Recherche avancée
Autres articles (84)
-
Gestion générale des documents
13 mai 2011, parMédiaSPIP ne modifie jamais le document original mis en ligne.
Pour chaque document mis en ligne il effectue deux opérations successives : la création d’une version supplémentaire qui peut être facilement consultée en ligne tout en laissant l’original téléchargeable dans le cas où le document original ne peut être lu dans un navigateur Internet ; la récupération des métadonnées du document original pour illustrer textuellement le fichier ;
Les tableaux ci-dessous expliquent ce que peut faire MédiaSPIP (...) -
Use, discuss, criticize
13 avril 2011, parTalk to people directly involved in MediaSPIP’s development, or to people around you who could use MediaSPIP to share, enhance or develop their creative projects.
The bigger the community, the more MediaSPIP’s potential will be explored and the faster the software will evolve.
A discussion list is available for all exchanges between users. -
Le profil des utilisateurs
12 avril 2011, parChaque utilisateur dispose d’une page de profil lui permettant de modifier ses informations personnelle. Dans le menu de haut de page par défaut, un élément de menu est automatiquement créé à l’initialisation de MediaSPIP, visible uniquement si le visiteur est identifié sur le site.
L’utilisateur a accès à la modification de profil depuis sa page auteur, un lien dans la navigation "Modifier votre profil" est (...)
Sur d’autres sites (9422)
-
C++ ffmpeg lib version 7.0 - annoying removing frames while exporting
4 septembre 2024, par Chris PI want to make a C++ lib named cppdub which will mimic the python module pydub.


One main function is to export the AudioSegment to a file with a specific format (example : mp3).


The code is :



AudioSegment AudioSegment::from_file(const std::string& file_path, const std::string& format, const std::string& codec,
 const std::map& parameters, int start_second, int duration) {

 avformat_network_init();
 av_log_set_level(AV_LOG_ERROR); // Adjust logging level as needed

 AVFormatContext* format_ctx = nullptr;
 if (avformat_open_input(&format_ctx, file_path.c_str(), nullptr, nullptr) != 0) {
 std::cerr << "Error: Could not open audio file." << std::endl;
 return AudioSegment(); // Return an empty AudioSegment on failure
 }

 if (avformat_find_stream_info(format_ctx, nullptr) < 0) {
 std::cerr << "Error: Could not find stream information." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 int audio_stream_index = -1;
 for (unsigned int i = 0; i < format_ctx->nb_streams; i++) {
 if (format_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
 audio_stream_index = i;
 break;
 }
 }

 if (audio_stream_index == -1) {
 std::cerr << "Error: Could not find audio stream." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVCodecParameters* codec_par = format_ctx->streams[audio_stream_index]->codecpar;
 const AVCodec* my_codec = avcodec_find_decoder(codec_par->codec_id);
 AVCodecContext* codec_ctx = avcodec_alloc_context3(my_codec);

 if (!codec_ctx) {
 std::cerr << "Error: Could not allocate codec context." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_parameters_to_context(codec_ctx, codec_par) < 0) {
 std::cerr << "Error: Could not initialize codec context." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_open2(codec_ctx, my_codec, nullptr) < 0) {
 std::cerr << "Error: Could not open codec." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 SwrContext* swr_ctx = swr_alloc();
 if (!swr_ctx) {
 std::cerr << "Error: Could not allocate SwrContext." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }
 codec_ctx->sample_rate = 44100;
 // Set up resampling context to convert to S16 format with 2 bytes per sample
 av_opt_set_chlayout(swr_ctx, "in_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_int(swr_ctx, "in_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", codec_ctx->sample_fmt, 0);

 AVChannelLayout dst_ch_layout;
 av_channel_layout_copy(&dst_ch_layout, &codec_ctx->ch_layout);
 av_channel_layout_uninit(&dst_ch_layout);
 av_channel_layout_default(&dst_ch_layout, 2);

 av_opt_set_chlayout(swr_ctx, "out_chlayout", &dst_ch_layout, 0);
 av_opt_set_int(swr_ctx, "out_sample_rate", codec_ctx->sample_rate, 0); // Match input sample rate
 av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", AV_SAMPLE_FMT_S16, 0); // Force S16 format

 if (swr_init(swr_ctx) < 0) {
 std::cerr << "Error: Failed to initialize the resampling context" << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVPacket packet;
 AVFrame* frame = av_frame_alloc();
 if (!frame) {
 std::cerr << "Error: Could not allocate frame." << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 std::vector<char> output;
 while (av_read_frame(format_ctx, &packet) >= 0) {
 if (packet.stream_index == audio_stream_index) {
 if (avcodec_send_packet(codec_ctx, &packet) == 0) {
 while (avcodec_receive_frame(codec_ctx, frame) == 0) {
 if (frame->pts != AV_NOPTS_VALUE) {
 frame->pts = av_rescale_q(frame->pts, codec_ctx->time_base, format_ctx->streams[audio_stream_index]->time_base);
 }

 uint8_t* output_buffer;
 int output_samples = av_rescale_rnd(
 swr_get_delay(swr_ctx, codec_ctx->sample_rate) + frame->nb_samples,
 codec_ctx->sample_rate, codec_ctx->sample_rate, AV_ROUND_UP);

 int output_buffer_size = av_samples_get_buffer_size(
 nullptr, 2, output_samples, AV_SAMPLE_FMT_S16, 1);

 output_buffer = (uint8_t*)av_malloc(output_buffer_size);

 if (output_buffer) {
 memset(output_buffer, 0, output_buffer_size); // Zero padding to avoid random noise
 int converted_samples = swr_convert(swr_ctx, &output_buffer, output_samples,
 (const uint8_t**)frame->extended_data, frame->nb_samples);

 if (converted_samples >= 0) {
 output.insert(output.end(), output_buffer, output_buffer + output_buffer_size);
 }
 else {
 std::cerr << "Error: Failed to convert audio samples." << std::endl;
 }
 // Make sure output_buffer is valid before freeing
 if (output_buffer != nullptr) {
 av_free(output_buffer);
 output_buffer = nullptr; // Prevent double-free
 }
 }
 else {
 std::cerr << "Error: Could not allocate output buffer." << std::endl;
 }
 }
 }
 else {
 std::cerr << "Error: Failed to send packet to codec context." << std::endl;
 }
 }
 av_packet_unref(&packet);
 }

 int frame_width = av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2; // Use 2 bytes per sample and 2 channels

 std::map metadata = {
 {"sample_width", 2}, // S16 format has 2 bytes per sample
 {"frame_rate", codec_ctx->sample_rate}, // Use the input sample rate
 {"channels", 2}, // Assuming stereo output
 {"frame_width", frame_width}
 };

 av_frame_free(&frame);
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);

 return AudioSegment(static_cast<const>(output.data()), output.size(), metadata);
}






std::ofstream AudioSegment::export_segment(const std::string& out_f,
 const std::string& format,
 const std::string& codec,
 const std::string& bitrate,
 const std::vector& parameters,
 const std::map& tags,
 const std::string& id3v2_version,
 const std::string& cover) {

 av_log_set_level(AV_LOG_DEBUG);
 AVCodecContext* codec_ctx = nullptr;
 AVFormatContext* format_ctx = nullptr;
 AVStream* stream = nullptr;
 AVFrame* frame = nullptr;
 AVPacket* pkt = nullptr;
 SwrContext* swr_ctx = nullptr;
 int ret;

 // Initialize format context
 if (avformat_alloc_output_context2(&format_ctx, nullptr, format.c_str(), out_f.c_str()) < 0) {
 throw std::runtime_error("Could not allocate format context.");
 }

 // Find encoder
 const AVCodec* codec_ptr = avcodec_find_encoder_by_name(codec.c_str());
 if (!codec_ptr) {
 throw std::runtime_error("Codec not found.");
 }

 // Add stream
 stream = avformat_new_stream(format_ctx, codec_ptr);
 if (!stream) {
 throw std::runtime_error("Failed to create new stream.");
 }

 // Allocate codec context
 codec_ctx = avcodec_alloc_context3(codec_ptr);
 if (!codec_ctx) {
 throw std::runtime_error("Could not allocate audio codec context.");
 }

 // Set codec parameters
 codec_ctx->bit_rate = std::stoi(bitrate);
 codec_ctx->sample_rate = this->get_frame_rate(); // Ensure this returns the correct sample rate
 av_channel_layout_default(&codec_ctx->ch_layout, 2);
 codec_ctx->sample_fmt = codec_ptr->sample_fmts ? codec_ptr->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;

 // Open codec
 if (avcodec_open2(codec_ctx, codec_ptr, nullptr) < 0) {
 throw std::runtime_error("Could not open codec.");
 }

 // Set codec parameters to the stream
 if (avcodec_parameters_from_context(stream->codecpar, codec_ctx) < 0) {
 throw std::runtime_error("Could not initialize stream codec parameters.");
 }

 // Open output file
 std::ofstream out_file(out_f, std::ios::binary);
 if (!out_file) {
 throw std::runtime_error("Failed to open output file.");
 }

 if (!(format_ctx->oformat->flags & AVFMT_NOFILE)) {
 if (avio_open(&format_ctx->pb, out_f.c_str(), AVIO_FLAG_WRITE) < 0) {
 throw std::runtime_error("Could not open output file.");
 }
 }

 // Write file header
 if (avformat_write_header(format_ctx, nullptr) < 0) {
 throw std::runtime_error("Error occurred when opening output file.");
 }

 // Initialize packet
 pkt = av_packet_alloc();
 if (!pkt) {
 throw std::runtime_error("Could not allocate AVPacket.");
 }

 // Initialize frame
 frame = av_frame_alloc();
 if (!frame) {
 throw std::runtime_error("Could not allocate AVFrame.");
 }
 frame->nb_samples = codec_ctx->frame_size;
 frame->format = codec_ctx->sample_fmt;
 frame->ch_layout = codec_ctx->ch_layout;

 // Allocate data buffer
 if (av_frame_get_buffer(frame, 0) < 0) {
 throw std::runtime_error("Could not allocate audio data buffers.");
 }

 // Initialize SwrContext for resampling
 swr_ctx = swr_alloc();
 if (!swr_ctx) {
 throw std::runtime_error("Could not allocate SwrContext.");
 }

 // Set options for resampling
 av_opt_set_chlayout(swr_ctx, "in_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_chlayout(swr_ctx, "out_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_int(swr_ctx, "in_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_int(swr_ctx, "out_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0); // Assuming input is S16
 av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", codec_ctx->sample_fmt, 0);

 // Initialize the resampling context
 if (swr_init(swr_ctx) < 0) {
 throw std::runtime_error("Failed to initialize SwrContext.");
 }

 int samples_read = 0;
 int total_samples = data_.size() / (av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2); // Assuming input is stereo

 while (samples_read < total_samples) {
 if (av_frame_make_writable(frame) < 0) {
 throw std::runtime_error("Frame not writable.");
 }

 int num_samples = std::min(codec_ctx->frame_size, total_samples - samples_read);

 // Prepare input data
 const uint8_t* input_data[2] = { reinterpret_cast<const>(data_.data() + samples_read * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2), nullptr };
 int output_samples = swr_convert(swr_ctx, frame->data, frame->nb_samples,
 input_data, num_samples);

 if (output_samples < 0) {
 throw std::runtime_error("Error converting audio samples.");
 }

 frame->nb_samples = output_samples;

 // Send the frame for encoding
 if (avcodec_send_frame(codec_ctx, frame) < 0) {
 throw std::runtime_error("Error sending frame for encoding.");
 }

 // Receive and write packets
 while (avcodec_receive_packet(codec_ctx, pkt) >= 0) {
 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 samples_read += num_samples;
 }

 // Flush the encoder
 if (avcodec_send_frame(codec_ctx, nullptr) < 0) {
 throw std::runtime_error("Error flushing the encoder.");
 }

 while (avcodec_receive_packet(codec_ctx, pkt) >= 0) {
 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 // Write file trailer
 av_write_trailer(format_ctx);

 // Cleanup
 av_frame_free(&frame);
 av_packet_free(&pkt);
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);

 if (!(format_ctx->oformat->flags & AVFMT_NOFILE)) {
 avio_closep(&format_ctx->pb);
 }
 avformat_free_context(format_ctx);

 out_file.close();
 return out_file;
}



</const></const></char>

I have no run time error but i see this message in console :


[file @ 0000018979db7180] Setting default whitelist 'file,crypto,data'
[SWR @ 000001897bcc4300] Using s16p internally between filters
[libmp3lame @ 0000018979d99b00] Trying to remove 431 more samples than there are in the queue
[AVIOContext @ 0000018979d983c0] Statistics: 670 bytes written, 0 seeks, 1 writeouts


I can play the exported mp3 file and the audio quallity is excellent (now).


But how to fix : Trying to remove 431 more samples than there are in the queue warning-error ?


-
FFmpeg Hardware Acceleration with NVENC produces Half Green output video
17 juin 2016, par Dan SandlandUsing the FFmpeg build found here : https://github.com/illuspas/ffmpeg-hw-win32
gcc 5.3.0
--enable-nvenc nvidia_video_sdk_6.0.1
--enable-libmfx Intel(R)_Media_SDK_2016.0.1
--enable-libfdk-aac 0.1.4
--enable-libspeex 1.2rc1
--enable-libx264 1:148.20150725
--enable-libopenh264 1.5.0
--enable-libx265 1.8
--enable-libopus 1.1.2
--enable-libmp3lame 3.99.5
--enable-libkvazaar 0.8.2./configure —prefix=/home/aliang/FFmpeg/x86_64 —enable-small —disable-debug —disable-doc —arch=x86_64 —cc=’ccache x86_64-w64-mingw32-gcc’ —cross-prefix=x86_64-w64-mingw32- —enable-cross-compile —target-os=mingw32 —enable-libfdk-aac —enable-libmp3lame —enable-libopus —enable-libspeex —enable-libx264 —enable-libx265 —enable-libmfx —enable-nvenc —enable-libopenh264 —enable-libkvazaar —enable-gpl —enable-nonfree
I’m running Windows on a MacBook Pro. I also tried with a more recent build and had the same output.
Input video is from sample-videos.com.
The ffmpeg command I am running is :
ffmpeg -y -i sample.mp4 -vcodec nvenc_h264 -pixel_format yuv420p -f mp4 sample-out-nvenc.mp4sample-out-nvenc.mp4 looks like this via ffplay or vlc :
When I grab a frame using jpeg2, the colors appear normal, but the height is squished.
ffmpeg -y -ss 15.5 -i sample.mp4 -vframes 1 -s 480x300 -f image2 grab.jpg
The ffprobe results for the output (sample-out-nvenc.mp4) :
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'sample-out-nvenc.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf57.25.100
Duration: 00:00:31.02, start: 0.021333, bitrate: 1994 kb/s
Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p(tv), 640x480 [SAR 1:1 DAR 4:3], 1650 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)
Metadata:
handler_name : VideoHandler
Stream #0:1(und): Audio: aac (mp4a / 0x6134706D), 48000 Hz, 5.1, fltp, 342 kb/s (default)
Metadata:
handler_name : SoundHandlerLastly the output from the nvenc encoding command :
ffmpeg -y -i sample.mp4 -vcodec nvenc_h264 -pixel_format yuv420p -f mp4 sample-out-nvenc.mp4
ffmpeg version 3.0 Copyright (c) 2000-2016 the FFmpeg developers
built with gcc 5.3.0 (GCC)
configuration: --prefix=/home/aliang/FFmpeg/x86_64 --enable-small --disable-debug --disable-doc --arch=x86_64 --cc='ccache x86_64-w64-mingw32-gcc' --cross-prefix=x86_64-w64-mingw32- --enable-cross-compile --target-os=mingw32 --enable-libfdk-aac --enable-libmp3lame --enable-libopus --enable-libspeex --enable-libx264 --enable-libx265 --enable-libmfx --enable-nvenc --enable-libopenh264 --enable-libkvazaar --enable-gpl --enable-nonfree
libavutil 55. 17.103 / 55. 17.103
libavcodec 57. 24.102 / 57. 24.102
libavformat 57. 25.100 / 57. 25.100
libavdevice 57. 0.101 / 57. 0.101
libavfilter 6. 31.100 / 6. 31.100
libswscale 4. 0.100 / 4. 0.100
libswresample 2. 0.101 / 2. 0.101
libpostproc 54. 0.100 / 54. 0.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'sample.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
creation_time : 1970-01-01 00:00:00
encoder : Lavf53.24.2
Duration: 00:00:31.00, start: 0.000000, bitrate: 1353 kb/s
Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p, 640x480 [SAR 1:1 DAR 4:3], 966 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)
Metadata:
creation_time : 1970-01-01 00:00:00
handler_name : VideoHandler
Stream #0:1(und): Audio: aac (mp4a / 0x6134706D), 48000 Hz, 5.1, fltp, 383 kb/s (default)
Metadata:
creation_time : 1970-01-01 00:00:00
handler_name : SoundHandler
Output #0, mp4, to 'sample-out-nvenc.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf57.25.100
Stream #0:0(und): Video: h264 (nvenc_h264) ([33][0][0][0] / 0x0021), yuv420p, 640x480 [SAR 1:1 DAR 4:3], q=-1--1, 2000 kb/s, 25 fps, 12800 tbn, 25 tbc (default)
Metadata:
creation_time : 1970-01-01 00:00:00
handler_name : VideoHandler
encoder : Lavc57.24.102 nvenc_h264
Side data:
unknown side data type 10 (24 bytes)
Stream #0:1(und): Audio: aac ([64][0][0][0] / 0x0040), 48000 Hz, 5.1, fltp, 341 kb/s (default)
Metadata:
creation_time : 1970-01-01 00:00:00
handler_name : SoundHandler
encoder : Lavc57.24.102 aac
Stream mapping:
Stream #0:0 -> #0:0 (h264 (native) -> h264 (nvenc_h264))
Stream #0:1 -> #0:1 (aac (native) -> aac (native))
Press [q] to stop, [?] for help
frame= 774 fps=253 q=-0.0 Lsize= 7551kB time=00:00:30.99 bitrate=1995.6kbits/s speed=10.1x
video:6236kB audio:1297kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.243011%
[aac @ 000001cdd9900520] Qavg: 743.457 -
C++ ffmpeg lib version 7.0 - export audio to different format
4 septembre 2024, par Chris PI want to make a C++ lib named cppdub which will mimic the python module pydub.


One main function is to export the AudioSegment to a file with a specific format (example : mp3).


The code is :



AudioSegment AudioSegment::from_file(const std::string& file_path, const std::string& format, const std::string& codec,
 const std::map& parameters, int start_second, int duration) {

 avformat_network_init();
 av_log_set_level(AV_LOG_ERROR); // Adjust logging level as needed

 AVFormatContext* format_ctx = nullptr;
 if (avformat_open_input(&format_ctx, file_path.c_str(), nullptr, nullptr) != 0) {
 std::cerr << "Error: Could not open audio file." << std::endl;
 return AudioSegment(); // Return an empty AudioSegment on failure
 }

 if (avformat_find_stream_info(format_ctx, nullptr) < 0) {
 std::cerr << "Error: Could not find stream information." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 int audio_stream_index = -1;
 for (unsigned int i = 0; i < format_ctx->nb_streams; i++) {
 if (format_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
 audio_stream_index = i;
 break;
 }
 }

 if (audio_stream_index == -1) {
 std::cerr << "Error: Could not find audio stream." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVCodecParameters* codec_par = format_ctx->streams[audio_stream_index]->codecpar;
 const AVCodec* my_codec = avcodec_find_decoder(codec_par->codec_id);
 AVCodecContext* codec_ctx = avcodec_alloc_context3(my_codec);

 if (!codec_ctx) {
 std::cerr << "Error: Could not allocate codec context." << std::endl;
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_parameters_to_context(codec_ctx, codec_par) < 0) {
 std::cerr << "Error: Could not initialize codec context." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 if (avcodec_open2(codec_ctx, my_codec, nullptr) < 0) {
 std::cerr << "Error: Could not open codec." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 SwrContext* swr_ctx = swr_alloc();
 if (!swr_ctx) {
 std::cerr << "Error: Could not allocate SwrContext." << std::endl;
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }
 codec_ctx->sample_rate = 44100;
 // Set up resampling context to convert to S16 format with 2 bytes per sample
 av_opt_set_chlayout(swr_ctx, "in_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_int(swr_ctx, "in_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", codec_ctx->sample_fmt, 0);

 AVChannelLayout dst_ch_layout;
 av_channel_layout_copy(&dst_ch_layout, &codec_ctx->ch_layout);
 av_channel_layout_uninit(&dst_ch_layout);
 av_channel_layout_default(&dst_ch_layout, 2);

 av_opt_set_chlayout(swr_ctx, "out_chlayout", &dst_ch_layout, 0);
 av_opt_set_int(swr_ctx, "out_sample_rate", codec_ctx->sample_rate, 0); // Match input sample rate
 av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", AV_SAMPLE_FMT_S16, 0); // Force S16 format

 if (swr_init(swr_ctx) < 0) {
 std::cerr << "Error: Failed to initialize the resampling context" << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 AVPacket packet;
 AVFrame* frame = av_frame_alloc();
 if (!frame) {
 std::cerr << "Error: Could not allocate frame." << std::endl;
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);
 return AudioSegment();
 }

 std::vector<char> output;
 while (av_read_frame(format_ctx, &packet) >= 0) {
 if (packet.stream_index == audio_stream_index) {
 if (avcodec_send_packet(codec_ctx, &packet) == 0) {
 while (avcodec_receive_frame(codec_ctx, frame) == 0) {
 if (frame->pts != AV_NOPTS_VALUE) {
 frame->pts = av_rescale_q(frame->pts, codec_ctx->time_base, format_ctx->streams[audio_stream_index]->time_base);
 }

 uint8_t* output_buffer;
 int output_samples = av_rescale_rnd(
 swr_get_delay(swr_ctx, codec_ctx->sample_rate) + frame->nb_samples,
 codec_ctx->sample_rate, codec_ctx->sample_rate, AV_ROUND_UP);

 int output_buffer_size = av_samples_get_buffer_size(
 nullptr, 2, output_samples, AV_SAMPLE_FMT_S16, 1);

 output_buffer = (uint8_t*)av_malloc(output_buffer_size);

 if (output_buffer) {
 memset(output_buffer, 0, output_buffer_size); // Zero padding to avoid random noise
 int converted_samples = swr_convert(swr_ctx, &output_buffer, output_samples,
 (const uint8_t**)frame->extended_data, frame->nb_samples);

 if (converted_samples >= 0) {
 output.insert(output.end(), output_buffer, output_buffer + output_buffer_size);
 }
 else {
 std::cerr << "Error: Failed to convert audio samples." << std::endl;
 }
 // Make sure output_buffer is valid before freeing
 if (output_buffer != nullptr) {
 av_free(output_buffer);
 output_buffer = nullptr; // Prevent double-free
 }
 }
 else {
 std::cerr << "Error: Could not allocate output buffer." << std::endl;
 }
 }
 }
 else {
 std::cerr << "Error: Failed to send packet to codec context." << std::endl;
 }
 }
 av_packet_unref(&packet);
 }

 int frame_width = av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2; // Use 2 bytes per sample and 2 channels

 std::map metadata = {
 {"sample_width", 2}, // S16 format has 2 bytes per sample
 {"frame_rate", codec_ctx->sample_rate}, // Use the input sample rate
 {"channels", 2}, // Assuming stereo output
 {"frame_width", frame_width}
 };

 av_frame_free(&frame);
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);
 avformat_close_input(&format_ctx);

 return AudioSegment(static_cast<const>(output.data()), output.size(), metadata);
}









std::ofstream AudioSegment::export_segment(const std::string& out_f,
 const std::string& format,
 const std::string& codec,
 const std::string& bitrate,
 const std::vector& parameters,
 const std::map& tags,
 const std::string& id3v2_version,
 const std::string& cover) {

 av_log_set_level(AV_LOG_DEBUG);
 AVCodecContext* codec_ctx = nullptr;
 AVFormatContext* format_ctx = nullptr;
 AVStream* stream = nullptr;
 AVFrame* frame = nullptr;
 AVPacket* pkt = nullptr;
 SwrContext* swr_ctx = nullptr;
 int ret;

 // Initialize format context
 if (avformat_alloc_output_context2(&format_ctx, nullptr, format.c_str(), out_f.c_str()) < 0) {
 throw std::runtime_error("Could not allocate format context.");
 }

 // Find encoder
 const AVCodec* codec_ptr = avcodec_find_encoder_by_name(codec.c_str());
 if (!codec_ptr) {
 throw std::runtime_error("Codec not found.");
 }

 // Add stream
 stream = avformat_new_stream(format_ctx, codec_ptr);
 if (!stream) {
 throw std::runtime_error("Failed to create new stream.");
 }

 // Allocate codec context
 codec_ctx = avcodec_alloc_context3(codec_ptr);
 if (!codec_ctx) {
 throw std::runtime_error("Could not allocate audio codec context.");
 }

 // Set codec parameters
 codec_ctx->bit_rate = std::stoi(bitrate);
 codec_ctx->sample_rate = this->get_frame_rate(); // Ensure this returns the correct sample rate
 av_channel_layout_default(&codec_ctx->ch_layout, 2);
 codec_ctx->sample_fmt = codec_ptr->sample_fmts ? codec_ptr->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;

 // Open codec
 if (avcodec_open2(codec_ctx, codec_ptr, nullptr) < 0) {
 throw std::runtime_error("Could not open codec.");
 }

 // Set codec parameters to the stream
 if (avcodec_parameters_from_context(stream->codecpar, codec_ctx) < 0) {
 throw std::runtime_error("Could not initialize stream codec parameters.");
 }

 // Open output file
 std::ofstream out_file(out_f, std::ios::binary);
 if (!out_file) {
 throw std::runtime_error("Failed to open output file.");
 }

 if (!(format_ctx->oformat->flags & AVFMT_NOFILE)) {
 if (avio_open(&format_ctx->pb, out_f.c_str(), AVIO_FLAG_WRITE) < 0) {
 throw std::runtime_error("Could not open output file.");
 }
 }

 // Write file header
 if (avformat_write_header(format_ctx, nullptr) < 0) {
 throw std::runtime_error("Error occurred when opening output file.");
 }

 // Initialize packet
 pkt = av_packet_alloc();
 if (!pkt) {
 throw std::runtime_error("Could not allocate AVPacket.");
 }

 // Initialize frame
 frame = av_frame_alloc();
 if (!frame) {
 throw std::runtime_error("Could not allocate AVFrame.");
 }
 frame->nb_samples = codec_ctx->frame_size;
 frame->format = codec_ctx->sample_fmt;
 frame->ch_layout = codec_ctx->ch_layout;

 // Allocate data buffer
 if (av_frame_get_buffer(frame, 0) < 0) {
 throw std::runtime_error("Could not allocate audio data buffers.");
 }

 // Initialize SwrContext for resampling
 swr_ctx = swr_alloc();
 if (!swr_ctx) {
 throw std::runtime_error("Could not allocate SwrContext.");
 }

 // Set options for resampling
 av_opt_set_chlayout(swr_ctx, "in_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_chlayout(swr_ctx, "out_chlayout", &codec_ctx->ch_layout, 0);
 av_opt_set_int(swr_ctx, "in_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_int(swr_ctx, "out_sample_rate", codec_ctx->sample_rate, 0);
 av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0); // Assuming input is S16
 av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", codec_ctx->sample_fmt, 0);

 // Initialize the resampling context
 if (swr_init(swr_ctx) < 0) {
 throw std::runtime_error("Failed to initialize SwrContext.");
 }

 int samples_read = 0;
 int total_samples = data_.size() / (av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2); // Assuming input is stereo

 while (samples_read < total_samples) {
 if (av_frame_make_writable(frame) < 0) {
 throw std::runtime_error("Frame not writable.");
 }

 int num_samples = std::min(codec_ctx->frame_size, total_samples - samples_read);

 // Prepare input data
 const uint8_t* input_data[2] = { reinterpret_cast<const>(data_.data() + samples_read * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * 2), nullptr };
 int output_samples = swr_convert(swr_ctx, frame->data, frame->nb_samples,
 input_data, num_samples);

 if (output_samples < 0) {
 throw std::runtime_error("Error converting audio samples.");
 }

 frame->nb_samples = output_samples;

 // Send the frame for encoding
 if (avcodec_send_frame(codec_ctx, frame) < 0) {
 throw std::runtime_error("Error sending frame for encoding.");
 }

 // Receive and write packets
 while (avcodec_receive_packet(codec_ctx, pkt) >= 0) {
 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 samples_read += num_samples;
 }

 // Flush the encoder
 if (avcodec_send_frame(codec_ctx, nullptr) < 0) {
 throw std::runtime_error("Error flushing the encoder.");
 }

 while (avcodec_receive_packet(codec_ctx, pkt) >= 0) {
 out_file.write(reinterpret_cast(pkt->data), pkt->size);
 av_packet_unref(pkt);
 }

 // Write file trailer
 av_write_trailer(format_ctx);

 // Cleanup
 av_frame_free(&frame);
 av_packet_free(&pkt);
 swr_free(&swr_ctx);
 avcodec_free_context(&codec_ctx);

 if (!(format_ctx->oformat->flags & AVFMT_NOFILE)) {
 avio_closep(&format_ctx->pb);
 }
 avformat_free_context(format_ctx);

 out_file.close();
 return out_file;
}

//declaration
/*
std::ofstream export_segment(const std::string& out_f,
 const std::string& format = "mp3",
 const std::string& codec = "libmp3lame",
 const std::string& bitrate = "128000",
 const std::vector& parameters = {},
 const std::map& tags = {},
 const std::string& id3v2_version = "4",
 const std::string& cover = "");
*/
</const></const></char>

This code only works for mp3 format. I also want to export to aac,ogg,flv,wav and any other popular formats.


Syndiquer tout le site
