File size: 12,368 Bytes
9c6594c |
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 |
from __future__ import division
import json
import os
import re
import sys
from subprocess import Popen, PIPE
from math import log, ceil
from tempfile import TemporaryFile
from warnings import warn
from functools import wraps
try:
import audioop
except ImportError:
import pyaudioop as audioop
if sys.version_info >= (3, 0):
basestring = str
FRAME_WIDTHS = {
8: 1,
16: 2,
32: 4,
}
ARRAY_TYPES = {
8: "b",
16: "h",
32: "i",
}
ARRAY_RANGES = {
8: (-0x80, 0x7f),
16: (-0x8000, 0x7fff),
32: (-0x80000000, 0x7fffffff),
}
def get_frame_width(bit_depth):
return FRAME_WIDTHS[bit_depth]
def get_array_type(bit_depth, signed=True):
t = ARRAY_TYPES[bit_depth]
if not signed:
t = t.upper()
return t
def get_min_max_value(bit_depth):
return ARRAY_RANGES[bit_depth]
def _fd_or_path_or_tempfile(fd, mode='w+b', tempfile=True):
close_fd = False
if fd is None and tempfile:
fd = TemporaryFile(mode=mode)
close_fd = True
if isinstance(fd, basestring):
fd = open(fd, mode=mode)
close_fd = True
try:
if isinstance(fd, os.PathLike):
fd = open(fd, mode=mode)
close_fd = True
except AttributeError:
# module os has no attribute PathLike, so we're on python < 3.6.
# The protocol we're trying to support doesn't exist, so just pass.
pass
return fd, close_fd
def db_to_float(db, using_amplitude=True):
"""
Converts the input db to a float, which represents the equivalent
ratio in power.
"""
db = float(db)
if using_amplitude:
return 10 ** (db / 20)
else: # using power
return 10 ** (db / 10)
def ratio_to_db(ratio, val2=None, using_amplitude=True):
"""
Converts the input float to db, which represents the equivalent
to the ratio in power represented by the multiplier passed in.
"""
ratio = float(ratio)
# accept 2 values and use the ratio of val1 to val2
if val2 is not None:
ratio = ratio / val2
# special case for multiply-by-zero (convert to silence)
if ratio == 0:
return -float('inf')
if using_amplitude:
return 20 * log(ratio, 10)
else: # using power
return 10 * log(ratio, 10)
def register_pydub_effect(fn, name=None):
"""
decorator for adding pydub effects to the AudioSegment objects.
example use:
@register_pydub_effect
def normalize(audio_segment):
...
or you can specify a name:
@register_pydub_effect("normalize")
def normalize_audio_segment(audio_segment):
...
"""
if isinstance(fn, basestring):
name = fn
return lambda fn: register_pydub_effect(fn, name)
if name is None:
name = fn.__name__
from .audio_segment import AudioSegment
setattr(AudioSegment, name, fn)
return fn
def make_chunks(audio_segment, chunk_length):
"""
Breaks an AudioSegment into chunks that are <chunk_length> milliseconds
long.
if chunk_length is 50 then you'll get a list of 50 millisecond long audio
segments back (except the last one, which can be shorter)
"""
number_of_chunks = ceil(len(audio_segment) / float(chunk_length))
return [audio_segment[i * chunk_length:(i + 1) * chunk_length]
for i in range(int(number_of_chunks))]
def which(program):
"""
Mimics behavior of UNIX which command.
"""
# Add .exe program extension for windows support
if os.name == "nt" and not program.endswith(".exe"):
program += ".exe"
envdir_list = [os.curdir] + os.environ["PATH"].split(os.pathsep)
for envdir in envdir_list:
program_path = os.path.join(envdir, program)
if os.path.isfile(program_path) and os.access(program_path, os.X_OK):
return program_path
def get_encoder_name():
"""
Return enconder default application for system, either avconv or ffmpeg
"""
if which("avconv"):
return "avconv"
elif which("ffmpeg"):
return "ffmpeg"
else:
# should raise exception
warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)
return "ffmpeg"
def get_player_name():
"""
Return enconder default application for system, either avconv or ffmpeg
"""
if which("avplay"):
return "avplay"
elif which("ffplay"):
return "ffplay"
else:
# should raise exception
warn("Couldn't find ffplay or avplay - defaulting to ffplay, but may not work", RuntimeWarning)
return "ffplay"
def get_prober_name():
"""
Return probe application, either avconv or ffmpeg
"""
if which("avprobe"):
return "avprobe"
elif which("ffprobe"):
return "ffprobe"
else:
# should raise exception
warn("Couldn't find ffprobe or avprobe - defaulting to ffprobe, but may not work", RuntimeWarning)
return "ffprobe"
def fsdecode(filename):
"""Wrapper for os.fsdecode which was introduced in python 3.2 ."""
if sys.version_info >= (3, 2):
PathLikeTypes = (basestring, bytes)
if sys.version_info >= (3, 6):
PathLikeTypes += (os.PathLike,)
if isinstance(filename, PathLikeTypes):
return os.fsdecode(filename)
else:
if isinstance(filename, bytes):
return filename.decode(sys.getfilesystemencoding())
if isinstance(filename, basestring):
return filename
raise TypeError("type {0} not accepted by fsdecode".format(type(filename)))
def get_extra_info(stderr):
"""
avprobe sometimes gives more information on stderr than
on the json output. The information has to be extracted
from stderr of the format of:
' Stream #0:0: Audio: flac, 88200 Hz, stereo, s32 (24 bit)'
or (macOS version):
' Stream #0:0: Audio: vorbis'
' 44100 Hz, stereo, fltp, 320 kb/s'
:type stderr: str
:rtype: list of dict
"""
extra_info = {}
re_stream = r'(?P<space_start> +)Stream #0[:\.](?P<stream_id>([0-9]+))(?P<content_0>.+)\n?(?! *Stream)((?P<space_end> +)(?P<content_1>.+))?'
for i in re.finditer(re_stream, stderr):
if i.group('space_end') is not None and len(i.group('space_start')) <= len(
i.group('space_end')):
content_line = ','.join([i.group('content_0'), i.group('content_1')])
else:
content_line = i.group('content_0')
tokens = [x.strip() for x in re.split('[:,]', content_line) if x]
extra_info[int(i.group('stream_id'))] = tokens
return extra_info
def mediainfo_json(filepath, read_ahead_limit=-1):
"""Return json dictionary with media info(codec, duration, size, bitrate...) from filepath
"""
prober = get_prober_name()
command_args = [
"-v", "info",
"-show_format",
"-show_streams",
]
try:
command_args += [fsdecode(filepath)]
stdin_parameter = None
stdin_data = None
except TypeError:
if prober == 'ffprobe':
command_args += ["-read_ahead_limit", str(read_ahead_limit),
"cache:pipe:0"]
else:
command_args += ["-"]
stdin_parameter = PIPE
file, close_file = _fd_or_path_or_tempfile(filepath, 'rb', tempfile=False)
file.seek(0)
stdin_data = file.read()
if close_file:
file.close()
command = [prober, '-of', 'json'] + command_args
res = Popen(command, stdin=stdin_parameter, stdout=PIPE, stderr=PIPE)
output, stderr = res.communicate(input=stdin_data)
output = output.decode("utf-8", 'ignore')
stderr = stderr.decode("utf-8", 'ignore')
info = json.loads(output)
if not info:
# If ffprobe didn't give any information, just return it
# (for example, because the file doesn't exist)
return info
extra_info = get_extra_info(stderr)
audio_streams = [x for x in info['streams'] if x['codec_type'] == 'audio']
if len(audio_streams) == 0:
return info
# We just operate on the first audio stream in case there are more
stream = audio_streams[0]
def set_property(stream, prop, value):
if prop not in stream or stream[prop] == 0:
stream[prop] = value
for token in extra_info[stream['index']]:
m = re.match('([su]([0-9]{1,2})p?) \(([0-9]{1,2}) bit\)$', token)
m2 = re.match('([su]([0-9]{1,2})p?)( \(default\))?$', token)
if m:
set_property(stream, 'sample_fmt', m.group(1))
set_property(stream, 'bits_per_sample', int(m.group(2)))
set_property(stream, 'bits_per_raw_sample', int(m.group(3)))
elif m2:
set_property(stream, 'sample_fmt', m2.group(1))
set_property(stream, 'bits_per_sample', int(m2.group(2)))
set_property(stream, 'bits_per_raw_sample', int(m2.group(2)))
elif re.match('(flt)p?( \(default\))?$', token):
set_property(stream, 'sample_fmt', token)
set_property(stream, 'bits_per_sample', 32)
set_property(stream, 'bits_per_raw_sample', 32)
elif re.match('(dbl)p?( \(default\))?$', token):
set_property(stream, 'sample_fmt', token)
set_property(stream, 'bits_per_sample', 64)
set_property(stream, 'bits_per_raw_sample', 64)
return info
def mediainfo(filepath):
"""Return dictionary with media info(codec, duration, size, bitrate...) from filepath
"""
prober = get_prober_name()
command_args = [
"-v", "quiet",
"-show_format",
"-show_streams",
filepath
]
command = [prober, '-of', 'old'] + command_args
res = Popen(command, stdout=PIPE)
output = res.communicate()[0].decode("utf-8")
if res.returncode != 0:
command = [prober] + command_args
output = Popen(command, stdout=PIPE).communicate()[0].decode("utf-8")
rgx = re.compile(r"(?:(?P<inner_dict>.*?):)?(?P<key>.*?)\=(?P<value>.*?)$")
info = {}
if sys.platform == 'win32':
output = output.replace("\r", "")
for line in output.split("\n"):
# print(line)
mobj = rgx.match(line)
if mobj:
# print(mobj.groups())
inner_dict, key, value = mobj.groups()
if inner_dict:
try:
info[inner_dict]
except KeyError:
info[inner_dict] = {}
info[inner_dict][key] = value
else:
info[key] = value
return info
def cache_codecs(function):
cache = {}
@wraps(function)
def wrapper():
try:
return cache[0]
except:
cache[0] = function()
return cache[0]
return wrapper
@cache_codecs
def get_supported_codecs():
encoder = get_encoder_name()
command = [encoder, "-codecs"]
res = Popen(command, stdout=PIPE, stderr=PIPE)
output = res.communicate()[0].decode("utf-8")
if res.returncode != 0:
return []
if sys.platform == 'win32':
output = output.replace("\r", "")
rgx = re.compile(r"^([D.][E.][AVS.][I.][L.][S.]) (\w*) +(.*)")
decoders = set()
encoders = set()
for line in output.split('\n'):
match = rgx.match(line.strip())
if not match:
continue
flags, codec, name = match.groups()
if flags[0] == 'D':
decoders.add(codec)
if flags[1] == 'E':
encoders.add(codec)
return (decoders, encoders)
def get_supported_decoders():
return get_supported_codecs()[0]
def get_supported_encoders():
return get_supported_codecs()[1]
def stereo_to_ms(audio_segment):
'''
Left-Right -> Mid-Side
'''
channel = audio_segment.split_to_mono()
channel = [channel[0].overlay(channel[1]), channel[0].overlay(channel[1].invert_phase())]
return AudioSegment.from_mono_audiosegments(channel[0], channel[1])
def ms_to_stereo(audio_segment):
'''
Mid-Side -> Left-Right
'''
channel = audio_segment.split_to_mono()
channel = [channel[0].overlay(channel[1]) - 3, channel[0].overlay(channel[1].invert_phase()) - 3]
return AudioSegment.from_mono_audiosegments(channel[0], channel[1])
|