aboutsummaryrefslogtreecommitdiffstats
path: root/libavformat/dss.c
blob: 083eb4ad43b2f9cb1b25f35f53ea2dd47dc1aae4 (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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
/*
 * Digital Speech Standard (DSS) demuxer
 * Copyright (c) 2014 Oleksij Rempel <linux@rempel-privat.de>
 *
 * 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
 */

#include "libavutil/attributes.h"
#include "libavutil/bswap.h"
#include "libavutil/channel_layout.h"
#include "libavutil/intreadwrite.h"

#include "avformat.h"
#include "internal.h"

#define DSS_HEAD_OFFSET_AUTHOR        0xc
#define DSS_AUTHOR_SIZE               16

#define DSS_HEAD_OFFSET_START_TIME    0x26
#define DSS_HEAD_OFFSET_END_TIME      0x32
#define DSS_TIME_SIZE                 12

#define DSS_HEAD_OFFSET_ACODEC        0x2a4
#define DSS_ACODEC_DSS_SP             0x0    /* SP mode */
#define DSS_ACODEC_G723_1             0x2    /* LP mode */

#define DSS_HEAD_OFFSET_COMMENT       0x31e
#define DSS_COMMENT_SIZE              64

#define DSS_BLOCK_SIZE                512
#define DSS_AUDIO_BLOCK_HEADER_SIZE   6
#define DSS_FRAME_SIZE                42

static const uint8_t frame_size[4] = { 24, 20, 4, 1 };

typedef struct DSSDemuxContext {
    unsigned int audio_codec;
    int counter;
    int swap;
    int dss_sp_swap_byte;
    int8_t *dss_sp_buf;

    int packet_size;
    int dss_header_size;
} DSSDemuxContext;

static int dss_probe(AVProbeData *p)
{
    if (   AV_RL32(p->buf) != MKTAG(0x2, 'd', 's', 's')
        && AV_RL32(p->buf) != MKTAG(0x3, 'd', 's', 's'))
        return 0;

    return AVPROBE_SCORE_MAX;
}

static int dss_read_metadata_date(AVFormatContext *s, unsigned int offset,
                                  const char *key)
{
    AVIOContext *pb = s->pb;
    char datetime[64], string[DSS_TIME_SIZE + 1] = { 0 };
    int y, month, d, h, minute, sec;
    int ret;

    avio_seek(pb, offset, SEEK_SET);

    ret = avio_read(s->pb, string, DSS_TIME_SIZE);
    if (ret < DSS_TIME_SIZE)
        return ret < 0 ? ret : AVERROR_EOF;

    if (sscanf(string, "%2d%2d%2d%2d%2d%2d", &y, &month, &d, &h, &minute, &sec) != 6)
        return AVERROR_INVALIDDATA;
    /* We deal with a two-digit year here, so set the default date to 2000
     * and hope it will never be used in the next century. */
    snprintf(datetime, sizeof(datetime), "%.4d-%.2d-%.2dT%.2d:%.2d:%.2d",
             y + 2000, month, d, h, minute, sec);
    return av_dict_set(&s->metadata, key, datetime, 0);
}

static int dss_read_metadata_string(AVFormatContext *s, unsigned int offset,
                                    unsigned int size, const char *key)
{
    AVIOContext *pb = s->pb;
    char *value;
    int ret;

    avio_seek(pb, offset, SEEK_SET);

    value = av_mallocz(size + 1);
    if (!value)
        return AVERROR(ENOMEM);

    ret = avio_read(s->pb, value, size);
    if (ret < size) {
        ret = ret < 0 ? ret : AVERROR_EOF;
        goto exit;
    }

    ret = av_dict_set(&s->metadata, key, value, 0);

exit:
    av_free(value);
    return ret;
}

static int dss_read_header(AVFormatContext *s)
{
    DSSDemuxContext *ctx = s->priv_data;
    AVIOContext *pb = s->pb;
    AVStream *st;
    int ret, version;

    st = avformat_new_stream(s, NULL);
    if (!st)
        return AVERROR(ENOMEM);

    version = avio_r8(pb);
    ctx->dss_header_size = version * DSS_BLOCK_SIZE;

    ret = dss_read_metadata_string(s, DSS_HEAD_OFFSET_AUTHOR,
                                   DSS_AUTHOR_SIZE, "author");
    if (ret)
        return ret;

    ret = dss_read_metadata_date(s, DSS_HEAD_OFFSET_END_TIME, "date");
    if (ret)
        return ret;

    ret = dss_read_metadata_string(s, DSS_HEAD_OFFSET_COMMENT,
                                   DSS_COMMENT_SIZE, "comment");
    if (ret)
        return ret;

    avio_seek(pb, DSS_HEAD_OFFSET_ACODEC, SEEK_SET);
    ctx->audio_codec = avio_r8(pb);

    if (ctx->audio_codec == DSS_ACODEC_DSS_SP) {
        st->codecpar->codec_id    = AV_CODEC_ID_DSS_SP;
        st->codecpar->sample_rate = 11025;
    } else if (ctx->audio_codec == DSS_ACODEC_G723_1) {
        st->codecpar->codec_id    = AV_CODEC_ID_G723_1;
        st->codecpar->sample_rate = 8000;
    } else {
        avpriv_request_sample(s, "Support for codec %x in DSS",
                              ctx->audio_codec);
        return AVERROR_PATCHWELCOME;
    }

    st->codecpar->codec_type     = AVMEDIA_TYPE_AUDIO;
    st->codecpar->channel_layout = AV_CH_LAYOUT_MONO;
    st->codecpar->channels       = 1;

    avpriv_set_pts_info(st, 64, 1, st->codecpar->sample_rate);
    st->start_time = 0;

    /* Jump over header */

    if (avio_seek(pb, ctx->dss_header_size, SEEK_SET) != ctx->dss_header_size)
        return AVERROR(EIO);

    ctx->counter = 0;
    ctx->swap    = 0;

    ctx->dss_sp_buf = av_malloc(DSS_FRAME_SIZE + 1);
    if (!ctx->dss_sp_buf)
        return AVERROR(ENOMEM);

    return 0;
}

static void dss_skip_audio_header(AVFormatContext *s, AVPacket *pkt)
{
    DSSDemuxContext *ctx = s->priv_data;
    AVIOContext *pb = s->pb;

    avio_skip(pb, DSS_AUDIO_BLOCK_HEADER_SIZE);
    ctx->counter += DSS_BLOCK_SIZE - DSS_AUDIO_BLOCK_HEADER_SIZE;
}

static void dss_sp_byte_swap(DSSDemuxContext *ctx,
                             uint8_t *dst, const uint8_t *src)
{
    int i;

    if (ctx->swap) {
        for (i = 3; i < DSS_FRAME_SIZE; i += 2)
            dst[i] = src[i];

        for (i = 0; i < DSS_FRAME_SIZE - 2; i += 2)
            dst[i] = src[i + 4];

        dst[1] = ctx->dss_sp_swap_byte;
    } else {
        memcpy(dst, src, DSS_FRAME_SIZE);
        ctx->dss_sp_swap_byte = src[DSS_FRAME_SIZE - 2];
    }

    /* make sure byte 40 is always 0 */
    dst[DSS_FRAME_SIZE - 2] = 0;
    ctx->swap             ^= 1;
}

static int dss_sp_read_packet(AVFormatContext *s, AVPacket *pkt)
{
    DSSDemuxContext *ctx = s->priv_data;
    AVStream *st = s->streams[0];
    int read_size, ret, offset = 0, buff_offset = 0;
    int64_t pos = avio_tell(s->pb);

    if (ctx->counter == 0)
        dss_skip_audio_header(s, pkt);

    if (ctx->swap) {
        read_size   = DSS_FRAME_SIZE - 2;
        buff_offset = 3;
    } else
        read_size = DSS_FRAME_SIZE;

    ctx->counter -= read_size;
    ctx->packet_size = DSS_FRAME_SIZE - 1;

    ret = av_new_packet(pkt, DSS_FRAME_SIZE);
    if (ret < 0)
        return ret;

    pkt->duration     = 264;
    pkt->pos = pos;
    pkt->stream_index = 0;
    s->bit_rate = 8LL * ctx->packet_size * st->codecpar->sample_rate * 512 / (506 * pkt->duration);

    if (ctx->counter < 0) {
        int size2 = ctx->counter + read_size;

        ret = avio_read(s->pb, ctx->dss_sp_buf + offset + buff_offset,
                        size2 - offset);
        if (ret < size2 - offset)
            goto error_eof;

        dss_skip_audio_header(s, pkt);
        offset = size2;
    }

    ret = avio_read(s->pb, ctx->dss_sp_buf + offset + buff_offset,
                    read_size - offset);
    if (ret < read_size - offset)
        goto error_eof;

    dss_sp_byte_swap(ctx, pkt->data, ctx->dss_sp_buf);

    if (ctx->dss_sp_swap_byte < 0) {
        ret = AVERROR(EAGAIN);
        goto error_eof;
    }

    return pkt->size;

error_eof:
    av_packet_unref(pkt);
    return ret < 0 ? ret : AVERROR_EOF;
}

static int dss_723_1_read_packet(AVFormatContext *s, AVPacket *pkt)
{
    DSSDemuxContext *ctx = s->priv_data;
    AVStream *st = s->streams[0];
    int size, byte, ret, offset;
    int64_t pos = avio_tell(s->pb);

    if (ctx->counter == 0)
        dss_skip_audio_header(s, pkt);

    /* We make one byte-step here. Don't forget to add offset. */
    byte = avio_r8(s->pb);
    if (byte == 0xff)
        return AVERROR_INVALIDDATA;

    size = frame_size[byte & 3];

    ctx->packet_size = size;
    ctx->counter -= size;

    ret = av_new_packet(pkt, size);
    if (ret < 0)
        return ret;
    pkt->pos = pos;

    pkt->data[0]  = byte;
    offset        = 1;
    pkt->duration = 240;
    s->bit_rate = 8LL * size * st->codecpar->sample_rate * 512 / (506 * pkt->duration);

    pkt->stream_index = 0;

    if (ctx->counter < 0) {
        int size2 = ctx->counter + size;

        ret = avio_read(s->pb, pkt->data + offset,
                        size2 - offset);
        if (ret < size2 - offset) {
            av_packet_unref(pkt);
            return ret < 0 ? ret : AVERROR_EOF;
        }

        dss_skip_audio_header(s, pkt);
        offset = size2;
    }

    ret = avio_read(s->pb, pkt->data + offset, size - offset);
    if (ret < size - offset) {
        av_packet_unref(pkt);
        return ret < 0 ? ret : AVERROR_EOF;
    }

    return pkt->size;
}

static int dss_read_packet(AVFormatContext *s, AVPacket *pkt)
{
    DSSDemuxContext *ctx = s->priv_data;

    if (ctx->audio_codec == DSS_ACODEC_DSS_SP)
        return dss_sp_read_packet(s, pkt);
    else
        return dss_723_1_read_packet(s, pkt);
}

static int dss_read_close(AVFormatContext *s)
{
    DSSDemuxContext *ctx = s->priv_data;

    av_freep(&ctx->dss_sp_buf);

    return 0;
}

static int dss_read_seek(AVFormatContext *s, int stream_index,
                         int64_t timestamp, int flags)
{
    DSSDemuxContext *ctx = s->priv_data;
    int64_t ret, seekto;
    uint8_t header[DSS_AUDIO_BLOCK_HEADER_SIZE];
    int offset;

    if (ctx->audio_codec == DSS_ACODEC_DSS_SP)
        seekto = timestamp / 264 * 41 / 506 * 512;
    else
        seekto = timestamp / 240 * ctx->packet_size / 506 * 512;

    if (seekto < 0)
        seekto = 0;

    seekto += ctx->dss_header_size;

    ret = avio_seek(s->pb, seekto, SEEK_SET);
    if (ret < 0)
        return ret;

    avio_read(s->pb, header, DSS_AUDIO_BLOCK_HEADER_SIZE);
    ctx->swap = !!(header[0] & 0x80);
    offset = 2*header[1] + 2*ctx->swap;
    if (offset < DSS_AUDIO_BLOCK_HEADER_SIZE)
        return AVERROR_INVALIDDATA;
    if (offset == DSS_AUDIO_BLOCK_HEADER_SIZE) {
        ctx->counter = 0;
        offset = avio_skip(s->pb, -DSS_AUDIO_BLOCK_HEADER_SIZE);
    } else {
        ctx->counter = DSS_BLOCK_SIZE - offset;
        offset = avio_skip(s->pb, offset - DSS_AUDIO_BLOCK_HEADER_SIZE);
    }
    ctx->dss_sp_swap_byte = -1;
    return 0;
}


AVInputFormat ff_dss_demuxer = {
    .name           = "dss",
    .long_name      = NULL_IF_CONFIG_SMALL("Digital Speech Standard (DSS)"),
    .priv_data_size = sizeof(DSSDemuxContext),
    .read_probe     = dss_probe,
    .read_header    = dss_read_header,
    .read_packet    = dss_read_packet,
    .read_close     = dss_read_close,
    .read_seek      = dss_read_seek,
    .extensions     = "dss"
};