Server IP : 85.214.239.14 / Your IP : 18.116.27.225 Web Server : Apache/2.4.62 (Debian) System : Linux h2886529.stratoserver.net 4.9.0 #1 SMP Tue Jan 9 19:45:01 MSK 2024 x86_64 User : www-data ( 33) PHP Version : 7.4.18 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, MySQL : OFF | cURL : OFF | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : OFF Directory : /proc/3/root/proc/3/task/3/root/usr/lib/python3.11/encodings/ |
Upload File : |
""" Python 'utf-8-sig' Codec This work similar to UTF-8 with the following changes: * On encoding/writing a UTF-8 encoded BOM will be prepended/written as the first three bytes. * On decoding/reading if the first three bytes are a UTF-8 encoded BOM, these bytes will be skipped. """ import codecs ### Codec APIs def encode(input, errors='strict'): return (codecs.BOM_UTF8 + codecs.utf_8_encode(input, errors)[0], len(input)) def decode(input, errors='strict'): prefix = 0 if input[:3] == codecs.BOM_UTF8: input = input[3:] prefix = 3 (output, consumed) = codecs.utf_8_decode(input, errors, True) return (output, consumed+prefix) class IncrementalEncoder(codecs.IncrementalEncoder): def __init__(self, errors='strict'): codecs.IncrementalEncoder.__init__(self, errors) self.first = 1 def encode(self, input, final=False): if self.first: self.first = 0 return codecs.BOM_UTF8 + \ codecs.utf_8_encode(input, self.errors)[0] else: return codecs.utf_8_encode(input, self.errors)[0] def reset(self): codecs.IncrementalEncoder.reset(self) self.first = 1 def getstate(self): return self.first def setstate(self, state): self.first = state class IncrementalDecoder(codecs.BufferedIncrementalDecoder): def __init__(self, errors='strict'): codecs.BufferedIncrementalDecoder.__init__(self, errors) self.first = 1 def _buffer_decode(self, input, errors, final): if self.first: if len(input) < 3: if codecs.BOM_UTF8.startswith(input): # not enough data to decide if this really is a BOM # => try again on the next call return ("", 0) else: self.first = 0 else: self.first = 0 if input[:3] == codecs.BOM_UTF8: (output, consumed) = \ codecs.utf_8_decode(input[3:], errors, final) return (output, consumed+3) return codecs.utf_8_decode(input, errors, final) def reset(self): codecs.BufferedIncrementalDecoder.reset(self) self.first = 1 def getstate(self): state = codecs.BufferedIncrementalDecoder.getstate(self) # state[1] must be 0 here, as it isn't passed along to the caller return (state[0], self.first) def setstate(self, state): # state[1] will be ignored by BufferedIncrementalDecoder.setstate() codecs.BufferedIncrementalDecoder.setstate(self, state) self.first = state[1] class StreamWriter(codecs.StreamWriter): def reset(self): codecs.StreamWriter.reset(self) try: del self.encode except AttributeError: pass def encode(self, input, errors='strict'): self.encode = codecs.utf_8_encode return encode(input, errors) class StreamReader(codecs.StreamReader): def reset(self): codecs.StreamReader.reset(self) try: del self.decode except AttributeError: pass def decode(self, input, errors='strict'): if len(input) < 3: if codecs.BOM_UTF8.startswith(input): # not enough data to decide if this is a BOM # => try again on the next call return ("", 0) elif input[:3] == codecs.BOM_UTF8: self.decode = codecs.utf_8_decode (output, consumed) = codecs.utf_8_decode(input[3:],errors) return (output, consumed+3) # (else) no BOM present self.decode = codecs.utf_8_decode return codecs.utf_8_decode(input, errors) ### encodings module API def getregentry(): return codecs.CodecInfo( name='utf-8-sig', encode=encode, decode=decode, incrementalencoder=IncrementalEncoder, incrementaldecoder=IncrementalDecoder, streamreader=StreamReader, streamwriter=StreamWriter, )