[FFmpeg-devel] [PATCH 1/2] lavfi/ebur128: add metadata injection.

[Clément Bœsch]

---
 doc/filters.texi        |  5 +++++
 libavfilter/f_ebur128.c | 29 +++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/doc/filters.texi b/doc/filters.texi
index a93b433..9fbda34 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -6252,6 +6252,11 @@ Set the EBU scale meter. Default is @code{9}. Common values are @code{9} and
 @code{18}, respectively for EBU scale meter +9 and EBU scale meter +18. Any
 other integer value between this range is allowed.
 
+ at item metadata
+Set metadata injection. Default is @code{0}. If set to @code{1}, the audio will
+be divided into 100ms frames, each of them out of the filter containing various
+loudness information.
+
 @end table
 
 Example of real-time graph using @command{ffplay}, with a EBU scale meter +18:
diff --git a/libavfilter/f_ebur128.c b/libavfilter/f_ebur128.c
index 66cc133..1d0513d 100644
--- a/libavfilter/f_ebur128.c
+++ b/libavfilter/f_ebur128.c
@@ -33,6 +33,7 @@
 #include "libavutil/avassert.h"
 #include "libavutil/avstring.h"
 #include "libavutil/channel_layout.h"
+#include "libavutil/dict.h"
 #include "libavutil/xga_font_data.h"
 #include "libavutil/opt.h"
 #include "libavutil/timestamp.h"
@@ -90,6 +91,7 @@ struct rect { int x, y, w, h; };
 
 typedef struct {
     const AVClass *class;           ///< AVClass context for log and options purpose
+    int metadata;                   ///< whether or not to inject loudness results in buffers
 
     /* video  */
     int do_video;                   ///< 1 if video output enabled, 0 otherwise
@@ -133,6 +135,7 @@ static const AVOption ebur128_options[] = {
     { "video", "set video output", OFFSET(do_video), AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, V|F },
     { "size",  "set video size",   OFFSET(w), AV_OPT_TYPE_IMAGE_SIZE, {.str = "640x480"}, 0, 0, V|F },
     { "meter", "set scale meter (+9 to +18)",  OFFSET(meter), AV_OPT_TYPE_INT, {.i64 = 9}, 9, 18, V|F },
+    { "metadata", "inject metadata in the filtergraph", OFFSET(metadata), AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, V|F },
     { NULL },
 };
 
@@ -311,6 +314,20 @@ static int config_video_output(AVFilterLink *outlink)
     return 0;
 }
 
+static int config_audio_input(AVFilterLink *inlink)
+{
+    AVFilterContext *ctx = inlink->dst;
+    EBUR128Context *ebur128 = ctx->priv;
+
+    /* force 100ms framing in case of metadata injection: the frames must have
+     * a granularity of the window overlap to be accurately exploited */
+    if (ebur128->metadata)
+        inlink->min_samples =
+        inlink->max_samples =
+        inlink->partial_buf_size = inlink->sample_rate / 10;
+    return 0;
+}
+
 static int config_audio_output(AVFilterLink *outlink)
 {
     int i;
@@ -648,6 +665,17 @@ static int filter_frame(AVFilterLink *inlink, AVFilterBufferRef *insamples)
                    "t: %-10s " LOG_FMT "\n", av_ts2timestr(pts, &outlink->time_base),
                    loudness_400, loudness_3000,
                    ebur128->integrated_loudness, ebur128->loudness_range);
+            if (ebur128->metadata) { /* happens only once per filter_frame call */
+                char metabuf[128];
+#define SET_META(name, var) do {                                            \
+    snprintf(metabuf, sizeof(metabuf), "%6.1f", var);                       \
+    av_dict_set(&insamples->metadata, "lavfi.r128." name, metabuf, 0);      \
+} while (0)
+                SET_META("L400",  loudness_400);
+                SET_META("L3000", loudness_3000);
+                SET_META("I",     ebur128->integrated_loudness);
+                SET_META("LRA",   ebur128->loudness_range);
+            }
         }
     }
 
@@ -747,6 +775,7 @@ static const AVFilterPad ebur128_inputs[] = {
         .type             = AVMEDIA_TYPE_AUDIO,
         .get_audio_buffer = ff_null_get_audio_buffer,
         .filter_frame     = filter_frame,
+        .config_props     = config_audio_input,
     },
     { NULL }
 };
-- 
1.8.1.4