cpython/Lib/encodings/gb2312.py
Serhiy Storchaka 8ab7b43a14
gh-62259: Add support of multi-byte encodings in the XML parser (GH-149860)
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.
2026-05-26 19:40:25 +00:00

48 lines
1.6 KiB
Python

#
# gb2312.py: Python Unicode Codec for GB2312
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_cn, codecs
import _multibytecodec as mbc
codec = _codecs_cn.getcodec('gb2312')
class Codec(codecs.Codec):
encode = codec.encode
decode = codec.decode
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
codecs.IncrementalEncoder):
codec = codec
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
codecs.IncrementalDecoder):
codec = codec
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
codec = codec
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
codec = codec
def getregentry():
return codecs.CodecInfo(
name='gb2312',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
_expat_decoding_table=(*range(128),
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
-1, -2, -2, -2, -2, -2, -2, -2, -2, -2, -1, -1, -1, -1, -1, -1,
-2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2,
-2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2,
-2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2,
-2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2, -2,
-2, -2, -2, -2, -2, -2, -2, -2, -1, -1, -1, -1, -1, -1, -1, -1),
)