Skip to content

F
ffmpeg.wasm-core
Commit b200a2c8 authored by Andreas Unterweger's avatar Andreas Unterweger Committed by Vittorio Giovara
Browse files
Options

examples: Fixed and extended Doxygen documentation 

Added parameter descriptions for all functions
 and converted in-function comments into regular
 (non-Doxygen) comments.
Signed-off-by: 's avatarVittorio Giovara <vittorio.giovara@gmail.com>
parent efddf2c0
Hide whitespace changes
Inline Side-by-side
Showing with 215 additions and 163 deletions
doc/examples/transcode_aac.c
View file @ b200a2c8
/* /*
* Copyright (c) 2013-2017 Andreas Unterweger
*
* This file is part of Libav. * This file is part of Libav.
* *
* Libav is free software; you can redistribute it and/or * Libav is free software; you can redistribute it and/or
...@@ -8,7 +10,7 @@ ...@@ -8,7 +10,7 @@
* *
* Libav is distributed in the hope that it will be useful, * Libav is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of * but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details. * Lesser General Public License for more details.
* *
* You should have received a copy of the GNU Lesser General Public * You should have received a copy of the GNU Lesser General Public
...@@ -18,10 +20,11 @@ ...@@ -18,10 +20,11 @@
/** /**
* @file * @file
* simple audio converter * Simple audio converter
* *
* @example transcode_aac.c * @example transcode_aac.c
* Convert an input audio file to AAC in an MP4 container using Libav. * Convert an input audio file to AAC in an MP4 container using Libav.
* Formats other than MP4 are supported based on the output file extension.
* @author Andreas Unterweger (dustsigns@gmail.com) * @author Andreas Unterweger (dustsigns@gmail.com)
*/ */
...@@ -39,9 +42,9 @@ ...@@ -39,9 +42,9 @@
#include "libavresample/avresample.h" #include "libavresample/avresample.h"
/** The output bit rate in kbit/s */ /* The output bit rate in bit/s */
#define OUTPUT_BIT_RATE 96000 #define OUTPUT_BIT_RATE 96000
/** The number of output channels */ /* The number of output channels */
#define OUTPUT_CHANNELS 2 #define OUTPUT_CHANNELS 2
/** /**
...@@ -56,7 +59,13 @@ static char *get_error_text(const int error) ...@@ -56,7 +59,13 @@ static char *get_error_text(const int error)
return error_buffer; return error_buffer;
} }
/** Open an input file and the required decoder. */ /**
* 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, static int open_input_file(const char *filename,
AVFormatContext **input_format_context, AVFormatContext **input_format_context,
AVCodecContext **input_codec_context) AVCodecContext **input_codec_context)
...@@ -65,7 +74,7 @@ static int open_input_file(const char *filename, ...@@ -65,7 +74,7 @@ static int open_input_file(const char *filename,
AVCodec *input_codec; AVCodec *input_codec;
int error; int error;
/** Open the input file to read from it. */ /* Open the input file to read from it. */
if ((error = avformat_open_input(input_format_context, filename, NULL, if ((error = avformat_open_input(input_format_context, filename, NULL,
NULL)) < 0) { NULL)) < 0) {
fprintf(stderr, "Could not open input file '%s' (error '%s')\n", fprintf(stderr, "Could not open input file '%s' (error '%s')\n",
...@@ -74,7 +83,7 @@ static int open_input_file(const char *filename, ...@@ -74,7 +83,7 @@ static int open_input_file(const char *filename,
return error; return error;
} }
/** Get information on the input file (number of streams etc.). */ /* Get information on the input file (number of streams etc.). */
if ((error = avformat_find_stream_info(*input_format_context, NULL)) < 0) { if ((error = avformat_find_stream_info(*input_format_context, NULL)) < 0) {
fprintf(stderr, "Could not open find stream info (error '%s')\n", fprintf(stderr, "Could not open find stream info (error '%s')\n",
get_error_text(error)); get_error_text(error));
...@@ -82,7 +91,7 @@ static int open_input_file(const char *filename, ...@@ -82,7 +91,7 @@ static int open_input_file(const char *filename,
return error; return error;
} }
/** Make sure that there is only one stream in the input file. */ /* Make sure that there is only one stream in the input file. */
if ((*input_format_context)->nb_streams != 1) { if ((*input_format_context)->nb_streams != 1) {
fprintf(stderr, "Expected one audio input stream, but found %d\n", fprintf(stderr, "Expected one audio input stream, but found %d\n",
(*input_format_context)->nb_streams); (*input_format_context)->nb_streams);
...@@ -90,14 +99,14 @@ static int open_input_file(const char *filename, ...@@ -90,14 +99,14 @@ static int open_input_file(const char *filename,
return AVERROR_EXIT; return AVERROR_EXIT;
} }
/** Find a decoder for the audio stream. */ /* Find a decoder for the audio stream. */
if (!(input_codec = avcodec_find_decoder((*input_format_context)->streams[0]->codecpar->codec_id))) { if (!(input_codec = avcodec_find_decoder((*input_format_context)->streams[0]->codecpar->codec_id))) {
fprintf(stderr, "Could not find input codec\n"); fprintf(stderr, "Could not find input codec\n");
avformat_close_input(input_format_context); avformat_close_input(input_format_context);
return AVERROR_EXIT; return AVERROR_EXIT;
} }
/** allocate a new decoding context */ /* Allocate a new decoding context. */
avctx = avcodec_alloc_context3(input_codec); avctx = avcodec_alloc_context3(input_codec);
if (!avctx) { if (!avctx) {
fprintf(stderr, "Could not allocate a decoding context\n"); fprintf(stderr, "Could not allocate a decoding context\n");
...@@ -105,7 +114,7 @@ static int open_input_file(const char *filename, ...@@ -105,7 +114,7 @@ static int open_input_file(const char *filename,
return AVERROR(ENOMEM); return AVERROR(ENOMEM);
} }
/** initialize the stream parameters with demuxer information */ /* Initialize the stream parameters with demuxer information. */
error = avcodec_parameters_to_context(avctx, (*input_format_context)->streams[0]->codecpar); error = avcodec_parameters_to_context(avctx, (*input_format_context)->streams[0]->codecpar);
if (error < 0) { if (error < 0) {
avformat_close_input(input_format_context); avformat_close_input(input_format_context);
...@@ -113,7 +122,7 @@ static int open_input_file(const char *filename, ...@@ -113,7 +122,7 @@ static int open_input_file(const char *filename,
return error; return error;
} }
/** Open the decoder for the audio stream to use it later. */ /* Open the decoder for the audio stream to use it later. */
if ((error = avcodec_open2(avctx, input_codec, NULL)) < 0) { if ((error = avcodec_open2(avctx, input_codec, NULL)) < 0) {
fprintf(stderr, "Could not open input codec (error '%s')\n", fprintf(stderr, "Could not open input codec (error '%s')\n",
get_error_text(error)); get_error_text(error));
...@@ -122,7 +131,7 @@ static int open_input_file(const char *filename, ...@@ -122,7 +131,7 @@ static int open_input_file(const char *filename,
return error; return error;
} }
/** Save the decoder context for easier access later. */ /* Save the decoder context for easier access later. */
*input_codec_context = avctx; *input_codec_context = avctx;
return 0; return 0;
...@@ -132,6 +141,11 @@ static int open_input_file(const char *filename, ...@@ -132,6 +141,11 @@ static int open_input_file(const char *filename,
* Open an output file and the required encoder. * Open an output file and the required encoder.
* Also set some basic encoder parameters. * Also set some basic encoder parameters.
* Some of these parameters are based on the input file's 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, static int open_output_file(const char *filename,
AVCodecContext *input_codec_context, AVCodecContext *input_codec_context,
...@@ -144,7 +158,7 @@ static int open_output_file(const char *filename, ...@@ -144,7 +158,7 @@ static int open_output_file(const char *filename,
AVCodec *output_codec = NULL; AVCodec *output_codec = NULL;
int error; int error;
/** Open the output file to write to it. */ /* Open the output file to write to it. */
if ((error = avio_open(&output_io_context, filename, if ((error = avio_open(&output_io_context, filename,
AVIO_FLAG_WRITE)) < 0) { AVIO_FLAG_WRITE)) < 0) {
fprintf(stderr, "Could not open output file '%s' (error '%s')\n", fprintf(stderr, "Could not open output file '%s' (error '%s')\n",
...@@ -152,16 +166,16 @@ static int open_output_file(const char *filename, ...@@ -152,16 +166,16 @@ static int open_output_file(const char *filename,
return error; return error;
} }
/** Create a new format context for the output container format. */ /* Create a new format context for the output container format. */
if (!(*output_format_context = avformat_alloc_context())) { if (!(*output_format_context = avformat_alloc_context())) {
fprintf(stderr, "Could not allocate output format context\n"); fprintf(stderr, "Could not allocate output format context\n");
return AVERROR(ENOMEM); return AVERROR(ENOMEM);
} }
/** Associate the output file (pointer) with the container format context. */ /* Associate the output file (pointer) with the container format context. */
(*output_format_context)->pb = output_io_context; (*output_format_context)->pb = output_io_context;
/** Guess the desired container format based on the file extension. */ /* Guess the desired container format based on the file extension. */
if (!((*output_format_context)->oformat = av_guess_format(NULL, filename, if (!((*output_format_context)->oformat = av_guess_format(NULL, filename,
NULL))) { NULL))) {
fprintf(stderr, "Could not find output file format\n"); fprintf(stderr, "Could not find output file format\n");
...@@ -171,13 +185,13 @@ static int open_output_file(const char *filename, ...@@ -171,13 +185,13 @@ static int open_output_file(const char *filename,
av_strlcpy((*output_format_context)->filename, filename, av_strlcpy((*output_format_context)->filename, filename,
sizeof((*output_format_context)->filename)); sizeof((*output_format_context)->filename));
/** Find the encoder to be used by its name. */ /* Find the encoder to be used by its name. */
if (!(output_codec = avcodec_find_encoder(AV_CODEC_ID_AAC))) { if (!(output_codec = avcodec_find_encoder(AV_CODEC_ID_AAC))) {
fprintf(stderr, "Could not find an AAC encoder.\n"); fprintf(stderr, "Could not find an AAC encoder.\n");
goto cleanup; goto cleanup;
} }
/** Create a new audio stream in the output file container. */ /* Create a new audio stream in the output file container. */
if (!(stream = avformat_new_stream(*output_format_context, NULL))) { if (!(stream = avformat_new_stream(*output_format_context, NULL))) {
fprintf(stderr, "Could not create new stream\n"); fprintf(stderr, "Could not create new stream\n");
error = AVERROR(ENOMEM); error = AVERROR(ENOMEM);
...@@ -191,31 +205,27 @@ static int open_output_file(const char *filename, ...@@ -191,31 +205,27 @@ static int open_output_file(const char *filename,
goto cleanup; goto cleanup;
} }
/** /* Set the basic encoder parameters.
* Set the basic encoder parameters. * The input file's sample rate is used to avoid a sample rate conversion. */
* The input file's sample rate is used to avoid a sample rate conversion.
*/
avctx->channels = OUTPUT_CHANNELS; avctx->channels = OUTPUT_CHANNELS;
avctx->channel_layout = av_get_default_channel_layout(OUTPUT_CHANNELS); avctx->channel_layout = av_get_default_channel_layout(OUTPUT_CHANNELS);
avctx->sample_rate = input_codec_context->sample_rate; avctx->sample_rate = input_codec_context->sample_rate;
avctx->sample_fmt = output_codec->sample_fmts[0]; avctx->sample_fmt = output_codec->sample_fmts[0];
avctx->bit_rate = OUTPUT_BIT_RATE; avctx->bit_rate = OUTPUT_BIT_RATE;
/** Allow the use of the experimental AAC encoder */ /* Allow the use of the experimental AAC encoder. */
avctx->strict_std_compliance = FF_COMPLIANCE_EXPERIMENTAL; avctx->strict_std_compliance = FF_COMPLIANCE_EXPERIMENTAL;
/** Set the sample rate for the container. */ /* Set the sample rate for the container. */
stream->time_base.den = input_codec_context->sample_rate; stream->time_base.den = input_codec_context->sample_rate;
stream->time_base.num = 1; stream->time_base.num = 1;
/** /* Some container formats (like MP4) require global headers to be present.
* Some container formats (like MP4) require global headers to be present * Mark the encoder so that it behaves accordingly. */
* Mark the encoder so that it behaves accordingly.
*/
if ((*output_format_context)->oformat->flags & AVFMT_GLOBALHEADER) if ((*output_format_context)->oformat->flags & AVFMT_GLOBALHEADER)
avctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER; avctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
/** Open the encoder for the audio stream to use it later. */ /* Open the encoder for the audio stream to use it later. */
if ((error = avcodec_open2(avctx, output_codec, NULL)) < 0) { if ((error = avcodec_open2(avctx, output_codec, NULL)) < 0) {
fprintf(stderr, "Could not open output codec (error '%s')\n", fprintf(stderr, "Could not open output codec (error '%s')\n",
get_error_text(error)); get_error_text(error));
...@@ -228,7 +238,7 @@ static int open_output_file(const char *filename, ...@@ -228,7 +238,7 @@ static int open_output_file(const char *filename,
goto cleanup; goto cleanup;
} }
/** Save the encoder context for easier access later. */ /* Save the encoder context for easier access later. */
*output_codec_context = avctx; *output_codec_context = avctx;
return 0; return 0;
...@@ -241,16 +251,23 @@ cleanup: ...@@ -241,16 +251,23 @@ cleanup:
return error < 0 ? error : AVERROR_EXIT; return error < 0 ? error : AVERROR_EXIT;
} }
/** Initialize one data packet for reading or writing. */ /**
* Initialize one data packet for reading or writing.
* @param packet Packet to be initialized
*/
static void init_packet(AVPacket *packet) static void init_packet(AVPacket *packet)
{ {
av_init_packet(packet); av_init_packet(packet);
/** Set the packet data and size so that it is recognized as being empty. */ /* Set the packet data and size so that it is recognized as being empty. */
packet->data = NULL; packet->data = NULL;
packet->size = 0; packet->size = 0;
} }
/** Initialize one audio frame for reading from the input file */ /**
* Initialize one audio frame for reading from the input file.
* @param[out] frame Frame to be initialized
* @return Error code (0 if successful)
*/
static int init_input_frame(AVFrame **frame) static int init_input_frame(AVFrame **frame)
{ {
if (!(*frame = av_frame_alloc())) { if (!(*frame = av_frame_alloc())) {
...@@ -264,27 +281,28 @@ static int init_input_frame(AVFrame **frame) ...@@ -264,27 +281,28 @@ static int init_input_frame(AVFrame **frame)
* Initialize the audio resampler based on the input and output codec settings. * Initialize the audio resampler based on the input and output codec settings.
* If the input and output sample formats differ, a conversion is required * If the input and output sample formats differ, a conversion is required
* libavresample takes care of this, but requires initialization. * libavresample 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, static int init_resampler(AVCodecContext *input_codec_context,
AVCodecContext *output_codec_context, AVCodecContext *output_codec_context,
AVAudioResampleContext **resample_context) AVAudioResampleContext **resample_context)
{ {
/** /* Only initialize the resampler if it is necessary, i.e.,
* Only initialize the resampler if it is necessary, i.e., * if and only if the sample formats differ. */
* if and only if the sample formats differ.
*/
if (input_codec_context->sample_fmt != output_codec_context->sample_fmt || if (input_codec_context->sample_fmt != output_codec_context->sample_fmt ||
input_codec_context->channels != output_codec_context->channels) { input_codec_context->channels != output_codec_context->channels) {
int error; int error;
/** Create a resampler context for the conversion. */ /* Create a resampler context for the conversion. */
if (!(*resample_context = avresample_alloc_context())) { if (!(*resample_context = avresample_alloc_context())) {
fprintf(stderr, "Could not allocate resample context\n"); fprintf(stderr, "Could not allocate resample context\n");
return AVERROR(ENOMEM); return AVERROR(ENOMEM);
} }
/** /* Set the conversion parameters.
* Set the conversion parameters.
* Default channel layouts based on the number of channels * Default channel layouts based on the number of channels
* are assumed for simplicity (they are sometimes not detected * are assumed for simplicity (they are sometimes not detected
* properly by the demuxer and/or decoder). * properly by the demuxer and/or decoder).
...@@ -302,7 +320,7 @@ static int init_resampler(AVCodecContext *input_codec_context, ...@@ -302,7 +320,7 @@ static int init_resampler(AVCodecContext *input_codec_context,
av_opt_set_int(*resample_context, "out_sample_fmt", av_opt_set_int(*resample_context, "out_sample_fmt",
output_codec_context->sample_fmt, 0); output_codec_context->sample_fmt, 0);
/** Open the resampler with the specified parameters. */ /* Open the resampler with the specified parameters. */
if ((error = avresample_open(*resample_context)) < 0) { if ((error = avresample_open(*resample_context)) < 0) {
fprintf(stderr, "Could not open resample context\n"); fprintf(stderr, "Could not open resample context\n");
avresample_free(resample_context); avresample_free(resample_context);
...@@ -312,10 +330,15 @@ static int init_resampler(AVCodecContext *input_codec_context, ...@@ -312,10 +330,15 @@ static int init_resampler(AVCodecContext *input_codec_context,
return 0; return 0;
} }
/** Initialize a FIFO buffer for the audio samples to be encoded. */ /**
* 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) static int init_fifo(AVAudioFifo **fifo, AVCodecContext *output_codec_context)
{ {
/** Create the FIFO buffer based on the specified output sample format. */ /* Create the FIFO buffer based on the specified output sample format. */
if (!(*fifo = av_audio_fifo_alloc(output_codec_context->sample_fmt, if (!(*fifo = av_audio_fifo_alloc(output_codec_context->sample_fmt,
output_codec_context->channels, 1))) { output_codec_context->channels, 1))) {
fprintf(stderr, "Could not allocate FIFO\n"); fprintf(stderr, "Could not allocate FIFO\n");
...@@ -324,7 +347,11 @@ static int init_fifo(AVAudioFifo **fifo, AVCodecContext *output_codec_context) ...@@ -324,7 +347,11 @@ static int init_fifo(AVAudioFifo **fifo, AVCodecContext *output_codec_context)
return 0; return 0;
} }
/** Write the header of the output file container. */ /**
* 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) static int write_output_file_header(AVFormatContext *output_format_context)
{ {
int error; int error;
...@@ -336,20 +363,32 @@ static int write_output_file_header(AVFormatContext *output_format_context) ...@@ -336,20 +363,32 @@ static int write_output_file_header(AVFormatContext *output_format_context)
return 0; return 0;
} }
/** Decode one audio frame from the input file. */ /**
* 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)
*/
static int decode_audio_frame(AVFrame *frame, static int decode_audio_frame(AVFrame *frame,
AVFormatContext *input_format_context, AVFormatContext *input_format_context,
AVCodecContext *input_codec_context, AVCodecContext *input_codec_context,
int *data_present, int *finished) int *data_present, int *finished)
{ {
/** Packet used for temporary storage. */ /* Packet used for temporary storage. */
AVPacket input_packet; AVPacket input_packet;
int error; int error;
init_packet(&input_packet); init_packet(&input_packet);
/** Read one audio frame from the input file into a temporary 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 ((error = av_read_frame(input_format_context, &input_packet)) < 0) {
/** If we are the the end of the file, flush the decoder below. */ /* If we are the the end of the file, flush the decoder below. */
if (error == AVERROR_EOF) if (error == AVERROR_EOF)
*finished = 1; *finished = 1;
else { else {
...@@ -359,12 +398,10 @@ static int decode_audio_frame(AVFrame *frame, ...@@ -359,12 +398,10 @@ static int decode_audio_frame(AVFrame *frame,
} }
} }
/** /* Decode the audio frame stored in the temporary packet.
* Decode the audio frame stored in the temporary packet.
* The input audio stream decoder is used to do this. * The input audio stream decoder is used to do this.
* If we are at the end of the file, pass an empty packet to the decoder * If we are at the end of the file, pass an empty packet to the decoder
* to flush it. * to flush it. */
*/
if ((error = avcodec_decode_audio4(input_codec_context, frame, if ((error = avcodec_decode_audio4(input_codec_context, frame,
data_present, &input_packet)) < 0) { data_present, &input_packet)) < 0) {
fprintf(stderr, "Could not decode frame (error '%s')\n", fprintf(stderr, "Could not decode frame (error '%s')\n",
...@@ -373,10 +410,8 @@ static int decode_audio_frame(AVFrame *frame, ...@@ -373,10 +410,8 @@ static int decode_audio_frame(AVFrame *frame,
return error; return error;
} }
/** /* If the decoder has not been flushed completely, we are not finished,
* If the decoder has not been flushed completely, we are not finished, * so that this function has to be called again. */
* so that this function has to be called again.
*/
if (*finished && *data_present) if (*finished && *data_present)
*finished = 0; *finished = 0;
av_packet_unref(&input_packet); av_packet_unref(&input_packet);
...@@ -387,6 +422,13 @@ static int decode_audio_frame(AVFrame *frame, ...@@ -387,6 +422,13 @@ static int decode_audio_frame(AVFrame *frame,
* Initialize a temporary storage for the specified number of audio samples. * Initialize a temporary storage for the specified number of audio samples.
* The conversion requires temporary storage due to the different format. * The conversion requires temporary storage due to the different format.
* The number of audio samples to be allocated is specified in frame_size. * 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, static int init_converted_samples(uint8_t ***converted_input_samples,
AVCodecContext *output_codec_context, AVCodecContext *output_codec_context,
...@@ -394,8 +436,7 @@ static int init_converted_samples(uint8_t ***converted_input_samples, ...@@ -394,8 +436,7 @@ static int init_converted_samples(uint8_t ***converted_input_samples,
{ {
int error; int error;
/** /* Allocate as many pointers as there are audio channels.
* Allocate as many pointers as there are audio channels.
* Each pointer will later point to the audio samples of the corresponding * Each pointer will later point to the audio samples of the corresponding
* channels (although it may be NULL for interleaved formats). * channels (although it may be NULL for interleaved formats).
*/ */
...@@ -405,10 +446,8 @@ static int init_converted_samples(uint8_t ***converted_input_samples, ...@@ -405,10 +446,8 @@ static int init_converted_samples(uint8_t ***converted_input_samples,
return AVERROR(ENOMEM); return AVERROR(ENOMEM);
} }
/** /* Allocate memory for the samples of all channels in one consecutive
* Allocate memory for the samples of all channels in one consecutive * block for convenience. */
* block for convenience.
*/
if ((error = av_samples_alloc(*converted_input_samples, NULL, if ((error = av_samples_alloc(*converted_input_samples, NULL,
output_codec_context->channels, output_codec_context->channels,
frame_size, frame_size,
...@@ -425,8 +464,15 @@ static int init_converted_samples(uint8_t ***converted_input_samples, ...@@ -425,8 +464,15 @@ static int init_converted_samples(uint8_t ***converted_input_samples,
/** /**
* Convert the input audio samples into the output sample format. * Convert the input audio samples into the output sample format.
* The conversion happens on a per-frame basis, the size of which is specified * The conversion happens on a per-frame basis, the size of which is
* by frame_size. * 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(uint8_t **input_data, static int convert_samples(uint8_t **input_data,
uint8_t **converted_data, const int frame_size, uint8_t **converted_data, const int frame_size,
...@@ -434,7 +480,7 @@ static int convert_samples(uint8_t **input_data, ...@@ -434,7 +480,7 @@ static int convert_samples(uint8_t **input_data,
{ {
int error; int error;
/** Convert the samples using the resampler. */ /* Convert the samples using the resampler. */
if ((error = avresample_convert(resample_context, converted_data, 0, if ((error = avresample_convert(resample_context, converted_data, 0,
frame_size, input_data, 0, frame_size)) < 0) { frame_size, input_data, 0, frame_size)) < 0) {
fprintf(stderr, "Could not convert input samples (error '%s')\n", fprintf(stderr, "Could not convert input samples (error '%s')\n",
...@@ -442,11 +488,9 @@ static int convert_samples(uint8_t **input_data, ...@@ -442,11 +488,9 @@ static int convert_samples(uint8_t **input_data,
return error; return error;
} }
/** /* Perform a sanity check so that the number of converted samples is
* Perform a sanity check so that the number of converted samples is
* not greater than the number of samples to be converted. * not greater than the number of samples to be converted.
* If the sample rates differ, this case has to be handled differently * If the sample rates differ, this case has to be handled differently. */
*/
if (avresample_available(resample_context)) { if (avresample_available(resample_context)) {
fprintf(stderr, "Converted samples left over\n"); fprintf(stderr, "Converted samples left over\n");
return AVERROR_EXIT; return AVERROR_EXIT;
...@@ -455,23 +499,28 @@ static int convert_samples(uint8_t **input_data, ...@@ -455,23 +499,28 @@ static int convert_samples(uint8_t **input_data,
return 0; return 0;
} }
/** Add converted input audio samples to the FIFO buffer for later processing. */ /**
* 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)
*/
static int add_samples_to_fifo(AVAudioFifo *fifo, static int add_samples_to_fifo(AVAudioFifo *fifo,
uint8_t **converted_input_samples, uint8_t **converted_input_samples,
const int frame_size) const int frame_size)
{ {
int error; int error;
/** /* Make the FIFO as large as it needs to be to hold both,
* Make the FIFO as large as it needs to be to hold both, * the old and the new samples. */
* the old and the new samples.
*/
if ((error = av_audio_fifo_realloc(fifo, av_audio_fifo_size(fifo) + frame_size)) < 0) { if ((error = av_audio_fifo_realloc(fifo, av_audio_fifo_size(fifo) + frame_size)) < 0) {
fprintf(stderr, "Could not reallocate FIFO\n"); fprintf(stderr, "Could not reallocate FIFO\n");
return error; return error;
} }
/** Store the new samples in the FIFO buffer. */ /* Store the new samples in the FIFO buffer. */
if (av_audio_fifo_write(fifo, (void **)converted_input_samples, if (av_audio_fifo_write(fifo, (void **)converted_input_samples,
frame_size) < frame_size) { frame_size) < frame_size) {
fprintf(stderr, "Could not write data to FIFO\n"); fprintf(stderr, "Could not write data to FIFO\n");
...@@ -481,55 +530,63 @@ static int add_samples_to_fifo(AVAudioFifo *fifo, ...@@ -481,55 +530,63 @@ static int add_samples_to_fifo(AVAudioFifo *fifo,
} }
/** /**
* Read one audio frame from the input file, decodes, converts and stores * Read one audio frame from the input file, decode, convert and store
* it in the FIFO buffer. * 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 resample_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)
*/ */
static int read_decode_convert_and_store(AVAudioFifo *fifo, static int read_decode_convert_and_store(AVAudioFifo *fifo,
AVFormatContext *input_format_context, AVFormatContext *input_format_context,
AVCodecContext *input_codec_context, AVCodecContext *input_codec_context,
AVCodecContext *output_codec_context, AVCodecContext *output_codec_context,
AVAudioResampleContext *resampler_context, AVAudioResampleContext *resample_context,
int *finished) int *finished)
{ {
/** Temporary storage of the input samples of the frame read from the file. */ /* Temporary storage of the input samples of the frame read from the file. */
AVFrame *input_frame = NULL; AVFrame *input_frame = NULL;
/** Temporary storage for the converted input samples. */ /* Temporary storage for the converted input samples. */
uint8_t **converted_input_samples = NULL; uint8_t **converted_input_samples = NULL;
int data_present; int data_present;
int ret = AVERROR_EXIT; int ret = AVERROR_EXIT;
/** Initialize temporary storage for one input frame. */ /* Initialize temporary storage for one input frame. */
if (init_input_frame(&input_frame)) if (init_input_frame(&input_frame))
goto cleanup; goto cleanup;
/** Decode one frame worth of audio samples. */ /* Decode one frame worth of audio samples. */
if (decode_audio_frame(input_frame, input_format_context, if (decode_audio_frame(input_frame, input_format_context,
input_codec_context, &data_present, finished)) input_codec_context, &data_present, finished))
goto cleanup; goto cleanup;
/** /* If we are at the end of the file and there are no more samples
* 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. * in the decoder which are delayed, we are actually finished.
* This must not be treated as an error. * This must not be treated as an error. */
*/
if (*finished && !data_present) { if (*finished && !data_present) {
ret = 0; ret = 0;
goto cleanup; goto cleanup;
} }
/** If there is decoded data, convert and store it */ /* If there is decoded data, convert and store it. */
if (data_present) { if (data_present) {
/** Initialize the temporary storage for the converted input samples. */ /* Initialize the temporary storage for the converted input samples. */
if (init_converted_samples(&converted_input_samples, output_codec_context, if (init_converted_samples(&converted_input_samples, output_codec_context,
input_frame->nb_samples)) input_frame->nb_samples))
goto cleanup; goto cleanup;
/** /* Convert the input samples to the desired output sample format.
* Convert the input samples to the desired output sample format. * This requires a temporary storage provided by converted_input_samples. */
* This requires a temporary storage provided by converted_input_samples.
*/
if (convert_samples(input_frame->extended_data, converted_input_samples, if (convert_samples(input_frame->extended_data, converted_input_samples,
input_frame->nb_samples, resampler_context)) input_frame->nb_samples, resample_context))
goto cleanup; goto cleanup;
/** Add the converted input samples to the FIFO buffer for later processing. */ /* Add the converted input samples to the FIFO buffer for later processing. */
if (add_samples_to_fifo(fifo, converted_input_samples, if (add_samples_to_fifo(fifo, converted_input_samples,
input_frame->nb_samples)) input_frame->nb_samples))
goto cleanup; goto cleanup;
...@@ -550,6 +607,10 @@ cleanup: ...@@ -550,6 +607,10 @@ cleanup:
/** /**
* Initialize one input frame for writing to the output file. * Initialize one input frame for writing to the output file.
* The frame will be exactly frame_size samples large. * 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)
*/ */
static int init_output_frame(AVFrame **frame, static int init_output_frame(AVFrame **frame,
AVCodecContext *output_codec_context, AVCodecContext *output_codec_context,
...@@ -557,28 +618,24 @@ static int init_output_frame(AVFrame **frame, ...@@ -557,28 +618,24 @@ static int init_output_frame(AVFrame **frame,
{ {
int error; int error;
/** Create a new frame to store the audio samples. */ /* Create a new frame to store the audio samples. */
if (!(*frame = av_frame_alloc())) { if (!(*frame = av_frame_alloc())) {
fprintf(stderr, "Could not allocate output frame\n"); fprintf(stderr, "Could not allocate output frame\n");
return AVERROR_EXIT; return AVERROR_EXIT;
} }
/** /* Set the frame's parameters, especially its size and format.
* Set the frame's parameters, especially its size and format.
* av_frame_get_buffer needs this to allocate memory for the * av_frame_get_buffer needs this to allocate memory for the
* audio samples of the frame. * audio samples of the frame.
* Default channel layouts based on the number of channels * Default channel layouts based on the number of channels
* are assumed for simplicity. * are assumed for simplicity. */
*/
(*frame)->nb_samples = frame_size; (*frame)->nb_samples = frame_size;
(*frame)->channel_layout = output_codec_context->channel_layout; (*frame)->channel_layout = output_codec_context->channel_layout;
(*frame)->format = output_codec_context->sample_fmt; (*frame)->format = output_codec_context->sample_fmt;
(*frame)->sample_rate = output_codec_context->sample_rate; (*frame)->sample_rate = output_codec_context->sample_rate;
/** /* Allocate the samples of the created frame. This call will make
* Allocate the samples of the created frame. This call will make * sure that the audio frame can hold as many samples as specified. */
* sure that the audio frame can hold as many samples as specified.
*/
if ((error = av_frame_get_buffer(*frame, 0)) < 0) { if ((error = av_frame_get_buffer(*frame, 0)) < 0) {
fprintf(stderr, "Could not allocate output frame samples (error '%s')\n", fprintf(stderr, "Could not allocate output frame samples (error '%s')\n",
get_error_text(error)); get_error_text(error));
...@@ -589,30 +646,36 @@ static int init_output_frame(AVFrame **frame, ...@@ -589,30 +646,36 @@ static int init_output_frame(AVFrame **frame,
return 0; return 0;
} }
/** Global timestamp for the audio frames */ /* Global timestamp for the audio frames. */
static int64_t pts = 0; static int64_t pts = 0;
/** Encode one frame worth of audio to the output file. */ /**
* 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
* decoded
* @return Error code (0 if successful)
*/
static int encode_audio_frame(AVFrame *frame, static int encode_audio_frame(AVFrame *frame,
AVFormatContext *output_format_context, AVFormatContext *output_format_context,
AVCodecContext *output_codec_context, AVCodecContext *output_codec_context,
int *data_present) int *data_present)
{ {
/** Packet used for temporary storage. */ /* Packet used for temporary storage. */
AVPacket output_packet; AVPacket output_packet;
int error; int error;
init_packet(&output_packet); init_packet(&output_packet);
/** Set a timestamp based on the sample rate for the container. */ /* Set a timestamp based on the sample rate for the container. */
if (frame) { if (frame) {
frame->pts = pts; frame->pts = pts;
pts += frame->nb_samples; pts += frame->nb_samples;
} }
/** /* Encode the audio frame and store it in the temporary packet.
* Encode the audio frame and store it in the temporary packet. * The output audio stream encoder is used to do this. */
* The output audio stream encoder is used to do this.
*/
if ((error = avcodec_encode_audio2(output_codec_context, &output_packet, if ((error = avcodec_encode_audio2(output_codec_context, &output_packet,
frame, data_present)) < 0) { frame, data_present)) < 0) {
fprintf(stderr, "Could not encode frame (error '%s')\n", fprintf(stderr, "Could not encode frame (error '%s')\n",
...@@ -621,7 +684,7 @@ static int encode_audio_frame(AVFrame *frame, ...@@ -621,7 +684,7 @@ static int encode_audio_frame(AVFrame *frame,
return error; return error;
} }
/** Write one audio frame from the temporary packet to the output file. */ /* Write one audio frame from the temporary packet to the output file. */
if (*data_present) { if (*data_present) {
if ((error = av_write_frame(output_format_context, &output_packet)) < 0) { if ((error = av_write_frame(output_format_context, &output_packet)) < 0) {
fprintf(stderr, "Could not write frame (error '%s')\n", fprintf(stderr, "Could not write frame (error '%s')\n",
...@@ -639,37 +702,37 @@ static int encode_audio_frame(AVFrame *frame, ...@@ -639,37 +702,37 @@ static int encode_audio_frame(AVFrame *frame,
/** /**
* Load one audio frame from the FIFO buffer, encode and write it to the * Load one audio frame from the FIFO buffer, encode and write it to the
* output file. * 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)
*/ */
static int load_encode_and_write(AVAudioFifo *fifo, static int load_encode_and_write(AVAudioFifo *fifo,
AVFormatContext *output_format_context, AVFormatContext *output_format_context,
AVCodecContext *output_codec_context) AVCodecContext *output_codec_context)
{ {
/** Temporary storage of the output samples of the frame written to the file. */ /* Temporary storage of the output samples of the frame written to the file. */
AVFrame *output_frame; AVFrame *output_frame;
/** /* Use the maximum number of possible samples per frame.
* Use the maximum number of possible samples per frame.
* If there is less than the maximum possible frame size in the FIFO * If there is less than the maximum possible frame size in the FIFO
* buffer use this number. Otherwise, use the maximum possible frame size * buffer use this number. Otherwise, use the maximum possible frame size. */
*/
const int frame_size = FFMIN(av_audio_fifo_size(fifo), const int frame_size = FFMIN(av_audio_fifo_size(fifo),
output_codec_context->frame_size); output_codec_context->frame_size);
int data_written; int data_written;
/** Initialize temporary storage for one output frame. */ /* Initialize temporary storage for one output frame. */
if (init_output_frame(&output_frame, output_codec_context, frame_size)) if (init_output_frame(&output_frame, output_codec_context, frame_size))
return AVERROR_EXIT; return AVERROR_EXIT;
/** /* Read as many samples from the FIFO buffer as required to fill the frame.
* Read as many samples from the FIFO buffer as required to fill the frame. * The samples are stored in the frame temporarily. */
* The samples are stored in the frame temporarily.
*/
if (av_audio_fifo_read(fifo, (void **)output_frame->data, frame_size) < frame_size) { if (av_audio_fifo_read(fifo, (void **)output_frame->data, frame_size) < frame_size) {
fprintf(stderr, "Could not read data from FIFO\n"); fprintf(stderr, "Could not read data from FIFO\n");
av_frame_free(&output_frame); av_frame_free(&output_frame);
return AVERROR_EXIT; return AVERROR_EXIT;
} }
/** Encode one frame worth of audio samples. */ /* Encode one frame worth of audio samples. */
if (encode_audio_frame(output_frame, output_format_context, if (encode_audio_frame(output_frame, output_format_context,
output_codec_context, &data_written)) { output_codec_context, &data_written)) {
av_frame_free(&output_frame); av_frame_free(&output_frame);
...@@ -679,7 +742,11 @@ static int load_encode_and_write(AVAudioFifo *fifo, ...@@ -679,7 +742,11 @@ static int load_encode_and_write(AVAudioFifo *fifo,
return 0; return 0;
} }
/** Write the trailer of the output file container. */ /**
* 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) static int write_output_file_trailer(AVFormatContext *output_format_context)
{ {
int error; int error;
...@@ -691,7 +758,6 @@ static int write_output_file_trailer(AVFormatContext *output_format_context) ...@@ -691,7 +758,6 @@ static int write_output_file_trailer(AVFormatContext *output_format_context)
return 0; return 0;
} }
/** Convert an audio file to an AAC file in an MP4 container. */
int main(int argc, char **argv) int main(int argc, char **argv)
{ {
AVFormatContext *input_format_context = NULL, *output_format_context = NULL; AVFormatContext *input_format_context = NULL, *output_format_context = NULL;
...@@ -700,89 +766,75 @@ int main(int argc, char **argv) ...@@ -700,89 +766,75 @@ int main(int argc, char **argv)
AVAudioFifo *fifo = NULL; AVAudioFifo *fifo = NULL;
int ret = AVERROR_EXIT; int ret = AVERROR_EXIT;
if (argc < 3) { if (argc != 3) {
fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]); fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]);
exit(1); exit(1);
} }
/** Register all codecs and formats so that they can be used. */ /* Register all codecs and formats so that they can be used. */
av_register_all(); av_register_all();
/** Open the input file for reading. */ /* Open the input file for reading. */
if (open_input_file(argv[1], &input_format_context, if (open_input_file(argv[1], &input_format_context,
&input_codec_context)) &input_codec_context))
goto cleanup; goto cleanup;
/** Open the output file for writing. */ /* Open the output file for writing. */
if (open_output_file(argv[2], input_codec_context, if (open_output_file(argv[2], input_codec_context,
&output_format_context, &output_codec_context)) &output_format_context, &output_codec_context))
goto cleanup; goto cleanup;
/** Initialize the resampler to be able to convert audio sample formats. */ /* Initialize the resampler to be able to convert audio sample formats. */
if (init_resampler(input_codec_context, output_codec_context, if (init_resampler(input_codec_context, output_codec_context,
&resample_context)) &resample_context))
goto cleanup; goto cleanup;
/** Initialize the FIFO buffer to store audio samples to be encoded. */ /* Initialize the FIFO buffer to store audio samples to be encoded. */
if (init_fifo(&fifo, output_codec_context)) if (init_fifo(&fifo, output_codec_context))
goto cleanup; goto cleanup;
/** Write the header of the output file container. */ /* Write the header of the output file container. */
if (write_output_file_header(output_format_context)) if (write_output_file_header(output_format_context))
goto cleanup; goto cleanup;
/** /* Loop as long as we have input samples to read or output samples
* Loop as long as we have input samples to read or output samples * to write; abort as soon as we have neither. */
* to write; abort as soon as we have neither.
*/
while (1) { while (1) {
/** Use the encoder's desired frame size for processing. */ /* Use the encoder's desired frame size for processing. */
const int output_frame_size = output_codec_context->frame_size; const int output_frame_size = output_codec_context->frame_size;
int finished = 0; int finished = 0;
/** /* Make sure that there is one frame worth of samples in the FIFO
* Make sure that there is one frame worth of samples in the FIFO
* buffer so that the encoder can do its work. * buffer so that the encoder can do its work.
* Since the decoder's and the encoder's frame size may differ, we * 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 * 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. * that they make up at least one frame worth of output samples. */
*/
while (av_audio_fifo_size(fifo) < output_frame_size) { while (av_audio_fifo_size(fifo) < output_frame_size) {
/** /* Decode one frame worth of audio samples, convert it to the
* Decode one frame worth of audio samples, convert it to the * output sample format and put it into the FIFO buffer. */
* output sample format and put it into the FIFO buffer.
*/
if (read_decode_convert_and_store(fifo, input_format_context, if (read_decode_convert_and_store(fifo, input_format_context,
input_codec_context, input_codec_context,
output_codec_context, output_codec_context,
resample_context, &finished)) resample_context, &finished))
goto cleanup; goto cleanup;
/** /* If we are at the end of the input file, we continue
* If we are at the end of the input file, we continue * encoding the remaining audio samples to the output file. */
* encoding the remaining audio samples to the output file.
*/
if (finished) if (finished)
break; break;
} }
/** /* If we have enough samples for the encoder, we encode them.
* If we have enough samples for the encoder, we encode them.
* At the end of the file, we pass the remaining samples to * At the end of the file, we pass the remaining samples to
* the encoder. * the encoder. */
*/
while (av_audio_fifo_size(fifo) >= output_frame_size || while (av_audio_fifo_size(fifo) >= output_frame_size ||
(finished && av_audio_fifo_size(fifo) > 0)) (finished && av_audio_fifo_size(fifo) > 0))
/** /* Take one frame worth of audio samples from the FIFO buffer,
* Take one frame worth of audio samples from the FIFO buffer, * encode it and write it to the output file. */
* encode it and write it to the output file.
*/
if (load_encode_and_write(fifo, output_format_context, if (load_encode_and_write(fifo, output_format_context,
output_codec_context)) output_codec_context))
goto cleanup; goto cleanup;
/** /* If we are at the end of the input file and have encoded
* If we are at the end of the input file and have encoded * all remaining samples, we can exit this loop and finish. */
* all remaining samples, we can exit this loop and finish.
*/
if (finished) { if (finished) {
int data_written; int data_written;
/** Flush the encoder as it may have delayed frames. */ /* Flush the encoder as it may have delayed frames. */
do { do {
if (encode_audio_frame(NULL, output_format_context, if (encode_audio_frame(NULL, output_format_context,
output_codec_context, &data_written)) output_codec_context, &data_written))
...@@ -792,7 +844,7 @@ int main(int argc, char **argv) ...@@ -792,7 +844,7 @@ int main(int argc, char **argv)
} }
} }
/** Write the trailer of the output file container. */ /* Write the trailer of the output file container. */
if (write_output_file_trailer(output_format_context)) if (write_output_file_trailer(output_format_context))
goto cleanup; goto cleanup;
ret = 0; ret = 0;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment