FM / encodings

/usr/lib64/python3.12/encodings

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
aliases.py	15677	0644	edit dl rm
ascii.py	1248	0644	edit dl rm
base64_codec.py	1533	0644	edit dl rm
big5.py	1019	0644	edit dl rm
big5hkscs.py	1039	0644	edit dl rm
bz2_codec.py	2249	0644	edit dl rm
charmap.py	2084	0644	edit dl rm
cp037.pyc	3109	0644	edit dl rm
cp273.pyc	3095	0644	edit dl rm
cp424.pyc	3139	0644	edit dl rm
cp437.pyc	13286	0644	edit dl rm
cp500.pyc	3109	0644	edit dl rm
cp720.py	13686	0644	edit dl rm
cp737.pyc	13688	0644	edit dl rm
cp775.pyc	13326	0644	edit dl rm
cp850.pyc	12867	0644	edit dl rm
cp852.pyc	13342	0644	edit dl rm
cp855.pyc	13655	0644	edit dl rm
cp856.pyc	3171	0644	edit dl rm
cp857.pyc	12668	0644	edit dl rm
cp858.py	34015	0644	edit dl rm
cp860.pyc	13257	0644	edit dl rm
cp861.pyc	13282	0644	edit dl rm
cp862.pyc	13515	0644	edit dl rm
cp863.pyc	13278	0644	edit dl rm
cp864.pyc	13323	0644	edit dl rm
cp865.pyc	13282	0644	edit dl rm
cp866.pyc	13695	0644	edit dl rm
cp869.pyc	13225	0644	edit dl rm
cp874.pyc	3237	0644	edit dl rm
cp875.pyc	3106	0644	edit dl rm
cp932.py	1023	0644	edit dl rm
cp949.py	1023	0644	edit dl rm
cp950.py	1023	0644	edit dl rm
cp1006.pyc	3185	0644	edit dl rm
cp1026.pyc	3113	0644	edit dl rm
cp1125.py	34597	0644	edit dl rm
cp1140.pyc	3099	0644	edit dl rm
cp1250.pyc	3136	0644	edit dl rm
cp1251.pyc	3133	0644	edit dl rm
cp1252.pyc	3136	0644	edit dl rm
cp1253.pyc	3149	0644	edit dl rm
cp1254.pyc	3138	0644	edit dl rm
cp1255.pyc	3157	0644	edit dl rm
cp1256.pyc	3135	0644	edit dl rm
cp1257.pyc	3143	0644	edit dl rm
cp1258.pyc	3141	0644	edit dl rm
euc_jisx0213.py	1051	0644	edit dl rm
euc_jis_2004.py	1051	0644	edit dl rm
euc_jp.py	1027	0644	edit dl rm
euc_kr.py	1027	0644	edit dl rm
gb2312.py	1027	0644	edit dl rm
gb18030.py	1031	0644	edit dl rm
gbk.py	1015	0644	edit dl rm
hex_codec.py	1508	0644	edit dl rm
hp_roman8.pyc	3310	0644	edit dl rm
hz.py	1011	0644	edit dl rm
idna.py	9710	0644	edit dl rm
iso2022_jp.py	1053	0644	edit dl rm
iso2022_jp_1.py	1061	0644	edit dl rm
iso2022_jp_2.py	1061	0644	edit dl rm
iso2022_jp_3.py	1061	0644	edit dl rm
iso2022_jp_2004.py	1073	0644	edit dl rm
iso2022_jp_ext.py	1069	0644	edit dl rm
iso2022_kr.py	1053	0644	edit dl rm
iso8859_1.pyc	3108	0644	edit dl rm
iso8859_2.pyc	3108	0644	edit dl rm
iso8859_3.pyc	3115	0644	edit dl rm
iso8859_4.pyc	3108	0644	edit dl rm
iso8859_5.pyc	3109	0644	edit dl rm
iso8859_6.pyc	3153	0644	edit dl rm
iso8859_7.pyc	3116	0644	edit dl rm
iso8859_8.pyc	3147	0644	edit dl rm
iso8859_9.pyc	3108	0644	edit dl rm
iso8859_10.pyc	3113	0644	edit dl rm
iso8859_11.pyc	3207	0644	edit dl rm
iso8859_13.pyc	3116	0644	edit dl rm
iso8859_14.pyc	3134	0644	edit dl rm
iso8859_15.pyc	3113	0644	edit dl rm
iso8859_16.pyc	3115	0644	edit dl rm
johab.py	1023	0644	edit dl rm
koi8_r.pyc	3160	0644	edit dl rm
koi8_t.py	13193	0644	edit dl rm
koi8_u.pyc	3146	0644	edit dl rm
kz1048.pyc	3123	0644	edit dl rm
latin_1.py	1264	0644	edit dl rm
mac_arabic.pyc	13172	0644	edit dl rm
mac_croatian.pyc	3155	0644	edit dl rm
mac_cyrillic.pyc	3145	0644	edit dl rm
mac_farsi.pyc	3089	0644	edit dl rm
mac_greek.pyc	3129	0644	edit dl rm
mac_iceland.pyc	3148	0644	edit dl rm
mac_latin2.pyc	3289	0644	edit dl rm
mac_roman.pyc	3146	0644	edit dl rm
mac_romanian.pyc	3156	0644	edit dl rm
mac_turkish.pyc	3149	0644	edit dl rm
mbcs.py	1211	0644	edit dl rm
oem.py	1019	0644	edit dl rm
palmos.py	13519	0644	edit dl rm
ptcp154.pyc	3230	0644	edit dl rm
punycode.py	6883	0644	edit dl rm
quopri_codec.py	1525	0644	edit dl rm
raw_unicode_escape.py	1332	0644	edit dl rm
rot_13.py	2449	0755	edit dl rm
shift_jis.py	1039	0644	edit dl rm
shift_jisx0213.py	1059	0644	edit dl rm
shift_jis_2004.py	1059	0644	edit dl rm
tis_620.pyc	3198	0644	edit dl rm
undefined.py	1299	0644	edit dl rm
unicode_escape.py	1304	0644	edit dl rm
utf_7.py	946	0644	edit dl rm
utf_8.py	1005	0644	edit dl rm
utf_8_sig.py	4133	0644	edit dl rm
utf_16.py	5236	0644	edit dl rm
utf_16_be.py	1037	0644	edit dl rm
utf_16_le.py	1037	0644	edit dl rm
utf_32.py	5129	0644	edit dl rm
utf_32_be.py	930	0644	edit dl rm
utf_32_le.py	930	0644	edit dl rm
uu_codec.py	2851	0644	edit dl rm
zlib_codec.py	2204	0644	edit dl rm
__init__.py	5884	0644	edit dl rm

Edit: /usr/lib64/python3.12/encodings/idna.py (9710B)

# 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):
    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, 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,
    )

cmd: