spherical: Change types of bounding and pad to uint32_t

[ffmpeg] / libavformat / matroskadec.c

diff --git a/libavformat/matroskadec.c b/libavformat/matroskadec.c
index e6737a70b27b923c9158014e7a5f3f748110f81a..bad034b77050a20aea22bf0bf793794f0de251af 100644 (file)
--- a/libavformat/matroskadec.c
+++ b/libavformat/matroskadec.c
@@ -89,6 +89,7 @@ typedef const struct EbmlSyntax {
     int list_elem_size;
     int data_offset;
     union {
+        int64_t     i;
         uint64_t    u;
         double      f;
         const char *s;
@@ -696,7 +697,7 @@ static const EbmlSyntax matroska_blockgroup[] = {
     { MATROSKA_ID_SIMPLEBLOCK,    EBML_BIN,  0, offsetof(MatroskaBlock, bin) },
     { MATROSKA_ID_BLOCKDURATION,  EBML_UINT, 0, offsetof(MatroskaBlock, duration) },
     { MATROSKA_ID_DISCARDPADDING, EBML_SINT, 0, offsetof(MatroskaBlock, discard_padding) },
-    { MATROSKA_ID_BLOCKREFERENCE, EBML_SINT, 0, offsetof(MatroskaBlock, reference) },
+    { MATROSKA_ID_BLOCKREFERENCE, EBML_SINT, 0, offsetof(MatroskaBlock, reference), { .i = INT64_MIN } },
     { MATROSKA_ID_CODECSTATE,     EBML_NONE },
     {                          1, EBML_UINT, 0, offsetof(MatroskaBlock, non_simple), { .u = 1 } },
     { 0 }
@@ -1071,6 +1072,9 @@ static int ebml_parse_nest(MatroskaDemuxContext *matroska, EbmlSyntax *syntax,
 
     for (i = 0; syntax[i].id; i++)
         switch (syntax[i].type) {
+        case EBML_SINT:
+            *(int64_t *) ((char *) data + syntax[i].data_offset) = syntax[i].def.i;
+            break;
         case EBML_UINT:
             *(uint64_t *) ((char *) data + syntax[i].data_offset) = syntax[i].def.u;
             break;
@@ -1909,16 +1913,63 @@ static int mkv_parse_video_projection(AVStream *st, const MatroskaTrack *track)
     AVSphericalMapping *spherical;
     enum AVSphericalProjection projection;
     size_t spherical_size;
+    uint32_t l = 0, t = 0, r = 0, b = 0;
+    uint32_t padding = 0;
     int ret;
+    GetByteContext gb;
+
+    bytestream2_init(&gb, track->video.projection.private.data,
+                     track->video.projection.private.size);
+
+    if (bytestream2_get_byte(&gb) != 0) {
+        av_log(NULL, AV_LOG_WARNING, "Unknown spherical metadata\n");
+        return 0;
+    }
+
+    bytestream2_skip(&gb, 3); // flags
 
     switch (track->video.projection.type) {
     case MATROSKA_VIDEO_PROJECTION_TYPE_EQUIRECTANGULAR:
-        projection = AV_SPHERICAL_EQUIRECTANGULAR;
+        if (track->video.projection.private.size == 20) {
+            t = bytestream2_get_be32(&gb);
+            b = bytestream2_get_be32(&gb);
+            l = bytestream2_get_be32(&gb);
+            r = bytestream2_get_be32(&gb);
+
+            if (b >= UINT_MAX - t || r >= UINT_MAX - l) {
+                av_log(NULL, AV_LOG_ERROR,
+                       "Invalid bounding rectangle coordinates "
+                       "%"PRIu32",%"PRIu32",%"PRIu32",%"PRIu32"\n",
+                       l, t, r, b);
+                return AVERROR_INVALIDDATA;
+            }
+        } else if (track->video.projection.private.size != 0) {
+            av_log(NULL, AV_LOG_ERROR, "Unknown spherical metadata\n");
+            return AVERROR_INVALIDDATA;
+        }
+
+        if (l || t || r || b)
+            projection = AV_SPHERICAL_EQUIRECTANGULAR_TILE;
+        else
+            projection = AV_SPHERICAL_EQUIRECTANGULAR;
         break;
     case MATROSKA_VIDEO_PROJECTION_TYPE_CUBEMAP:
-        if (track->video.projection.private.size < 4)
+        if (track->video.projection.private.size < 4) {
+            av_log(NULL, AV_LOG_ERROR, "Missing projection private properties\n");
             return AVERROR_INVALIDDATA;
-        projection = AV_SPHERICAL_CUBEMAP;
+        } else if (track->video.projection.private.size == 12) {
+            uint32_t layout = bytestream2_get_be32(&gb);
+            if (layout) {
+                av_log(NULL, AV_LOG_WARNING,
+                       "Unknown spherical cubemap layout %"PRIu32"\n", layout);
+                return 0;
+            }
+            projection = AV_SPHERICAL_CUBEMAP;
+            padding = bytestream2_get_be32(&gb);
+        } else {
+            av_log(NULL, AV_LOG_ERROR, "Unknown spherical metadata\n");
+            return AVERROR_INVALIDDATA;
+        }
         break;
     default:
         return 0;
@@ -1933,6 +1984,13 @@ static int mkv_parse_video_projection(AVStream *st, const MatroskaTrack *track)
     spherical->pitch = (int32_t)(track->video.projection.pitch * (1 << 16));
     spherical->roll  = (int32_t)(track->video.projection.roll  * (1 << 16));
 
+    spherical->padding = padding;
+
+    spherical->bound_left   = l;
+    spherical->bound_top    = t;
+    spherical->bound_right  = r;
+    spherical->bound_bottom = b;
+
     ret = av_stream_add_side_data(st, AV_PKT_DATA_SPHERICAL, (uint8_t *)spherical,
                                   spherical_size);
     if (ret < 0) {
@@ -2285,7 +2343,7 @@ static int matroska_parse_tracks(AVFormatContext *s)
                 track->audio.coded_framesize <= 0 ||
                 track->audio.sub_packet_h    <= 0 ||
                 track->audio.frame_size      <= 0 ||
-                track->audio.sub_packet_size <= 0)
+                track->audio.sub_packet_size <= 0 && codec_id != AV_CODEC_ID_SIPR)
                 return AVERROR_INVALIDDATA;
             track->audio.buf = av_malloc_array(track->audio.sub_packet_h,
                                                track->audio.frame_size);
@@ -3361,7 +3419,7 @@ static int matroska_parse_cluster_incremental(MatroskaDemuxContext *matroska)
         matroska->current_cluster_num_blocks = blocks_list->nb_elem;
         i                                    = blocks_list->nb_elem - 1;
         if (blocks[i].bin.size > 0 && blocks[i].bin.data) {
-            int is_keyframe = blocks[i].non_simple ? !blocks[i].reference : -1;
+            int is_keyframe = blocks[i].non_simple ? blocks[i].reference == INT64_MIN : -1;
             uint8_t* additional = blocks[i].additional.size > 0 ?
                                     blocks[i].additional.data : NULL;
             if (!blocks[i].non_simple)
@@ -3399,7 +3457,7 @@ static int matroska_parse_cluster(MatroskaDemuxContext *matroska)
     blocks      = blocks_list->elem;
     for (i = 0; i < blocks_list->nb_elem; i++)
         if (blocks[i].bin.size > 0 && blocks[i].bin.data) {
-            int is_keyframe = blocks[i].non_simple ? !blocks[i].reference : -1;
+            int is_keyframe = blocks[i].non_simple ? blocks[i].reference == INT64_MIN : -1;
             res = matroska_parse_block(matroska, blocks[i].bin.data,
                                        blocks[i].bin.size, blocks[i].bin.pos,
                                        cluster.timecode, blocks[i].duration,