X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavfilter%2Faf_silencedetect.c;h=53f54d1834f587150984996fd32600cdfce0da76;hb=3a3e8c35b63a40c4d59161097dc8652c15d13779;hp=6e321a5d9717f44a8c7b4d2e0dcc6f5bb0ec6e56;hpb=5c1aafff2d844b177b0b20db4a38d8460992558b;p=ffmpeg diff --git a/libavfilter/af_silencedetect.c b/libavfilter/af_silencedetect.c index 6e321a5d971..53f54d1834f 100644 --- a/libavfilter/af_silencedetect.c +++ b/libavfilter/af_silencedetect.c @@ -35,10 +35,10 @@ typedef struct SilenceDetectContext { const AVClass *class; double noise; ///< noise amplitude ratio - double duration; ///< minimum duration of silence until notification + int64_t duration; ///< minimum duration of silence until notification int mono; ///< mono mode : check each channel separately (default = check when ALL channels are silent) int channels; ///< number of channels - int independant_channels; ///< number of entries in following arrays (always 1 in mono mode) + int independent_channels; ///< number of entries in following arrays (always 1 in mono mode) int64_t *nb_null_samples; ///< (array) current number of continuous zero samples int64_t *start; ///< (array) if silence is detected, this value contains the time of the first zero sample (default/unset = INT64_MIN) int64_t frame_end; ///< pts of the end of the current frame (used to compute duration of silence at EOS) @@ -50,14 +50,16 @@ typedef struct SilenceDetectContext { AVRational time_base); } SilenceDetectContext; +#define MAX_DURATION (24*3600*1000000LL) #define OFFSET(x) offsetof(SilenceDetectContext, x) #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_AUDIO_PARAM static const AVOption silencedetect_options[] = { { "n", "set noise tolerance", OFFSET(noise), AV_OPT_TYPE_DOUBLE, {.dbl=0.001}, 0, DBL_MAX, FLAGS }, { "noise", "set noise tolerance", OFFSET(noise), AV_OPT_TYPE_DOUBLE, {.dbl=0.001}, 0, DBL_MAX, FLAGS }, - { "d", "set minimum duration in seconds", OFFSET(duration), AV_OPT_TYPE_DOUBLE, {.dbl=2.}, 0, 24*60*60, FLAGS }, - { "duration", "set minimum duration in seconds", OFFSET(duration), AV_OPT_TYPE_DOUBLE, {.dbl=2.}, 0, 24*60*60, FLAGS }, - { "mono", "check each channel separately", OFFSET(mono), AV_OPT_TYPE_BOOL, {.i64=0.}, 0, 1, FLAGS }, + { "d", "set minimum duration in seconds", OFFSET(duration), AV_OPT_TYPE_DURATION, {.i64=2000000}, 0, MAX_DURATION,FLAGS }, + { "duration", "set minimum duration in seconds", OFFSET(duration), AV_OPT_TYPE_DURATION, {.i64=2000000}, 0, MAX_DURATION,FLAGS }, + { "mono", "check each channel separately", OFFSET(mono), AV_OPT_TYPE_BOOL, {.i64=0}, 0, 1, FLAGS }, + { "m", "check each channel separately", OFFSET(mono), AV_OPT_TYPE_BOOL, {.i64=0}, 0, 1, FLAGS }, { NULL } }; @@ -77,12 +79,12 @@ static av_always_inline void update(SilenceDetectContext *s, AVFrame *insamples, int is_silence, int current_sample, int64_t nb_samples_notify, AVRational time_base) { - int channel = current_sample % s->independant_channels; + int channel = current_sample % s->independent_channels; if (is_silence) { if (s->start[channel] == INT64_MIN) { s->nb_null_samples[channel]++; if (s->nb_null_samples[channel] >= nb_samples_notify) { - s->start[channel] = insamples->pts + av_rescale_q(current_sample / s->channels + 1 - nb_samples_notify * s->independant_channels / s->channels, + s->start[channel] = insamples->pts + av_rescale_q(current_sample / s->channels + 1 - nb_samples_notify * s->independent_channels / s->channels, (AVRational){ 1, s->last_sample_rate }, time_base); set_meta(insamples, s->mono ? channel + 1 : 0, "silence_start", av_ts2timestr(s->start[channel], &time_base)); @@ -141,14 +143,15 @@ static int config_input(AVFilterLink *inlink) int c; s->channels = inlink->channels; - s->independant_channels = s->mono ? s->channels : 1; - s->nb_null_samples = av_mallocz_array(sizeof(*s->nb_null_samples), s->independant_channels); + s->duration = av_rescale(s->duration, inlink->sample_rate, AV_TIME_BASE); + s->independent_channels = s->mono ? s->channels : 1; + s->nb_null_samples = av_mallocz_array(sizeof(*s->nb_null_samples), s->independent_channels); if (!s->nb_null_samples) return AVERROR(ENOMEM); - s->start = av_malloc_array(sizeof(*s->start), s->independant_channels); + s->start = av_malloc_array(sizeof(*s->start), s->independent_channels); if (!s->start) return AVERROR(ENOMEM); - for (c = 0; c < s->independant_channels; c++) + for (c = 0; c < s->independent_channels; c++) s->start[c] = INT64_MIN; switch (inlink->format) { @@ -173,12 +176,12 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *insamples) const int nb_channels = inlink->channels; const int srate = inlink->sample_rate; const int nb_samples = insamples->nb_samples * nb_channels; - const int64_t nb_samples_notify = srate * s->duration * (s->mono ? 1 : nb_channels); + const int64_t nb_samples_notify = s->duration * (s->mono ? 1 : nb_channels); int c; // scale number of null samples to the new sample rate if (s->last_sample_rate && s->last_sample_rate != srate) - for (c = 0; c < s->independant_channels; c++) { + for (c = 0; c < s->independent_channels; c++) { s->nb_null_samples[c] = srate * s->nb_null_samples[c] / s->last_sample_rate; } s->last_sample_rate = srate; @@ -186,7 +189,6 @@ static int filter_frame(AVFilterLink *inlink, AVFrame *insamples) s->frame_end = insamples->pts + av_rescale_q(insamples->nb_samples, (AVRational){ 1, s->last_sample_rate }, inlink->time_base); - // TODO: document metadata s->silencedetect(s, insamples, nb_samples, nb_samples_notify, inlink->time_base); @@ -231,7 +233,7 @@ static av_cold void uninit(AVFilterContext *ctx) SilenceDetectContext *s = ctx->priv; int c; - for (c = 0; c < s->independant_channels; c++) + for (c = 0; c < s->independent_channels; c++) if (s->start[c] > INT64_MIN) update(s, NULL, 0, c, 0, s->time_base); av_freep(&s->nb_null_samples); @@ -256,7 +258,7 @@ static const AVFilterPad silencedetect_outputs[] = { { NULL } }; -AVFilter ff_af_silencedetect = { +const AVFilter ff_af_silencedetect = { .name = "silencedetect", .description = NULL_IF_CONFIG_SMALL("Detect silence."), .priv_size = sizeof(SilenceDetectContext),