Implemented a switch that has to be used for SBR AAC / AAC+ / HE-AAC if the source file is an AAC file and the AAC file contains SBR AAC data (no automatic detection possible in this case!).

ChangeLog

@@ -1,3 +1,9 @@
+2003-08-18  Moritz Bunkus  <moritz@bunkus.org>
+
+        * mkvmerge: Implemented a switch that has to be used for SBR AAC /
+        AAC+ / HE-AAC if the source file is an AAC file and the AAC file
+        contains SBR AAC data (no automatic detection possible in this case!).
+
 2003-08-14  Moritz Bunkus  <moritz@bunkus.org>
 
         * mkvmerge: Low bitrate AC3 tracks from Real's DNET are identified

doc/mkvmerge.1

@@ -226,6 +226,21 @@ tracks by selecting different track IDs each time.
 \fB\-t\fR, \fB\-\-tags\fR <\fITID\fR:\fIfile\fR>
 Read tags for the track with the number \fITID\fR from the \fIfile\fR. See
 the section about tags below for details.
+.TP
+\fB\-\-aab\-is\-sbr\fR <\fITID\fR>
+Tells \fBmkvmerge\fR that the track with the ID \fITID\fR is SBR AAC (also
+known as HE-AAC or AAC+). This options is needed if a) the source file is an
+AAC file (NOT for a Matroska file) and b) the AAC file contains SBR AAC data.
+The reason for this switch is that it is technically impossible to
+automatically tell normal AAC data from SBR AAC data without decoding a
+complete AAC frame. As there are several patent issues with AAC decoders I
+won't implement this decoding stage. So for SBR AAC files this switch is
+mandatory. The resulting file might not play back correctly or even not at
+all if the switch was omitted.
+.br
+If the source file is a Matroska file then the CodecID should be enough to
+detect SBR AAC. However, if the CodecID is wrong then this switch can be used
+to correct that.
 
 .LP
 Options that only apply to video tracks:

src/matroska.h

@@ -26,11 +26,12 @@
 #define MKV_A_AAC_2MAIN  "A_AAC/MPEG2/MAIN"
 #define MKV_A_AAC_2LC    "A_AAC/MPEG2/LC"
 #define MKV_A_AAC_2SSR   "A_AAC/MPEG2/SSR"
+#define MKV_A_AAC_2SBR   "A_AAC/MPEG2/LC/SBR"
 #define MKV_A_AAC_4MAIN  "A_AAC/MPEG4/MAIN"
 #define MKV_A_AAC_4LC    "A_AAC/MPEG4/LC"
 #define MKV_A_AAC_4SSR   "A_AAC/MPEG4/SSR"
 #define MKV_A_AAC_4LTP   "A_AAC/MPEG4/LTP"
-#define MKV_A_AAC_4SBR   "A_AAC/MPEG4/SBR"
+#define MKV_A_AAC_4SBR   "A_AAC/MPEG4/LC/SBR"
 #define MKV_A_AC3        "A_AC3"
 #define MKV_A_DTS        "A_DTS"
 #define MKV_A_MP3        "A_MPEG/L3"

src/mkvmerge.cpp

@@ -279,6 +279,7 @@ static void usage() {
     "  --language <TID:lang>    Sets the language for the track (ISO639-2\n"
     "                           code, see --list-languages).\n"
     "  -t, --tags <TID:file>    Read tags for the track from a XML file.\n"
+    "  --aac-is-sbr <TID>       Track with the ID is HE-AAC/AAC+/SBR-AAC.\n"
     "\n Options that only apply to video tracks:\n"
     "  -f, --fourcc <FOURCC>    Forces the FourCC to the specified value.\n"
     "                           Works only for video tracks.\n"
@@ -1043,6 +1044,7 @@ static void identify(const char *filename) {
   ti.atracks = new vector<int64_t>;
   ti.vtracks = new vector<int64_t>;
   ti.stracks = new vector<int64_t>;
+  ti.aac_is_sbr = new vector<int64_t>;
 
   file = (filelist_t *)safemalloc(sizeof(filelist_t));
 
@@ -1096,6 +1098,7 @@ static void parse_args(int argc, char **argv) {
   ti.languages = new vector<language_t>;
   ti.sub_charsets = new vector<language_t>;
   ti.all_tags = new vector<tags_t>;
+  ti.aac_is_sbr = new vector<int64_t>;
   ti.aspect_ratio = 0.0;
   ti.atracks = new vector<int64_t>;
   ti.vtracks = new vector<int64_t>;
@@ -1474,6 +1477,18 @@ static void parse_args(int argc, char **argv) {
       parse_tags(argv[i + 1], tags);
       ti.all_tags->push_back(tags);
       i++;
+
+    } else if (!strcmp(argv[i], "--aac-is-sbr")) {
+      if ((i + 1) >= argc) {
+        mxprint(stderr, "Error: %s lacks the track ID.\n", argv[i]);
+        exit(1);
+      }
+      if (!parse_int(argv[i + 1], id) || (id < 0)) {
+        mxprint(stderr, "Error: '%s' is not a valid track ID.\n", argv[i + 1]);
+        exit(1);
+      }
+      ti.aac_is_sbr->push_back(id);
+      i++;
     }
 
     // The argument is an input file.
@@ -1523,6 +1538,7 @@ static void parse_args(int argc, char **argv) {
       delete ti.languages;
       delete ti.sub_charsets;
       delete ti.all_tags;
+      delete ti.aac_is_sbr;
       memset(&ti, 0, sizeof(track_info_t));
       ti.audio_syncs = new vector<audio_sync_t>;
       ti.cue_creations = new vector<cue_creation_t>;
@@ -1530,6 +1546,7 @@ static void parse_args(int argc, char **argv) {
       ti.languages = new vector<language_t>;
       ti.sub_charsets = new vector<language_t>;
       ti.all_tags = new vector<tags_t>;
+      ti.aac_is_sbr = new vector<int64_t>;
       ti.aspect_ratio = 0.0;
       ti.atracks = new vector<int64_t>;
       ti.vtracks = new vector<int64_t>;

src/p_aac.cpp

@@ -184,6 +184,8 @@ void aac_packetizer_c::set_headers() {
       set_codec_id(MKV_A_AAC_4SSR);
     else if (profile == AAC_PROFILE_LTP)
       set_codec_id(MKV_A_AAC_4LTP);
+    else if (profile == AAC_PROFILE_SBR)
+      set_codec_id(MKV_A_AAC_4SBR);
     else
       die("aac_packetizer: Unknown AAC MPEG-4 object type %d.", profile);
   } else {
@@ -193,6 +195,8 @@ void aac_packetizer_c::set_headers() {
       set_codec_id(MKV_A_AAC_2LC);
     else if (profile == AAC_PROFILE_SSR)
       set_codec_id(MKV_A_AAC_2SSR);
+    else if (profile == AAC_PROFILE_SBR)
+      set_codec_id(MKV_A_AAC_2SBR);
     else
       die("aac_packetizer: Unknown AAC MPEG-2 profile %d.", profile);
   }

src/p_aac.h

@@ -34,6 +34,7 @@
 #define AAC_PROFILE_LC   1
 #define AAC_PROFILE_SSR  2
 #define AAC_PROFILE_LTP  3
+#define AAC_PROFILE_SBR  4
 
 class aac_packetizer_c: public generic_packetizer_c {
 private:

src/pr_generic.cpp

@@ -614,6 +614,7 @@ track_info_t *duplicate_track_info(track_info_t *src) {
   dst->all_tags = new vector<tags_t>(*src->all_tags);
   for (i = 0; i < src->all_tags->size(); i++)
     (*dst->all_tags)[i].file_name = safestrdup((*src->all_tags)[i].file_name);
+  dst->aac_is_sbr = new vector<int64_t>(*src->aac_is_sbr);
   dst->private_data = (unsigned char *)safememdup(src->private_data,
                                                   src->private_size);
   dst->sub_charset = safestrdup(src->sub_charset);
@@ -643,6 +644,7 @@ void free_track_info(track_info_t *ti) {
   for (i = 0; i < ti->all_tags->size(); i++)
     safefree((*ti->all_tags)[i].file_name);
   delete ti->all_tags;
+  delete ti->aac_is_sbr;
   safefree(ti->language);
   safefree(ti->private_data);
   safefree(ti->sub_charset);

src/pr_generic.h

@@ -109,6 +109,8 @@ typedef struct {
   vector<tags_t> *all_tags;     // As given on the command line
   tags_t *tags_ptr;             // For this very track
   KaxTags *tags;                // For this very track
+
+  vector<int64_t> *aac_is_sbr;  // For AAC+/HE-AAC/SBR
 } track_info_t;
 
 class generic_reader_c;

src/r_aac.cpp

@@ -56,7 +56,7 @@ int aac_reader_c::probe_file(mm_io_c *mm_io, int64_t size) {
 
 aac_reader_c::aac_reader_c(track_info_t *nti) throw (error_c):
   generic_reader_c(nti) {
-  int adif;
+  int adif, i;
   aac_header_t aacheader;
 
   try {
@@ -77,12 +77,24 @@ aac_reader_c::aac_reader_c(track_info_t *nti) throw (error_c):
         throw error_c("aac_reader: No valid AAC packet found in the first "
                       SINITCHUNKSIZE " bytes.\n");
       guess_adts_version();
-      mxprint(stdout, "emphasis_present: %s\n", emphasis_present ? "true" :
-              "false");
       adif = 0;
     }
     bytes_processed = 0;
     ti->id = 0;                 // ID for this track.
+
+    for (i = 0; i < ti->aac_is_sbr->size(); i++)
+      if ((*ti->aac_is_sbr)[i] == 0) {
+        aacheader.profile = AAC_PROFILE_SBR;
+        break;
+      }
+    if (aacheader.profile != AAC_PROFILE_SBR)
+      mxprint(stdout,
+              "WARNING! AAC files may contain HE-AAC / AAC+ / SBR AAC audio. "
+              "This can NOT be detected automatically. Therefore you have to "
+              "specifiy '--aac-is-sbr 0' manually for this input file if the "
+              "file actually contains SBR AAC. The file will be muxed in the "
+              "WRONG way otherwise. Also read mkvmerge's documentation.\n");
+
     aacpacketizer = new aac_packetizer_c(this, aacheader.id, aacheader.profile,
                                          aacheader.sample_rate,
                                          aacheader.channels, ti,

src/r_matroska.cpp

@@ -392,6 +392,8 @@ void kax_reader_c::verify_tracks() {
                      !strcmp(t->codec_id, MKV_A_AAC_4LC) ||
                      !strcmp(t->codec_id, MKV_A_AAC_4SSR) ||
                      !strcmp(t->codec_id, MKV_A_AAC_4LTP) ||
+                     !strcmp(t->codec_id, MKV_A_AAC_4SBR) ||
+                     !strcmp(t->codec_id, MKV_A_AAC_2SBR) ||
                      !strcmp(t->codec_id, MKV_A_AAC_4SBR))
             t->a_formattag = FOURCC('M', 'P', '4', 'A');
           else {
@@ -1179,7 +1181,7 @@ void kax_reader_c::create_packetizers() {
           } else if (t->a_formattag == FOURCC('M', 'P', '4', 'A')) {
             // A_AAC/MPEG2/MAIN
             // 0123456789012345
-            int id, profile;
+            int id, profile, sbridx;
 
             if (t->codec_id[10] == '2')
               id = AAC_ID_MPEG2;
@@ -1198,11 +1200,18 @@ void kax_reader_c::create_packetizers() {
               profile = AAC_PROFILE_SSR;
             else if (!strcmp(&t->codec_id[12], "LTP"))
               profile = AAC_PROFILE_LTP;
+            else if (!strcmp(&t->codec_id[12], "LC/SBR"))
+              profile = AAC_PROFILE_SBR;
             else {
               mxprint(stderr, "Error: matroska_reader: Malformed codec id "
                       "%s for track %d.\n", t->codec_id, t->tnum);
               exit(1);
             }
+            for (sbridx = 0; sbridx < ti->aac_is_sbr->size(); sbridx++)
+              if ((*ti->aac_is_sbr)[sbridx] == t->tnum) {
+                profile = AAC_PROFILE_SBR;
+                break;
+              }
 
             t->packetizer = new aac_packetizer_c(this, id, profile,
                                                  (unsigned long)t->a_sfreq,