lavf/matroska: add support for ARIB captions

3 files changed, 54 insertions, 0 deletions

diff --git a/libavformat/matroska.c b/libavformat/matroska.c
index 90d94b65bf..79b2d09984 100644
--- a/libavformat/matroska.c
+++ b/libavformat/matroska.c
@@ -76,6 +76,7 @@ const CodecTags ff_mkv_codec_tags[]={
     {"S_DVBSUB"         , AV_CODEC_ID_DVB_SUBTITLE},
     {"S_HDMV/PGS"       , AV_CODEC_ID_HDMV_PGS_SUBTITLE},
     {"S_HDMV/TEXTST"    , AV_CODEC_ID_HDMV_TEXT_SUBTITLE},
+    {"S_ARIBSUB"        , AV_CODEC_ID_ARIB_CAPTION},
 
     {"V_AV1"            , AV_CODEC_ID_AV1},
     {"V_AVS2"           , AV_CODEC_ID_AVS2},
diff --git a/libavformat/matroskadec.c b/libavformat/matroskadec.c
index d582f566a2..3a888e3ada 100644
--- a/libavformat/matroskadec.c
+++ b/libavformat/matroskadec.c
@@ -50,6 +50,7 @@
 #include "libavutil/time_internal.h"
 #include "libavutil/spherical.h"
 
+#include "libavcodec/avcodec.h"
 #include "libavcodec/bytestream.h"
 #include "libavcodec/flac.h"
 #include "libavcodec/mpeg4audio.h"
@@ -2813,6 +2814,35 @@ static int matroska_parse_tracks(AVFormatContext *s)
             /* we don't need any value stored in CodecPrivate.
                make sure that it's not exported as extradata. */
             track->codec_priv.size = 0;
+        } else if (codec_id == AV_CODEC_ID_ARIB_CAPTION && track->codec_priv.size == 3) {
+            int component_tag = track->codec_priv.data[0];
+            int data_component_id = AV_RB16(track->codec_priv.data + 1);
+
+            switch (data_component_id) {
+            case 0x0008:
+                // [0x30..0x37] are component tags utilized for
+                // non-mobile captioning service ("profile A").
+                if (component_tag >= 0x30 && component_tag <= 0x37) {
+                    st->codecpar->profile = FF_PROFILE_ARIB_PROFILE_A;
+                }
+                break;
+            case 0x0012:
+                // component tag 0x87 signifies a mobile/partial reception
+                // (1seg) captioning service ("profile C").
+                if (component_tag == 0x87) {
+                    st->codecpar->profile = FF_PROFILE_ARIB_PROFILE_C;
+                }
+                break;
+            default:
+                break;
+            }
+
+            if (st->codecpar->profile == FF_PROFILE_UNKNOWN)
+                av_log(matroska->ctx, AV_LOG_WARNING,
+                       "Unknown ARIB caption profile utilized: %02x / %04x\n",
+                       component_tag, data_component_id);
+
+            track->codec_priv.size = 0;
         }
         track->codec_priv.size -= extradata_offset;
 
diff --git a/libavformat/matroskaenc.c b/libavformat/matroskaenc.c
index 113541bd9a..954b7d828f 100644
--- a/libavformat/matroskaenc.c
+++ b/libavformat/matroskaenc.c
@@ -58,6 +58,7 @@
 #include "libavutil/stereo3d.h"
 
 #include "libavcodec/av1.h"
+#include "libavcodec/avcodec.h"
 #include "libavcodec/codec_desc.h"
 #include "libavcodec/xiph.h"
 #include "libavcodec/mpeg4audio.h"
@@ -1142,6 +1143,27 @@ static int mkv_assemble_native_codecprivate(AVFormatContext *s, AVIOContext *dyn
         else
             *size_to_reserve = MAX_PCE_SIZE;
         break;
+    case AV_CODEC_ID_ARIB_CAPTION: {
+        unsigned stream_identifier, data_component_id;
+        switch (par->profile) {
+        case FF_PROFILE_ARIB_PROFILE_A:
+            stream_identifier = 0x30;
+            data_component_id = 0x0008;
+            break;
+        case FF_PROFILE_ARIB_PROFILE_C:
+            stream_identifier = 0x87;
+            data_component_id = 0x0012;
+            break;
+        default:
+            av_log(s, AV_LOG_ERROR,
+                   "Unset/unknown ARIB caption profile %d utilized!\n",
+                   par->profile);
+            return AVERROR_INVALIDDATA;
+        }
+        avio_w8(dyn_cp, stream_identifier);
+        avio_wb16(dyn_cp, data_component_id);
+        break;
+    }
 #endif
     default:
         if (CONFIG_MATROSKA_MUXER && par->codec_id == AV_CODEC_ID_PRORES &&
@@ -3274,6 +3296,7 @@ static const AVCodecTag additional_subtitle_tags[] = {
     { AV_CODEC_ID_DVB_SUBTITLE,      0xFFFFFFFF },
     { AV_CODEC_ID_DVD_SUBTITLE,      0xFFFFFFFF },
     { AV_CODEC_ID_HDMV_PGS_SUBTITLE, 0xFFFFFFFF },
+    { AV_CODEC_ID_ARIB_CAPTION,      0xFFFFFFFF },
     { AV_CODEC_ID_NONE,              0xFFFFFFFF }
 };