[FFmpeg-devel] [PATCH] libavfilter/f_select: switch to activate and properly handle EOF pts

[Li-Heng Chen]

This patch solves a potential EOF pts bug that can be triggered with other filters: when placing select filter before fps filter, the EOF pts in `f_select` always indicate the last input frame regardless of the frame selected. This may cause unwanted duplication of the last-selected-frame in `vf_fps`. Switching the filtering process from `filter_frame` to `activate` allows to properly set EOF pts by ff_outlink_set_status.

This bug can be reproduced by the ffmpeg cmd below (bitstreams in
fate-suite can reproduce this issue):

ffmpeg -y -i /path/ffmpeg/fate-suite/h264/bbc2.sample.h264 -vf select='gte(n\,0)*gte(24\,n)',fps=25/1 out.y4m

Signed-off-by: Li-Heng Chen <lihengc at netflix.com>
---
libavfilter/f_select.c | 49 +++++++++++++++++++++++++++++++++---------
1 file changed, 39 insertions(+), 10 deletions(-)

diff --git a/libavfilter/f_select.c b/libavfilter/f_select.c
index 1cfe2d59e5..e01f476b5b 100644
--- a/libavfilter/f_select.c
+++ b/libavfilter/f_select.c
@@ -33,6 +33,7 @@
#include "libavutil/opt.h"
#include "libavutil/pixdesc.h"
#include "avfilter.h"
+#include "filters.h"
#include "audio.h"
#include "formats.h"
#include "internal.h"
@@ -159,6 +160,7 @@ typedef struct SelectContext {
    double select;
    int select_out;                 ///< mark the selected output pad index
    int nb_outputs;
+    int64_t eof_pts;
} SelectContext;

#define OFFSET(x) offsetof(SelectContext, x)
@@ -215,6 +217,7 @@ static int config_input(AVFilterLink *inlink)

    select->bitdepth = desc->comp[0].depth;
    select->nb_planes = is_yuv ? 1 : av_pix_fmt_count_planes(inlink->format);
+    select->eof_pts = AV_NOPTS_VALUE;

    for (int plane = 0; plane < select->nb_planes; plane++) {
        ptrdiff_t line_size = av_image_get_linesize(inlink->format, inlink->w, plane);
@@ -336,7 +339,7 @@ static void select_frame(AVFilterContext *ctx, AVFrame *frame)
    if (isnan(select->var_values[VAR_START_T]))
        select->var_values[VAR_START_T] = TS2D(frame->pts) * av_q2d(inlink->time_base);

-    select->var_values[VAR_N  ] = inlink->frame_count_out;
+    select->var_values[VAR_N  ] = inlink->frame_count_out - 1;
    select->var_values[VAR_PTS] = TS2D(frame->pts);
    select->var_values[VAR_T  ] = TS2D(frame->pts) * av_q2d(inlink->time_base);
    select->var_values[VAR_POS] = frame->pkt_pos == -1 ? NAN : frame->pkt_pos;
@@ -409,17 +412,43 @@ static void select_frame(AVFilterContext *ctx, AVFrame *frame)
    select->var_values[VAR_PREV_T]   = select->var_values[VAR_T];
}

-static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
+static int activate(AVFilterContext *ctx)
{
-    AVFilterContext *ctx = inlink->dst;
+    int ret, status;
    SelectContext *select = ctx->priv;
+    AVFilterLink *inlink = ctx->inputs[0];
+    AVFilterLink *outlink = ctx->outputs[0];
+    AVFrame *in;
+    int64_t pts;

-    select_frame(ctx, frame);
-    if (select->select)
-        return ff_filter_frame(ctx->outputs[select->select_out], frame);
+    FF_FILTER_FORWARD_STATUS_BACK(outlink, inlink);

-    av_frame_free(&frame);
-    return 0;
+    ret = ff_inlink_consume_frame(inlink, &in);
+    if (ret < 0)
+        return ret;
+    if (ret > 0) {
+        select_frame(ctx, in);
+        if (select->select)
+            return ff_filter_frame(ctx->outputs[select->select_out], in);
+    }
+    av_frame_free(&in);
+
+    ret = ff_inlink_acknowledge_status(inlink, &status, &pts);
+
+    if (((int64_t)select->var_values[VAR_N] - (int64_t)select->var_values[VAR_PREV_SELECTED_N] == 1) ||
+        (status == AVERROR_EOF && select->select))
+        select->eof_pts = pts;
+
+    if (ret && status == AVERROR_EOF) {
+        av_log(ctx, AV_LOG_TRACE, "N:EOF PTS:%"PRId64"\n",
+               select->eof_pts);
+        ff_outlink_set_status(outlink, status, select->eof_pts);
+        return 0;
+    }
+
+    FF_FILTER_FORWARD_WANTED(outlink, inlink);
+
+    return FFERROR_NOT_READY;
}

static int request_frame(AVFilterLink *outlink)
@@ -467,7 +496,6 @@ static const AVFilterPad avfilter_af_aselect_inputs[] = {
        .name         = "default",
        .type         = AVMEDIA_TYPE_AUDIO,
        .config_props = config_input,
-        .filter_frame = filter_frame,
    },
};

@@ -475,6 +503,7 @@ const AVFilter ff_af_aselect = {
    .name        = "aselect",
    .description = NULL_IF_CONFIG_SMALL("Select audio frames to pass in output."),
    .init        = aselect_init,
+    .activate    = activate,
    .uninit      = uninit,
    .priv_size   = sizeof(SelectContext),
    FILTER_INPUTS(avfilter_af_aselect_inputs),
@@ -522,7 +551,6 @@ static const AVFilterPad avfilter_vf_select_inputs[] = {
        .name         = "default",
        .type         = AVMEDIA_TYPE_VIDEO,
        .config_props = config_input,
-        .filter_frame = filter_frame,
    },
};

@@ -530,6 +558,7 @@ const AVFilter ff_vf_select = {
    .name          = "select",
    .description   = NULL_IF_CONFIG_SMALL("Select video frames to pass in output."),
    .init          = select_init,
+    .activate      = activate,
    .uninit        = uninit,
    .priv_size     = sizeof(SelectContext),
    .priv_class    = &select_class,
-- 
2.32.1 (Apple Git-133)