/usr/lib/pypy/dist-packages/idna/codec.py is in pypy-idna 2.6-1.
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 | from .core import encode, decode, alabel, ulabel, IDNAError
import codecs
import re
_unicode_dots_re = re.compile(u'[\u002e\u3002\uff0e\uff61]')
class Codec(codecs.Codec):
def encode(self, data, errors='strict'):
if errors != 'strict':
raise IDNAError("Unsupported error handling \"{0}\"".format(errors))
if not data:
return "", 0
return encode(data), len(data)
def decode(self, data, errors='strict'):
if errors != 'strict':
raise IDNAError("Unsupported error handling \"{0}\"".format(errors))
if not data:
return u"", 0
return decode(data), len(data)
class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
def _buffer_encode(self, data, errors, final):
if errors != 'strict':
raise IDNAError("Unsupported error handling \"{0}\"".format(errors))
if not data:
return ("", 0)
labels = _unicode_dots_re.split(data)
trailing_dot = u''
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(alabel(label))
if size:
size += 1
size += len(label)
# Join with U+002E
result = ".".join(result) + trailing_dot
size += len(trailing_dot)
return (result, size)
class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
def _buffer_decode(self, data, errors, final):
if errors != 'strict':
raise IDNAError("Unsupported error handling \"{0}\"".format(errors))
if not data:
return (u"", 0)
# IDNA allows decoding to operate on Unicode strings, too.
if isinstance(data, unicode):
labels = _unicode_dots_re.split(data)
else:
# Must be ASCII string
data = str(data)
unicode(data, "ascii")
labels = data.split(".")
trailing_dot = u''
if labels:
if not labels[-1]:
trailing_dot = u'.'
del labels[-1]
elif not final:
# Keep potentially unfinished label until the next call
del labels[-1]
if labels:
trailing_dot = u'.'
result = []
size = 0
for label in labels:
result.append(ulabel(label))
if size:
size += 1
size += len(label)
result = u".".join(result) + trailing_dot
size += len(trailing_dot)
return (result, size)
class StreamWriter(Codec, codecs.StreamWriter):
pass
class StreamReader(Codec, codecs.StreamReader):
pass
def getregentry():
return codecs.CodecInfo(
name='idna',
encode=Codec().encode,
decode=Codec().decode,
incrementalencoder=IncrementalEncoder,
incrementaldecoder=IncrementalDecoder,
streamwriter=StreamWriter,
streamreader=StreamReader,
)
|