mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-23 12:43:46 +02:00
Merge commit '14f031d7ecfabba0ef02776d4516aa3dcb7c40d8'
* commit '14f031d7ecfabba0ef02776d4516aa3dcb7c40d8': dv: use AVStream.index instead of abusing AVStream.id lavfi: add ashowinfo filter avcodec: Add a RFC 3389 comfort noise codec lpc: Add a function for calculating reflection coefficients from samples lpc: Add a function for calculating reflection coefficients from autocorrelation coefficients lavr: document upper bound on number of output samples. lavr: add general API usage doxy indeo3: remove duplicate capabilities line. fate: ac3: Add dependencies Conflicts: Changelog doc/filters.texi libavcodec/Makefile libavcodec/allcodecs.c libavcodec/avcodec.h libavcodec/codec_desc.c libavcodec/version.h libavfilter/Makefile libavfilter/af_ashowinfo.c libavfilter/allfilters.c libavfilter/version.h libavutil/avutil.h Merged-by: Michael Niedermayer <michaelni@gmx.at>
This commit is contained in:
commit
e79c3858b3
1
configure
vendored
1
configure
vendored
@ -1607,6 +1607,7 @@ atrac3_decoder_select="mdct"
|
||||
binkaudio_dct_decoder_select="mdct rdft dct sinewin"
|
||||
binkaudio_rdft_decoder_select="mdct rdft sinewin"
|
||||
cavs_decoder_select="golomb mpegvideo"
|
||||
comfortnoise_encoder_select="lpc"
|
||||
cook_decoder_select="mdct sinewin"
|
||||
cscd_decoder_select="lzo"
|
||||
cscd_decoder_suggest="zlib"
|
||||
|
@ -414,37 +414,34 @@ A description of each shown parameter follows:
|
||||
sequential number of the input frame, starting from 0
|
||||
|
||||
@item pts
|
||||
presentation TimeStamp of the input frame, expressed as a number of
|
||||
time base units. The time base unit depends on the filter input pad, and
|
||||
is usually 1/@var{sample_rate}.
|
||||
Presentation timestamp of the input frame, in time base units; the time base
|
||||
depends on the filter input pad, and is usually 1/@var{sample_rate}.
|
||||
|
||||
@item pts_time
|
||||
presentation TimeStamp of the input frame, expressed as a number of
|
||||
seconds
|
||||
presentation timestamp of the input frame in seconds
|
||||
|
||||
@item pos
|
||||
position of the frame in the input stream, -1 if this information in
|
||||
unavailable and/or meaningless (for example in case of synthetic audio)
|
||||
|
||||
@item fmt
|
||||
sample format name
|
||||
sample format
|
||||
|
||||
@item chlayout
|
||||
channel layout description
|
||||
|
||||
@item nb_samples
|
||||
number of samples (per each channel) contained in the filtered frame
|
||||
channel layout
|
||||
|
||||
@item rate
|
||||
sample rate for the audio frame
|
||||
|
||||
@item checksum
|
||||
Adler-32 checksum (printed in hexadecimal) of all the planes of the input frame
|
||||
@item nb_samples
|
||||
number of samples (per channel) in the frame
|
||||
|
||||
@item plane_checksum
|
||||
Adler-32 checksum (printed in hexadecimal) for each input frame plane,
|
||||
expressed in the form "[@var{c0} @var{c1} @var{c2} @var{c3} @var{c4} @var{c5}
|
||||
@var{c6} @var{c7}]"
|
||||
@item checksum
|
||||
Adler-32 checksum (printed in hexadecimal) of the audio data. For planar audio
|
||||
the data is treated as if all the planes were concatenated.
|
||||
|
||||
@item plane_checksums
|
||||
A list of Adler-32 checksums for each data plane.
|
||||
@end table
|
||||
|
||||
@section asplit
|
||||
|
@ -145,6 +145,8 @@ OBJS-$(CONFIG_CLJR_DECODER) += cljr.o
|
||||
OBJS-$(CONFIG_CLJR_ENCODER) += cljr.o
|
||||
OBJS-$(CONFIG_CLLC_DECODER) += cllc.o
|
||||
OBJS-$(CONFIG_COOK_DECODER) += cook.o
|
||||
OBJS-$(CONFIG_COMFORTNOISE_DECODER) += cngdec.o celp_filters.o
|
||||
OBJS-$(CONFIG_COMFORTNOISE_ENCODER) += cngenc.o
|
||||
OBJS-$(CONFIG_CPIA_DECODER) += cpia.o
|
||||
OBJS-$(CONFIG_CSCD_DECODER) += cscd.o
|
||||
OBJS-$(CONFIG_CYUV_DECODER) += cyuv.o
|
||||
|
@ -97,6 +97,7 @@ void avcodec_register_all(void)
|
||||
REGISTER_DECODER (CINEPAK, cinepak);
|
||||
REGISTER_ENCDEC (CLJR, cljr);
|
||||
REGISTER_DECODER (CLLC, cllc);
|
||||
REGISTER_ENCDEC (COMFORTNOISE, comfortnoise);
|
||||
REGISTER_DECODER (CPIA, cpia);
|
||||
REGISTER_DECODER (CSCD, cscd);
|
||||
REGISTER_DECODER (CYUV, cyuv);
|
||||
|
@ -426,6 +426,7 @@ enum AVCodecID {
|
||||
AV_CODEC_ID_IAC,
|
||||
AV_CODEC_ID_ILBC,
|
||||
AV_CODEC_ID_OPUS_DEPRECATED,
|
||||
AV_CODEC_ID_COMFORT_NOISE,
|
||||
AV_CODEC_ID_FFWAVESYNTH = MKBETAG('F','F','W','S'),
|
||||
AV_CODEC_ID_8SVX_RAW = MKBETAG('8','S','V','X'),
|
||||
AV_CODEC_ID_SONIC = MKBETAG('S','O','N','C'),
|
||||
|
162
libavcodec/cngdec.c
Normal file
162
libavcodec/cngdec.c
Normal file
@ -0,0 +1,162 @@
|
||||
/*
|
||||
* RFC 3389 comfort noise generator
|
||||
* Copyright (c) 2012 Martin Storsjo
|
||||
*
|
||||
* This file is part of FFmpeg.
|
||||
*
|
||||
* FFmpeg is free software; you can redistribute it and/or
|
||||
* modify it under the terms of the GNU Lesser General Public
|
||||
* License as published by the Free Software Foundation; either
|
||||
* version 2.1 of the License, or (at your option) any later version.
|
||||
*
|
||||
* FFmpeg is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
* Lesser General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU Lesser General Public
|
||||
* License along with FFmpeg; if not, write to the Free Software
|
||||
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
||||
*/
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "libavutil/common.h"
|
||||
#include "avcodec.h"
|
||||
#include "celp_filters.h"
|
||||
#include "libavutil/lfg.h"
|
||||
|
||||
typedef struct CNGContext {
|
||||
AVFrame avframe;
|
||||
float *refl_coef, *target_refl_coef;
|
||||
float *lpc_coef;
|
||||
int order;
|
||||
int energy, target_energy;
|
||||
float *filter_out;
|
||||
float *excitation;
|
||||
AVLFG lfg;
|
||||
} CNGContext;
|
||||
|
||||
static av_cold int cng_decode_close(AVCodecContext *avctx)
|
||||
{
|
||||
CNGContext *p = avctx->priv_data;
|
||||
av_free(p->refl_coef);
|
||||
av_free(p->target_refl_coef);
|
||||
av_free(p->lpc_coef);
|
||||
av_free(p->filter_out);
|
||||
av_free(p->excitation);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static av_cold int cng_decode_init(AVCodecContext *avctx)
|
||||
{
|
||||
CNGContext *p = avctx->priv_data;
|
||||
|
||||
avctx->sample_fmt = AV_SAMPLE_FMT_S16;
|
||||
avctx->channels = 1;
|
||||
avctx->sample_rate = 8000;
|
||||
|
||||
avcodec_get_frame_defaults(&p->avframe);
|
||||
avctx->coded_frame = &p->avframe;
|
||||
p->order = 12;
|
||||
avctx->frame_size = 640;
|
||||
p->refl_coef = av_mallocz(p->order * sizeof(*p->refl_coef));
|
||||
p->target_refl_coef = av_mallocz(p->order * sizeof(*p->target_refl_coef));
|
||||
p->lpc_coef = av_mallocz(p->order * sizeof(*p->lpc_coef));
|
||||
p->filter_out = av_mallocz((avctx->frame_size + p->order) *
|
||||
sizeof(*p->filter_out));
|
||||
p->excitation = av_mallocz(avctx->frame_size * sizeof(*p->excitation));
|
||||
if (!p->refl_coef || !p->target_refl_coef || !p->lpc_coef ||
|
||||
!p->filter_out || !p->excitation) {
|
||||
cng_decode_close(avctx);
|
||||
return AVERROR(ENOMEM);
|
||||
}
|
||||
|
||||
av_lfg_init(&p->lfg, 0);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void make_lpc_coefs(float *lpc, const float *refl, int order)
|
||||
{
|
||||
float buf[100];
|
||||
float *next, *cur;
|
||||
int m, i;
|
||||
next = buf;
|
||||
cur = lpc;
|
||||
for (m = 0; m < order; m++) {
|
||||
next[m] = refl[m];
|
||||
for (i = 0; i < m; i++)
|
||||
next[i] = cur[i] + refl[m] * cur[m - i - 1];
|
||||
FFSWAP(float*, next, cur);
|
||||
}
|
||||
if (cur != lpc)
|
||||
memcpy(lpc, cur, sizeof(*lpc) * order);
|
||||
}
|
||||
|
||||
static int cng_decode_frame(AVCodecContext *avctx, void *data,
|
||||
int *got_frame_ptr, AVPacket *avpkt)
|
||||
{
|
||||
|
||||
CNGContext *p = avctx->priv_data;
|
||||
int buf_size = avpkt->size;
|
||||
int ret, i;
|
||||
int16_t *buf_out;
|
||||
float e = 1.0;
|
||||
float scaling;
|
||||
|
||||
if (avpkt->size) {
|
||||
float dbov = -avpkt->data[0] / 10.0;
|
||||
p->target_energy = 1081109975 * pow(10, dbov) * 0.75;
|
||||
memset(p->target_refl_coef, 0, sizeof(p->refl_coef));
|
||||
for (i = 0; i < FFMIN(avpkt->size - 1, p->order); i++) {
|
||||
p->target_refl_coef[i] = (avpkt->data[1 + i] - 127) / 128.0;
|
||||
}
|
||||
make_lpc_coefs(p->lpc_coef, p->refl_coef, p->order);
|
||||
}
|
||||
|
||||
p->energy = p->energy / 2 + p->target_energy / 2;
|
||||
for (i = 0; i < p->order; i++)
|
||||
p->refl_coef[i] = 0.6 *p->refl_coef[i] + 0.4 * p->target_refl_coef[i];
|
||||
|
||||
for (i = 0; i < p->order; i++)
|
||||
e *= 1.0 - p->refl_coef[i]*p->refl_coef[i];
|
||||
|
||||
scaling = sqrt(e * p->energy / 1081109975);
|
||||
for (i = 0; i < avctx->frame_size; i++) {
|
||||
int r = (av_lfg_get(&p->lfg) & 0xffff) - 0x8000;
|
||||
p->excitation[i] = scaling * r;
|
||||
}
|
||||
ff_celp_lp_synthesis_filterf(p->filter_out + p->order, p->lpc_coef,
|
||||
p->excitation, avctx->frame_size, p->order);
|
||||
|
||||
p->avframe.nb_samples = avctx->frame_size;
|
||||
if ((ret = avctx->get_buffer(avctx, &p->avframe)) < 0) {
|
||||
av_log(avctx, AV_LOG_ERROR, "get_buffer() failed\n");
|
||||
return ret;
|
||||
}
|
||||
buf_out = (int16_t *)p->avframe.data[0];
|
||||
for (i = 0; i < avctx->frame_size; i++)
|
||||
buf_out[i] = p->filter_out[i + p->order];
|
||||
memcpy(p->filter_out, p->filter_out + avctx->frame_size,
|
||||
p->order * sizeof(*p->filter_out));
|
||||
|
||||
*got_frame_ptr = 1;
|
||||
*(AVFrame *)data = p->avframe;
|
||||
|
||||
return buf_size;
|
||||
}
|
||||
|
||||
AVCodec ff_comfortnoise_decoder = {
|
||||
.name = "comfortnoise",
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
.id = AV_CODEC_ID_COMFORT_NOISE,
|
||||
.priv_data_size = sizeof(CNGContext),
|
||||
.init = cng_decode_init,
|
||||
.decode = cng_decode_frame,
|
||||
.close = cng_decode_close,
|
||||
.long_name = NULL_IF_CONFIG_SMALL("RFC 3389 comfort noise generator"),
|
||||
.sample_fmts = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_S16,
|
||||
AV_SAMPLE_FMT_NONE },
|
||||
.capabilities = CODEC_CAP_DELAY | CODEC_CAP_DR1,
|
||||
};
|
116
libavcodec/cngenc.c
Normal file
116
libavcodec/cngenc.c
Normal file
@ -0,0 +1,116 @@
|
||||
/*
|
||||
* RFC 3389 comfort noise generator
|
||||
* Copyright (c) 2012 Martin Storsjo
|
||||
*
|
||||
* This file is part of FFmpeg.
|
||||
*
|
||||
* FFmpeg is free software; you can redistribute it and/or
|
||||
* modify it under the terms of the GNU Lesser General Public
|
||||
* License as published by the Free Software Foundation; either
|
||||
* version 2.1 of the License, or (at your option) any later version.
|
||||
*
|
||||
* FFmpeg is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
* Lesser General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU Lesser General Public
|
||||
* License along with FFmpeg; if not, write to the Free Software
|
||||
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
||||
*/
|
||||
|
||||
#include <math.h>
|
||||
|
||||
#include "libavutil/common.h"
|
||||
#include "avcodec.h"
|
||||
#include "internal.h"
|
||||
#include "lpc.h"
|
||||
|
||||
typedef struct CNGContext {
|
||||
LPCContext lpc;
|
||||
int order;
|
||||
int32_t *samples32;
|
||||
double *ref_coef;
|
||||
} CNGContext;
|
||||
|
||||
static av_cold int cng_encode_close(AVCodecContext *avctx)
|
||||
{
|
||||
CNGContext *p = avctx->priv_data;
|
||||
ff_lpc_end(&p->lpc);
|
||||
av_free(p->samples32);
|
||||
av_free(p->ref_coef);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static av_cold int cng_encode_init(AVCodecContext *avctx)
|
||||
{
|
||||
CNGContext *p = avctx->priv_data;
|
||||
int ret;
|
||||
|
||||
if (avctx->channels != 1) {
|
||||
av_log(avctx, AV_LOG_ERROR, "Only mono supported\n");
|
||||
return AVERROR(EINVAL);
|
||||
}
|
||||
|
||||
avctx->frame_size = 640;
|
||||
p->order = 10;
|
||||
if ((ret = ff_lpc_init(&p->lpc, avctx->frame_size, p->order, FF_LPC_TYPE_LEVINSON)) < 0)
|
||||
return ret;
|
||||
p->samples32 = av_malloc(avctx->frame_size * sizeof(*p->samples32));
|
||||
p->ref_coef = av_malloc(p->order * sizeof(*p->ref_coef));
|
||||
if (!p->samples32 || !p->ref_coef) {
|
||||
cng_encode_close(avctx);
|
||||
return AVERROR(ENOMEM);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int cng_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
|
||||
const AVFrame *frame, int *got_packet_ptr)
|
||||
{
|
||||
CNGContext *p = avctx->priv_data;
|
||||
int ret, i;
|
||||
double energy = 0;
|
||||
int qdbov;
|
||||
int16_t *samples = (int16_t*) frame->data[0];
|
||||
|
||||
if ((ret = ff_alloc_packet(avpkt, 1 + p->order))) {
|
||||
av_log(avctx, AV_LOG_ERROR, "Error getting output packet\n");
|
||||
return ret;
|
||||
}
|
||||
|
||||
for (i = 0; i < frame->nb_samples; i++) {
|
||||
p->samples32[i] = samples[i];
|
||||
energy += samples[i] * samples[i];
|
||||
}
|
||||
energy /= frame->nb_samples;
|
||||
if (energy > 0) {
|
||||
double dbov = 10 * log10(energy / 1081109975);
|
||||
qdbov = av_clip(-floor(dbov), 0, 127);
|
||||
} else {
|
||||
qdbov = 127;
|
||||
}
|
||||
ret = ff_lpc_calc_ref_coefs(&p->lpc, p->samples32, p->order, p->ref_coef);
|
||||
avpkt->data[0] = qdbov;
|
||||
for (i = 0; i < p->order; i++)
|
||||
avpkt->data[1 + i] = p->ref_coef[i] * 127 + 127;
|
||||
|
||||
*got_packet_ptr = 1;
|
||||
avpkt->size = 1 + p->order;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
AVCodec ff_comfortnoise_encoder = {
|
||||
.name = "comfortnoise",
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
.id = AV_CODEC_ID_COMFORT_NOISE,
|
||||
.priv_data_size = sizeof(CNGContext),
|
||||
.init = cng_encode_init,
|
||||
.encode2 = cng_encode_frame,
|
||||
.close = cng_encode_close,
|
||||
.long_name = NULL_IF_CONFIG_SMALL("RFC 3389 comfort noise generator"),
|
||||
.sample_fmts = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_S16,
|
||||
AV_SAMPLE_FMT_NONE },
|
||||
};
|
@ -2264,6 +2264,13 @@ static const AVCodecDescriptor codec_descriptors[] = {
|
||||
.long_name = NULL_IF_CONFIG_SMALL("Opus (Opus Interactive Audio Codec)"),
|
||||
.props = AV_CODEC_PROP_LOSSY,
|
||||
},
|
||||
{
|
||||
.id = AV_CODEC_ID_COMFORT_NOISE,
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
.name = "comfortnoise",
|
||||
.long_name = NULL_IF_CONFIG_SMALL("RFC 3389 Comfort Noise"),
|
||||
.props = AV_CODEC_PROP_LOSSY,
|
||||
},
|
||||
{
|
||||
.id = AV_CODEC_ID_TAK,
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
|
@ -149,6 +149,18 @@ static int estimate_best_order(double *ref, int min_order, int max_order)
|
||||
return est;
|
||||
}
|
||||
|
||||
int ff_lpc_calc_ref_coefs(LPCContext *s,
|
||||
const int32_t *samples, int order, double *ref)
|
||||
{
|
||||
double autoc[MAX_LPC_ORDER + 1];
|
||||
|
||||
s->lpc_apply_welch_window(samples, s->blocksize, s->windowed_samples);
|
||||
s->lpc_compute_autocorr(s->windowed_samples, s->blocksize, order, autoc);
|
||||
compute_ref_coefs(autoc, order, ref, NULL);
|
||||
|
||||
return order;
|
||||
}
|
||||
|
||||
/**
|
||||
* Calculate LPC coefficients for multiple orders
|
||||
*
|
||||
|
@ -93,6 +93,9 @@ int ff_lpc_calc_coefs(LPCContext *s,
|
||||
enum FFLPCType lpc_type, int lpc_passes,
|
||||
int omethod, int max_shift, int zero_shift);
|
||||
|
||||
int ff_lpc_calc_ref_coefs(LPCContext *s,
|
||||
const int32_t *samples, int order, double *ref);
|
||||
|
||||
/**
|
||||
* Initialize LPCContext.
|
||||
*/
|
||||
@ -111,6 +114,37 @@ void ff_lpc_end(LPCContext *s);
|
||||
#define LPC_TYPE float
|
||||
#endif
|
||||
|
||||
/**
|
||||
* Schur recursion.
|
||||
* Produces reflection coefficients from autocorrelation data.
|
||||
*/
|
||||
static inline void compute_ref_coefs(const LPC_TYPE *autoc, int max_order,
|
||||
LPC_TYPE *ref, LPC_TYPE *error)
|
||||
{
|
||||
int i, j;
|
||||
LPC_TYPE err;
|
||||
LPC_TYPE gen0[MAX_LPC_ORDER], gen1[MAX_LPC_ORDER];
|
||||
|
||||
for (i = 0; i < max_order; i++)
|
||||
gen0[i] = gen1[i] = autoc[i + 1];
|
||||
|
||||
err = autoc[0];
|
||||
ref[0] = -gen1[0] / err;
|
||||
err += gen1[0] * ref[0];
|
||||
if (error)
|
||||
error[0] = err;
|
||||
for (i = 1; i < max_order; i++) {
|
||||
for (j = 0; j < max_order - i; j++) {
|
||||
gen1[j] = gen1[j + 1] + ref[i - 1] * gen0[j];
|
||||
gen0[j] = gen1[j + 1] * ref[i - 1] + gen0[j];
|
||||
}
|
||||
ref[i] = -gen1[0] / err;
|
||||
err += gen1[0] * ref[i];
|
||||
if (error)
|
||||
error[i] = err;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Levinson-Durbin recursion.
|
||||
* Produce LPC coefficients from autocorrelation data.
|
||||
|
@ -29,7 +29,7 @@
|
||||
#include "libavutil/avutil.h"
|
||||
|
||||
#define LIBAVCODEC_VERSION_MAJOR 54
|
||||
#define LIBAVCODEC_VERSION_MINOR 69
|
||||
#define LIBAVCODEC_VERSION_MINOR 70
|
||||
#define LIBAVCODEC_VERSION_MICRO 100
|
||||
|
||||
#define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \
|
||||
|
@ -23,84 +23,117 @@
|
||||
* filter for showing textual audio frame information
|
||||
*/
|
||||
|
||||
#include <inttypes.h>
|
||||
#include <stddef.h>
|
||||
|
||||
#include "libavutil/adler32.h"
|
||||
#include "libavutil/audioconvert.h"
|
||||
#include "libavutil/common.h"
|
||||
#include "libavutil/mem.h"
|
||||
#include "libavutil/timestamp.h"
|
||||
#include "libavutil/samplefmt.h"
|
||||
|
||||
#include "audio.h"
|
||||
#include "avfilter.h"
|
||||
|
||||
typedef struct {
|
||||
unsigned int frame;
|
||||
} ShowInfoContext;
|
||||
typedef struct AShowInfoContext {
|
||||
/**
|
||||
* Scratch space for individual plane checksums for planar audio
|
||||
*/
|
||||
uint32_t *plane_checksums;
|
||||
|
||||
static av_cold int init(AVFilterContext *ctx, const char *args)
|
||||
/**
|
||||
* Frame counter
|
||||
*/
|
||||
uint64_t frame;
|
||||
} AShowInfoContext;
|
||||
|
||||
static int config_input(AVFilterLink *inlink)
|
||||
{
|
||||
ShowInfoContext *showinfo = ctx->priv;
|
||||
showinfo->frame = 0;
|
||||
AShowInfoContext *s = inlink->dst->priv;
|
||||
int channels = av_get_channel_layout_nb_channels(inlink->channel_layout);
|
||||
s->plane_checksums = av_malloc(channels * sizeof(*s->plane_checksums));
|
||||
if (!s->plane_checksums)
|
||||
return AVERROR(ENOMEM);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int filter_samples(AVFilterLink *inlink, AVFilterBufferRef *samplesref)
|
||||
static void uninit(AVFilterContext *ctx)
|
||||
{
|
||||
AShowInfoContext *s = ctx->priv;
|
||||
av_freep(&s->plane_checksums);
|
||||
}
|
||||
|
||||
static int filter_samples(AVFilterLink *inlink, AVFilterBufferRef *buf)
|
||||
{
|
||||
AVFilterContext *ctx = inlink->dst;
|
||||
ShowInfoContext *showinfo = ctx->priv;
|
||||
uint32_t plane_checksum[8] = {0}, checksum = 0;
|
||||
AShowInfoContext *s = ctx->priv;
|
||||
char chlayout_str[128];
|
||||
int plane;
|
||||
int linesize =
|
||||
samplesref->audio->nb_samples *
|
||||
av_get_bytes_per_sample(samplesref->format);
|
||||
if (!av_sample_fmt_is_planar(samplesref->format))
|
||||
linesize *= av_get_channel_layout_nb_channels(samplesref->audio->channel_layout);
|
||||
uint32_t checksum = 0;
|
||||
int channels = av_get_channel_layout_nb_channels(buf->audio->channel_layout);
|
||||
int planar = av_sample_fmt_is_planar(buf->format);
|
||||
int block_align = av_get_bytes_per_sample(buf->format) * (planar ? 1 : channels);
|
||||
int data_size = buf->audio->nb_samples * block_align;
|
||||
int planes = planar ? channels : 1;
|
||||
int i;
|
||||
|
||||
for (plane = 0; plane < 8 && samplesref->data[plane]; plane++) {
|
||||
uint8_t *data = samplesref->data[plane];
|
||||
for (i = 0; i < planes; i++) {
|
||||
uint8_t *data = buf->extended_data[i];
|
||||
|
||||
plane_checksum[plane] = av_adler32_update(plane_checksum[plane],
|
||||
data, linesize);
|
||||
checksum = av_adler32_update(checksum, data, linesize);
|
||||
s->plane_checksums[i] = av_adler32_update(0, data, data_size);
|
||||
checksum = i ? av_adler32_update(checksum, data, data_size) :
|
||||
s->plane_checksums[0];
|
||||
}
|
||||
|
||||
av_get_channel_layout_string(chlayout_str, sizeof(chlayout_str), -1,
|
||||
samplesref->audio->channel_layout);
|
||||
buf->audio->channel_layout);
|
||||
|
||||
av_log(ctx, AV_LOG_INFO,
|
||||
"n:%d pts:%s pts_time:%s pos:%"PRId64" "
|
||||
"fmt:%s chlayout:%s nb_samples:%d rate:%d "
|
||||
"checksum:%08X plane_checksum[%08X",
|
||||
showinfo->frame,
|
||||
av_ts2str(samplesref->pts), av_ts2timestr(samplesref->pts, &inlink->time_base),
|
||||
samplesref->pos,
|
||||
av_get_sample_fmt_name(samplesref->format),
|
||||
chlayout_str,
|
||||
samplesref->audio->nb_samples,
|
||||
samplesref->audio->sample_rate,
|
||||
checksum,
|
||||
plane_checksum[0]);
|
||||
"n:%"PRIu64" pts:%s pts_time:%s pos:%"PRId64" "
|
||||
"fmt:%s chlayout:%s rate:%d nb_samples:%d "
|
||||
"checksum:%08X ",
|
||||
s->frame,
|
||||
av_ts2str(buf->pts), av_ts2timestr(buf->pts, &inlink->time_base),
|
||||
buf->pos,
|
||||
av_get_sample_fmt_name(buf->format), chlayout_str,
|
||||
buf->audio->sample_rate, buf->audio->nb_samples,
|
||||
checksum);
|
||||
|
||||
for (plane = 1; plane < 8 && samplesref->data[plane]; plane++)
|
||||
av_log(ctx, AV_LOG_INFO, " %08X", plane_checksum[plane]);
|
||||
av_log(ctx, AV_LOG_INFO, "plane_checksums: [ ");
|
||||
for (i = 0; i < planes; i++)
|
||||
av_log(ctx, AV_LOG_INFO, "%08X ", s->plane_checksums[i]);
|
||||
av_log(ctx, AV_LOG_INFO, "]\n");
|
||||
|
||||
showinfo->frame++;
|
||||
return ff_filter_samples(inlink->dst->outputs[0], samplesref);
|
||||
s->frame++;
|
||||
return ff_filter_samples(inlink->dst->outputs[0], buf);
|
||||
}
|
||||
|
||||
static const AVFilterPad inputs[] = {
|
||||
{
|
||||
.name = "default",
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
.get_audio_buffer = ff_null_get_audio_buffer,
|
||||
.config_props = config_input,
|
||||
.filter_samples = filter_samples,
|
||||
.min_perms = AV_PERM_READ,
|
||||
},
|
||||
{ NULL },
|
||||
};
|
||||
|
||||
static const AVFilterPad outputs[] = {
|
||||
{
|
||||
.name = "default",
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
},
|
||||
{ NULL },
|
||||
};
|
||||
|
||||
AVFilter avfilter_af_ashowinfo = {
|
||||
.name = "ashowinfo",
|
||||
.description = NULL_IF_CONFIG_SMALL("Show textual information for each audio frame."),
|
||||
|
||||
.priv_size = sizeof(ShowInfoContext),
|
||||
.init = init,
|
||||
|
||||
.inputs = (const AVFilterPad[]) {{ .name = "default",
|
||||
.type = AVMEDIA_TYPE_AUDIO,
|
||||
.get_audio_buffer = ff_null_get_audio_buffer,
|
||||
.filter_samples = filter_samples,
|
||||
.min_perms = AV_PERM_READ, },
|
||||
{ .name = NULL}},
|
||||
|
||||
.outputs = (const AVFilterPad[]) {{ .name = "default",
|
||||
.type = AVMEDIA_TYPE_AUDIO },
|
||||
{ .name = NULL}},
|
||||
.priv_size = sizeof(AShowInfoContext),
|
||||
.uninit = uninit,
|
||||
.inputs = inputs,
|
||||
.outputs = outputs,
|
||||
};
|
||||
|
@ -30,7 +30,7 @@
|
||||
|
||||
#define LIBAVFILTER_VERSION_MAJOR 3
|
||||
#define LIBAVFILTER_VERSION_MINOR 20
|
||||
#define LIBAVFILTER_VERSION_MICRO 109
|
||||
#define LIBAVFILTER_VERSION_MICRO 110
|
||||
|
||||
#define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \
|
||||
LIBAVFILTER_VERSION_MINOR, \
|
||||
|
@ -391,7 +391,7 @@ int avpriv_dv_produce_packet(DVDemuxContext *c, AVPacket *pkt,
|
||||
pkt->pos = pos;
|
||||
pkt->size = size;
|
||||
pkt->flags |= AV_PKT_FLAG_KEY;
|
||||
pkt->stream_index = c->vst->id;
|
||||
pkt->stream_index = c->vst->index;
|
||||
pkt->pts = c->frames;
|
||||
|
||||
c->frames++;
|
||||
|
@ -23,9 +23,76 @@
|
||||
|
||||
/**
|
||||
* @file
|
||||
* @ingroup lavr
|
||||
* external API header
|
||||
*/
|
||||
|
||||
/**
|
||||
* @defgroup lavr Libavresample
|
||||
* @{
|
||||
*
|
||||
* Libavresample (lavr) is a library that handles audio resampling, sample
|
||||
* format conversion and mixing.
|
||||
*
|
||||
* Interaction with lavr is done through AVAudioResampleContext, which is
|
||||
* allocated with avresample_alloc_context(). It is opaque, so all parameters
|
||||
* must be set with the @ref avoptions API.
|
||||
*
|
||||
* For example the following code will setup conversion from planar float sample
|
||||
* format to interleaved signed 16-bit integer, downsampling from 48kHz to
|
||||
* 44.1kHz and downmixing from 5.1 channels to stereo (using the default mixing
|
||||
* matrix):
|
||||
* @code
|
||||
* AVAudioResampleContext *avr = avresample_alloc_context();
|
||||
* av_opt_set_int(avr, "in_channel_layout", AV_CH_LAYOUT_5POINT1, 0);
|
||||
* av_opt_set_int(avr, "out_channel_layout", AV_CH_LAYOUT_STEREO, 0);
|
||||
* av_opt_set_int(avr, "in_sample_rate", 48000, 0);
|
||||
* av_opt_set_int(avr, "out_sample_rate", 44100, 0);
|
||||
* av_opt_set_int(avr, "in_sample_fmt", AV_SAMPLE_FMT_FLTP, 0);
|
||||
* av_opt_set_int(avr, "out_sample_fmt, AV_SAMPLE_FMT_S16, 0);
|
||||
* @endcode
|
||||
*
|
||||
* Once the context is initialized, it must be opened with avresample_open(). If
|
||||
* you need to change the conversion parameters, you must close the context with
|
||||
* avresample_close(), change the parameters as described above, then reopen it
|
||||
* again.
|
||||
*
|
||||
* The conversion itself is done by repeatedly calling avresample_convert().
|
||||
* Note that the samples may get buffered in two places in lavr. The first one
|
||||
* is the output FIFO, where the samples end up if the output buffer is not
|
||||
* large enough. The data stored in there may be retrieved at any time with
|
||||
* avresample_read(). The second place is the resampling delay buffer,
|
||||
* applicable only when resampling is done. The samples in it require more input
|
||||
* before they can be processed. Their current amount is returned by
|
||||
* avresample_get_delay(). At the end of conversion the resampling buffer can be
|
||||
* flushed by calling avresample_convert() with NULL input.
|
||||
*
|
||||
* The following code demonstrates the conversion loop assuming the parameters
|
||||
* from above and caller-defined functions get_input() and handle_output():
|
||||
* @code
|
||||
* uint8_t **input;
|
||||
* int in_linesize, in_samples;
|
||||
*
|
||||
* while (get_input(&input, &in_linesize, &in_samples)) {
|
||||
* uint8_t *output
|
||||
* int out_linesize;
|
||||
* int out_samples = avresample_available(avr) +
|
||||
* av_rescale_rnd(avresample_get_delay(avr) +
|
||||
* in_samples, 44100, 48000, AV_ROUND_UP);
|
||||
* av_samples_alloc(&output, &out_linesize, 2, out_samples,
|
||||
* AV_SAMPLE_FMT_S16, 0);
|
||||
* out_samples = avresample_convert(avr, &output, out_linesize, out_samples,
|
||||
* input, in_linesize, in_samples);
|
||||
* handle_output(output, out_linesize, out_samples);
|
||||
* av_freep(&output);
|
||||
* }
|
||||
* @endcode
|
||||
*
|
||||
* When the conversion is finished and the FIFOs are flushed if required, the
|
||||
* conversion context and everything associated with it must be freed with
|
||||
* avresample_free().
|
||||
*/
|
||||
|
||||
#include "libavutil/audioconvert.h"
|
||||
#include "libavutil/avutil.h"
|
||||
#include "libavutil/dict.h"
|
||||
@ -198,6 +265,10 @@ int avresample_set_compensation(AVAudioResampleContext *avr, int sample_delta,
|
||||
/**
|
||||
* Convert input samples and write them to the output FIFO.
|
||||
*
|
||||
* The upper bound on the number of output samples is given by
|
||||
* avresample_available() + (avresample_get_delay() + number of input samples) *
|
||||
* output sample rate / input sample rate.
|
||||
*
|
||||
* The output data can be NULL or have fewer allocated samples than required.
|
||||
* In this case, any remaining samples not written to the output will be added
|
||||
* to an internal FIFO buffer, to be returned at the next call to this function
|
||||
@ -289,4 +360,8 @@ int avresample_available(AVAudioResampleContext *avr);
|
||||
*/
|
||||
int avresample_read(AVAudioResampleContext *avr, uint8_t **output, int nb_samples);
|
||||
|
||||
/**
|
||||
* @}
|
||||
*/
|
||||
|
||||
#endif /* AVRESAMPLE_AVRESAMPLE_H */
|
||||
|
@ -39,6 +39,7 @@
|
||||
* @li @ref libavf "libavformat" I/O and muxing/demuxing library
|
||||
* @li @ref lavd "libavdevice" special devices muxing/demuxing library
|
||||
* @li @ref lavu "libavutil" common utility library
|
||||
* @li @ref libswresample "libswresample" audio resampling, format conversion and mixing
|
||||
* @li @subpage libpostproc post processing library
|
||||
* @li @subpage libswscale color conversion and scaling library
|
||||
*/
|
||||
|
@ -44,14 +44,17 @@ fate-eac3-4: REF = $(SAMPLES)/eac3/serenity_english_5.1_1536_small.pcm
|
||||
|
||||
$(FATE_AC3) $(FATE_EAC3): CMP = oneoff
|
||||
|
||||
FATE_AC3_ENCODE += fate-ac3-encode
|
||||
FATE_AC3-$(call DEMDEC, AC3, AC3) += $(FATE_AC3)
|
||||
FATE_EAC3-$(call DEMDEC, EAC3, EAC3) += $(FATE_EAC3)
|
||||
|
||||
FATE_AC3-$(call ENCDEC, AC3, AC3) += fate-ac3-encode
|
||||
fate-ac3-encode: CMD = enc_dec_pcm ac3 wav s16le $(REF) -c:a ac3 -b:a 128k
|
||||
fate-ac3-encode: CMP_SHIFT = -1024
|
||||
fate-ac3-encode: CMP_TARGET = 399.62
|
||||
fate-ac3-encode: SIZE_TOLERANCE = 488
|
||||
fate-ac3-encode: FUZZ = 4
|
||||
|
||||
FATE_EAC3_ENCODE += fate-eac3-encode
|
||||
FATE_EAC3-$(call ENCDEC, EAC3, EAC3) += fate-eac3-encode
|
||||
fate-eac3-encode: CMD = enc_dec_pcm eac3 wav s16le $(REF) -c:a eac3 -b:a 128k
|
||||
fate-eac3-encode: CMP_SHIFT = -1024
|
||||
fate-eac3-encode: CMP_TARGET = 514.02
|
||||
@ -61,15 +64,13 @@ fate-eac3-encode: FUZZ = 3
|
||||
fate-ac3-encode fate-eac3-encode: CMP = stddev
|
||||
fate-ac3-encode fate-eac3-encode: REF = $(SAMPLES)/audio-reference/luckynight_2ch_44kHz_s16.wav
|
||||
|
||||
FATE_AC3_FIXED_ENCODE += fate-ac3-fixed-encode
|
||||
FATE_AC3-$(call ENCMUX, AC3_FIXED, AC3) += fate-ac3-fixed-encode
|
||||
fate-ac3-fixed-encode: tests/data/asynth-44100-2.wav
|
||||
fate-ac3-fixed-encode: SRC = $(TARGET_PATH)/tests/data/asynth-44100-2.wav
|
||||
fate-ac3-fixed-encode: CMD = md5 -i $(SRC) -c ac3_fixed -ab 128k -f ac3 -flags +bitexact
|
||||
fate-ac3-fixed-encode: CMP = oneline
|
||||
fate-ac3-fixed-encode: REF = a1d1fc116463b771abf5aef7ed37d7b1
|
||||
|
||||
FATE_SAMPLES_AVCONV += $(FATE_AC3) $(FATE_AC3_ENCODE) $(FATE_AC3_FIXED_ENCODE)
|
||||
FATE_SAMPLES_AVCONV += $(FATE_EAC3) $(FATE_EAC3_ENCODE)
|
||||
FATE_SAMPLES_AVCONV- += $(FATE_AC3-yes) $(FATE_EAC3-yes)
|
||||
|
||||
fate-ac3: $(FATE_AC3) $(FATE_AC3_ENCODE) $(FATE_AC3_FIXED_ENCODE)
|
||||
fate-ac3: $(FATE_EAC3) $(FATE_EAC3_ENCODE)
|
||||
fate-ac3: $(FATE_AC3-yes) $(FATE_EAC3-yes)
|
||||
|
Loading…
Reference in New Issue
Block a user