1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229
|
/*
* Interface to libtwolame for mp2 encoding
* Copyright (c) 2012 Paul B Mahol
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
/**
* @file
* Interface to libtwolame for mp2 encoding.
*/
#include <twolame.h>
#include "libavutil/channel_layout.h"
#include "libavutil/common.h"
#include "libavutil/opt.h"
#include "avcodec.h"
#include "codec_internal.h"
#include "encode.h"
#include "mpegaudio.h"
typedef struct TWOLAMEContext {
AVClass *class;
int mode;
int psymodel;
int energy;
int error_protection;
int copyright;
int original;
int verbosity;
twolame_options *glopts;
int64_t next_pts;
} TWOLAMEContext;
static av_cold int twolame_encode_close(AVCodecContext *avctx)
{
TWOLAMEContext *s = avctx->priv_data;
twolame_close(&s->glopts);
return 0;
}
static av_cold int twolame_encode_init(AVCodecContext *avctx)
{
TWOLAMEContext *s = avctx->priv_data;
int ret;
avctx->frame_size = TWOLAME_SAMPLES_PER_FRAME;
avctx->initial_padding = 512 - 32 + 1;
s->glopts = twolame_init();
if (!s->glopts)
return AVERROR(ENOMEM);
twolame_set_verbosity(s->glopts, s->verbosity);
twolame_set_mode(s->glopts, s->mode);
twolame_set_psymodel(s->glopts, s->psymodel);
twolame_set_energy_levels(s->glopts, s->energy);
twolame_set_error_protection(s->glopts, s->error_protection);
twolame_set_copyright(s->glopts, s->copyright);
twolame_set_original(s->glopts, s->original);
twolame_set_num_channels(s->glopts, avctx->ch_layout.nb_channels);
twolame_set_in_samplerate(s->glopts, avctx->sample_rate);
twolame_set_out_samplerate(s->glopts, avctx->sample_rate);
if (!avctx->bit_rate) {
if ((s->mode == TWOLAME_AUTO_MODE && avctx->ch_layout.nb_channels == 1) || s->mode == TWOLAME_MONO)
avctx->bit_rate = avctx->sample_rate < 28000 ? 80000 : 192000;
else
avctx->bit_rate = avctx->sample_rate < 28000 ? 160000 : 384000;
}
if (avctx->flags & AV_CODEC_FLAG_QSCALE || !avctx->bit_rate) {
twolame_set_VBR(s->glopts, TRUE);
twolame_set_VBR_level(s->glopts,
avctx->global_quality / (float) FF_QP2LAMBDA);
av_log(avctx, AV_LOG_WARNING,
"VBR in MP2 is a hack, use another codec that supports it.\n");
} else {
twolame_set_bitrate(s->glopts, avctx->bit_rate / 1000);
}
ret = twolame_init_params(s->glopts);
if (ret) {
twolame_encode_close(avctx);
return AVERROR_UNKNOWN;
}
return 0;
}
static int twolame_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
const AVFrame *frame, int *got_packet_ptr)
{
TWOLAMEContext *s = avctx->priv_data;
int ret;
if ((ret = ff_alloc_packet(avctx, avpkt, MPA_MAX_CODED_FRAME_SIZE)) < 0)
return ret;
if (frame) {
switch (avctx->sample_fmt) {
case AV_SAMPLE_FMT_FLT:
ret = twolame_encode_buffer_float32_interleaved(s->glopts,
(const float *)frame->data[0],
frame->nb_samples,
avpkt->data,
avpkt->size);
break;
case AV_SAMPLE_FMT_FLTP:
ret = twolame_encode_buffer_float32(s->glopts,
(const float *)frame->data[0],
(const float *)frame->data[1],
frame->nb_samples,
avpkt->data, avpkt->size);
break;
case AV_SAMPLE_FMT_S16:
ret = twolame_encode_buffer_interleaved(s->glopts,
(const short int *)frame->data[0],
frame->nb_samples,
avpkt->data, avpkt->size);
break;
case AV_SAMPLE_FMT_S16P:
ret = twolame_encode_buffer(s->glopts,
(const short int *)frame->data[0],
(const short int *)frame->data[1],
frame->nb_samples,
avpkt->data, avpkt->size);
break;
default:
av_log(avctx, AV_LOG_ERROR,
"Unsupported sample format %d.\n", avctx->sample_fmt);
return AVERROR_BUG;
}
} else {
ret = twolame_encode_flush(s->glopts, avpkt->data, avpkt->size);
}
if (!ret) // no bytes written
return 0;
if (ret < 0) // twolame error
return AVERROR_UNKNOWN;
if (frame) {
avpkt->duration = ff_samples_to_time_base(avctx, frame->nb_samples);
if (frame->pts != AV_NOPTS_VALUE)
avpkt->pts = frame->pts - ff_samples_to_time_base(avctx, avctx->initial_padding);
} else {
avpkt->pts = s->next_pts;
}
// this is for setting pts for flushed packet(s).
if (avpkt->pts != AV_NOPTS_VALUE)
s->next_pts = avpkt->pts + avpkt->duration;
av_shrink_packet(avpkt, ret);
*got_packet_ptr = 1;
return 0;
}
#define OFFSET(x) offsetof(TWOLAMEContext, x)
#define AE AV_OPT_FLAG_AUDIO_PARAM | AV_OPT_FLAG_ENCODING_PARAM
static const AVOption options[] = {
{ "mode", "Mpeg Mode", OFFSET(mode), AV_OPT_TYPE_INT, { .i64 = TWOLAME_AUTO_MODE }, TWOLAME_AUTO_MODE, TWOLAME_MONO, AE, .unit = "mode"},
{ "auto", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = TWOLAME_AUTO_MODE }, 0, 0, AE, .unit = "mode" },
{ "stereo", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = TWOLAME_STEREO }, 0, 0, AE, .unit = "mode" },
{ "joint_stereo", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = TWOLAME_JOINT_STEREO }, 0, 0, AE, .unit = "mode" },
{ "dual_channel", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = TWOLAME_DUAL_CHANNEL }, 0, 0, AE, .unit = "mode" },
{ "mono", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = TWOLAME_MONO }, 0, 0, AE, .unit = "mode" },
{ "psymodel", "Psychoacoustic Model", OFFSET(psymodel), AV_OPT_TYPE_INT, { .i64 = 3 }, -1, 4, AE},
{ "energy_levels","enable energy levels", OFFSET(energy), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE},
{ "error_protection","enable CRC error protection", OFFSET(error_protection), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE},
{ "copyright", "set MPEG Audio Copyright flag", OFFSET(copyright), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE},
{ "original", "set MPEG Audio Original flag", OFFSET(original), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, AE},
{ "verbosity", "set library optput level (0-10)", OFFSET(verbosity), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 10, AE},
{ NULL },
};
static const AVClass twolame_class = {
.class_name = "libtwolame encoder",
.item_name = av_default_item_name,
.option = options,
.version = LIBAVUTIL_VERSION_INT,
};
static const FFCodecDefault twolame_defaults[] = {
{ "b", "0" },
{ NULL },
};
static const int twolame_samplerates[] = {
16000, 22050, 24000, 32000, 44100, 48000, 0
};
const FFCodec ff_libtwolame_encoder = {
.p.name = "libtwolame",
CODEC_LONG_NAME("libtwolame MP2 (MPEG audio layer 2)"),
.p.type = AVMEDIA_TYPE_AUDIO,
.p.id = AV_CODEC_ID_MP2,
.p.capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_DELAY,
.caps_internal = FF_CODEC_CAP_NOT_INIT_THREADSAFE,
.priv_data_size = sizeof(TWOLAMEContext),
.init = twolame_encode_init,
FF_CODEC_ENCODE_CB(twolame_encode_frame),
.close = twolame_encode_close,
.defaults = twolame_defaults,
.p.priv_class = &twolame_class,
CODEC_SAMPLEFMTS(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_FLTP,
AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S16P),
CODEC_CH_LAYOUTS(AV_CHANNEL_LAYOUT_MONO, AV_CHANNEL_LAYOUT_STEREO),
CODEC_SAMPLERATES_ARRAY(twolame_samplerates),
.p.wrapper_name = "libtwolame",
};
|