jamie/wavinfo
1
0
Fork 0
mirror of https://github.com/iluvcapra/wavinfo.git synced 2025-12-31 08:50:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed bext parsing for metacorder

Browse Source 
These have really screwed-up bext chunks that aren't zero-filled.
This commit is contained in:
Jamie Hardt
2019-01-01 19:30:43 -08:00
parent d37726f090
commit ae09897abf
3 changed files with 81 additions and 133 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
examples/wavinfo.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@@ -12,118 +12,47 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 5,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"pp = pprint.PrettyPrinter(indent=4)" "pp = pprint.PrettyPrinter(indent=4)"
] ]
}, },
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"testfile_path = \"../tests/test_files/\"\n",
"sound_devices_file = testfile_path + \"A101_1.WAV\"\n",
"\n",
"info = wavinfo.WavInfoReader(sound_devices_file)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WavInfoFormat(audio_format=1, channel_count=2, sample_rate=48000, byte_rate=288000, block_align=6, bits_per_sample=24)\n"
]
}
],
"source": [
"pp.pprint(info.fmt)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WavBextFormat(description='sSPEED=023.976-ND\\r\\nsTAKE=1\\r\\nsUBITS=$12311801\\r\\nsSWVER=2.67\\r\\nsPROJECT=BMH\\r\\nsSCENE=A101\\r\\nsFILENAME=A101_1.WAV\\r\\nsTAPE=18Y12M31\\r\\nsTRK1=MKH516 A\\r\\nsTRK2=Boom\\r\\nsNOTE=\\r\\n', originator='Sound Dev: 702T S#GR1112089007', originator_ref='USSDVGR1112089007124001008206301', originator_date='2018-12-31', originator_time='12:40:00', time_reference=2190940753, version=1, umid=b'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00', loudness_value=0.0, loudness_range=0.0, max_true_peak=0.0, max_momentary_loudness=0.0, max_shortterm_loudness=0.0, coding_history='A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch\\r\\n')\n"
]
}
],
"source": [
"pp.pprint(info.bext)"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('BMH', 'A101', '1', 240239)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"info.ixml.project, info.ixml.scene, info.ixml.take, info.data.frame_count"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": [
"metacorder_path = '../tests/test_files/metacorder/Sr001-001-06_01.WAV'\n",
"\n",
"info = wavinfo.WavInfoReader(metacorder_path)"
]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 7,
"metadata": {}, "metadata": {
"outputs": [], "scrolled": true
"source": [ },
"pro_tools_file = testfile_path + \"PT A101_4.A1.wav\""
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"[ ChunkDescriptor(ident=b'bext', start=20, length=858),\n", "[ ChunkDescriptor(ident=b'bext', start=20, length=858),\n",
" ChunkDescriptor(ident=b'iXML', start=886, length=5226),\n", " ChunkDescriptor(ident=b'fmt ', start=886, length=16),\n",
" ChunkDescriptor(ident=b'fmt ', start=6120, length=16),\n", " ChunkDescriptor(ident=b'data', start=910, length=1725696),\n",
" ChunkDescriptor(ident=b'data', start=6144, length=864840),\n", " ChunkDescriptor(ident=b'iXML', start=1726614, length=2852),\n",
" ChunkDescriptor(ident=b'umid', start=870992, length=24),\n", " ChunkDescriptor(ident=b'iXTC', start=1729474, length=20)]\n"
" ChunkDescriptor(ident=b'minf', start=871024, length=16),\n",
" ChunkDescriptor(ident=b'regn', start=871048, length=92)]\n"
] ]
} }
], ],
"source": [ "source": [
"import wavinfo.wave_parser\n", "import wavinfo.wave_parser\n",
"\n", "\n",
"with open(pro_tools_file,'rb') as f:\n", "with open(metacorder_path,'rb') as f:\n",
" chunk_tree = wavinfo.wave_parser.parse_chunk(f)\n", " chunk_tree = wavinfo.wave_parser.parse_chunk(f)\n",
"\n", "\n",
"pp.pprint(chunk_tree.children)" "pp.pprint(chunk_tree.children)"
@@ -131,39 +60,49 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 12,
"metadata": {}, "metadata": {},
"outputs": [],
"source": [
"# with open(metacorder_path,'rb') as f:\n",
"# f.seek(chunk_tree.children[4].start)\n",
"# iXTC_data = f.read(chunk_tree.children[4].length)\n",
" \n",
"# print(iXTC_data)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"scrolled": true
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"WavBextFormat(description='dUBITS=12311804\\r\\ndSCENE=A101\\r\\ndTAKE=4\\r\\ndTAPE=18Y12M31\\r\\ndFRAMERATE=23.976ND\\r\\ndSPEED=023.976-NDF\\r\\ndTRK1=MKH516 A\\r\\ndTRK2=Boom\\r\\n', originator='Sound Dev: 702T S#GR1112089007', originator_ref='aa4CKtcd13Vk', originator_date='2018-12-31', originator_time='12:40:07', time_reference=2191709524, version=0, umid=b'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00', loudness_value=0.0, loudness_range=0.0, max_true_peak=0.0, max_momentary_loudness=0.0, max_shortterm_loudness=0.0, coding_history='A=PCM,F=48000,W=24,M=stereo,R=48000,T=2 Ch\\r\\n')\n" "WavBextFormat(description='gSCENE=001\\r\\ngTAKE=06\\r\\ngTAPE=Sr001\\r\\ngUBITS=00000000\\r\\n', originator='Metacorder Demo', originator_ref='', originator_date='2019:01:01', originator_time='13:36:16', time_reference=2350375830, version=0, umid=b'\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00', loudness_value=0.0, loudness_range=0.0, max_true_peak=0.0, max_momentary_loudness=0.0, max_shortterm_loudness=0.0, coding_history='')\n"
] ]
} }
], ],
"source": [ "source": [
"ptinfo = wavinfo.WavInfoReader(pro_tools_file)\n", "with open(metacorder_path,'rb') as f:\n",
" f.seek(chunk_tree.children[0].start)\n",
" bext_raw = f.read(chunk_tree.children[0].length)\n",
"\n", "\n",
"print(ptinfo.bext)" "# ptinfo = wavinfo.WavInfoReader(metacorder_path)\n",
"\n",
"print(wavinfo.WavInfoReader(metacorder_path).bext)"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": null,
"metadata": {}, "metadata": {
"outputs": [ "scrolled": false
{ },
"data": { "outputs": [],
"text/plain": [
"'<BWFXML><IXML_VERSION>1.61</IXML_VERSION><STEINBERG><ATTR_LIST><ATTR><TYPE>string</TYPE><NAME>MediaLibrary</NAME><VALUE>The Recordist Christmas 2018</VALUE></ATTR><ATTR><TYPE>string</TYPE><NAME>MediaCategoryPost</NAME><VALUE>Bullets</VALUE></ATTR><ATTR><TYPE>string</TYPE><NAME>MediaLibraryManufacturerName</NAME><VALUE>Creative Sound Design, LLC</VALUE></ATTR><ATTR><TYPE>string</TYPE><NAME>AudioSoundEditor</NAME><VALUE>Frank Bry</VALUE></ATTR><ATTR><TYPE>string</TYPE><NAME>MediaComment</NAME><VALUE>BULLET Impact Plastic LCD TV Screen Shatter Debris 2x</VALUE></ATTR><ATTR><TYPE>string</TYPE><NAME>MusicalCategory</NAME><VALUE>Bullets</VALUE></ATTR></ATTR_LIST></STEINBERG></BWFXML>'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"library_sound = testfile_path + 'BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'\n", "library_sound = testfile_path + 'BULLET Impact Plastic LCD TV Screen Shatter Debris 2x.wav'\n",
"\n", "\n",
@@ -174,25 +113,11 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": null,
"metadata": {}, "metadata": {
"outputs": [ "scrolled": true
{ },
"name": "stdout", "outputs": [],
"output_type": "stream",
"text": [
"[ ChunkDescriptor(ident=b'fmt ', start=20, length=40),\n",
" ChunkDescriptor(ident=b'bext', start=68, length=604),\n",
" ChunkDescriptor(ident=b'data', start=680, length=2833404),\n",
" ChunkDescriptor(ident=b'ID3 ', start=2834092, length=2048),\n",
" ChunkDescriptor(ident=b'SMED', start=2836148, length=5468),\n",
" ListChunkDescriptor(signature=b'INFO', children=[ChunkDescriptor(ident=b'IPRD', start=2841636, length=30), ChunkDescriptor(ident=b'IGNR', start=2841674, length=8), ChunkDescriptor(ident=b'IART', start=2841690, length=10), ChunkDescriptor(ident=b'ICMT', start=2841708, length=54), ChunkDescriptor(ident=b'ICOP', start=2841770, length=84), ChunkDescriptor(ident=b'ISFT', start=2841862, length=12), ChunkDescriptor(ident=b'ICRD', start=2841882, length=12)]),\n",
" ChunkDescriptor(ident=b'iXML', start=2841902, length=686),\n",
" ChunkDescriptor(ident=b'umid', start=2842596, length=24),\n",
" ChunkDescriptor(ident=b'_PMX', start=2842628, length=3560)]\n"
]
}
],
"source": [ "source": [
"with open(library_sound,'rb') as f:\n", "with open(library_sound,'rb') as f:\n",
" chunk_tree = wavinfo.wave_parser.parse_chunk(f)\n", " chunk_tree = wavinfo.wave_parser.parse_chunk(f)\n",

16
tests/test_wave_parsing.py
View File

@@ -29,7 +29,7 @@ class TestWaveInfo(TestCase):
for dirpath, dirnames, filenames in os.walk('tests/test_files'): for dirpath, dirnames, filenames in os.walk('tests/test_files'):
for filename in filenames: for filename in filenames:
name, ext = os.path.splitext(filename) name, ext = os.path.splitext(filename)
if ext == '.wav': if ext in ['.wav','.WAV']:
yield os.path.join(dirpath, filename) yield os.path.join(dirpath, filename)
@@ -68,13 +68,23 @@ class TestWaveInfo(TestCase):
self.assertEqual( info.bext.description, ffprobe_info['format']['tags']['comment'] ) self.assertEqual( info.bext.description, ffprobe_info['format']['tags']['comment'] )
self.assertEqual( info.bext.originator, ffprobe_info['format']['tags']['encoded_by'] ) self.assertEqual( info.bext.originator, ffprobe_info['format']['tags']['encoded_by'] )
self.assertEqual( info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference'] ) if 'originator_reference' in ffprobe_info['format']['tags']:
self.assertEqual( info.bext.originator_ref, ffprobe_info['format']['tags']['originator_reference'] )
else:
self.assertEqual( info.bext.originator_ref, None)
# these don't always reflect the bext info # these don't always reflect the bext info
#self.assertEqual( info.bext.originator_date, ffprobe_info['format']['tags']['date'] ) #self.assertEqual( info.bext.originator_date, ffprobe_info['format']['tags']['date'] )
#self.assertEqual( info.bext.originator_time, ffprobe_info['format']['tags']['creation_time'] ) #self.assertEqual( info.bext.originator_time, ffprobe_info['format']['tags']['creation_time'] )
self.assertEqual( info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference']) ) self.assertEqual( info.bext.time_reference, int(ffprobe_info['format']['tags']['time_reference']) )
self.assertEqual( info.bext.coding_history, ffprobe_info['format']['tags']['coding_history'] )
if 'coding_history' in ffprobe_info['format']['tags']:
if len(ffprobe_info['format']['tags']['coding_history']) > 0:
self.assertEqual( info.bext.coding_history, ffprobe_info['format']['tags']['coding_history'] )
else:
self.assertEqual( info.bext.coding_history, None )
else:
self.assertEqual( info.bext.coding_history, None )
def test_ixml(self): def test_ixml(self):
expected = {'A101_4.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '4', expected = {'A101_4.WAV': {'project' : 'BMH', 'scene': 'A101', 'take': '4',

27
wavinfo/wave_reader.py
View File

@@ -87,7 +87,7 @@ class WavInfoReader():
bits_per_sample = unpacked[5] bits_per_sample = unpacked[5]
) )
def _get_bext(self,f): def _get_bext(self,f,encoding='ascii'):
bext_data = self._find_chunk_data(b'bext',f,default_none=True) bext_data = self._find_chunk_data(b'bext',f,default_none=True)
@@ -117,11 +117,24 @@ class WavInfoReader():
rest_starts = struct.calcsize(packstring) rest_starts = struct.calcsize(packstring)
unpacked = struct.unpack(packstring, bext_data[:rest_starts]) unpacked = struct.unpack(packstring, bext_data[:rest_starts])
return WavBextFormat(description=unpacked[0].decode('ascii').rstrip('\0'), def sanatize_bytes(bytes):
originator = unpacked[1].decode('ascii').rstrip('\0'), first_null = next( (index for index, byte in enumerate(bytes) if byte == 0 ), None )
originator_ref = unpacked[2].decode('ascii').rstrip('\0'), if first_null is not None:
originator_date = unpacked[3].decode('ascii'), trimmed = bytes[:first_null]
originator_time = unpacked[4].decode('ascii'), else:
trimmed = bytes
decoded = trimmed.decode(encoding)
if len(decoded) > 0:
return decoded
else:
return None
return WavBextFormat(description=sanatize_bytes(unpacked[0]),
originator = sanatize_bytes(unpacked[1]),
originator_ref = sanatize_bytes(unpacked[2]),
originator_date = sanatize_bytes(unpacked[3]),
originator_time = sanatize_bytes(unpacked[4]),
time_reference = unpacked[5], time_reference = unpacked[5],
version = unpacked[6], version = unpacked[6],
umid = unpacked[7], umid = unpacked[7],
@@ -130,7 +143,7 @@ class WavInfoReader():
max_true_peak = unpacked[10] / 100.0, max_true_peak = unpacked[10] / 100.0,
max_momentary_loudness = unpacked[11] / 100.0, max_momentary_loudness = unpacked[11] / 100.0,
max_shortterm_loudness = unpacked[12] / 100.0, max_shortterm_loudness = unpacked[12] / 100.0,
coding_history = bext_data[rest_starts:].decode('ascii').rstrip('\0') coding_history = sanatize_bytes(bext_data[rest_starts:])
) )
def _get_ixml(self,f): def _get_ixml(self,f):