简介：
ffplay的音频输出通过SDL实现，主要流程分为如下几步：
- 打开音频设备，设置参数
- 启动SDL音频设备播放
- SDL音频回调函数读取数据
代码如下：
case AVMEDIA_TYPE_AUDIO:
//从avctx(即AVCodecContext)中获取音频格式参数
sample_rate = avctx->sample_rate;
nb_channels = avctx->channels;
channel_layout = avctx->channel_layout;
/* prepare audio output 准备音频输出*/
//调用audio_open打开sdl音频输出，实际打开的设备参数保存在audio_tgt，返回值表示输出设备的缓冲区大小
if ((ret = audio_open(is, channel_layout, nb_channels, sample_rate, &is->audio_tgt)) < 0)
goto fail;
is->audio_hw_buf_size = ret;
is->audio_src = is->audio_tgt; //暂且将数据源参数等同于目标输出参数
//初始化audio_buf相关参数
is->audio_buf_size = 0;
is->audio_buf_index = 0;
/* init averaging filter 初始化averaging滤镜, 非audio master时使用 */
is->audio_diff_avg_coef = exp(log(0.01) / AUDIO_DIFF_AVG_NB);
is->audio_diff_avg_count = 0;
/* 由于我们没有精确的音频数据填充FIFO,故只有在大于该阈值时才进行校正音频同步*/
is->audio_diff_threshold = (double)(is->audio_hw_buf_size) / is->audio_tgt.bytes_per_sec;
is->audio_stream = stream_index; // 获取audio的stream索引
is->audio_st = ic->streams[stream_index]; // 获取audio的stream指针
// 初始化ffplay封装的音频解码器
decoder_init(&is->auddec, avctx, &is->audioq, is->continue_read_thread);
if ((is->ic->iformat->flags & (AVFMT_NOBINSEARCH | AVFMT_NOGENSEARCH | AVFMT_NO_BYTE_SEEK)) && !is->ic->iformat->read_seek) {
is->auddec.start_pts = is->audio_st->start_time;
is->auddec.start_pts_tb = is->audio_st->time_base;
}
// 启动音频解码线程
if ((ret = decoder_start(&is->auddec, audio_thread, "audio_decoder", is)) < 0)
goto out;
// 0:播放 非0：暂停
SDL_PauseAudioDevice(audio_dev, 0);
break;
打开音频设备
static int audio_open(void *opaque, int64_t wanted_channel_layout,
int wanted_nb_channels, int wanted_sample_rate,
struct AudioParams *audio_hw_params)
{
SDL_AudioSpec wanted_spec, spec;
const char *env;
static const int next_nb_channels[] = {0, 0, 1, 6, 2, 6, 4, 6};
static const int next_sample_rates[] = {0, 44100, 48000, 96000, 192000};
int next_sample_rate_idx = FF_ARRAY_ELEMS(next_sample_rates) - 1;
env = SDL_getenv("SDL_AUDIO_CHANNELS");
if (env) { // 若环境变量有设置，优先从环境变量取得声道数和声道布局
wanted_nb_channels = atoi(env);
wanted_channel_layout = av_get_default_channel_layout(wanted_nb_channels);
}
if (!wanted_channel_layout || wanted_nb_channels != av_get_channel_layout_nb_channels(wanted_channel_layout)) {
wanted_channel_layout = av_get_default_channel_layout(wanted_nb_channels);
wanted_channel_layout &= ~AV_CH_LAYOUT_STEREO_DOWNMIX;
}
// 根据channel_layout获取nb_channels，当传入参数wanted_nb_channels不匹配时，此处会作修正
wanted_nb_channels = av_get_channel_layout_nb_channels(wanted_channel_layout);
wanted_spec.channels = wanted_nb_channels;
wanted_spec.freq = wanted_sample_rate;
if (wanted_spec.freq <= 0 || wanted_spec.channels <= 0) {
av_log(NULL, AV_LOG_ERROR, "Invalid sample rate or channel count!\n");
return -1;
}
while (next_sample_rate_idx && next_sample_rates[next_sample_rate_idx] >= wanted_spec.freq)
next_sample_rate_idx--; // 从采样率数组中找到第一个不大于传入参数wanted_sample_rate的值
// 音频采样格式有两大类型：planar和packed，假设一个双声道音频文件，一个左声道采样点记作L，一个右声道采样点记作R，则：
// planar存储格式：(plane1)LLLLLLLL...LLLL (plane2)RRRRRRRR...RRRR
// packed存储格式：(plane1)LRLRLRLR...........................LRLR
// 在这两种采样类型下，又细分多种采样格式，如AV_SAMPLE_FMT_S16、AV_SAMPLE_FMT_S16P等，
// 注意SDL2.0目前不支持planar格式
// channel_layout是int64_t类型，表示音频声道布局，每bit代表一个特定的声道，参考channel_layout.h中的定义，一目了然
// 数据量(bits/秒) = 采样率(Hz) * 采样深度(bit) * 声道数
wanted_spec.format = AUDIO_S16SYS;
wanted_spec.silence = 0;
/*
* 一次读取多长的数据
* SDL_AUDIO_MAX_CALLBACKS_PER_SEC一秒最多回调次数，避免频繁的回调
* Audio buffer size in samples (power of 2)
*/
wanted_spec.samples = FFMAX(SDL_AUDIO_MIN_BUFFER_SIZE,
2 << av_log2(wanted_spec.freq / SDL_AUDIO_MAX_CALLBACKS_PER_SEC));
wanted_spec.callback = sdl_audio_callback;
wanted_spec.userdata = opaque;
// 打开音频设备并创建音频处理线程。期望的参数是wanted_spec，实际得到的硬件参数是spec
// 1) SDL提供两种使音频设备取得音频数据方法：
// a. push，SDL以特定的频率调用回调函数，在回调函数中取得音频数据
// b. pull，用户程序以特定的频率调用SDL_QueueAudio()，向音频设备提供数据。此种情况wanted_spec.callback=NULL
// 2) 音频设备打开后播放静音，不启动回调，调用SDL_PauseAudio(0)后启动回调，开始正常播放音频
// SDL_OpenAudioDevice()第一个参数为NULL时，等价于SDL_OpenAudio()
while (!(audio_dev = SDL_OpenAudioDevice(NULL, 0, &wanted_spec, &spec, SDL_AUDIO_ALLOW_FREQUENCY_CHANGE | SDL_AUDIO_ALLOW_CHANNELS_CHANGE))) {
av_log(NULL, AV_LOG_WARNING, "SDL_OpenAudio (%d channels, %d Hz): %s\n",
wanted_spec.channels, wanted_spec.freq, SDL_GetError());
wanted_spec.channels = next_nb_channels[FFMIN(7, wanted_spec.channels)];
if (!wanted_spec.channels) {
wanted_spec.freq = next_sample_rates[next_sample_rate_idx--];
wanted_spec.channels = wanted_nb_channels;
if (!wanted_spec.freq) {
av_log(NULL, AV_LOG_ERROR,
"No more combinations to try, audio open failed\n");
return -1;
}
}
wanted_channel_layout = av_get_default_channel_layout(wanted_spec.channels);
}
// 检查打开音频设备的实际参数：采样格式
if (spec.format != AUDIO_S16SYS) {
av_log(NULL, AV_LOG_ERROR,
"SDL advised audio format %d is not supported!\n", spec.format);
return -1;
}
// 检查打开音频设备的实际参数：声道数
if (spec.channels != wanted_spec.channels) {
wanted_channel_layout = av_get_default_channel_layout(spec.channels);
if (!wanted_channel_layout) {
av_log(NULL, AV_LOG_ERROR,
"SDL advised channel count %d is not supported!\n", spec.channels);
return -1;
}
}
// wanted_spec是期望的参数，spec是实际的参数，wanted_spec和spec都是SDL中的结构。
// 此处audio_hw_params是FFmpeg中的参数，输出参数供上级函数使用
// audio_hw_params保存的参数，就是在做重采样的时候要转成的格式。
audio_hw_params->fmt = AV_SAMPLE_FMT_S16;
audio_hw_params->freq = spec.freq;
audio_hw_params->channel_layout = wanted_channel_layout;
audio_hw_params->channels = spec.channels;
/* audio_hw_params->frame_size这里只是计算一个采样点占用的字节数 */
audio_hw_params->frame_size = av_samples_get_buffer_size(NULL, audio_hw_params->channels,
1, audio_hw_params->fmt, 1);
audio_hw_params->bytes_per_sec = av_samples_get_buffer_size(NULL, audio_hw_params->channels,
audio_hw_params->freq,
audio_hw_params->fmt, 1);
if (audio_hw_params->bytes_per_sec <= 0 || audio_hw_params->frame_size <= 0) {
av_log(NULL, AV_LOG_ERROR, "av_samples_get_buffer_size failed\n");
return -1;
}
// 比如2帧数据，一帧就是1024个采样点， 1024*2*2 * 2 = 8192字节
return spec.size; /* SDL内部缓存的数据字节, samples * channels *byte_per_sample */
}
读取数据
static void sdl_audio_callback(void *opaque, Uint8 *stream, int len)
{
VideoState *is = opaque;
int audio_size, len1;
audio_callback_time = av_gettime_relative();
while (len > 0) { // 循环读取，直到读取到足够的数据
/* (1)如果is->audio_buf_index < is->audio_buf_size则说明上次拷贝还剩余一些数据，
* 先拷贝到stream再调用audio_decode_frame
* (2)如果audio_buf消耗完了，则调用audio_decode_frame重新填充audio_buf
*/
if (is->audio_buf_index >= is->audio_buf_size) {
audio_size = audio_decode_frame(is);
if (audio_size < 0) {
/* if error, just output silence */
is->audio_buf = NULL;
is->audio_buf_size = SDL_AUDIO_MIN_BUFFER_SIZE / is->audio_tgt.frame_size
* is->audio_tgt.frame_size;
} else {
if (is->show_mode != SHOW_MODE_VIDEO)
update_sample_display(is, (int16_t *)is->audio_buf, audio_size);
is->audio_buf_size = audio_size; // 讲字节 多少字节
}
is->audio_buf_index = 0;
}
//根据缓冲区剩余大小量力而行
len1 = is->audio_buf_size - is->audio_buf_index;
if (len1 > len) // len = 3000 < len1 4096
len1 = len;
//根据audio_volume决定如何输出audio_buf
/* 判断是否为静音，以及当前音量的大小，如果音量为最大则直接拷贝数据 */
if (!is->muted && is->audio_buf && is->audio_volume == SDL_MIX_MAXVOLUME)
memcpy(stream, (uint8_t *)is->audio_buf + is->audio_buf_index, len1);
else {
memset(stream, 0, len1);
// 3.调整音量
/* 如果处于mute状态则直接使用stream填0数据, 暂停时is->audio_buf = NULL */
if (!is->muted && is->audio_buf)
SDL_MixAudioFormat(stream, (uint8_t *)is->audio_buf + is->audio_buf_index,
AUDIO_S16SYS, len1, is->audio_volume);
}
len -= len1;
stream += len1;
/* 更新is->audio_buf_index，指向audio_buf中未被拷贝到stream的数据（剩余数据）的起始位置 */
is->audio_buf_index += len1;
}
is->audio_write_buf_size = is->audio_buf_size - is->audio_buf_index;
/* Let's assume the audio driver that is used by SDL has two periods. */
if (!isnan(is->audio_clock)) {
set_clock_at(&is->audclk, is->audio_clock -
(double)(2 * is->audio_hw_buf_size + is->audio_write_buf_size)
/ is->audio_tgt.bytes_per_sec,
is->audio_clock_serial,
audio_callback_time / 1000000.0);
sync_clock_to_slave(&is->extclk, &is->audclk);
}
}