summaryrefslogtreecommitdiffstats
path: root/libavfilter/af_volume.c
blob: 3d76f12f2cc6647dc12af5f638978e4145e849d2 (plain)
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
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
/*
 * Copyright (c) 2011 Stefano Sabatini
 * Copyright (c) 2012 Justin Ruggles <justin.ruggles@gmail.com>
 *
 * 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
 * audio volume filter
 */

#include "libavutil/channel_layout.h"
#include "libavutil/common.h"
#include "libavutil/eval.h"
#include "libavutil/ffmath.h"
#include "libavutil/float_dsp.h"
#include "libavutil/intreadwrite.h"
#include "libavutil/opt.h"
#include "libavutil/replaygain.h"

#include "audio.h"
#include "avfilter.h"
#include "formats.h"
#include "internal.h"
#include "af_volume.h"

static const char * const precision_str[] = {
    "fixed", "float", "double"
};

static const char *const var_names[] = {
    "n",                   ///< frame number (starting at zero)
    "nb_channels",         ///< number of channels
    "nb_consumed_samples", ///< number of samples consumed by the filter
    "nb_samples",          ///< number of samples in the current frame
    "pos",                 ///< position in the file of the frame
    "pts",                 ///< frame presentation timestamp
    "sample_rate",         ///< sample rate
    "startpts",            ///< PTS at start of stream
    "startt",              ///< time at start of stream
    "t",                   ///< time in the file of the frame
    "tb",                  ///< timebase
    "volume",              ///< last set value
    NULL
};

#define OFFSET(x) offsetof(VolumeContext, x)
#define A AV_OPT_FLAG_AUDIO_PARAM
#define F AV_OPT_FLAG_FILTERING_PARAM

static const AVOption volume_options[] = {
    { "volume", "set volume adjustment expression",
            OFFSET(volume_expr), AV_OPT_TYPE_STRING, { .str = "1.0" }, .flags = A|F },
    { "precision", "select mathematical precision",
            OFFSET(precision), AV_OPT_TYPE_INT, { .i64 = PRECISION_FLOAT }, PRECISION_FIXED, PRECISION_DOUBLE, A|F, "precision" },
        { "fixed",  "select 8-bit fixed-point",     0, AV_OPT_TYPE_CONST, { .i64 = PRECISION_FIXED  }, INT_MIN, INT_MAX, A|F, "precision" },
        { "float",  "select 32-bit floating-point", 0, AV_OPT_TYPE_CONST, { .i64 = PRECISION_FLOAT  }, INT_MIN, INT_MAX, A|F, "precision" },
        { "double", "select 64-bit floating-point", 0, AV_OPT_TYPE_CONST, { .i64 = PRECISION_DOUBLE }, INT_MIN, INT_MAX, A|F, "precision" },
    { "eval", "specify when to evaluate expressions", OFFSET(eval_mode), AV_OPT_TYPE_INT, {.i64 = EVAL_MODE_ONCE}, 0, EVAL_MODE_NB-1, .flags = A|F, "eval" },
         { "once",  "eval volume expression once", 0, AV_OPT_TYPE_CONST, {.i64=EVAL_MODE_ONCE},  .flags = A|F, .unit = "eval" },
         { "frame", "eval volume expression per-frame",                  0, AV_OPT_TYPE_CONST, {.i64=EVAL_MODE_FRAME}, .flags = A|F, .unit = "eval" },
    { "replaygain", "Apply replaygain side data when present",
            OFFSET(replaygain), AV_OPT_TYPE_INT, { .i64 = REPLAYGAIN_DROP }, REPLAYGAIN_DROP, REPLAYGAIN_ALBUM, A|F, "replaygain" },
        { "drop",   "replaygain side data is dropped", 0, AV_OPT_TYPE_CONST, { .i64 = REPLAYGAIN_DROP   }, 0, 0, A|F, "replaygain" },
        { "ignore", "replaygain side data is ignored", 0, AV_OPT_TYPE_CONST, { .i64 = REPLAYGAIN_IGNORE }, 0, 0, A|F, "replaygain" },
        { "track",  "track gain is preferred",         0, AV_OPT_TYPE_CONST, { .i64 = REPLAYGAIN_TRACK  }, 0, 0, A|F, "replaygain" },
        { "album",  "album gain is preferred",         0, AV_OPT_TYPE_CONST, { .i64 = REPLAYGAIN_ALBUM  }, 0, 0, A|F, "replaygain" },
    { "replaygain_preamp", "Apply replaygain pre-amplification",
            OFFSET(replaygain_preamp), AV_OPT_TYPE_DOUBLE, { .dbl = 0.0 }, -15.0, 15.0, A|F },
    { "replaygain_noclip", "Apply replaygain clipping prevention",
            OFFSET(replaygain_noclip), AV_OPT_TYPE_BOOL, { .i64 = 1 }, 0, 1, A|F },
    { NULL }
};

AVFILTER_DEFINE_CLASS(volume);

static int set_expr(AVExpr **pexpr, const char *expr, void *log_ctx)
{
    int ret;
    AVExpr *old = NULL;

    if (*pexpr)
        old = *pexpr;
    ret = av_expr_parse(pexpr, expr, var_names,
                        NULL, NULL, NULL, NULL, 0, log_ctx);
    if (ret < 0) {
        av_log(log_ctx, AV_LOG_ERROR,
               "Error when evaluating the volume expression '%s'\n", expr);
        *pexpr = old;
        return ret;
    }

    av_expr_free(old);
    return 0;
}

static av_cold int init(AVFilterContext *ctx)
{
    VolumeContext *vol = ctx->priv;

    vol->fdsp = avpriv_float_dsp_alloc(0);
    if (!vol->fdsp)
        return AVERROR(ENOMEM);

    return set_expr(&vol->volume_pexpr, vol->volume_expr, ctx);
}

static av_cold void uninit(AVFilterContext *ctx)
{
    VolumeContext *vol = ctx->priv;
    av_expr_free(vol->volume_pexpr);
    av_opt_free(vol);
    av_freep(&vol->fdsp);
}

static int query_formats(AVFilterContext *ctx)
{
    VolumeContext *vol = ctx->priv;
    AVFilterFormats *formats = NULL;
    AVFilterChannelLayouts *layouts;
    static const enum AVSampleFormat sample_fmts[][7] = {
        [PRECISION_FIXED] = {
            AV_SAMPLE_FMT_U8,
            AV_SAMPLE_FMT_U8P,
            AV_SAMPLE_FMT_S16,
            AV_SAMPLE_FMT_S16P,
            AV_SAMPLE_FMT_S32,
            AV_SAMPLE_FMT_S32P,
            AV_SAMPLE_FMT_NONE
        },
        [PRECISION_FLOAT] = {
            AV_SAMPLE_FMT_FLT,
            AV_SAMPLE_FMT_FLTP,
            AV_SAMPLE_FMT_NONE
        },
        [PRECISION_DOUBLE] = {
            AV_SAMPLE_FMT_DBL,
            AV_SAMPLE_FMT_DBLP,
            AV_SAMPLE_FMT_NONE
        }
    };
    int ret;

    layouts = ff_all_channel_counts();
    if (!layouts)
        return AVERROR(ENOMEM);
    ret = ff_set_common_channel_layouts(ctx, layouts);
    if (ret < 0)
        return ret;

    formats = ff_make_format_list(sample_fmts[vol->precision]);
    if (!formats)
        return AVERROR(ENOMEM);
    ret = ff_set_common_formats(ctx, formats);
    if (ret < 0)
        return ret;

    formats = ff_all_samplerates();
    if (!formats)
        return AVERROR(ENOMEM);
    return ff_set_common_samplerates(ctx, formats);
}

static inline void scale_samples_u8(uint8_t *dst, const uint8_t *src,
                                    int nb_samples, int volume)
{
    int i;
    for (i = 0; i < nb_samples; i++)
        dst[i] = av_clip_uint8(((((int64_t)src[i] - 128) * volume + 128) >> 8) + 128);
}

static inline void scale_samples_u8_small(uint8_t *dst, const uint8_t *src,
                                          int nb_samples, int volume)
{
    int i;
    for (i = 0; i < nb_samples; i++)
        dst[i] = av_clip_uint8((((src[i] - 128) * volume + 128) >> 8) + 128);
}

static inline void scale_samples_s16(uint8_t *dst, const uint8_t *src,
                                     int nb_samples, int volume)
{
    int i;
    int16_t *smp_dst       = (int16_t *)dst;
    const int16_t *smp_src = (const int16_t *)src;
    for (i = 0; i < nb_samples; i++)
        smp_dst[i] = av_clip_int16(((int64_t)smp_src[i] * volume + 128) >> 8);
}

static inline void scale_samples_s16_small(uint8_t *dst, const uint8_t *src,
                                           int nb_samples, int volume)
{
    int i;
    int16_t *smp_dst       = (int16_t *)dst;
    const int16_t *smp_src = (const int16_t *)src;
    for (i = 0; i < nb_samples; i++)
        smp_dst[i] = av_clip_int16((smp_src[i] * volume + 128) >> 8);
}

static inline void scale_samples_s32(uint8_t *dst, const uint8_t *src,
                                     int nb_samples, int volume)
{
    int i;
    int32_t *smp_dst       = (int32_t *)dst;
    const int32_t *smp_src = (const int32_t *)src;
    for (i = 0; i < nb_samples; i++)
        smp_dst[i] = av_clipl_int32((((int64_t)smp_src[i] * volume + 128) >> 8));
}

static av_cold void volume_init(VolumeContext *vol)
{
    vol->samples_align = 1;

    switch (av_get_packed_sample_fmt(vol->sample_fmt)) {
    case AV_SAMPLE_FMT_U8:
        if (vol->volume_i < 0x1000000)
            vol->scale_samples = scale_samples_u8_small;
        else
            vol->scale_samples = scale_samples_u8;
        break;
    case AV_SAMPLE_FMT_S16:
        if (vol->volume_i < 0x10000)
            vol->scale_samples = scale_samples_s16_small;
        else
            vol->scale_samples = scale_samples_s16;
        break;
    case AV_SAMPLE_FMT_S32:
        vol->scale_samples = scale_samples_s32;
        break;
    case AV_SAMPLE_FMT_FLT:
        vol->samples_align = 4;
        break;
    case AV_SAMPLE_FMT_DBL:
        vol->samples_align = 8;
        break;
    }

    if (ARCH_X86)
        ff_volume_init_x86(vol);
}

static int set_volume(AVFilterContext *ctx)
{
    VolumeContext *vol = ctx->priv;

    vol->volume = av_expr_eval(vol->volume_pexpr, vol->var_values, NULL);
    if (isnan(vol->volume)) {
        if (vol->eval_mode == EVAL_MODE_ONCE) {
            av_log(ctx, AV_LOG_ERROR, "Invalid value NaN for volume\n");
            return AVERROR(EINVAL);
        } else {
            av_log(ctx, AV_LOG_WARNING, "Invalid value NaN for volume, setting to 0\n");
            vol->volume = 0;
        }
    }
    vol->var_values[VAR_VOLUME] = vol->volume;

    av_log(ctx, AV_LOG_VERBOSE, "n:%f t:%f pts:%f precision:%s ",
           vol->var_values[VAR_N], vol->var_values[VAR_T], vol->var_values[VAR_PTS],
           precision_str[vol->precision]);

    if (vol->precision == PRECISION_FIXED) {
        vol->volume_i = (int)(vol->volume * 256 + 0.5);
        vol->volume   = vol->volume_i / 256.0;
        av_log(ctx, AV_LOG_VERBOSE, "volume_i:%d/255 ", vol->volume_i);
    }
    av_log(ctx, AV_LOG_VERBOSE, "volume:%f volume_dB:%f\n",
           vol->volume, 20.0*log10(vol->volume));

    volume_init(vol);
    return 0;
}

static int config_output(AVFilterLink *outlink)
{
    AVFilterContext *ctx = outlink->src;
    VolumeContext *vol   = ctx->priv;
    AVFilterLink *inlink = ctx->inputs[0];

    vol->sample_fmt = inlink->format;
    vol->channels   = inlink->channels;
    vol->planes     = av_sample_fmt_is_planar(inlink->format) ? vol->channels : 1;

    vol->var_values[VAR_N] =
    vol->var_values[VAR_NB_CONSUMED_SAMPLES] =
    vol->var_values[VAR_NB_SAMPLES] =
    vol->var_values[VAR_POS] =
    vol->var_values[VAR_PTS] =
    vol->var_values[VAR_STARTPTS] =
    vol->var_values[VAR_STARTT] =
    vol->var_values[VAR_T] =
    vol->var_values[VAR_VOLUME] = NAN;

    vol->var_values[VAR_NB_CHANNELS] = inlink->channels;
    vol->var_values[VAR_TB]          = av_q2d(inlink->time_base);
    vol->var_values[VAR_SAMPLE_RATE] = inlink->sample_rate;

    av_log(inlink->src, AV_LOG_VERBOSE, "tb:%f sample_rate:%f nb_channels:%f\n",
           vol->var_values[VAR_TB],
           vol->var_values[VAR_SAMPLE_RATE],
           vol->var_values[VAR_NB_CHANNELS]);

    return set_volume(ctx);
}

static int process_command(AVFilterContext *ctx, const char *cmd, const char *args,
                           char *res, int res_len, int flags)
{
    VolumeContext *vol = ctx->priv;
    int ret = AVERROR(ENOSYS);

    if (!strcmp(cmd, "volume")) {
        if ((ret = set_expr(&vol->volume_pexpr, args, ctx)) < 0)
            return ret;
        if (vol->eval_mode == EVAL_MODE_ONCE)
            set_volume(ctx);
    }

    return ret;
}

#define D2TS(d)  (isnan(d) ? AV_NOPTS_VALUE : (int64_t)(d))
#define TS2D(ts) ((ts) == AV_NOPTS_VALUE ? NAN : (double)(ts))
#define TS2T(ts, tb) ((ts) == AV_NOPTS_VALUE ? NAN : (double)(ts)*av_q2d(tb))

static int filter_frame(AVFilterLink *inlink, AVFrame *buf)
{
    AVFilterContext *ctx = inlink->dst;
    VolumeContext *vol    = inlink->dst->priv;
    AVFilterLink *outlink = inlink->dst->outputs[0];
    int nb_samples        = buf->nb_samples;
    AVFrame *out_buf;
    int64_t pos;
    AVFrameSideData *sd = av_frame_get_side_data(buf, AV_FRAME_DATA_REPLAYGAIN);
    int ret;

    if (sd && vol->replaygain != REPLAYGAIN_IGNORE) {
        if (vol->replaygain != REPLAYGAIN_DROP) {
            AVReplayGain *replaygain = (AVReplayGain*)sd->data;
            int32_t gain  = 100000;
            uint32_t peak = 100000;
            float g, p;

            if (vol->replaygain == REPLAYGAIN_TRACK &&
                replaygain->track_gain != INT32_MIN) {
                gain = replaygain->track_gain;

                if (replaygain->track_peak != 0)
                    peak = replaygain->track_peak;
            } else if (replaygain->album_gain != INT32_MIN) {
                gain = replaygain->album_gain;

                if (replaygain->album_peak != 0)
                    peak = replaygain->album_peak;
            } else {
                av_log(inlink->dst, AV_LOG_WARNING, "Both ReplayGain gain "
                       "values are unknown.\n");
            }
            g = gain / 100000.0f;
            p = peak / 100000.0f;

            av_log(inlink->dst, AV_LOG_VERBOSE,
                   "Using gain %f dB from replaygain side data.\n", g);

            vol->volume   = ff_exp10((g + vol->replaygain_preamp) / 20);
            if (vol->replaygain_noclip)
                vol->volume = FFMIN(vol->volume, 1.0 / p);
            vol->volume_i = (int)(vol->volume * 256 + 0.5);

            volume_init(vol);
        }
        av_frame_remove_side_data(buf, AV_FRAME_DATA_REPLAYGAIN);
    }

    if (isnan(vol->var_values[VAR_STARTPTS])) {
        vol->var_values[VAR_STARTPTS] = TS2D(buf->pts);
        vol->var_values[VAR_STARTT  ] = TS2T(buf->pts, inlink->time_base);
    }
    vol->var_values[VAR_PTS] = TS2D(buf->pts);
    vol->var_values[VAR_T  ] = TS2T(buf->pts, inlink->time_base);
    vol->var_values[VAR_N  ] = inlink->frame_count_out;

    pos = buf->pkt_pos;
    vol->var_values[VAR_POS] = pos == -1 ? NAN : pos;
    if (vol->eval_mode == EVAL_MODE_FRAME)
        set_volume(ctx);

    if (vol->volume == 1.0 || vol->volume_i == 256) {
        out_buf = buf;
        goto end;
    }

    /* do volume scaling in-place if input buffer is writable */
    if (av_frame_is_writable(buf)
            && (vol->precision != PRECISION_FIXED || vol->volume_i > 0)) {
        out_buf = buf;
    } else {
        out_buf = ff_get_audio_buffer(inlink, nb_samples);
        if (!out_buf) {
            av_frame_free(&buf);
            return AVERROR(ENOMEM);
        }
        ret = av_frame_copy_props(out_buf, buf);
        if (ret < 0) {
            av_frame_free(&out_buf);
            av_frame_free(&buf);
            return ret;
        }
    }

    if (vol->precision != PRECISION_FIXED || vol->volume_i > 0) {
        int p, plane_samples;

        if (av_sample_fmt_is_planar(buf->format))
            plane_samples = FFALIGN(nb_samples, vol->samples_align);
        else
            plane_samples = FFALIGN(nb_samples * vol->channels, vol->samples_align);

        if (vol->precision == PRECISION_FIXED) {
            for (p = 0; p < vol->planes; p++) {
                vol->scale_samples(out_buf->extended_data[p],
                                   buf->extended_data[p], plane_samples,
                                   vol->volume_i);
            }
        } else if (av_get_packed_sample_fmt(vol->sample_fmt) == AV_SAMPLE_FMT_FLT) {
            for (p = 0; p < vol->planes; p++) {
                vol->fdsp->vector_fmul_scalar((float *)out_buf->extended_data[p],
                                             (const float *)buf->extended_data[p],
                                             vol->volume, plane_samples);
            }
        } else {
            for (p = 0; p < vol->planes; p++) {
                vol->fdsp->vector_dmul_scalar((double *)out_buf->extended_data[p],
                                             (const double *)buf->extended_data[p],
                                             vol->volume, plane_samples);
            }
        }
    }

    emms_c();

    if (buf != out_buf)
        av_frame_free(&buf);

end:
    vol->var_values[VAR_NB_CONSUMED_SAMPLES] += out_buf->nb_samples;
    return ff_filter_frame(outlink, out_buf);
}

static const AVFilterPad avfilter_af_volume_inputs[] = {
    {
        .name           = "default",
        .type           = AVMEDIA_TYPE_AUDIO,
        .filter_frame   = filter_frame,
    },
    { NULL }
};

static const AVFilterPad avfilter_af_volume_outputs[] = {
    {
        .name         = "default",
        .type         = AVMEDIA_TYPE_AUDIO,
        .config_props = config_output,
    },
    { NULL }
};

AVFilter ff_af_volume = {
    .name           = "volume",
    .description    = NULL_IF_CONFIG_SMALL("Change input volume."),
    .query_formats  = query_formats,
    .priv_size      = sizeof(VolumeContext),
    .priv_class     = &volume_class,
    .init           = init,
    .uninit         = uninit,
    .inputs         = avfilter_af_volume_inputs,
    .outputs        = avfilter_af_volume_outputs,
    .flags          = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC,
    .process_command = process_command,
};
OpenPOWER on IntegriCloud