/
SDL_audiocvt.c
1046 lines (889 loc) · 33.5 KB
1
2
/*
Simple DirectMedia Layer
3
Copyright (C) 1997-2017 Sam Lantinga <slouken@libsdl.org>
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
This software is provided 'as-is', without any express or implied
warranty. In no event will the authors be held liable for any damages
arising from the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it
freely, subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not
claim that you wrote the original software. If you use this software
in a product, an acknowledgment in the product documentation would be
appreciated but is not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
*/
#include "../SDL_internal.h"
/* Functions for audio drivers to perform runtime conversion of audio format */
#include "SDL_audio.h"
#include "SDL_audio_c.h"
28
#include "SDL_loadso.h"
29
#include "SDL_assert.h"
30
#include "../SDL_dataqueue.h"
31
32
33
34
35
#ifdef HAVE_LIBSAMPLERATE
#include "samplerate.h"
#endif
36
37
38
39
40
/* Effectively mix right and left channels into a single channel */
static void SDLCALL
SDL_ConvertMono(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
41
42
float *dst = (float *) cvt->buf;
const float *src = dst;
43
44
int i;
45
46
47
48
49
LOG_DEBUG_CONVERT("stereo", "mono");
SDL_assert(format == AUDIO_F32SYS);
for (i = cvt->len_cvt / 8; i; --i, src += 2) {
*(dst++) = (float) ((((double) src[0]) + ((double) src[1])) * 0.5);
50
51
52
53
54
55
56
57
58
59
60
61
62
}
cvt->len_cvt /= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Discard top 4 channels */
static void SDLCALL
SDL_ConvertStrip(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
63
64
float *dst = (float *) cvt->buf;
const float *src = dst;
65
66
int i;
67
68
LOG_DEBUG_CONVERT("6 channels", "stereo");
SDL_assert(format == AUDIO_F32SYS);
69
70
71
72
for (i = cvt->len_cvt / (sizeof (float) * 6); i; --i, src += 6, dst += 2) {
dst[0] = src[0];
dst[1] = src[1];
73
74
75
76
77
78
79
80
81
82
83
84
85
}
cvt->len_cvt /= 3;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Discard top 2 channels of 6 */
static void SDLCALL
SDL_ConvertStrip_2(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
86
87
float *dst = (float *) cvt->buf;
const float *src = dst;
88
89
int i;
90
91
LOG_DEBUG_CONVERT("6 channels", "quad");
SDL_assert(format == AUDIO_F32SYS);
92
93
94
95
96
97
for (i = cvt->len_cvt / (sizeof (float) * 6); i; --i, src += 6, dst += 4) {
dst[0] = src[0];
dst[1] = src[1];
dst[2] = src[2];
dst[3] = src[3];
98
99
100
101
102
103
104
105
106
107
108
109
110
}
cvt->len_cvt /= 6;
cvt->len_cvt *= 4;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Duplicate a mono channel to both stereo channels */
static void SDLCALL
SDL_ConvertStereo(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
111
112
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 2);
113
114
int i;
115
116
LOG_DEBUG_CONVERT("mono", "stereo");
SDL_assert(format == AUDIO_F32SYS);
117
118
119
120
121
for (i = cvt->len_cvt / sizeof (float); i; --i) {
src--;
dst -= 2;
dst[0] = dst[1] = *src;
122
123
124
125
126
127
128
129
130
131
132
133
134
135
}
cvt->len_cvt *= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Duplicate a stereo channel to a pseudo-5.1 stream */
static void SDLCALL
SDL_ConvertSurround(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
int i;
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
float lf, rf, ce;
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 3);
LOG_DEBUG_CONVERT("stereo", "5.1");
SDL_assert(format == AUDIO_F32SYS);
for (i = cvt->len_cvt / 8; i; --i) {
dst -= 6;
src -= 2;
lf = src[0];
rf = src[1];
ce = (lf * 0.5f) + (rf * 0.5f);
dst[0] = src[0];
dst[1] = src[1];
dst[2] = lf - ce;
dst[3] = rf - ce;
dst[4] = dst[5] = ce;
154
}
155
156
157
158
159
160
161
162
163
164
165
166
cvt->len_cvt *= 3;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
/* Duplicate a stereo channel to a pseudo-4.0 stream */
static void SDLCALL
SDL_ConvertSurround_4(SDL_AudioCVT * cvt, SDL_AudioFormat format)
{
167
168
169
const float *src = (const float *) (cvt->buf + cvt->len_cvt);
float *dst = (float *) (cvt->buf + cvt->len_cvt * 2);
float lf, rf, ce;
170
171
int i;
172
173
174
175
176
177
178
179
180
181
182
183
184
LOG_DEBUG_CONVERT("stereo", "quad");
SDL_assert(format == AUDIO_F32SYS);
for (i = cvt->len_cvt / 8; i; --i) {
dst -= 4;
src -= 2;
lf = src[0];
rf = src[1];
ce = (lf / 2) + (rf / 2);
dst[0] = src[0];
dst[1] = src[1];
dst[2] = lf - ce;
dst[3] = rf - ce;
185
}
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
cvt->len_cvt *= 2;
if (cvt->filters[++cvt->filter_index]) {
cvt->filters[cvt->filter_index] (cvt, format);
}
}
int
SDL_ConvertAudio(SDL_AudioCVT * cvt)
{
/* !!! FIXME: (cvt) should be const; stack-copy it here. */
/* !!! FIXME: (actually, we can't...len_cvt needs to be updated. Grr.) */
/* Make sure there's data to convert */
if (cvt->buf == NULL) {
202
return SDL_SetError("No buffer allocated for conversion");
203
}
204
205
206
207
/* Return okay if no conversion is necessary */
cvt->len_cvt = cvt->len;
if (cvt->filters[0] == NULL) {
208
return 0;
209
210
211
212
213
}
/* Set up the conversion and go! */
cvt->filter_index = 0;
cvt->filters[0] (cvt, cvt->src_format);
214
return 0;
215
216
}
217
218
static void SDLCALL
SDL_Convert_Byteswap(SDL_AudioCVT *cvt, SDL_AudioFormat format)
219
{
220
221
222
#if DEBUG_CONVERT
printf("Converting byte order\n");
#endif
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
switch (SDL_AUDIO_BITSIZE(format)) {
#define CASESWAP(b) \
case b: { \
Uint##b *ptr = (Uint##b *) cvt->buf; \
int i; \
for (i = cvt->len_cvt / sizeof (*ptr); i; --i, ++ptr) { \
*ptr = SDL_Swap##b(*ptr); \
} \
break; \
}
CASESWAP(16);
CASESWAP(32);
CASESWAP(64);
#undef CASESWAP
default: SDL_assert(!"unhandled byteswap datatype!"); break;
}
243
244
245
246
247
248
249
250
251
252
if (cvt->filters[++cvt->filter_index]) {
/* flip endian flag for data. */
if (format & SDL_AUDIO_MASK_ENDIAN) {
format &= ~SDL_AUDIO_MASK_ENDIAN;
} else {
format |= SDL_AUDIO_MASK_ENDIAN;
}
cvt->filters[cvt->filter_index](cvt, format);
}
253
254
255
256
}
static int
257
SDL_BuildAudioTypeCVTToFloat(SDL_AudioCVT *cvt, const SDL_AudioFormat src_fmt)
258
{
259
int retval = 0; /* 0 == no conversion necessary. */
260
261
262
263
264
if ((SDL_AUDIO_ISBIGENDIAN(src_fmt) != 0) == (SDL_BYTEORDER == SDL_LIL_ENDIAN)) {
cvt->filters[cvt->filter_index++] = SDL_Convert_Byteswap;
retval = 1; /* added a converter. */
}
265
266
if (!SDL_AUDIO_ISFLOAT(src_fmt)) {
267
268
const Uint16 src_bitsize = SDL_AUDIO_BITSIZE(src_fmt);
const Uint16 dst_bitsize = 32;
269
SDL_AudioFilter filter = NULL;
270
271
272
273
274
switch (src_fmt & ~SDL_AUDIO_MASK_ENDIAN) {
case AUDIO_S8: filter = SDL_Convert_S8_to_F32; break;
case AUDIO_U8: filter = SDL_Convert_U8_to_F32; break;
case AUDIO_S16: filter = SDL_Convert_S16_to_F32; break;
275
case AUDIO_U16: filter = SDL_Convert_U16_to_F32; break;
276
277
case AUDIO_S32: filter = SDL_Convert_S32_to_F32; break;
default: SDL_assert(!"Unexpected audio format!"); break;
278
279
}
280
281
282
283
if (!filter) {
return SDL_SetError("No conversion available for these formats");
}
284
285
286
287
288
289
290
291
cvt->filters[cvt->filter_index++] = filter;
if (src_bitsize < dst_bitsize) {
const int mult = (dst_bitsize / src_bitsize);
cvt->len_mult *= mult;
cvt->len_ratio *= mult;
} else if (src_bitsize > dst_bitsize) {
cvt->len_ratio /= (src_bitsize / dst_bitsize);
}
292
293
retval = 1; /* added a converter. */
294
295
}
296
return retval;
297
298
}
299
300
static int
SDL_BuildAudioTypeCVTFromFloat(SDL_AudioCVT *cvt, const SDL_AudioFormat dst_fmt)
301
{
302
303
304
int retval = 0; /* 0 == no conversion necessary. */
if (!SDL_AUDIO_ISFLOAT(dst_fmt)) {
305
306
const Uint16 dst_bitsize = SDL_AUDIO_BITSIZE(dst_fmt);
const Uint16 src_bitsize = 32;
307
308
309
310
311
SDL_AudioFilter filter = NULL;
switch (dst_fmt & ~SDL_AUDIO_MASK_ENDIAN) {
case AUDIO_S8: filter = SDL_Convert_F32_to_S8; break;
case AUDIO_U8: filter = SDL_Convert_F32_to_U8; break;
case AUDIO_S16: filter = SDL_Convert_F32_to_S16; break;
312
case AUDIO_U16: filter = SDL_Convert_F32_to_U16; break;
313
314
315
316
317
318
319
case AUDIO_S32: filter = SDL_Convert_F32_to_S32; break;
default: SDL_assert(!"Unexpected audio format!"); break;
}
if (!filter) {
return SDL_SetError("No conversion available for these formats");
}
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
cvt->filters[cvt->filter_index++] = filter;
if (src_bitsize < dst_bitsize) {
const int mult = (dst_bitsize / src_bitsize);
cvt->len_mult *= mult;
cvt->len_ratio *= mult;
} else if (src_bitsize > dst_bitsize) {
cvt->len_ratio /= (src_bitsize / dst_bitsize);
}
retval = 1; /* added a converter. */
}
if ((SDL_AUDIO_ISBIGENDIAN(dst_fmt) != 0) == (SDL_BYTEORDER == SDL_LIL_ENDIAN)) {
cvt->filters[cvt->filter_index++] = SDL_Convert_Byteswap;
retval = 1; /* added a converter. */
}
return retval;
338
339
340
}
341
342
343
344
/* !!! FIXME: We only have this macro salsa because SDL_AudioCVT doesn't store
!!! FIXME: channel info or integer sample rates, so we have to have
!!! FIXME: function entry points for each supported channel count and
!!! FIXME: multiple vs arbitrary. When we rev the ABI, remove this. */
345
346
#define RESAMPLER_FUNCS(chans) \
static void SDLCALL \
347
SDL_Upsample_Multiple_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) { \
348
SDL_assert(format == AUDIO_F32SYS); \
349
SDL_Upsample_Multiple(cvt, chans); \
350
351
} \
static void SDLCALL \
352
SDL_Upsample_Arbitrary_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) { \
353
SDL_assert(format == AUDIO_F32SYS); \
354
355
SDL_Upsample_Arbitrary(cvt, chans); \
}\
356
static void SDLCALL \
357
SDL_Downsample_Multiple_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) { \
358
SDL_assert(format == AUDIO_F32SYS); \
359
SDL_Downsample_Multiple(cvt, chans); \
360
361
} \
static void SDLCALL \
362
SDL_Downsample_Arbitrary_c##chans(SDL_AudioCVT *cvt, SDL_AudioFormat format) { \
363
SDL_assert(format == AUDIO_F32SYS); \
364
SDL_Downsample_Arbitrary(cvt, chans); \
365
366
367
368
369
370
371
372
}
RESAMPLER_FUNCS(1)
RESAMPLER_FUNCS(2)
RESAMPLER_FUNCS(4)
RESAMPLER_FUNCS(6)
RESAMPLER_FUNCS(8)
#undef RESAMPLER_FUNCS
373
static int
374
SDL_FindFrequencyMultiple(const int src_rate, const int dst_rate)
375
{
376
int lo, hi;
377
378
379
380
SDL_assert(src_rate != 0);
SDL_assert(dst_rate != 0);
SDL_assert(src_rate != dst_rate);
381
382
383
384
385
386
387
388
if (src_rate < dst_rate) {
lo = src_rate;
hi = dst_rate;
} else {
lo = dst_rate;
hi = src_rate;
}
389
390
391
if ((hi % lo) != 0)
return 0; /* not a multiple. */
392
393
394
return hi / lo;
}
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
static SDL_AudioFilter
ChooseResampler(const int dst_channels, const int src_rate, const int dst_rate)
{
const int upsample = (src_rate < dst_rate) ? 1 : 0;
const int multiple = SDL_FindFrequencyMultiple(src_rate, dst_rate);
SDL_AudioFilter filter = NULL;
#define PICK_CHANNEL_FILTER(upordown, resampler) switch (dst_channels) { \
case 1: filter = SDL_##upordown##_##resampler##_c1; break; \
case 2: filter = SDL_##upordown##_##resampler##_c2; break; \
case 4: filter = SDL_##upordown##_##resampler##_c4; break; \
case 6: filter = SDL_##upordown##_##resampler##_c6; break; \
case 8: filter = SDL_##upordown##_##resampler##_c8; break; \
default: break; \
}
if (upsample) {
if (multiple) {
PICK_CHANNEL_FILTER(Upsample, Multiple);
} else {
PICK_CHANNEL_FILTER(Upsample, Arbitrary);
}
} else {
if (multiple) {
PICK_CHANNEL_FILTER(Downsample, Multiple);
421
} else {
422
PICK_CHANNEL_FILTER(Downsample, Arbitrary);
423
}
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
}
#undef PICK_CHANNEL_FILTER
return filter;
}
static int
SDL_BuildAudioResampleCVT(SDL_AudioCVT * cvt, const int dst_channels,
const int src_rate, const int dst_rate)
{
SDL_AudioFilter filter;
if (src_rate == dst_rate) {
return 0; /* no conversion necessary. */
}
filter = ChooseResampler(dst_channels, src_rate, dst_rate);
if (filter == NULL) {
return SDL_SetError("No conversion available for these rates");
}
445
446
447
448
449
450
451
452
453
/* Update (cvt) with filter details... */
cvt->filters[cvt->filter_index++] = filter;
if (src_rate < dst_rate) {
const double mult = ((double) dst_rate) / ((double) src_rate);
cvt->len_mult *= (int) SDL_ceil(mult);
cvt->len_ratio *= mult;
} else {
cvt->len_ratio /= ((double) src_rate) / ((double) dst_rate);
454
455
}
456
return 1; /* added a converter. */
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
}
/* Creates a set of audio filters to convert from one format to another.
Returns -1 if the format conversion is not supported, 0 if there's
no conversion needed, or 1 if the audio filter is set up.
*/
int
SDL_BuildAudioCVT(SDL_AudioCVT * cvt,
SDL_AudioFormat src_fmt, Uint8 src_channels, int src_rate,
SDL_AudioFormat dst_fmt, Uint8 dst_channels, int dst_rate)
{
/* Sanity check target pointer */
if (cvt == NULL) {
return SDL_InvalidParamError("cvt");
}
475
476
477
/* Make sure we zero out the audio conversion before error checking */
SDL_zerop(cvt);
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
/* there are no unsigned types over 16 bits, so catch this up front. */
if ((SDL_AUDIO_BITSIZE(src_fmt) > 16) && (!SDL_AUDIO_ISSIGNED(src_fmt))) {
return SDL_SetError("Invalid source format");
}
if ((SDL_AUDIO_BITSIZE(dst_fmt) > 16) && (!SDL_AUDIO_ISSIGNED(dst_fmt))) {
return SDL_SetError("Invalid destination format");
}
/* prevent possible divisions by zero, etc. */
if ((src_channels == 0) || (dst_channels == 0)) {
return SDL_SetError("Source or destination channels is zero");
}
if ((src_rate == 0) || (dst_rate == 0)) {
return SDL_SetError("Source or destination rate is zero");
}
493
#if DEBUG_CONVERT
494
495
496
497
498
499
500
501
502
503
504
505
506
507
printf("Build format %04x->%04x, channels %u->%u, rate %d->%d\n",
src_fmt, dst_fmt, src_channels, dst_channels, src_rate, dst_rate);
#endif
/* Start off with no conversion necessary */
cvt->src_format = src_fmt;
cvt->dst_format = dst_fmt;
cvt->needed = 0;
cvt->filter_index = 0;
cvt->filters[0] = NULL;
cvt->len_mult = 1;
cvt->len_ratio = 1.0;
cvt->rate_incr = ((double) dst_rate) / ((double) src_rate);
508
509
510
511
512
513
514
515
516
/* Type conversion goes like this now:
- byteswap to CPU native format first if necessary.
- convert to native Float32 if necessary.
- resample and change channel count if necessary.
- convert back to native format.
- byteswap back to foreign format if necessary.
The expectation is we can process data faster in float32
(possibly with SIMD), and making several passes over the same
517
buffer is likely to be CPU cache-friendly, avoiding the
518
519
520
521
biggest performance hit in modern times. Previously we had
(script-generated) custom converters for every data type and
it was a bloat on SDL compile times and final library size. */
522
523
524
525
526
527
528
529
530
531
532
533
/* see if we can skip float conversion entirely. */
if (src_rate == dst_rate && src_channels == dst_channels) {
if (src_fmt == dst_fmt) {
return 0;
}
/* just a byteswap needed? */
if ((src_fmt & ~SDL_AUDIO_MASK_ENDIAN) == (dst_fmt & ~SDL_AUDIO_MASK_ENDIAN)) {
cvt->filters[cvt->filter_index++] = SDL_Convert_Byteswap;
cvt->needed = 1;
return 1;
}
534
535
}
536
/* Convert data types, if necessary. Updates (cvt). */
537
if (SDL_BuildAudioTypeCVTToFloat(cvt, src_fmt) < 0) {
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
return -1; /* shouldn't happen, but just in case... */
}
/* Channel conversion */
if (src_channels != dst_channels) {
if ((src_channels == 1) && (dst_channels > 1)) {
cvt->filters[cvt->filter_index++] = SDL_ConvertStereo;
cvt->len_mult *= 2;
src_channels = 2;
cvt->len_ratio *= 2;
}
if ((src_channels == 2) && (dst_channels == 6)) {
cvt->filters[cvt->filter_index++] = SDL_ConvertSurround;
src_channels = 6;
cvt->len_mult *= 3;
cvt->len_ratio *= 3;
}
if ((src_channels == 2) && (dst_channels == 4)) {
cvt->filters[cvt->filter_index++] = SDL_ConvertSurround_4;
src_channels = 4;
cvt->len_mult *= 2;
cvt->len_ratio *= 2;
}
while ((src_channels * 2) <= dst_channels) {
cvt->filters[cvt->filter_index++] = SDL_ConvertStereo;
cvt->len_mult *= 2;
src_channels *= 2;
cvt->len_ratio *= 2;
}
if ((src_channels == 6) && (dst_channels <= 2)) {
cvt->filters[cvt->filter_index++] = SDL_ConvertStrip;
src_channels = 2;
cvt->len_ratio /= 3;
}
if ((src_channels == 6) && (dst_channels == 4)) {
cvt->filters[cvt->filter_index++] = SDL_ConvertStrip_2;
src_channels = 4;
cvt->len_ratio /= 2;
}
/* This assumes that 4 channel audio is in the format:
Left {front/back} + Right {front/back}
so converting to L/R stereo works properly.
*/
while (((src_channels % 2) == 0) &&
((src_channels / 2) >= dst_channels)) {
cvt->filters[cvt->filter_index++] = SDL_ConvertMono;
src_channels /= 2;
cvt->len_ratio /= 2;
}
if (src_channels != dst_channels) {
/* Uh oh.. */ ;
}
}
/* Do rate conversion, if necessary. Updates (cvt). */
593
if (SDL_BuildAudioResampleCVT(cvt, dst_channels, src_rate, dst_rate) < 0) {
594
595
596
return -1; /* shouldn't happen, but just in case... */
}
597
/* Move to final data type. */
598
if (SDL_BuildAudioTypeCVTFromFloat(cvt, dst_fmt) < 0) {
599
return -1; /* shouldn't happen, but just in case... */
600
}
601
602
cvt->needed = (cvt->filter_index != 0);
603
604
605
return (cvt->needed);
}
606
607
608
typedef int (*SDL_ResampleAudioStreamFunc)(SDL_AudioStream *stream, const float *inbuf, const int inbuflen, float *outbuf, const int outbuflen);
typedef void (*SDL_ResetAudioStreamResamplerFunc)(SDL_AudioStream *stream);
typedef void (*SDL_CleanupAudioStreamResamplerFunc)(SDL_AudioStream *stream);
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
struct SDL_AudioStream
{
SDL_AudioCVT cvt_before_resampling;
SDL_AudioCVT cvt_after_resampling;
SDL_DataQueue *queue;
Uint8 *work_buffer;
int work_buffer_len;
Uint8 *resample_buffer;
int resample_buffer_len;
int src_sample_frame_size;
SDL_AudioFormat src_format;
Uint8 src_channels;
int src_rate;
int dst_sample_frame_size;
SDL_AudioFormat dst_format;
Uint8 dst_channels;
int dst_rate;
double rate_incr;
Uint8 pre_resample_channels;
int packetlen;
630
631
632
633
void *resampler_state;
SDL_ResampleAudioStreamFunc resampler_func;
SDL_ResetAudioStreamResamplerFunc reset_resampler_func;
SDL_CleanupAudioStreamResamplerFunc cleanup_resampler_func;
634
635
};
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
#ifdef HAVE_LIBSAMPLERATE
typedef struct
{
void *SRC_lib;
SRC_STATE* (*src_new)(int converter_type, int channels, int *error);
int (*src_process)(SRC_STATE *state, SRC_DATA *data);
int (*src_reset)(SRC_STATE *state);
SRC_STATE* (*src_delete)(SRC_STATE *state);
const char* (*src_strerror)(int error);
SRC_STATE *SRC_state;
} SDL_AudioStreamResamplerState_SRC;
static SDL_bool
LoadLibSampleRate(SDL_AudioStreamResamplerState_SRC *state)
{
#ifdef LIBSAMPLERATE_DYNAMIC
state->SRC_lib = SDL_LoadObject(LIBSAMPLERATE_DYNAMIC);
if (!state->SRC_lib) {
return SDL_FALSE;
}
#endif
state->src_new = (SRC_STATE* (*)(int converter_type, int channels, int *error))SDL_LoadFunction(state->SRC_lib, "src_new");
state->src_process = (int (*)(SRC_STATE *state, SRC_DATA *data))SDL_LoadFunction(state->SRC_lib, "src_process");
state->src_reset = (int(*)(SRC_STATE *state))SDL_LoadFunction(state->SRC_lib, "src_reset");
state->src_delete = (SRC_STATE* (*)(SRC_STATE *state))SDL_LoadFunction(state->SRC_lib, "src_delete");
state->src_strerror = (const char* (*)(int error))SDL_LoadFunction(state->SRC_lib, "src_strerror");
if (!state->src_new || !state->src_process || !state->src_reset || !state->src_delete || !state->src_strerror) {
return SDL_FALSE;
}
return SDL_TRUE;
}
static int
SDL_ResampleAudioStream_SRC(SDL_AudioStream *stream, const float *inbuf, const int inbuflen, float *outbuf, const int outbuflen)
{
SDL_AudioStreamResamplerState_SRC *state = (SDL_AudioStreamResamplerState_SRC*)stream->resampler_state;
SRC_DATA data;
int result;
data.data_in = inbuf;
data.input_frames = inbuflen / ( sizeof(float) * stream->pre_resample_channels );
data.input_frames_used = 0;
data.data_out = outbuf;
data.output_frames = outbuflen / (sizeof(float) * stream->pre_resample_channels);
data.end_of_input = 0;
data.src_ratio = stream->rate_incr;
result = state->src_process(state->SRC_state, &data);
if (result != 0) {
SDL_SetError("src_process() failed: %s", state->src_strerror(result));
return 0;
}
/* If this fails, we need to store them off somewhere */
SDL_assert(data.input_frames_used == data.input_frames);
return data.output_frames_gen * (sizeof(float) * stream->pre_resample_channels);
}
static void
SDL_ResetAudioStreamResampler_SRC(SDL_AudioStream *stream)
{
SDL_AudioStreamResamplerState_SRC *state = (SDL_AudioStreamResamplerState_SRC*)stream->resampler_state;
state->src_reset(state->SRC_state);
}
static void
SDL_CleanupAudioStreamResampler_SRC(SDL_AudioStream *stream)
{
SDL_AudioStreamResamplerState_SRC *state = (SDL_AudioStreamResamplerState_SRC*)stream->resampler_state;
if (state) {
if (state->SRC_lib) {
SDL_UnloadObject(state->SRC_lib);
}
state->src_delete(state->SRC_state);
SDL_free(state);
}
stream->resampler_state = NULL;
stream->resampler_func = NULL;
stream->reset_resampler_func = NULL;
stream->cleanup_resampler_func = NULL;
}
static SDL_bool
SetupLibSampleRateResampling(SDL_AudioStream *stream)
{
int result;
SDL_AudioStreamResamplerState_SRC *state = (SDL_AudioStreamResamplerState_SRC *)SDL_calloc(1, sizeof(*state));
if (!state) {
return SDL_FALSE;
}
if (!LoadLibSampleRate(state)) {
SDL_free(state);
return SDL_FALSE;
}
stream->resampler_state = state;
stream->resampler_func = SDL_ResampleAudioStream_SRC;
stream->reset_resampler_func = SDL_ResetAudioStreamResampler_SRC;
stream->cleanup_resampler_func = SDL_CleanupAudioStreamResampler_SRC;
state->SRC_state = state->src_new(SRC_SINC_FASTEST, stream->pre_resample_channels, &result);
if (!state->SRC_state) {
SDL_SetError("src_new() failed: %s", state->src_strerror(result));
SDL_CleanupAudioStreamResampler_SRC(stream);
return SDL_FALSE;
}
return SDL_TRUE;
}
#endif /* HAVE_LIBSAMPLERATE */
typedef struct
{
SDL_bool resampler_seeded;
float resampler_state[8];
} SDL_AudioStreamResamplerState;
static int
SDL_ResampleAudioStream(SDL_AudioStream *stream, const float *inbuf, const int inbuflen, float *outbuf, const int outbuflen)
{
/* !!! FIXME: this resampler sucks, but not much worse than our usual resampler. :) */ /* ... :( */
SDL_AudioStreamResamplerState *state = (SDL_AudioStreamResamplerState*)stream->resampler_state;
const int chans = (int)stream->pre_resample_channels;
const int framelen = chans * sizeof(float);
const int total = (inbuflen / framelen);
const int finalpos = total - chans;
const double src_incr = 1.0 / stream->rate_incr;
double idx = 0.0;
float *dst = outbuf;
float last_sample[SDL_arraysize(state->resampler_state)];
int consumed = 0;
int i;
SDL_assert(chans <= SDL_arraysize(last_sample));
SDL_assert((inbuflen % framelen) == 0);
if (!state->resampler_seeded) {
for (i = 0; i < chans; i++) {
state->resampler_state[i] = inbuf[i];
}
state->resampler_seeded = SDL_TRUE;
}
for (i = 0; i < chans; i++) {
last_sample[i] = state->resampler_state[i];
}
while (consumed < total) {
const int pos = ((int)idx) * chans;
const float *src = &inbuf[(pos >= finalpos) ? finalpos : pos];
SDL_assert(dst < (outbuf + (outbuflen / framelen)));
for (i = 0; i < chans; i++) {
const float val = *(src++);
*(dst++) = (val + last_sample[i]) * 0.5f;
last_sample[i] = val;
}
consumed = pos + chans;
idx += src_incr;
}
for (i = 0; i < chans; i++) {
state->resampler_state[i] = last_sample[i];
}
return (int)((dst - outbuf) * sizeof(float));
}
static void
SDL_ResetAudioStreamResampler(SDL_AudioStream *stream)
{
SDL_AudioStreamResamplerState *state = (SDL_AudioStreamResamplerState*)stream->resampler_state;
state->resampler_seeded = SDL_FALSE;
}
static void
SDL_CleanupAudioStreamResampler(SDL_AudioStream *stream)
{
SDL_free(stream->resampler_state);
}
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
SDL_AudioStream *SDL_NewAudioStream(const SDL_AudioFormat src_format,
const Uint8 src_channels,
const int src_rate,
const SDL_AudioFormat dst_format,
const Uint8 dst_channels,
const int dst_rate)
{
const int packetlen = 4096; /* !!! FIXME: good enough for now. */
Uint8 pre_resample_channels;
SDL_AudioStream *retval;
retval = (SDL_AudioStream *) SDL_calloc(1, sizeof (SDL_AudioStream));
if (!retval) {
return NULL;
}
/* If increasing channels, do it after resampling, since we'd just
do more work to resample duplicate channels. If we're decreasing, do
it first so we resample the interpolated data instead of interpolating
the resampled data (!!! FIXME: decide if that works in practice, though!). */
pre_resample_channels = SDL_min(src_channels, dst_channels);
retval->src_sample_frame_size = SDL_AUDIO_BITSIZE(src_format) * src_channels;
retval->src_format = src_format;
retval->src_channels = src_channels;
retval->src_rate = src_rate;
retval->dst_sample_frame_size = SDL_AUDIO_BITSIZE(dst_format) * dst_channels;
retval->dst_format = dst_format;
retval->dst_channels = dst_channels;
retval->dst_rate = dst_rate;
retval->pre_resample_channels = pre_resample_channels;
retval->packetlen = packetlen;
retval->rate_incr = ((double) dst_rate) / ((double) src_rate);
/* Not resampling? It's an easy conversion (and maybe not even that!). */
if (src_rate == dst_rate) {
retval->cvt_before_resampling.needed = SDL_FALSE;
retval->cvt_before_resampling.len_mult = 1;
864
865
if (SDL_BuildAudioCVT(&retval->cvt_after_resampling, src_format, src_channels, dst_rate, dst_format, dst_channels, dst_rate) < 0) {
SDL_FreeAudioStream(retval);
866
867
868
869
870
return NULL; /* SDL_BuildAudioCVT should have called SDL_SetError. */
}
} else {
/* Don't resample at first. Just get us to Float32 format. */
/* !!! FIXME: convert to int32 on devices without hardware float. */
871
872
if (SDL_BuildAudioCVT(&retval->cvt_before_resampling, src_format, src_channels, src_rate, AUDIO_F32SYS, pre_resample_channels, src_rate) < 0) {
SDL_FreeAudioStream(retval);
873
874
875
return NULL; /* SDL_BuildAudioCVT should have called SDL_SetError. */
}
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
#ifdef HAVE_LIBSAMPLERATE
SetupLibSampleRateResampling(retval);
#endif
if (!retval->resampler_func) {
retval->resampler_state = SDL_calloc(1, sizeof(SDL_AudioStreamResamplerState));
if (!retval->resampler_state) {
SDL_FreeAudioStream(retval);
SDL_OutOfMemory();
return NULL;
}
retval->resampler_func = SDL_ResampleAudioStream;
retval->reset_resampler_func = SDL_ResetAudioStreamResampler;
retval->cleanup_resampler_func = SDL_CleanupAudioStreamResampler;
}
892
/* Convert us to the final format after resampling. */
893
894
if (SDL_BuildAudioCVT(&retval->cvt_after_resampling, AUDIO_F32SYS, pre_resample_channels, dst_rate, dst_format, dst_channels, dst_rate) < 0) {
SDL_FreeAudioStream(retval);
895
896
897
898
899
900
return NULL; /* SDL_BuildAudioCVT should have called SDL_SetError. */
}
}
retval->queue = SDL_NewDataQueue(packetlen, packetlen * 2);
if (!retval->queue) {
901
SDL_FreeAudioStream(retval);
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
return NULL; /* SDL_NewDataQueue should have called SDL_SetError. */
}
return retval;
}
static Uint8 *
EnsureBufferSize(Uint8 **buf, int *len, const int newlen)
{
if (*len < newlen) {
void *ptr = SDL_realloc(*buf, newlen);
if (!ptr) {
SDL_OutOfMemory();
return NULL;
}
*buf = (Uint8 *) ptr;
*len = newlen;
}
return *buf;
}
int
SDL_AudioStreamPut(SDL_AudioStream *stream, const void *buf, const Uint32 _buflen)
{
int buflen = (int) _buflen;
if (!stream) {
return SDL_InvalidParamError("stream");
} else if (!buf) {
return SDL_InvalidParamError("buf");
} else if (buflen == 0) {
return 0; /* nothing to do. */
} else if ((buflen % stream->src_sample_frame_size) != 0) {
return SDL_SetError("Can't add partial sample frames");
}
if (stream->cvt_before_resampling.needed) {
const int workbuflen = buflen * stream->cvt_before_resampling.len_mult; /* will be "* 1" if not needed */
Uint8 *workbuf = EnsureBufferSize(&stream->work_buffer, &stream->work_buffer_len, workbuflen);
if (workbuf == NULL) {
return -1; /* probably out of memory. */
}
SDL_memcpy(workbuf, buf, buflen);
stream->cvt_before_resampling.buf = workbuf;
stream->cvt_before_resampling.len = buflen;
if (SDL_ConvertAudio(&stream->cvt_before_resampling) == -1) {
return -1; /* uhoh! */
}
buf = workbuf;
buflen = stream->cvt_before_resampling.len_cvt;
}
if (stream->dst_rate != stream->src_rate) {
const int workbuflen = buflen * ((int) SDL_ceil(stream->rate_incr));
float *workbuf = (float *) EnsureBufferSize(&stream->resample_buffer, &stream->resample_buffer_len, workbuflen);
if (workbuf == NULL) {
return -1; /* probably out of memory. */
}
960
buflen = stream->resampler_func(stream, (float *) buf, buflen, workbuf, workbuflen);
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
buf = workbuf;
}
if (stream->cvt_after_resampling.needed) {
const int workbuflen = buflen * stream->cvt_before_resampling.len_mult; /* will be "* 1" if not needed */
Uint8 *workbuf;
if (buf == stream->resample_buffer) {
workbuf = EnsureBufferSize(&stream->resample_buffer, &stream->resample_buffer_len, workbuflen);
} else {
const int inplace = (buf == stream->work_buffer);
workbuf = EnsureBufferSize(&stream->work_buffer, &stream->work_buffer_len, workbuflen);
if (workbuf && !inplace) {
SDL_memcpy(workbuf, buf, buflen);
}
}
if (workbuf == NULL) {
return -1; /* probably out of memory. */
}
stream->cvt_after_resampling.buf = workbuf;
stream->cvt_after_resampling.len = buflen;
if (SDL_ConvertAudio(&stream->cvt_after_resampling) == -1) {
return -1; /* uhoh! */
}
buf = workbuf;
buflen = stream->cvt_after_resampling.len_cvt;
}
return SDL_WriteToDataQueue(stream->queue, buf, buflen);
}
void
SDL_AudioStreamClear(SDL_AudioStream *stream)
{
if (!stream) {
SDL_InvalidParamError("stream");
} else {
SDL_ClearDataQueue(stream->queue, stream->packetlen * 2);