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
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
|
# This module implements the RFCs 3490 (IDNA) and 3491 (Nameprep)
import stringprep, re, codecs
from unicodedata import ucd_3_2_0 as unicodedata
# IDNA section 3.1
dots = re.compile("[\u002E\u3002\uFF0E\uFF61]")
# IDNA section 5
ace_prefix = b"xn--"
sace_prefix = "xn--"
# This assumes query strings, so AllowUnassigned is true
def nameprep(label):
# Map
newlabel = []
for c in label:
if stringprep.in_table_b1(c):
# Map to nothing
continue
newlabel.append(stringprep.map_table_b2(c))
label = "".join(newlabel)
# Normalize
label = unicodedata.normalize("NFKC", label)
# Prohibit
for c in label:
if stringprep.in_table_c12(c) or \
stringprep.in_table_c22(c) or \
stringprep.in_table_c3(c) or \
stringprep.in_table_c4(c) or \
stringprep.in_table_c5(c) or \
stringprep.in_table_c6(c) or \
stringprep.in_table_c7(c) or \
stringprep.in_table_c8(c) or \
stringprep.in_table_c9(c):
raise UnicodeError("Invalid character %r" % c)
# Check bidi
RandAL = [stringprep.in_table_d1(x) for x in label]
if any(RandAL):
# There is a RandAL char in the string. Must perform further
# tests:
# 1) The characters in section 5.8 MUST be prohibited.
# This is table C.8, which was already checked
# 2) If a string contains any RandALCat character, the string
# MUST NOT contain any LCat character.
if any(stringprep.in_table_d2(x) for x in label):
raise UnicodeError("Violation of BIDI requirement 2")
# 3) If a string contains any RandALCat character, a
# RandALCat character MUST be the first character of the
# string, and a RandALCat character MUST be the last
# character of the string.
if not RandAL[0] or not RandAL[-1]:
raise UnicodeError("Violation of BIDI requirement 3")
return label
def ToASCII(label):
try:
# Step 1: try ASCII
label = label.encode("ascii")
except UnicodeError:
pass
else:
# Skip to step 3: UseSTD3ASCIIRules is false, so
# Skip to step 8.
if 0 < len(label) < 64:
return label
raise UnicodeError("label empty or too long")
# Step 2: nameprep
label = nameprep(label)
# Step 3: UseSTD3ASCIIRules is false
# Step 4: try ASCII
try:
label = label.encode("ascii")
except UnicodeError:
pass
else:
# Skip to step 8.
if 0 < len(label) < 64:
return label
raise UnicodeError("label empty or too long")
# Step 5: Check ACE prefix
if label.startswith(sace_prefix):
raise UnicodeError("Label starts with ACE prefix")
# Step 6: Encode with PUNYCODE
label = label.encode("punycode")
# Step 7: Prepend ACE prefix
label = ace_prefix + label
# Step 8: Check size
if 0 < len(label) < 64:
return label
raise UnicodeError("label empty or too long")
def ToUnicode(label):
# Step 1: Check for ASCII
if isinstance(label, bytes):
pure_ascii = True
else:
try:
label = label.encode("ascii")
pure_ascii = True
except UnicodeError:
pure_ascii = False
if not pure_ascii:
# Step 2: Perform nameprep
label = nameprep(label)
# It doesn't say this, but apparently, it should be ASCII now
try:
label = label.encode("ascii")
except UnicodeError:
raise UnicodeError("Invalid character in IDN label")
# Step 3: Check for ACE prefix
if not label.startswith(ace_prefix):
return str(label, "ascii")
# Step 4: Remove ACE prefix
label1 = label[len(ace_prefix):]
# Step 5: Decode using PUNYCODE
result = label1.decode("punycode")
# Step 6: Apply ToASCII
label2 = ToASCII(result)
# Step 7: Compare the result of step 6 with the one of step 3
# label2 will already be in lower case.
if str(label, "ascii").lower() != str(label2, "ascii"):
raise UnicodeError("IDNA does not round-trip", label, label2)
# Step 8: return the result of step 5
return result
### Codec APIs
class Codec(codecs.Codec):
def encode(self, input, errors='strict'):
if errors != 'strict':
# IDNA is quite clear that implementations must be strict
raise UnicodeError("unsupported error handling "+errors)
if not input:
return b'', 0
try:
result = input.encode('ascii')
except UnicodeEncodeError:
pass
else:
# ASCII name: fast path
labels = result.split(b'.')
for label in labels[:-1]:
if not (0 < len(label) < 64):
raise UnicodeError("label empty or too long")
if len(labels[-1]) >= 64:
raise UnicodeError("label too long")
return result, len(input)
result = bytearray()
labels = dots.split(input)
if labels and not labels[-1]:
trailing_dot = b'.'
del labels[-1]
else:
trailing_dot = b''
for label in labels:
if result:
# Join with U+002E
result.extend(b'.')
result.extend(ToASCII(label))
return bytes(result+trailing_dot), len(input)
def decode(self, input, errors='strict'):
if errors != 'strict':
raise UnicodeError("Unsupported error handling "+errors)
if not input:
return "", 0
# IDNA allows decoding to operate on Unicode strings, too.
if not isinstance(input, bytes):
# XXX obviously wrong, see #3232
input = bytes(input)
if ace_prefix not in input:
# Fast path
try:
return input.decode('ascii'), len(input)
except UnicodeDecodeError:
pass
labels = input.split(b".")
if labels and len(labels[-1]) == 0:
trailing_dot = '.'
del labels[-1]
else:
trailing_dot = ''
result = []
for label in labels:
result.append(ToUnicode(label))
return ".".join(result)+trailing_dot, len(input)
class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
def _buffer_encode(self, input, errors, final):
if errors != 'strict':
# IDNA is quite clear that implementations must be strict
raise UnicodeError("unsupported error handling "+errors)
if not input:
return (b'', 0)
labels = dots.split(input)
trailing_dot = b''
if labels:
if not labels[-1]:
trailing_dot = b'.'
del labels[-1]
elif not final:
# Keep potentially unfinished label until the next call
del labels[-1]
if labels:
trailing_dot = b'.'
result = bytearray()
size = 0
for label in labels:
if size:
# Join with U+002E
result.extend(b'.')
size += 1
result.extend(ToASCII(label))
size += len(label)
result += trailing_dot
size += len(trailing_dot)
return (bytes(result), size)
class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
def _buffer_decode(self, input, errors, final):
if errors != 'strict':
raise UnicodeError("Unsupported error handling "+errors)
if not input:
return ("", 0)
# IDNA allows decoding to operate on Unicode strings, too.
if isinstance(input, str):
labels = dots.split(input)
else:
# Must be ASCII string
input = str(input, "ascii")
labels = input.split(".")
trailing_dot = ''
if labels:
if not labels[-1]:
trailing_dot = '.'
del labels[-1]
elif not final:
# Keep potentially unfinished label until the next call
del labels[-1]
if labels:
trailing_dot = '.'
result = []
size = 0
for label in labels:
result.append(ToUnicode(label))
if size:
size += 1
size += len(label)
result = ".".join(result) + trailing_dot
size += len(trailing_dot)
return (result, size)
class StreamWriter(Codec,codecs.StreamWriter):
pass
class StreamReader(Codec,codecs.StreamReader):
pass
### encodings module API
def getregentry():
return codecs.CodecInfo(
name='idna',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamwriter=StreamWriter,
streamreader=StreamReader,
)
|
