diff options
author | rfelker <rfelker@b3059339-0415-0410-9bf9-f77b7e298cf2> | 2005-04-17 17:17:52 +0000 |
---|---|---|
committer | rfelker <rfelker@b3059339-0415-0410-9bf9-f77b7e298cf2> | 2005-04-17 17:17:52 +0000 |
commit | 552878546397efd7d6fda343287411ba8d407884 (patch) | |
tree | 12af8a79dd2bf24f454ebec6e00600d511939970 /libmpdemux/demux_audio.c | |
parent | 4593e0f2cfe2ffd42bf8e9dbab8b251cb8518785 (diff) | |
download | mpv-552878546397efd7d6fda343287411ba8d407884.tar.bz2 mpv-552878546397efd7d6fda343287411ba8d407884.tar.xz |
nico partially fixed the bug i reported; here's the rest of the fix.
basically demux_audio was mixing data in its header buffer in a bogus
manner, whereby it could sometimes "make up" valid mpeg headers where
no such header actually occurred in the file. it should be correct now.
btw these changes also fix the bug where mplayer reports huge initial
cpu usage for sound when playing mp3 files.
git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@15206 b3059339-0415-0410-9bf9-f77b7e298cf2
Diffstat (limited to 'libmpdemux/demux_audio.c')
-rw-r--r-- | libmpdemux/demux_audio.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/libmpdemux/demux_audio.c b/libmpdemux/demux_audio.c index bc812e5ffa..9b6be0e36e 100644 --- a/libmpdemux/demux_audio.c +++ b/libmpdemux/demux_audio.c @@ -159,6 +159,7 @@ int demux_audio_open(demuxer_t* demuxer) { break; } else if((mp3_flen = mp_get_mp3_header(hdr,&mp3_chans,&mp3_freq,&mpa_spf,&mpa_layer)) > 0) { stream_skip(s, mp3_flen - HDR_SIZE); + step = HDR_SIZE; mp3_found = add_mp3_hdr(&mp3_hdrs, st_pos, mp3_chans, mp3_freq, mp3_flen); if (mp3_found) { frmt = MP3; |