def getstate(self):
# additional state info from the base class must be None here,
# as it isn't passed along to the caller
state = codecs.BufferedIncrementalDecoder.getstate(self)[0]
# additional state info we pass to the caller:
# 0: stream is in natural order for this platform
# 1: stream is in unnatural order
# 2: endianness hasn't been determined yet
if self.decoder is None:
return (state, 2)
addstate = int((sys.byteorder == "big") !=
(self.decoder is codecs.utf_16_be_decode))
return (state, addstate)
python类utf_16_be_decode()的实例源码
def setstate(self, state):
# state[1] will be ignored by BufferedIncrementalDecoder.setstate()
codecs.BufferedIncrementalDecoder.setstate(self, state)
state = state[1]
if state == 0:
self.decoder = (codecs.utf_16_be_decode
if sys.byteorder == "big"
else codecs.utf_16_le_decode)
elif state == 1:
self.decoder = (codecs.utf_16_le_decode
if sys.byteorder == "big"
else codecs.utf_16_be_decode)
else:
self.decoder = None
def decode(self, input, errors='strict'):
(object, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, False)
if byteorder == -1:
self.decode = codecs.utf_16_le_decode
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (object, consumed)
### encodings module API
def _buffer_decode(self, input, errors, final):
if self.decoder is None:
(output, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, final)
if byteorder == -1:
self.decoder = codecs.utf_16_le_decode
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)
def decode(self, input, errors='strict'):
(object, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, False)
if byteorder == -1:
self.decode = codecs.utf_16_le_decode
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError,"UTF-16 stream does not start with BOM"
return (object, consumed)
### encodings module API
def decode(input, errors='strict'):
return codecs.utf_16_be_decode(input, errors, True)
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 _buffer_decode(self, input, errors, final):
if self.decoder is None:
(output, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, final)
if byteorder == -1:
self.decoder = codecs.utf_16_le_decode
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)
def decode(self, input, errors='strict'):
(object, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, False)
if byteorder == -1:
self.decode = codecs.utf_16_le_decode
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError,"UTF-16 stream does not start with BOM"
return (object, consumed)
### encodings module API
def decode(input, errors='strict'):
return codecs.utf_16_be_decode(input, errors, True)
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 decode(input, errors='strict'):
return codecs.utf_16_be_decode(input, errors, True)
def _buffer_decode(self, input, errors, final):
if self.decoder is None:
(output, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, final)
if byteorder == -1:
self.decoder = codecs.utf_16_le_decode
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)
def decode(self, input, errors='strict'):
(object, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, False)
if byteorder == -1:
self.decode = codecs.utf_16_le_decode
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError,"UTF-16 stream does not start with BOM"
return (object, consumed)
### encodings module API
def _buffer_decode(self, input, errors, final):
if self.decoder is None:
(output, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, final)
if byteorder == -1:
self.decoder = codecs.utf_16_le_decode
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)
def decode(self, input, errors='strict'):
(object, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, False)
if byteorder == -1:
self.decode = codecs.utf_16_le_decode
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError,"UTF-16 stream does not start with BOM"
return (object, consumed)
### encodings module API
def decode(input, errors='strict'):
return codecs.utf_16_be_decode(input, errors, True)
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 decode(input, errors='strict'):
return codecs.utf_16_be_decode(input, errors, True)
def _buffer_decode(self, input, errors, final):
if self.decoder is None:
(output, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, final)
if byteorder == -1:
self.decoder = codecs.utf_16_le_decode
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)
