examples/muxing: add support to audio resampling

Allows to encode to output in case the destination sample format is
different from AV_SAMPLE_FMT_S16.

1 files changed, 93 insertions, 28 deletions

diff --git a/doc/examples/muxing.c b/doc/examples/muxing.c
index c4ffee8cfc..a8f979f4be 100644
--- a/doc/examples/muxing.c
+++ b/doc/examples/muxing.c
@@ -34,9 +34,11 @@
 #include <string.h>
 #include <math.h>
 
+#include <libavutil/opt.h>
 #include <libavutil/mathematics.h>
 #include <libavformat/avformat.h>
 #include <libswscale/swscale.h>
+#include <libswresample/swresample.h>
 
 /* 5 seconds stream duration */
 #define STREAM_DURATION   200.0
@@ -46,13 +48,6 @@
 
 static int sws_flags = SWS_BICUBIC;
 
-/**************************************************************/
-/* audio output */
-
-static float t, tincr, tincr2;
-static int16_t *samples;
-static int audio_input_frame_size;
-
 /* Add an output stream. */
 static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
                             enum AVCodecID codec_id)
@@ -78,7 +73,7 @@ static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
 
     switch ((*codec)->type) {
     case AVMEDIA_TYPE_AUDIO:
-        c->sample_fmt  = AV_SAMPLE_FMT_S16;
+        c->sample_fmt  = AV_SAMPLE_FMT_FLTP;
         c->bit_rate    = 64000;
         c->sample_rate = 44100;
         c->channels    = 2;
@@ -126,8 +121,17 @@ static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
 /* audio output */
 
 static float t, tincr, tincr2;
-static int16_t *samples;
-static int audio_input_frame_size;
+
+static uint8_t **src_samples_data;
+static int       src_samples_linesize;
+static int       src_nb_samples;
+
+static int max_dst_nb_samples;
+uint8_t **dst_samples_data;
+int       dst_samples_linesize;
+int       dst_samples_size;
+
+struct SwrContext *swr_ctx = NULL;
 
 static void open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
 {
@@ -149,17 +153,51 @@ static void open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
     /* increment frequency by 110 Hz per second */
     tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
 
-    if (c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)
-        audio_input_frame_size = 10000;
-    else
-        audio_input_frame_size = c->frame_size;
-    samples = av_malloc(audio_input_frame_size *
-                        av_get_bytes_per_sample(c->sample_fmt) *
-                        c->channels);
-    if (!samples) {
-        fprintf(stderr, "Could not allocate audio samples buffer\n");
+    src_nb_samples = c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE ?
+        10000 : c->frame_size;
+
+    ret = av_samples_alloc_array_and_samples(&src_samples_data, &src_samples_linesize, c->channels,
+                                             src_nb_samples, c->sample_fmt, 0);
+    if (ret < 0) {
+        fprintf(stderr, "Could not allocate source samples\n");
+        exit(1);
+    }
+
+    /* create resampler context */
+    if (c->sample_fmt != AV_SAMPLE_FMT_S16) {
+        swr_ctx = swr_alloc();
+        if (!swr_ctx) {
+            fprintf(stderr, "Could not allocate resampler context\n");
+            exit(1);
+        }
+
+        /* set options */
+        av_opt_set_int       (swr_ctx, "in_channel_count",   c->channels,       0);
+        av_opt_set_int       (swr_ctx, "in_sample_rate",     c->sample_rate,    0);
+        av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt",      AV_SAMPLE_FMT_S16, 0);
+        av_opt_set_int       (swr_ctx, "out_channel_count",  c->channels,       0);
+        av_opt_set_int       (swr_ctx, "out_sample_rate",    c->sample_rate,    0);
+        av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt",     c->sample_fmt,     0);
+
+        /* initialize the resampling context */
+        if ((ret = swr_init(swr_ctx)) < 0) {
+            fprintf(stderr, "Failed to initialize the resampling context\n");
+            exit(1);
+        }
+    }
+
+    /* compute the number of converted samples: buffering is avoided
+     * ensuring that the output buffer will contain at least all the
+     * converted input samples */
+    max_dst_nb_samples = src_nb_samples;
+    ret = av_samples_alloc_array_and_samples(&dst_samples_data, &dst_samples_linesize, c->channels,
+                                             max_dst_nb_samples, c->sample_fmt, 0);
+    if (ret < 0) {
+        fprintf(stderr, "Could not allocate destination samples\n");
         exit(1);
     }
+    dst_samples_size = av_samples_get_buffer_size(NULL, c->channels, max_dst_nb_samples,
+                                                  c->sample_fmt, 0);
 }
 
 /* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
@@ -184,18 +222,45 @@ static void write_audio_frame(AVFormatContext *oc, AVStream *st)
     AVCodecContext *c;
     AVPacket pkt = { 0 }; // data and size must be 0;
     AVFrame *frame = avcodec_alloc_frame();
-    int got_packet, ret;
+    int got_packet, ret, dst_nb_samples;
 
     av_init_packet(&pkt);
     c = st->codec;
 
-    get_audio_frame(samples, audio_input_frame_size, c->channels);
-    frame->nb_samples = audio_input_frame_size;
+    get_audio_frame((int16_t *)src_samples_data[0], src_nb_samples, c->channels);
+
+    /* convert samples from native format to destination codec format, using the resampler */
+    if (swr_ctx) {
+        /* compute destination number of samples */
+        dst_nb_samples = av_rescale_rnd(swr_get_delay(swr_ctx, c->sample_rate) + src_nb_samples,
+                                        c->sample_rate, c->sample_rate, AV_ROUND_UP);
+        if (dst_nb_samples > max_dst_nb_samples) {
+            av_free(dst_samples_data[0]);
+            ret = av_samples_alloc(dst_samples_data, &dst_samples_linesize, c->channels,
+                                   dst_nb_samples, c->sample_fmt, 0);
+            if (ret < 0)
+                exit(1);
+            max_dst_nb_samples = dst_nb_samples;
+            dst_samples_size = av_samples_get_buffer_size(NULL, c->channels, dst_nb_samples,
+                                                          c->sample_fmt, 0);
+        }
+
+        /* convert to destination format */
+        ret = swr_convert(swr_ctx,
+                          dst_samples_data, dst_nb_samples,
+                          (const uint8_t **)src_samples_data, src_nb_samples);
+        if (ret < 0) {
+            fprintf(stderr, "Error while converting\n");
+            exit(1);
+        }
+    } else {
+        dst_samples_data[0] = src_samples_data[0];
+        dst_nb_samples = src_nb_samples;
+    }
+
+    frame->nb_samples = dst_nb_samples;
     avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
-                             (uint8_t *)samples,
-                             audio_input_frame_size *
-                             av_get_bytes_per_sample(c->sample_fmt) *
-                             c->channels, 1);
+                             dst_samples_data[0], dst_samples_size, 0);
 
     ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
     if (ret < 0) {
@@ -221,8 +286,8 @@ static void write_audio_frame(AVFormatContext *oc, AVStream *st)
 static void close_audio(AVFormatContext *oc, AVStream *st)
 {
     avcodec_close(st->codec);
-
-    av_free(samples);
+    av_free(src_samples_data[0]);
+    av_free(dst_samples_data[0]);
 }
 
 /**************************************************************/