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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
|
# implements a factory to create codec instances for a given java charset
import codecs
from array import array
from functools import partial
from java.lang import StringBuilder
from java.nio import ByteBuffer, CharBuffer
from java.nio.charset import Charset, IllegalCharsetNameException
from StringIO import StringIO
python_to_java = {
'cp932': 'cp942',
'iso2022_jp': 'ISO-2022-JP',
'iso2022_jp_2': 'ISO-2022-JP-2',
'iso2022_kr': 'ISO-2022-KR',
'shift_jisx0213': 'x-SJIS_0213',
}
def _java_factory(encoding):
encoding = python_to_java.get(encoding, encoding)
supported = False
try:
supported = Charset.isSupported(encoding)
except IllegalCharsetNameException:
pass
if not supported:
return None, set()
charset = Charset.forName(encoding) # FIXME should we return this canonical name? could be best... TBD
entry = codecs.CodecInfo(
name=encoding,
encode=Codec(encoding).encode,
decode=Codec(encoding).decode,
incrementalencoder=partial(IncrementalEncoder, encoding=encoding),
incrementaldecoder=partial(IncrementalDecoder, encoding=encoding),
streamreader=partial(StreamReader, encoding=encoding),
streamwriter=partial(StreamWriter, encoding=encoding)
)
return entry, charset.aliases()
class Codec(object): # (codecs.Codec):
def __init__(self, encoding):
self.encoding = encoding
def decode(self, input, errors='strict', final=True):
error_function = codecs.lookup_error(errors)
input_buffer = ByteBuffer.wrap(array('b', input))
decoder = Charset.forName(self.encoding).newDecoder()
output_buffer = CharBuffer.allocate(min(max(int(len(input) / 2), 256), 1024))
builder = StringBuilder(int(decoder.averageCharsPerByte() * len(input)))
while True:
result = decoder.decode(input_buffer, output_buffer, False)
pos = output_buffer.position()
output_buffer.rewind()
builder.append(output_buffer.subSequence(0, pos))
if result.isUnderflow():
if final:
_process_incomplete_decode(self.encoding, input, error_function, input_buffer, builder)
break
_process_decode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.toString(), input_buffer.position()
def encode(self, input, errors='strict'):
error_function = codecs.lookup_error(errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
encoder = Charset.forName(self.encoding).newEncoder()
output_buffer = ByteBuffer.allocate(min(max(len(input) * 2, 256), 1024))
builder = StringIO()
while True:
result = encoder.encode(input_buffer, output_buffer, True)
pos = output_buffer.position()
output_buffer.rewind()
builder.write(output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue(), len(input)
class NonfinalCodec(Codec):
def decode(self, input, errors='strict'):
return Codec.decode(self, input, errors, final=False)
class IncrementalEncoder(codecs.IncrementalEncoder):
def __init__(self, errors='strict', encoding=None):
assert encoding
self.encoding = encoding
self.errors = errors
self.encoder = Charset.forName(self.encoding).newEncoder()
self.output_buffer = ByteBuffer.allocate(1024)
def encode(self, input, final=False):
error_function = codecs.lookup_error(self.errors)
# workaround non-BMP issues - need to get the exact count of chars, not codepoints
input_buffer = CharBuffer.allocate(StringBuilder(input).length())
input_buffer.put(input)
input_buffer.rewind()
self.output_buffer.rewind()
builder = StringIO()
while True:
result = self.encoder.encode(input_buffer, self.output_buffer, final)
pos = self.output_buffer.position()
self.output_buffer.rewind()
builder.write(self.output_buffer.array()[0:pos].tostring())
if result.isUnderflow():
break
_process_encode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.getvalue()
class IncrementalDecoder(codecs.IncrementalDecoder):
def __init__(self, errors='strict', encoding=None,):
assert encoding
self.encoding = encoding
self.errors = errors
self.decoder = Charset.forName(self.encoding).newDecoder()
self.output_buffer = CharBuffer.allocate(1024)
self.buffer = ''
def decode(self, input, final=False):
error_function = codecs.lookup_error(self.errors)
input_array = array('b', self.buffer + str(input))
input_buffer = ByteBuffer.wrap(input_array)
builder = StringBuilder(int(self.decoder.averageCharsPerByte() * len(input)))
self.output_buffer.rewind()
while True:
result = self.decoder.decode(input_buffer, self.output_buffer, final)
pos = self.output_buffer.position()
self.output_buffer.rewind()
builder.append(self.output_buffer.subSequence(0, pos))
if result.isUnderflow():
if not final:
# Keep around any remaining input for next call to decode
self.buffer = input_array[input_buffer.position():input_buffer.limit()].tostring()
else:
_process_incomplete_decode(self.encoding, input, error_function, input_buffer, builder)
break
_process_decode_errors(self.encoding, input, result, error_function, input_buffer, builder)
return builder.toString()
def reset(self):
self.buffer = ""
self.decoder.reset()
def getstate(self):
# No way to extract the internal state of a Java decoder.
return self.buffer or "", 0
def setstate(self, state):
self.buffer, _ = state or ("", 0)
# No way to restore: reset possible EOF state.
self.decoder.reset()
class StreamWriter(NonfinalCodec, codecs.StreamWriter):
def __init__(self, stream, errors='strict', encoding=None, ):
NonfinalCodec.__init__(self, encoding)
codecs.StreamWriter.__init__(self, stream, errors)
class StreamReader(NonfinalCodec, codecs.StreamReader):
def __init__(self, stream, errors='strict', encoding=None, ):
NonfinalCodec.__init__(self, encoding)
codecs.StreamReader.__init__(self, stream, errors)
def _process_decode_errors(encoding, input, result, error_function, input_buffer, builder):
if result.isError():
e = UnicodeDecodeError(
encoding,
input,
input_buffer.position(),
input_buffer.position() + result.length(),
'illegal multibyte sequence')
replacement, pos = error_function(e)
if not isinstance(replacement, unicode):
raise TypeError()
pos = int(pos)
if pos < 0:
pos = input_buffer.limit() + pos
if pos > input_buffer.limit():
raise IndexError()
builder.append(replacement)
input_buffer.position(pos)
def _process_incomplete_decode(encoding, input, error_function, input_buffer, builder):
if input_buffer.position() < input_buffer.limit():
e = UnicodeDecodeError(
encoding,
input,
input_buffer.position(),
input_buffer.limit(),
'illegal multibyte sequence')
replacement, pos = error_function(e)
if not isinstance(replacement, unicode):
raise TypeError()
pos = int(pos)
if pos < 0:
pos = input_buffer.limit() + pos
if pos > input_buffer.limit():
raise IndexError()
builder.append(replacement)
input_buffer.position(pos)
def _get_unicode(input_buffer, result):
return input_buffer.subSequence(0, result.length()).toString()
def _process_encode_errors(encoding, input, result, error_function, input_buffer, builder):
if result.isError():
e = UnicodeEncodeError(
encoding,
input,
input_buffer.position(),
input_buffer.position() + result.length(),
'illegal multibyte sequence')
replacement, pos = error_function(e)
if not isinstance(replacement, unicode):
raise TypeError()
pos = int(pos)
if pos < 0:
pos = input_buffer.limit() + pos
if pos > input_buffer.limit():
raise IndexError()
builder.write(str(replacement))
input_buffer.position(pos)
|
