javascript - 浏览器中的mp3流解码

Question

我正在尝试使用 emscripten 和 libmad 在浏览器中设置 mp3 流接收器。
我设法使用低级 API 解码 mp3 文件，并将其完全加载到内存中。我的下一步是将其分块加载。
在 given example我使用随机大小(从 20 到 40 kbyte)分配的缓冲区来模拟碎片包，并将文件部分复制到这些缓冲区。

我的解码算法与 this question 中的答案相关但这有点不同。主要对象是Decoder，它通过addFragment方法接收片段。解码器有一个待处理片段的拉取和一个粘合缓冲区。当用户添加第一个片段时，其尾部被复制到粘合缓冲区的前半部分。当添加第二个片段时，它开始被复制到胶水的后半部分。当解码器到达事件缓冲区末尾时，它会切换到粘合，反之亦然。我确保所有这些缓冲区部分都是一致的，并且 mad_stream 指向切换之前指向的相同逻辑字节。

decoder.cpp 中的重要片段

void Decoder::addFragment          //adds the fragment to decoding queue
(intptr_t bufferPtr, uint32_t length)
{
    if (length < GLUE_LENGTH / 2) {
        return;
    }
    uint8_t* buffer = (uint8_t(*))bufferPtr;
    RawBuffer rb = {buffer, length};
    pending.push_back(rb);

    switch (state) {
        case empty:
            mad_stream_buffer(&stream, buffer, length);

            for (int i = 0; i < GLUE_LENGTH/2; ++i) {
                glue[i] = buffer[length - GLUE_LENGTH/2 + i];
            }

            state = onBufferHalf;
            prepareNextBuffer();
            break;
        case onBufferHalf:
            for (int i = 0; i < GLUE_LENGTH/2; ++i) {
                glue[GLUE_LENGTH/2 + i] = buffer[i];
            }

            state = onBufferFull;
            break;
        case onGlueHalf:
            for (int i = 0; i < GLUE_LENGTH/2; ++i) {
                glue[GLUE_LENGTH/2 + i] = buffer[i];
            }

            state = onGlueFull;
            cached = false;
            prepareNextBuffer();
            break;
        default:
            break;
    }
}

emscripten::val Decoder::decode     //decodes up to requested amount of frames
(uint32_t count)
{
    emscripten::val ret = emscripten::val::undefined();

    int available = framesLeft(count);
    if (available > 0) {
        ret = context.call<emscripten::val>("createBuffer", channels, available * samplesPerFrame, sampleRate);

        std::vector<emscripten::val> chans(channels, emscripten::val::undefined());
        for (int i = 0; i < channels; ++i) {
            chans[i] = ret.call<emscripten::val>("getChannelData", i);
        } 

        for (int i = 0; i < available; ++i) {
            int res = mad_frame_decode(&frame, &stream);

            if (res != 0) {
                if (MAD_RECOVERABLE(stream.error)) {
                    continue;
                } else {
                    break;
                }
            }

            mad_synth_frame(&synth, &frame);
            for (int j = 0; j < samplesPerFrame; ++j) {
                for (int k = 0; k < channels; ++k) {
                    float value = mad_f_todouble(synth.pcm.samples[k][j]);
                    chans[k].set(std::to_string(success * samplesPerFrame + j), emscripten::val(value));
                }
            }
        }

        cachedLength -= available;
        if (cachedLength == 0) {
            cached = false;
            prepareNextBuffer();
        }
    }
    return ret;
}


//tells how many frames can be decoded on the same
//sample rate, same amount of channels without switching the buffers
//it is required in Decoder::decode method to understand the size of 
//allocating AudioContext::AudioBuffer.

uint32_t Decoder::framesLeft(uint32_t max)
{
    if (state == empty || state == onGlueHalf) {
        return 0;
    }

    if (cached == false) {
        mad_stream probe;
        mad_header ph;
        initializeProbe(probe);
        mad_header_init(&ph);

        while (cachedLength < max) {
            if (mad_header_decode(&ph, &probe) == 0) {
                if (sampleRate == 0) {
                    sampleRate = ph.samplerate;
                    channels = MAD_NCHANNELS(&ph);
                    samplesPerFrame = MAD_NSBSAMPLES(&ph) * 32;
                } else {
                    if (sampleRate != ph.samplerate || channels != MAD_NCHANNELS(&ph) || samplesPerFrame != MAD_NSBSAMPLES(&ph) * 32) {
                        break;
                    }
                }
                if (probe.next_frame > probe.this_frame) {
                    ++cachedLength;
                }
            } else {
                if (!MAD_RECOVERABLE(probe.error)) {
                    break;
                }
            }
        }

        cachedNext = probe.next_frame;
        cachedThis = probe.this_frame;
        cachedError = probe.error;
        mad_header_finish(&ph);
        mad_stream_finish(&probe);
        cached = true;
    }

    return std::min(cachedLength, max);
}

//this method fastforwards the stream
//to the cached end
void Decoder::pullBuffer()
{
    if (cached == false) {
        throw 2;
    }
    stream.this_frame = cachedThis;
    stream.next_frame = cachedNext;
    stream.error = cachedError;
}

//this method switches the stream to glue buffer
//or to the next pending buffer
//copies the parts to the glue buffer if required

void Decoder::changeBuffer()
{
    uint32_t left;
    switch (state) {
        case empty:
            throw 3;
        case onBufferHalf:
            switchToGlue();
            state = onGlueHalf;
            break;
        case onBufferFull:
            switchToGlue();
            state = onGlueFull;
            break;
        case onGlueHalf:
            throw 4;
            break;
        case onGlueFull:
            switchBuffer(pending[0].ptr, pending[0].length);

            for (int i = 0; i < GLUE_LENGTH/2; ++i) {
                glue[i] = pending[0].ptr[pending[0].length - GLUE_LENGTH/2 + i];
            }
            state = onBufferHalf;

            if (pending.size() > 1) {
                for (int i = 0; i < GLUE_LENGTH/2; ++i) {
                    glue[GLUE_LENGTH/2 + i] = pending[1].ptr[i];
                }
                state = onBufferFull;
            }
    }

    cached = false;
}

//this method seeks the decodable data in pending buffers
//prepares if any proper data has been found
void Decoder::prepareNextBuffer()
{
    bool shift;
    do {
        shift = false;
        framesLeft();
        if (cachedLength == 0 && state != empty && state != onGlueHalf) {
            pullBuffer();
            changeBuffer();
            shift = true;
        }
    } while (shift);
}

//low level method to switch to glue buffer, also frees the drained fragment
void Decoder::switchToGlue()
{
    switchBuffer(glue, GLUE_LENGTH);
    stream.error = MAD_ERROR_NONE;

    free(pending[0].ptr);
    pending.pop_front();
}

//low level method which actually switch mad_stream
//to another buffer
void Decoder::switchBuffer(uint8_t* bufferPtr, uint32_t length)
{
    uint32_t left;
    left = stream.bufend - stream.next_frame;
    mad_stream_buffer(&stream, bufferPtr + GLUE_LENGTH / 2 - left, length - (GLUE_LENGTH / 2 - left));
    stream.error = MAD_ERROR_NONE;
}

Here是我的带有完整代码的存储库。要尝试它，您需要使用 CMake 构建它(应该安装 emscripten)并从浏览器的构建目录中打开 index.html。

问题
播放失真。我尝试检查移位前后最后一个成功帧周围的字节、mad_stream 的所有不同子结构 - 一切似乎都正常工作，但仍然无法正常工作。我的最新进展是构建和托管here 。我真的很困惑，我不知道该怎么做才能消除播放中的失真。

如果有人帮助我，我将非常感激。

Answer 1

我找到了! MAD 工作得很好，只是因为我的内部计数器，我一直在输出中跳过第一个解码帧。

for (int i = 0; success < available; ++i) {
            int res = mad_frame_decode(frame, stream);

            if (res == 0) {
                ++**success**;
            } else {
                if (MAD_RECOVERABLE(stream->error)) {

                    std::cout << "Unexpected error during the decoding process: " << mad_stream_errorstr(stream) << std::endl;
                    continue;
                } else {
                    break;
                }
            }

            mad_synth_frame(synth, frame);

            for (int j = 0; j < samplesPerFrame; ++j) {
                for (int k = 0; k < channels; ++k) {
                    float value = mad_f_todouble(synth->pcm.samples[k][j]);
                    chans[k].set(std::to_string(success * samplesPerFrame + j), emscripten::val(value));
                }
            }
        }

将成功更改为i并且成功了。