mirror of
https://github.com/python/cpython
synced 2026-10-23 07:34:49 +03:00
8ab7b43a14
Supported encodings: "cp932", "cp949", "cp950", "Big5","EUC-JP", "GB2312", "GBK", "johab", and "Shift_JIS". Partially supported encodings (only BMP characters): "Big5-HKSCS", "EUC_JIS-2004", "EUC_JISX0213", "Shift_JIS-2004", "Shift_JISX0213", "utf-8-sig" and non-standard aliases like "UTF8" (without hyphen). The parser now raises ValueError for known unsupported multi-byte encodings such us "ISO-2022-JP" or "raw-unicode-escape" instead of failing later, when encounter non-ASCII data.
47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
""" Python 'raw-unicode-escape' Codec
|
|
|
|
|
|
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
|
|
|
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
|
|
|
"""
|
|
import codecs
|
|
|
|
### Codec APIs
|
|
|
|
class Codec(codecs.Codec):
|
|
|
|
# Note: Binding these as C functions will result in the class not
|
|
# converting them to methods. This is intended.
|
|
encode = codecs.raw_unicode_escape_encode
|
|
decode = codecs.raw_unicode_escape_decode
|
|
|
|
class IncrementalEncoder(codecs.IncrementalEncoder):
|
|
def encode(self, input, final=False):
|
|
return codecs.raw_unicode_escape_encode(input, self.errors)[0]
|
|
|
|
class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
|
|
def _buffer_decode(self, input, errors, final):
|
|
return codecs.raw_unicode_escape_decode(input, errors, final)
|
|
|
|
class StreamWriter(Codec,codecs.StreamWriter):
|
|
pass
|
|
|
|
class StreamReader(Codec,codecs.StreamReader):
|
|
def decode(self, input, errors='strict'):
|
|
return codecs.raw_unicode_escape_decode(input, errors, False)
|
|
|
|
### encodings module API
|
|
|
|
def getregentry():
|
|
return codecs.CodecInfo(
|
|
name='raw-unicode-escape',
|
|
encode=Codec.encode,
|
|
decode=Codec.decode,
|
|
incrementalencoder=IncrementalEncoder,
|
|
incrementaldecoder=IncrementalDecoder,
|
|
streamwriter=StreamWriter,
|
|
streamreader=StreamReader,
|
|
_expat_decoding_table=False,
|
|
)
|