[FFmpeg-cvslog] mov: store display matrix in a stream side data

[Vittorio Giovara]

ffmpeg | branch: master | Vittorio Giovara <vittorio.giovara at gmail.com> | Thu May 15 22:06:50 2014 -0400| [853cc025d63ee2539fc0460dab62c5b9a3fd2043] | committer: Anton Khirnov

mov: store display matrix in a stream side data

Signed-off-by: Anton Khirnov <anton at khirnov.net>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=853cc025d63ee2539fc0460dab62c5b9a3fd2043
---

 libavformat/isom.h |    2 ++
 libavformat/mov.c  |   62 +++++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 54 insertions(+), 10 deletions(-)

diff --git a/libavformat/isom.h b/libavformat/isom.h
index bf0792c..b2d5574 100644
--- a/libavformat/isom.h
+++ b/libavformat/isom.h
@@ -135,6 +135,8 @@ typedef struct MOVStreamContext {
     int64_t track_end;    ///< used for dts generation in fragmented movie files
     unsigned int rap_group_count;
     MOVSbgp *rap_group;
+
+    int32_t *display_matrix;
 } MOVStreamContext;
 
 typedef struct MOVContext {
diff --git a/libavformat/mov.c b/libavformat/mov.c
index e3dc67b..7a40d05 100644
--- a/libavformat/mov.c
+++ b/libavformat/mov.c
@@ -2344,7 +2344,7 @@ static int mov_read_tkhd(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     int width;
     int height;
     int64_t disp_transform[2];
-    int display_matrix[3][2];
+    int display_matrix[3][3];
     AVStream *st;
     MOVStreamContext *sc;
     int version;
@@ -2381,11 +2381,12 @@ static int mov_read_tkhd(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 
     //read in the display matrix (outlined in ISO 14496-12, Section 6.2.2)
     // they're kept in fixed point format through all calculations
-    // ignore u,v,z b/c we don't need the scale factor to calc aspect ratio
+    // save u,v,z to store the whole matrix in the AV_PKT_DATA_DISPLAYMATRIX
+    // side data, but the scale factor is not needed to calculate aspect ratio
     for (i = 0; i < 3; i++) {
         display_matrix[i][0] = avio_rb32(pb);   // 16.16 fixed point
         display_matrix[i][1] = avio_rb32(pb);   // 16.16 fixed point
-        avio_rb32(pb);           // 2.30 fixed point (not used)
+        display_matrix[i][2] = avio_rb32(pb);   //  2.30 fixed point
     }
 
     width = avio_rb32(pb);       // 16.16 fixed point track width
@@ -2393,6 +2394,25 @@ static int mov_read_tkhd(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     sc->width = width >> 16;
     sc->height = height >> 16;
 
+    // save the matrix when it is not the default identity
+    if (display_matrix[0][0] != (1 << 16) ||
+        display_matrix[1][1] != (1 << 16) ||
+        display_matrix[2][2] != (1 << 30) ||
+        display_matrix[0][1] || display_matrix[0][2] ||
+        display_matrix[1][0] || display_matrix[1][2] ||
+        display_matrix[2][0] || display_matrix[2][1]) {
+        int i, j;
+
+        av_freep(&sc->display_matrix);
+        sc->display_matrix = av_malloc(sizeof(int32_t) * 9);
+        if (!sc->display_matrix)
+            return AVERROR(ENOMEM);
+
+        for (i = 0; i < 3; i++)
+            for (j = 0; j < 3; j++)
+                sc->display_matrix[i * 3 + j] = display_matrix[j][i];
+    }
+
     // transform the display width/height according to the matrix
     // skip this if the display matrix is the default identity matrix
     // or if it is rotating the picture, ex iPhone 3GS
@@ -2975,6 +2995,7 @@ static int mov_read_close(AVFormatContext *s)
         av_freep(&sc->stts_data);
         av_freep(&sc->stps_data);
         av_freep(&sc->rap_group);
+        av_freep(&sc->display_matrix);
     }
 
     if (mov->dv_demux) {
@@ -3049,14 +3070,35 @@ static int mov_read_header(AVFormatContext *s)
 
     for (i = 0; i < s->nb_streams; i++) {
         AVStream *st = s->streams[i];
+        MOVStreamContext *sc = st->priv_data;
 
-        if (st->codec->codec_type != AVMEDIA_TYPE_AUDIO)
-            continue;
-
-        err = ff_replaygain_export(st, s->metadata);
-        if (err < 0) {
-            mov_read_close(s);
-            return err;
+        switch (st->codec->codec_type) {
+        case AVMEDIA_TYPE_AUDIO:
+            err = ff_replaygain_export(st, s->metadata);
+            if (err < 0) {
+                mov_read_close(s);
+                return err;
+            }
+            break;
+        case AVMEDIA_TYPE_VIDEO:
+            if (sc->display_matrix) {
+                AVPacketSideData *sd, *tmp;
+
+                tmp = av_realloc_array(st->side_data,
+                                       st->nb_side_data + 1, sizeof(*tmp));
+                if (!tmp)
+                    return AVERROR(ENOMEM);
+
+                st->side_data = tmp;
+                st->nb_side_data++;
+
+                sd = &st->side_data[st->nb_side_data - 1];
+                sd->type = AV_PKT_DATA_DISPLAYMATRIX;
+                sd->size = sizeof(int32_t) * 9;
+                sd->data = (uint8_t*)sc->display_matrix;
+                sc->display_matrix = NULL;
+            }
+            break;
         }
     }