[FFmpeg-devel] [PATCH 1/3 v7] avformat: add a Tile Grid stream group type

[FFmpeg-devel] [PATCH 1/3 v7] avformat: add a Tile Grid stream group type

[James Almer]

This will be used to support tiled image formats like HEIF.

Signed-off-by: James Almer <jamrial@gmail.com>
---
Fixed comment about sizeof(AVStreamGroupTileGrid).

 libavformat/avformat.c |   5 +++
 libavformat/avformat.h | 100 +++++++++++++++++++++++++++++++++++++++++
 libavformat/dump.c     |  29 ++++++++++++
 libavformat/options.c  |  32 +++++++++++++
 4 files changed, 166 insertions(+)

diff --git a/libavformat/avformat.c b/libavformat/avformat.c
index 8e8c6fbe55..32ef440207 100644
--- a/libavformat/avformat.c
+++ b/libavformat/avformat.c
@@ -100,6 +100,11 @@ void ff_free_stream_group(AVStreamGroup **pstg)
         av_iamf_mix_presentation_free(&stg->params.iamf_mix_presentation);
         break;
     }
+    case AV_STREAM_GROUP_PARAMS_TILE_GRID:
+        av_opt_free(stg->params.tile_grid);
+        av_freep(&stg->params.tile_grid->offsets);
+        av_freep(&stg->params.tile_grid);
+        break;
     default:
         break;
     }
diff --git a/libavformat/avformat.h b/libavformat/avformat.h
index 5d0fe82250..0b1c2e46b5 100644
--- a/libavformat/avformat.h
+++ b/libavformat/avformat.h
@@ -1018,10 +1018,109 @@ typedef struct AVStream {
     int pts_wrap_bits;
 } AVStream;
 
+/**
+ * AVStreamGroupTileGrid holds information on how to combine several
+ * independent images on a single grid for presentation. None of the tiles may
+ * overlap inside the grid.
+ *
+ * The following is an example of a simple grid with 3 rows and 4 columns:
+ *
+ * +---+---+---+---+
+ * | 0 | 1 | 2 | 3 |
+ * +---+---+---+---+
+ * | 4 | 5 | 6 | 7 |
+ * +---+---+---+---+
+ * | 8 | 9 |10 |11 |
+ * +---+---+---+---+
+ *
+ * Assuming all tiles have a dimension of 512x512, the
+ * @ref AVStreamGroupTileGrid.offsets "offset" of the topleft pixel of
+ * the first @ref AVStreamGroup.streams "stream" in the group is "0,0", the
+ * @ref AVStreamGroupTileGrid.offsets "offset" of the topleft pixel of
+ * the second @ref AVStreamGroup.streams "stream" in the group is "512,0", the
+ * @ref AVStreamGroupTileGrid.offsets "offset" of the topleft pixel of
+ * the fifth @ref AVStreamGroup.streams "stream" in the group is "0,512", the
+ * @ref AVStreamGroupTileGrid.offsets "offset", of the topleft pixel of
+ * the sixth @ref AVStreamGroup.streams "stream" in the group is "512,512",
+ * etc.
+ *
+ * sizeof(AVStreamGroupTileGrid) is not a part of the ABI and may only be
+ * allocated by avformat_stream_group_create().
+ */
+typedef struct AVStreamGroupTileGrid {
+    const AVClass *av_class;
+
+    /**
+     * Width of the final image in the grid.
+     *
+     * Must be > 0.
+     */
+    int coded_width;
+    /**
+     * Width of the final image in the grid.
+     *
+     * Must be > 0.
+     */
+    int coded_height;
+
+    /**
+     * An @ref AVStreamGroup.nb_streams "nb_streams" sized array of offsets in
+     * pixels from the topleft edge of the grid, indicating where each stream
+     * should be placed.
+     * It must be allocated with the av_malloc() family of functions.
+     *
+     * - demuxing: set by libavformat, must not be modified by the caller.
+     * - muxing: set by the caller before avformat_write_header().
+     *
+     * Freed by libavformat in avformat_free_context().
+     */
+    struct {
+        int x;
+        int y;
+    } *offsets;
+
+    /**
+     * Offset in pixels from the left edge of the grid where the actual image
+     * meant for presentation starts.
+     *
+     * This field must be >= 0 and <= @ref coded_width.
+     */
+    int horizontal_offset;
+    /**
+     * Offset in pixels from the top edge of the grid where the actual image
+     * meant for presentation starts.
+     *
+     * This field must be >= 0 and <= @ref coded_height.
+     */
+    int vertical_offset;
+
+    /**
+     * Width of the final image for presentation.
+     *
+     * Must be > 0 and <= (@ref coded_width - @ref horizontal_offset).
+     * When it's not equal to (@ref coded_width - @ref horizontal_offset), the
+     * result of (@ref coded_width - width - @ref horizontal_offset) is the
+     * amount amount of pixels to be cropped from the right edge of the
+     * final image before presentation.
+     */
+    int width;
+    /**
+     * Height of the final image for presentation.
+     *
+     * Must be > 0 and <= (@ref coded_height - @ref vertical_offset).
+     * When it's not equal to (@ref coded_height - @ref vertical_offset), the
+     * result of (@ref coded_height - height - @ref vertical_offset) is the
+     * amount amount of pixels to be cropped from the bottom edge of the
+     * final image before presentation.
+     */
+    int height;
+} AVStreamGroupTileGrid;
+
 enum AVStreamGroupParamsType {
     AV_STREAM_GROUP_PARAMS_NONE,
     AV_STREAM_GROUP_PARAMS_IAMF_AUDIO_ELEMENT,
     AV_STREAM_GROUP_PARAMS_IAMF_MIX_PRESENTATION,
+    AV_STREAM_GROUP_PARAMS_TILE_GRID,
 };
 
 struct AVIAMFAudioElement;
@@ -1062,6 +1161,7 @@ typedef struct AVStreamGroup {
     union {
         struct AVIAMFAudioElement *iamf_audio_element;
         struct AVIAMFMixPresentation *iamf_mix_presentation;
+        struct AVStreamGroupTileGrid *tile_grid;
     } params;
 
     /**
diff --git a/libavformat/dump.c b/libavformat/dump.c
index aff51b43f6..c9b7369bcd 100644
--- a/libavformat/dump.c
+++ b/libavformat/dump.c
@@ -22,6 +22,7 @@
 #include <stdio.h>
 #include <stdint.h>
 
+#include "libavutil/avstring.h"
 #include "libavutil/channel_layout.h"
 #include "libavutil/display.h"
 #include "libavutil/iamf.h"
@@ -721,6 +722,34 @@ static void dump_stream_group(const AVFormatContext *ic, uint8_t *printed,
         }
         break;
     }
+    case AV_STREAM_GROUP_PARAMS_TILE_GRID: {
+        const AVStreamGroupTileGrid *tile_grid = stg->params.tile_grid;
+        AVCodecContext *avctx = avcodec_alloc_context3(NULL);
+        const char *ptr = NULL;
+        av_log(NULL, AV_LOG_INFO, " Tile Grid:");
+        if (avctx && stg->nb_streams && !avcodec_parameters_to_context(avctx, stg->streams[0]->codecpar)) {
+            avctx->width  = tile_grid->width;
+            avctx->height = tile_grid->height;
+            avctx->coded_width  = tile_grid->coded_width;
+            avctx->coded_height = tile_grid->coded_height;
+            if (ic->dump_separator)
+                av_opt_set(avctx, "dump_separator", ic->dump_separator, 0);
+            buf[0] = 0;
+            avcodec_string(buf, sizeof(buf), avctx, is_output);
+            ptr = av_stristr(buf, " ");
+        }
+        avcodec_free_context(&avctx);
+        if (ptr)
+            av_log(NULL, AV_LOG_INFO, "%s", ptr);
+        av_log(NULL, AV_LOG_INFO, "\n");
+        dump_metadata(NULL, stg->metadata, "    ", AV_LOG_INFO);
+        for (int i = 0; i < stg->nb_streams; i++) {
+            const AVStream *st = stg->streams[i];
+            dump_stream_format(ic, st->index, i, index, is_output, AV_LOG_VERBOSE);
+            printed[st->index] = 1;
+        }
+        break;
+    }
     default:
         break;
     }
diff --git a/libavformat/options.c b/libavformat/options.c
index 75ec86ce05..ed96ba4afb 100644
--- a/libavformat/options.c
+++ b/libavformat/options.c
@@ -337,6 +337,26 @@ fail:
     return NULL;
 }
 
+#define FLAGS AV_OPT_FLAG_ENCODING_PARAM | AV_OPT_FLAG_VIDEO_PARAM
+#define OFFSET(x) offsetof(AVStreamGroupTileGrid, x)
+static const AVOption tile_grid_options[] = {
+    { "grid_size", "size of the output image", OFFSET(coded_width),
+        AV_OPT_TYPE_IMAGE_SIZE, { .str = NULL }, 0, INT_MAX, FLAGS },
+    { "horizontal_offset", NULL, OFFSET(horizontal_offset), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, INT_MAX, FLAGS },
+    { "vertical_offset", NULL, OFFSET(vertical_offset),     AV_OPT_TYPE_INT, { .i64 = 0 }, 0, INT_MAX, FLAGS },
+    { "output_size", "size of valid pixels in output image meant for presentation", OFFSET(width),
+        AV_OPT_TYPE_IMAGE_SIZE, { .str = NULL }, 0, INT_MAX, FLAGS },
+    { NULL },
+};
+#undef FLAGS
+#undef OFFSET
+
+static const AVClass tile_grid_class = {
+    .class_name = "AVStreamGroupTileGrid",
+    .version    = LIBAVUTIL_VERSION_INT,
+    .option     = tile_grid_options,
+};
+
 static void *stream_group_child_next(void *obj, void *prev)
 {
     AVStreamGroup *stg = obj;
@@ -346,6 +366,8 @@ static void *stream_group_child_next(void *obj, void *prev)
             return stg->params.iamf_audio_element;
         case AV_STREAM_GROUP_PARAMS_IAMF_MIX_PRESENTATION:
             return stg->params.iamf_mix_presentation;
+        case AV_STREAM_GROUP_PARAMS_TILE_GRID:
+            return stg->params.tile_grid;
         default:
             break;
         }
@@ -368,6 +390,9 @@ static const AVClass *stream_group_child_iterate(void **opaque)
     case AV_STREAM_GROUP_PARAMS_IAMF_MIX_PRESENTATION:
         ret = av_iamf_mix_presentation_get_class();
         break;
+    case AV_STREAM_GROUP_PARAMS_TILE_GRID:
+        ret = &tile_grid_class;
+        break;
     default:
         break;
     }
@@ -429,6 +454,13 @@ AVStreamGroup *avformat_stream_group_create(AVFormatContext *s,
         if (!stg->params.iamf_mix_presentation)
             goto fail;
         break;
+    case AV_STREAM_GROUP_PARAMS_TILE_GRID:
+        stg->params.tile_grid = av_mallocz(sizeof(*stg->params.tile_grid));
+        if (!stg->params.tile_grid)
+            goto fail;
+        stg->params.tile_grid->av_class = &tile_grid_class;
+        av_opt_set_defaults(stg->params.tile_grid);
+        break;
     default:
         goto fail;
     }
-- 
2.43.0

_______________________________________________
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".

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

[James Almer]

Export each tile as its own stream, and the grid information as a Stream Group
of type TILE_GRID.
This also enables exporting other stream items like thumbnails, which may be
present in non tiled HEIF images too. For those, the primary stream will be
tagged with the default disposition.

Based on a patch by Swaraj Hota

Signed-off-by: James Almer <jamrial@gmail.com>
---
Now supports exporting more than one grid if present, as well as the item name
for the grid as stream group metadata.

 libavformat/avformat.h |   6 +
 libavformat/dump.c     |   2 +
 libavformat/isom.h     |  15 +-
 libavformat/mov.c      | 343 +++++++++++++++++++++++++++++++++++++----
 4 files changed, 339 insertions(+), 27 deletions(-)

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);
         }
-- 
2.43.0

_______________________________________________
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".

[FFmpeg-devel] [PATCH 3/3 v4] fate/mov: test remuxing all stream heif items

[James Almer]

Signed-off-by: James Almer <jamrial@gmail.com>
---
No changes since last version.

 tests/fate/mov.mak                                       | 2 +-
 tests/ref/fate/mov-heic-demux-still-image-multiple-items | 7 +++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/tests/fate/mov.mak b/tests/fate/mov.mak
index f202f36d96..f549ae33d7 100644
--- a/tests/fate/mov.mak
+++ b/tests/fate/mov.mak
@@ -156,7 +156,7 @@ fate-mov-heic-demux-still-image-1-item: CMD = framemd5 -i $(TARGET_SAMPLES)/heif
 
 FATE_MOV_FFMPEG-$(call FRAMEMD5, MOV, HEVC, HEVC_PARSER) \
                            += fate-mov-heic-demux-still-image-multiple-items
-fate-mov-heic-demux-still-image-multiple-items: CMD = framemd5 -i $(TARGET_SAMPLES)/heif-conformance/C003.heic -c:v copy
+fate-mov-heic-demux-still-image-multiple-items: CMD = framemd5 -i $(TARGET_SAMPLES)/heif-conformance/C003.heic -c:v copy -map 0
 
 # Resulting remux should have:
 # 1. first audio stream with AV_DISPOSITION_HEARING_IMPAIRED
diff --git a/tests/ref/fate/mov-heic-demux-still-image-multiple-items b/tests/ref/fate/mov-heic-demux-still-image-multiple-items
index c850c1ff9c..753cef267a 100644
--- a/tests/ref/fate/mov-heic-demux-still-image-multiple-items
+++ b/tests/ref/fate/mov-heic-demux-still-image-multiple-items
@@ -2,10 +2,17 @@
 #version: 2
 #hash: MD5
 #extradata 0,                             100, 5444bf01e03182c73ae957179d560f4d
+#extradata 1,                             100, 5444bf01e03182c73ae957179d560f4d
 #tb 0: 1/1
 #media_type 0: video
 #codec_id 0: hevc
 #dimensions 0: 1280x720
 #sar 0: 0/1
+#tb 1: 1/1
+#media_type 1: video
+#codec_id 1: hevc
+#dimensions 1: 1280x720
+#sar 1: 0/1
 #stream#, dts,        pts, duration,     size, hash
 0,          0,          0,        1,   111554, 03ceabfab39afd2e2e796b9362111f32
+1,          0,          0,        1,   112393, daa001d351c088a5bc328459e2501c95
-- 
2.43.0

_______________________________________________
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".