fftools/ffmpeg_mux_init: allow mapping a stream group from one of the inputs

Signed-off-by: James Almer <jamrial@gmail.com>
This commit is contained in:
James Almer 2024-04-15 12:04:07 -03:00
parent 8616cfe089
commit ecf87dd230
2 changed files with 177 additions and 5 deletions

View File

@ -663,10 +663,11 @@ Not all muxers support embedded thumbnails, and those who do, only support a few
Creates a program with the specified @var{title}, @var{program_num} and adds the specified
@var{stream}(s) to it.
@item -stream_group type=@var{type}:st=@var{stream}[:st=@var{stream}][:stg=@var{stream_group}][:id=@var{stream_group_id}...] (@emph{output})
@item -stream_group [map=@var{input_file_id}=@var{stream_group}][type=@var{type}:]st=@var{stream}[:st=@var{stream}][:stg=@var{stream_group}][:id=@var{stream_group_id}...] (@emph{output})
Creates a stream group of the specified @var{type}, @var{stream_group_id} and adds the specified
@var{stream}(s) and/or previously defined @var{stream_group}(s) to it.
Creates a stream group of the specified @var{type} and @var{stream_group_id}, or by
@var{map}ping an input group, adding the specified @var{stream}(s) and/or previously
defined @var{stream_group}(s) to it.
@var{type} can be one of the following:
@table @option
@ -863,6 +864,27 @@ all sub-mix element's @var{annotations}s
@end table
E.g. to create an scalable 5.1 IAMF file from several WAV input files
@example
ffmpeg -i front.wav -i back.wav -i center.wav -i lfe.wav
-map 0:0 -map 1:0 -map 2:0 -map 3:0 -c:a opus
-stream_group type=iamf_audio_element:id=1:st=0:st=1:st=2:st=3,
demixing=parameter_id=998,
recon_gain=parameter_id=101,
layer=ch_layout=stereo,
layer=ch_layout=5.1,
-stream_group type=iamf_mix_presentation:id=2:stg=0:annotations=en-us=Mix_Presentation,
submix=parameter_id=100:parameter_rate=48000|element=stg=0:parameter_id=100:annotations=en-us=Scalable_Submix|layout=sound_system=stereo|layout=sound_system=5.1
-streamid 0:0 -streamid 1:1 -streamid 2:2 -streamid 3:3 output.iamf
@end example
To copy the two stream groups (Audio Element and Mix Presentation) from an input IAMF file with four
streams into an mp4 output
@example
ffmpeg -i input.iamf -c:a copy -stream_group map=0=0:st=0:st=1:st=2:st=3 -stream_group map=0=1:stg=0
-streamid 0:0 -streamid 1:1 -streamid 2:2 -streamid 3:3 output.mp4
@end example
@item -target @var{type} (@emph{output})
Specify target file type (@code{vcd}, @code{svcd}, @code{dvd}, @code{dv},
@code{dv50}). @var{type} may be prefixed with @code{pal-}, @code{ntsc-} or

View File

@ -2232,11 +2232,137 @@ fail:
return ret;
}
static int of_serialize_options(Muxer *mux, void *obj, AVBPrint *bp)
{
char *ptr;
int ret;
ret = av_opt_serialize(obj, 0, AV_OPT_SERIALIZE_SKIP_DEFAULTS | AV_OPT_SERIALIZE_SEARCH_CHILDREN,
&ptr, '=', ':');
if (ret < 0) {
av_log(mux, AV_LOG_ERROR, "Failed to serialize group\n");
return ret;
}
av_bprintf(bp, "%s", ptr);
ret = strlen(ptr);
av_free(ptr);
return ret;
}
#define SERIALIZE(parent, child) do { \
ret = of_serialize_options(mux, parent->child, bp); \
if (ret < 0) \
return ret; \
} while (0)
#define SERIALIZE_LOOP(parent, child, suffix, separator) do { \
for (int j = 0; j < parent->nb_## child ## suffix; j++) { \
av_bprintf(bp, separator#child "="); \
SERIALIZE(parent, child ## suffix[j]); \
} \
} while (0)
static int64_t get_stream_group_index_from_id(Muxer *mux, int64_t id)
{
AVFormatContext *oc = mux->fc;
for (unsigned i = 0; i < oc->nb_stream_groups; i++)
if (oc->stream_groups[i]->id == id)
return oc->stream_groups[i]->index;
return AVERROR(EINVAL);
}
static int of_map_group(Muxer *mux, AVDictionary **dict, AVBPrint *bp, const char *map)
{
AVStreamGroup *stg;
int ret, file_idx, stream_idx;
char *ptr;
file_idx = strtol(map, &ptr, 0);
if (file_idx >= nb_input_files || file_idx < 0 || map == ptr) {
av_log(mux, AV_LOG_ERROR, "Invalid input file index: %d.\n", file_idx);
return AVERROR(EINVAL);
}
stream_idx = strtol(*ptr == '=' ? ptr + 1 : ptr, &ptr, 0);
if (*ptr || stream_idx >= input_files[file_idx]->ctx->nb_stream_groups || stream_idx < 0) {
av_log(mux, AV_LOG_ERROR, "Invalid input stream group index: %d.\n", stream_idx);
return AVERROR(EINVAL);
}
stg = input_files[file_idx]->ctx->stream_groups[stream_idx];
ret = of_serialize_options(mux, stg, bp);
if (ret < 0)
return ret;
ret = av_dict_parse_string(dict, bp->str, "=", ":", 0);
if (ret < 0)
av_log(mux, AV_LOG_ERROR, "Error parsing mapped group specification %s\n", ptr);
av_dict_set_int(dict, "type", stg->type, 0);
av_log(mux, AV_LOG_VERBOSE, "stg %s\n", bp->str);
av_bprint_clear(bp);
switch(stg->type) {
case AV_STREAM_GROUP_PARAMS_IAMF_AUDIO_ELEMENT: {
AVIAMFAudioElement *audio_element = stg->params.iamf_audio_element;
if (audio_element->demixing_info) {
av_bprintf(bp, ",demixing=");
SERIALIZE(audio_element, demixing_info);
}
if (audio_element->recon_gain_info) {
av_bprintf(bp, ",recon_gain=");
SERIALIZE(audio_element, recon_gain_info);
}
SERIALIZE_LOOP(audio_element, layer, s, ",");
break;
}
case AV_STREAM_GROUP_PARAMS_IAMF_MIX_PRESENTATION: {
AVIAMFMixPresentation *mix = stg->params.iamf_mix_presentation;
for (int i = 0; i < mix->nb_submixes; i++) {
AVIAMFSubmix *submix = mix->submixes[i];
av_bprintf(bp, ",submix=");
SERIALIZE(mix, submixes[i]);
for (int j = 0; j < submix->nb_elements; j++) {
AVIAMFSubmixElement *element = submix->elements[j];
int64_t id = get_stream_group_index_from_id(mux, element->audio_element_id);
if (id < 0) {
av_log(mux, AV_LOG_ERROR, "Invalid or missing stream group index in"
"submix element");
return id;
}
av_bprintf(bp, "|element=");
SERIALIZE(submix, elements[j]);
if (ret)
av_bprintf(bp, ":");
av_bprintf(bp, "stg=%"PRId64, id);
}
SERIALIZE_LOOP(submix, layout, s, "|");
}
break;
}
default:
av_log(mux, AV_LOG_ERROR, "Unsupported mapped group type %d.\n", stg->type);
ret = AVERROR(EINVAL);
break;
}
av_log(mux, AV_LOG_VERBOSE, "extra %s\n", bp->str);
return 0;
}
static int of_parse_group_token(Muxer *mux, const char *token, char *ptr)
{
AVFormatContext *oc = mux->fc;
AVStreamGroup *stg;
AVDictionary *dict = NULL, *tmp = NULL;
char *mapped_string = NULL;
const AVDictionaryEntry *e;
const AVOption opts[] = {
{ "type", "Set group type", offsetof(AVStreamGroup, type), AV_OPT_TYPE_INT,
@ -2262,8 +2388,31 @@ static int of_parse_group_token(Muxer *mux, const char *token, char *ptr)
return ret;
}
av_dict_copy(&tmp, dict, 0);
e = av_dict_get(dict, "map", NULL, 0);
if (e) {
AVBPrint bp;
if (ptr) {
av_log(mux, AV_LOG_ERROR, "Unexpected extra parameters when mapping a"
" stream group\n");
ret = AVERROR(EINVAL);
goto end;
}
av_bprint_init(&bp, 0, AV_BPRINT_SIZE_AUTOMATIC);
ret = of_map_group(mux, &tmp, &bp, e->value);
if (ret < 0) {
av_bprint_finalize(&bp, NULL);
goto end;
}
av_bprint_finalize(&bp, &mapped_string);
ptr = mapped_string;
}
// "type" is not a user settable AVOption in AVStreamGroup, so handle it here
e = av_dict_get(dict, "type", NULL, 0);
e = av_dict_get(tmp, "type", NULL, 0);
if (!e) {
av_log(mux, AV_LOG_ERROR, "No type specified for Stream Group in \"%s\"\n", token);
ret = AVERROR(EINVAL);
@ -2278,7 +2427,6 @@ static int of_parse_group_token(Muxer *mux, const char *token, char *ptr)
goto end;
}
av_dict_copy(&tmp, dict, 0);
stg = avformat_stream_group_create(oc, type, &tmp);
if (!stg) {
ret = AVERROR(ENOMEM);
@ -2331,6 +2479,7 @@ static int of_parse_group_token(Muxer *mux, const char *token, char *ptr)
// make sure that nothing but "st" and "stg" entries are left in the dict
e = NULL;
av_dict_set(&tmp, "map", NULL, 0);
av_dict_set(&tmp, "type", NULL, 0);
while (e = av_dict_iterate(tmp, e)) {
if (!strcmp(e->key, "st") || !strcmp(e->key, "stg"))
@ -2343,6 +2492,7 @@ static int of_parse_group_token(Muxer *mux, const char *token, char *ptr)
ret = 0;
end:
av_free(mapped_string);
av_dict_free(&dict);
av_dict_free(&tmp);