mirror of
https://github.com/python/cpython
synced 2026-10-23 07:34:49 +03:00
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.
53 lines
2 KiB
Python
53 lines
2 KiB
Python
#
|
|
# shift_jis_2004.py: Python Unicode Codec for SHIFT_JIS_2004
|
|
#
|
|
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
|
#
|
|
|
|
import _codecs_jp, codecs
|
|
import _multibytecodec as mbc
|
|
|
|
codec = _codecs_jp.getcodec('shift_jis_2004')
|
|
|
|
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='shift_jis_2004',
|
|
encode=Codec().encode,
|
|
decode=Codec().decode,
|
|
incrementalencoder=IncrementalEncoder,
|
|
incrementaldecoder=IncrementalDecoder,
|
|
streamreader=StreamReader,
|
|
streamwriter=StreamWriter,
|
|
_expat_decoding_table=(
|
|
*range(0x5c), 0xa5, *range(0x5d, 0x7e), 0x203e, 0x7f,
|
|
-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,
|
|
-1, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65, 0xff66, 0xff67,
|
|
0xff68, 0xff69, 0xff6a, 0xff6b, 0xff6c, 0xff6d, 0xff6e, 0xff6f,
|
|
0xff70, 0xff71, 0xff72, 0xff73, 0xff74, 0xff75, 0xff76, 0xff77,
|
|
0xff78, 0xff79, 0xff7a, 0xff7b, 0xff7c, 0xff7d, 0xff7e, 0xff7f,
|
|
0xff80, 0xff81, 0xff82, 0xff83, 0xff84, 0xff85, 0xff86, 0xff87,
|
|
0xff88, 0xff89, 0xff8a, 0xff8b, 0xff8c, 0xff8d, 0xff8e, 0xff8f,
|
|
0xff90, 0xff91, 0xff92, 0xff93, 0xff94, 0xff95, 0xff96, 0xff97,
|
|
0xff98, 0xff99, 0xff9a, 0xff9b, 0xff9c, 0xff9d, 0xff9e, 0xff9f,
|
|
-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),
|
|
)
|