileDescription>(*kax_a)) =
+          cstr_to_UTFstring(attch->mime_type);;
+
+      if (attch->mime_type != NULL)
+        *static_cast<EbmlString *>(&GetChild<KaxMimeType>(*kax_a)) =
+          attch->mime_type;
+
+      name = &attch->name[strlen(attch->name) - 1];
+      while ((name != attch->name) && (*name != '/'))
+        name--;
+      if (*name == '/')
+        name++;
+      if (*name == 0)
+        die("Internal error: *name == 0 on %d.", __LINE__);
+
+      *static_cast<EbmlUnicodeString *>
+        (&GetChild<KaxFileName>(*kax_a)) =
+        cstr_to_UTFstring(name);
+
+      try {
+        io = new mm_io_c(attch->name, MODE_READ);
+        io->setFilePointer(0, seek_end);
+        size = io->getFilePointer();
+        io->setFilePointer(0, seek_beginning);
+
+        buffer = new binary[size];
+        io->read(buffer, size);
+        delete io;
+
+        fdata = &GetChild<KaxFileData>(*kax_a);
+        fdata->SetBuffer(buffer, size);
+      } catch (...) {
+        mxprint(stderr, "Error: Could not open the attachment '%s'.\n",
+                attch->name);
+      }
+    }
+  }
+
+  kax_as->Render(*out);
+  delete kax_as;
+}
+
 static void create_readers() {
   filelist_t *file;
   int i;
@@ -851,6 +942,8 @@ static void parse_args(int argc, char **argv) {
   cue_creation_t cues;
   int64_t id;
   language_t lang;
+  attachment_t *attachment;
+  mm_io_c *io;
 
   memset(&ti, 0, sizeof(track_info_t));
   ti.audio_syncs = new vector<audio_sync_t>;
@@ -862,6 +955,8 @@ static void parse_args(int argc, char **argv) {
   ti.atracks = new vector<int64_t>;
   ti.vtracks = new vector<int64_t>;
   ti.stracks = new vector<int64_t>;
+  attachment = (attachment_t *)safemalloc(sizeof(attachment_t));
+  memset(attachment, 0, sizeof(attachment_t));
 
   // Check if only information about the file is wanted. In this mode only
   // two parameters are allowed: the --identify switch and the file.
@@ -1034,6 +1129,62 @@ static void parse_args(int argc, char **argv) {
     else if (!strcmp(argv[i], "--no-lacing"))
       no_lacing = true;
 
+    else if (!strcmp(argv[i], "--attachment-description")) {
+      if ((i + 1) >= argc) {
+        mxprint(stderr, "Error: --attachment-description lacks the "
+                "description.\n");
+        exit(1);
+      }
+      safefree(attachment->description);
+      attachment->description = safestrdup(argv[i + 1]);
+      i++;
+
+    } else if (!strcmp(argv[i], "--attachment-mime-type")) {
+      if ((i + 1) >= argc) {
+        mxprint(stderr, "Error: --attachment-mime-type lacks the "
+                "MIME type.\n");
+        exit(1);
+      }
+      safefree(attachment->mime_type);
+      attachment->mime_type = safestrdup(argv[i + 1]);
+      i++;
+
+    } else if (!strcmp(argv[i], "--attach-file") ||
+               !strcmp(argv[i], "--attach-file-once")) {
+      if ((i + 1) >= argc) {
+        mxprint(stderr, "Error: %s lacks the file name.\n", argv[i]);
+        exit(1);
+      }
+
+      if (attachment->mime_type == NULL) {
+        mxprint(stderr, "Error: No MIME type was set for the attachment '%s'."
+                "\n", argv[i + 1]);
+        exit(1);
+      }
+
+      attachment->name = safestrdup(argv[i + 1]);
+      if (!strcmp(argv[i], "--attach-file"))
+        attachment->to_all_files = true;
+      try {
+        io = new mm_io_c(attachment->name, MODE_READ);
+        io->setFilePointer(0, seek_end);
+        attachment->size = io->getFilePointer();
+        delete io;
+        if (attachment->size == 0)
+          throw exception();
+      } catch (...) {
+        mxprint(stderr, "Error: Could not open the attachment '%s', or its "
+                "size is 0.\n", attachment->name);
+        exit(1);
+      }
+
+      attachments.push_back(attachment);
+      attachment = (attachment_t *)safemalloc(sizeof(attachment_t));
+      memset(attachment, 0, sizeof(attachment_t));
+
+      i++;
+    }
+
     // Options that apply to the next input file only.
     else if (!strcmp(argv[i], "-A") || !strcmp(argv[i], "--noaudio"))
       ti.no_audio = true;
@@ -1213,6 +1364,12 @@ static void parse_args(int argc, char **argv) {
       mxprint(stderr, "Warning: '--dont-link' is only useful in combination "
               "with '--split'.\n");
   }
+
+  for (i = 0; i < attachments.size(); i++) {
+    attachment_sizes_first += attachments[i]->size;
+    if (attachments[i]->to_all_files)
+      attachment_sizes_others += attachments[i]->size;
+  }
 }
 
 static char **add_string(int &num, char **values, char *new_string) {
@@ -1442,6 +1599,7 @@ void create_next_output_file(bool last_file, bool first_file) {
 
     cluster_helper->set_output(out);
     render_headers(out, last_file, first_file);
+    render_attachments(out);
 
     return;
   }
@@ -1464,6 +1622,7 @@ void create_next_output_file(bool last_file, bool first_file) {
 
   cluster_helper->set_output(out);
   render_headers(out, last_file, first_file);
+  render_attachments(out);
 
   file_num++;
 }