FFmpeg  4.3.1
transcode_aac.c

Convert an input audio file to AAC in an MP4 container using FFmpeg.Formats other than MP4 are supported based on the output file extension.

Author
Andreas Unterweger (dusts.nosp@m.igns.nosp@m.@gmai.nosp@m.l.co.nosp@m.m)
/*
* Copyright (c) 2013-2018 Andreas Unterweger
*
* 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
*/
/**
* @file
* Simple audio converter
*
* @example transcode_aac.c
* Convert an input audio file to AAC in an MP4 container using FFmpeg.
* Formats other than MP4 are supported based on the output file extension.
* @author Andreas Unterweger (dustsigns@gmail.com)
*/
#include <stdio.h>
#include "libavutil/opt.h"
/* The output bit rate in bit/s */
#define OUTPUT_BIT_RATE 96000
/* The number of output channels */
#define OUTPUT_CHANNELS 2
/**
* Open an input file and the required decoder.
* @param filename File to be opened
* @param[out] input_format_context Format context of opened file
* @param[out] input_codec_context Codec context of opened file
* @return Error code (0 if successful)
*/
static int open_input_file(const char *filename,
AVFormatContext **input_format_context,
AVCodecContext **input_codec_context)
{
AVCodec *input_codec;
int error;
/* Open the input file to read from it. */
if ((error = avformat_open_input(input_format_context, filename, NULL,
NULL)) < 0) {
fprintf(stderr, "Could not open input file '%s' (error '%s')\n",
filename, av_err2str(error));
*input_format_context = NULL;
return error;
}
/* Get information on the input file (number of streams etc.). */
if ((error = avformat_find_stream_info(*input_format_context, NULL)) < 0) {
fprintf(stderr, "Could not open find stream info (error '%s')\n",
av_err2str(error));
avformat_close_input(input_format_context);
return error;
}
/* Make sure that there is only one stream in the input file. */
if ((*input_format_context)->nb_streams != 1) {
fprintf(stderr, "Expected one audio input stream, but found %d\n",
(*input_format_context)->nb_streams);
avformat_close_input(input_format_context);
return AVERROR_EXIT;
}
/* Find a decoder for the audio stream. */
if (!(input_codec = avcodec_find_decoder((*input_format_context)->streams[0]->codecpar->codec_id))) {
fprintf(stderr, "Could not find input codec\n");
avformat_close_input(input_format_context);
return AVERROR_EXIT;
}
/* Allocate a new decoding context. */
avctx = avcodec_alloc_context3(input_codec);
if (!avctx) {
fprintf(stderr, "Could not allocate a decoding context\n");
avformat_close_input(input_format_context);
return AVERROR(ENOMEM);
}
/* Initialize the stream parameters with demuxer information. */
error = avcodec_parameters_to_context(avctx, (*input_format_context)->streams[0]->codecpar);
if (error < 0) {
avformat_close_input(input_format_context);
return error;
}
/* Open the decoder for the audio stream to use it later. */
if ((error = avcodec_open2(avctx, input_codec, NULL)) < 0) {
fprintf(stderr, "Could not open input codec (error '%s')\n",
av_err2str(error));
avformat_close_input(input_format_context);
return error;
}
/* Save the decoder context for easier access later. */
*input_codec_context = avctx;
return 0;
}
/**
* Open an output file and the required encoder.
* Also set some basic encoder parameters.
* Some of these parameters are based on the input file's parameters.
* @param filename File to be opened
* @param input_codec_context Codec context of input file
* @param[out] output_format_context Format context of output file
* @param[out] output_codec_context Codec context of output file
* @return Error code (0 if successful)
*/
static int open_output_file(const char *filename,
AVCodecContext *input_codec_context,
AVFormatContext **output_format_context,
AVCodecContext **output_codec_context)
{
AVCodecContext *avctx = NULL;
AVIOContext *output_io_context = NULL;
AVStream *stream = NULL;
AVCodec *output_codec = NULL;
int error;
/* Open the output file to write to it. */
if ((error = avio_open(&output_io_context, filename,
AVIO_FLAG_WRITE)) < 0) {
fprintf(stderr, "Could not open output file '%s' (error '%s')\n",
filename, av_err2str(error));
return error;
}
/* Create a new format context for the output container format. */
if (!(*output_format_context = avformat_alloc_context())) {
fprintf(stderr, "Could not allocate output format context\n");
return AVERROR(ENOMEM);
}
/* Associate the output file (pointer) with the container format context. */
(*output_format_context)->pb = output_io_context;
/* Guess the desired container format based on the file extension. */
if (!((*output_format_context)->oformat = av_guess_format(NULL, filename,
NULL))) {
fprintf(stderr, "Could not find output file format\n");
goto cleanup;
}
if (!((*output_format_context)->url = av_strdup(filename))) {
fprintf(stderr, "Could not allocate url.\n");
error = AVERROR(ENOMEM);
goto cleanup;
}
/* Find the encoder to be used by its name. */
if (!(output_codec = avcodec_find_encoder(AV_CODEC_ID_AAC))) {
fprintf(stderr, "Could not find an AAC encoder.\n");
goto cleanup;
}
/* Create a new audio stream in the output file container. */
if (!(stream = avformat_new_stream(*output_format_context, NULL))) {
fprintf(stderr, "Could not create new stream\n");
error = AVERROR(ENOMEM);
goto cleanup;
}
avctx = avcodec_alloc_context3(output_codec);
if (!avctx) {
fprintf(stderr, "Could not allocate an encoding context\n");
error = AVERROR(ENOMEM);
goto cleanup;
}
/* Set the basic encoder parameters.
* The input file's sample rate is used to avoid a sample rate conversion. */
avctx->sample_rate = input_codec_context->sample_rate;
avctx->sample_fmt = output_codec->sample_fmts[0];
/* Allow the use of the experimental AAC encoder. */
/* Set the sample rate for the container. */
stream->time_base.den = input_codec_context->sample_rate;
stream->time_base.num = 1;
/* Some container formats (like MP4) require global headers to be present.
* Mark the encoder so that it behaves accordingly. */
if ((*output_format_context)->oformat->flags & AVFMT_GLOBALHEADER)
/* Open the encoder for the audio stream to use it later. */
if ((error = avcodec_open2(avctx, output_codec, NULL)) < 0) {
fprintf(stderr, "Could not open output codec (error '%s')\n",
av_err2str(error));
goto cleanup;
}
error = avcodec_parameters_from_context(stream->codecpar, avctx);
if (error < 0) {
fprintf(stderr, "Could not initialize stream parameters\n");
goto cleanup;
}
/* Save the encoder context for easier access later. */
*output_codec_context = avctx;
return 0;
cleanup:
avio_closep(&(*output_format_context)->pb);
avformat_free_context(*output_format_context);
*output_format_context = NULL;
return error < 0 ? error : AVERROR_EXIT;
}
/**
* Initialize one data packet for reading or writing.
* @param packet Packet to be initialized
*/
static void init_packet(AVPacket *packet)
{
av_init_packet(packet);
/* Set the packet data and size so that it is recognized as being empty. */
packet->data = NULL;
packet->size = 0;
}
/**
* Initialize one audio frame for reading from the input file.
* @param[out] frame Frame to be initialized
* @return Error code (0 if successful)
*/
{
if (!(*frame = av_frame_alloc())) {
fprintf(stderr, "Could not allocate input frame\n");
return AVERROR(ENOMEM);
}
return 0;
}
/**
* Initialize the audio resampler based on the input and output codec settings.
* If the input and output sample formats differ, a conversion is required
* libswresample takes care of this, but requires initialization.
* @param input_codec_context Codec context of the input file
* @param output_codec_context Codec context of the output file
* @param[out] resample_context Resample context for the required conversion
* @return Error code (0 if successful)
*/
static int init_resampler(AVCodecContext *input_codec_context,
AVCodecContext *output_codec_context,
SwrContext **resample_context)
{
int error;
/*
* Create a resampler context for the conversion.
* Set the conversion parameters.
* Default channel layouts based on the number of channels
* are assumed for simplicity (they are sometimes not detected
* properly by the demuxer and/or decoder).
*/
*resample_context = swr_alloc_set_opts(NULL,
av_get_default_channel_layout(output_codec_context->channels),
output_codec_context->sample_fmt,
output_codec_context->sample_rate,
av_get_default_channel_layout(input_codec_context->channels),
input_codec_context->sample_fmt,
input_codec_context->sample_rate,
0, NULL);
if (!*resample_context) {
fprintf(stderr, "Could not allocate resample context\n");
return AVERROR(ENOMEM);
}
/*
* Perform a sanity check so that the number of converted samples is
* not greater than the number of samples to be converted.
* If the sample rates differ, this case has to be handled differently
*/
av_assert0(output_codec_context->sample_rate == input_codec_context->sample_rate);
/* Open the resampler with the specified parameters. */
if ((error = swr_init(*resample_context)) < 0) {
fprintf(stderr, "Could not open resample context\n");
swr_free(resample_context);
return error;
}
return 0;
}
/**
* Initialize a FIFO buffer for the audio samples to be encoded.
* @param[out] fifo Sample buffer
* @param output_codec_context Codec context of the output file
* @return Error code (0 if successful)
*/
static int init_fifo(AVAudioFifo **fifo, AVCodecContext *output_codec_context)
{
/* Create the FIFO buffer based on the specified output sample format. */
if (!(*fifo = av_audio_fifo_alloc(output_codec_context->sample_fmt,
output_codec_context->channels, 1))) {
fprintf(stderr, "Could not allocate FIFO\n");
return AVERROR(ENOMEM);
}
return 0;
}
/**
* Write the header of the output file container.
* @param output_format_context Format context of the output file
* @return Error code (0 if successful)
*/
static int write_output_file_header(AVFormatContext *output_format_context)
{
int error;
if ((error = avformat_write_header(output_format_context, NULL)) < 0) {
fprintf(stderr, "Could not write output file header (error '%s')\n",
av_err2str(error));
return error;
}
return 0;
}
/**
* Decode one audio frame from the input file.
* @param frame Audio frame to be decoded
* @param input_format_context Format context of the input file
* @param input_codec_context Codec context of the input file
* @param[out] data_present Indicates whether data has been decoded
* @param[out] finished Indicates whether the end of file has
* been reached and all data has been
* decoded. If this flag is false, there
* is more data to be decoded, i.e., this
* function has to be called again.
* @return Error code (0 if successful)
*/
AVFormatContext *input_format_context,
AVCodecContext *input_codec_context,
int *data_present, int *finished)
{
/* Packet used for temporary storage. */
AVPacket input_packet;
int error;
init_packet(&input_packet);
/* Read one audio frame from the input file into a temporary packet. */
if ((error = av_read_frame(input_format_context, &input_packet)) < 0) {
/* If we are at the end of the file, flush the decoder below. */
if (error == AVERROR_EOF)
*finished = 1;
else {
fprintf(stderr, "Could not read frame (error '%s')\n",
av_err2str(error));
return error;
}
}
/* Send the audio frame stored in the temporary packet to the decoder.
* The input audio stream decoder is used to do this. */
if ((error = avcodec_send_packet(input_codec_context, &input_packet)) < 0) {
fprintf(stderr, "Could not send packet for decoding (error '%s')\n",
av_err2str(error));
return error;
}
/* Receive one frame from the decoder. */
error = avcodec_receive_frame(input_codec_context, frame);
/* If the decoder asks for more data to be able to decode a frame,
* return indicating that no data is present. */
if (error == AVERROR(EAGAIN)) {
error = 0;
goto cleanup;
/* If the end of the input file is reached, stop decoding. */
} else if (error == AVERROR_EOF) {
*finished = 1;
error = 0;
goto cleanup;
} else if (error < 0) {
fprintf(stderr, "Could not decode frame (error '%s')\n",
av_err2str(error));
goto cleanup;
/* Default case: Return decoded data. */
} else {
*data_present = 1;
goto cleanup;
}
cleanup:
av_packet_unref(&input_packet);
return error;
}
/**
* Initialize a temporary storage for the specified number of audio samples.
* The conversion requires temporary storage due to the different format.
* The number of audio samples to be allocated is specified in frame_size.
* @param[out] converted_input_samples Array of converted samples. The
* dimensions are reference, channel
* (for multi-channel audio), sample.
* @param output_codec_context Codec context of the output file
* @param frame_size Number of samples to be converted in
* each round
* @return Error code (0 if successful)
*/
static int init_converted_samples(uint8_t ***converted_input_samples,
AVCodecContext *output_codec_context,
int frame_size)
{
int error;
/* Allocate as many pointers as there are audio channels.
* Each pointer will later point to the audio samples of the corresponding
* channels (although it may be NULL for interleaved formats).
*/
if (!(*converted_input_samples = calloc(output_codec_context->channels,
sizeof(**converted_input_samples)))) {
fprintf(stderr, "Could not allocate converted input sample pointers\n");
return AVERROR(ENOMEM);
}
/* Allocate memory for the samples of all channels in one consecutive
* block for convenience. */
if ((error = av_samples_alloc(*converted_input_samples, NULL,
output_codec_context->channels,
frame_size,
output_codec_context->sample_fmt, 0)) < 0) {
fprintf(stderr,
"Could not allocate converted input samples (error '%s')\n",
av_err2str(error));
av_freep(&(*converted_input_samples)[0]);
free(*converted_input_samples);
return error;
}
return 0;
}
/**
* Convert the input audio samples into the output sample format.
* The conversion happens on a per-frame basis, the size of which is
* specified by frame_size.
* @param input_data Samples to be decoded. The dimensions are
* channel (for multi-channel audio), sample.
* @param[out] converted_data Converted samples. The dimensions are channel
* (for multi-channel audio), sample.
* @param frame_size Number of samples to be converted
* @param resample_context Resample context for the conversion
* @return Error code (0 if successful)
*/
static int convert_samples(const uint8_t **input_data,
uint8_t **converted_data, const int frame_size,
SwrContext *resample_context)
{
int error;
/* Convert the samples using the resampler. */
if ((error = swr_convert(resample_context,
converted_data, frame_size,
input_data , frame_size)) < 0) {
fprintf(stderr, "Could not convert input samples (error '%s')\n",
av_err2str(error));
return error;
}
return 0;
}
/**
* Add converted input audio samples to the FIFO buffer for later processing.
* @param fifo Buffer to add the samples to
* @param converted_input_samples Samples to be added. The dimensions are channel
* (for multi-channel audio), sample.
* @param frame_size Number of samples to be converted
* @return Error code (0 if successful)
*/
uint8_t **converted_input_samples,
const int frame_size)
{
int error;
/* Make the FIFO as large as it needs to be to hold both,
* the old and the new samples. */
if ((error = av_audio_fifo_realloc(fifo, av_audio_fifo_size(fifo) + frame_size)) < 0) {
fprintf(stderr, "Could not reallocate FIFO\n");
return error;
}
/* Store the new samples in the FIFO buffer. */
if (av_audio_fifo_write(fifo, (void **)converted_input_samples,
frame_size) < frame_size) {
fprintf(stderr, "Could not write data to FIFO\n");
return AVERROR_EXIT;
}
return 0;
}
/**
* Read one audio frame from the input file, decode, convert and store
* it in the FIFO buffer.
* @param fifo Buffer used for temporary storage
* @param input_format_context Format context of the input file
* @param input_codec_context Codec context of the input file
* @param output_codec_context Codec context of the output file
* @param resampler_context Resample context for the conversion
* @param[out] finished Indicates whether the end of file has
* been reached and all data has been
* decoded. If this flag is false,
* there is more data to be decoded,
* i.e., this function has to be called
* again.
* @return Error code (0 if successful)
*/
AVFormatContext *input_format_context,
AVCodecContext *input_codec_context,
AVCodecContext *output_codec_context,
SwrContext *resampler_context,
int *finished)
{
/* Temporary storage of the input samples of the frame read from the file. */
AVFrame *input_frame = NULL;
/* Temporary storage for the converted input samples. */
uint8_t **converted_input_samples = NULL;
int data_present = 0;
int ret = AVERROR_EXIT;
/* Initialize temporary storage for one input frame. */
if (init_input_frame(&input_frame))
goto cleanup;
/* Decode one frame worth of audio samples. */
if (decode_audio_frame(input_frame, input_format_context,
input_codec_context, &data_present, finished))
goto cleanup;
/* If we are at the end of the file and there are no more samples
* in the decoder which are delayed, we are actually finished.
* This must not be treated as an error. */
if (*finished) {
ret = 0;
goto cleanup;
}
/* If there is decoded data, convert and store it. */
if (data_present) {
/* Initialize the temporary storage for the converted input samples. */
if (init_converted_samples(&converted_input_samples, output_codec_context,
input_frame->nb_samples))
goto cleanup;
/* Convert the input samples to the desired output sample format.
* This requires a temporary storage provided by converted_input_samples. */
if (convert_samples((const uint8_t**)input_frame->extended_data, converted_input_samples,
input_frame->nb_samples, resampler_context))
goto cleanup;
/* Add the converted input samples to the FIFO buffer for later processing. */
if (add_samples_to_fifo(fifo, converted_input_samples,
input_frame->nb_samples))
goto cleanup;
ret = 0;
}
ret = 0;
cleanup:
if (converted_input_samples) {
av_freep(&converted_input_samples[0]);
free(converted_input_samples);
}
av_frame_free(&input_frame);
return ret;
}
/**
* Initialize one input frame for writing to the output file.
* The frame will be exactly frame_size samples large.
* @param[out] frame Frame to be initialized
* @param output_codec_context Codec context of the output file
* @param frame_size Size of the frame
* @return Error code (0 if successful)
*/
AVCodecContext *output_codec_context,
int frame_size)
{
int error;
/* Create a new frame to store the audio samples. */
if (!(*frame = av_frame_alloc())) {
fprintf(stderr, "Could not allocate output frame\n");
return AVERROR_EXIT;
}
/* Set the frame's parameters, especially its size and format.
* av_frame_get_buffer needs this to allocate memory for the
* audio samples of the frame.
* Default channel layouts based on the number of channels
* are assumed for simplicity. */
(*frame)->nb_samples = frame_size;
(*frame)->channel_layout = output_codec_context->channel_layout;
(*frame)->format = output_codec_context->sample_fmt;
(*frame)->sample_rate = output_codec_context->sample_rate;
/* Allocate the samples of the created frame. This call will make
* sure that the audio frame can hold as many samples as specified. */
if ((error = av_frame_get_buffer(*frame, 0)) < 0) {
fprintf(stderr, "Could not allocate output frame samples (error '%s')\n",
av_err2str(error));
return error;
}
return 0;
}
/* Global timestamp for the audio frames. */
static int64_t pts = 0;
/**
* Encode one frame worth of audio to the output file.
* @param frame Samples to be encoded
* @param output_format_context Format context of the output file
* @param output_codec_context Codec context of the output file
* @param[out] data_present Indicates whether data has been
* encoded
* @return Error code (0 if successful)
*/
AVFormatContext *output_format_context,
AVCodecContext *output_codec_context,
int *data_present)
{
/* Packet used for temporary storage. */
AVPacket output_packet;
int error;
init_packet(&output_packet);
/* Set a timestamp based on the sample rate for the container. */
if (frame) {
}
/* Send the audio frame stored in the temporary packet to the encoder.
* The output audio stream encoder is used to do this. */
error = avcodec_send_frame(output_codec_context, frame);
/* The encoder signals that it has nothing more to encode. */
if (error == AVERROR_EOF) {
error = 0;
goto cleanup;
} else if (error < 0) {
fprintf(stderr, "Could not send packet for encoding (error '%s')\n",
av_err2str(error));
return error;
}
/* Receive one encoded frame from the encoder. */
error = avcodec_receive_packet(output_codec_context, &output_packet);
/* If the encoder asks for more data to be able to provide an
* encoded frame, return indicating that no data is present. */
if (error == AVERROR(EAGAIN)) {
error = 0;
goto cleanup;
/* If the last frame has been encoded, stop encoding. */
} else if (error == AVERROR_EOF) {
error = 0;
goto cleanup;
} else if (error < 0) {
fprintf(stderr, "Could not encode frame (error '%s')\n",
av_err2str(error));
goto cleanup;
/* Default case: Return encoded data. */
} else {
*data_present = 1;
}
/* Write one audio frame from the temporary packet to the output file. */
if (*data_present &&
(error = av_write_frame(output_format_context, &output_packet)) < 0) {
fprintf(stderr, "Could not write frame (error '%s')\n",
av_err2str(error));
goto cleanup;
}
cleanup:
av_packet_unref(&output_packet);
return error;
}
/**
* Load one audio frame from the FIFO buffer, encode and write it to the
* output file.
* @param fifo Buffer used for temporary storage
* @param output_format_context Format context of the output file
* @param output_codec_context Codec context of the output file
* @return Error code (0 if successful)
*/
AVFormatContext *output_format_context,
AVCodecContext *output_codec_context)
{
/* Temporary storage of the output samples of the frame written to the file. */
AVFrame *output_frame;
/* Use the maximum number of possible samples per frame.
* If there is less than the maximum possible frame size in the FIFO
* buffer use this number. Otherwise, use the maximum possible frame size. */
const int frame_size = FFMIN(av_audio_fifo_size(fifo),
output_codec_context->frame_size);
int data_written;
/* Initialize temporary storage for one output frame. */
if (init_output_frame(&output_frame, output_codec_context, frame_size))
return AVERROR_EXIT;
/* Read as many samples from the FIFO buffer as required to fill the frame.
* The samples are stored in the frame temporarily. */
if (av_audio_fifo_read(fifo, (void **)output_frame->data, frame_size) < frame_size) {
fprintf(stderr, "Could not read data from FIFO\n");
av_frame_free(&output_frame);
return AVERROR_EXIT;
}
/* Encode one frame worth of audio samples. */
if (encode_audio_frame(output_frame, output_format_context,
output_codec_context, &data_written)) {
av_frame_free(&output_frame);
return AVERROR_EXIT;
}
av_frame_free(&output_frame);
return 0;
}
/**
* Write the trailer of the output file container.
* @param output_format_context Format context of the output file
* @return Error code (0 if successful)
*/
static int write_output_file_trailer(AVFormatContext *output_format_context)
{
int error;
if ((error = av_write_trailer(output_format_context)) < 0) {
fprintf(stderr, "Could not write output file trailer (error '%s')\n",
av_err2str(error));
return error;
}
return 0;
}
int main(int argc, char **argv)
{
AVFormatContext *input_format_context = NULL, *output_format_context = NULL;
AVCodecContext *input_codec_context = NULL, *output_codec_context = NULL;
SwrContext *resample_context = NULL;
AVAudioFifo *fifo = NULL;
int ret = AVERROR_EXIT;
if (argc != 3) {
fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]);
exit(1);
}
/* Open the input file for reading. */
if (open_input_file(argv[1], &input_format_context,
&input_codec_context))
goto cleanup;
/* Open the output file for writing. */
if (open_output_file(argv[2], input_codec_context,
&output_format_context, &output_codec_context))
goto cleanup;
/* Initialize the resampler to be able to convert audio sample formats. */
if (init_resampler(input_codec_context, output_codec_context,
&resample_context))
goto cleanup;
/* Initialize the FIFO buffer to store audio samples to be encoded. */
if (init_fifo(&fifo, output_codec_context))
goto cleanup;
/* Write the header of the output file container. */
if (write_output_file_header(output_format_context))
goto cleanup;
/* Loop as long as we have input samples to read or output samples
* to write; abort as soon as we have neither. */
while (1) {
/* Use the encoder's desired frame size for processing. */
const int output_frame_size = output_codec_context->frame_size;
int finished = 0;
/* Make sure that there is one frame worth of samples in the FIFO
* buffer so that the encoder can do its work.
* Since the decoder's and the encoder's frame size may differ, we
* need to FIFO buffer to store as many frames worth of input samples
* that they make up at least one frame worth of output samples. */
while (av_audio_fifo_size(fifo) < output_frame_size) {
/* Decode one frame worth of audio samples, convert it to the
* output sample format and put it into the FIFO buffer. */
if (read_decode_convert_and_store(fifo, input_format_context,
input_codec_context,
output_codec_context,
resample_context, &finished))
goto cleanup;
/* If we are at the end of the input file, we continue
* encoding the remaining audio samples to the output file. */
if (finished)
break;
}
/* If we have enough samples for the encoder, we encode them.
* At the end of the file, we pass the remaining samples to
* the encoder. */
while (av_audio_fifo_size(fifo) >= output_frame_size ||
(finished && av_audio_fifo_size(fifo) > 0))
/* Take one frame worth of audio samples from the FIFO buffer,
* encode it and write it to the output file. */
if (load_encode_and_write(fifo, output_format_context,
output_codec_context))
goto cleanup;
/* If we are at the end of the input file and have encoded
* all remaining samples, we can exit this loop and finish. */
if (finished) {
int data_written;
/* Flush the encoder as it may have delayed frames. */
do {
data_written = 0;
if (encode_audio_frame(NULL, output_format_context,
output_codec_context, &data_written))
goto cleanup;
} while (data_written);
break;
}
}
/* Write the trailer of the output file container. */
if (write_output_file_trailer(output_format_context))
goto cleanup;
ret = 0;
cleanup:
if (fifo)
swr_free(&resample_context);
if (output_codec_context)
avcodec_free_context(&output_codec_context);
if (output_format_context) {
avio_closep(&output_format_context->pb);
avformat_free_context(output_format_context);
}
if (input_codec_context)
avcodec_free_context(&input_codec_context);
if (input_format_context)
avformat_close_input(&input_format_context);
return ret;
}
Audio FIFO Buffer.
simple assert() macros that are a bit more flexible than ISO C assert().
#define av_assert0(cond)
assert() equivalent, that is always enabled.
Definition: avassert.h:37
Libavcodec external API header.
#define FF_COMPLIANCE_EXPERIMENTAL
Allow nonstandardized experimental things.
Definition: avcodec.h:1594
Main libavformat public API header.
#define AVFMT_GLOBALHEADER
Format wants global header.
Definition: avformat.h:461
Buffered I/O operations.
int avio_open(AVIOContext **s, const char *url, int flags)
Create and initialize a AVIOContext for accessing the resource indicated by url.
#define AVIO_FLAG_WRITE
write-only
Definition: avio.h:675
int avio_closep(AVIOContext **s)
Close the resource accessed by the AVIOContext *s, free it and set the pointer pointing to it to NULL...
#define FFMIN(a, b)
Definition: common.h:96
static AVFrame * frame
reference-counted frame API
int64_t av_get_default_channel_layout(int nb_channels)
Return default channel layout for a given number of channels.
int avcodec_parameters_from_context(AVCodecParameters *par, const AVCodecContext *codec)
Fill the parameters struct based on the values from the supplied codec context.
int avcodec_open2(AVCodecContext *avctx, const AVCodec *codec, AVDictionary **options)
Initialize the AVCodecContext to use the given AVCodec.
AVCodec * avcodec_find_decoder(enum AVCodecID id)
Find a registered decoder with a matching codec ID.
#define AV_CODEC_FLAG_GLOBAL_HEADER
Place global headers in extradata instead of every keyframe.
Definition: avcodec.h:329
AVCodec * avcodec_find_encoder(enum AVCodecID id)
Find a registered encoder with a matching codec ID.
int avcodec_parameters_to_context(AVCodecContext *codec, const AVCodecParameters *par)
Fill the codec context based on the values from the supplied codec parameters.
AVCodecContext * avcodec_alloc_context3(const AVCodec *codec)
Allocate an AVCodecContext and set its fields to default values.
void avcodec_free_context(AVCodecContext **avctx)
Free the codec context and everything associated with it and write NULL to the provided pointer.
@ AV_CODEC_ID_AAC
Definition: codec_id.h:412
int avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame)
Return decoded output data from a decoder.
int avcodec_send_packet(AVCodecContext *avctx, const AVPacket *avpkt)
Supply raw packet data as input to a decoder.
int avcodec_receive_packet(AVCodecContext *avctx, AVPacket *avpkt)
Read encoded data from the encoder.
int avcodec_send_frame(AVCodecContext *avctx, const AVFrame *frame)
Supply a raw video or audio frame to the encoder.
void av_packet_unref(AVPacket *pkt)
Wipe the packet.
void av_init_packet(AVPacket *pkt)
Initialize optional fields of a packet with default values.
void avformat_free_context(AVFormatContext *s)
Free an AVFormatContext and all its streams.
AVFormatContext * avformat_alloc_context(void)
Allocate an AVFormatContext.
AVStream * avformat_new_stream(AVFormatContext *s, const AVCodec *c)
Add a new stream to a media file.
int av_read_frame(AVFormatContext *s, AVPacket *pkt)
Return the next frame of a stream.
int avformat_find_stream_info(AVFormatContext *ic, AVDictionary **options)
Read packets of a media file to get stream information.
void avformat_close_input(AVFormatContext **s)
Close an opened input AVFormatContext.
int avformat_open_input(AVFormatContext **ps, const char *url, ff_const59 AVInputFormat *fmt, AVDictionary **options)
Open an input stream and read the header.
av_warn_unused_result int avformat_write_header(AVFormatContext *s, AVDictionary **options)
Allocate the stream private data and write the stream header to an output media file.
ff_const59 AVOutputFormat * av_guess_format(const char *short_name, const char *filename, const char *mime_type)
Return the output format in the list of registered output formats which best matches the provided par...
int av_write_trailer(AVFormatContext *s)
Write the stream trailer to an output media file and free the file private data.
int av_write_frame(AVFormatContext *s, AVPacket *pkt)
Write a packet to an output media file.
int av_audio_fifo_write(AVAudioFifo *af, void **data, int nb_samples)
Write data to an AVAudioFifo.
av_warn_unused_result int av_audio_fifo_realloc(AVAudioFifo *af, int nb_samples)
Reallocate an AVAudioFifo.
struct AVAudioFifo AVAudioFifo
Context for an Audio FIFO Buffer.
Definition: audio_fifo.h:49
void av_audio_fifo_free(AVAudioFifo *af)
Free an AVAudioFifo.
AVAudioFifo * av_audio_fifo_alloc(enum AVSampleFormat sample_fmt, int channels, int nb_samples)
Allocate an AVAudioFifo.
int av_audio_fifo_size(AVAudioFifo *af)
Get the current number of samples in the AVAudioFifo available for reading.
int av_audio_fifo_read(AVAudioFifo *af, void **data, int nb_samples)
Read data from an AVAudioFifo.
#define AVERROR_EXIT
Immediate exit was requested; the called function should not be restarted.
Definition: error.h:56
#define AVERROR_EOF
End of file.
Definition: error.h:55
#define av_err2str(errnum)
Convenience macro, the return value should be used only directly in function arguments but never stan...
Definition: error.h:119
#define AVERROR(e)
Definition: error.h:43
int av_frame_get_buffer(AVFrame *frame, int align)
Allocate new buffer(s) for audio or video data.
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
AVFrame * av_frame_alloc(void)
Allocate an AVFrame and set its fields to default values.
void av_freep(void *ptr)
Free a memory block which has been allocated with a function of av_malloc() or av_realloc() family,...
char * av_strdup(const char *s) av_malloc_attrib
Duplicate a string.
int av_samples_alloc(uint8_t **audio_data, int *linesize, int nb_channels, int nb_samples, enum AVSampleFormat sample_fmt, int align)
Allocate a samples buffer for nb_samples samples, and fill data pointers and linesize accordingly.
struct SwrContext SwrContext
The libswresample context.
Definition: swresample.h:182
void swr_free(struct SwrContext **s)
Free the given SwrContext and set the pointer to NULL.
int swr_convert(struct SwrContext *s, uint8_t **out, int out_count, const uint8_t **in, int in_count)
Convert audio.
struct SwrContext * swr_alloc_set_opts(struct SwrContext *s, int64_t out_ch_layout, enum AVSampleFormat out_sample_fmt, int out_sample_rate, int64_t in_ch_layout, enum AVSampleFormat in_sample_fmt, int in_sample_rate, int log_offset, void *log_ctx)
Allocate SwrContext if needed and set/reset common parameters.
int swr_init(struct SwrContext *s)
Initialize context after user parameters have been set.
AVOptions.
main external API structure.
Definition: avcodec.h:526
enum AVSampleFormat sample_fmt
audio sample format
Definition: avcodec.h:1194
int strict_std_compliance
strictly follow the standard (MPEG-4, ...).
Definition: avcodec.h:1589
int64_t bit_rate
the average bitrate
Definition: avcodec.h:576
int sample_rate
samples per second
Definition: avcodec.h:1186
int flags
AV_CODEC_FLAG_*.
Definition: avcodec.h:606
int channels
number of audio channels
Definition: avcodec.h:1187
uint64_t channel_layout
Audio channel layout.
Definition: avcodec.h:1237
int frame_size
Number of samples per channel in an audio frame.
Definition: avcodec.h:1206
AVCodec.
Definition: codec.h:190
enum AVSampleFormat * sample_fmts
array of supported sample formats, or NULL if unknown, array is terminated by -1
Definition: codec.h:213
Format I/O context.
Definition: avformat.h:1335
This structure describes decoded (raw) audio or video data.
Definition: frame.h:300
int nb_samples
number of audio samples (per channel) described by this frame
Definition: frame.h:366
int64_t pts
Presentation timestamp in time_base units (time when frame should be shown to user).
Definition: frame.h:393
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:314
uint8_t ** extended_data
pointers to the data planes/channels.
Definition: frame.h:347
Bytestream IO Context.
Definition: avio.h:161
This structure stores compressed data.
Definition: packet.h:332
int size
Definition: packet.h:356
uint8_t * data
Definition: packet.h:355
int num
Numerator.
Definition: rational.h:59
int den
Denominator.
Definition: rational.h:60
Stream structure.
Definition: avformat.h:865
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:1012
AVRational time_base
This is the fundamental unit of time (in seconds) in terms of which frame timestamps are represented.
Definition: avformat.h:894
libswresample public header
static void init_packet(AVPacket *packet)
Initialize one data packet for reading or writing.
static int add_samples_to_fifo(AVAudioFifo *fifo, uint8_t **converted_input_samples, const int frame_size)
Add converted input audio samples to the FIFO buffer for later processing.
static int init_input_frame(AVFrame **frame)
Initialize one audio frame for reading from the input file.
int main(int argc, char **argv)
static int encode_audio_frame(AVFrame *frame, AVFormatContext *output_format_context, AVCodecContext *output_codec_context, int *data_present)
Encode one frame worth of audio to the output file.
#define OUTPUT_BIT_RATE
Definition: transcode_aac.c:47
#define OUTPUT_CHANNELS
Definition: transcode_aac.c:49
static int64_t pts
static int decode_audio_frame(AVFrame *frame, AVFormatContext *input_format_context, AVCodecContext *input_codec_context, int *data_present, int *finished)
Decode one audio frame from the input file.
static int open_output_file(const char *filename, AVCodecContext *input_codec_context, AVFormatContext **output_format_context, AVCodecContext **output_codec_context)
Open an output file and the required encoder.
static int init_resampler(AVCodecContext *input_codec_context, AVCodecContext *output_codec_context, SwrContext **resample_context)
Initialize the audio resampler based on the input and output codec settings.
static int write_output_file_header(AVFormatContext *output_format_context)
Write the header of the output file container.
static int init_output_frame(AVFrame **frame, AVCodecContext *output_codec_context, int frame_size)
Initialize one input frame for writing to the output file.
static int read_decode_convert_and_store(AVAudioFifo *fifo, AVFormatContext *input_format_context, AVCodecContext *input_codec_context, AVCodecContext *output_codec_context, SwrContext *resampler_context, int *finished)
Read one audio frame from the input file, decode, convert and store it in the FIFO buffer.
static int open_input_file(const char *filename, AVFormatContext **input_format_context, AVCodecContext **input_codec_context)
Open an input file and the required decoder.
Definition: transcode_aac.c:58
static int init_fifo(AVAudioFifo **fifo, AVCodecContext *output_codec_context)
Initialize a FIFO buffer for the audio samples to be encoded.
static int load_encode_and_write(AVAudioFifo *fifo, AVFormatContext *output_format_context, AVCodecContext *output_codec_context)
Load one audio frame from the FIFO buffer, encode and write it to the output file.
static int write_output_file_trailer(AVFormatContext *output_format_context)
Write the trailer of the output file container.
static int convert_samples(const uint8_t **input_data, uint8_t **converted_data, const int frame_size, SwrContext *resample_context)
Convert the input audio samples into the output sample format.
static int init_converted_samples(uint8_t ***converted_input_samples, AVCodecContext *output_codec_context, int frame_size)
Initialize a temporary storage for the specified number of audio samples.