aboutsummaryrefslogtreecommitdiffstats
path: root/libavfilter/af_aecho.c
blob: 4e45ab9a8b649af9c7ed3c745ee736707fb73671 (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
/*
 * Copyright (c) 2013 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
 */

#include "libavutil/avassert.h"
#include "libavutil/avstring.h"
#include "libavutil/opt.h"
#include "libavutil/samplefmt.h"
#include "avfilter.h"
#include "audio.h"
#include "filters.h"
#include "internal.h"

typedef struct AudioEchoContext {
    const AVClass *class;
    float in_gain, out_gain;
    char *delays, *decays;
    float *delay, *decay;
    int nb_echoes;
    int delay_index;
    uint8_t **delayptrs;
    int max_samples, fade_out;
    int *samples;
    int eof;
    int64_t next_pts;

    void (*echo_samples)(struct AudioEchoContext *ctx, uint8_t **delayptrs,
                         uint8_t * const *src, uint8_t **dst,
                         int nb_samples, int channels);
} AudioEchoContext;

#define OFFSET(x) offsetof(AudioEchoContext, x)
#define A AV_OPT_FLAG_AUDIO_PARAM|AV_OPT_FLAG_FILTERING_PARAM

static const AVOption aecho_options[] = {
    { "in_gain",  "set signal input gain",  OFFSET(in_gain),  AV_OPT_TYPE_FLOAT,  {.dbl=0.6}, 0, 1, A },
    { "out_gain", "set signal output gain", OFFSET(out_gain), AV_OPT_TYPE_FLOAT,  {.dbl=0.3}, 0, 1, A },
    { "delays",   "set list of signal delays", OFFSET(delays), AV_OPT_TYPE_STRING, {.str="1000"}, 0, 0, A },
    { "decays",   "set list of signal decays", OFFSET(decays), AV_OPT_TYPE_STRING, {.str="0.5"}, 0, 0, A },
    { NULL }
};

AVFILTER_DEFINE_CLASS(aecho);

static void count_items(char *item_str, int *nb_items)
{
    char *p;

    *nb_items = 1;
    for (p = item_str; *p; p++) {
        if (*p == '|')
            (*nb_items)++;
    }

}

static void fill_items(char *item_str, int *nb_items, float *items)
{
    char *p, *saveptr = NULL;
    int i, new_nb_items = 0;

    p = item_str;
    for (i = 0; i < *nb_items; i++) {
        char *tstr = av_strtok(p, "|", &saveptr);
        p = NULL;
        if (tstr)
            new_nb_items += av_sscanf(tstr, "%f", &items[new_nb_items]) == 1;
    }

    *nb_items = new_nb_items;
}

static av_cold void uninit(AVFilterContext *ctx)
{
    AudioEchoContext *s = ctx->priv;

    av_freep(&s->delay);
    av_freep(&s->decay);
    av_freep(&s->samples);

    if (s->delayptrs)
        av_freep(&s->delayptrs[0]);
    av_freep(&s->delayptrs);
}

static av_cold int init(AVFilterContext *ctx)
{
    AudioEchoContext *s = ctx->priv;
    int nb_delays, nb_decays, i;

    if (!s->delays || !s->decays) {
        av_log(ctx, AV_LOG_ERROR, "Missing delays and/or decays.\n");
        return AVERROR(EINVAL);
    }

    count_items(s->delays, &nb_delays);
    count_items(s->decays, &nb_decays);

    s->delay = av_realloc_f(s->delay, nb_delays, sizeof(*s->delay));
    s->decay = av_realloc_f(s->decay, nb_decays, sizeof(*s->decay));
    if (!s->delay || !s->decay)
        return AVERROR(ENOMEM);

    fill_items(s->delays, &nb_delays, s->delay);
    fill_items(s->decays, &nb_decays, s->decay);

    if (nb_delays != nb_decays) {
        av_log(ctx, AV_LOG_ERROR, "Number of delays %d differs from number of decays %d.\n", nb_delays, nb_decays);
        return AVERROR(EINVAL);
    }

    s->nb_echoes = nb_delays;
    if (!s->nb_echoes) {
        av_log(ctx, AV_LOG_ERROR, "At least one decay & delay must be set.\n");
        return AVERROR(EINVAL);
    }

    s->samples = av_realloc_f(s->samples, nb_delays, sizeof(*s->samples));
    if (!s->samples)
        return AVERROR(ENOMEM);

    for (i = 0; i < nb_delays; i++) {
        if (s->delay[i] <= 0 || s->delay[i] > 90000) {
            av_log(ctx, AV_LOG_ERROR, "delay[%d]: %f is out of allowed range: (0, 90000]\n", i, s->delay[i]);
            return AVERROR(EINVAL);
        }
        if (s->decay[i] <= 0 || s->decay[i] > 1) {
            av_log(ctx, AV_LOG_ERROR, "decay[%d]: %f is out of allowed range: (0, 1]\n", i, s->decay[i]);
            return AVERROR(EINVAL);
        }
    }

    s->next_pts = AV_NOPTS_VALUE;

    av_log(ctx, AV_LOG_DEBUG, "nb_echoes:%d\n", s->nb_echoes);
    return 0;
}

static int query_formats(AVFilterContext *ctx)
{
    AVFilterChannelLayouts *layouts;
    AVFilterFormats *formats;
    static const enum AVSampleFormat sample_fmts[] = {
        AV_SAMPLE_FMT_S16P, AV_SAMPLE_FMT_S32P,
        AV_SAMPLE_FMT_FLTP, 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);
    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);
}

#define MOD(a, b) (((a) >= (b)) ? (a) - (b) : (a))

#define ECHO(name, type, min, max)                                          \
static void echo_samples_## name ##p(AudioEchoContext *ctx,                 \
                                     uint8_t **delayptrs,                   \
                                     uint8_t * const *src, uint8_t **dst,   \
                                     int nb_samples, int channels)          \
{                                                                           \
    const double out_gain = ctx->out_gain;                                  \
    const double in_gain = ctx->in_gain;                                    \
    const int nb_echoes = ctx->nb_echoes;                                   \
    const int max_samples = ctx->max_samples;                               \
    int i, j, chan, av_uninit(index);                                       \
                                                                            \
    av_assert1(channels > 0); /* would corrupt delay_index */               \
                                                                            \
    for (chan = 0; chan < channels; chan++) {                               \
        const type *s = (type *)src[chan];                                  \
        type *d = (type *)dst[chan];                                        \
        type *dbuf = (type *)delayptrs[chan];                               \
                                                                            \
        index = ctx->delay_index;                                           \
        for (i = 0; i < nb_samples; i++, s++, d++) {                        \
            double out, in;                                                 \
                                                                            \
            in = *s;                                                        \
            out = in * in_gain;                                             \
            for (j = 0; j < nb_echoes; j++) {                               \
                int ix = index + max_samples - ctx->samples[j];             \
                ix = MOD(ix, max_samples);                                  \
                out += dbuf[ix] * ctx->decay[j];                            \
            }                                                               \
            out *= out_gain;                                                \
                                                                            \
            *d = av_clipd(out, min, max);                                   \
            dbuf[index] = in;                                               \
                                                                            \
            index = MOD(index + 1, max_samples);                            \
        }                                                                   \
    }                                                                       \
    ctx->delay_index = index;                                               \
}

ECHO(dbl, double,  -1.0,      1.0      )
ECHO(flt, float,   -1.0,      1.0      )
ECHO(s16, int16_t, INT16_MIN, INT16_MAX)
ECHO(s32, int32_t, INT32_MIN, INT32_MAX)

static int config_output(AVFilterLink *outlink)
{
    AVFilterContext *ctx = outlink->src;
    AudioEchoContext *s = ctx->priv;
    float volume = 1.0;
    int i;

    for (i = 0; i < s->nb_echoes; i++) {
        s->samples[i] = s->delay[i] * outlink->sample_rate / 1000.0;
        s->max_samples = FFMAX(s->max_samples, s->samples[i]);
        volume += s->decay[i];
    }

    if (s->max_samples <= 0) {
        av_log(ctx, AV_LOG_ERROR, "Nothing to echo - missing delay samples.\n");
        return AVERROR(EINVAL);
    }
    s->fade_out = s->max_samples;

    if (volume * s->in_gain * s->out_gain > 1.0)
        av_log(ctx, AV_LOG_WARNING,
               "out_gain %f can cause saturation of output\n", s->out_gain);

    switch (outlink->format) {
    case AV_SAMPLE_FMT_DBLP: s->echo_samples = echo_samples_dblp; break;
    case AV_SAMPLE_FMT_FLTP: s->echo_samples = echo_samples_fltp; break;
    case AV_SAMPLE_FMT_S16P: s->echo_samples = echo_samples_s16p; break;
    case AV_SAMPLE_FMT_S32P: s->echo_samples = echo_samples_s32p; break;
    }


    if (s->delayptrs)
        av_freep(&s->delayptrs[0]);
    av_freep(&s->delayptrs);

    return av_samples_alloc_array_and_samples(&s->delayptrs, NULL,
                                              outlink->channels,
                                              s->max_samples,
                                              outlink->format, 0);
}

static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
{
    AVFilterContext *ctx = inlink->dst;
    AudioEchoContext *s = ctx->priv;
    AVFrame *out_frame;

    if (av_frame_is_writable(frame)) {
        out_frame = frame;
    } else {
        out_frame = ff_get_audio_buffer(ctx->outputs[0], frame->nb_samples);
        if (!out_frame) {
            av_frame_free(&frame);
            return AVERROR(ENOMEM);
        }
        av_frame_copy_props(out_frame, frame);
    }

    s->echo_samples(s, s->delayptrs, frame->extended_data, out_frame->extended_data,
                    frame->nb_samples, inlink->channels);

    s->next_pts = frame->pts + av_rescale_q(frame->nb_samples, (AVRational){1, inlink->sample_rate}, inlink->time_base);

    if (frame != out_frame)
        av_frame_free(&frame);

    return ff_filter_frame(ctx->outputs[0], out_frame);
}

static int request_frame(AVFilterLink *outlink)
{
    AVFilterContext *ctx = outlink->src;
    AudioEchoContext *s = ctx->priv;
    int nb_samples = FFMIN(s->fade_out, 2048);
    AVFrame *frame = ff_get_audio_buffer(outlink, nb_samples);

    if (!frame)
        return AVERROR(ENOMEM);
    s->fade_out -= nb_samples;

    av_samples_set_silence(frame->extended_data, 0,
                           frame->nb_samples,
                           outlink->channels,
                           frame->format);

    s->echo_samples(s, s->delayptrs, frame->extended_data, frame->extended_data,
                    frame->nb_samples, outlink->channels);

    frame->pts = s->next_pts;
    if (s->next_pts != AV_NOPTS_VALUE)
        s->next_pts += av_rescale_q(nb_samples, (AVRational){1, outlink->sample_rate}, outlink->time_base);

    return ff_filter_frame(outlink, frame);
}

static int activate(AVFilterContext *ctx)
{
    AVFilterLink *inlink = ctx->inputs[0];
    AVFilterLink *outlink = ctx->outputs[0];
    AudioEchoContext *s = ctx->priv;
    AVFrame *in;
    int ret, status;
    int64_t pts;

    FF_FILTER_FORWARD_STATUS_BACK(outlink, inlink);

    ret = ff_inlink_consume_frame(inlink, &in);
    if (ret < 0)
        return ret;
    if (ret > 0)
        return filter_frame(inlink, in);

    if (!s->eof && ff_inlink_acknowledge_status(inlink, &status, &pts)) {
        if (status == AVERROR_EOF)
            s->eof = 1;
    }

    if (s->eof && s->fade_out <= 0) {
        ff_outlink_set_status(outlink, AVERROR_EOF, s->next_pts);
        return 0;
    }

    if (!s->eof)
        FF_FILTER_FORWARD_WANTED(outlink, inlink);

    return request_frame(outlink);
}

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

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

const AVFilter ff_af_aecho = {
    .name          = "aecho",
    .description   = NULL_IF_CONFIG_SMALL("Add echoing to the audio."),
    .query_formats = query_formats,
    .priv_size     = sizeof(AudioEchoContext),
    .priv_class    = &aecho_class,
    .init          = init,
    .activate      = activate,
    .uninit        = uninit,
    .inputs        = aecho_inputs,
    .outputs       = aecho_outputs,
};