ꦫꦣꦺꦤ꧀ꦄꦤ꧀ꦠꦱꦺꦤ

PATH: usr / lib64 / python2.7 / encodings

# 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(u"[\u002E\u3002\uFF0E\uFF61]")

# IDNA section 5
ace_prefix = "xn--"
uace_prefix = unicode(ace_prefix, "ascii")

# 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 = u"".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 = map(stringprep.in_table_d1, 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 filter(stringprep.in_table_d2, 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(uace_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):
    if len(label) > 1024:
        # Protection from https://github.com/python/cpython/issues/98433.
        # https://datatracker.ietf.org/doc/html/rfc5894#section-6
        # doesn't specify a label size limit prior to NAMEPREP. But having
        # one makes practical sense.
        # This leaves ample room for nameprep() to remove Nothing characters
        # per https://www.rfc-editor.org/rfc/rfc3454#section-3.1 while still
        # preventing us from wasting time decoding a big thing that'll just
        # hit the actual <= 63 length limit in Step 6.
        raise UnicodeError("label way too long")
    # Step 1: Check for ASCII
    if isinstance(label, str):
        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 unicode(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 label.lower() != label2:
        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 "", 0

result = []
        labels = dots.split(input)
        if labels and len(labels[-1])==0:
            trailing_dot = '.'
            del labels[-1]
        else:
            trailing_dot = ''
        for label in labels:
            result.append(ToASCII(label))
        # Join with U+002E
        return ".".join(result)+trailing_dot, len(input)

def decode(self,input,errors='strict'):

if errors != 'strict':
            raise UnicodeError("Unsupported error handling "+errors)

if not input:
            return u"", 0

# IDNA allows decoding to operate on Unicode strings, too.
        if isinstance(input, unicode):
            labels = dots.split(input)
        else:
            # Must be ASCII string
            input = str(input)
            unicode(input, "ascii")
            labels = input.split(".")

if labels and len(labels[-1]) == 0:
            trailing_dot = u'.'
            del labels[-1]
        else:
            trailing_dot = u''

result = []
        for label in labels:
            result.append(ToUnicode(label))

return u".".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 ("", 0)

labels = dots.split(input)
        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(ToASCII(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, input, errors, final):
        if errors != 'strict':
            raise UnicodeError("Unsupported error handling "+errors)

if not input:
            return (u"", 0)

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(ToUnicode(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

### encodings module API

def getregentry():
    return codecs.CodecInfo(
        name='idna',
        encode=Codec().encode,
        decode=Codec().decode,
        incrementalencoder=IncrementalEncoder,
        incrementaldecoder=IncrementalDecoder,
        streamwriter=StreamWriter,
        streamreader=StreamReader,
    )

[+] ..
[-] iso8859_7.pyo [edit]
[-] palmos.py [edit]
[-] iso8859_3.py [edit]
[-] euc_jisx0213.pyc [edit]
[-] cp500.pyo [edit]
[-] cp775.pyc [edit]
[-] iso2022_jp_2.pyo [edit]
[-] latin_1.pyc [edit]
[-] gbk.pyo [edit]
[-] iso2022_jp_3.pyc [edit]
[-] cp437.pyo [edit]
[-] euc_jis_2004.py [edit]
[-] iso8859_15.py [edit]
[-] cp1256.py [edit]
[-] mac_croatian.py [edit]
[-] cp949.pyo [edit]
[-] cp1140.pyc [edit]
[-] raw_unicode_escape.py [edit]
[-] unicode_escape.py [edit]
[-] iso8859_8.pyo [edit]
[-] cp1250.pyo [edit]
[-] iso2022_jp_1.pyc [edit]
[-] utf_16.pyc [edit]
[-] gbk.pyc [edit]
[-] cp500.pyc [edit]
[-] johab.pyo [edit]
[-] utf_32_be.py [edit]
[-] mac_roman.py [edit]
[-] iso8859_14.py [edit]
[-] mac_greek.pyc [edit]
[-] __init__.pyo [edit]
[-] cp862.py [edit]
[-] charmap.py [edit]
[-] tis_620.pyo [edit]
[-] euc_kr.pyo [edit]
[-] iso2022_jp_2004.py [edit]
[-] iso8859_5.py [edit]
[-] cp1251.py [edit]
[-] iso8859_10.py [edit]
[-] koi8_u.py [edit]
[-] cp865.pyo [edit]
[-] hz.py [edit]
[-] cp037.py [edit]
[-] euc_jisx0213.py [edit]
[-] utf_32_le.py [edit]
[-] cp1026.py [edit]
[-] cp1256.pyc [edit]
[-] punycode.pyo [edit]
[-] iso8859_1.pyc [edit]
[-] cp949.pyc [edit]
[-] iso2022_jp_ext.py [edit]
[-] utf_32_le.pyo [edit]
[-] big5hkscs.pyo [edit]
[-] iso8859_11.py [edit]
[-] latin_1.py [edit]
[-] hp_roman8.pyo [edit]
[-] hex_codec.pyo [edit]
[-] iso8859_1.pyo [edit]
[-] utf_32.py [edit]
[-] mac_latin2.pyc [edit]
[-] iso8859_8.pyc [edit]
[-] ascii.pyo [edit]
[-] cp720.pyo [edit]
[-] cp1006.pyo [edit]
[-] cp852.pyo [edit]
[-] quopri_codec.py [edit]
[-] iso2022_kr.pyc [edit]
[-] bz2_codec.pyc [edit]
[-] cp437.pyc [edit]
[-] iso8859_3.pyc [edit]
[-] hz.pyo [edit]
[-] raw_unicode_escape.pyo [edit]
[-] tis_620.py [edit]
[-] utf_16_be.pyc [edit]
[-] cp850.pyc [edit]
[-] cp950.pyc [edit]
[-] iso8859_11.pyo [edit]
[-] cp1257.pyc [edit]
[-] iso8859_2.pyo [edit]
[-] cp874.pyo [edit]
[-] euc_jis_2004.pyc [edit]
[-] shift_jis.pyc [edit]
[-] unicode_escape.pyo [edit]
[-] rot_13.py [edit]
[-] cp874.py [edit]
[-] cp874.pyc [edit]
[-] utf_16_le.pyc [edit]
[-] cp1257.pyo [edit]
[-] shift_jis.py [edit]
[-] cp864.pyc [edit]
[-] iso8859_2.py [edit]
[-] gb18030.py [edit]
[-] cp864.py [edit]
[-] cp875.py [edit]
[-] cp932.pyc [edit]
[-] koi8_r.pyc [edit]
[-] punycode.pyc [edit]
[-] cp1254.py [edit]
[-] string_escape.pyo [edit]
[-] undefined.py [edit]
[-] cp1251.pyc [edit]
[-] iso2022_jp.pyo [edit]
[-] koi8_r.pyo [edit]
[-] cp037.pyc [edit]
[-] iso8859_6.py [edit]
[-] cp1006.py [edit]
[-] gb18030.pyo [edit]
[-] cp860.py [edit]
[-] mac_latin2.pyo [edit]
[-] cp862.pyo [edit]
[-] mac_farsi.py [edit]
[-] iso8859_15.pyo [edit]
[-] iso8859_9.pyc [edit]
[-] hex_codec.py [edit]
[-] mac_cyrillic.pyc [edit]
[-] mac_cyrillic.py [edit]
[-] cp1257.py [edit]
[-] quopri_codec.pyc [edit]
[-] ptcp154.py [edit]
[-] cp949.py [edit]
[-] iso8859_2.pyc [edit]
[-] cp424.pyc [edit]
[-] cp775.pyo [edit]
[-] cp861.py [edit]
[-] mac_arabic.py [edit]
[-] zlib_codec.py [edit]
[-] iso2022_jp_1.pyo [edit]
[-] bz2_codec.pyo [edit]
[-] __init__.pyc [edit]
[-] ascii.pyc [edit]
[-] big5.pyo [edit]
[-] iso8859_8.py [edit]
[-] gb2312.py [edit]
[-] palmos.pyo [edit]
[-] cp875.pyo [edit]
[-] mac_arabic.pyo [edit]
[-] cp1252.pyo [edit]
[-] mac_centeuro.pyc [edit]
[-] cp1251.pyo [edit]
[-] cp850.pyo [edit]
[-] cp1253.pyo [edit]
[-] cp424.pyo [edit]
[-] utf_8_sig.py [edit]
[-] iso8859_4.pyc [edit]
[-] unicode_internal.pyo [edit]
[-] cp1026.pyo [edit]
[-] cp863.pyo [edit]
[-] gbk.py [edit]
[-] mac_centeuro.py [edit]
[-] utf_7.pyo [edit]
[-] shift_jis_2004.pyo [edit]
[-] zlib_codec.pyc [edit]
[-] euc_jis_2004.pyo [edit]
[-] cp037.pyo [edit]
[-] big5hkscs.py [edit]
[-] mac_croatian.pyc [edit]
[-] mac_iceland.py [edit]
[-] base64_codec.py [edit]
[-] iso8859_5.pyc [edit]
[-] aliases.py [edit]
[-] undefined.pyc [edit]
[-] mac_roman.pyo [edit]
[-] iso8859_7.py [edit]
[-] utf_16_be.pyo [edit]
[-] iso8859_15.pyc [edit]
[-] big5hkscs.pyc [edit]
[-] latin_1.pyo [edit]
[-] tis_620.pyc [edit]
[-] cp424.py [edit]
[-] mac_turkish.pyc [edit]
[-] iso2022_jp_3.pyo [edit]
[-] utf_16_le.py [edit]
[-] cp437.py [edit]
[-] iso8859_16.py [edit]
[-] hz.pyc [edit]
[-] cp869.pyc [edit]
[-] gb2312.pyo [edit]
[-] cp866.py [edit]
[-] cp852.pyc [edit]
[-] iso8859_6.pyo [edit]
[-] euc_kr.py [edit]
[-] uu_codec.pyc [edit]
[-] unicode_internal.pyc [edit]
[-] cp500.py [edit]
[-] iso2022_jp_3.py [edit]
[-] mac_centeuro.pyo [edit]
[-] iso2022_kr.pyo [edit]
[-] koi8_u.pyc [edit]
[-] cp1250.py [edit]
[-] cp869.py [edit]
[-] shift_jisx0213.py [edit]
[-] idna.pyc [edit]
[-] charmap.pyc [edit]
[-] utf_8.py [edit]
[-] iso8859_10.pyo [edit]
[-] cp737.py [edit]
[-] gb18030.pyc [edit]
[-] cp855.pyo [edit]
[-] base64_codec.pyo [edit]
[-] cp850.py [edit]
[-] cp1255.pyo [edit]
[-] iso2022_jp_1.py [edit]
[-] utf_16_le.pyo [edit]
[-] cp1254.pyo [edit]
[-] euc_jp.pyo [edit]
[-] string_escape.pyc [edit]
[-] iso8859_11.pyc [edit]
[-] cp1255.py [edit]
[-] euc_kr.pyc [edit]
[-] cp1026.pyc [edit]
[-] utf_32_be.pyo [edit]
[-] cp875.pyc [edit]
[-] cp720.pyc [edit]
[-] undefined.pyo [edit]
[-] euc_jisx0213.pyo [edit]
[-] cp863.py [edit]
[-] cp858.py [edit]
[-] utf_8_sig.pyc [edit]
[-] koi8_r.py [edit]
[-] iso8859_4.pyo [edit]
[-] iso8859_13.pyc [edit]
[-] mac_greek.py [edit]
[-] cp1254.pyc [edit]
[-] cp950.pyo [edit]
[-] cp1253.py [edit]
[-] cp1253.pyc [edit]
[-] cp866.pyo [edit]
[-] cp856.pyo [edit]
[-] rot_13.pyc [edit]
[-] shift_jisx0213.pyo [edit]
[-] mac_iceland.pyc [edit]
[-] cp861.pyo [edit]
[-] euc_jp.py [edit]
[-] punycode.py [edit]
[-] iso8859_3.pyo [edit]
[-] big5.pyc [edit]
[-] ptcp154.pyo [edit]
[-] mac_farsi.pyc [edit]
[-] base64_codec.pyc [edit]
[-] utf_8.pyc [edit]
[-] ascii.py [edit]
[-] cp932.py [edit]
[-] shift_jis_2004.py [edit]
[-] mac_iceland.pyo [edit]
[-] johab.pyc [edit]
[-] iso8859_9.pyo [edit]
[-] bz2_codec.py [edit]
[-] utf_7.py [edit]
[-] cp861.pyc [edit]
[-] cp855.py [edit]
[-] unicode_internal.py [edit]
[-] cp863.pyc [edit]
[-] cp862.pyc [edit]
[-] cp855.pyc [edit]
[-] utf_32.pyo [edit]
[-] iso8859_6.pyc [edit]
[-] koi8_u.pyo [edit]
[-] uu_codec.py [edit]
[-] utf_16.py [edit]
[-] hp_roman8.pyc [edit]
[-] idna.pyo [edit]
[-] mac_croatian.pyo [edit]
[-] mac_farsi.pyo [edit]
[-] iso2022_jp_2004.pyc [edit]
[-] shift_jis_2004.pyc [edit]
[-] raw_unicode_escape.pyc [edit]
[-] iso8859_14.pyo [edit]
[-] utf_32.pyc [edit]
[-] mac_romanian.pyc [edit]
[-] string_escape.py [edit]
[-] iso8859_5.pyo [edit]
[-] cp865.pyc [edit]
[-] rot_13.pyo [edit]
[-] utf_32_le.pyc [edit]
[-] iso8859_16.pyc [edit]
[-] cp1258.py [edit]
[-] mac_arabic.pyc [edit]
[-] mbcs.pyo [edit]
[-] cp950.py [edit]
[-] cp857.py [edit]
[-] cp1140.py [edit]
[-] cp860.pyo [edit]
[-] cp852.py [edit]
[-] cp1256.pyo [edit]
[-] iso8859_10.pyc [edit]
[-] charmap.pyo [edit]
[-] hp_roman8.py [edit]
[-] mac_roman.pyc [edit]
[-] gb2312.pyc [edit]
[-] iso8859_13.pyo [edit]
[-] cp1006.pyc [edit]
[-] cp864.pyo [edit]
[-] aliases.pyo [edit]
[-] iso8859_9.py [edit]
[-] idna.py [edit]
[-] __init__.py [edit]
[-] cp1255.pyc [edit]
[-] mac_turkish.py [edit]
[-] shift_jis.pyo [edit]
[-] palmos.pyc [edit]
[-] shift_jisx0213.pyc [edit]
[-] utf_16_be.py [edit]
[-] cp856.py [edit]
[-] ptcp154.pyc [edit]
[-] mac_turkish.pyo [edit]
[-] cp857.pyo [edit]
[-] mac_greek.pyo [edit]
[-] cp720.py [edit]
[-] iso8859_4.py [edit]
[-] quopri_codec.pyo [edit]
[-] mac_cyrillic.pyo [edit]
[-] cp1258.pyc [edit]
[-] euc_jp.pyc [edit]
[-] iso2022_jp_ext.pyo [edit]
[-] iso8859_13.py [edit]
[-] mbcs.pyc [edit]
[-] hex_codec.pyc [edit]
[-] cp858.pyo [edit]
[-] unicode_escape.pyc [edit]
[-] aliases.pyc [edit]
[-] iso2022_jp_ext.pyc [edit]
[-] mbcs.py [edit]
[-] iso2022_jp_2004.pyo [edit]
[-] johab.py [edit]
[-] cp775.py [edit]
[-] iso2022_kr.py [edit]
[-] iso8859_14.pyc [edit]
[-] cp856.pyc [edit]
[-] utf_8_sig.pyo [edit]
[-] cp1250.pyc [edit]
[-] uu_codec.pyo [edit]
[-] mac_romanian.pyo [edit]
[-] cp737.pyo [edit]
[-] iso8859_7.pyc [edit]
[-] big5.py [edit]
[-] iso8859_16.pyo [edit]
[-] iso2022_jp.py [edit]
[-] utf_32_be.pyc [edit]
[-] iso2022_jp.pyc [edit]
[-] cp1140.pyo [edit]
[-] utf_16.pyo [edit]
[-] utf_8.pyo [edit]
[-] cp932.pyo [edit]
[-] iso8859_1.py [edit]
[-] iso2022_jp_2.py [edit]
[-] cp857.pyc [edit]
[-] mac_romanian.py [edit]
[-] zlib_codec.pyo [edit]
[-] cp1252.py [edit]
[-] iso2022_jp_2.pyc [edit]
[-] cp737.pyc [edit]
[-] cp858.pyc [edit]
[-] cp865.py [edit]
[-] utf_7.pyc [edit]
[-] cp1252.pyc [edit]
[-] cp866.pyc [edit]
[-] cp1258.pyo [edit]
[-] mac_latin2.py [edit]
[-] cp869.pyo [edit]
[-] cp860.pyc [edit]