1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
import os, string
codecs = {
'cn': ('gb2312', 'gbk', 'gb18030', 'hz'),
'tw': ('big5', 'cp950'),
'hk': ('big5hkscs',),
'jp': ('cp932', 'shift_jis', 'euc_jp', 'euc_jisx0213', 'shift_jisx0213',
'euc_jis_2004', 'shift_jis_2004'),
'kr': ('cp949', 'euc_kr', 'johab'),
'iso2022': ('iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2',
'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext',
'iso2022_kr'),
}
TEMPLATE = string.Template("""\
#
# $encoding.py: Python Unicode Codec for $ENCODING
#
# Written by Hye-Shik Chang <perky@FreeBSD.org>
#
import _codecs_$owner, codecs
import _multibytecodec as mbc
codec = _codecs_$owner.getcodec('$encoding')
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='$encoding',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
""")
def gencodecs(prefix):
for loc, encodings in codecs.items():
for enc in encodings:
code = TEMPLATE.substitute(ENCODING=enc.upper(),
encoding=enc.lower(),
owner=loc)
codecpath = os.path.join(prefix, enc + '.py')
with open(codecpath, 'w') as f:
f.write(code)
if __name__ == '__main__':
import sys
gencodecs(sys.argv[1])
|
GitWeb
