libav: encoding/decoding error: get_buffer() failed - c

I am trying to edit the given Audio encoding/decoding examples of the libav located in libav-11.4/doc/examples/avcodec.c.
I simply want to encode a .wav file into aac and then decode back to .wav
But in the decoding step I allways get the following error:
[aac # 0x...] get_buffer() failed
Error while decoding
The Edited example code:
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#ifdef HAVE_AV_CONFIG_H
#undef HAVE_AV_CONFIG_H
#endif
#include "libavcodec/avcodec.h"
#include "libavutil/channel_layout.h"
#include "libavutil/common.h"
#include "libavutil/imgutils.h"
#include "libavutil/mathematics.h"
#include "libavutil/samplefmt.h"
#define INBUF_SIZE 4096
#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(AVCodec *codec, enum AVSampleFormat sample_fmt)
{
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt)
return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(AVCodec *codec)
{
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates)
return 44100;
p = codec->supported_samplerates;
while (*p) {
best_samplerate = FFMAX(*p, best_samplerate);
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(AVCodec *codec)
{
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channels = 0;
if (!codec->channel_layouts)
return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channels) {
best_ch_layout = *p;
best_nb_channels = nb_channels;
}
p++;
}
return best_ch_layout;
}
/*
* Audio encoding example
*/
static void audio_encode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
AVFrame *frame;
AVPacket pkt;
int i, j, k, ret, got_output;
int buffer_size;
FILE *f, *outfile;
uint16_t *samples;
float t, tincr;
printf("Audio encoding\n");
/* find the MP2 encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_AAC);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
/* put sample parameters */
c->bit_rate = 64000;
/* check that the encoder supports s16 pcm input */
c->sample_fmt = AV_SAMPLE_FMT_S16;
if (!check_sample_fmt(codec, c->sample_fmt)) {
fprintf(stderr, "encoder does not support %s",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
/* select other audio parameters supported by the encoder */
c->sample_rate = select_sample_rate(codec);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "could not open %s\n", filename);
exit(1);
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
fprintf(stderr, "could not open %s\n", filename);
exit(1);
}
/* frame containing input raw audio */
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
/* the codec gives us the frame size, in samples,
* we calculate the size of the samples buffer in bytes */
buffer_size = av_samples_get_buffer_size(NULL, c->channels, c->frame_size,
c->sample_fmt, 0);
samples = av_malloc(buffer_size);
if (!samples) {
fprintf(stderr, "could not allocate %d bytes for samples buffer\n",
buffer_size);
exit(1);
}
/* setup the data pointers in the AVFrame */
ret = avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
(const uint8_t*)samples, buffer_size, 0);
if (ret < 0) {
fprintf(stderr, "could not setup audio frame\n");
exit(1);
}
/* encode a single tone sound */
t = 0;
tincr = 2 * M_PI * 440.0 / c->sample_rate;
for(i=0;i<200;i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
for (j = 0; j < c->frame_size; j++) {
samples[2*j] = (int)(sin(t) * 10000);
for (k = 1; k < c->channels; k++)
samples[2*j + k] = samples[2*j];
t += tincr;
}
/* encode the samples */
ret = avcodec_encode_audio2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "error encoding audio frame\n");
exit(1);
}
if (got_output) {
fwrite(pkt.data, 1, pkt.size, outfile);
av_free_packet(&pkt);
}
}
fclose(f);
fclose(outfile);
av_freep(&samples);
av_frame_free(&frame);
avcodec_close(c);
av_free(c);
}
/*
* Audio decoding.
*/
static void audio_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int len;
FILE *f, *outfile;
uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
AVFrame *decoded_frame = NULL;
av_init_packet(&avpkt);
printf("Audio decoding\n");
/* find the mpeg audio decoder */
codec = avcodec_find_decoder(AV_CODEC_ID_AAC);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "could not open %s\n", filename);
exit(1);
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(c);
exit(1);
}
/* decode until eof */
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
while (avpkt.size > 0) {
int got_frame = 0;
if (!decoded_frame) {
if (!(decoded_frame = av_frame_alloc())) {
fprintf(stderr, "out of memory\n");
exit(1);
}
}
len = avcodec_decode_audio4(c, decoded_frame, &got_frame, &avpkt);
if (len < 0) {
fprintf(stderr, "Error while decoding\n");
exit(1);
}
if (got_frame) {
/* if a frame has been decoded, output it */
int data_size = av_samples_get_buffer_size(NULL, c->channels,
decoded_frame->nb_samples,
c->sample_fmt, 1);
fwrite(decoded_frame->data[0], 1, data_size, outfile);
}
avpkt.size -= len;
avpkt.data += len;
if (avpkt.size < AUDIO_REFILL_THRESH) {
/* Refill the input buffer, to avoid trying to decode
* incomplete frames. Instead of this, one could also use
* a parser, or use a proper container format through
* libavformat. */
memmove(inbuf, avpkt.data, avpkt.size);
avpkt.data = inbuf;
len = fread(avpkt.data + avpkt.size, 1,
AUDIO_INBUF_SIZE - avpkt.size, f);
if (len > 0)
avpkt.size += len;
}
}
fclose(outfile);
fclose(f);
avcodec_close(c);
av_free(c);
av_frame_free(&decoded_frame);
}
int main(int argc, char **argv)
{
const char *filename;
/* register all the codecs */
avcodec_register_all();
filename = argv[1];
audio_encode_example("test.aac", filename);
audio_decode_example("out.wav", "test.aac");
return 0;
}
EDIT:
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#ifdef HAVE_AV_CONFIG_H
#undef HAVE_AV_CONFIG_H
#endif
#include "libavcodec/avcodec.h"
#include "libavutil/channel_layout.h"
#include "libavutil/common.h"
#include "libavutil/imgutils.h"
#include "libavutil/mathematics.h"
#include "libavutil/samplefmt.h"
#include "libavformat/avformat.h"
#define INBUF_SIZE 4096
#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(AVCodec *codec, enum AVSampleFormat sample_fmt)
{
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt)
return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(AVCodec *codec)
{
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates)
return 44100;
p = codec->supported_samplerates;
while (*p) {
best_samplerate = FFMAX(*p, best_samplerate);
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(AVCodec *codec)
{
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channels = 0;
if (!codec->channel_layouts)
return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channels) {
best_ch_layout = *p;
best_nb_channels = nb_channels;
}
p++;
}
return best_ch_layout;
}
/*
* Audio encoding example
*/
static void audio_encode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
AVFrame *frame;
AVPacket pkt;
int i, j, k, ret, got_output;
int buffer_size;
FILE *f, *outfile;
uint16_t *samples;
float t, tincr;
printf("Audio encoding\n");
/* find the MP2 encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_AAC);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
/* put sample parameters */
c->bit_rate = 64000;
/* check that the encoder supports s16 pcm input */
c->sample_fmt = AV_SAMPLE_FMT_S16;
if (!check_sample_fmt(codec, c->sample_fmt)) {
fprintf(stderr, "encoder does not support %s",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
/* select other audio parameters supported by the encoder */
c->sample_rate = select_sample_rate(codec);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "could not open %s\n", filename);
exit(1);
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
fprintf(stderr, "could not open %s\n", filename);
exit(1);
}
/* frame containing input raw audio */
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
/* the codec gives us the frame size, in samples,
* we calculate the size of the samples buffer in bytes */
buffer_size = av_samples_get_buffer_size(NULL, c->channels, c->frame_size,
c->sample_fmt, 0);
samples = av_malloc(buffer_size);
if (!samples) {
fprintf(stderr, "could not allocate %d bytes for samples buffer\n",
buffer_size);
exit(1);
}
/* setup the data pointers in the AVFrame */
ret = avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
(const uint8_t*)samples, buffer_size, 0);
if (ret < 0) {
fprintf(stderr, "could not setup audio frame\n");
exit(1);
}
/* encode a single tone sound */
t = 0;
tincr = 2 * M_PI * 440.0 / c->sample_rate;
for(i=0;i<200;i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
for (j = 0; j < c->frame_size; j++) {
samples[2*j] = (int)(sin(t) * 10000);
for (k = 1; k < c->channels; k++)
samples[2*j + k] = samples[2*j];
t += tincr;
}
/* encode the samples */
ret = avcodec_encode_audio2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "error encoding audio frame\n");
exit(1);
}
if (got_output) {
fwrite(pkt.data, 1, pkt.size, outfile);
av_free_packet(&pkt);
}
}
fclose(f);
fclose(outfile);
av_freep(&samples);
av_frame_free(&frame);
avcodec_close(c);
av_free(c);
}
/*
* Audio decoding.
*/
static void audio_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int len;
FILE *f, *outfile;
uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
AVFrame *decoded_frame = NULL;
av_init_packet(&avpkt);
printf("Audio decoding\n");
/* find the mpeg audio decoder */
codec = avcodec_find_decoder(AV_CODEC_ID_AAC);
if (!codec) {
fprintf(stderr, "codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "could not open codec\n");
exit(1);
}
/*
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "could not open %s\n", filename);
exit(1);
}
*/
AVFormatContext *s = avformat_alloc_context();
int ret = avformat_open_input(&s, filename, NULL, NULL);
if (ret != 0)
{
abort();
}
// Retrieve stream information
printf("sdfsdf\n");
if(avformat_find_stream_info(s, NULL)<0)
{
printf("Could not find stream info");// Couldn't find stream information
}
// Dump information about file into standard error
av_dump_format(s, 0, filename, 0);
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(c);
exit(1);
}
/* decode until eof */
//avpkt.data = inbuf;
//avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
int read_ok = av_read_frame(s,&avpkt);
while (read_ok)
{
read_ok = av_read_frame(s,&avpkt);
int got_frame = 0;
if (!decoded_frame) {
if (!(decoded_frame = av_frame_alloc())) {
fprintf(stderr, "out of memory\n");
exit(1);
}
}
len = avcodec_decode_audio4(c, decoded_frame, &got_frame, &avpkt);
if (len < 0) {
fprintf(stderr, "Error while decoding\n");
exit(1);
}
if (got_frame) {
/* if a frame has been decoded, output it */
int data_size = av_samples_get_buffer_size(NULL, c->channels,
decoded_frame->nb_samples,
c->sample_fmt, 1);
fwrite(decoded_frame->data[0], 1, data_size, outfile);
}
/*
avpkt.size -= len;
avpkt.data += len;
if (avpkt.size < AUDIO_REFILL_THRESH) {
memmove(inbuf, avpkt.data, avpkt.size);
avpkt.data = inbuf;
len = fread(avpkt.data + avpkt.size, 1,
AUDIO_INBUF_SIZE - avpkt.size, f);
if (len > 0)
avpkt.size += len;
}*/
}
fclose(outfile);
// fclose(f);
avcodec_close(c);
av_free(c);
av_frame_free(&decoded_frame);
}
int main(int argc, char **argv)
{
const char *filename;
/* register all the codecs */
avcodec_register_all();
av_register_all();
filename = argv[1];
audio_encode_example("test.aac", filename);
audio_decode_example("out.wav", "test.aac");
return 0;
}

See this post, you can't use fopen/fread to feed raw AAC data into the decoder, you need to use av_read_frame().

Related

FFMPEG RTSP Server using muxing doc example

I am trying to develop RTSP server using FFMPEG. For that I slightly modified muxing file located at doc/example/ folder inside FFMPEG repository.
Giving my source code of RTSP server example:
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <libavutil/avassert.h>
#include <libavutil/channel_layout.h>
#include <libavutil/opt.h>
#include <libavutil/mathematics.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <libswresample/swresample.h>
#define STREAM_DURATION 10.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_PIX_FMT AV_PIX_FMT_YUV420P /* default pix_fmt */
#define SCALE_FLAGS SWS_BICUBIC
// a wrapper around a single output AVStream
typedef struct OutputStream {
AVStream *st;
AVCodecContext *enc;
/* pts of the next frame that will be generated */
int64_t next_pts;
int samples_count;
AVFrame *frame;
AVFrame *tmp_frame;
float t, tincr, tincr2;
struct SwsContext *sws_ctx;
struct SwrContext *swr_ctx;
} OutputStream;
static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt)
{
AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;
printf("pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
pkt->stream_index);
}
static int write_frame(AVFormatContext *fmt_ctx, const AVRational *time_base, AVStream *st, AVPacket *pkt)
{
/* rescale output packet timestamp values from codec to stream timebase */
av_packet_rescale_ts(pkt, *time_base, st->time_base);
pkt->stream_index = st->index;
/* Write the compressed frame to the media file. */
log_packet(fmt_ctx, pkt);
return av_interleaved_write_frame(fmt_ctx, pkt);
}
/* Add an output stream. */
static void add_stream(OutputStream *ost, AVFormatContext *oc,
AVCodec **codec,
enum AVCodecID codec_id)
{
AVCodecContext *c;
int i;
/* find the encoder */
*codec = avcodec_find_encoder(codec_id);
if (!(*codec)) {
fprintf(stderr, "Could not find encoder for '%s'\n",
avcodec_get_name(codec_id));
exit(1);
}
ost->st = avformat_new_stream(oc, NULL);
if (!ost->st) {
fprintf(stderr, "Could not allocate stream\n");
exit(1);
}
ost->st->id = oc->nb_streams-1;
c = avcodec_alloc_context3(*codec);
if (!c) {
fprintf(stderr, "Could not alloc an encoding context\n");
exit(1);
}
ost->enc = c;
switch ((*codec)->type) {
case AVMEDIA_TYPE_AUDIO:
c->sample_fmt = (*codec)->sample_fmts ?
(*codec)->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;
c->bit_rate = 64000;
c->sample_rate = 44100;
if ((*codec)->supported_samplerates) {
c->sample_rate = (*codec)->supported_samplerates[0];
for (i = 0; (*codec)->supported_samplerates[i]; i++) {
if ((*codec)->supported_samplerates[i] == 44100)
c->sample_rate = 44100;
}
}
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
c->channel_layout = AV_CH_LAYOUT_STEREO;
if ((*codec)->channel_layouts) {
c->channel_layout = (*codec)->channel_layouts[0];
for (i = 0; (*codec)->channel_layouts[i]; i++) {
if ((*codec)->channel_layouts[i] == AV_CH_LAYOUT_STEREO)
c->channel_layout = AV_CH_LAYOUT_STEREO;
}
}
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
ost->st->time_base = (AVRational){ 1, c->sample_rate };
break;
case AVMEDIA_TYPE_VIDEO:
c->codec_id = codec_id;
c->bit_rate = 400000;
/* Resolution must be a multiple of two. */
c->width = 352;
c->height = 288;
/* timebase: This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented. For fixed-fps content,
* timebase should be 1/framerate and timestamp increments should be
* identical to 1. */
ost->st->time_base = (AVRational){ 1, STREAM_FRAME_RATE };
c->time_base = ost->st->time_base;
c->gop_size = 12; /* emit one intra frame every twelve frames at most */
c->pix_fmt = STREAM_PIX_FMT;
if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
/* just for testing, we also add B-frames */
c->max_b_frames = 2;
}
if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
/* Needed to avoid using macroblocks in which some coeffs overflow.
* This does not happen with normal video, it just happens here as
* the motion of the chroma plane does not match the luma plane. */
c->mb_decision = 2;
}
break;
default:
break;
}
/* Some formats want stream headers to be separate. */
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}
/**************************************************************/
/* audio output */
static AVFrame *alloc_audio_frame(enum AVSampleFormat sample_fmt,
uint64_t channel_layout,
int sample_rate, int nb_samples)
{
AVFrame *frame = av_frame_alloc();
int ret;
if (!frame) {
fprintf(stderr, "Error allocating an audio frame\n");
exit(1);
}
frame->format = sample_fmt;
frame->channel_layout = channel_layout;
frame->sample_rate = sample_rate;
frame->nb_samples = nb_samples;
if (nb_samples) {
ret = av_frame_get_buffer(frame, 0);
if (ret < 0) {
fprintf(stderr, "Error allocating an audio buffer\n");
exit(1);
}
}
return frame;
}
static void open_audio(AVFormatContext *oc, AVCodec *codec, OutputStream *ost, AVDictionary *opt_arg)
{
AVCodecContext *c;
int nb_samples;
int ret;
AVDictionary *opt = NULL;
c = ost->enc;
/* open it */
av_dict_copy(&opt, opt_arg, 0);
ret = avcodec_open2(c, codec, &opt);
av_dict_free(&opt);
if (ret < 0) {
fprintf(stderr, "Could not open audio codec: %s\n", av_err2str(ret));
exit(1);
}
/* init signal generator */
ost->t = 0;
ost->tincr = 2 * M_PI * 110.0 / c->sample_rate;
/* increment frequency by 110 Hz per second */
ost->tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
if (c->codec->capabilities & AV_CODEC_CAP_VARIABLE_FRAME_SIZE)
nb_samples = 10000;
else
nb_samples = c->frame_size;
ost->frame = alloc_audio_frame(c->sample_fmt, c->channel_layout,
c->sample_rate, nb_samples);
ost->tmp_frame = alloc_audio_frame(AV_SAMPLE_FMT_S16, c->channel_layout,
c->sample_rate, nb_samples);
/* copy the stream parameters to the muxer */
ret = avcodec_parameters_from_context(ost->st->codecpar, c);
if (ret < 0) {
fprintf(stderr, "Could not copy the stream parameters\n");
exit(1);
}
/* create resampler context */
ost->swr_ctx = swr_alloc();
if (!ost->swr_ctx) {
fprintf(stderr, "Could not allocate resampler context\n");
exit(1);
}
/* set options */
av_opt_set_int (ost->swr_ctx, "in_channel_count", c->channels, 0);
av_opt_set_int (ost->swr_ctx, "in_sample_rate", c->sample_rate, 0);
av_opt_set_sample_fmt(ost->swr_ctx, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0);
av_opt_set_int (ost->swr_ctx, "out_channel_count", c->channels, 0);
av_opt_set_int (ost->swr_ctx, "out_sample_rate", c->sample_rate, 0);
av_opt_set_sample_fmt(ost->swr_ctx, "out_sample_fmt", c->sample_fmt, 0);
/* initialize the resampling context */
if ((ret = swr_init(ost->swr_ctx)) < 0) {
fprintf(stderr, "Failed to initialize the resampling context\n");
exit(1);
}
}
/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
* 'nb_channels' channels. */
static AVFrame *get_audio_frame(OutputStream *ost)
{
AVFrame *frame = ost->tmp_frame;
int j, i, v;
int16_t *q = (int16_t*)frame->data[0];
/* check if we want to generate more frames */
if (av_compare_ts(ost->next_pts, ost->enc->time_base,
STREAM_DURATION, (AVRational){ 1, 1 }) >= 0)
return NULL;
for (j = 0; j <frame->nb_samples; j++) {
v = (int)(sin(ost->t) * 10000);
for (i = 0; i < ost->enc->channels; i++)
*q++ = v;
ost->t += ost->tincr;
ost->tincr += ost->tincr2;
}
frame->pts = ost->next_pts;
ost->next_pts += frame->nb_samples;
return frame;
}
/*
* encode one audio frame and send it to the muxer
* return 1 when encoding is finished, 0 otherwise
*/
static int write_audio_frame(AVFormatContext *oc, OutputStream *ost)
{
AVCodecContext *c;
AVPacket pkt = { 0 }; // data and size must be 0;
AVFrame *frame;
int ret;
int got_packet;
int dst_nb_samples;
av_init_packet(&pkt);
c = ost->enc;
frame = get_audio_frame(ost);
if (frame) {
/* convert samples from native format to destination codec format, using the resampler */
/* compute destination number of samples */
dst_nb_samples = av_rescale_rnd(swr_get_delay(ost->swr_ctx, c->sample_rate) + frame->nb_samples,
c->sample_rate, c->sample_rate, AV_ROUND_UP);
av_assert0(dst_nb_samples == frame->nb_samples);
/* when we pass a frame to the encoder, it may keep a reference to it
* internally;
* make sure we do not overwrite it here
*/
ret = av_frame_make_writable(ost->frame);
if (ret < 0)
exit(1);
/* convert to destination format */
ret = swr_convert(ost->swr_ctx,
ost->frame->data, dst_nb_samples,
(const uint8_t **)frame->data, frame->nb_samples);
if (ret < 0) {
fprintf(stderr, "Error while converting\n");
exit(1);
}
frame = ost->frame;
frame->pts = av_rescale_q(ost->samples_count, (AVRational){1, c->sample_rate}, c->time_base);
ost->samples_count += dst_nb_samples;
}
ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
if (ret < 0) {
fprintf(stderr, "Error encoding audio frame: %s\n", av_err2str(ret));
exit(1);
}
if (got_packet) {
ret = write_frame(oc, &c->time_base, ost->st, &pkt);
if (ret < 0) {
fprintf(stderr, "Error while writing audio frame: %s\n",
av_err2str(ret));
exit(1);
}
}
return (frame || got_packet) ? 0 : 1;
}
/**************************************************************/
/* video output */
static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height)
{
AVFrame *picture;
int ret;
picture = av_frame_alloc();
if (!picture)
return NULL;
picture->format = pix_fmt;
picture->width = width;
picture->height = height;
/* allocate the buffers for the frame data */
ret = av_frame_get_buffer(picture, 32);
if (ret < 0) {
fprintf(stderr, "Could not allocate frame data.\n");
exit(1);
}
return picture;
}
static void open_video(AVFormatContext *oc, AVCodec *codec, OutputStream *ost, AVDictionary *opt_arg)
{
int ret;
AVCodecContext *c = ost->enc;
AVDictionary *opt = NULL;
av_dict_copy(&opt, opt_arg, 0);
/* open the codec */
ret = avcodec_open2(c, codec, &opt);
av_dict_free(&opt);
if (ret < 0) {
fprintf(stderr, "Could not open video codec: %s\n", av_err2str(ret));
exit(1);
}
/* allocate and init a re-usable frame */
ost->frame = alloc_picture(c->pix_fmt, c->width, c->height);
if (!ost->frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
/* If the output format is not YUV420P, then a temporary YUV420P
* picture is needed too. It is then converted to the required
* output format. */
ost->tmp_frame = NULL;
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
ost->tmp_frame = alloc_picture(AV_PIX_FMT_YUV420P, c->width, c->height);
if (!ost->tmp_frame) {
fprintf(stderr, "Could not allocate temporary picture\n");
exit(1);
}
}
/* copy the stream parameters to the muxer */
ret = avcodec_parameters_from_context(ost->st->codecpar, c);
if (ret < 0) {
fprintf(stderr, "Could not copy the stream parameters\n");
exit(1);
}
}
/* Prepare a dummy image. */
static void fill_yuv_image(AVFrame *pict, int frame_index,
int width, int height)
{
int x, y, i;
i = frame_index;
/* Y */
for (y = 0; y < height; y++)
for (x = 0; x < width; x++)
pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;
/* Cb and Cr */
for (y = 0; y < height / 2; y++) {
for (x = 0; x < width / 2; x++) {
pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
}
}
}
static AVFrame *get_video_frame(OutputStream *ost)
{
AVCodecContext *c = ost->enc;
/* check if we want to generate more frames */
if (av_compare_ts(ost->next_pts, c->time_base,
STREAM_DURATION, (AVRational){ 1, 1 }) >= 0)
return NULL;
/* when we pass a frame to the encoder, it may keep a reference to it
* internally; make sure we do not overwrite it here */
if (av_frame_make_writable(ost->frame) < 0)
exit(1);
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
/* as we only generate a YUV420P picture, we must convert it
* to the codec pixel format if needed */
if (!ost->sws_ctx) {
ost->sws_ctx = sws_getContext(c->width, c->height,
AV_PIX_FMT_YUV420P,
c->width, c->height,
c->pix_fmt,
SCALE_FLAGS, NULL, NULL, NULL);
if (!ost->sws_ctx) {
fprintf(stderr,
"Could not initialize the conversion context\n");
exit(1);
}
}
fill_yuv_image(ost->tmp_frame, ost->next_pts, c->width, c->height);
sws_scale(ost->sws_ctx,
(const uint8_t * const *)ost->tmp_frame->data, ost->tmp_frame->linesize,
0, c->height, ost->frame->data, ost->frame->linesize);
} else {
fill_yuv_image(ost->frame, ost->next_pts, c->width, c->height);
}
ost->frame->pts = ost->next_pts++;
return ost->frame;
}
/*
* encode one video frame and send it to the muxer
* return 1 when encoding is finished, 0 otherwise
*/
static int write_video_frame(AVFormatContext *oc, OutputStream *ost)
{
int ret;
AVCodecContext *c;
AVFrame *frame;
int got_packet = 0;
AVPacket pkt = { 0 };
c = ost->enc;
frame = get_video_frame(ost);
av_init_packet(&pkt);
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_packet);
if (ret < 0) {
fprintf(stderr, "Error encoding video frame: %s\n", av_err2str(ret));
exit(1);
}
if (got_packet) {
ret = write_frame(oc, &c->time_base, ost->st, &pkt);
} else {
ret = 0;
}
if (ret < 0) {
fprintf(stderr, "Error while writing video frame: %s\n", av_err2str(ret));
exit(1);
}
return (frame || got_packet) ? 0 : 1;
}
static void close_stream(AVFormatContext *oc, OutputStream *ost)
{
avcodec_free_context(&ost->enc);
av_frame_free(&ost->frame);
av_frame_free(&ost->tmp_frame);
sws_freeContext(ost->sws_ctx);
swr_free(&ost->swr_ctx);
}
/**************************************************************/
/* media file output */
int main(int argc, char **argv)
{
OutputStream video_st = { 0 }, audio_st = { 0 };
const char *filename;
AVOutputFormat *fmt;
AVFormatContext *oc;
AVCodec *audio_codec, *video_codec;
int ret;
int have_video = 0, have_audio = 0;
int encode_video = 0, encode_audio = 0;
AVDictionary *opt = NULL;
int i;
/* Initialize libavcodec, and register all codecs and formats. */
av_register_all();
avformat_network_init();
if (argc < 2) {
printf("usage: %s output_file\n"
"API example program to output a media file with libavformat.\n"
"This program generates a synthetic audio and video stream, encodes and\n"
"muxes them into a file named output_file.\n"
"The output format is automatically guessed according to the file extension.\n"
"Raw images can also be output by using '%%d' in the filename.\n"
"\n", argv[0]);
return 1;
}
filename = argv[1];
for (i = 2; i+1 < argc; i+=2) {
if (!strcmp(argv[i], "-flags") || !strcmp(argv[i], "-fflags"))
av_dict_set(&opt, argv[i]+1, argv[i+1], 0);
}
/* allocate the output media context */
avformat_alloc_output_context2(&oc, NULL, "rtsp", filename);
if (!oc) {
printf("Could not deduce output format from file extension: using MPEG.\n");
avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);
}
if (!oc)
return 1;
fmt = oc->oformat;
/* Add the audio and video streams using the default format codecs
* and initialize the codecs. */
if (fmt->video_codec != AV_CODEC_ID_NONE) {
add_stream(&video_st, oc, &video_codec, fmt->video_codec);
have_video = 1;
encode_video = 1;
}
if (fmt->audio_codec != AV_CODEC_ID_NONE) {
add_stream(&audio_st, oc, &audio_codec, fmt->audio_codec);
have_audio = 1;
encode_audio = 1;
}
/* Now that all the parameters are set, we can open the audio and
* video codecs and allocate the necessary encode buffers. */
if (have_video)
open_video(oc, video_codec, &video_st, opt);
if (have_audio)
open_audio(oc, audio_codec, &audio_st, opt);
av_dump_format(oc, 0, filename, 1);
/* open the output file, if needed */
if (!(fmt->flags & AVFMT_NOFILE)) {
ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
fprintf(stderr, "Could not open '%s': %s\n", filename,
av_err2str(ret));
return 1;
}
}
/* Write the stream header, if any. */
ret = avformat_write_header(oc, &opt);
if (ret < 0) {
fprintf(stderr, "Error occurred when opening output file: %s\n",
av_err2str(ret));
return 1;
}
while (encode_video || encode_audio) {
/* select the stream to encode */
if (encode_video &&
(!encode_audio || av_compare_ts(video_st.next_pts, video_st.enc->time_base,
audio_st.next_pts, audio_st.enc->time_base) <= 0)) {
encode_video = !write_video_frame(oc, &video_st);
} else {
encode_audio = !write_audio_frame(oc, &audio_st);
}
}
/* Write the trailer, if any. The trailer must be written before you
* close the CodecContexts open when you wrote the header; otherwise
* av_write_trailer() may try to use memory that was freed on
* av_codec_close(). */
av_write_trailer(oc);
/* Close each codec. */
if (have_video)
close_stream(oc, &video_st);
if (have_audio)
close_stream(oc, &audio_st);
if (!(fmt->flags & AVFMT_NOFILE))
/* Close the output file. */
avio_closep(&oc->pb);
/* free the stream */
avformat_free_context(oc);
return 0;
}
After compiling it, I am running binary:
$ ./muxing rtsp://127.0.0.1/test
Output #0, rtsp, to 'rtsp://127.0.0.1/test':
Stream #0:0: Video: mpeg4, yuv420p, 352x288, q=2-31, 400 kb/s, 25 tbn
Stream #0:1: Audio: aac (LC), 44100 Hz, stereo, fltp, 64 kb/s
[tcp # 0x2b9d220] Connection to tcp://127.0.0.1:554?timeout=0 failed: Connection refused
Error occurred when opening output file: Connection refused
But getting Connection refused error,
I created this repository for rtsp server using ffserver code:
https://github.com/harshil1991/ffserver.git
Now I can able to integrate this source code in my existing repo.

How to open a .sw file using libav library in c language?

I created a .sw(16 bit pcm) file by passing an audio file. Now I am trying to get back the original audio(.mp3) by passing the .sw file as an input to the following file.
How can I read the .sw file content so that I can get back the mp3 file. Below is the code,
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/frame.h>
#include <libavutil/samplefmt.h>
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(const AVCodec *codec, enum AVSampleFormat sample_fmt)
{
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt)
return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(const AVCodec *codec)
{
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates)
return 44100;
p = codec->supported_samplerates;
while (*p) {
if (!best_samplerate || abs(44100 - *p) < abs(44100 - best_samplerate))
best_samplerate = *p;
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(const AVCodec *codec)
{
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channels = 0;
if (!codec->channel_layouts)
return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channels) {
best_ch_layout = *p;
best_nb_channels = nb_channels;
}
p++;
}
return best_ch_layout;
}
static void encode(AVCodecContext *ctx, AVFrame *frame, AVPacket *pkt,
FILE *output)
{
int ret;
/* send the frame for encoding */
ret = avcodec_send_frame(ctx, frame);
if (ret < 0) {
fprintf(stderr, "Error sending the frame to the encoder\n");
exit(1);
}
/* read all the available output packets (in general there may be any
* number of them */
while (ret >= 0) {
ret = avcodec_receive_packet(ctx, pkt);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
return;
else if (ret < 0) {
fprintf(stderr, "Error encoding audio frame\n");
exit(1);
}
fwrite(pkt->data, 1, pkt->size, output);
av_packet_unref(pkt);
}
}
int main(int argc, char **argv)
{
const char *filename;
const AVCodec *codec;
AVCodecContext *c= NULL;
AVFrame *frame;
AVPacket *pkt;
int i, j, k, ret;
FILE *f;
uint16_t *samples;
float t, tincr;
av_register_all();
avcodec_register_all();
if (argc <= 1) {
fprintf(stderr, "Usage: %s <output file>\n", argv[0]);
return 0;
}
filename = argv[1];
/* find the MP2 encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_MP3);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate audio codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 64000;
/* check that the encoder supports s16 pcm input */
c->sample_fmt = AV_SAMPLE_FMT_S16P;
if (!check_sample_fmt(codec, c->sample_fmt)) {
fprintf(stderr, "Encoder does not support sample format %s",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
/* select other audio parameters supported by the encoder */
c->sample_rate = select_sample_rate(codec);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
/* packet for holding encoded output */
pkt = av_packet_alloc();
if (!pkt) {
fprintf(stderr, "could not allocate the packet\n");
exit(1);
}
/* frame containing input raw audio */
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
/* allocate the data buffers */
ret = av_frame_get_buffer(frame, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate audio data buffers\n");
exit(1);
}
/* encode a single tone sound */
t = 0;
tincr = 2 * M_PI * 440.0 / c->sample_rate;
for (i = 0; i < 200; i++) {
/* make sure the frame is writable -- makes a copy if the encoder
* kept a reference internally */
ret = av_frame_make_writable(frame);
if (ret < 0)
exit(1);
samples = (uint16_t*)frame->data[0];
for (j = 0; j < c->frame_size; j++) {
samples[2*j] = (int)(sin(t) * 10000);
for (k = 1; k < c->channels; k++)
samples[2*j + k] = samples[2*j];
t += tincr;
}
encode(c, frame, pkt, f);
}
/* flush the encoder */
encode(c, NULL, pkt, f);
fclose(f);
av_frame_free(&frame);
av_packet_free(&pkt);
avcodec_free_context(&c);
return 0;
}
I just want to know, where and how the .sw file is reading in the above audio encoding code?

Decode AAC with FFmpeg in RTP packet

I'm trying to decode AAC in RTP packet with FFmpeg. According to rfc document the RTP payload is audioMuxElement mapped directly. I try remove the RTP header and read the remaining bytes to AVPacket struct, but the avcodec_decode_audio4() returning error -1094995529. Here is the code:
#include "stdafx.h"
#include "stdio.h"
#include "conio.h"
extern "C"
{
#ifndef __STDC_CONSTANT_MACROS
#define __STDC_CONSTANT_MACROS
#endif
#include <libavcodec\avcodec.h>
#include <libavformat\avformat.h>
}
// compatibility with newer API
#if LIBAVCODEC_VERSION_INT < AV_VERSION_INT(55,28,1)
#define av_frame_alloc avcodec_alloc_frame
#define av_frame_free avcodec_free_frame
#endif
#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096
#define SAMPLE_RATE 44100
#define CHANNEL_NUM 2
static void decode_packet();
int main(int argc, char *argv[]) {
decode_packet();
getch();
return 0;
}
static void decode_packet()
{
const char *filename = "D:\\NoRTP_AACPacket.dat";
const char *outfilename = "D:\\test2.pcm";
AVCodec *codec;
AVFormatContext *pFormatCtx = NULL;
AVCodecContext * pCodecCtx= NULL;
int len;
FILE *f, *outfile;
uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
AVFrame *decoded_frame = NULL;
av_register_all();
av_init_packet(&avpkt);
printf("Decode audio file %s to %s\n", filename, outfilename);
// Find the decoder for the audio stream
codec=avcodec_find_decoder(AV_CODEC_ID_AAC_LATM);
if(codec==NULL) {
fprintf(stderr, "Codec not found\n");
return; // Codec not found
}
pCodecCtx = avcodec_alloc_context3(codec);
if (!pCodecCtx) {
fprintf(stderr, "Could not allocate audio codec context\n");
return;
}
pCodecCtx->sample_rate = SAMPLE_RATE;
pCodecCtx->channels = CHANNEL_NUM;
/* open it */
if (avcodec_open2(pCodecCtx, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
return;
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
return;
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(pCodecCtx);
return;
}
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
// supposed to do this but don't have AVFormatContext
// int frReadStt = av_read_frame(pFormatCtx, &avpkt);
/* decode until eof */
while (avpkt.size > 0) {
int i, ch;
int got_frame = 0;
if (!decoded_frame) {
if (!(decoded_frame = av_frame_alloc())) {
fprintf(stderr, "Could not allocate audio frame\n");
return;
}
}
len = avcodec_decode_audio4(pCodecCtx, decoded_frame, &got_frame, &avpkt);
if (len < 0) {
fprintf(stderr, "Error while decoding. len = %d \n",len);
return;
}
if (got_frame) {
/* if a frame has been decoded, output it */
int data_size = av_get_bytes_per_sample(pCodecCtx->sample_fmt);
if (data_size < 0) {
/* This should not occur, checking just for paranoia */
fprintf(stderr, "Failed to calculate data size\n");
return;
}
for (i=0; i < decoded_frame->nb_samples; i++)
for (ch=0; ch < pCodecCtx->channels; ch++)
fwrite(decoded_frame->data[ch] + data_size*i, 1, data_size, outfile);
}
avpkt.size -= len;
avpkt.data += len;
avpkt.dts =
avpkt.pts = AV_NOPTS_VALUE;
// frReadStt = av_read_frame(pFormatCtx, &avpkt);
if (avpkt.size < AUDIO_REFILL_THRESH) {
/* Refill the input buffer, to avoid trying to decode
* incomplete frames. Instead of this, one could also use
* a parser, or use a proper container format through
* libavformat. */
memmove(inbuf, avpkt.data, avpkt.size);
avpkt.data = inbuf;
len = fread(avpkt.data + avpkt.size, 1,
AUDIO_INBUF_SIZE - avpkt.size, f);
if (len > 0)
avpkt.size += len;
}
}
fclose(outfile);
fclose(f);
avcodec_close(pCodecCtx);
av_free(pCodecCtx);
av_frame_free(&decoded_frame);
printf("Finish decode audio file %s to %s\n", filename, outfilename);
}
I learnt from this question that I should use av_read_frame() instead of fread but I only have RTP payload not a whole file. Is it right to directly map rtp payload to AVPacket struct? If not then how should I decode the RTP payload?
I ended up using codec AV_CODEC_ID_AAC instead of AV_CODEC_ID_AAC_LATM. After digging into rfc and ISO document, I figured out that the packet is format in LATM but the input packet for AAC Decoder have to be formatted in ADTS, so a bit of parser have to be written here. I can't post the code but it's not too hard to write one.

Error when decode AAC with avcodec_decode_audio4()

I'm trying to decode AAC with FFmpeg native decoder and encountered an error
SSR is not implemeted. Update your FFmpeg version to newest from Git. If the problem still occurs, it mean that your file has a feature which has not implemented.
Function avcodec_decode_audio4() return -1163346256. Is this because of FFmpeg version? I downloaded shared and dev version from here. Is this up to date?
Here is the source code:
#include "stdafx.h"
#include "stdio.h"
#include "conio.h"
extern "C"
{
#ifndef __STDC_CONSTANT_MACROS
#define __STDC_CONSTANT_MACROS
#endif
#include <libavcodec\avcodec.h>
#include <libavformat/avformat.h>
}
// compatibility with newer API
#if LIBAVCODEC_VERSION_INT < AV_VERSION_INT(55,28,1)
#define av_frame_alloc avcodec_alloc_frame
#define av_frame_free avcodec_free_frame
#endif
#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096
static void audio_decode_example(const char *outfilename, const char *filename);
int main(int argc, char *argv[]) {
audio_decode_example("D:\\sample.pcm","D:\\sample.m4a");
getch();
return 0;
}
/*
* Audio decoding.
*/
static void audio_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVFormatContext *pFormatCtx = NULL;
AVCodecContext *pCodecCtxOrig = NULL;
AVCodecContext * pCodecCtx= NULL;
int len;
FILE *f, *outfile;
uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
AVFrame *decoded_frame = NULL;
av_register_all();
av_init_packet(&avpkt);
printf("Decode audio file %s to %s\n", filename, outfilename);
// Open file to get format context
if(avformat_open_input(&pFormatCtx, filename, NULL, NULL)!=0){
printf("Couldn't open file");
return; // Couldn't open file
}
// Retrieve stream information
if(avformat_find_stream_info(pFormatCtx, NULL)<0){
printf("Couldn't find stream information");
return; // Couldn't find stream information
}
// Dump information about file onto standard error
av_dump_format(pFormatCtx, 0, filename, 0);
// Find the first audio stream
int audioStream = -1;
int i =0;
for(i=0; i<pFormatCtx->nb_streams; i++) {
if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO) {
audioStream=i;
break;
}
}
if(audioStream==-1) {
printf("Didn't find a audio stream");
return; // Didn't find a audio stream
}
// Get a pointer to the codec context for the audio stream
pCodecCtxOrig=pFormatCtx->streams[audioStream]->codec;
// Find the decoder for the audio stream
codec=avcodec_find_decoder(pCodecCtxOrig->codec_id);
if(codec==NULL) {
fprintf(stderr, "Codec not found\n");
return; // Codec not found
}
pCodecCtx = avcodec_alloc_context3(codec);
if (!pCodecCtx) {
fprintf(stderr, "Could not allocate audio codec context\n");
return;
}
if(avcodec_copy_context(pCodecCtx, pCodecCtxOrig) != 0) {
fprintf(stderr, "Couldn't copy codec context");
return; // Error copying codec context
}
/* open it */
if (avcodec_open2(pCodecCtx, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
return;
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
return;
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(pCodecCtx);
return;
}
/* decode until eof */
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
while (avpkt.size > 0) {
int i, ch;
int got_frame = 0;
if (!decoded_frame) {
if (!(decoded_frame = av_frame_alloc())) {
fprintf(stderr, "Could not allocate audio frame\n");
return;
}
}
len = avcodec_decode_audio4(pCodecCtx, decoded_frame, &got_frame, &avpkt);
if (len < 0) {
fprintf(stderr, "Error while decoding. len = %d \n",len);
return;
}
if (got_frame) {
/* if a frame has been decoded, output it */
int data_size = av_get_bytes_per_sample(pCodecCtx->sample_fmt);
if (data_size < 0) {
/* This should not occur, checking just for paranoia */
fprintf(stderr, "Failed to calculate data size\n");
return;
}
for (i=0; i < decoded_frame->nb_samples; i++)
for (ch=0; ch < pCodecCtx->channels; ch++)
fwrite(decoded_frame->data[ch] + data_size*i, 1, data_size, outfile);
}
avpkt.size -= len;
avpkt.data += len;
avpkt.dts =
avpkt.pts = AV_NOPTS_VALUE;
if (avpkt.size < AUDIO_REFILL_THRESH) {
/* Refill the input buffer, to avoid trying to decode
* incomplete frames. Instead of this, one could also use
* a parser, or use a proper container format through
* libavformat. */
memmove(inbuf, avpkt.data, avpkt.size);
avpkt.data = inbuf;
len = fread(avpkt.data + avpkt.size, 1,
AUDIO_INBUF_SIZE - avpkt.size, f);
if (len > 0)
avpkt.size += len;
}
}
fclose(outfile);
fclose(f);
avcodec_close(pCodecCtx);
av_free(pCodecCtx);
av_frame_free(&decoded_frame);
}
I have also read this question: How to decode AAC using avcodec_decode_audio4? but no solution is provided.
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
return;
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(pCodecCtx);
return;
}
/* decode until eof */
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
while (avpkt.size > 0) {
int i, ch;
int got_frame = 0;
Yeah, that's not going to work. You can't dump raw bytes from some random muxing format (potentially mp4) into a decoder and expect it to work. Use av_read_frame() to read individual audio packets from the muxing format, and feed the resulting AVPacket into the decoder using avcodec_decode_audio4(). See e.g. the dranger api tutorial. I know api-example.c uses the above code, but that unfortunately only works for a very limited subset of cases. Also see the detailed description in the API docs.

C - Transcoding to UDP using FFmpeg?

I'm trying to use the FFmpeg libraries to take an existing video file and stream it over a UDP connection. Specifically, I've been looking at the muxing.c and demuxing.c example files in the source code doc/example directory of FFmpeg. The demuxing file presents code which allows an input video to be converted into the video and audio streams. The muxing file presents code which creates fake data and can already be output to a UDP connection as I would like. I've begun work combining the two. Below can be found my code which is basically a copy of the muxing file with some parts replaced/appended with parts of the demuxing file. Unfortunately I'm running into plenty of complications attempting my goal through this approach. Is there an existing source code example which does the transcoding I'm looking for? Or at least a tutorial on how one might create this? If not, at least a few pointers might be helpful in directing my work in combing the two files to achieve my goal. Specifically, I'm getting the error:
[NULL # 0x23b4040] Unable to find a suitable output format for 'udp://localhost:7777'
Could not deduce output format from file extension: using MPEG.
Output #0, mpeg, to 'udp://localhost:7777':
Even though the muxing file could accept UDP formats. Any suggestions? Thank you much!
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <libavutil/mathematics.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
/* 5 seconds stream duration */
#define STREAM_DURATION 200.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_NB_FRAMES ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
#define STREAM_PIX_FMT AV_PIX_FMT_YUV420P /* default pix_fmt */
//FROM DE
static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static AVStream *video_stream = NULL, *audio_stream = NULL;
static const char *src_filename = NULL;
static const char *video_dst_filename = NULL;
static const char *audio_dst_filename = NULL;
static FILE *video_dst_file = NULL;
static FILE *audio_dst_file = NULL;
static uint8_t *video_dst_data[4] = {NULL};
static int video_dst_linesize[4];
static int video_dst_bufsize;
static uint8_t **audio_dst_data = NULL;
static int audio_dst_linesize;
static int audio_dst_bufsize;
static int video_stream_idx = -1, audio_stream_idx = -1;
static AVFrame *frame = NULL;
static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;
//END DE
static int sws_flags = SWS_BICUBIC;
/**************************************************************/
/* audio output */
static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;
/* Add an output stream. */
static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
enum AVCodecID codec_id)
{
AVCodecContext *c;
AVStream *st;
/* find the encoder */
*codec = avcodec_find_encoder(codec_id);
if (!(*codec)) {
fprintf(stderr, "Could not find encoder for '%s'\n",
avcodec_get_name(codec_id));
exit(1);
}
st = avformat_new_stream(oc, *codec);
if (!st) {
fprintf(stderr, "Could not allocate stream\n");
exit(1);
}
st->id = oc->nb_streams-1;
c = st->codec;
switch ((*codec)->type) {
case AVMEDIA_TYPE_AUDIO:
st->id = 1;
c->sample_fmt = AV_SAMPLE_FMT_S16;
c->bit_rate = 64000;
c->sample_rate = 44100;
c->channels = 2;
break;
case AVMEDIA_TYPE_VIDEO:
c->codec_id = codec_id;
c->bit_rate = 400000;
/* Resolution must be a multiple of two. */
c->width = 352;
c->height = 288;
/* timebase: This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented. For fixed-fps content,
* timebase should be 1/framerate and timestamp increments should be
* identical to 1. */
c->time_base.den = STREAM_FRAME_RATE;
c->time_base.num = 1;
c->gop_size = 12; /* emit one intra frame every twelve frames at most */
c->pix_fmt = STREAM_PIX_FMT;
if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
/* just for testing, we also add B frames */
c->max_b_frames = 2;
}
if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
/* Needed to avoid using macroblocks in which some coeffs overflow.
* This does not happen with normal video, it just happens here as
* the motion of the chroma plane does not match the luma plane. */
c->mb_decision = 2;
}
break;
default:
break;
}
/* Some formats want stream headers to be separate. */
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= CODEC_FLAG_GLOBAL_HEADER;
return st;
}
/**************************************************************/
/* audio output */
static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;
static void open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
AVCodecContext *c;
int ret;
c = st->codec;
/* open it */
ret = avcodec_open2(c, codec, NULL);
if (ret < 0) {
fprintf(stderr, "Could not open audio codec: %s\n", av_err2str(ret));
exit(1);
}
/* init signal generator */
t = 0;
tincr = 2 * M_PI * 110.0 / c->sample_rate;
/* increment frequency by 110 Hz per second */
tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
if (c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)
audio_input_frame_size = 10000;
else
audio_input_frame_size = c->frame_size;
samples = av_malloc(audio_input_frame_size *
av_get_bytes_per_sample(c->sample_fmt) *
c->channels);
if (!samples) {
fprintf(stderr, "Could not allocate audio samples buffer\n");
exit(1);
}
}
/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
* 'nb_channels' channels. */
static void get_audio_frame(int16_t *samples, int frame_size, int nb_channels)
{
int j, i, v;
int16_t *q;
q = samples;
for (j = 0; j < frame_size; j++) {
v = (int)(sin(t) * 10000);
for (i = 0; i < nb_channels; i++)
*q++ = v;
t += tincr;
tincr += tincr2;
}
}
static void write_audio_frame(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
AVPacket pkt = { 0 }; // data and size must be 0;
AVFrame *frame = avcodec_alloc_frame();
int got_packet, ret;
av_init_packet(&pkt);
c = st->codec;
get_audio_frame(samples, audio_input_frame_size, c->channels);
frame->nb_samples = audio_input_frame_size;
avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
(uint8_t *)samples,
audio_input_frame_size *
av_get_bytes_per_sample(c->sample_fmt) *
c->channels, 1);
ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
if (ret < 0) {
fprintf(stderr, "Error encoding audio frame: %s\n", av_err2str(ret));
exit(1);
}
if (!got_packet)
return;
pkt.stream_index = st->index;
/* Write the compressed frame to the media file. */
ret = av_interleaved_write_frame(oc, &pkt);
if (ret != 0) {
fprintf(stderr, "Error while writing audio frame: %s\n",
av_err2str(ret));
exit(1);
}
avcodec_free_frame(&frame);
}
static void close_audio(AVFormatContext *oc, AVStream *st)
{
avcodec_close(st->codec);
av_free(samples);
}
/**************************************************************/
/* video output */
static AVFrame *frame;
static AVPicture src_picture, dst_picture;
static int frame_count;
static void open_video(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
int ret;
AVCodecContext *c = st->codec;
/* open the codec */
ret = avcodec_open2(c, codec, NULL);
if (ret < 0) {
fprintf(stderr, "Could not open video codec: %s\n", av_err2str(ret));
exit(1);
}
/* allocate and init a re-usable frame */
frame = avcodec_alloc_frame();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
/* Allocate the encoded raw picture. */
ret = avpicture_alloc(&dst_picture, c->pix_fmt, c->width, c->height);
if (ret < 0) {
fprintf(stderr, "Could not allocate picture: %s\n", av_err2str(ret));
exit(1);
}
/* If the output format is not YUV420P, then a temporary YUV420P
* picture is needed too. It is then converted to the required
* output format. */
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
ret = avpicture_alloc(&src_picture, AV_PIX_FMT_YUV420P, c->width, c->height);
if (ret < 0) {
fprintf(stderr, "Could not allocate temporary picture: %s\n",
av_err2str(ret));
exit(1);
}
}
/* copy data and linesize picture pointers to frame */
*((AVPicture *)frame) = dst_picture;
}
/* Prepare a dummy image. */
static void fill_yuv_image(AVPicture *pict, int frame_index,
int width, int height)
{
int x, y, i;
i = frame_index;
/* Y */
for (y = 0; y < height; y++)
for (x = 0; x < width; x++)
pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;
/* Cb and Cr */
for (y = 0; y < height / 2; y++) {
for (x = 0; x < width / 2; x++) {
pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
}
}
}
static void write_video_frame(AVFormatContext *oc, AVStream *st)
{
int ret;
static struct SwsContext *sws_ctx;
AVCodecContext *c = st->codec;
if (frame_count >= STREAM_NB_FRAMES) {
/* No more frames to compress. The codec has a latency of a few
* frames if using B-frames, so we get the last frames by
* passing the same picture again. */
} else {
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
/* as we only generate a YUV420P picture, we must convert it
* to the codec pixel format if needed */
if (!sws_ctx) {
sws_ctx = sws_getContext(c->width, c->height, AV_PIX_FMT_YUV420P,
c->width, c->height, c->pix_fmt,
sws_flags, NULL, NULL, NULL);
if (!sws_ctx) {
fprintf(stderr,
"Could not initialize the conversion context\n");
exit(1);
}
}
fill_yuv_image(&src_picture, frame_count, c->width, c->height);
sws_scale(sws_ctx,
(const uint8_t * const *)src_picture.data, src_picture.linesize,
0, c->height, dst_picture.data, dst_picture.linesize);
} else {
fill_yuv_image(&dst_picture, frame_count, c->width, c->height);
}
}
if (oc->oformat->flags & AVFMT_RAWPICTURE) {
/* Raw video case - directly store the picture in the packet */
AVPacket pkt;
av_init_packet(&pkt);
pkt.flags |= AV_PKT_FLAG_KEY;
pkt.stream_index = st->index;
pkt.data = dst_picture.data[0];
pkt.size = sizeof(AVPicture);
ret = av_interleaved_write_frame(oc, &pkt);
} else {
AVPacket pkt = { 0 };
int got_packet;
av_init_packet(&pkt);
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_packet);
if (ret < 0) {
fprintf(stderr, "Error encoding video frame: %s\n", av_err2str(ret));
exit(1);
}
/* If size is zero, it means the image was buffered. */
if (!ret && got_packet && pkt.size) {
pkt.stream_index = st->index;
/* Write the compressed frame to the media file. */
ret = av_interleaved_write_frame(oc, &pkt);
} else {
ret = 0;
}
}
if (ret != 0) {
fprintf(stderr, "Error while writing video frame: %s\n", av_err2str(ret));
exit(1);
}
frame_count++;
}
static void close_video(AVFormatContext *oc, AVStream *st)
{
avcodec_close(st->codec);
av_free(src_picture.data[0]);
av_free(dst_picture.data[0]);
av_free(frame);
}
static int open_codec_context(int *stream_idx,
AVFormatContext *fmt_ctx, enum AVMediaType type)
{
int ret;
AVStream *st;
AVCodecContext *dec_ctx = NULL;
AVCodec *dec = NULL;
ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
if (ret < 0) {
fprintf(stderr, "Could not find %s stream in input file '%s'\n",
av_get_media_type_string(type), src_filename);
return ret;
} else {
*stream_idx = ret;
st = fmt_ctx->streams[*stream_idx];
/* find decoder for the stream */
dec_ctx = st->codec;
dec = avcodec_find_decoder(dec_ctx->codec_id);
if (!dec) {
fprintf(stderr, "Failed to find %s codec\n",
av_get_media_type_string(type));
return ret;
}
if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) {
fprintf(stderr, "Failed to open %s codec\n",
av_get_media_type_string(type));
return ret;
}
}
return 0;
}
/**************************************************************/
/* media file output */
int main(int argc, char **argv)
{
const char *filename;
AVOutputFormat *fmt;
AVFormatContext *oc;
AVStream *audio_st, *video_st;
AVCodec *audio_codec, *video_codec;
double audio_pts, video_pts;
int ret = 0, got_frame;;
/* Initialize libavcodec, and register all codecs and formats. */
av_register_all();
if (argc != 3) {
printf("usage: %s input_file output_file\n"
"\n", argv[0]);
return 1;
}
src_filename = argv[1];
filename = argv[2];
/* allocate the output media context */
avformat_alloc_output_context2(&oc, NULL, NULL, filename);
if (!oc) {
printf("Could not deduce output format from file extension: using MPEG.\n");
avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);
}
if (!oc) {
return 1;
}
fmt = oc->oformat;
/* Add the audio and video streams using the default format codecs
* and initialize the codecs. */
video_stream = NULL;
audio_stream = NULL;
//FROM DE
/* open input file, and allocate format context */
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
fprintf(stderr, "Could not open source file %s\n", src_filename);
exit(1);
}
/* retrieve stream information */
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
fprintf(stderr, "Could not find stream information\n");
exit(1);
}
if (open_codec_context(&video_stream_idx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) {
video_stream = fmt_ctx->streams[video_stream_idx];
video_dec_ctx = video_stream->codec;
/* allocate image where the decoded image will be put */
ret = av_image_alloc(video_dst_data, video_dst_linesize,
video_dec_ctx->width, video_dec_ctx->height,
video_dec_ctx->pix_fmt, 1);
if (ret < 0) {
fprintf(stderr, "Could not allocate raw video buffer\n");
goto end;
}
video_dst_bufsize = ret;
}
if (open_codec_context(&audio_stream_idx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
int nb_planes;
audio_stream = fmt_ctx->streams[audio_stream_idx];
audio_dec_ctx = audio_stream->codec;
nb_planes = av_sample_fmt_is_planar(audio_dec_ctx->sample_fmt) ?
audio_dec_ctx->channels : 1;
audio_dst_data = av_mallocz(sizeof(uint8_t *) * nb_planes);
if (!audio_dst_data) {
fprintf(stderr, "Could not allocate audio data buffers\n");
ret = AVERROR(ENOMEM);
goto end;
}
}
//END DE
/* Now that all the parameters are set, we can open the audio and
* video codecs and allocate the necessary encode buffers. */
if (video_stream)
open_video(oc, video_codec, video_stream);
if (audio_stream)
open_audio(oc, audio_codec, audio_stream);
av_dump_format(oc, 0, filename, 1);
/* open the output file, if needed */
if (!(fmt->flags & AVFMT_NOFILE)) {
ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
fprintf(stderr, "Could not open '%s': %s\n", filename,
av_err2str(ret));
return 1;
}
}
/* Write the stream header, if any. */
ret = avformat_write_header(oc, NULL);
if (ret < 0) {
fprintf(stderr, "Error occurred when opening output file: %s\n",
av_err2str(ret));
return 1;
}
if (frame)
frame->pts = 0;
for (;;) {
/* Compute current audio and video time. */
if (audio_stream)
audio_pts = (double)audio_stream->pts.val * audio_stream->time_base.num / audio_stream->time_base.den;
else
audio_pts = 0.0;
if (video_stream)
video_pts = (double)video_stream->pts.val * video_stream->time_base.num /
video_stream->time_base.den;
else
video_pts = 0.0;
if ((!audio_stream || audio_pts >= STREAM_DURATION) &&
(!video_stream || video_pts >= STREAM_DURATION))
break;
/* write interleaved audio and video frames */
if (!video_stream || (video_stream && audio_st && audio_pts < video_pts)) {
write_audio_frame(oc, audio_stream);
} else {
write_video_frame(oc, video_stream);
frame->pts += av_rescale_q(1, video_stream->codec->time_base, video_stream->time_base);
}
}
/* Write the trailer, if any. The trailer must be written before you
* close the CodecContexts open when you wrote the header; otherwise
* av_write_trailer() may try to use memory that was freed on
* av_codec_close(). */
av_write_trailer(oc);
/* Close each codec. */
if (video_st)
close_video(oc, video_st);
if (audio_st)
close_audio(oc, audio_st);
if (!(fmt->flags & AVFMT_NOFILE))
/* Close the output file. */
avio_close(oc->pb);
/* free the stream */
avformat_free_context(oc);
end:
if (video_dec_ctx)
avcodec_close(video_dec_ctx);
if (audio_dec_ctx)
avcodec_close(audio_dec_ctx);
avformat_close_input(&fmt_ctx);
if (video_dst_file)
fclose(video_dst_file);
if (audio_dst_file)
fclose(audio_dst_file);
av_free(frame);
av_free(video_dst_data[0]);
av_free(audio_dst_data);
return 0;
}
The trouble you are facing is because udp is not a multimedia format. It is a network protocol. Ffmpeg converts to multimedia formats and can dump output to various locations such as disk (the most common case) or in this case on the network. So you must decide what format you want your content to be transmuxed to before you send it out over udp. From the command line this would be done using the -f format flag. Streamable formats are transport stream, webm in containers and elementary streams. You may want to use rtp for streaming over udp else on the reciever side you will face problems of missing packets and out of order arrival.
Given your current state, I suggest first you achieve what you want to do via the command line itself. This will give you an understanding of what are the various things you must do. Then you can go to the program.

Categories

Resources