Skip to content

Instantly share code, notes, and snippets.

@Suhail
Last active Jan 21, 2020
Embed
What would you like to do?
/*
I am sending encode(uint8_t, int, void *) data from a 12 MB file then calling a flush. This is the output I get:
Attempting to capture audio from a file...
Initializing encoder...
sample rate: 48000
Read 12292096 bytes from a file
------------------------------------------
Size of in_linesize: 12292096
out_samples: 1
Size of out resampled converted data: 128
Encoding...
You need to keep sending data.
Encoding...
Received new encoded data of size 146 bytes
Received new encoded data of size 6 bytes
You need to keep sending data.
It writes to a file after where test.m4a is 2 bytes for some reason
*/
#include "encode.h"
extern "C" {
#include <libavcodec/avcodec.h>
#include <libavresample/avresample.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/frame.h>
#include <libavutil/opt.h>
#include <libavutil/samplefmt.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
}
namespace ffmpeg_encode {
const AVCodec *codec;
AVCodecContext *c = NULL;
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(const AVCodec *codec,
enum AVSampleFormat sample_fmt) {
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt) return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(const AVCodec *codec) {
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates) return 44100;
p = codec->supported_samplerates;
while (*p) {
if (!best_samplerate || abs(44100 - *p) < abs(44100 - best_samplerate))
best_samplerate = *p;
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(const AVCodec *codec) {
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channels = 0;
if (!codec->channel_layouts) return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channels) {
best_ch_layout = *p;
best_nb_channels = nb_channels;
}
p++;
}
return best_ch_layout;
}
static void encode(AVCodecContext *ctx, AVFrame *frame, AVPacket *pkt,
void (*callback)(uint8_t *, int)) {
printf("Encoding...\n");
int ret;
/* send the frame for encoding */
ret = avcodec_send_frame(ctx, frame);
if (ret < 0) {
fprintf(stderr, "Error sending the frame to the encoder\n");
exit(1);
}
/* read all the available output packets (in general there may be any
* number of them */
while (ret >= 0) {
ret = avcodec_receive_packet(ctx, pkt);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
printf("You need to keep sending data.\n");
} else if (ret < 0) {
fprintf(stderr, "Error encoding audio frame\n");
exit(1);
} else if (ret == 0 && pkt->size > 0) {
callback(pkt->data, pkt->size);
}
av_packet_unref(pkt);
}
}
void init() {
printf("Initializing encoder...\n");
/* register all the codecs */
avcodec_register_all();
/* find the MP2 encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_AAC);
if (!codec) {
printf("Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
printf("Could not allocate audio codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 64000;
/* check that the encoder supports s16 pcm input */
c->sample_fmt = AV_SAMPLE_FMT_FLTP;
// c->profile = FF_PROFILE_AAC_MAIN;
if (!check_sample_fmt(codec, c->sample_fmt)) {
printf("Encoder does not support sample format %s\n",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
// printf("encoder format set: %d\n", c->sample_fmt);
/* select other audio parameters supported by the encoder */
c->sample_rate = select_sample_rate(codec);
c->sample_rate = 48000;
printf("sample rate: %d\n", c->sample_rate);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
}
int encode(uint8_t *data, int size, void (*callback)(uint8_t *, int)) {
AVFrame *frame = nullptr;
AVPacket *pkt = nullptr;
int ret;
uint16_t *samples = nullptr;
printf("------------------------------------------\n");
if (!c) {
printf("Error: Need to initialize codec context\n");
return -1;
}
if (callback == nullptr) {
printf("Please provide a callback\n");
return -1;
}
if (data == nullptr) {
printf("no data\n");
return -1;
}
/* packet for holding encoded output */
pkt = av_packet_alloc();
if (!pkt) {
fprintf(stderr, "could not allocate the packet\n");
exit(1);
}
/* frame containing input raw audio */
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
/* allocate the data buffers */
ret = av_frame_get_buffer(frame, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate audio data buffers\n");
exit(1);
}
ret = av_frame_make_writable(frame);
if (ret < 0) {
printf("Error: frame not writable\n");
exit(1);
}
/* Convert from planar to interleaved */
AVAudioResampleContext *avr = avresample_alloc_context();
if (!avr) {
printf("Error: Could not initialize resample context\n");
return 0;
}
AVSampleFormat in_sample_fmt = AV_SAMPLE_FMT_FLT;
AVSampleFormat out_sample_fmt = AV_SAMPLE_FMT_FLTP;
av_opt_set_int(avr, "in_channel_layout", AV_CH_LAYOUT_STEREO, 0);
av_opt_set_int(avr, "out_channel_layout", AV_CH_LAYOUT_STEREO, 0);
av_opt_set_int(avr, "in_sample_rate", 48000, 0);
av_opt_set_int(avr, "out_sample_rate", 48000, 0);
av_opt_set_int(avr, "in_sample_fmt", in_sample_fmt, 0); // Interleaved
av_opt_set_int(avr, "out_sample_fmt", out_sample_fmt,
0); // Non-interleaved
if (avresample_open(avr) < 0) {
printf("Error: Could not open resample context\n");
return 0;
}
uint8_t **input = nullptr;
int in_linesize = 0, in_samples = 0;
uint8_t *output = nullptr;
int out_linesize;
input = &data;
in_samples = 1; // maybe?
in_linesize = size;
printf("Size of in_linesize: %d\n", in_linesize);
int out_samples = avresample_get_out_samples(avr, in_samples);
av_samples_alloc(&output, &out_linesize, 2, out_samples, out_sample_fmt, 0);
// TODO: Don't allow in_linesize to be 0 avoiding optimizations
out_samples = avresample_convert(avr, &output, out_linesize, out_samples,
input, 0, in_samples);
printf("out_samples: %d\n", out_samples);
printf("Size of out resampled converted data: %d\n", out_linesize);
while (avresample_available(avr) > 0) {
printf("reading...\n");
avresample_read(avr, &output, out_samples);
}
/* encode an audio chunk */
samples = (uint16_t *)frame->data[0];
memcpy(samples, output, out_linesize);
encode(c, frame, pkt, callback);
/* flush the encoder */
encode(c, NULL, pkt, callback);
av_frame_free(&frame);
av_packet_free(&pkt);
/* For resampling */
av_freep(&output);
if (avr) avresample_close(avr);
return 0;
}
void destroy() { avcodec_free_context(&c); }
} // namespace ffmpeg_encode
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment