summaryrefslogtreecommitdiffstats
path: root/Lib/sunau.py
blob: 2cb35a7ebdcb789d123a57aacbc332318b341a09 (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
# Stuff to parse Sun and NeXT audio files.
#
# An audio consists of a header followed by the data.  The structure
# of the header is as follows.
#
#	+---------------+
#	| magic word    |
#	+---------------+
#	| header size   |
#	+---------------+
#	| data size     |
#	+---------------+
#	| encoding      |
#	+---------------+
#	| sample rate   |
#	+---------------+
#	| # of channels |
#	+---------------+
#	| info          |
#	|               |
#	+---------------+
#
# The magic word consists of the 4 characters '.snd'.  Apart from the
# info field, all header fields are 4 bytes in size.  They are all
# 32-bit unsigned integers encoded in big-endian byte order.
#
# The header size really gives the start of the data.
# The data size is the physical size of the data.  From the other
# parameter the number of frames can be calculated.
# The encoding gives the way in which audio samples are encoded.
# Possible values are listed below.
# The info field currently consists of an ASCII string giving a
# human-readable description of the audio file.  The info field is
# padded with NUL bytes to the header size.
#
# Usage.
#
# Reading audio files:
#	f = au.open(file, 'r')
# or
#	f = au.openfp(filep, 'r')
# where file is the name of a file and filep is an open file pointer.
# The open file pointer must have methods read(), seek(), and close().
# When the setpos() and rewind() methods are not used, the seek()
# method is not  necessary.
#
# This returns an instance of a class with the following public methods:
#	getnchannels()	-- returns number of audio channels (1 for
#			   mono, 2 for stereo)
#	getsampwidth()	-- returns sample width in bytes
#	getframerate()	-- returns sampling frequency
#	getnframes()	-- returns number of audio frames
#	getcomptype()	-- returns compression type ('NONE' for AIFF files)
#	getcompname()	-- returns human-readable version of
#			   compression type ('not compressed' for AIFF files)
#	getparams()	-- returns a tuple consisting of all of the
#			   above in the above order
#	getmarkers()	-- returns None (for compatibility with the
#			   aifc module)
#	getmark(id)	-- raises an error since the mark does not
#			   exist (for compatibility with the aifc module)
#	readframes(n)	-- returns at most n frames of audio
#	rewind()	-- rewind to the beginning of the audio stream
#	setpos(pos)	-- seek to the specified position
#	tell()		-- return the current position
#	close()		-- close the instance (make it unusable)
# The position returned by tell() and the position given to setpos()
# are compatible and have nothing to do with the actual postion in the
# file.
# The close() method is called automatically when the class instance
# is destroyed.
#
# Writing audio files:
#	f = au.open(file, 'w')
# or
#	f = au.openfp(filep, 'w')
# where file is the name of a file and filep is an open file pointer.
# The open file pointer must have methods write(), tell(), seek(), and
# close().
#
# This returns an instance of a class with the following public methods:
#	setnchannels(n)	-- set the number of channels
#	setsampwidth(n)	-- set the sample width
#	setframerate(n)	-- set the frame rate
#	setnframes(n)	-- set the number of frames
#	setcomptype(type, name)
#			-- set the compression type and the
#			   human-readable compression type
#	setparams(nchannels, sampwidth, framerate, nframes, comptype, compname)
#			-- set all parameters at once
#	tell()		-- return current position in output file
#	writeframesraw(data)
#			-- write audio frames without pathing up the
#			   file header
#	writeframes(data)
#			-- write audio frames and patch up the file header
#	close()		-- patch up the file header and close the
#			   output file
# You should set the parameters before the first writeframesraw or
# writeframes.  The total number of frames does not need to be set,
# but when it is set to the correct value, the header does not have to
# be patched up.
# It is best to first set all parameters, perhaps possibly the
# compression type, and then write audio frames using writeframesraw.
# When all frames have been written, either call writeframes('') or
# close() to patch up the sizes in the header.
# The close() method is called automatically when the class instance
# is destroyed.

# from <multimedia/audio_filehdr.h>
AUDIO_FILE_MAGIC = 0x2e736e64
AUDIO_FILE_ENCODING_MULAW_8 = 1
AUDIO_FILE_ENCODING_LINEAR_8 = 2
AUDIO_FILE_ENCODING_LINEAR_16 = 3
AUDIO_FILE_ENCODING_LINEAR_24 = 4
AUDIO_FILE_ENCODING_LINEAR_32 = 5
AUDIO_FILE_ENCODING_FLOAT = 6
AUDIO_FILE_ENCODING_DOUBLE = 7
AUDIO_FILE_ENCODING_ADPCM_G721 = 23
AUDIO_FILE_ENCODING_ADPCM_G722 = 24
AUDIO_FILE_ENCODING_ADPCM_G723_3 = 25
AUDIO_FILE_ENCODING_ADPCM_G723_5 = 26
AUDIO_FILE_ENCODING_ALAW_8 = 27

# from <multimedia/audio_hdr.h>
AUDIO_UNKNOWN_SIZE = 0xFFFFFFFFL	# ((unsigned)(~0))

_simple_encodings = [AUDIO_FILE_ENCODING_MULAW_8,
		     AUDIO_FILE_ENCODING_LINEAR_8,
		     AUDIO_FILE_ENCODING_LINEAR_16,
		     AUDIO_FILE_ENCODING_LINEAR_24,
		     AUDIO_FILE_ENCODING_LINEAR_32,
		     AUDIO_FILE_ENCODING_ALAW_8]

def _read_u32(file):
	x = 0L
	for i in range(4):
		byte = file.read(1)
		if byte == '':
			raise EOFError
		x = x*256 + ord(byte)
	return x

def _write_u32(file, x):
	data = []
	for i in range(4):
		d, m = divmod(x, 256)
		data.insert(0, m)
		x = d
	for i in range(4):
		file.write(chr(int(data[i])))

class Au_read:
	def initfp(self, file):
		self._file = file
		self._soundpos = 0
		magic = int(_read_u32(file))
		if magic != AUDIO_FILE_MAGIC:
			raise Error, 'bad magic number'
		self._hdr_size = int(_read_u32(file))
		if self._hdr_size < 24:
			raise Error, 'header size too small'
		if self._hdr_size > 100:
			raise Error, 'header size rediculously large'
		self._data_size = _read_u32(file)
		if self._data_size != AUDIO_UNKNOWN_SIZE:
			self._data_size = int(self._data_size)
		self._encoding = int(_read_u32(file))
		if self._encoding not in _simple_encodings:
			raise Error, 'encoding not (yet) supported'
		if self._encoding in (AUDIO_FILE_ENCODING_MULAW_8,
			  AUDIO_FILE_ENCODING_LINEAR_8,
			  AUDIO_FILE_ENCODING_ALAW_8):
			self._sampwidth = 2
			self._framesize = 1
		elif self._encoding == AUDIO_FILE_ENCODING_LINEAR_16:
			self._framesize = self._sampwidth = 2
		elif self._encoding == AUDIO_FILE_ENCODING_LINEAR_24:
			self._framesize = self._sampwidth = 3
		elif self._encoding == AUDIO_FILE_ENCODING_LINEAR_32:
			self._framesize = self._sampwidth = 4
		else:
			raise Error, 'unknown encoding'
		self._framerate = int(_read_u32(file))
		self._nchannels = int(_read_u32(file))
		self._framesize = self._framesize * self._nchannels
		if self._hdr_size > 24:
			self._info = file.read(self._hdr_size - 24)
			for i in range(len(self._info)):
				if self._info[i] == '\0':
					self._info = self._info[:i]
					break
		else:
			self._info = ''
		return self

	def init(self, filename):
		import builtin
		return self.initfp(builtin.open(filename, 'r'))

	def __del__(self):
		if self._file:
			self.close()

	def getfp(self):
		return self._file

	def getnchannels(self):
		return self._nchannels

	def getsampwidth(self):
		return self._sampwidth

	def getframerate(self):
		return self._framerate

	def getnframes(self):
		if self._data_size == AUDIO_UNKNOWN_SIZE:
			return AUDIO_UNKNOWN_SIZE
		if self._encoding in _simple_encodings:
			return self._data_size / self._framesize
		return 0		# XXX--must do some arithmetic here

	def getcomptype(self):
		if self._encoding == AUDIO_FILE_ENCODING_MULAW_8:
			return 'ULAW'
		elif self._encoding == AUDIO_FILE_ENCODING_ALAW_8:
			return 'ALAW'
		else:
			return 'NONE'

	def getcompname(self):
		if self._encoding == AUDIO_FILE_ENCODING_MULAW_8:
			return 'CCITT G.711 u-law'
		elif self._encoding == AUDIO_FILE_ENCODING_ALAW_8:
			return 'CCITT G.711 A-law'
		else:
			return 'not compressed'

	def getparams(self):
		return self.getnchannels(), self.getsampwidth(), \
			  self.getframerate(), self.getnframes(), \
			  self.getcomptype(), self.getcompname()

	def getmarkers(self):
		return None

	def getmark(self, id):
		raise Error, 'no marks'

	def readframes(self, nframes):
		if self._encoding in _simple_encodings:
			if nframes == AUDIO_UNKNOWN_SIZE:
				data = self._file.read()
			else:
				data = self._file.read(nframes * self._sampwidth * self._nchannels)
			if self._encoding == AUDIO_FILE_ENCODING_MULAW_8:
				import audioop
				data = audioop.ulaw2lin(data, self._sampwidth)
			return data
		return None		# XXX--not implemented yet

	def rewind(self):
		self._soundpos = 0
		self._file.seek(self._hdr_size)

	def tell(self):
		return self._soundpos

	def setpos(self, pos):
		if pos < 0 or pos > self.getnframes():
			raise Error, 'position not in range'
		self._file.seek(pos * self._framesize + self._hdr_size)
		self._soundpos = pos

	def close(self):
		self._file = None

class Au_write:
	def init(self, filename):
		import builtin
		return self.initfp(builtin.open(filename, 'w'))

	def initfp(self, file):
		self._file = file
		self._framerate = 0
		self._nchannels = 0
		self._sampwidth = 0
		self._framesize = 0
		self._nframes = AUDIO_UNKNOWN_SIZE
		self._nframeswritten = 0
		self._datawritten = 0
		self._datalength = 0
		self._info = ''
		self._comptype = 'ULAW'	# default is U-law
		return self

	def __del__(self):
		if self._file:
			self.close()

	def setnchannels(self, nchannels):
		if self._nframeswritten:
			raise Error, 'cannot change parameters after starting to write'
		if nchannels not in (1, 2, 4):
			raise Error, 'only 1, 2, or 4 channels supported'
		self._nchannels = nchannels

	def getnchannels(self):
		if not self._nchannels:
			raise Error, 'number of channels not set'
		return self._nchannels

	def setsampwidth(self, sampwidth):
		if self._nframeswritten:
			raise Error, 'cannot change parameters after starting to write'
		if sampwidth not in (1, 2, 4):
			raise Error, 'bad sample width'
		self._sampwidth = sampwidth

	def getsampwidth(self):
		if not self._framerate:
			raise Error, 'sample width not specified'
		return self._sampwidth

	def setframerate(self, framerate):
		if self._nframeswritten:
			raise Error, 'cannot change parameters after starting to write'
		self._framerate = framerate

	def getframerate(self):
		if not self._framerate:
			raise Error, 'frame rate not set'
		return self._framerate

	def setnframes(self, nframes):
		if self._nframeswritten:
			raise Error, 'cannot change parameters after starting to write'
		if nframes < 0:
			raise Error, '# of frames cannot be negative'
		self._nframes = nframes

	def getnframes(self):
		return self._nframeswritten

	def setcomptype(self, type, name):
		if type in ('NONE', 'ULAW'):
			self._comptype = type
		else:
			raise Error, 'unknown compression type'

	def getcomptype(self):
		return self._comptype

	def getcompname(self):
		if self._comptype == 'ULAW':
			return 'CCITT G.711 u-law'
		elif self._comptype == 'ALAW':
			return 'CCITT G.711 A-law'
		else:
			return 'not compressed'

	def setparams(self, (nchannels, sampwidth, framerate, nframes, comptype, compname)):
		self.setnchannels(nchannels)
		self.setsampwidth(sampwidth)
		self.setframerate(framerate)
		self.setnframes(nframes)
		self.setcomptype(comptype, compname)

	def getparams(self):
		return self.getnchannels(), self.getsampwidth(), \
			  self.getframerate(), self.getnframes(), \
			  self.getcomptype(), self.getcompname()

	def tell(self):
		return self._nframeswritten

	def writeframesraw(self, data):
		self._ensure_header_written()
		nframes = len(data) / self._framesize
		if self._comptype == 'ULAW':
			import audioop
			data = audioop.lin2ulaw(data, self._sampwidth)
		self._file.write(data)
		self._nframeswritten = self._nframeswritten + nframes
		self._datawritten = self._datawritten + len(data)

	def writeframes(self, data):
		self.writeframesraw(data)
		if self._nframeswritten != self._nframes or \
			  self._datalength != self._datawritten:
			self._patchheader()

	def close(self):
		self._ensure_header_written()
		if self._nframeswritten != self._nframes or \
			  self._datalength != self._datawritten:
			self._patchheader()
		self._file.flush()
		self._file = None

	#
	# private methods
	#
	def _ensure_header_written(self):
		if not self._nframeswritten:
			if not self._nchannels:
				raise Error, '# of channels not specified'
			if not self._sampwidth:
				raise Error, 'sample width not specified'
			if not self._framerate:
				raise Error, 'frame rate not specified'
			self._write_header()

	def _write_header(self):
		if self._comptype == 'NONE':
			if self._sampwidth == 1:
				encoding = AUDIO_FILE_ENCODING_LINEAR_8
				self._framesize = 1
			elif self._sampwidth == 2:
				encoding = AUDIO_FILE_ENCODING_LINEAR_16
				self._framesize = 2
			elif self._sampwidth == 4:
				encoding = AUDIO_FILE_ENCODING_LINEAR_32
				self._framesize = 4
			else:
				raise Error, 'internal error'
		elif self._comptype == 'ULAW':
			encoding = AUDIO_FILE_ENCODING_MULAW_8
			self._framesize = 1
		else:
			raise Error, 'internal error'
		self._framesize = self._framesize * self._nchannels
		_write_u32(self._file, AUDIO_FILE_MAGIC)
		header_size = 25 + len(self._info)
		header_size = (header_size + 7) & ~7
		_write_u32(self._file, header_size)
		if self._nframes == AUDIO_UNKNOWN_SIZE:
			length = AUDIO_UNKNOWN_SIZE
		else:
			length = self._nframes * self._framesize
		_write_u32(self._file, length)
		self._datalength = length
		_write_u32(self._file, encoding)
		_write_u32(self._file, self._framerate)
		_write_u32(self._file, self._nchannels)
		self._file.write(self._info)
		self._file.write('\0'*(header_size - len(self._info) - 24))

	def _patchheader(self):
		self._file.seek(8)
		_write_u32(self._file, self._datawritten)
		self._datalength = self._datawritten
		self._file.seek(0, 2)

def open(filename, mode):
	if mode == 'r':
		return Au_read().init(filename)
	elif mode == 'w':
		return Au_write().init(filename)
	else:
		raise Error, "mode must be 'r' or 'w'"

def openfp(filep, mode):
	if mode == 'r':
		return Au_read().initfp(filep)
	elif mode == 'w':
		return Au_write().initfp(filep)
	else:
		raise Error, "mode must be 'r' or 'w'"