Current Dir: /snap/core22/2955/usr/lib/python3.10/encodings/
[DIR] __pycache__ [ delete | rename ]
[FILE] aliases.py [ edit | delete | rename ]
[FILE] ascii.py [ edit | delete | rename ]
[FILE] base64_codec.py [ edit | delete | rename ]
[FILE] big5.py [ edit | delete | rename ]
[FILE] big5hkscs.py [ edit | delete | rename ]
[FILE] bz2_codec.py [ edit | delete | rename ]
[FILE] charmap.py [ edit | delete | rename ]
[FILE] cp037.py [ edit | delete | rename ]
[FILE] cp273.py [ edit | delete | rename ]
[FILE] cp424.py [ edit | delete | rename ]
[FILE] cp437.py [ edit | delete | rename ]
[FILE] cp500.py [ edit | delete | rename ]
[FILE] cp720.py [ edit | delete | rename ]
[FILE] cp737.py [ edit | delete | rename ]
[FILE] cp775.py [ edit | delete | rename ]
[FILE] cp850.py [ edit | delete | rename ]
[FILE] cp852.py [ edit | delete | rename ]
[FILE] cp855.py [ edit | delete | rename ]
[FILE] cp856.py [ edit | delete | rename ]
[FILE] cp857.py [ edit | delete | rename ]
[FILE] cp858.py [ edit | delete | rename ]
[FILE] cp860.py [ edit | delete | rename ]
[FILE] cp861.py [ edit | delete | rename ]
[FILE] cp862.py [ edit | delete | rename ]
[FILE] cp863.py [ edit | delete | rename ]
[FILE] cp864.py [ edit | delete | rename ]
[FILE] cp865.py [ edit | delete | rename ]
[FILE] cp866.py [ edit | delete | rename ]
[FILE] cp869.py [ edit | delete | rename ]
[FILE] cp874.py [ edit | delete | rename ]
[FILE] cp875.py [ edit | delete | rename ]
[FILE] cp932.py [ edit | delete | rename ]
[FILE] cp949.py [ edit | delete | rename ]
[FILE] cp950.py [ edit | delete | rename ]
[FILE] cp1006.py [ edit | delete | rename ]
[FILE] cp1026.py [ edit | delete | rename ]
[FILE] cp1125.py [ edit | delete | rename ]
[FILE] cp1140.py [ edit | delete | rename ]
[FILE] cp1250.py [ edit | delete | rename ]
[FILE] cp1251.py [ edit | delete | rename ]
[FILE] cp1252.py [ edit | delete | rename ]
[FILE] cp1253.py [ edit | delete | rename ]
[FILE] cp1254.py [ edit | delete | rename ]
[FILE] cp1255.py [ edit | delete | rename ]
[FILE] cp1256.py [ edit | delete | rename ]
[FILE] cp1257.py [ edit | delete | rename ]
[FILE] cp1258.py [ edit | delete | rename ]
[FILE] euc_jisx0213.py [ edit | delete | rename ]
[FILE] euc_jis_2004.py [ edit | delete | rename ]
[FILE] euc_jp.py [ edit | delete | rename ]
[FILE] euc_kr.py [ edit | delete | rename ]
[FILE] gb2312.py [ edit | delete | rename ]
[FILE] gb18030.py [ edit | delete | rename ]
[FILE] gbk.py [ edit | delete | rename ]
[FILE] hex_codec.py [ edit | delete | rename ]
[FILE] hp_roman8.py [ edit | delete | rename ]
[FILE] hz.py [ edit | delete | rename ]
[FILE] idna.py [ edit | delete | rename ]
[FILE] iso2022_jp.py [ edit | delete | rename ]
[FILE] iso2022_jp_1.py [ edit | delete | rename ]
[FILE] iso2022_jp_2.py [ edit | delete | rename ]
[FILE] iso2022_jp_3.py [ edit | delete | rename ]
[FILE] iso2022_jp_2004.py [ edit | delete | rename ]
[FILE] iso2022_jp_ext.py [ edit | delete | rename ]
[FILE] iso2022_kr.py [ edit | delete | rename ]
[FILE] iso8859_1.py [ edit | delete | rename ]
[FILE] iso8859_2.py [ edit | delete | rename ]
[FILE] iso8859_3.py [ edit | delete | rename ]
[FILE] iso8859_4.py [ edit | delete | rename ]
[FILE] iso8859_5.py [ edit | delete | rename ]
[FILE] iso8859_6.py [ edit | delete | rename ]
[FILE] iso8859_7.py [ edit | delete | rename ]
[FILE] iso8859_8.py [ edit | delete | rename ]
[FILE] iso8859_9.py [ edit | delete | rename ]
[FILE] iso8859_10.py [ edit | delete | rename ]
[FILE] iso8859_11.py [ edit | delete | rename ]
[FILE] iso8859_13.py [ edit | delete | rename ]
[FILE] iso8859_14.py [ edit | delete | rename ]
[FILE] iso8859_15.py [ edit | delete | rename ]
[FILE] iso8859_16.py [ edit | delete | rename ]
[FILE] johab.py [ edit | delete | rename ]
[FILE] koi8_r.py [ edit | delete | rename ]
[FILE] koi8_t.py [ edit | delete | rename ]
[FILE] koi8_u.py [ edit | delete | rename ]
[FILE] kz1048.py [ edit | delete | rename ]
[FILE] latin_1.py [ edit | delete | rename ]
[FILE] mac_arabic.py [ edit | delete | rename ]
[FILE] mac_croatian.py [ edit | delete | rename ]
[FILE] mac_cyrillic.py [ edit | delete | rename ]
[FILE] mac_farsi.py [ edit | delete | rename ]
[FILE] mac_greek.py [ edit | delete | rename ]
[FILE] mac_iceland.py [ edit | delete | rename ]
[FILE] mac_latin2.py [ edit | delete | rename ]
[FILE] mac_roman.py [ edit | delete | rename ]
[FILE] mac_romanian.py [ edit | delete | rename ]
[FILE] mac_turkish.py [ edit | delete | rename ]
[FILE] mbcs.py [ edit | delete | rename ]
[FILE] oem.py [ edit | delete | rename ]
[FILE] palmos.py [ edit | delete | rename ]
[FILE] ptcp154.py [ edit | delete | rename ]
[FILE] punycode.py [ edit | delete | rename ]
[FILE] quopri_codec.py [ edit | delete | rename ]
[FILE] raw_unicode_escape.py [ edit | delete | rename ]
[FILE] rot_13.py [ edit | delete | rename ]
[FILE] shift_jis.py [ edit | delete | rename ]
[FILE] shift_jisx0213.py [ edit | delete | rename ]
[FILE] shift_jis_2004.py [ edit | delete | rename ]
[FILE] tis_620.py [ edit | delete | rename ]
[FILE] undefined.py [ edit | delete | rename ]
[FILE] unicode_escape.py [ edit | delete | rename ]
[FILE] utf_7.py [ edit | delete | rename ]
[FILE] utf_8.py [ edit | delete | rename ]
[FILE] utf_8_sig.py [ edit | delete | rename ]
[FILE] utf_16.py [ edit | delete | rename ]
[FILE] utf_16_be.py [ edit | delete | rename ]
[FILE] utf_16_le.py [ edit | delete | rename ]
[FILE] utf_32.py [ edit | delete | rename ]
[FILE] utf_32_be.py [ edit | delete | rename ]
[FILE] utf_32_le.py [ edit | delete | rename ]
[FILE] uu_codec.py [ edit | delete | rename ]
[FILE] zlib_codec.py [ edit | delete | rename ]
[FILE] __init__.py [ edit | delete | rename ]
Viewing: /snap/core22/2955/usr/lib/python3.10/encodings/utf_8_sig.py
""" 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,
)