[FFmpeg-devel] [PATCH 1/2] avformat/mov: Rework the AVIF parser to handle multiple items

[Vignesh Venkatasubramanian <vigneshv-at-google.com@ffmpeg.org>]

Stores the item ids of all the items found in the file and
processes the primary item at the end of the meta box. This patch
does not change any behavior. It sets up the code for parsing
alpha channel (and possibly images with 'grid') in follow up
patches.

Signed-off-by: Vignesh Venkatasubramanian <vigneshv@google.com>
---
 libavformat/isom.h |   4 ++
 libavformat/mov.c  | 146 ++++++++++++++++++++++++++++-----------------
 2 files changed, 95 insertions(+), 55 deletions(-)

diff --git a/libavformat/isom.h b/libavformat/isom.h
index f05c2d9c28..d8b262e915 100644
--- a/libavformat/isom.h
+++ b/libavformat/isom.h
@@ -318,6 +318,10 @@ typedef struct MOVContext {
     uint32_t max_stts_delta;
     int is_still_picture_avif;
     int primary_item_id;
+    int *avif_item_ids;
+    int avif_item_ids_size;
+    int *avif_extent_lengths;
+    int64_t *avif_extent_offsets;
 } MOVContext;
 
 int ff_mp4_read_descr_len(AVIOContext *pb);
diff --git a/libavformat/mov.c b/libavformat/mov.c
index 88669faa70..cd87088f3e 100644
--- a/libavformat/mov.c
+++ b/libavformat/mov.c
@@ -4683,6 +4683,69 @@ static int mov_read_custom(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     return ret;
 }
 
+static int avif_add_stream(MOVContext *c, int item_id)
+{
+    MOVStreamContext *sc;
+    AVStream *st;
+    int item_index = -1;
+    for (int i = 0; i < c->avif_item_ids_size; i++)
+        if (c->avif_item_ids[i] == item_id) {
+            item_index = i;
+            break;
+        }
+    if (item_index < 0)
+        return AVERROR_INVALIDDATA;
+    st = avformat_new_stream(c->fc, NULL);
+    if (!st)
+        return AVERROR(ENOMEM);
+    st->id = c->fc->nb_streams;
+    sc = av_mallocz(sizeof(MOVStreamContext));
+    if (!sc)
+        return AVERROR(ENOMEM);
+
+    st->priv_data = sc;
+    st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO;
+    st->codecpar->codec_id = AV_CODEC_ID_AV1;
+    sc->ffindex = st->index;
+    c->trak_index = st->index;
+    st->avg_frame_rate.num = st->avg_frame_rate.den = 1;
+    st->time_base.num = st->time_base.den = 1;
+    st->nb_frames = 1;
+    sc->time_scale = 1;
+    sc = st->priv_data;
+    sc->pb = c->fc->pb;
+    sc->pb_is_copied = 1;
+
+    // Populate the necessary fields used by mov_build_index.
+    sc->stsc_count = 1;
+    sc->stsc_data = av_malloc_array(1, sizeof(*sc->stsc_data));
+    if (!sc->stsc_data)
+        return AVERROR(ENOMEM);
+    sc->stsc_data[0].first = 1;
+    sc->stsc_data[0].count = 1;
+    sc->stsc_data[0].id = 1;
+    sc->chunk_count = 1;
+    sc->chunk_offsets = av_malloc_array(1, sizeof(*sc->chunk_offsets));
+    if (!sc->chunk_offsets)
+        return AVERROR(ENOMEM);
+    sc->sample_count = 1;
+    sc->sample_sizes = av_malloc_array(1, sizeof(*sc->sample_sizes));
+    if (!sc->sample_sizes)
+        return AVERROR(ENOMEM);
+    sc->stts_count = 1;
+    sc->stts_data = av_malloc_array(1, sizeof(*sc->stts_data));
+    if (!sc->stts_data)
+        return AVERROR(ENOMEM);
+    sc->stts_data[0].count = 1;
+    // Not used for still images. But needed by mov_build_index.
+    sc->stts_data[0].duration = 0;
+    sc->sample_sizes[0] = c->avif_extent_lengths[item_index];
+    sc->chunk_offsets[0] = c->avif_extent_offsets[item_index];
+
+    mov_build_index(c, st);
+    return 0;
+}
+
 static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 {
     while (atom.size > 8) {
@@ -4692,9 +4755,23 @@ static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom)
         tag = avio_rl32(pb);
         atom.size -= 4;
         if (tag == MKTAG('h','d','l','r')) {
+            int ret;
             avio_seek(pb, -8, SEEK_CUR);
             atom.size += 8;
-            return mov_read_default(c, pb, atom);
+            if ((ret = mov_read_default(c, pb, atom)) < 0)
+                return ret;
+            if (c->is_still_picture_avif) {
+                int ret;
+                // Add a stream for the YUV planes (primary item).
+                if ((ret = avif_add_stream(c, c->primary_item_id)) < 0)
+                    return ret;
+                // For still AVIF images, the meta box contains all the
+                // necessary information that would generally be provided by the
+                // moov box. So simply mark that we have found the moov box so
+                // that parsing can continue.
+                c->found_moov = 1;
+            }
+            return ret;
         }
     }
     return 0;
@@ -7483,8 +7560,6 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     int item_count, extent_count;
     uint64_t base_offset, extent_offset, extent_length;
     uint8_t value;
-    AVStream *st;
-    MOVStreamContext *sc;
 
     if (!c->is_still_picture_avif) {
         // * For non-avif, we simply ignore the iloc box.
@@ -7498,27 +7573,6 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
         return 0;
     }
 
-    st = avformat_new_stream(c->fc, NULL);
-    if (!st)
-        return AVERROR(ENOMEM);
-    st->id = c->fc->nb_streams;
-    sc = av_mallocz(sizeof(MOVStreamContext));
-    if (!sc)
-        return AVERROR(ENOMEM);
-
-    st->priv_data = sc;
-    st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO;
-    st->codecpar->codec_id = AV_CODEC_ID_AV1;
-    sc->ffindex = st->index;
-    c->trak_index = st->index;
-    st->avg_frame_rate.num = st->avg_frame_rate.den = 1;
-    st->time_base.num = st->time_base.den = 1;
-    st->nb_frames = 1;
-    sc->time_scale = 1;
-    sc = st->priv_data;
-    sc->pb = c->fc->pb;
-    sc->pb_is_copied = 1;
-
     version = avio_r8(pb);
     avio_rb24(pb);  // flags.
 
@@ -7534,32 +7588,20 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     }
     item_count = (version < 2) ? avio_rb16(pb) : avio_rb32(pb);
 
-    // Populate the necessary fields used by mov_build_index.
-    sc->stsc_count = 1;
-    sc->stsc_data = av_malloc_array(1, sizeof(*sc->stsc_data));
-    if (!sc->stsc_data)
+    c->avif_item_ids = av_malloc_array(item_count, sizeof(*c->avif_item_ids));
+    if (!c->avif_item_ids)
         return AVERROR(ENOMEM);
-    sc->stsc_data[0].first = 1;
-    sc->stsc_data[0].count = 1;
-    sc->stsc_data[0].id = 1;
-    sc->chunk_count = 1;
-    sc->chunk_offsets = av_malloc_array(1, sizeof(*sc->chunk_offsets));
-    if (!sc->chunk_offsets)
+    c->avif_item_ids_size = item_count;
+    c->avif_extent_lengths = av_malloc_array(item_count, sizeof(*c->avif_extent_lengths));
+    if (!c->avif_extent_lengths)
         return AVERROR(ENOMEM);
-    sc->sample_count = 1;
-    sc->sample_sizes = av_malloc_array(1, sizeof(*sc->sample_sizes));
-    if (!sc->sample_sizes)
+    c->avif_extent_offsets = av_malloc_array(item_count, sizeof(*c->avif_extent_offsets));
+    if (!c->avif_extent_offsets)
         return AVERROR(ENOMEM);
-    sc->stts_count = 1;
-    sc->stts_data = av_malloc_array(1, sizeof(*sc->stts_data));
-    if (!sc->stts_data)
-        return AVERROR(ENOMEM);
-    sc->stts_data[0].count = 1;
-    // Not used for still images. But needed by mov_build_index.
-    sc->stts_data[0].duration = 0;
 
     for (int i = 0; i < item_count; i++) {
         int item_id = (version < 2) ? avio_rb16(pb) : avio_rb32(pb);
+        c->avif_item_ids[i] = item_id;
         if (version > 0)
             avio_rb16(pb);  // construction_method.
         avio_rb16(pb);  // data_reference_index.
@@ -7575,20 +7617,11 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
             if (rb_size(pb, &extent_offset, offset_size) < 0 ||
                 rb_size(pb, &extent_length, length_size) < 0)
                 return AVERROR_INVALIDDATA;
-            if (item_id == c->primary_item_id) {
-                sc->sample_sizes[0] = extent_length;
-                sc->chunk_offsets[0] = base_offset + extent_offset;
-            }
+            c->avif_extent_lengths[i] = extent_length;
+            c->avif_extent_offsets[i] = base_offset + extent_offset;
         }
     }
 
-    mov_build_index(c, st);
-
-    // For still AVIF images, the iloc box contains all the necessary
-    // information that would generally be provided by the moov box. So simply
-    // mark that we have found the moov box so that parsing can continue.
-    c->found_moov = 1;
-
     return atom.size;
 }
 
@@ -8192,6 +8225,9 @@ static int mov_read_close(AVFormatContext *s)
 
     av_freep(&mov->aes_decrypt);
     av_freep(&mov->chapter_tracks);
+    av_freep(&mov->avif_item_ids);
+    av_freep(&mov->avif_extent_lengths);
+    av_freep(&mov->avif_extent_offsets);
 
     return 0;
 }
-- 
2.37.0.144.g8ac04bfd2-goog

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".