[FFmpeg-devel,2/3,v5] avformat/mov: add support for tile HEIF still images

diff --git a/libavformat/avformat.h b/libavformat/avformat.h
index 0b1c2e46b5..ad95306efb 100644
--- a/libavformat/avformat.h
+++ b/libavformat/avformat.h
@@ -811,6 +811,12 @@  typedef struct AVIndexEntry {
  * The video stream contains still images.
  */
 #define AV_DISPOSITION_STILL_IMAGE          (1 << 20)
+/**
+ * The video stream is intended to be merged with another stream before
+ * presentation.
+ * Used for example to signal the stream contains a tile from a HEIF grid.
+ */
+#define AV_DISPOSITION_TILE                 (1 << 21)
 
 /**
  * @return The AV_DISPOSITION_* flag corresponding to disp or a negative error
diff --git a/libavformat/dump.c b/libavformat/dump.c
index c9b7369bcd..de0e1d8b39 100644
--- a/libavformat/dump.c
+++ b/libavformat/dump.c
@@ -640,6 +640,8 @@  static void dump_stream_format(const AVFormatContext *ic, int i,
         av_log(NULL, log_level, " (still image)");
     if (st->disposition & AV_DISPOSITION_NON_DIEGETIC)
         av_log(NULL, log_level, " (non-diegetic)");
+    if (st->disposition & AV_DISPOSITION_TILE)
+        av_log(NULL, log_level, " (tile)");
     av_log(NULL, log_level, "\n");
 
     dump_metadata(NULL, st->metadata, extra_indent, log_level);
diff --git a/libavformat/isom.h b/libavformat/isom.h
index 77221d06e4..cedbd237d6 100644
--- a/libavformat/isom.h
+++ b/libavformat/isom.h
@@ -264,15 +264,24 @@  typedef struct MOVStreamContext {
 
 typedef struct HEIFItem {
     AVStream *st;
+    char *name;
     int item_id;
     int64_t extent_length;
     int64_t extent_offset;
-    int64_t size;
+    int tile_rows;
+    int tile_cols;
     int width;
     int height;
     int type;
+    int is_idat_relative;
 } HEIFItem;
 
+typedef struct HEIFGrid {
+    HEIFItem *item;
+    int16_t *tile_id_list;
+    int nb_tiles;
+} HEIFGrid;
+
 typedef struct MOVContext {
     const AVClass *class; ///< class for private options
     AVFormatContext *fc;
@@ -336,6 +345,10 @@  typedef struct MOVContext {
     int cur_item_id;
     HEIFItem *heif_item;
     int nb_heif_item;
+    HEIFGrid *heif_grid;
+    int nb_heif_grid;
+    int thmb_item_id;
+    int64_t idat_offset;
     int interleaved_read;
 } MOVContext;
 
diff --git a/libavformat/mov.c b/libavformat/mov.c
index 5fae777adb..237516ed0a 100644
--- a/libavformat/mov.c
+++ b/libavformat/mov.c
@@ -185,6 +185,30 @@  static int mov_read_mac_string(MOVContext *c, AVIOContext *pb, int len,
     return p - dst;
 }
 
+static AVStream *get_curr_st(MOVContext *c)
+{
+    AVStream *st = NULL;
+
+    if (c->fc->nb_streams < 1)
+        return NULL;
+
+    for (int i = 0; i < c->nb_heif_item; i++) {
+        HEIFItem *item = &c->heif_item[i];
+
+        if (!item->st)
+            continue;
+        if (item->st->id != c->cur_item_id)
+            continue;
+
+        st = item->st;
+        break;
+    }
+    if (!st)
+        st = c->fc->streams[c->fc->nb_streams-1];
+
+    return st;
+}
+
 static int mov_read_covr(MOVContext *c, AVIOContext *pb, int type, int len)
 {
     AVStream *st;
@@ -1767,9 +1791,9 @@  static int mov_read_colr(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     uint16_t color_primaries, color_trc, color_matrix;
     int ret;
 
-    if (c->fc->nb_streams < 1)
+    st = get_curr_st(c);
+    if (!st)
         return 0;
-    st = c->fc->streams[c->fc->nb_streams - 1];
 
     ret = ffio_read_size(pb, color_parameter_type, 4);
     if (ret < 0)
@@ -2117,9 +2141,9 @@  static int mov_read_glbl(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     AVStream *st;
     int ret;
 
-    if (c->fc->nb_streams < 1)
+    st = get_curr_st(c);
+    if (!st)
         return 0;
-    st = c->fc->streams[c->fc->nb_streams-1];
 
     if ((uint64_t)atom.size > (1<<30))
         return AVERROR_INVALIDDATA;
@@ -4951,12 +4975,10 @@  static int heif_add_stream(MOVContext *c, HEIFItem *item)
     st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO;
     st->codecpar->codec_id = mov_codec_id(st, item->type);
     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;
 
@@ -7784,11 +7806,55 @@  static int mov_read_pitm(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     return atom.size;
 }
 
+static int mov_read_idat(MOVContext *c, AVIOContext *pb, MOVAtom atom)
+{
+    c->idat_offset = avio_tell(pb);
+    return 0;
+}
+
+static int read_image_grid(AVFormatContext *s, AVStreamGroupTileGrid *tile_grid,
+                           HEIFItem *item)
+{
+    MOVContext *c = s->priv_data;
+    int64_t offset = 0, pos = avio_tell(s->pb);
+    uint8_t flags;
+
+    if (!(s->pb->seekable & AVIO_SEEKABLE_NORMAL)) {
+        av_log(c->fc, AV_LOG_INFO, "grid box with non seekable input\n");
+        return AVERROR_PATCHWELCOME;
+    }
+    if (item->is_idat_relative) {
+        if (!c->idat_offset) {
+            av_log(c->fc, AV_LOG_ERROR, "missing idat box required by the image grid\n");
+            return AVERROR_INVALIDDATA;
+        }
+        offset = c->idat_offset;
+    }
+
+    avio_seek(s->pb, item->extent_offset + offset, SEEK_SET);
+
+    avio_r8(s->pb);    /* version */
+    flags = avio_r8(s->pb);
+
+    item->tile_rows = avio_r8(s->pb) + 1;
+    item->tile_cols = avio_r8(s->pb) + 1;
+    /* actual width and height of output image */
+    tile_grid->width  = (flags & 1) ? avio_rb32(s->pb) : avio_rb16(s->pb);
+    tile_grid->height = (flags & 1) ? avio_rb32(s->pb) : avio_rb16(s->pb);
+
+    av_log(c->fc, AV_LOG_TRACE, "grid: grid_rows %d grid_cols %d output_width %d output_height %d\n",
+           item->tile_rows, item->tile_cols, tile_grid->width, tile_grid->height);
+
+    avio_seek(s->pb, pos, SEEK_SET);
+
+    return 0;
+}
+
 static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 {
     int version, offset_size, length_size, base_offset_size, index_size;
     int item_count, extent_count;
-    uint64_t base_offset, extent_offset, extent_length;
+    int64_t base_offset, extent_offset, extent_length;
     uint8_t value;
 
     if (c->found_moov) {
@@ -7845,6 +7911,8 @@  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 (offset_type == 1)
+                c->heif_item[i].is_idat_relative = 1;
             c->heif_item[i].extent_length = extent_length;
             c->heif_item[i].extent_offset = base_offset + extent_offset;
             av_log(c->fc, AV_LOG_TRACE, "iloc: item_idx %d, offset_type %d, "
@@ -7859,7 +7927,7 @@  static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 
 static int mov_read_infe(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 {
-    char item_name[128];
+    AVBPrint item_name;
     int64_t size = atom.size;
     uint32_t item_type;
     int item_id;
@@ -7869,27 +7937,32 @@  static int mov_read_infe(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     avio_rb24(pb);  // flags.
     size -= 4;
 
-    if (version != 2) {
-        av_log(c->fc, AV_LOG_ERROR, "infe: version != 2 not supported\n");
+    if (version < 2) {
+        av_log(c->fc, AV_LOG_ERROR, "infe: version < 2 not supported\n");
         return AVERROR_PATCHWELCOME;
     }
 
-    item_id = avio_rb16(pb);
+    item_id = version > 2 ? avio_rb32(pb) : avio_rb16(pb);
     avio_rb16(pb); // item_protection_index
     item_type = avio_rl32(pb);
     size -= 8;
-    size -= avio_get_str(pb, INT_MAX, item_name, sizeof(item_name));
 
-    av_log(c->fc, AV_LOG_TRACE, "infe: item_id %d, item_type %s, item_name %s\n",
-           item_id, av_fourcc2str(item_type), item_name);
+    av_bprint_init(&item_name, 0, AV_BPRINT_SIZE_UNLIMITED);
+    ret = ff_read_string_to_bprint_overwrite(pb, &item_name, size);
+    if (ret < 0) {
+        av_bprint_finalize(&item_name, NULL);
+        return ret;
+    }
 
-    // Skip all but the primary item until support is added
-    if (item_id != c->primary_item_id)
-        return 0;
+    av_log(c->fc, AV_LOG_TRACE, "infe: item_id %d, item_type %s, item_name %s\n",
+           item_id, av_fourcc2str(item_type), item_name.str);
 
+    size -= ret + 1;
     if (size > 0)
         avio_skip(pb, size);
 
+    if (ret)
+        av_bprint_finalize(&item_name, &c->heif_item[c->cur_item_id].name);
     c->heif_item[c->cur_item_id].item_id = item_id;
     c->heif_item[c->cur_item_id].type    = item_type;
 
@@ -7900,9 +7973,6 @@  static int mov_read_infe(MOVContext *c, AVIOContext *pb, MOVAtom atom)
         if (ret < 0)
             return ret;
         break;
-    default:
-        av_log(c->fc, AV_LOG_TRACE, "infe: ignoring item_type %s\n", av_fourcc2str(item_type));
-        break;
     }
 
     c->cur_item_id++;
@@ -7959,6 +8029,81 @@  static int mov_read_iref(MOVContext *c, AVIOContext *pb, MOVAtom atom)
     return mov_read_default(c, pb, atom);
 }
 
+static int mov_read_dimg(MOVContext *c, AVIOContext *pb, MOVAtom atom)
+{
+    HEIFItem *item = NULL;
+    HEIFGrid *grid;
+    int entries, i;
+    int from_item_id = avio_rb16(pb);
+
+    for (int i = 0; i < c->nb_heif_grid; i++) {
+        if (c->heif_grid[i].item->item_id == from_item_id) {
+            av_log(c->fc, AV_LOG_ERROR, "More than one 'dimg' box referencing the same 'grid'\n");
+            return AVERROR_INVALIDDATA;
+        }
+    }
+    for (int i = 0; i < c->nb_heif_item; i++) {
+        if (c->heif_item[i].item_id != from_item_id)
+            continue;
+        item = &c->heif_item[i];
+        if (item->type != MKTAG('g','r','i','d')) {
+            avpriv_report_missing_feature(c->fc, "Derived item of type %s", av_fourcc2str(item->type));
+            return 0;
+        }
+        break;
+    }
+    if (!item) {
+        av_log(c->fc, AV_LOG_ERROR, "Missing grid information\n");
+        return AVERROR_INVALIDDATA;
+    }
+
+    grid = av_realloc_array(c->heif_grid, c->nb_heif_grid + 1U,
+                            sizeof(*c->heif_grid));
+    if (!grid)
+        return AVERROR(ENOMEM);
+    c->heif_grid = grid;
+    grid = &grid[c->nb_heif_grid++];
+
+    entries = avio_rb16(pb);
+    grid->tile_id_list = av_malloc_array(entries, sizeof(*grid->tile_id_list));
+    if (!grid->tile_id_list)
+        return AVERROR(ENOMEM);
+    /* 'to' item ids */
+    for (i = 0; i < entries; i++)
+        grid->tile_id_list[i] = avio_rb16(pb);
+    grid->nb_tiles = entries;
+    grid->item = item;
+
+    av_log(c->fc, AV_LOG_TRACE, "dimg: from_item_id %d, entries %d\n",
+           from_item_id, entries);
+
+    return 0;
+}
+
+static int mov_read_thmb(MOVContext *c, AVIOContext *pb, MOVAtom atom)
+{
+    int entries;
+    int to_item_id, from_item_id = avio_rb16(pb);
+
+    entries = avio_rb16(pb);
+    if (entries > 1) {
+        avpriv_request_sample(c->fc, "More than one thmb entry");
+        return AVERROR_PATCHWELCOME;
+    }
+    /* 'to' item ids */
+    to_item_id = avio_rb16(pb);
+
+    if (to_item_id != c->primary_item_id)
+        return 0;
+
+    c->thmb_item_id = from_item_id;
+
+    av_log(c->fc, AV_LOG_TRACE, "thmb: from_item_id %d, entries %d\n",
+           from_item_id, entries);
+
+    return 0;
+}
+
 static int mov_read_ispe(MOVContext *c, AVIOContext *pb, MOVAtom atom)
 {
     uint32_t width, height;
@@ -8079,10 +8224,6 @@  static int mov_read_iprp(MOVContext *c, AVIOContext *pb, MOVAtom atom)
             av_log(c->fc, AV_LOG_TRACE, "ipma: property_index %d, item_id %d, item_type %s\n",
                    index + 1, item_id, av_fourcc2str(ref->type));
 
-            // Skip properties referencing items other than the primary item until support is added
-            if (item_id != c->primary_item_id)
-                continue;
-
             c->cur_item_id = item_id;
 
             ret = mov_read_default(c, &ref->b.pub,
@@ -8211,6 +8352,9 @@  static const MOVParseTableEntry mov_default_parse_table[] = {
 { MKTAG('p','c','m','C'), mov_read_pcmc }, /* PCM configuration box */
 { MKTAG('p','i','t','m'), mov_read_pitm },
 { MKTAG('e','v','c','C'), mov_read_glbl },
+{ MKTAG('d','i','m','g'), mov_read_dimg },
+{ MKTAG('t','h','m','b'), mov_read_thmb },
+{ MKTAG('i','d','a','t'), mov_read_idat },
 { MKTAG('i','r','e','f'), mov_read_iref },
 { MKTAG('i','s','p','e'), mov_read_ispe },
 { MKTAG('i','p','r','p'), mov_read_iprp },
@@ -8718,7 +8862,12 @@  static int mov_read_close(AVFormatContext *s)
 
     av_freep(&mov->aes_decrypt);
     av_freep(&mov->chapter_tracks);
+    for (i = 0; i < mov->nb_heif_item; i++)
+        av_freep(&mov->heif_item[i].name);
     av_freep(&mov->heif_item);
+    for (i = 0; i < mov->nb_heif_grid; i++)
+        av_freep(&mov->heif_grid[i].tile_id_list);
+    av_freep(&mov->heif_grid);
 
     return 0;
 }
@@ -8858,6 +9007,123 @@  fail:
     return ret;
 }
 
+static int mov_set_tile_grid_offsets(AVFormatContext *s, AVStreamGroup *stg,
+                                     const HEIFGrid *grid)
+{
+    AVStreamGroupTileGrid *tile_grid = stg->params.tile_grid;
+    int ret, x = 0, y = 0, i = 0;
+
+    tile_grid->offsets = av_calloc(grid->nb_tiles, sizeof(*tile_grid->offsets));
+    if (!tile_grid->offsets)
+        return AVERROR(ENOMEM);
+
+    while (y < tile_grid->coded_height) {
+        int left_col = i;
+
+        while (x < tile_grid->coded_width) {
+            if (i == grid->nb_tiles) {
+                ret = AVERROR(EINVAL);
+                goto fail;
+            }
+
+            tile_grid->offsets[i].x = x;
+            tile_grid->offsets[i].y = y;
+
+            x += stg->streams[i++]->codecpar->width;
+        }
+
+        if (x > tile_grid->coded_width) {
+            avpriv_request_sample(s, "Non uniform HEIF tiles");
+            ret = AVERROR_PATCHWELCOME;
+            goto fail;
+        }
+
+        x  = 0;
+        y += stg->streams[left_col]->codecpar->height;
+    }
+
+    if (y > tile_grid->coded_height || i != grid->nb_tiles) {
+        avpriv_request_sample(s, "Non uniform HEIF tiles");
+        ret = AVERROR_PATCHWELCOME;
+        goto fail;
+    }
+
+    return 0;
+fail:
+    av_freep(&tile_grid->offsets);
+
+    return ret;
+}
+
+static int mov_parse_tiles(AVFormatContext *s)
+{
+    MOVContext *mov = s->priv_data;
+    int err;
+
+    for (int i = 0; i < mov->nb_heif_grid; i++) {
+        AVStreamGroup *stg = avformat_stream_group_create(s, AV_STREAM_GROUP_PARAMS_TILE_GRID, NULL);
+        AVStreamGroupTileGrid *tile_grid;
+        HEIFGrid *grid = &mov->heif_grid[i];
+        int coded_width = 0, coded_height = 0;
+        int size;
+
+        if (!stg)
+            return AVERROR(ENOMEM);
+
+        tile_grid = stg->params.tile_grid;
+        err = read_image_grid(s, tile_grid, grid->item);
+        if (err < 0)
+            return err;
+
+        for (int j = 0; j < grid->nb_tiles; j++) {
+            int tile_id = grid->tile_id_list[j];
+
+            for (int k = 0; k < mov->nb_heif_item; k++) {
+                const HEIFItem *item = &mov->heif_item[k];
+                AVStream *st = item->st;
+
+                if (item->item_id != tile_id)
+                    continue;
+                if (!st) {
+                    av_log(s, AV_LOG_ERROR, "HEIF tile %d doesn't reference a stream\n", tile_id);
+                    return AVERROR_INVALIDDATA;
+                }
+
+                st->codecpar->width  = item->width;
+                st->codecpar->height = item->height;
+
+                err = avformat_stream_group_add_stream(stg, st);
+                if (err == AVERROR(EEXIST))
+                    return AVERROR_INVALIDDATA;
+                else if (err < 0)
+                    return err;
+
+                st->disposition |= AV_DISPOSITION_TILE;
+                break;
+            }
+        }
+
+        size = grid->item->tile_rows * grid->item->tile_cols;
+        for (int i = 0; i < grid->item->tile_cols; i++)
+            coded_width += stg->streams[i]->codecpar->width;
+        for (int i = 0; i < size; i += grid->item->tile_cols)
+            coded_height += stg->streams[i]->codecpar->height;
+
+        tile_grid->coded_width  = coded_width;
+        tile_grid->coded_height = coded_height;
+
+        err = mov_set_tile_grid_offsets(s, stg, grid);
+        if (err < 0)
+            return AVERROR_INVALIDDATA;
+
+        if (grid->item->name)
+            av_dict_set(&stg->metadata, "title", grid->item->name, 0);
+    }
+
+
+    return 0;
+}
+
 static int mov_read_header(AVFormatContext *s)
 {
     MOVContext *mov = s->priv_data;
@@ -8874,6 +9140,8 @@  static int mov_read_header(AVFormatContext *s)
 
     mov->fc = s;
     mov->trak_index = -1;
+    mov->thmb_item_id = -1;
+    mov->primary_item_id = -1;
     /* .mov and .mp4 aren't streamable anyway (only progressive download if moov is before mdat) */
     if (pb->seekable & AVIO_SEEKABLE_NORMAL)
         atom.size = avio_size(pb);
@@ -8896,20 +9164,43 @@  static int mov_read_header(AVFormatContext *s)
     av_log(mov->fc, AV_LOG_TRACE, "on_parse_exit_offset=%"PRId64"\n", avio_tell(pb));
 
     if (mov->found_iloc) {
+        if (mov->nb_heif_grid) {
+            err = mov_parse_tiles(s);
+            if (err < 0)
+                return err;
+        }
+
         for (i = 0; i < mov->nb_heif_item; i++) {
             HEIFItem *item = &mov->heif_item[i];
             MOVStreamContext *sc;
             AVStream *st;
+            int64_t offset = 0;
 
-            if (!item->st)
+            if (!item->st) {
+                if (item->item_id == mov->thmb_item_id) {
+                    av_log(s, AV_LOG_ERROR, "HEIF thumbnail doesn't reference a stream\n");
+                    return AVERROR_INVALIDDATA;
+                }
                 continue;
+            }
+            if (item->is_idat_relative) {
+                if (!mov->idat_offset) {
+                    av_log(s, AV_LOG_ERROR, "Missing idat box for item %d\n", item->item_id);
+                    return AVERROR_INVALIDDATA;
+                }
+                offset = mov->idat_offset;
+            }
 
             st = item->st;
             sc = st->priv_data;
             st->codecpar->width  = item->width;
             st->codecpar->height = item->height;
+
             sc->sample_sizes[0]  = item->extent_length;
-            sc->chunk_offsets[0] = item->extent_offset;
+            sc->chunk_offsets[0] = item->extent_offset + offset;
+
+            if (item->item_id == mov->primary_item_id)
+                st->disposition |= AV_DISPOSITION_DEFAULT;
 
             mov_build_index(mov, st);
         }