avformat/mov: Only read the primary item for AVIF

Update the still AVIF parser to only read the primary item. With this
patch, AVIF still images with exif/icc/alpha channel will no longer
fail to parse.

For example, this patch enables parsing of files in:
https://github.com/AOMediaCodec/av1-avif/tree/master/testFiles/Microsoft

Adding two fate tests:
1) demuxing of still image with 1 item - this test will pass regardless
   of this patch.
2) demuxing of still image with 2 items - this test will fail without
   this patch and will pass with patch applied.

Partially fixes trac ticket #7621

Signed-off-by: Vignesh Venkatasubramanian <vigneshv@google.com>
Signed-off-by: James Zern <jzern@google.com>

libavformat/isom.h

@@ -317,6 +317,7 @@ typedef struct MOVContext {
     uint32_t mfra_size;
     uint32_t max_stts_delta;
     int is_still_picture_avif;
+    int primary_item_id;
 } MOVContext;
 
 int ff_mp4_read_descr_len(AVIOContext *pb);

libavformat/mov.c

@@ -7470,6 +7470,13 @@ static int rb_size(AVIOContext *pb, uint64_t* value, int size)
     return size;
 }
 
+static int mov_read_pitm(MOVContext *c, AVIOContext *pb, MOVAtom atom)
+{
+    avio_rb32(pb);  // version & flags.
+    c->primary_item_id = avio_rb16(pb);
+    return atom.size;
+}
+
 static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 {
     int version, offset_size, length_size, base_offset_size, index_size;
@@ -7526,34 +7533,25 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
         return AVERROR_PATCHWELCOME;
     }
     item_count = (version < 2) ? avio_rb16(pb) : avio_rb32(pb);
-    if (item_count > 1) {
-        // For still AVIF images, we only support one item. Second item will
-        // generally be found for AVIF images with alpha channel. We don't
-        // support them as of now.
-        av_log(c->fc, AV_LOG_ERROR, "iloc: item_count > 1 not supported.\n");
-        return AVERROR_PATCHWELCOME;
-    }
 
     // Populate the necessary fields used by mov_build_index.
-    sc->stsc_count = item_count;
+    sc->stsc_count = 1;
-    sc->stsc_data = av_malloc_array(item_count, sizeof(*sc->stsc_data));
+    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 = item_count;
+    sc->chunk_count = 1;
-    sc->chunk_offsets =
+    sc->chunk_offsets = av_malloc_array(1, sizeof(*sc->chunk_offsets));
-        av_malloc_array(item_count, sizeof(*sc->chunk_offsets));
     if (!sc->chunk_offsets)
         return AVERROR(ENOMEM);
-    sc->sample_count = item_count;
+    sc->sample_count = 1;
-    sc->sample_sizes =
+    sc->sample_sizes = av_malloc_array(1, sizeof(*sc->sample_sizes));
-        av_malloc_array(item_count, sizeof(*sc->sample_sizes));
     if (!sc->sample_sizes)
         return AVERROR(ENOMEM);
-    sc->stts_count = item_count;
+    sc->stts_count = 1;
-    sc->stts_data = av_malloc_array(item_count, sizeof(*sc->stts_data));
+    sc->stts_data = av_malloc_array(1, sizeof(*sc->stts_data));
     if (!sc->stts_data)
         return AVERROR(ENOMEM);
     sc->stts_data[0].count = 1;
@@ -7561,7 +7559,7 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     sc->stts_data[0].duration = 0;
 
     for (int i = 0; i < item_count; i++) {
-        (version < 2) ? avio_rb16(pb) : avio_rb32(pb);  // item_id;
+        int item_id = (version < 2) ? avio_rb16(pb) : avio_rb32(pb);
         if (version > 0)
             avio_rb16(pb);  // construction_method.
         avio_rb16(pb);  // data_reference_index.
@@ -7577,10 +7575,12 @@ 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;
             }
         }
+    }
 
     mov_build_index(c, st);
 
@@ -7696,6 +7696,7 @@ static const MOVParseTableEntry mov_default_parse_table[] = {
 { MKTAG('S','A','N','D'), mov_read_SAND }, /* non diegetic audio box */
 { MKTAG('i','l','o','c'), mov_read_iloc },
 { MKTAG('p','c','m','C'), mov_read_pcmc }, /* PCM configuration box */
+{ MKTAG('p','i','t','m'), mov_read_pitm },
 { 0, NULL }
 };
 

tests/fate/mov.mak

@@ -17,6 +17,10 @@ FATE_MOV = fate-mov-3elist \
            fate-mov-bbi-elst-starts-b \
            fate-mov-neg-firstpts-discard-frames \
            fate-mov-stream-shorter-than-movie \
+# FIXME: Uncomment these two lines once the test files are uploaded to the fate
+# server.
+#           fate-mov-avif-demux-still-image-1-item \
+#           fate-mov-avif-demux-still-image-multiple-items \
 
 FATE_MOV_FFPROBE = fate-mov-neg-firstpts-discard \
                    fate-mov-neg-firstpts-discard-vorbis \
@@ -138,6 +142,15 @@ FATE_MOV_FFMPEG_FFPROBE-$(call TRANSCODE, TTML SUBRIP, MP4 MOV, SRT_DEMUXER TTML
 fate-mov-mp4-ttml-stpp: CMD = transcode srt $(TARGET_SAMPLES)/sub/SubRip_capability_tester.srt mp4 "-map 0:s -c:s ttml -time_base:s 1:1000" "-map 0 -c copy" "-of json -show_entries packet:stream=index,codec_type,codec_tag_string,codec_tag,codec_name,time_base,start_time,duration_ts,duration,nb_frames,nb_read_packets:stream_tags"
 fate-mov-mp4-ttml-dfxp: CMD = transcode srt $(TARGET_SAMPLES)/sub/SubRip_capability_tester.srt mp4 "-map 0:s -c:s ttml -time_base:s 1:1000 -tag:s dfxp -strict unofficial" "-map 0 -c copy" "-of json -show_entries packet:stream=index,codec_type,codec_tag_string,codec_tag,codec_name,time_base,start_time,duration_ts,duration,nb_frames,nb_read_packets:stream_tags"
 
+# FIXME: Uncomment these two tests once the test files are uploaded to the fate
+# server.
+# avif demuxing - still image with 1 item.
+#fate-mov-avif-demux-still-image-1-item: CMD = framemd5 -i $(TARGET_SAMPLES)/avif/still_image.avif -c:v copy
+
+# avif demuxing - still image with multiple items. only the primary item will be
+# parsed.
+#fate-mov-avif-demux-still-image-multiple-items: CMD = framemd5 -i $(TARGET_SAMPLES)/avif/still_image_exif.avif -c:v copy
+
 # Resulting remux should have:
 # 1. first audio stream with AV_DISPOSITION_HEARING_IMPAIRED
 # 2. second audio stream with AV_DISPOSITION_VISUAL_IMPAIRED | DESCRIPTIONS

tests/ref/fate/mov-avif-demux-still-image-1-item

@@ -0,0 +1,11 @@
+#format: frame checksums
+#version: 2
+#hash: MD5
+#extradata 0,                              13, b52ae298d37128862ef1918cf916239c
+#tb 0: 1/1
+#media_type 0: video
+#codec_id 0: av1
+#dimensions 0: 352x288
+#sar 0: 1/1
+#stream#, dts,        pts, duration,     size, hash
+0,          0,          0,        1,    36265, 235b0c6e389c4084845981e08d60db04

tests/ref/fate/mov-avif-demux-still-image-multiple-items

@@ -0,0 +1,11 @@
+#format: frame checksums
+#version: 2
+#hash: MD5
+#extradata 0,                              13, b52ae298d37128862ef1918cf916239c
+#tb 0: 1/1
+#media_type 0: video
+#codec_id 0: av1
+#dimensions 0: 352x288
+#sar 0: 1/1
+#stream#, dts,        pts, duration,     size, hash
+0,          0,          0,        1,    36265, 235b0c6e389c4084845981e08d60db04