def x_comm(self):
"""
extract comment field
sets: encoding, lang, shortcomment, longcomment
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.language = data[1:4]
self.shortcomment = ''
self.longcomment = ''
if is_double_byte(self.encoding):
for i in range(4,len(data)-1):
if data[i:i+2] == '\x00\x00':
self.shortcomment = data[4:i].strip('\x00')
self.longcomment = data[i+2:].strip('\x00')
break
else:
for i in range(4,len(data)):
if data[i] == '\x00':
self.shortcomment = data[4:i].strip('\x00')
self.longcomment = data[i+1:].strip('\x00')
break
debug('Read Field: %s Len: %d Enc: %s Lang: %s Comm: %s' %
(self.fid, self.length, self.encoding, self.language,
str([self.shortcomment, self.longcomment])))
def x_text(self):
"""
Extract Text Fields
@todo: handle multiple strings seperated by \x00
sets: encoding, strings
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
rawtext = data[1:]
if normalize_encoding(self.encoding) == 'latin_1':
text = rawtext
self.strings = text.split('\x00')
else:
text = rawtext.decode(self.encoding)
if is_double_byte(self.encoding):
self.strings = text.split('\x00\x00')
else:
self.strings = text.split('\x00')
try:
dummy = text.encode('utf_8')
debug('Read Field: %s Len: %d Enc: %s Text: %s' %
(self.fid, self.length, self.encoding, str([text])))
except UnicodeDecodeError:
debug('Read Field: %s Len: %d Enc: %s Text: %s (Err)' %
(self.fid, self.length, self.encoding, str([text])))
def parse_frames(self):
""" Recursively Parse Frames """
read = 0
readframes = 0
while read < self.tag["size"]:
framedata = self.get_next_frame(self.tag["size"] - read)
if framedata:
try:
read += len(framedata)
if self.version == 2.2:
frame = ID3v2_2_Frame(frame=framedata)
elif self.version == 2.3:
frame = ID3v2_3_Frame(frame=framedata)
elif self.version == 2.4:
frame = ID3v2_4_Frame(frame=framedata)
readframes += 1
self.frames.append(frame)
except ID3Exception:
pass # ignore unrecognised frames
else:
self.tag["padding"] = self._read_null_bytes()
debug("NULL Padding: %d" % self.tag["padding"])
break
# do a sanity check on the size/padding
if not self.tag.has_key("padding"):
self.tag["padding"] = 0
if self.tag["size"] != read + self.tag["padding"]:
self.tag["size"] = read + self.tag["padding"]
return len(self.frames)
def x_text(self):
"""
Extract Text Fields
@todo: handle multiple strings seperated by \x00
sets: encoding, strings
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
rawtext = data[1:]
if normalize_encoding(self.encoding) == 'latin_1':
text = rawtext
self.strings = text.split('\x00')
else:
text = rawtext.decode(self.encoding)
if is_double_byte(self.encoding):
self.strings = text.split('\x00\x00')
else:
self.strings = text.split('\x00')
try:
dummy = text.encode('utf_8')
debug('Read Field: %s Len: %d Enc: %s Text: %s' %
(self.fid, self.length, self.encoding, str([text])))
except UnicodeDecodeError:
debug('Read Field: %s Len: %d Enc: %s Text: %s (Err)' %
(self.fid, self.length, self.encoding, str([text])))
def parse_frames(self):
""" Recursively Parse Frames """
read = 0
readframes = 0
while read < self.tag["size"]:
framedata = self.get_next_frame(self.tag["size"] - read)
if framedata:
try:
read += len(framedata)
if self.version == '2.2':
frame = ID3v2_2_Frame(frame=framedata)
elif self.version == '2.3':
frame = ID3v2_3_Frame(frame=framedata)
elif self.version == '2.4':
frame = ID3v2_4_Frame(frame=framedata)
readframes += 1
self.frames.append(frame)
except ID3Exception:
pass # ignore unrecognised frames
else:
self.tag["padding"] = self._read_null_bytes()
debug("NULL Padding: %d" % self.tag["padding"])
break
# do a sanity check on the size/padding
if not self.tag.has_key("padding"):
self.tag["padding"] = 0
if self.tag["size"] != read + self.tag["padding"]:
self.tag["size"] = read + self.tag["padding"]
return len(self.frames)
def x_comm(self):
"""
extract comment field
sets: encoding, lang, shortcomment, longcomment
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.language = data[1:4]
self.shortcomment = ''
self.longcomment = ''
if is_double_byte(self.encoding):
for i in range(4, len(data) - 1):
if data[i:i + 2] == '\x00\x00':
self.shortcomment = data[4:i].strip('\x00')
self.longcomment = data[i + 2:].strip('\x00')
break
else:
for i in range(4, len(data)):
if data[i] == '\x00':
self.shortcomment = data[4:i].strip('\x00')
self.longcomment = data[i + 1:].strip('\x00')
break
debug('Read Field: %s Len: %d Enc: %s Lang: %s Comm: %s' %
(self.fid, self.length, self.encoding, self.language,
str([self.shortcomment, self.longcomment])))
def x_geob(self):
"""
Extract GEOB
set: encoding, mimetype, filename, desc, obj
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.mimetype = ''
self.filename = ''
self.desc = ''
self.obj = ''
for i in range(1, len(data)):
if data[i] == '\x00':
self.mimetype = data[1:i]
break
if not self.mimetype:
raise ID3FrameException("Unable to extract GEOB. Missing mimetype")
# FIXME: because filename and desc are optional, we should be
# smarter about splitting
if is_double_byte(self.encoding):
for i in range(len(self.mimetype) + 2, len(data) - 1):
if data[i:i + 2] == '\x00\x00':
self.filename = data[len(self.mimetype) + 2:i]
ptr = len(self.mimetype) + len(self.filename) + 4
break
else:
for i in range(len(self.mimetype) + 2, len(data) - 1):
if data[i] == '\x00':
self.filename = data[len(self.mimetype) + 2:i]
ptr = len(self.mimetype) + len(self.filename) + 3
break
if is_double_byte(self.encoding):
for i in range(ptr, len(data) - 1):
if data[i:i + 2] == '\x00\x00':
self.desc = data[ptr:i]
self.obj = data[i + 2:]
break
else:
for i in range(ptr, len(data) - 1):
if data[i] == '\x00':
self.desc = data[ptr:i]
self.obj = data[i + 1:]
break
debug(
"Read Field: %s Len: %d Enc: %s Mime: %s Filename: %s Desc: %s ObjLen: %d"
% (self.fid, self.length, self.encoding, self.mimetype,
self.filename, self.desc, len(self.obj)))
def x_geob(self):
"""
Extract GEOB
set: encoding, mimetype, filename, desc, obj
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.mimetype = ''
self.filename = ''
self.desc = ''
self.obj = ''
for i in range(1,len(data)):
if data[i] == '\x00':
self.mimetype = data[1:i]
break
if not self.mimetype:
raise ID3FrameException("Unable to extract GEOB. Missing mimetype")
# FIXME: because filename and desc are optional, we should be
# smarter about splitting
if is_double_byte(self.encoding):
for i in range(len(self.mimetype)+2,len(data)-1):
if data[i:i+2] == '\x00\x00':
self.filename = data[len(self.mimetype)+2:i]
ptr = len(self.mimetype) + len(self.filename) + 4
break
else:
for i in range(len(self.mimetype)+2,len(data)-1):
if data[i] == '\x00':
self.filename = data[len(self.mimetype)+2:i]
ptr = len(self.mimetype) + len(self.filename) + 3
break
if is_double_byte(self.encoding):
for i in range(ptr,len(data)-1):
if data[i:i+2] == '\x00\x00':
self.desc = data[ptr:i]
self.obj = data[i+2:]
break
else:
for i in range(ptr,len(data)-1):
if data[i] == '\x00':
self.desc = data[ptr:i]
self.obj = data[i+1:]
break
debug("Read Field: %s Len: %d Enc: %s Mime: %s Filename: %s Desc: %s ObjLen: %d" %
(self.fid, self.length, self.encoding, self.mimetype,
self.filename, self.desc, len(self.obj)))
def x_pcnt(self):
"""
Extract Play Count
sets: counter
"""
data = self.rawdata
bytes = self.length
counter = 0
if bytes == 4:
counter = struct.unpack('!I',data)[0]
else:
for i in range(0,bytes):
counter += struct.unpack('B',data[i]) * pow(256,i)
debug('Read Field: %s Len: %d Count: %d' % (self.fid, bytes, counter))
self.counter = counter
def x_pcnt(self):
"""
Extract Play Count
sets: counter
"""
data = self.rawdata
bytes = self.length
counter = 0
if bytes == 4:
counter = struct.unpack('!I', data)[0]
else:
for i in range(0, bytes):
counter += struct.unpack('B', data[i]) * pow(256, i)
debug('Read Field: %s Len: %d Count: %d' % (self.fid, bytes, counter))
self.counter = counter
def x_apic(self):
"""
Extract APIC
set: encoding, mimetype, desc, pict, picttype
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.mimetype = ''
self.desc = ''
self.pict = ''
self.picttype = 0
# get mime type (must be latin-1)
for i in range(1,len(data)):
if data[i] == '\x00':
self.mimetype = data[1:i]
break
if not self.mimetype:
raise ID3FrameException("APIC extraction failed. Missing mimetype")
picttype = ord(data[len(self.mimetype) + 2])
# get picture description
if is_double_byte(self.encoding):
for i in range(len(self.mimetype) + 2, len(data)-1):
if data[i:i+2] == '\x00\x00':
self.desc = data[len(self.mimetype)+2:i]
self.pict = data[i+2:]
break
else:
for i in range(len(self.mimetype) + 2, len(data)):
if data[i] == '\x00':
self.desc = data[len(self.mimetype)+2:i]
self.pict = data[i+1:]
break
debug('Read Field: %s Len: %d PicType: %d Mime: %s Desc: %s PicLen: %d' %
(self.fid, self.length, self.picttype, self.mimetype,
self.desc, len(self.pict)))
def x_apic(self):
"""
Extract APIC
set: encoding, mimetype, desc, pict, picttype
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.mimetype = ''
self.desc = ''
self.pict = ''
self.picttype = 0
# get mime type (must be latin-1)
imgtype = data[1:4]
if not imgtype:
raise ID3FrameException("APIC extraction failed. Missing mimetype")
if imgtype not in ID3V2_2_FRAME_IMAGE_FORMAT_TO_MIME_TYPE.keys():
raise ID3FrameException("Unrecognised mime-type")
else:
self.mimetype = ID3V2_2_FRAME_IMAGE_FORMAT_TO_MIME_TYPE[imgtype]
picttype = ord(data[len(imgtype) + 1])
# get picture description
for i in range(len(imgtype) + 2, len(data) - 1):
print[data[i:i + 3]]
if data[i] == '\x00':
self.desc = data[len(imgtype) + 2:i]
if data[i + 1] == '\x00':
self.pict = data[i + 2:]
else:
self.pict = data[i + 1:]
break
debug(
'Read Field: %s Len: %d PicType: %d Mime: %s Desc: %s PicLen: %d' %
(self.fid, self.length, self.picttype, self.mimetype, self.desc,
len(self.pict)))
def x_apic(self):
"""
Extract APIC
set: encoding, mimetype, desc, pict, picttype
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.mimetype = ''
self.desc = ''
self.pict = ''
self.picttype = 0
# get mime type (must be latin-1)
imgtype = data[1:4]
if not imgtype:
raise ID3FrameException("APIC extraction failed. Missing mimetype")
if imgtype not in ID3V2_2_FRAME_IMAGE_FORMAT_TO_MIME_TYPE.keys():
raise ID3FrameException("Unrecognised mime-type")
else:
self.mimetype = ID3V2_2_FRAME_IMAGE_FORMAT_TO_MIME_TYPE[imgtype]
picttype = ord(data[len(imgtype) + 1])
# get picture description
for i in range(len(imgtype) + 2, len(data) - 1):
#print [data[i:i+3]]
if data[i] == '\x00':
self.desc = data[len(imgtype)+2:i]
if data[i+1] == '\x00':
self.pict = data[i+2:]
else:
self.pict = data[i+1:]
break
debug('Read Field: %s Len: %d PicType: %d Mime: %s Desc: %s PicLen: %d' %
(self.fid, self.length, self.picttype, self.mimetype,
self.desc, len(self.pict)))
def x_apic(self):
"""
Extract APIC
set: encoding, mimetype, desc, pict, picttype
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
self.mimetype = ''
self.desc = ''
self.pict = ''
self.picttype = 0
# get mime type (must be latin-1)
for i in range(1, len(data)):
if data[i] == '\x00':
self.mimetype = data[1:i]
break
if not self.mimetype:
raise ID3FrameException("APIC extraction failed. Missing mimetype")
picttype = ord(data[len(self.mimetype) + 2])
# get picture description
for i in range(len(self.mimetype) + 2, len(data) - 1):
if data[i] == '\x00':
self.desc = data[len(self.mimetype) + 2:i]
if data[i + 1] == '\x00':
self.pict = data[i + 2:]
else:
self.pict = data[i + 1:]
break
debug(
'Read Field: %s Len: %d PicType: %d Mime: %s Desc: %s PicLen: %d' %
(self.fid, self.length, self.picttype, self.mimetype, self.desc,
len(self.pict)))
def parse_header(self):
"""
Parse Header of the file
"""
self.f.seek(0)
data = self.f.read(ID3V2_FILE_HEADER_LENGTH)
if len(data) != ID3V2_FILE_HEADER_LENGTH:
raise ID3HeaderInvalidException("ID3 tag header is incomplete")
self.tag = {}
self.frames = []
id3, ver, flags, rawsize = struct.unpack("!3sHB4s", data)
if id3 != "ID3":
raise ID3HeaderInvalidException("ID3v2 header not found")
self.tag["size"] = unsyncsafe(rawsize)
# NOTE: size = excluding header + footer
version = 2 + (ver / 0x100) * 0.1
if version not in self.supported:
raise ID3NotImplementedException("version %s not supported" % \
str(version))
else:
self.version = version
if self.version in [2.4, 2.3]:
for flagname, bit in ID3V2_3_TAG_HEADER_FLAGS:
self.tag[flagname] = (flags >> bit) & 0x01
elif self.version in [2.2]:
for flagname, bit in ID3V2_2_TAG_HEADER_FLAGS:
self.tag[flagname] = (flags >> bit) & 0x01
if self.tag.has_key("ext") and self.tag["ext"]:
self.parse_ext_header()
debug(self.tag)
def parse_header(self):
"""
Parse Header of the file
"""
self.f.seek(0)
data = self.f.read(ID3V2_FILE_HEADER_LENGTH)
if len(data) != ID3V2_FILE_HEADER_LENGTH:
raise ID3HeaderInvalidException("ID3 tag header is incomplete")
self.tag = {}
self.frames = []
id3, ver, flags, rawsize = struct.unpack("!3sHB4s", data)
if id3 != "ID3":
raise ID3HeaderInvalidException("ID3v2 header not found")
self.tag["size"] = unsyncsafe(rawsize)
# NOTE: size = excluding header + footer
version = '2.%d' % (ver >> 8)
if version not in self.supported:
raise ID3NotImplementedException("version %s not supported" % \
version)
else:
self.version = version
if self.version in ('2.4', '2.3'):
for flagname, bit in ID3V2_3_TAG_HEADER_FLAGS:
self.tag[flagname] = (flags >> bit) & 0x01
elif self.version == '2.2':
for flagname, bit in ID3V2_2_TAG_HEADER_FLAGS:
self.tag[flagname] = (flags >> bit) & 0x01
if self.tag.has_key("ext") and self.tag["ext"]:
self.parse_ext_header()
debug(self.tag)
def x_wxxx(self):
"""
Extract URL
set: encoding, desc, url
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
if is_double_byte(self.encoding):
for i in range(1, len(data) - 1):
if data[i:i + 2] == '\x00\x00':
self.desc = data[1:i]
self.url = data[i + 2:]
break
else:
for i in range(1, len(data)):
if data[i] == '\x00':
self.desc = data[1:i]
self.url = data[i + 1:]
break
debug(
"Read field: %s Len: %s Enc: %s Desc: %s URL: %s" %
(self.fid, self.length, self.encoding, self.desc, str([self.url])))
def x_wxxx(self):
"""
Extract URL
set: encoding, desc, url
"""
data = self.rawdata
self.encoding = encodings[ord(data[0])]
if is_double_byte(self.encoding):
for i in range(1,len(data)-1):
if data[i:i+2] == '\x00\x00':
self.desc = data[1:i]
self.url = data[i+2:]
break
else:
for i in range(1,len(data)):
if data[i] == '\x00':
self.desc = data[1:i]
self.url = data[i+1:]
break
debug("Read field: %s Len: %s Enc: %s Desc: %s URL: %s" %
(self.fid, self.length, self.encoding,
self.desc, str([self.url])))
def x_url(self):
debug("Read Field: %s Len: %d Data: %s" %
(self.fid, self.length, [self.rawdata]))
return
def x_url(self):
debug("Read Field: %s Len: %d Data: %s" %
(self.fid, self.length, [self.rawdata]))
return
