xref: /netbsd-src/usr.bin/audio/common/libaudio.h (revision b4c3b934ba8f0d7056bc0563e12450f4fc698e94)
1 /*	$NetBSD: libaudio.h,v 1.22 2024/03/08 06:57:59 mrg Exp $	*/
2 
3 /*
4  * Copyright (c) 1999, 2009, 2013, 2015, 2019, 2024 Matthew R. Green
5  * All rights reserved.
6  *
7  * Redistribution and use in source and binary forms, with or without
8  * modification, are permitted provided that the following conditions
9  * are met:
10  * 1. Redistributions of source code must retain the above copyright
11  *    notice, this list of conditions and the following disclaimer.
12  * 2. Redistributions in binary form must reproduce the above copyright
13  *    notice, this list of conditions and the following disclaimer in the
14  *    documentation and/or other materials provided with the distribution.
15  *
16  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
17  * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
18  * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
19  * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
20  * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
21  * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
23  * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
24  * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
25  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26  * SUCH DAMAGE.
27  */
28 
29 /*
30  * audio formats
31  */
32 #define AUDIO_FORMAT_DEFAULT	-1
33 #define AUDIO_FORMAT_NONE	1
34 #define AUDIO_FORMAT_SUN	2
35 #define AUDIO_FORMAT_WAV	3
36 
37 int	audio_format_from_str (char *);
38 
39 /*
40  * Audio encoding formats; this is a additional to those set
41  * in sys/audioio.h, but with a large offset to avoid future
42  * conflicts (additional ones are libaudio-software only.)
43  *
44  * This is to support floating-point WAV files.  These require
45  * software conversion to a supported format.
46  */
47 #define	AUDIO_ENCODING_LIBAUDIO_FLOAT32    1001	/* 32-bit IEEE FP. */
48 #define	AUDIO_ENCODING_LIBAUDIO_FLOAT64    1002	/* 64-bit IEEE FP. */
49 
50 /*
51  * We copy the Sun/NeXT on-disk audio header format and document what
52  * we know of it here.
53  *
54  * The header size appears to be an offset to where the data really
55  * begins, rather than defining the real length of the audio header.
56  * The Sun/NeXT audio format seems to only use 24 bytes of data (with
57  * an additional 8 bytes of nuls written, padding it to 32 bytes).
58  *
59  * If the size of the audio data is unknown (eg, reading from a pipe)
60  * the Sun demo audio tools place AUDIO_UNKNOWN_SIZE in the
61  * `data_size' member.
62  *
63  * For stereo data, the channels appear to be interleaved with the
64  * left channel first.  For more channels, who knows?
65  */
66 
67 /*
68  * This is the Sun/NeXT audio file magic value.  Note that it
69  * is also `.snd' in ASCII.
70  */
71 #define	AUDIO_FILE_MAGIC		((u_int32_t)0x2e736e64)
72 #define AUDIO_UNKNOWN_SIZE		((unsigned)(~0))
73 
74 typedef struct {
75 	u_int32_t	magic;
76 	u_int32_t	hdr_size;	/* header size; in bytes */
77 	u_int32_t	data_size;	/* optional; in bytes */
78 	u_int32_t	encoding;	/* see below */
79 	u_int32_t	sample_rate;	/* per second */
80 	u_int32_t	channels;	/* number of interleaved channels */
81 } sun_audioheader;
82 
83 #define Audio_filehdr sun_audioheader	/* SunOS compat(?) */
84 
85 /*
86  * these are the types of "encoding" for above.  taken from the
87  * SunOS <multimedia/audio_filehdr.h>.
88  */
89 #define	AUDIO_FILE_ENCODING_MULAW_8		1
90 #define	AUDIO_FILE_ENCODING_LINEAR_8		2
91 #define	AUDIO_FILE_ENCODING_LINEAR_16		3
92 #define	AUDIO_FILE_ENCODING_LINEAR_24		4
93 #define	AUDIO_FILE_ENCODING_LINEAR_32		5
94 #define	AUDIO_FILE_ENCODING_FLOAT		6
95 #define	AUDIO_FILE_ENCODING_DOUBLE		7
96 #define	AUDIO_FILE_ENCODING_ADPCM_G721		23
97 #define	AUDIO_FILE_ENCODING_ADPCM_G722		24
98 #define	AUDIO_FILE_ENCODING_ADPCM_G723_3	25
99 #define	AUDIO_FILE_ENCODING_ADPCM_G723_5	26
100 #define	AUDIO_FILE_ENCODING_ALAW_8		27
101 
102 const char *audio_enc_from_val (int);
103 int	audio_enc_to_val (const char *);
104 
105 int	audio_sun_to_encoding (int, u_int *, u_int *);
106 int	audio_encoding_to_sun (int, int, int *);
107 
108 /*
109  * RIFF WAVE files.  Sources: RFC 2361, and various Microsoft docs
110  * https://learn.microsoft.com/en-us/windows/win32/xaudio2/resource-interchange-file-format--riff-
111  * https://learn.microsoft.com/en-us/previous-versions/windows/hardware/design/dn653308(v=vs.85)
112  * "Multimedia Programming Interface and Data Specifications 1.0" chapter 4
113  */
114 
115 /*
116  * This is the WAV audio file magic value.  Note that it
117  * is also `RIFF' and `WAVE' in ASCII.
118  */
119 #define	WAVAUDIO_FILE_MAGIC_RIFF	((u_int32_t)0x52494646)
120 #define	WAVAUDIO_FILE_MAGIC_WAVE	((u_int32_t)0x57415645)
121 #define	WAVAUDIO_FILE_MAGIC_FMT		((u_int32_t)0x666d7420)
122 #define	WAVAUDIO_FILE_MAGIC_DATA	((u_int32_t)0x64617461)
123 
124 /* From RFC 2361 */
125 #define WAVE_FORMAT_UNKNOWN		(0x0000)
126 #define WAVE_FORMAT_PCM			(0x0001)
127 #define WAVE_FORMAT_ADPCM		(0x0002)
128 #define WAVE_FORMAT_IEEE_FLOAT		(0x0003)
129 #define WAVE_FORMAT_VSELP		(0x0004)
130 #define WAVE_FORMAT_IBM_CVSD		(0x0005)
131 #define WAVE_FORMAT_ALAW		(0x0006)
132 #define WAVE_FORMAT_MULAW		(0x0007)
133 #define WAVE_FORMAT_OKI_ADPCM		(0x0010)
134 #define WAVE_FORMAT_IMA_ADPCM		(0x0011)
135 #define WAVE_FORMAT_MEDIASPACE_ADPCM	(0x0012)
136 #define WAVE_FORMAT_SIERRA_ADPCM	(0x0013)
137 #define WAVE_FORMAT_G723_ADPCM		(0x0014)
138 #define WAVE_FORMAT_DIGISTD		(0x0015)
139 #define WAVE_FORMAT_DIGIFIX		(0x0016)
140 #define WAVE_FORMAT_DIALOGIC_OKI_ADPCM	(0x0017)
141 #define WAVE_FORMAT_MEDIAVISION_ADPCM	(0x0018)
142 #define WAVE_FORMAT_CU_CODEC		(0x0019)
143 #define WAVE_FORMAT_YAMAHA_ADPCM	(0x0020)
144 #define WAVE_FORMAT_SONARC		(0x0021)
145 #define WAVE_FORMAT_DSPGROUP_TRUESPEECH	(0x0022)
146 #define WAVE_FORMAT_ECHOSC1		(0x0023)
147 #define WAVE_FORMAT_AUDIOFILE_AF36	(0x0024)
148 #define WAVE_FORMAT_APTX		(0x0025)
149 #define WAVE_FORMAT_AUDIOFILE_AF10	(0x0026)
150 #define WAVE_FORMAT_PROSODY_1612	(0x0027)
151 #define WAVE_FORMAT_LRC			(0x0028)
152 #define WAVE_FORMAT_DOLBY_AC2		(0x0030)
153 #define WAVE_FORMAT_GSM610		(0x0031)
154 #define WAVE_FORMAT_MSNAUDIO		(0x0032)
155 #define WAVE_FORMAT_ANTEX_ADPCME	(0x0033)
156 #define WAVE_FORMAT_CONTROL_RES_VQLPC	(0x0034)
157 #define WAVE_FORMAT_DIGIREAL		(0x0035)
158 #define WAVE_FORMAT_DIGIADPCM		(0x0036)
159 #define WAVE_FORMAT_CONTROL_RES_CR10	(0x0037)
160 #define WAVE_FORMAT_NMS_VBXADPCM	(0x0038)
161 #define WAVE_FORMAT_ROLAND_RDAC		(0x0039)
162 #define WAVE_FORMAT_ECHOSC3		(0x003a)
163 #define WAVE_FORMAT_ROCKWELL_ADPCM	(0x003b)
164 #define WAVE_FORMAT_ROCKWELL_DIGITALK	(0x003c)
165 #define WAVE_FORMAT_XEBEC		(0x003d)
166 #define WAVE_FORMAT_G721_ADPCM		(0x0040)
167 #define WAVE_FORMAT_G728_CELP		(0x0041)
168 #define WAVE_FORMAT_MSG723		(0x0042)
169 #define WAVE_FORMAT_MPEG		(0x0050)
170 #define WAVE_FORMAT_RT24		(0x0052)
171 #define WAVE_FORMAT_PAC			(0x0053)
172 #define WAVE_FORMAT_MPEGLAYER3		(0x0055)
173 #define WAVE_FORMAT_LUCENT_G723		(0x0059)
174 #define WAVE_FORMAT_CIRRUS		(0x0060)
175 #define WAVE_FORMAT_ESPCM		(0x0061)
176 #define WAVE_FORMAT_VOXWARE		(0x0062)
177 #define WAVE_FORMAT_CANOPUS_ATRAC	(0x0063)
178 #define WAVE_FORMAT_G726_ADPCM		(0x0064)
179 #define WAVE_FORMAT_G722_ADPCM		(0x0065)
180 #define WAVE_FORMAT_DSAT		(0x0066)
181 #define WAVE_FORMAT_DSAT_DISPLAY	(0x0067)
182 #define WAVE_FORMAT_VOXWARE_BYTE_ALIGNED (0x0069)
183 #define WAVE_FORMAT_VOXWARE_AC8		(0x0070)
184 #define WAVE_FORMAT_VOXWARE_AC10	(0x0071)
185 #define WAVE_FORMAT_VOXWARE_AC16	(0x0072)
186 #define WAVE_FORMAT_VOXWARE_AC20	(0x0073)
187 #define WAVE_FORMAT_VOXWARE_RT24	(0x0074)
188 #define WAVE_FORMAT_VOXWARE_RT29	(0x0075)
189 #define WAVE_FORMAT_VOXWARE_RT29HW	(0x0076)
190 #define WAVE_FORMAT_VOXWARE_VR12	(0x0077)
191 #define WAVE_FORMAT_VOXWARE_VR18	(0x0078)
192 #define WAVE_FORMAT_VOXWARE_TQ40	(0x0079)
193 #define WAVE_FORMAT_SOFTSOUND		(0x0080)
194 #define WAVE_FORMAT_VOXWARE_TQ60	(0x0081)
195 #define WAVE_FORMAT_MSRT24		(0x0082)
196 #define WAVE_FORMAT_G729A		(0x0083)
197 #define WAVE_FORMAT_MVI_MV12		(0x0084)
198 #define WAVE_FORMAT_DF_G726		(0x0085)
199 #define WAVE_FORMAT_DF_GSM610		(0x0086)
200 #define WAVE_FORMAT_ISIAUDIO		(0x0088)
201 #define WAVE_FORMAT_ONLIVE		(0x0089)
202 #define WAVE_FORMAT_SBC24		(0x0091)
203 #define WAVE_FORMAT_DOLBY_AC3_SPDIF	(0x0092)
204 #define WAVE_FORMAT_ZYXEL_ADPCM		(0x0097)
205 #define WAVE_FORMAT_PHILIPS_LPCBB	(0x0098)
206 #define WAVE_FORMAT_PACKED		(0x0099)
207 #define WAVE_FORMAT_RHETOREX_ADPCM	(0x0100)
208 #define WAVE_FORMAT_IRAT		(0x0101)
209 #define WAVE_FORMAT_VIVO_G723		(0x0111)
210 #define WAVE_FORMAT_VIVO_SIREN		(0x0112)
211 #define WAVE_FORMAT_DIGITAL_G723	(0x0123)
212 #define WAVE_FORMAT_CREATIVE_ADPCM	(0x0200)
213 #define WAVE_FORMAT_CREATIVE_FASTSPEECH8 (0x0202)
214 #define WAVE_FORMAT_CREATIVE_FASTSPEECH10 (0x0203)
215 #define WAVE_FORMAT_QUARTERDECK		(0x0220)
216 #define WAVE_FORMAT_FM_TOWNS_SND	(0x0300)
217 #define WAVE_FORMAT_BTV_DIGITAL		(0x0400)
218 #define WAVE_FORMAT_VME_VMPCM		(0x0680)
219 #define WAVE_FORMAT_OLIGSM		(0x1000)
220 #define WAVE_FORMAT_OLIADPCM		(0x1001)
221 #define WAVE_FORMAT_OLICELP		(0x1002)
222 #define WAVE_FORMAT_OLISBC		(0x1003)
223 #define WAVE_FORMAT_OLIOPR		(0x1004)
224 #define WAVE_FORMAT_LH_CODEC		(0x1100)
225 #define WAVE_FORMAT_NORRIS		(0x1400)
226 #define WAVE_FORMAT_ISIAUDIO2		(0x1401)
227 #define WAVE_FORMAT_SOUNDSPACE_MUSICOMPRESS (0x1500)
228 #define WAVE_FORMAT_DVM			(0x2000)
229 
230 #define WAVE_FORMAT_EXTENSIBLE		(0xfffe)
231 
232 const char *wav_enc_from_val (int);
233 
234 typedef struct {
235 	char		name[4];
236 	u_int32_t	len;
237 } wav_audioheaderpart;
238 
239 typedef struct {
240 	u_int16_t	tag;
241 	u_int16_t	channels;
242 	u_int32_t	sample_rate;
243 	u_int32_t	avg_bytes_per_sec;
244 	u_int16_t	alignment;
245 	u_int16_t	bits_per_sample;
246 } __packed wav_audioheaderfmt;
247 
248 typedef struct {
249 	u_int16_t	len;
250 	u_int16_t	valid_bits;
251 	u_int32_t	speaker_pos_mask;
252 	u_int16_t	sub_tag;
253 	u_int8_t	guid[14];
254 } __packed wav_audiohdrextensible;
255 
256 /* returns size of header, or -ve for failure */
257 ssize_t audio_wav_parse_hdr (void *, size_t, u_int *, u_int *, u_int *, u_int *, off_t *);
258 
259 extern int verbose;
260 
261 /*
262  * audio routine error codes
263  */
264 #define AUDIO_ENOENT		-1		/* no such audio format */
265 #define AUDIO_ESHORTHDR		-2		/* short header */
266 #define AUDIO_EWAVUNSUPP	-3		/* WAV: unsupported file */
267 #define AUDIO_EWAVBADPCM	-4		/* WAV: bad PCM bps */
268 #define AUDIO_EWAVNODATA	-5		/* WAV: missing data */
269 #define AUDIO_EINTERNAL		-6		/* internal error */
270 
271 #define AUDIO_MAXERRNO		5
272 
273 /* and something to get a string associated with this error */
274 const char *audio_errstring (int);
275 
276 /*
277  * generic routines?
278  */
279 void	decode_int (const char *, int *);
280 void	decode_uint (const char *, unsigned *);
281 void	decode_time (const char *, struct timeval *);
282 void	decode_encoding (const char *, int *);
283 
284 /*
285  * Track info, for reading/writing sun/wav header.
286  *
287  * Note that write_header() may change the values of format,
288  * encoding.
289  */
290 
291 struct track_info {
292 	int	outfd;
293 	char	*header_info;
294 	int	format;
295 	int	encoding;
296 	int	precision;
297 	int	qflag;
298 	off_t	total_size;
299 	int	sample_rate;
300 	int	channels;
301 };
302 
303 typedef void (*write_conv_func) (u_char *, int);
304 
305 void	write_header (struct track_info *);
306 write_conv_func write_get_conv_func(struct track_info *);
307 
308 /* backends for the above */
309 int sun_prepare_header(struct track_info *ti, void **hdrp, size_t *lenp, int *leftp);
310 int wav_prepare_header(struct track_info *ti, void **hdrp, size_t *lenp, int *leftp);
311 write_conv_func sun_write_get_conv_func(struct track_info *ti);
312 write_conv_func wav_write_get_conv_func(struct track_info *ti);
313 
314 extern char	audio_default_info[8];
315 
316 /*
317  * get/put 16/32 bits of big/little endian data
318  */
319 #include <sys/types.h>
320 #include <machine/endian.h>
321 #include <machine/bswap.h>
322 
323 #if BYTE_ORDER == BIG_ENDIAN
324 
325 #define getle16(v)	bswap16(v)
326 #define getle32(v)	bswap32(v)
327 #define getbe16(v)	(v)
328 #define getbe32(v)	(v)
329 
330 #define putle16(x,v)	(x) = bswap16(v)
331 #define putle32(x,v)	(x) = bswap32(v)
332 #define putbe16(x,v)	(x) = (v)
333 #define putbe32(x,v)	(x) = (v)
334 
335 #else
336 
337 #define getle16(v)	(v)
338 #define getle32(v)	(v)
339 #define getbe16(v)	bswap16(v)
340 #define getbe32(v)	bswap32(v)
341 
342 #define putle16(x,v)	(x) = (v)
343 #define putle32(x,v)	(x) = (v)
344 #define putbe16(x,v)	(x) = bswap16(v)
345 #define putbe32(x,v)	(x) = bswap32(v)
346 
347 #endif
348