mpegvideo_enc: Fix encoding videos with less frames than the delay of the encoder

When the encoder is fed with less frames than its delay, the picture list
looks like { NULL, NULL, ..., frame, frame, frame }. When flushing the
encoder (input frame == NULL), we need to ensure the picture list is
shifted enough so that we do not return an empty packet, which would
mean the encoder has finished, while it has not encoded any frame.

Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>

1 files changed, 16 insertions, 4 deletions

diff --git a/libavcodec/mpegvideo_enc.c b/libavcodec/mpegvideo_enc.c
index 9dd30e6a2d..44c93953c3 100644
--- a/libavcodec/mpegvideo_enc.c
+++ b/libavcodec/mpegvideo_enc.c
@@ -962,8 +962,9 @@ static int load_input_picture(MpegEncContext *s, const AVFrame *pic_arg)
     Picture *pic = NULL;
     int64_t pts;
     int i, display_picture_number = 0, ret;
-    const int encoding_delay = s->max_b_frames ? s->max_b_frames :
-                                                 (s->low_delay ? 0 : 1);
+    int encoding_delay = s->max_b_frames ? s->max_b_frames
+                                         : (s->low_delay ? 0 : 1);
+    int flush_offset = 1;
     int direct = 1;
 
     if (pic_arg) {
@@ -1075,11 +1076,22 @@ static int load_input_picture(MpegEncContext *s, const AVFrame *pic_arg)
 
         pic->f->display_picture_number = display_picture_number;
         pic->f->pts = pts; // we set this here to avoid modifiying pic_arg
+    } else {
+        /* Flushing: When we have not received enough input frames,
+         * ensure s->input_picture[0] contains the first picture */
+        for (flush_offset = 0; flush_offset < encoding_delay + 1; flush_offset++)
+            if (s->input_picture[flush_offset])
+                break;
+
+        if (flush_offset <= 1)
+            flush_offset = 1;
+        else
+            encoding_delay = encoding_delay - flush_offset + 1;
     }
 
     /* shift buffer entries */
-    for (i = 1; i < MAX_PICTURE_COUNT /*s->encoding_delay + 1*/; i++)
-        s->input_picture[i - 1] = s->input_picture[i];
+    for (i = flush_offset; i < MAX_PICTURE_COUNT /*s->encoding_delay + 1*/; i++)
+        s->input_picture[i - flush_offset] = s->input_picture[i];
 
     s->input_picture[encoding_delay] = (Picture*) pic;