From d02ae31fb255a151ebf0546f1a349ccf951666a2 Mon Sep 17 00:00:00 2001
From: Anton Khirnov <anton@khirnov.net>
Date: Fri, 10 Jun 2022 14:45:48 +0200
Subject: [PATCH] fftools/ffmpeg: use pre-BSF DTS for choosing next output

The following commits will add a new buffering stage after bitstream
filters, which should not be taken into account for choosing next
output.

OutputStream.last_mux_dts is also used by the muxing code to make up
missing DTS values - that field is now moved to the muxer-private
MuxStream object.
---
 fftools/ffmpeg.c     |  8 +++++---
 fftools/ffmpeg.h     |  2 +-
 fftools/ffmpeg_mux.c | 20 +++++++++++++-------
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/fftools/ffmpeg.c b/fftools/ffmpeg.c
index bed87a2199..50e17b1890 100644
--- a/fftools/ffmpeg.c
+++ b/fftools/ffmpeg.c
@@ -716,6 +716,9 @@ static void output_packet(OutputFile *of, AVPacket *pkt,
 {
     int ret = 0;
 
+    if (!eof && pkt->dts != AV_NOPTS_VALUE)
+        ost->last_mux_dts = av_rescale_q(pkt->dts, ost->mux_timebase, AV_TIME_BASE_Q);
+
     /* apply the output bitstream filters */
     if (ost->bsf_ctx) {
         ret = av_bsf_send_packet(ost->bsf_ctx, eof ? NULL : pkt);
@@ -3459,9 +3462,8 @@ static OutputStream *choose_output(void)
         if (ost->filter && ost->last_filter_pts != AV_NOPTS_VALUE) {
             opts = ost->last_filter_pts;
         } else {
-            opts = ost->last_mux_dts == AV_NOPTS_VALUE ? INT64_MIN :
-                       av_rescale_q(ost->last_mux_dts, ost->st->time_base,
-                                    AV_TIME_BASE_Q);
+            opts = ost->last_mux_dts == AV_NOPTS_VALUE ?
+                   INT64_MIN : ost->last_mux_dts;
             if (ost->last_mux_dts == AV_NOPTS_VALUE)
                 av_log(NULL, AV_LOG_DEBUG,
                     "cur_dts is invalid st:%d (%d) [init:%d i_done:%d finish:%d] (this is harmless if it occurs once at the start per stream)\n",
diff --git a/fftools/ffmpeg.h b/fftools/ffmpeg.h
index 7ff303e370..090bf67d2d 100644
--- a/fftools/ffmpeg.h
+++ b/fftools/ffmpeg.h
@@ -468,7 +468,7 @@ typedef struct OutputStream {
     /* pts of the first frame encoded for this stream, used for limiting
      * recording time */
     int64_t first_pts;
-    /* dts of the last packet sent to the muxer */
+    /* dts of the last packet sent to the muxing queue, in AV_TIME_BASE_Q */
     int64_t last_mux_dts;
     /* pts of the last frame received from the filters, in AV_TIME_BASE_Q */
     int64_t last_filter_pts;
diff --git a/fftools/ffmpeg_mux.c b/fftools/ffmpeg_mux.c
index 0fd7888d4f..a3350a73e9 100644
--- a/fftools/ffmpeg_mux.c
+++ b/fftools/ffmpeg_mux.c
@@ -41,6 +41,10 @@ typedef struct MuxStream {
      * Updated when a packet is either pushed or pulled from the queue.
      */
     size_t muxing_queue_data_size;
+
+    /* dts of the last packet sent to the muxer, in the stream timebase
+     * used for making up missing dts values */
+    int64_t last_mux_dts;
 } MuxStream;
 
 struct Muxer {
@@ -106,6 +110,7 @@ static int queue_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt)
 
 static void write_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt)
 {
+    MuxStream *ms = &of->mux->streams[ost->index];
     AVFormatContext *s = of->ctx;
     AVStream *st = ost->st;
     int ret;
@@ -133,21 +138,21 @@ static void write_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt)
                    pkt->dts, pkt->pts,
                    ost->file_index, ost->st->index);
             pkt->pts =
-            pkt->dts = pkt->pts + pkt->dts + ost->last_mux_dts + 1
-                     - FFMIN3(pkt->pts, pkt->dts, ost->last_mux_dts + 1)
-                     - FFMAX3(pkt->pts, pkt->dts, ost->last_mux_dts + 1);
+            pkt->dts = pkt->pts + pkt->dts + ms->last_mux_dts + 1
+                     - FFMIN3(pkt->pts, pkt->dts, ms->last_mux_dts + 1)
+                     - FFMAX3(pkt->pts, pkt->dts, ms->last_mux_dts + 1);
         }
         if ((st->codecpar->codec_type == AVMEDIA_TYPE_AUDIO || st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO || st->codecpar->codec_type == AVMEDIA_TYPE_SUBTITLE) &&
             pkt->dts != AV_NOPTS_VALUE &&
-            ost->last_mux_dts != AV_NOPTS_VALUE) {
-            int64_t max = ost->last_mux_dts + !(s->oformat->flags & AVFMT_TS_NONSTRICT);
+            ms->last_mux_dts != AV_NOPTS_VALUE) {
+            int64_t max = ms->last_mux_dts + !(s->oformat->flags & AVFMT_TS_NONSTRICT);
             if (pkt->dts < max) {
                 int loglevel = max - pkt->dts > 2 || st->codecpar->codec_type == AVMEDIA_TYPE_VIDEO ? AV_LOG_WARNING : AV_LOG_DEBUG;
                 if (exit_on_error)
                     loglevel = AV_LOG_ERROR;
                 av_log(s, loglevel, "Non-monotonous DTS in output stream "
                        "%d:%d; previous: %"PRId64", current: %"PRId64"; ",
-                       ost->file_index, ost->st->index, ost->last_mux_dts, pkt->dts);
+                       ost->file_index, ost->st->index, ms->last_mux_dts, pkt->dts);
                 if (exit_on_error) {
                     av_log(NULL, AV_LOG_FATAL, "aborting.\n");
                     exit_program(1);
@@ -161,7 +166,7 @@ static void write_packet(OutputFile *of, OutputStream *ost, AVPacket *pkt)
             }
         }
     }
-    ost->last_mux_dts = pkt->dts;
+    ms->last_mux_dts = pkt->dts;
 
     ost->data_size += pkt->size;
     ost->packets_written++;
@@ -423,6 +428,7 @@ int of_muxer_init(OutputFile *of, AVDictionary *opts, int64_t limit_filesize)
             ret = AVERROR(ENOMEM);
             goto fail;
         }
+        ms->last_mux_dts = AV_NOPTS_VALUE;
     }
 
     mux->limit_filesize = limit_filesize;