lavc: pad last audio frame with silence when needed.

4 files changed, 74 insertions, 8 deletions

diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h
index bec13e7c1a..102df3a7a0 100644
--- a/libavcodec/avcodec.h
+++ b/libavcodec/avcodec.h
@@ -3860,15 +3860,11 @@ int attribute_deprecated avcodec_encode_audio(AVCodecContext *avctx,
  * @param[in] frame AVFrame containing the raw audio data to be encoded.
  *                  May be NULL when flushing an encoder that has the
  *                  CODEC_CAP_DELAY capability set.
- *                  There are 2 codec capabilities that affect the allowed
- *                  values of frame->nb_samples.
- *                  If CODEC_CAP_SMALL_LAST_FRAME is set, then only the final
- *                  frame may be smaller than avctx->frame_size, and all other
- *                  frames must be equal to avctx->frame_size.
  *                  If CODEC_CAP_VARIABLE_FRAME_SIZE is set, then each frame
  *                  can have any number of samples.
- *                  If neither is set, frame->nb_samples must be equal to
- *                  avctx->frame_size for all frames.
+ *                  If it is not set, frame->nb_samples must be equal to
+ *                  avctx->frame_size for all frames except the last.
+ *                  The final frame may be smaller than avctx->frame_size.
  * @param[out] got_packet_ptr This field is set to 1 by libavcodec if the
  *                            output packet is non-empty, and to 0 if it is
  *                            empty. If the function returns an error, the
diff --git a/libavcodec/internal.h b/libavcodec/internal.h
index bedb2ed85d..57d551d850 100644
--- a/libavcodec/internal.h
+++ b/libavcodec/internal.h
@@ -70,6 +70,12 @@ typedef struct AVCodecInternal {
      */
     int sample_count;
 #endif
+
+    /**
+     * An audio frame with less than required samples has been submitted and
+     * padded with silence. Reject all subsequent frames.
+     */
+    int last_audio_frame;
 } AVCodecInternal;
 
 struct AVCodecDefault {
diff --git a/libavcodec/utils.c b/libavcodec/utils.c
index ca386646c3..9631c99899 100644
--- a/libavcodec/utils.c
+++ b/libavcodec/utils.c
@@ -857,11 +857,58 @@ int ff_alloc_packet(AVPacket *avpkt, int size)
     }
 }
 
+/**
+ * Pad last frame with silence.
+ */
+static int pad_last_frame(AVCodecContext *s, AVFrame **dst, const AVFrame *src)
+{
+    AVFrame *frame = NULL;
+    uint8_t *buf   = NULL;
+    int ret;
+
+    if (!(frame = avcodec_alloc_frame()))
+        return AVERROR(ENOMEM);
+    *frame = *src;
+
+    if ((ret = av_samples_get_buffer_size(&frame->linesize[0], s->channels,
+                                          s->frame_size, s->sample_fmt, 0)) < 0)
+        goto fail;
+
+    if (!(buf = av_malloc(ret))) {
+        ret = AVERROR(ENOMEM);
+        goto fail;
+    }
+
+    frame->nb_samples = s->frame_size;
+    if ((ret = avcodec_fill_audio_frame(frame, s->channels, s->sample_fmt,
+                                        buf, ret, 0)) < 0)
+        goto fail;
+    if ((ret = av_samples_copy(frame->extended_data, src->extended_data, 0, 0,
+                               src->nb_samples, s->channels, s->sample_fmt)) < 0)
+        goto fail;
+    if ((ret = av_samples_set_silence(frame->extended_data, src->nb_samples,
+                                      frame->nb_samples - src->nb_samples,
+                                      s->channels, s->sample_fmt)) < 0)
+        goto fail;
+
+    *dst = frame;
+
+    return 0;
+
+fail:
+    if (frame->extended_data != frame->data)
+        av_freep(&frame->extended_data);
+    av_freep(&buf);
+    av_freep(&frame);
+    return ret;
+}
+
 int attribute_align_arg avcodec_encode_audio2(AVCodecContext *avctx,
                                               AVPacket *avpkt,
                                               const AVFrame *frame,
                                               int *got_packet_ptr)
 {
+    AVFrame *padded_frame = NULL;
     int ret;
     int user_packet = !!avpkt->data;
 
@@ -879,6 +926,16 @@ int attribute_align_arg avcodec_encode_audio2(AVCodecContext *avctx,
             if (frame->nb_samples > avctx->frame_size)
                 return AVERROR(EINVAL);
         } else if (!(avctx->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)) {
+            if (frame->nb_samples < avctx->frame_size &&
+                !avctx->internal->last_audio_frame) {
+                ret = pad_last_frame(avctx, &padded_frame, frame);
+                if (ret < 0)
+                    return ret;
+
+                frame = padded_frame;
+                avctx->internal->last_audio_frame = 1;
+            }
+
             if (frame->nb_samples != avctx->frame_size)
                 return AVERROR(EINVAL);
         }
@@ -919,6 +976,13 @@ int attribute_align_arg avcodec_encode_audio2(AVCodecContext *avctx,
              here to simplify things */
     avpkt->flags |= AV_PKT_FLAG_KEY;
 
+    if (padded_frame) {
+        av_freep(&padded_frame->data[0]);
+        if (padded_frame->extended_data != padded_frame->data)
+            av_freep(&padded_frame->extended_data);
+        av_freep(&padded_frame);
+    }
+
     return ret;
 }
 
diff --git a/libavcodec/version.h b/libavcodec/version.h
index be39f4ffca..da7796abb0 100644
--- a/libavcodec/version.h
+++ b/libavcodec/version.h
@@ -28,7 +28,7 @@
 
 #define LIBAVCODEC_VERSION_MAJOR 54
 #define LIBAVCODEC_VERSION_MINOR 13
-#define LIBAVCODEC_VERSION_MICRO  0
+#define LIBAVCODEC_VERSION_MICRO  1
 
 #define LIBAVCODEC_VERSION_INT  AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \
                                                LIBAVCODEC_VERSION_MINOR, \