1. 音频输出模块

1.1 音频输出流程

1. 打开SDL音频设备,设置参数
2. 启动SDL音频设备播放
3. SDL音频回调函数读取数据,也就是从FrameQueue中读取Frame到SDL回调函数中的Buffer中

audio的输出在SDL下是被动的,即开启SDL音频后,当SDL需要数据输出时则通过回调函数的方式告诉应用者改传入多少数据,但是这里存在问题:

• ffmpeg解码一个AVPacket音频到AVFrame后,AVFrame中存储的音频数据大小与SDL回调需要的数据不一定相等 (回调函数每次获取的数据量是固定的)

• 特别是如果实现声音的变速功能,那么每一帧AVFrame做变速后大小概率和SDL回调所需要的数据大小不一致.

  这就需要再添加一级缓冲区来解决问题了,即是从FrameQueue中获取Frame数据后,先存到一个Buffer中,如果再从这个Buffer中读取数据给SDL的回调函数.

1.2 音频输出模型图

注意:aduio_decode_frame这个函数没有解码,而是将数据放入缓存Buffer中去,最多只是执行了重采样而已(输出源和输入参数不一致时要重采样!)

2. 打开SDL音频设备

SDL音频输出参数是一开始就设置好的!!! 当码流解出来的参数和预设参数不一致时需要重采样成SDL音频输出的参数,这样才能正常播放.

音频设备打开其实是在解复用线程中实现的.解复用线程先打开音频设备,设定音频回调函数供SDL音频播放线程回调使用,然后创建解码线程!

 main()->stream_open()->read_thread()->stream_component_open()->audio_open(is, channel_layout, nb_channels, sample_rate, &is->audio_tgt)

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;
#endif/* 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); //0.794  exp，高等数学里以自然常数e为底的指数函数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;SDL_PauseAudioDevice(audio_dev, 0);break;

通过audio_open获取输出设备参数audio_tgt,然后将audio_tgt赋值给audio_src,如果audio_src参数和输入参数一致的话则不需要进行重采样操作,否则将引入重采样机制.

最后初始化了几个audio_buf相关参数(也就是上图的缓存Buffer):

• audio_buf:从要输出的AVFrame中取得音频数据(PCM),必要时进行重采样.
• audio_buf_size:audio_buf总大小
• audio_buf_index:下一次可读大的audio_buf位置.
• audio_write_buf_size:audio_buf剩余的buffer长度,也就是audio_buf_size-dudio_buf_index

在audio_open中,通过SDL_OpenAudioDevice注册sdl_audio_callback函数为音频输出的回调函数,这样音频输出的总逻辑就是sdl_audio_callback了

audio_open详解

audio_open的工作就是获取输出设备的参数,并且为音频输出线程设置回调函数.

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, nb_samples * channels *byte_per_sample */
}

bytes_per_sec就说一秒钟音频字节数=采样率 * 声道数 * 采样格式大小（bit） /8

音频一帧大小=一帧采样点数（AAC为1024）*声道数 * 采样格式大小（bit）/8

spec.size取的是两帧数据大小

sdl_audio_callback

/*** @brief sdl_audio_callback* @param opaque    指向user的数据* @param stream    拷贝PCM的地址* @param len       需要拷贝的长度*/
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可能产生延迟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 4096len1 = 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);}
}

首先解释sdl_audio_callback的参数含义:

• opaque就是指向VideoPlayer大管家,由wanted_spec.userdata = opaque;设置
• stream这个就是回调缓冲区,我们回调得到的数据都会存放到这个缓冲区中
• len是回调缓冲区需要的数据量,也就是需要拷贝的长度

while(len>0)就是一直读取数据,直到读满为止

if (is->audio_buf_index >= is->audio_buf_size)这个意思是说我们用户设置的缓冲区没有数据了,得通过audio_decode_frame函数进行获取数据

len1是缓冲区大小,如果缓冲区len1<=len的话就全部读取,否则就读取len长度,剩余留在缓冲区中待下次读取.

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);}

这段代码很容易读懂,就是如果不是静音,并且缓冲区不为空且音量为最大值 那么就直接将数据拷贝到stream中

否则如果音量为0就直接写入0数据即可,不然就要调用SDL_MixAudioFormat设置音量,然后写入.

audio_decode_frame

static int audio_decode_frame(VideoState *is)
{int data_size, resampled_data_size;int64_t dec_channel_layout;av_unused double audio_clock0;int wanted_nb_samples;Frame *af;if (is->paused)return -1;do {
#if defined(_WIN32)while (frame_queue_nb_remaining(&is->sampq) == 0) {if ((av_gettime_relative() - audio_callback_time) > 1000000LL * is->audio_hw_buf_size / is->audio_tgt.bytes_per_sec / 2)return -1;av_usleep (1000);}
#endif// 若队列头部可读，则由af指向可读帧if (!(af = frame_queue_peek_readable(&is->sampq)))return -1;frame_queue_next(&is->sampq);} while (af->serial != is->audioq.serial);// 根据frame中指定的音频参数获取缓冲区的大小 af->frame->channels * af->frame->nb_samples * 2data_size = av_samples_get_buffer_size(NULL,af->frame->channels,af->frame->nb_samples,af->frame->format, 1);// 获取声道布局dec_channel_layout =(af->frame->channel_layout &&af->frame->channels == av_get_channel_layout_nb_channels(af->frame->channel_layout)) ?af->frame->channel_layout : av_get_default_channel_layout(af->frame->channels);// 获取样本数校正值：若同步时钟是音频，则不调整样本数；否则根据同步需要调整样本数wanted_nb_samples = synchronize_audio(is, af->frame->nb_samples);// is->audio_tgt是SDL可接受的音频帧数，是audio_open()中取得的参数// 在audio_open()函数中又有"is->audio_src = is->audio_tgt""// 此处表示：如果frame中的音频参数 == is->audio_src == is->audio_tgt，// 那音频重采样的过程就免了(因此时is->swr_ctr是NULL)// 否则使用frame(源)和is->audio_tgt(目标)中的音频参数来设置is->swr_ctx，// 并使用frame中的音频参数来赋值is->audio_src else {// 未经重采样，则将指针指向frame中的音频数据/*重采样代码后面单独分析*/is->audio_buf = af->frame->data[0]; //将audio_buf指向帧数据resampled_data_size = data_size;audio_clock0 = is->audio_clock;/* update the audio clock with the pts */if (!isnan(af->pts))is->audio_clock = af->pts + (double) af->frame->nb_samples / af->frame->sample_rate;elseis->audio_clock = NAN;is->audio_clock_serial = af->serial;
#ifdef DEBUG{static double last_clock;printf("audio: delay=%0.3f clock=%0.3f clock0=%0.3f\n",is->audio_clock - last_clock,is->audio_clock, audio_clock0);last_clock = is->audio_clock;}
#endifreturn resampled_data_size;
}

audio_decode_frame函数就是冲FrameQueue中获取Frame数据,然后判断是否需要重采样(下面详解,这边忽略),然后将audio_buf指向帧中的buff,这里可以看出audio_buf并不是直接申请一段空间,而是直接复用帧的缓冲区而已,最重要的是考虑下面时钟代码的原理!!!

is->audio_clock = af->pts + (double) af->frame->nb_samples / af->frame->sample_rate;

时钟为什么这样设置呢???

我们知道af->pts(单位为秒,在存入队列前就设置过了)是指向audio_buf一开始的位置,而(double) af->frame->nb_samples / af->frame->sample_rate;是计算一帧的时间,也就是说这里的audio_clock时钟现在是指向这一帧结尾的位置;如下图所示

那么这样具体有什么用呢???

我们看sdl_audio_callback结尾的一段代码:

    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);}

audio_write_buf_size是计算的是未读的字节数

我们现在时钟需要设置播放位置的pts,但是我们只知道audio_clock也就是audio_buf的pts,然后我们通过每秒钟为多少字节来计算sdl播放的pts,看图:

3. 音频重采样

static int audio_decode_frame(VideoState *is)
{int data_size, resampled_data_size;int64_t dec_channel_layout;av_unused double audio_clock0;int wanted_nb_samples;Frame *af;if (is->paused)return -1;do {
#if defined(_WIN32)while (frame_queue_nb_remaining(&is->sampq) == 0) {if ((av_gettime_relative() - audio_callback_time) > 1000000LL * is->audio_hw_buf_size / is->audio_tgt.bytes_per_sec / 2)return -1;av_usleep (1000);}
#endif// 若队列头部可读，则由af指向可读帧if (!(af = frame_queue_peek_readable(&is->sampq)))return -1;frame_queue_next(&is->sampq);} while (af->serial != is->audioq.serial);// 根据frame中指定的音频参数获取缓冲区的大小 af->frame->channels * af->frame->nb_samples * 2data_size = av_samples_get_buffer_size(NULL,af->frame->channels,af->frame->nb_samples,af->frame->format, 1);// 获取声道布局dec_channel_layout =(af->frame->channel_layout &&af->frame->channels == av_get_channel_layout_nb_channels(af->frame->channel_layout)) ?af->frame->channel_layout : av_get_default_channel_layout(af->frame->channels);// 获取样本数校正值：若同步时钟是音频，则不调整样本数；否则根据同步需要调整样本数wanted_nb_samples = synchronize_audio(is, af->frame->nb_samples);// is->audio_tgt是SDL可接受的音频帧数，是audio_open()中取得的参数// 在audio_open()函数中又有"is->audio_src = is->audio_tgt""// 此处表示：如果frame中的音频参数 == is->audio_src == is->audio_tgt，// 那音频重采样的过程就免了(因此时is->swr_ctr是NULL)// 否则使用frame(源)和is->audio_tgt(目标)中的音频参数来设置is->swr_ctx，// 并使用frame中的音频参数来赋值is->audio_srcif (af->frame->format           != is->audio_src.fmt            || // 采样格式dec_channel_layout      != is->audio_src.channel_layout || // 通道布局af->frame->sample_rate  != is->audio_src.freq           || // 采样率// 第4个条件, 要改变样本数量, 那就是需要初始化重采样(wanted_nb_samples      != af->frame->nb_samples && !is->swr_ctx) // samples不同且swr_ctx没有初始化) {swr_free(&is->swr_ctx);is->swr_ctx = swr_alloc_set_opts(NULL,is->audio_tgt.channel_layout,  // 目标输出is->audio_tgt.fmt,is->audio_tgt.freq,dec_channel_layout,            // 数据源af->frame->format,af->frame->sample_rate,0, NULL);if (!is->swr_ctx || swr_init(is->swr_ctx) < 0) {av_log(NULL, AV_LOG_ERROR,"Cannot create sample rate converter for conversion of %d Hz %s %d channels to %d Hz %s %d channels!\n",af->frame->sample_rate, av_get_sample_fmt_name(af->frame->format), af->frame->channels,is->audio_tgt.freq, av_get_sample_fmt_name(is->audio_tgt.fmt), is->audio_tgt.channels);swr_free(&is->swr_ctx);return -1;}is->audio_src.channel_layout = dec_channel_layout;is->audio_src.channels       = af->frame->channels;is->audio_src.freq = af->frame->sample_rate;is->audio_src.fmt = af->frame->format;}if (is->swr_ctx) {// 重采样输入参数1：输入音频样本数是af->frame->nb_samples// 重采样输入参数2：输入音频缓冲区const uint8_t **in = (const uint8_t **)af->frame->extended_data; // data[0] data[1]// 重采样输出参数1：输出音频缓冲区尺寸uint8_t **out = &is->audio_buf1; //真正分配缓存audio_buf1，指向是用audio_buf// 重采样输出参数2：输出音频缓冲区int out_count = (int64_t)wanted_nb_samples * is->audio_tgt.freq / af->frame->sample_rate+ 256;int out_size  = av_samples_get_buffer_size(NULL, is->audio_tgt.channels,out_count, is->audio_tgt.fmt, 0);int len2;if (out_size < 0) {av_log(NULL, AV_LOG_ERROR, "av_samples_get_buffer_size() failed\n");return -1;}// 如果frame中的样本数经过校正，则条件成立if (wanted_nb_samples != af->frame->nb_samples) {int sample_delta = (wanted_nb_samples - af->frame->nb_samples) * is->audio_tgt.freq/ af->frame->sample_rate;int compensation_distance = wanted_nb_samples * is->audio_tgt.freq / af->frame->sample_rate;// swr_set_compensationif (swr_set_compensation(is->swr_ctx,sample_delta,compensation_distance) < 0) {av_log(NULL, AV_LOG_ERROR, "swr_set_compensation() failed\n");return -1;}}av_fast_malloc(&is->audio_buf1, &is->audio_buf1_size, out_size);if (!is->audio_buf1)return AVERROR(ENOMEM);// 音频重采样：返回值是重采样后得到的音频数据中单个声道的样本数len2 = swr_convert(is->swr_ctx, out, out_count, in, af->frame->nb_samples);if (len2 < 0) {av_log(NULL, AV_LOG_ERROR, "swr_convert() failed\n");return -1;}if (len2 == out_count) {av_log(NULL, AV_LOG_WARNING, "audio buffer is probably too small\n");if (swr_init(is->swr_ctx) < 0)swr_free(&is->swr_ctx);}// 重采样返回的一帧音频数据大小(以字节为单位)is->audio_buf = is->audio_buf1;resampled_data_size = len2 * is->audio_tgt.channels * av_get_bytes_per_sample(is->audio_tgt.fmt);} else {// 未经重采样，则将指针指向frame中的音频数据is->audio_buf = af->frame->data[0]; // s16交错模式data[0], fltp data[0] data[1]resampled_data_size = data_size;}audio_clock0 = is->audio_clock;/* update the audio clock with the pts */if (!isnan(af->pts))is->audio_clock = af->pts + (double) af->frame->nb_samples / af->frame->sample_rate;elseis->audio_clock = NAN;is->audio_clock_serial = af->serial;
#ifdef DEBUG{static double last_clock;printf("audio: delay=%0.3f clock=%0.3f clock0=%0.3f\n",is->audio_clock - last_clock,is->audio_clock, audio_clock0);last_clock = is->audio_clock;}
#endifreturn resampled_data_size;
}

样本补偿

/***@}**@name低级选项设置功能*这些功能提供了一种设置不可能的低级选项的方法*使用AVOption API。*@{*//***激活重采样补偿（“软”补偿）。这个功能是*在swr_next_pts（）中需要时内部调用。**@参数[in， out]s分配的Swr上下文。如果没有初始化，*或SWR_FLAG_RESAMPLE未设置，swr_init（）是*使用设置的标志调用。*@参数[in]每个样品的PTSsample_delta增量*@参数[in]compensation_distance要补偿的样本数*@return>=0成功，AVERROR错误代码如果：*@li@c s为NULL，*@li@ccompensation_distance小于0，*@li@ccompensation_distance是0但sample_delta不是，*@li重新取样器不支持的补偿，或*@liswr_init（）调用时失败。*/
int swr_set_compensation(struct SwrContext *s, int sample_delta, int compensation_distance);