aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/ttaenc.c
blob: aefa2bee00ee0a7be6fae647399ab90f971f00ed (plain) (blame)
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
/*
 * TTA (The Lossless True Audio) encoder
 *
 * 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
 */

#define BITSTREAM_WRITER_LE
#include "ttadata.h"
#include "ttaencdsp.h"
#include "avcodec.h"
#include "codec_internal.h"
#include "encode.h"
#include "put_bits.h"
#include "internal.h"
#include "libavutil/crc.h"

typedef struct TTAEncContext {
    const AVCRC *crc_table;
    int bps;
    TTAChannel *ch_ctx;
    TTAEncDSPContext dsp;
} TTAEncContext;

static av_cold int tta_encode_init(AVCodecContext *avctx)
{
    TTAEncContext *s = avctx->priv_data;

    s->crc_table = av_crc_get_table(AV_CRC_32_IEEE_LE);

    switch (avctx->sample_fmt) {
    case AV_SAMPLE_FMT_U8:
        avctx->bits_per_raw_sample = 8;
        break;
    case AV_SAMPLE_FMT_S16:
        avctx->bits_per_raw_sample = 16;
        break;
    case AV_SAMPLE_FMT_S32:
        if (avctx->bits_per_raw_sample > 24)
            av_log(avctx, AV_LOG_WARNING, "encoding as 24 bits-per-sample\n");
        avctx->bits_per_raw_sample = 24;
    }

    s->bps = avctx->bits_per_raw_sample >> 3;
    avctx->frame_size = 256 * avctx->sample_rate / 245;

    s->ch_ctx = av_malloc_array(avctx->ch_layout.nb_channels, sizeof(*s->ch_ctx));
    if (!s->ch_ctx)
        return AVERROR(ENOMEM);

    ff_ttaencdsp_init(&s->dsp);

    return 0;
}

static int32_t get_sample(const AVFrame *frame, int sample,
                          enum AVSampleFormat format)
{
    int32_t ret;

    if (format == AV_SAMPLE_FMT_U8) {
        ret = frame->data[0][sample] - 0x80;
    } else if (format == AV_SAMPLE_FMT_S16) {
        const int16_t *ptr = (const int16_t *)frame->data[0];
        ret = ptr[sample];
    } else {
        const int32_t *ptr = (const int32_t *)frame->data[0];
        ret = ptr[sample] >> 8;
    }

    return ret;
}

static int tta_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
                            const AVFrame *frame, int *got_packet_ptr)
{
    TTAEncContext *s = avctx->priv_data;
    PutBitContext pb;
    int ret, i, out_bytes, cur_chan, res, samples;
    int64_t pkt_size =  frame->nb_samples * 2LL * avctx->ch_layout.nb_channels * s->bps;

pkt_alloc:
    cur_chan = 0, res = 0, samples = 0;
    if ((ret = ff_alloc_packet(avctx, avpkt, pkt_size)) < 0)
        return ret;
    init_put_bits(&pb, avpkt->data, avpkt->size);

    // init per channel states
    for (i = 0; i < avctx->ch_layout.nb_channels; i++) {
        s->ch_ctx[i].predictor = 0;
        ff_tta_filter_init(&s->ch_ctx[i].filter, ff_tta_filter_configs[s->bps - 1]);
        ff_tta_rice_init(&s->ch_ctx[i].rice, 10, 10);
    }

    for (i = 0; i < frame->nb_samples * avctx->ch_layout.nb_channels; i++) {
        TTAChannel *c = &s->ch_ctx[cur_chan];
        TTAFilter *filter = &c->filter;
        TTARice *rice = &c->rice;
        uint32_t k, unary, outval;
        int32_t value, temp;

        value = get_sample(frame, samples++, avctx->sample_fmt);

        if (avctx->ch_layout.nb_channels > 1) {
            if (cur_chan < avctx->ch_layout.nb_channels - 1)
                value  = res = get_sample(frame, samples, avctx->sample_fmt) - value;
            else
                value -= res / 2;
        }

        temp = value;
#define PRED(x, k) (int32_t)((((uint64_t)(x) << (k)) - (x)) >> (k))
        switch (s->bps) {
        case 1: value -= PRED(c->predictor, 4); break;
        case 2:
        case 3: value -= PRED(c->predictor, 5); break;
        }
        c->predictor = temp;

        s->dsp.filter_process(filter->qm, filter->dx, filter->dl, &filter->error, &value,
                              filter->shift, filter->round);
        outval = (value > 0) ? (value << 1) - 1: -value << 1;

        k = rice->k0;

        rice->sum0 += outval - (rice->sum0 >> 4);
        if (rice->k0 > 0 && rice->sum0 < ff_tta_shift_16[rice->k0])
            rice->k0--;
        else if (rice->sum0 > ff_tta_shift_16[rice->k0 + 1])
            rice->k0++;

        if (outval >= ff_tta_shift_1[k]) {
            outval -= ff_tta_shift_1[k];
            k = rice->k1;

            rice->sum1 += outval - (rice->sum1 >> 4);
            if (rice->k1 > 0 && rice->sum1 < ff_tta_shift_16[rice->k1])
                rice->k1--;
            else if (rice->sum1 > ff_tta_shift_16[rice->k1 + 1])
                rice->k1++;

            unary = 1 + (outval >> k);
            if (unary + 100LL > put_bits_left(&pb)) {
                if (pkt_size < INT_MAX/2) {
                    pkt_size *= 2;
                    av_packet_unref(avpkt);
                    goto pkt_alloc;
                } else
                    return AVERROR(ENOMEM);
            }
            do {
                if (unary > 31) {
                    put_bits(&pb, 31, 0x7FFFFFFF);
                    unary -= 31;
                } else {
                    put_bits(&pb, unary, (1U << unary) - 1);
                    unary = 0;
                }
            } while (unary);
        }

        put_bits(&pb, 1, 0);

        if (k)
            put_bits(&pb, k, outval & (ff_tta_shift_1[k] - 1));

        if (cur_chan < avctx->ch_layout.nb_channels - 1)
            cur_chan++;
        else
            cur_chan = 0;
    }

    flush_put_bits(&pb);
    out_bytes = put_bytes_output(&pb);
    put_bits32(&pb, av_crc(s->crc_table, UINT32_MAX, avpkt->data, out_bytes) ^ UINT32_MAX);
    flush_put_bits(&pb);

    avpkt->pts      = frame->pts;
    avpkt->size     = out_bytes + 4;
    avpkt->duration = ff_samples_to_time_base(avctx, frame->nb_samples);
    *got_packet_ptr = 1;
    return 0;
}

static av_cold int tta_encode_close(AVCodecContext *avctx)
{
    TTAEncContext *s = avctx->priv_data;
    av_freep(&s->ch_ctx);
    return 0;
}

const AVCodec ff_tta_encoder = {
    .name           = "tta",
    .long_name      = NULL_IF_CONFIG_SMALL("TTA (True Audio)"),
    .type           = AVMEDIA_TYPE_AUDIO,
    .id             = AV_CODEC_ID_TTA,
    .priv_data_size = sizeof(TTAEncContext),
    .init           = tta_encode_init,
    .close          = tta_encode_close,
    .encode2        = tta_encode_frame,
    .capabilities   = AV_CODEC_CAP_SMALL_LAST_FRAME,
    .sample_fmts    = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_U8,
                                                     AV_SAMPLE_FMT_S16,
                                                     AV_SAMPLE_FMT_S32,
                                                     AV_SAMPLE_FMT_NONE },
    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE,
};