FFmpeg/libavformat/oggparsespeex.c
Anton Khirnov 9200514ad8 lavf: replace AVStream.codec with AVStream.codecpar
Currently, AVStream contains an embedded AVCodecContext instance, which
is used by demuxers to export stream parameters to the caller and by
muxers to receive stream parameters from the caller. It is also used
internally as the codec context that is passed to parsers.

In addition, it is also widely used by the callers as the decoding (when
demuxer) or encoding (when muxing) context, though this has been
officially discouraged since Libav 11.

There are multiple important problems with this approach:
    - the fields in AVCodecContext are in general one of
        * stream parameters
        * codec options
        * codec state
      However, it's not clear which ones are which. It is consequently
      unclear which fields are a demuxer allowed to set or a muxer allowed to
      read. This leads to erratic behaviour depending on whether decoding or
      encoding is being performed or not (and whether it uses the AVStream
      embedded codec context).
    - various synchronization issues arising from the fact that the same
      context is used by several different APIs (muxers/demuxers,
      parsers, bitstream filters and encoders/decoders) simultaneously, with
      there being no clear rules for who can modify what and the different
      processes being typically delayed with respect to each other.
    - avformat_find_stream_info() making it necessary to support opening
      and closing a single codec context multiple times, thus
      complicating the semantics of freeing various allocated objects in the
      codec context.

Those problems are resolved by replacing the AVStream embedded codec
context with a newly added AVCodecParameters instance, which stores only
the stream parameters exported by the demuxers or read by the muxers.
2016-02-23 17:01:58 +01:00

137 lines
4.6 KiB
C

/*
Copyright (C) 2008 Reimar Döffinger
Permission is hereby granted, free of charge, to any person
obtaining a copy of this software and associated documentation
files (the "Software"), to deal in the Software without
restriction, including without limitation the rights to use, copy,
modify, merge, publish, distribute, sublicense, and/or sell copies
of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
**/
#include <stdlib.h>
#include "libavutil/bswap.h"
#include "libavutil/avstring.h"
#include "libavutil/channel_layout.h"
#include "libavcodec/get_bits.h"
#include "libavcodec/bytestream.h"
#include "avformat.h"
#include "internal.h"
#include "oggdec.h"
struct speex_params {
int packet_size;
int final_packet_duration;
int seq;
};
static int speex_header(AVFormatContext *s, int idx) {
struct ogg *ogg = s->priv_data;
struct ogg_stream *os = ogg->streams + idx;
struct speex_params *spxp = os->private;
AVStream *st = s->streams[idx];
uint8_t *p = os->buf + os->pstart;
if (!spxp) {
spxp = av_mallocz(sizeof(*spxp));
if (!spxp)
return AVERROR(ENOMEM);
os->private = spxp;
}
if (spxp->seq > 1)
return 0;
if (spxp->seq == 0) {
int frames_per_packet;
st->codecpar->codec_type = AVMEDIA_TYPE_AUDIO;
st->codecpar->codec_id = AV_CODEC_ID_SPEEX;
st->codecpar->sample_rate = AV_RL32(p + 36);
st->codecpar->channels = AV_RL32(p + 48);
if (st->codecpar->channels < 1 || st->codecpar->channels > 2) {
av_log(s, AV_LOG_ERROR, "invalid channel count. Speex must be mono or stereo.\n");
return AVERROR_INVALIDDATA;
}
st->codecpar->channel_layout = st->codecpar->channels == 1 ? AV_CH_LAYOUT_MONO :
AV_CH_LAYOUT_STEREO;
spxp->packet_size = AV_RL32(p + 56);
frames_per_packet = AV_RL32(p + 64);
if (frames_per_packet)
spxp->packet_size *= frames_per_packet;
st->codecpar->extradata_size = os->psize;
st->codecpar->extradata = av_malloc(st->codecpar->extradata_size
+ AV_INPUT_BUFFER_PADDING_SIZE);
memcpy(st->codecpar->extradata, p, st->codecpar->extradata_size);
avpriv_set_pts_info(st, 64, 1, st->codecpar->sample_rate);
} else
ff_vorbis_stream_comment(s, st, p, os->psize);
spxp->seq++;
return 1;
}
static int ogg_page_packets(struct ogg_stream *os)
{
int i;
int packets = 0;
for (i = 0; i < os->nsegs; i++)
if (os->segments[i] < 255)
packets++;
return packets;
}
static int speex_packet(AVFormatContext *s, int idx)
{
struct ogg *ogg = s->priv_data;
struct ogg_stream *os = ogg->streams + idx;
struct speex_params *spxp = os->private;
int packet_size = spxp->packet_size;
if (os->flags & OGG_FLAG_EOS && os->lastpts != AV_NOPTS_VALUE &&
os->granule > 0) {
/* first packet of final page. we have to calculate the final packet
duration here because it is the only place we know the next-to-last
granule position. */
spxp->final_packet_duration = os->granule - os->lastpts -
packet_size * (ogg_page_packets(os) - 1);
}
if (!os->lastpts && os->granule > 0)
/* first packet */
os->lastpts = os->lastdts = os->granule - packet_size *
ogg_page_packets(os);
if (os->flags & OGG_FLAG_EOS && os->segp == os->nsegs &&
spxp->final_packet_duration)
/* final packet */
os->pduration = spxp->final_packet_duration;
else
os->pduration = packet_size;
return 0;
}
const struct ogg_codec ff_speex_codec = {
.magic = "Speex ",
.magicsize = 8,
.header = speex_header,
.packet = speex_packet,
.nb_header = 2,
};