def createStringObject(string):
if isinstance(string, unicode):
return TextStringObject(string)
elif isinstance(string, str):
if string.startswith(codecs.BOM_UTF16_BE):
retval = TextStringObject(string.decode("utf-16"))
retval.autodetect_utf16 = True
return retval
else:
# This is probably a big performance hit here, but we need to
# convert string objects into the text/unicode-aware version if
# possible... and the only way to check if that's possible is
# to try. Some strings are strings, some are just byte arrays.
try:
retval = TextStringObject(decode_pdfdocencoding(string))
retval.autodetect_pdfdocencoding = True
return retval
except UnicodeDecodeError:
return ByteStringObject(string)
else:
raise TypeError("createStringObject should have str or unicode arg")
python类BOM_UTF16_BE的实例源码
def writeToStream(self, stream, encryption_key):
# Try to write the string out as a PDFDocEncoding encoded string. It's
# nicer to look at in the PDF file. Sadly, we take a performance hit
# here for trying...
try:
bytearr = encode_pdfdocencoding(self)
except UnicodeEncodeError:
bytearr = codecs.BOM_UTF16_BE + self.encode("utf-16be")
if encryption_key:
bytearr = RC4_encrypt(encryption_key, bytearr)
obj = ByteStringObject(bytearr)
obj.writeToStream(stream, None)
else:
stream.write("(")
for c in bytearr:
if not c.isalnum() and c != ' ':
stream.write("\\%03o" % ord(c))
else:
stream.write(c)
stream.write(")")
def encodingFromContents( contents ):
if( len(contents) > len(codecs.BOM_UTF8)
and contents[0:len(codecs.BOM_UTF8)] == codecs.BOM_UTF8 ):
encoding = 'utf-8'
elif( len(contents) > len(codecs.BOM_UTF16_LE)
and contents[0:len(codecs.BOM_UTF16_LE)] in [codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE]):
encoding = 'utf-16'
elif( len(contents) > len(codecs.BOM_UTF32_LE)
and contents[0:len(codecs.BOM_UTF32_LE)] in [codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE]):
encoding = 'utf-32'
else:
encoding = locale.getdefaultlocale()[1]
# Mac says mac-roman when utf-8 is what is required
if encoding == 'mac-roman':
encoding = 'utf-8'
if encoding is None:
encoding = 'iso8859-1'
return encoding
def createStringObject(string):
if isinstance(string, utils.string_type):
return TextStringObject(string)
elif isinstance(string, utils.bytes_type):
try:
if string.startswith(codecs.BOM_UTF16_BE):
retval = TextStringObject(string.decode("utf-16"))
retval.autodetect_utf16 = True
return retval
else:
# This is probably a big performance hit here, but we need to
# convert string objects into the text/unicode-aware version if
# possible... and the only way to check if that's possible is
# to try. Some strings are strings, some are just byte arrays.
retval = TextStringObject(decode_pdfdocencoding(string))
retval.autodetect_pdfdocencoding = True
return retval
except UnicodeDecodeError:
return ByteStringObject(string)
else:
raise TypeError("createStringObject should have str or unicode arg")
def writeToStream(self, stream, encryption_key):
# Try to write the string out as a PDFDocEncoding encoded string. It's
# nicer to look at in the PDF file. Sadly, we take a performance hit
# here for trying...
try:
bytearr = encode_pdfdocencoding(self)
except UnicodeEncodeError:
bytearr = codecs.BOM_UTF16_BE + self.encode("utf-16be")
if encryption_key:
bytearr = RC4_encrypt(encryption_key, bytearr)
obj = ByteStringObject(bytearr)
obj.writeToStream(stream, None)
else:
stream.write(b_("("))
for c in bytearr:
if not chr_(c).isalnum() and c != b_(' '):
stream.write(b_("\\%03o" % ord_(c)))
else:
stream.write(b_(chr_(c)))
stream.write(b_(")"))
def _detect_encoding(self, fileid):
if isinstance(fileid, PathPointer):
s = fileid.open().readline()
else:
with open(fileid, 'rb') as infile:
s = infile.readline()
if s.startswith(codecs.BOM_UTF16_BE):
return 'utf-16-be'
if s.startswith(codecs.BOM_UTF16_LE):
return 'utf-16-le'
if s.startswith(codecs.BOM_UTF32_BE):
return 'utf-32-be'
if s.startswith(codecs.BOM_UTF32_LE):
return 'utf-32-le'
if s.startswith(codecs.BOM_UTF8):
return 'utf-8'
m = re.match(br'\s*<\?xml\b.*\bencoding="([^"]+)"', s)
if m:
return m.group(1).decode()
m = re.match(br"\s*<\?xml\b.*\bencoding='([^']+)'", s)
if m:
return m.group(1).decode()
# No encoding found -- what should the default be?
return 'utf-8'
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
if encoding:
self.rawStream.seek(seek)
return lookupEncoding(encoding)
else:
self.rawStream.seek(0)
return None
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def determine_encoding(self):
while not self.eof and len(self.raw_buffer) < 2:
self.update_raw()
if not isinstance(self.raw_buffer, unicode):
if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
self.raw_decode = codecs.utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = codecs.utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = codecs.utf_8_decode
self.encoding = 'utf-8'
self.update(1)
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def determine_encoding(self):
while not self.eof and len(self.raw_buffer) < 2:
self.update_raw()
if not isinstance(self.raw_buffer, unicode):
if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
self.raw_decode = codecs.utf_16_le_decode
self.encoding = 'utf-16-le'
elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
self.raw_decode = codecs.utf_16_be_decode
self.encoding = 'utf-16-be'
else:
self.raw_decode = codecs.utf_8_decode
self.encoding = 'utf-8'
self.update(1)
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
def guess_json_utf(data):
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
return 'utf-16' # BOM included
nullcount = sample.count(_null)
if nullcount == 0:
return 'utf-8'
if nullcount == 2:
if sample[::2] == _null2: # 1st and 3rd are null
return 'utf-16-be'
if sample[1::2] == _null2: # 2nd and 4th are null
return 'utf-16-le'
# Did not detect 2 valid UTF-16 ascii-range characters
if nullcount == 3:
if sample[:3] == _null3:
return 'utf-32-be'
if sample[1:] == _null3:
return 'utf-32-le'
# Did not detect a valid UTF-32 ascii-range character
return None
def detectBOM(self):
"""Attempts to detect at BOM at the start of the stream. If
an encoding can be determined from the BOM return the name of the
encoding otherwise return None"""
bomDict = {
codecs.BOM_UTF8: 'utf-8',
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
}
# Go to beginning of file and read in 4 bytes
string = self.rawStream.read(4)
assert isinstance(string, bytes)
# Try detecting the BOM using bytes from the string
encoding = bomDict.get(string[:3]) # UTF-8
seek = 3
if not encoding:
# Need to detect UTF-32 before UTF-16
encoding = bomDict.get(string) # UTF-32
seek = 4
if not encoding:
encoding = bomDict.get(string[:2]) # UTF-16
seek = 2
# Set the read position past the BOM if one was found, otherwise
# set it to the start of the stream
self.rawStream.seek(encoding and seek or 0)
return encoding
