[FFmpeg-devel] [PATCH 2/4 v8] avformat/mov: add support for tile HEIF still images
James Almer
jamrial at gmail.com
Sun Feb 11 20:56:59 EET 2024
Export tiles as streams, 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.
Based on a patch by Swaraj Hota
Signed-off-by: James Almer <jamrial at gmail.com>
---
libavformat/avformat.c | 8 +
libavformat/avformat.h | 6 +
libavformat/dump.c | 2 +
libavformat/internal.h | 5 +
libavformat/isom.h | 16 +-
libavformat/mov.c | 492 +++++++++++++++++++++++++++++++++++++----
6 files changed, 484 insertions(+), 45 deletions(-)
diff --git a/libavformat/avformat.c b/libavformat/avformat.c
index f53ba4ce58..eb898223d2 100644
--- a/libavformat/avformat.c
+++ b/libavformat/avformat.c
@@ -119,6 +119,14 @@ void ff_remove_stream(AVFormatContext *s, AVStream *st)
ff_free_stream(&s->streams[ --s->nb_streams ]);
}
+void ff_remove_stream_group(AVFormatContext *s, AVStreamGroup *stg)
+{
+ av_assert0(s->nb_stream_groups > 0);
+ av_assert0(s->stream_groups[ s->nb_stream_groups - 1 ] == stg);
+
+ ff_free_stream_group(&s->stream_groups[ --s->nb_stream_groups ]);
+}
+
/* XXX: suppress the packet queue */
void ff_flush_packet_queue(AVFormatContext *s)
{
diff --git a/libavformat/avformat.h b/libavformat/avformat.h
index 92751e5aee..27b052bad5 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 756db8c87e..6123ca58a5 100644
--- a/libavformat/dump.c
+++ b/libavformat/dump.c
@@ -657,6 +657,8 @@ 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/internal.h b/libavformat/internal.h
index c66f959e9f..5603ca1ab5 100644
--- a/libavformat/internal.h
+++ b/libavformat/internal.h
@@ -637,6 +637,11 @@ void ff_remove_stream(AVFormatContext *s, AVStream *st);
* is not yet attached to an AVFormatContext.
*/
void ff_free_stream_group(AVStreamGroup **pstg);
+/**
+ * Remove a stream group from its AVFormatContext and free it.
+ * The stream group must be the last stream group of the AVFormatContext.
+ */
+void ff_remove_stream_group(AVFormatContext *s, AVStreamGroup *stg);
unsigned int ff_codec_get_tag(const AVCodecTag *tags, enum AVCodecID id);
diff --git a/libavformat/isom.h b/libavformat/isom.h
index a4cca4c798..d96722fe79 100644
--- a/libavformat/isom.h
+++ b/libavformat/isom.h
@@ -267,15 +267,25 @@ 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;
+ unsigned int *tile_idx_list;
+ int16_t *tile_id_list;
+ int nb_tiles;
+} HEIFGrid;
+
typedef struct MOVContext {
const AVClass *class; ///< class for private options
AVFormatContext *fc;
@@ -339,6 +349,10 @@ 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 42b0135987..23343c7ae2 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;
@@ -7809,11 +7831,18 @@ 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 mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
{
+ HEIFItem *heif_item;
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) {
@@ -7832,17 +7861,20 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
base_offset_size = (value >> 4) & 0xF;
index_size = !version ? 0 : (value & 0xF);
if (index_size) {
- av_log(c->fc, AV_LOG_ERROR, "iloc: index_size != 0 not supported.\n");
+ avpriv_report_missing_feature(c->fc, "iloc: index_size != 0");
return AVERROR_PATCHWELCOME;
}
item_count = (version < 2) ? avio_rb16(pb) : avio_rb32(pb);
- if (!c->heif_item) {
- c->heif_item = av_calloc(item_count, sizeof(*c->heif_item));
- if (!c->heif_item)
- return AVERROR(ENOMEM);
- c->nb_heif_item = item_count;
- }
+ heif_item = av_realloc_array(c->heif_item, item_count, sizeof(*c->heif_item));
+ if (!heif_item)
+ return AVERROR(ENOMEM);
+ c->heif_item = heif_item;
+ if (item_count > c->nb_heif_item)
+ memset(c->heif_item + c->nb_heif_item, 0,
+ sizeof(*c->heif_item) * (item_count - c->nb_heif_item));
+ c->nb_heif_item = FFMAX(c->nb_heif_item, item_count);
+ c->cur_item_id = 0;
av_log(c->fc, AV_LOG_TRACE, "iloc: item_count %d\n", item_count);
for (int i = 0; i < item_count; i++) {
@@ -7852,7 +7884,7 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
if (avio_feof(pb))
return AVERROR_INVALIDDATA;
if (offset_type > 1) {
- avpriv_request_sample(c->fc, "iloc offset type %d", offset_type);
+ avpriv_report_missing_feature(c->fc, "iloc offset type %d", offset_type);
return AVERROR_PATCHWELCOME;
}
c->heif_item[i].item_id = item_id;
@@ -7863,13 +7895,15 @@ static int mov_read_iloc(MOVContext *c, AVIOContext *pb, MOVAtom atom)
extent_count = avio_rb16(pb);
if (extent_count > 1) {
// For still AVIF images, we only support one extent item.
- av_log(c->fc, AV_LOG_ERROR, "iloc: extent_count > 1 not supported\n");
+ avpriv_report_missing_feature(c->fc, "iloc: extent_count > 1");
return AVERROR_PATCHWELCOME;
}
for (int j = 0; j < extent_count; j++) {
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, "
@@ -7884,7 +7918,7 @@ 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;
@@ -7894,27 +7928,32 @@ 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;
@@ -7925,9 +7964,6 @@ 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++;
@@ -7937,6 +7973,7 @@ static int mov_read_infe(MOVContext *c, AVIOContext *pb, MOVAtom atom)
static int mov_read_iinf(MOVContext *c, AVIOContext *pb, MOVAtom atom)
{
+ HEIFItem *heif_item;
int entry_count;
int version, ret;
@@ -7954,13 +7991,14 @@ static int mov_read_iinf(MOVContext *c, AVIOContext *pb, MOVAtom atom)
avio_rb24(pb); // flags.
entry_count = version ? avio_rb32(pb) : avio_rb16(pb);
- if (!c->heif_item) {
- c->heif_item = av_calloc(entry_count, sizeof(*c->heif_item));
- if (!c->heif_item)
- return AVERROR(ENOMEM);
- c->nb_heif_item = entry_count;
- }
-
+ heif_item = av_realloc_array(c->heif_item, entry_count, sizeof(*c->heif_item));
+ if (!heif_item)
+ return AVERROR(ENOMEM);
+ c->heif_item = heif_item;
+ if (entry_count > c->nb_heif_item)
+ memset(c->heif_item + c->nb_heif_item, 0,
+ sizeof(*c->heif_item) * (entry_count - c->nb_heif_item));
+ c->nb_heif_item = FFMAX(c->nb_heif_item, entry_count);
c->cur_item_id = 0;
for (int i = 0; i < entry_count; i++) {
@@ -7977,11 +8015,125 @@ static int mov_read_iinf(MOVContext *c, AVIOContext *pb, MOVAtom atom)
return 0;
}
+static int mov_read_iref_dimg(MOVContext *c, AVIOContext *pb, int version)
+{
+ HEIFItem *item = NULL;
+ HEIFGrid *grid;
+ int entries, i;
+ int from_item_id = version ? avio_rb32(pb) : 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];
+
+ switch (item->type) {
+ case MKTAG('g','r','i','d'):
+ case MKTAG('i','o','v','l'):
+ break;
+ default:
+ 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));
+ grid->tile_idx_list = av_calloc(entries, sizeof(*grid->tile_idx_list));
+ if (!grid->tile_id_list || !grid->tile_idx_list)
+ return AVERROR(ENOMEM);
+ /* 'to' item ids */
+ for (i = 0; i < entries; i++)
+ grid->tile_id_list[i] = version ? avio_rb32(pb) : 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_iref_thmb(MOVContext *c, AVIOContext *pb, int version)
+{
+ int entries;
+ int to_item_id, from_item_id = version ? avio_rb32(pb) : avio_rb16(pb);
+
+ entries = avio_rb16(pb);
+ if (entries > 1) {
+ avpriv_request_sample(c->fc, "thmb in iref referencing several items");
+ return AVERROR_PATCHWELCOME;
+ }
+ /* 'to' item ids */
+ to_item_id = version ? avio_rb32(pb) : 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_iref(MOVContext *c, AVIOContext *pb, MOVAtom atom)
{
- avio_rb32(pb); /* version and flags */
+ int version = avio_r8(pb);
+ avio_rb24(pb); // flags
atom.size -= 4;
- return mov_read_default(c, pb, atom);
+
+ if (version > 1) {
+ av_log(c->fc, AV_LOG_WARNING, "Unknown iref box version %d\n", version);
+ return 0;
+ }
+
+ while (atom.size) {
+ uint32_t type, size = avio_rb32(pb);
+ int64_t next = avio_tell(pb);
+
+ if (size < 14 || next < 0 || next > INT64_MAX - size)
+ return AVERROR_INVALIDDATA;
+
+ next += size - 4;
+ type = avio_rl32(pb);
+ switch (type) {
+ case MKTAG('d','i','m','g'):
+ mov_read_iref_dimg(c, pb, version);
+ break;
+ case MKTAG('t','h','m','b'):
+ mov_read_iref_thmb(c, pb, version);
+ break;
+ default:
+ av_log(c->fc, AV_LOG_DEBUG, "Unknown iref type %s size %"PRIu32"\n",
+ av_fourcc2str(type), size);
+ }
+
+ atom.size -= size;
+ avio_seek(pb, next, SEEK_SET);
+ }
+ return 0;
}
static int mov_read_ispe(MOVContext *c, AVIOContext *pb, MOVAtom atom)
@@ -8104,10 +8256,6 @@ 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,
@@ -8236,6 +8384,7 @@ 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('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 },
@@ -8745,7 +8894,14 @@ 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[i].tile_idx_list);
+ }
+ av_freep(&mov->heif_grid);
return 0;
}
@@ -8885,6 +9041,229 @@ fail:
return ret;
}
+static int read_image_grid(AVFormatContext *s, AVStreamGroup *stg,
+ AVStreamGroupTileGrid *tile_grid, HEIFGrid *grid)
+{
+ MOVContext *c = s->priv_data;
+ HEIFItem *item = grid->item;
+ int64_t offset = 0, pos = avio_tell(s->pb);
+ int x = 0, y = 0, i = 0;
+ int flags, size;
+
+ 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);
+
+ size = item->tile_rows * item->tile_cols;
+ for (int i = 0; i < item->tile_cols; i++)
+ tile_grid->coded_width += stg->streams[i]->codecpar->width;
+ for (int i = 0; i < size; i += item->tile_cols)
+ tile_grid->coded_height += stg->streams[i]->codecpar->height;
+
+ tile_grid->offsets = av_calloc(tile_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 == tile_grid->nb_tiles)
+ return AVERROR(EINVAL);
+
+ tile_grid->offsets[i].horizontal = x;
+ tile_grid->offsets[i].vertical = y;
+
+ x += stg->streams[i++]->codecpar->width;
+ }
+
+ if (x > tile_grid->coded_width) {
+ avpriv_request_sample(s, "Non uniform HEIF tiles");
+ return AVERROR_PATCHWELCOME;
+ }
+
+ x = 0;
+ y += stg->streams[left_col]->codecpar->height;
+ }
+
+ if (y > tile_grid->coded_height || i != tile_grid->nb_tiles) {
+ avpriv_request_sample(s, "Non uniform HEIF tiles");
+ return AVERROR_PATCHWELCOME;
+ }
+
+ return 0;
+}
+
+static int read_image_overlay(AVFormatContext *s, AVStreamGroupTileGrid *tile_grid,
+ HEIFGrid *grid)
+{
+ MOVContext *c = s->priv_data;
+ HEIFItem *item = grid->item;
+ uint16_t canvas_fill_value[4];
+ int64_t offset = 0, pos = avio_tell(s->pb);
+ int ret = 0, flags;
+
+ if (!(s->pb->seekable & AVIO_SEEKABLE_NORMAL)) {
+ av_log(c->fc, AV_LOG_INFO, "iovl 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 overlay\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);
+
+ for (int i = 0; i < 4; i++)
+ canvas_fill_value[i] = avio_rb16(s->pb);
+ av_log(c->fc, AV_LOG_TRACE, "iovl: canvas_fill_value { %u, %u, %u, %u }\n",
+ canvas_fill_value[0], canvas_fill_value[1],
+ canvas_fill_value[2], canvas_fill_value[3]);
+ for (int i = 0; i < 4; i++)
+ tile_grid->background[i] = canvas_fill_value[i];
+
+ /* actual width and height of output image */
+ tile_grid->width =
+ tile_grid->coded_width = (flags & 1) ? avio_rb32(s->pb) : avio_rb16(s->pb);
+ tile_grid->height =
+ tile_grid->coded_height = (flags & 1) ? avio_rb32(s->pb) : avio_rb16(s->pb);
+ av_log(c->fc, AV_LOG_TRACE, "iovl: output_width %d, output_height %d\n",
+ tile_grid->width, tile_grid->height);
+
+ tile_grid->offsets = av_malloc_array(tile_grid->nb_tiles, sizeof(*tile_grid->offsets));
+ if (!tile_grid->offsets) {
+ ret = AVERROR(ENOMEM);
+ goto fail;
+ }
+
+ for (int i = 0; i < tile_grid->nb_tiles; i++) {
+ tile_grid->offsets[i].idx = grid->tile_idx_list[i];
+ tile_grid->offsets[i].horizontal = (flags & 1) ? avio_rb32(s->pb) : avio_rb16(s->pb);
+ tile_grid->offsets[i].vertical = (flags & 1) ? avio_rb32(s->pb) : avio_rb16(s->pb);
+ av_log(c->fc, AV_LOG_TRACE, "iovl: stream_idx[%d] %u, horizontal_offset[%d] %d, vertical_offset[%d] %d\n",
+ i, tile_grid->offsets[i].idx,
+ i, tile_grid->offsets[i].horizontal, i, tile_grid->offsets[i].vertical);
+ }
+
+fail:
+ avio_seek(s->pb, pos, SEEK_SET);
+
+ return ret;
+}
+
+static int mov_parse_tiles(AVFormatContext *s)
+{
+ MOVContext *mov = s->priv_data;
+
+ 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 err, loop = 1;
+
+ if (!stg)
+ return AVERROR(ENOMEM);
+
+ stg->id = grid->item->item_id;
+ tile_grid = stg->params.tile_grid;
+
+ 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_WARNING, "HEIF item id %d from grid id %d doesn't "
+ "reference a stream\n",
+ tile_id, grid->item->item_id);
+ ff_remove_stream_group(s, stg);
+ loop = 0;
+ break;
+ }
+
+ err = avformat_stream_group_add_stream(stg, st);
+ if (err == AVERROR(EEXIST)) {
+ unsigned int l;
+ for (l = 0; l < stg->nb_streams; l++)
+ if (stg->streams[l]->index == st->index)
+ break;
+ av_assert0(l < stg->nb_streams);
+ grid->tile_idx_list[j] = l;
+ break;
+ } else if (err < 0)
+ return err;
+
+ grid->tile_idx_list[j] = stg->nb_streams - 1;
+ st->codecpar->width = item->width;
+ st->codecpar->height = item->height;
+ st->disposition |= AV_DISPOSITION_TILE;
+ break;
+ }
+
+ if (!loop)
+ break;
+ }
+
+ if (!loop)
+ continue;
+
+ tile_grid->nb_tiles = grid->nb_tiles;
+
+ switch (grid->item->type) {
+ case MKTAG('g','r','i','d'):
+ err = read_image_grid(s, stg, tile_grid, grid);
+ break;
+ case MKTAG('i','o','v','l'):
+ err = read_image_overlay(s, tile_grid, grid);
+ break;
+ default:
+ av_assert0(0);
+ }
+ if (err < 0)
+ return err;
+
+
+ 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;
@@ -8901,6 +9280,8 @@ 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);
@@ -8923,20 +9304,43 @@ 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
More information about the ffmpeg-devel
mailing list