diff mbox series

[FFmpeg-devel,v3] avformat/mp3dec: Subtract known padding from duration

Message ID 20230823183335.988006-1-ulrik.mikaelsson@gmail.com
State New
Headers show
Series [FFmpeg-devel,v3] avformat/mp3dec: Subtract known padding from duration | expand

Checks

Context Check Description
yinshiyou/make_loongarch64 success Make finished
yinshiyou/make_fate_loongarch64 success Make fate finished
andriy/make_x86 success Make finished
andriy/make_fate_x86 success Make fate finished

Commit Message

Ulrik Mikaelsson Aug. 23, 2023, 6:33 p.m. UTC 
When an Info-tag is present, marking initial and trailing samples as
padding, those samples should not be included in the calculation of track
duration.

This solves a surprising user experience where converting a WAV->MP3->WAV,
ffprobe will show the duration of the mp3 as slightly longer than both the
input and the output.

As a result, the estimated duration and imprecise seek-results of some
FATE-tests have been updated.
---
 libavformat/mp3dec.c                 | 19 +++++++++++++------
 tests/ref/fate/gapless-mp3-side-data |  4 ++--
 tests/ref/seek/extra-mp3             |  8 ++++----
 3 files changed, 19 insertions(+), 12 deletions(-)

Comments

Ulrik Mikaelsson Aug. 25, 2023, 9:31 a.m. UTC | #1 
Just noticed that there is a ticket
https://trac.ffmpeg.org/ticket/10163 about this, that I believe is
solved with this patch.

Den ons 23 aug. 2023 kl 20:33 skrev Ulrik Mikaelsson
<ulrik.mikaelsson@gmail.com>:
>
> When an Info-tag is present, marking initial and trailing samples as
> padding, those samples should not be included in the calculation of track
> duration.
>
> This solves a surprising user experience where converting a WAV->MP3->WAV,
> ffprobe will show the duration of the mp3 as slightly longer than both the
> input and the output.
>
> As a result, the estimated duration and imprecise seek-results of some
> FATE-tests have been updated.
> ---
>  libavformat/mp3dec.c                 | 19 +++++++++++++------
>  tests/ref/fate/gapless-mp3-side-data |  4 ++--
>  tests/ref/seek/extra-mp3             |  8 ++++----
>  3 files changed, 19 insertions(+), 12 deletions(-)
>
> diff --git a/libavformat/mp3dec.c b/libavformat/mp3dec.c
> index 05c13228bc..24ec4dae06 100644
> --- a/libavformat/mp3dec.c
> +++ b/libavformat/mp3dec.c
> @@ -51,6 +51,7 @@ typedef struct {
>      int usetoc;
>      unsigned frames; /* Total number of frames in file */
>      unsigned header_filesize;   /* Total number of bytes in the stream */
> +    unsigned frame_duration;   /* Frame duration in st->time_base */
>      int is_cbr;
>  } MP3DecContext;
>
> @@ -339,6 +340,7 @@ static int mp3_parse_vbr_tags(AVFormatContext *s, AVStream *st, int64_t base)
>
>      mp3->frames = 0;
>      mp3->header_filesize   = 0;
> +    mp3->frame_duration = av_rescale_q(spf, (AVRational){1, c.sample_rate}, st->time_base);
>
>      mp3_parse_info_tag(s, st, &c, spf);
>      mp3_parse_vbri_tag(s, st, base);
> @@ -349,11 +351,17 @@ static int mp3_parse_vbr_tags(AVFormatContext *s, AVStream *st, int64_t base)
>      /* Skip the vbr tag frame */
>      avio_seek(s->pb, base + vbrtag_size, SEEK_SET);
>
> -    if (mp3->frames)
> -        st->duration = av_rescale_q(mp3->frames, (AVRational){spf, c.sample_rate},
> +    if (mp3->frames) {
> +        int64_t full_duration;
> +
> +        full_duration = mp3->frames * (int64_t)spf;
> +        st->duration = av_rescale_q(full_duration - mp3->start_pad - mp3->end_pad,
> +                                    (AVRational){1, c.sample_rate},
>                                      st->time_base);
> -    if (mp3->header_filesize && mp3->frames && !mp3->is_cbr)
> -        st->codecpar->bit_rate = av_rescale(mp3->header_filesize, 8 * c.sample_rate, mp3->frames * (int64_t)spf);
> +
> +        if (mp3->header_filesize &&  !mp3->is_cbr)
> +            st->codecpar->bit_rate = av_rescale(mp3->header_filesize, 8 * c.sample_rate, full_duration);
> +    }
>
>      return 0;
>  }
> @@ -589,8 +597,7 @@ static int mp3_seek(AVFormatContext *s, int stream_index, int64_t timestamp,
>          return best_pos;
>
>      if (mp3->is_cbr && ie == &ie1 && mp3->frames) {
> -        int frame_duration = av_rescale(st->duration, 1, mp3->frames);
> -        ie1.timestamp = frame_duration * av_rescale(best_pos - si->data_offset, mp3->frames, mp3->header_filesize);
> +        ie1.timestamp = mp3->frame_duration * av_rescale(best_pos - si->data_offset, mp3->frames, mp3->header_filesize);
>      }
>
>      avpriv_update_cur_dts(s, st, ie->timestamp);
> diff --git a/tests/ref/fate/gapless-mp3-side-data b/tests/ref/fate/gapless-mp3-side-data
> index caf42068dc..495a5bb865 100644
> --- a/tests/ref/fate/gapless-mp3-side-data
> +++ b/tests/ref/fate/gapless-mp3-side-data
> @@ -596,5 +596,5 @@ packet|codec_type=audio|stream_index=0|pts=218603520|pts_time=15.490612|dts=2186
>
>  packet|codec_type=audio|stream_index=0|pts=218972160|pts_time=15.516735|dts=218972160|dts_time=15.516735|duration=368640|duration_time=0.026122|size=418|pos=249718|flags=K__|data_hash=CRC32:3789f3cf|side_data|side_data_type=Skip Samples|skip_samples=0|discard_padding=1152|skip_reason=0|discard_reason=0
>
> -stream|index=0|codec_name=mp3|profile=unknown|codec_type=audio|codec_tag_string=[0][0][0][0]|codec_tag=0x0000|sample_fmt=fltp|sample_rate=44100|channels=2|channel_layout=stereo|bits_per_sample=0|initial_padding=0|id=N/A|r_frame_rate=0/0|avg_frame_rate=0/0|time_base=1/14112000|start_pts=353600|start_time=0.025057|duration_ts=219340800|duration=15.542857|bit_rate=128000|max_bit_rate=N/A|bits_per_raw_sample=N/A|nb_frames=N/A|nb_read_frames=N/A|nb_read_packets=595|disposition:default=0|disposition:dub=0|disposition:original=0|disposition:comment=0|disposition:lyrics=0|disposition:karaoke=0|disposition:forced=0|disposition:hearing_impaired=0|disposition:visual_impaired=0|disposition:clean_effects=0|disposition:attached_pic=0|disposition:timed_thumbnails=0|disposition:captions=0|disposition:descriptions=0|disposition:metadata=0|disposition:dependent=0|disposition:still_image=0|tag:encoder=LAME3.93
> -format|filename=gapless.mp3|nb_streams=1|nb_programs=0|format_name=mp3|start_time=0.025057|duration=15.542857|size=250264|bit_rate=128812|probe_score=51|tag:title=test
> +stream|index=0|codec_name=mp3|profile=unknown|codec_type=audio|codec_tag_string=[0][0][0][0]|codec_tag=0x0000|sample_fmt=fltp|sample_rate=44100|channels=2|channel_layout=stereo|bits_per_sample=0|initial_padding=0|id=N/A|r_frame_rate=0/0|avg_frame_rate=0/0|time_base=1/14112000|start_pts=353600|start_time=0.025057|duration_ts=218521600|duration=15.484807|bit_rate=128000|max_bit_rate=N/A|bits_per_raw_sample=N/A|nb_frames=N/A|nb_read_frames=N/A|nb_read_packets=595|disposition:default=0|disposition:dub=0|disposition:original=0|disposition:comment=0|disposition:lyrics=0|disposition:karaoke=0|disposition:forced=0|disposition:hearing_impaired=0|disposition:visual_impaired=0|disposition:clean_effects=0|disposition:attached_pic=0|disposition:timed_thumbnails=0|disposition:captions=0|disposition:descriptions=0|disposition:metadata=0|disposition:dependent=0|disposition:still_image=0|tag:encoder=LAME3.93
> +format|filename=gapless.mp3|nb_streams=1|nb_programs=0|format_name=mp3|start_time=0.025057|duration=15.484807|size=250264|bit_rate=129295|probe_score=51|tag:title=test
> diff --git a/tests/ref/seek/extra-mp3 b/tests/ref/seek/extra-mp3
> index fdfb1a7c66..ec5947a9d5 100644
> --- a/tests/ref/seek/extra-mp3
> +++ b/tests/ref/seek/extra-mp3
> @@ -8,11 +8,11 @@ ret: 0         st: 0 flags:1 dts: 0.809796 pts: 0.809796 pos:  14407 size:   418
>  ret: 0         st: 0 flags:1  ts:-0.317499
>  ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
>  ret: 0         st:-1 flags:0  ts: 2.576668
> -ret: 0         st: 0 flags:1 dts: 2.586122 pts: 2.586122 pos:  42828 size:   418
> +ret: 0         st: 0 flags:1 dts: 2.612245 pts: 2.612245 pos:  43246 size:   418
>  ret: 0         st:-1 flags:1  ts: 1.470835
>  ret: 0         st: 0 flags:1 dts: 1.462857 pts: 1.462857 pos:  24856 size:   418
>  ret: 0         st: 0 flags:0  ts: 0.365002
> -ret: 0         st: 0 flags:1 dts: 0.365714 pts: 0.365714 pos:   7302 size:   418
> +ret: 0         st: 0 flags:1 dts: 0.391837 pts: 0.391837 pos:   7720 size:   418
>  ret: 0         st: 0 flags:1  ts:-0.740831
>  ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
>  ret: 0         st:-1 flags:0  ts: 2.153336
> @@ -22,11 +22,11 @@ ret: 0         st: 0 flags:1 dts: 1.044898 pts: 1.044898 pos:  18169 size:   418
>  ret: 0         st: 0 flags:0  ts:-0.058330
>  ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
>  ret: 0         st: 0 flags:1  ts: 2.835837
> -ret: 0         st: 0 flags:1 dts: 2.821224 pts: 2.821224 pos:  46590 size:   418
> +ret: 0         st: 0 flags:1 dts: 2.847347 pts: 2.847347 pos:  47008 size:   418
>  ret: 0         st:-1 flags:0  ts: 1.730004
>  ret: 0         st: 0 flags:1 dts: 1.750204 pts: 1.750204 pos:  29454 size:   418
>  ret: 0         st:-1 flags:1  ts: 0.624171
> -ret: 0         st: 0 flags:1 dts: 0.600816 pts: 0.600816 pos:  11064 size:   418
> +ret: 0         st: 0 flags:1 dts: 0.626939 pts: 0.626939 pos:  11482 size:   418
>  ret: 0         st: 0 flags:0  ts:-0.481662
>  ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
>  ret: 0         st: 0 flags:1  ts: 2.412505
> --
> 2.39.2
>
diff mbox series

Patch

diff --git a/libavformat/mp3dec.c b/libavformat/mp3dec.c
index 05c13228bc..24ec4dae06 100644
--- a/libavformat/mp3dec.c
+++ b/libavformat/mp3dec.c
@@ -51,6 +51,7 @@  typedef struct {
     int usetoc;
     unsigned frames; /* Total number of frames in file */
     unsigned header_filesize;   /* Total number of bytes in the stream */
+    unsigned frame_duration;   /* Frame duration in st->time_base */
     int is_cbr;
 } MP3DecContext;
 
@@ -339,6 +340,7 @@  static int mp3_parse_vbr_tags(AVFormatContext *s, AVStream *st, int64_t base)
 
     mp3->frames = 0;
     mp3->header_filesize   = 0;
+    mp3->frame_duration = av_rescale_q(spf, (AVRational){1, c.sample_rate}, st->time_base);
 
     mp3_parse_info_tag(s, st, &c, spf);
     mp3_parse_vbri_tag(s, st, base);
@@ -349,11 +351,17 @@  static int mp3_parse_vbr_tags(AVFormatContext *s, AVStream *st, int64_t base)
     /* Skip the vbr tag frame */
     avio_seek(s->pb, base + vbrtag_size, SEEK_SET);
 
-    if (mp3->frames)
-        st->duration = av_rescale_q(mp3->frames, (AVRational){spf, c.sample_rate},
+    if (mp3->frames) {
+        int64_t full_duration;
+
+        full_duration = mp3->frames * (int64_t)spf;
+        st->duration = av_rescale_q(full_duration - mp3->start_pad - mp3->end_pad,
+                                    (AVRational){1, c.sample_rate},
                                     st->time_base);
-    if (mp3->header_filesize && mp3->frames && !mp3->is_cbr)
-        st->codecpar->bit_rate = av_rescale(mp3->header_filesize, 8 * c.sample_rate, mp3->frames * (int64_t)spf);
+
+        if (mp3->header_filesize &&  !mp3->is_cbr)
+            st->codecpar->bit_rate = av_rescale(mp3->header_filesize, 8 * c.sample_rate, full_duration);
+    }
 
     return 0;
 }
@@ -589,8 +597,7 @@  static int mp3_seek(AVFormatContext *s, int stream_index, int64_t timestamp,
         return best_pos;
 
     if (mp3->is_cbr && ie == &ie1 && mp3->frames) {
-        int frame_duration = av_rescale(st->duration, 1, mp3->frames);
-        ie1.timestamp = frame_duration * av_rescale(best_pos - si->data_offset, mp3->frames, mp3->header_filesize);
+        ie1.timestamp = mp3->frame_duration * av_rescale(best_pos - si->data_offset, mp3->frames, mp3->header_filesize);
     }
 
     avpriv_update_cur_dts(s, st, ie->timestamp);
diff --git a/tests/ref/fate/gapless-mp3-side-data b/tests/ref/fate/gapless-mp3-side-data
index caf42068dc..495a5bb865 100644
--- a/tests/ref/fate/gapless-mp3-side-data
+++ b/tests/ref/fate/gapless-mp3-side-data
@@ -596,5 +596,5 @@  packet|codec_type=audio|stream_index=0|pts=218603520|pts_time=15.490612|dts=2186
 
 packet|codec_type=audio|stream_index=0|pts=218972160|pts_time=15.516735|dts=218972160|dts_time=15.516735|duration=368640|duration_time=0.026122|size=418|pos=249718|flags=K__|data_hash=CRC32:3789f3cf|side_data|side_data_type=Skip Samples|skip_samples=0|discard_padding=1152|skip_reason=0|discard_reason=0
 
-stream|index=0|codec_name=mp3|profile=unknown|codec_type=audio|codec_tag_string=[0][0][0][0]|codec_tag=0x0000|sample_fmt=fltp|sample_rate=44100|channels=2|channel_layout=stereo|bits_per_sample=0|initial_padding=0|id=N/A|r_frame_rate=0/0|avg_frame_rate=0/0|time_base=1/14112000|start_pts=353600|start_time=0.025057|duration_ts=219340800|duration=15.542857|bit_rate=128000|max_bit_rate=N/A|bits_per_raw_sample=N/A|nb_frames=N/A|nb_read_frames=N/A|nb_read_packets=595|disposition:default=0|disposition:dub=0|disposition:original=0|disposition:comment=0|disposition:lyrics=0|disposition:karaoke=0|disposition:forced=0|disposition:hearing_impaired=0|disposition:visual_impaired=0|disposition:clean_effects=0|disposition:attached_pic=0|disposition:timed_thumbnails=0|disposition:captions=0|disposition:descriptions=0|disposition:metadata=0|disposition:dependent=0|disposition:still_image=0|tag:encoder=LAME3.93 
-format|filename=gapless.mp3|nb_streams=1|nb_programs=0|format_name=mp3|start_time=0.025057|duration=15.542857|size=250264|bit_rate=128812|probe_score=51|tag:title=test
+stream|index=0|codec_name=mp3|profile=unknown|codec_type=audio|codec_tag_string=[0][0][0][0]|codec_tag=0x0000|sample_fmt=fltp|sample_rate=44100|channels=2|channel_layout=stereo|bits_per_sample=0|initial_padding=0|id=N/A|r_frame_rate=0/0|avg_frame_rate=0/0|time_base=1/14112000|start_pts=353600|start_time=0.025057|duration_ts=218521600|duration=15.484807|bit_rate=128000|max_bit_rate=N/A|bits_per_raw_sample=N/A|nb_frames=N/A|nb_read_frames=N/A|nb_read_packets=595|disposition:default=0|disposition:dub=0|disposition:original=0|disposition:comment=0|disposition:lyrics=0|disposition:karaoke=0|disposition:forced=0|disposition:hearing_impaired=0|disposition:visual_impaired=0|disposition:clean_effects=0|disposition:attached_pic=0|disposition:timed_thumbnails=0|disposition:captions=0|disposition:descriptions=0|disposition:metadata=0|disposition:dependent=0|disposition:still_image=0|tag:encoder=LAME3.93
+format|filename=gapless.mp3|nb_streams=1|nb_programs=0|format_name=mp3|start_time=0.025057|duration=15.484807|size=250264|bit_rate=129295|probe_score=51|tag:title=test
diff --git a/tests/ref/seek/extra-mp3 b/tests/ref/seek/extra-mp3
index fdfb1a7c66..ec5947a9d5 100644
--- a/tests/ref/seek/extra-mp3
+++ b/tests/ref/seek/extra-mp3
@@ -8,11 +8,11 @@  ret: 0         st: 0 flags:1 dts: 0.809796 pts: 0.809796 pos:  14407 size:   418
 ret: 0         st: 0 flags:1  ts:-0.317499
 ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
 ret: 0         st:-1 flags:0  ts: 2.576668
-ret: 0         st: 0 flags:1 dts: 2.586122 pts: 2.586122 pos:  42828 size:   418
+ret: 0         st: 0 flags:1 dts: 2.612245 pts: 2.612245 pos:  43246 size:   418
 ret: 0         st:-1 flags:1  ts: 1.470835
 ret: 0         st: 0 flags:1 dts: 1.462857 pts: 1.462857 pos:  24856 size:   418
 ret: 0         st: 0 flags:0  ts: 0.365002
-ret: 0         st: 0 flags:1 dts: 0.365714 pts: 0.365714 pos:   7302 size:   418
+ret: 0         st: 0 flags:1 dts: 0.391837 pts: 0.391837 pos:   7720 size:   418
 ret: 0         st: 0 flags:1  ts:-0.740831
 ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
 ret: 0         st:-1 flags:0  ts: 2.153336
@@ -22,11 +22,11 @@  ret: 0         st: 0 flags:1 dts: 1.044898 pts: 1.044898 pos:  18169 size:   418
 ret: 0         st: 0 flags:0  ts:-0.058330
 ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
 ret: 0         st: 0 flags:1  ts: 2.835837
-ret: 0         st: 0 flags:1 dts: 2.821224 pts: 2.821224 pos:  46590 size:   418
+ret: 0         st: 0 flags:1 dts: 2.847347 pts: 2.847347 pos:  47008 size:   418
 ret: 0         st:-1 flags:0  ts: 1.730004
 ret: 0         st: 0 flags:1 dts: 1.750204 pts: 1.750204 pos:  29454 size:   418
 ret: 0         st:-1 flags:1  ts: 0.624171
-ret: 0         st: 0 flags:1 dts: 0.600816 pts: 0.600816 pos:  11064 size:   418
+ret: 0         st: 0 flags:1 dts: 0.626939 pts: 0.626939 pos:  11482 size:   418
 ret: 0         st: 0 flags:0  ts:-0.481662
 ret: 0         st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos:   1451 size:   417
 ret: 0         st: 0 flags:1  ts: 2.412505