/usr/lib/python3/dist-packages/requests/packages/idna/core.py is in python3-requests 2.12.4-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 | from . import idnadata
import bisect
import unicodedata
import re
import sys
from .intranges import intranges_contain
_virama_combining_class = 9
_alabel_prefix = b'xn--'
_unicode_dots_re = re.compile(u'[\u002e\u3002\uff0e\uff61]')
if sys.version_info[0] == 3:
unicode = str
unichr = chr
class IDNAError(UnicodeError):
""" Base exception for all IDNA-encoding related problems """
pass
class IDNABidiError(IDNAError):
""" Exception when bidirectional requirements are not satisfied """
pass
class InvalidCodepoint(IDNAError):
""" Exception when a disallowed or unallocated codepoint is used """
pass
class InvalidCodepointContext(IDNAError):
""" Exception when the codepoint is not valid in the context it is used """
pass
def _combining_class(cp):
return unicodedata.combining(unichr(cp))
def _is_script(cp, script):
return intranges_contain(ord(cp), idnadata.scripts[script])
def _punycode(s):
return s.encode('punycode')
def _unot(s):
return 'U+{0:04X}'.format(s)
def valid_label_length(label):
if len(label) > 63:
return False
return True
def valid_string_length(label, trailing_dot):
if len(label) > (254 if trailing_dot else 253):
return False
return True
def check_bidi(label, check_ltr=False):
# Bidi rules should only be applied if string contains RTL characters
bidi_label = False
for (idx, cp) in enumerate(label, 1):
direction = unicodedata.bidirectional(cp)
if direction == '':
# String likely comes from a newer version of Unicode
raise IDNABidiError('Unknown directionality in label {0} at position {1}'.format(repr(label), idx))
if direction in ['R', 'AL', 'AN']:
bidi_label = True
break
if not bidi_label and not check_ltr:
return True
# Bidi rule 1
direction = unicodedata.bidirectional(label[0])
if direction in ['R', 'AL']:
rtl = True
elif direction == 'L':
rtl = False
else:
raise IDNABidiError('First codepoint in label {0} must be directionality L, R or AL'.format(repr(label)))
valid_ending = False
number_type = False
for (idx, cp) in enumerate(label, 1):
direction = unicodedata.bidirectional(cp)
if rtl:
# Bidi rule 2
if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
raise IDNABidiError('Invalid direction for codepoint at position {0} in a right-to-left label'.format(idx))
# Bidi rule 3
if direction in ['R', 'AL', 'EN', 'AN']:
valid_ending = True
elif direction != 'NSM':
valid_ending = False
# Bidi rule 4
if direction in ['AN', 'EN']:
if not number_type:
number_type = direction
else:
if number_type != direction:
raise IDNABidiError('Can not mix numeral types in a right-to-left label')
else:
# Bidi rule 5
if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
raise IDNABidiError('Invalid direction for codepoint at position {0} in a left-to-right label'.format(idx))
# Bidi rule 6
if direction in ['L', 'EN']:
valid_ending = True
elif direction != 'NSM':
valid_ending = False
if not valid_ending:
raise IDNABidiError('Label ends with illegal codepoint directionality')
return True
def check_initial_combiner(label):
if unicodedata.category(label[0])[0] == 'M':
raise IDNAError('Label begins with an illegal combining character')
return True
def check_hyphen_ok(label):
if label[2:4] == '--':
raise IDNAError('Label has disallowed hyphens in 3rd and 4th position')
if label[0] == '-' or label[-1] == '-':
raise IDNAError('Label must not start or end with a hyphen')
return True
def check_nfc(label):
if unicodedata.normalize('NFC', label) != label:
raise IDNAError('Label must be in Normalization Form C')
def valid_contextj(label, pos):
cp_value = ord(label[pos])
if cp_value == 0x200c:
if pos > 0:
if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
return True
ok = False
for i in range(pos-1, -1, -1):
joining_type = idnadata.joining_types.get(ord(label[i]))
if joining_type == 'T':
continue
if joining_type in ['L', 'D']:
ok = True
break
if not ok:
return False
ok = False
for i in range(pos+1, len(label)):
joining_type = idnadata.joining_types.get(ord(label[i]))
if joining_type == 'T':
continue
if joining_type in ['R', 'D']:
ok = True
break
return ok
if cp_value == 0x200d:
if pos > 0:
if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
return True
return False
else:
return False
def valid_contexto(label, pos, exception=False):
cp_value = ord(label[pos])
if cp_value == 0x00b7:
if 0 < pos < len(label)-1:
if ord(label[pos - 1]) == 0x006c and ord(label[pos + 1]) == 0x006c:
return True
return False
elif cp_value == 0x0375:
if pos < len(label)-1 and len(label) > 1:
return _is_script(label[pos + 1], 'Greek')
return False
elif cp_value == 0x05f3 or cp_value == 0x05f4:
if pos > 0:
return _is_script(label[pos - 1], 'Hebrew')
return False
elif cp_value == 0x30fb:
for cp in label:
if cp == u'\u30fb':
continue
if not _is_script(cp, 'Hiragana') and not _is_script(cp, 'Katakana') and not _is_script(cp, 'Han'):
return False
return True
elif 0x660 <= cp_value <= 0x669:
for cp in label:
if 0x6f0 <= ord(cp) <= 0x06f9:
return False
return True
elif 0x6f0 <= cp_value <= 0x6f9:
for cp in label:
if 0x660 <= ord(cp) <= 0x0669:
return False
return True
def check_label(label):
if isinstance(label, (bytes, bytearray)):
label = label.decode('utf-8')
if len(label) == 0:
raise IDNAError('Empty Label')
check_nfc(label)
check_hyphen_ok(label)
check_initial_combiner(label)
for (pos, cp) in enumerate(label):
cp_value = ord(cp)
if intranges_contain(cp_value, idnadata.codepoint_classes['PVALID']):
continue
elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTJ']):
if not valid_contextj(label, pos):
raise InvalidCodepointContext('Joiner {0} not allowed at position {1} in {2}'.format(_unot(cp_value), pos+1, repr(label)))
elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTO']):
if not valid_contexto(label, pos):
raise InvalidCodepointContext('Codepoint {0} not allowed at position {1} in {2}'.format(_unot(cp_value), pos+1, repr(label)))
else:
raise InvalidCodepoint('Codepoint {0} at position {1} of {2} not allowed'.format(_unot(cp_value), pos+1, repr(label)))
check_bidi(label)
def alabel(label):
try:
label = label.encode('ascii')
try:
ulabel(label)
except:
raise IDNAError('The label {0} is not a valid A-label'.format(label))
if not valid_label_length(label):
raise IDNAError('Label too long')
return label
except UnicodeError:
pass
if not label:
raise IDNAError('No Input')
label = unicode(label)
check_label(label)
label = _punycode(label)
label = _alabel_prefix + label
if not valid_label_length(label):
raise IDNAError('Label too long')
return label
def ulabel(label):
if not isinstance(label, (bytes, bytearray)):
try:
label = label.encode('ascii')
except UnicodeError:
check_label(label)
return label
label = label.lower()
if label.startswith(_alabel_prefix):
label = label[len(_alabel_prefix):]
else:
check_label(label)
return label.decode('ascii')
label = label.decode('punycode')
check_label(label)
return label
def uts46_remap(domain, std3_rules=True, transitional=False):
"""Re-map the characters in the string according to UTS46 processing."""
from .uts46data import uts46data
output = u""
try:
for pos, char in enumerate(domain):
code_point = ord(char)
uts46row = uts46data[code_point if code_point < 256 else
bisect.bisect_left(uts46data, (code_point, "Z")) - 1]
status = uts46row[1]
replacement = uts46row[2] if len(uts46row) == 3 else None
if (status == "V" or
(status == "D" and not transitional) or
(status == "3" and std3_rules and replacement is None)):
output += char
elif replacement is not None and (status == "M" or
(status == "3" and std3_rules) or
(status == "D" and transitional)):
output += replacement
elif status != "I":
raise IndexError()
return unicodedata.normalize("NFC", output)
except IndexError:
raise InvalidCodepoint(
"Codepoint {0} not allowed at position {1} in {2}".format(
_unot(code_point), pos + 1, repr(domain)))
def encode(s, strict=False, uts46=False, std3_rules=False, transitional=False):
if isinstance(s, (bytes, bytearray)):
s = s.decode("ascii")
if uts46:
s = uts46_remap(s, std3_rules, transitional)
trailing_dot = False
result = []
if strict:
labels = s.split('.')
else:
labels = _unicode_dots_re.split(s)
while labels and not labels[0]:
del labels[0]
if not labels:
raise IDNAError('Empty domain')
if labels[-1] == '':
del labels[-1]
trailing_dot = True
for label in labels:
result.append(alabel(label))
if trailing_dot:
result.append(b'')
s = b'.'.join(result)
if not valid_string_length(s, trailing_dot):
raise IDNAError('Domain too long')
return s
def decode(s, strict=False, uts46=False, std3_rules=False):
if isinstance(s, (bytes, bytearray)):
s = s.decode("ascii")
if uts46:
s = uts46_remap(s, std3_rules, False)
trailing_dot = False
result = []
if not strict:
labels = _unicode_dots_re.split(s)
else:
labels = s.split(u'.')
while labels and not labels[0]:
del labels[0]
if not labels:
raise IDNAError('Empty domain')
if not labels[-1]:
del labels[-1]
trailing_dot = True
for label in labels:
result.append(ulabel(label))
if trailing_dot:
result.append(u'')
return u'.'.join(result)
|