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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
""" Python 'utf-16' Codec
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""
import codecs, sys
### Codec APIs
encode = codecs.utf_16_encode
def decode(input, errors='strict'):
return codecs.utf_16_decode(input, errors, True)
class IncrementalEncoder(codecs.IncrementalEncoder):
def __init__(self, errors='strict'):
codecs.IncrementalEncoder.__init__(self, errors)
self.encoder = None
def encode(self, input, final=False):
if self.encoder is None:
result = codecs.utf_16_encode(input, self.errors)[0]
if sys.byteorder == 'little':
self.encoder = codecs.utf_16_le_encode
else:
self.encoder = codecs.utf_16_be_encode
return result
return self.encoder(input, self.errors)[0]
def reset(self):
codecs.IncrementalEncoder.reset(self)
self.encoder = None
def getstate(self):
# state info we return to the caller:
# 0: stream is in natural order for this platform
# 2: endianness hasn't been determined yet
# (we're never writing in unnatural order)
return (2 if self.encoder is None else 0)
def setstate(self, state):
if state:
self.encoder = None
else:
if sys.byteorder == 'little':
self.encoder = codecs.utf_16_le_encode
else:
self.encoder = codecs.utf_16_be_encode
class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
def __init__(self, errors='strict'):
codecs.BufferedIncrementalDecoder.__init__(self, errors)
self.decoder = None
def _buffer_decode(self, input, errors, final):
if self.decoder is None:
(output, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, final)
if byteorder == -1:
self.decoder = codecs.utf_16_le_decode
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)
def reset(self):
codecs.BufferedIncrementalDecoder.reset(self)
self.decoder = None
def getstate(self):
# additonal state info from the base class must be None here,
# as it isn't passed along to the caller
state = codecs.BufferedIncrementalDecoder.getstate(self)[0]
# additional state info we pass to the caller:
# 0: stream is in natural order for this platform
# 1: stream is in unnatural order
# 2: endianness hasn't been determined yet
if self.decoder is None:
return (state, 2)
addstate = int((sys.byteorder == "big") !=
(self.decoder is codecs.utf_16_be_decode))
return (state, addstate)
def setstate(self, state):
# state[1] will be ignored by BufferedIncrementalDecoder.setstate()
codecs.BufferedIncrementalDecoder.setstate(self, state)
state = state[1]
if state == 0:
self.decoder = (codecs.utf_16_be_decode
if sys.byteorder == "big"
else codecs.utf_16_le_decode)
elif state == 1:
self.decoder = (codecs.utf_16_le_decode
if sys.byteorder == "big"
else codecs.utf_16_be_decode)
else:
self.decoder = None
class StreamWriter(codecs.StreamWriter):
def __init__(self, stream, errors='strict'):
self.bom_written = False
codecs.StreamWriter.__init__(self, stream, errors)
def encode(self, input, errors='strict'):
self.bom_written = True
result = codecs.utf_16_encode(input, errors)
if sys.byteorder == 'little':
self.encode = codecs.utf_16_le_encode
else:
self.encode = codecs.utf_16_be_encode
return result
class StreamReader(codecs.StreamReader):
def reset(self):
codecs.StreamReader.reset(self)
try:
del self.decode
except AttributeError:
pass
def decode(self, input, errors='strict'):
(object, consumed, byteorder) = \
codecs.utf_16_ex_decode(input, errors, 0, False)
if byteorder == -1:
self.decode = codecs.utf_16_le_decode
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError,"UTF-16 stream does not start with BOM"
return (object, consumed)
### encodings module API
def getregentry():
return codecs.CodecInfo(
name='utf-16',
encode=encode,
decode=decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamreader=StreamReader,
streamwriter=StreamWriter,
)
|
