PNG  IHDRxsBIT|d pHYs+tEXtSoftwarewww.inkscape.org<,tEXtComment File Manager

File Manager

Path: /opt/cloudlinux/venv/lib/python3.11/site-packages/pip/_vendor/idna/

Viewing File: core.py

import bisect
import re
import unicodedata
from typing import Optional, Union

from . import idnadata
from .intranges import intranges_contain

_virama_combining_class = 9
_alabel_prefix = b"xn--"
_unicode_dots_re = re.compile("[\u002e\u3002\uff0e\uff61]")


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: int) -> int:
    v = unicodedata.combining(chr(cp))
    if v == 0:
        if not unicodedata.name(chr(cp)):
            raise ValueError("Unknown character in unicodedata")
    return v


def _is_script(cp: str, script: str) -> bool:
    return intranges_contain(ord(cp), idnadata.scripts[script])


def _punycode(s: str) -> bytes:
    return s.encode("punycode")


def _unot(s: int) -> str:
    return "U+{:04X}".format(s)


def valid_label_length(label: Union[bytes, str]) -> bool:
    if len(label) > 63:
        return False
    return True


def valid_string_length(label: Union[bytes, str], trailing_dot: bool) -> bool:
    if len(label) > (254 if trailing_dot else 253):
        return False
    return True


def check_bidi(label: str, check_ltr: bool = False) -> bool:
    # 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 {} at position {}".format(repr(label), idx))
        if direction in ["R", "AL", "AN"]:
            bidi_label = True
    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 {} must be directionality L, R or AL".format(repr(label)))

    valid_ending = False
    number_type: Optional[str] = None
    for idx, cp in enumerate(label, 1):
        direction = unicodedata.bidirectional(cp)

        if rtl:
            # Bidi rule 2
            if direction not in [
                "R",
                "AL",
                "AN",
                "EN",
                "ES",
                "CS",
                "ET",
                "ON",
                "BN",
                "NSM",
            ]:
                raise IDNABidiError("Invalid direction for codepoint at position {} 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 direction not in ["L", "EN", "ES", "CS", "ET", "ON", "BN", "NSM"]:
                raise IDNABidiError("Invalid direction for codepoint at position {} 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: str) -> bool:
    if unicodedata.category(label[0])[0] == "M":
        raise IDNAError("Label begins with an illegal combining character")
    return True


def check_hyphen_ok(label: str) -> bool:
    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: str) -> None:
    if unicodedata.normalize("NFC", label) != label:
        raise IDNAError("Label must be in Normalization Form C")


def valid_contextj(label: str, pos: int) -> bool:
    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 == ord("T"):
                continue
            elif joining_type in [ord("L"), ord("D")]:
                ok = True
                break
            else:
                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 == ord("T"):
                continue
            elif joining_type in [ord("R"), ord("D")]:
                ok = True
                break
            else:
                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: str, pos: int, exception: bool = False) -> bool:
    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 == "\u30fb":
                continue
            if _is_script(cp, "Hiragana") or _is_script(cp, "Katakana") or _is_script(cp, "Han"):
                return True
        return False

    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

    return False


def check_label(label: Union[str, bytes, bytearray]) -> None:
    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"]):
            try:
                if not valid_contextj(label, pos):
                    raise InvalidCodepointContext(
                        "Joiner {} not allowed at position {} in {}".format(_unot(cp_value), pos + 1, repr(label))
                    )
            except ValueError:
                raise IDNAError(
                    "Unknown codepoint adjacent to joiner {} at position {} in {}".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 {} not allowed at position {} in {}".format(_unot(cp_value), pos + 1, repr(label))
                )
        else:
            raise InvalidCodepoint(
                "Codepoint {} at position {} of {} not allowed".format(_unot(cp_value), pos + 1, repr(label))
            )

    check_bidi(label)


def alabel(label: str) -> bytes:
    try:
        label_bytes = label.encode("ascii")
        ulabel(label_bytes)
        if not valid_label_length(label_bytes):
            raise IDNAError("Label too long")
        return label_bytes
    except UnicodeEncodeError:
        pass

    check_label(label)
    label_bytes = _alabel_prefix + _punycode(label)

    if not valid_label_length(label_bytes):
        raise IDNAError("Label too long")

    return label_bytes


def ulabel(label: Union[str, bytes, bytearray]) -> str:
    if not isinstance(label, (bytes, bytearray)):
        try:
            label_bytes = label.encode("ascii")
        except UnicodeEncodeError:
            check_label(label)
            return label
    else:
        label_bytes = label

    label_bytes = label_bytes.lower()
    if label_bytes.startswith(_alabel_prefix):
        label_bytes = label_bytes[len(_alabel_prefix) :]
        if not label_bytes:
            raise IDNAError("Malformed A-label, no Punycode eligible content found")
        if label_bytes.decode("ascii")[-1] == "-":
            raise IDNAError("A-label must not end with a hyphen")
    else:
        check_label(label_bytes)
        return label_bytes.decode("ascii")

    try:
        label = label_bytes.decode("punycode")
    except UnicodeError:
        raise IDNAError("Invalid A-label")
    check_label(label)
    return label


def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False) -> str:
    """Re-map the characters in the string according to UTS46 processing."""
    from .uts46data import uts46data

    output = ""

    for pos, char in enumerate(domain):
        code_point = ord(char)
        try:
            uts46row = uts46data[code_point if code_point < 256 else bisect.bisect_left(uts46data, (code_point, "Z")) - 1]
            status = uts46row[1]
            replacement: Optional[str] = None
            if len(uts46row) == 3:
                replacement = uts46row[2]
            if (
                status == "V"
                or (status == "D" and not transitional)
                or (status == "3" and not std3_rules and replacement is None)
            ):
                output += char
            elif replacement is not None and (
                status == "M" or (status == "3" and not std3_rules) or (status == "D" and transitional)
            ):
                output += replacement
            elif status != "I":
                raise IndexError()
        except IndexError:
            raise InvalidCodepoint(
                "Codepoint {} not allowed at position {} in {}".format(_unot(code_point), pos + 1, repr(domain))
            )

    return unicodedata.normalize("NFC", output)


def encode(
    s: Union[str, bytes, bytearray],
    strict: bool = False,
    uts46: bool = False,
    std3_rules: bool = False,
    transitional: bool = False,
) -> bytes:
    if not isinstance(s, str):
        try:
            s = str(s, "ascii")
        except UnicodeDecodeError:
            raise IDNAError("should pass a unicode string to the function rather than a byte string.")
    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)
    if not labels or labels == [""]:
        raise IDNAError("Empty domain")
    if labels[-1] == "":
        del labels[-1]
        trailing_dot = True
    for label in labels:
        s = alabel(label)
        if s:
            result.append(s)
        else:
            raise IDNAError("Empty 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: Union[str, bytes, bytearray],
    strict: bool = False,
    uts46: bool = False,
    std3_rules: bool = False,
) -> str:
    try:
        if not isinstance(s, str):
            s = str(s, "ascii")
    except UnicodeDecodeError:
        raise IDNAError("Invalid ASCII in A-label")
    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(".")
    if not labels or labels == [""]:
        raise IDNAError("Empty domain")
    if not labels[-1]:
        del labels[-1]
        trailing_dot = True
    for label in labels:
        s = ulabel(label)
        if s:
            result.append(s)
        else:
            raise IDNAError("Empty label")
    if trailing_dot:
        result.append("")
    return ".".join(result)
b IDATxytVսϓ22 A@IR :hCiZ[v*E:WũZA ^dQeQ @ !jZ'>gsV仿$|?g)&x-EIENT ;@xT.i%-X}SvS5.r/UHz^_$-W"w)Ɗ/@Z &IoX P$K}JzX:;` &, ŋui,e6mX ԵrKb1ԗ)DADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADA݀!I*]R;I2$eZ#ORZSrr6mteffu*((Pu'v{DIߔ4^pIm'77WEEE;vƎ4-$]'RI{\I&G :IHJ DWBB=\WR޽m o$K(V9ABB.}jѢv`^?IOȅ} ڶmG}T#FJ`56$-ھ}FI&v;0(h;Б38CӧOWf!;A i:F_m9s&|q%=#wZprrrla A &P\\СC[A#! {olF} `E2}MK/vV)i{4BffV\|ۭX`b@kɶ@%i$K z5zhmX[IXZ` 'b%$r5M4º/l ԃߖxhʔ)[@=} K6IM}^5k㏷݆z ΗÿO:gdGBmyT/@+Vɶ纽z񕏵l.y޴it뭷zV0[Y^>Wsqs}\/@$(T7f.InݺiR$푔n.~?H))\ZRW'Mo~v Ov6oԃxz! S,&xm/yɞԟ?'uaSѽb,8GלKboi&3t7Y,)JJ c[nzӳdE&KsZLӄ I?@&%ӟ۶mSMMњ0iؐSZ,|J+N ~,0A0!5%Q-YQQa3}$_vVrf9f?S8`zDADADADADADADADADAdqP,تmMmg1V?rSI꒟]u|l RCyEf٢9 jURbztѰ!m5~tGj2DhG*{H9)꒟ר3:(+3\?/;TUݭʴ~S6lڧUJ*i$d(#=Yݺd{,p|3B))q:vN0Y.jkק6;SɶVzHJJЀ-utѹսk>QUU\޲~]fFnK?&ߡ5b=z9)^|u_k-[y%ZNU6 7Mi:]ۦtk[n X(e6Bb."8cۭ|~teuuw|ήI-5"~Uk;ZicEmN/:]M> cQ^uiƞ??Ңpc#TUU3UakNwA`:Y_V-8.KKfRitv޲* 9S6ֿj,ՃNOMߤ]z^fOh|<>@Å5 _/Iu?{SY4hK/2]4%it5q]GGe2%iR| W&f*^]??vq[LgE_3f}Fxu~}qd-ږFxu~I N>\;͗O֊:̗WJ@BhW=y|GgwܷH_NY?)Tdi'?խwhlmQi !SUUsw4kӺe4rfxu-[nHtMFj}H_u~w>)oV}(T'ebʒv3_[+vn@Ȭ\S}ot}w=kHFnxg S 0eޢm~l}uqZfFoZuuEg `zt~? b;t%>WTkķh[2eG8LIWx,^\thrl^Ϊ{=dž<}qV@ ⠨Wy^LF_>0UkDuʫuCs$)Iv:IK;6ֲ4{^6եm+l3>݆uM 9u?>Zc }g~qhKwڭeFMM~pМuqǿz6Tb@8@Y|jx](^]gf}M"tG -w.@vOqh~/HII`S[l.6nØXL9vUcOoB\xoǤ'T&IǍQw_wpv[kmO{w~>#=P1Pɞa-we:iǏlHo׈꒟f9SzH?+shk%Fs:qVhqY`jvO'ρ?PyX3lх]˾uV{ݞ]1,MzYNW~̈́ joYn}ȚF߾׮mS]F z+EDxm/d{F{-W-4wY듏:??_gPf ^3ecg ҵs8R2מz@TANGj)}CNi/R~}c:5{!ZHӋӾ6}T]G]7W6^n 9*,YqOZj:P?Q DFL|?-^.Ɵ7}fFh׶xe2Pscz1&5\cn[=Vn[ĶE鎀uˌd3GII k;lNmشOuuRVfBE]ۣeӶu :X-[(er4~LHi6:Ѻ@ԅrST0trk%$Č0ez" *z"T/X9|8.C5Feg}CQ%͞ˣJvL/?j^h&9xF`њZ(&yF&Iݻfg#W;3^{Wo^4'vV[[K';+mӍִ]AC@W?1^{එyh +^]fm~iԵ]AB@WTk̏t uR?l.OIHiYyԶ]Aˀ7c:q}ힽaf6Z~қm(+sK4{^6}T*UUu]n.:kx{:2 _m=sAߤU@?Z-Vކеz왍Nэ{|5 pڶn b p-@sPg]0G7fy-M{GCF'%{4`=$-Ge\ eU:m+Zt'WjO!OAF@ik&t݆ϥ_ e}=]"Wz_.͜E3leWFih|t-wZۍ-uw=6YN{6|} |*={Ѽn.S.z1zjۻTH]흾 DuDvmvK.`V]yY~sI@t?/ϓ. m&["+P?MzovVЫG3-GRR[(!!\_,^%?v@ҵő m`Y)tem8GMx.))A]Y i`ViW`?^~!S#^+ѽGZj?Vģ0.))A꨷lzL*]OXrY`DBBLOj{-MH'ii-ϰ ok7^ )쭡b]UXSְmռY|5*cֽk0B7镹%ڽP#8nȎq}mJr23_>lE5$iwui+ H~F`IjƵ@q \ @#qG0".0" l`„.0! ,AQHN6qzkKJ#o;`Xv2>,tێJJ7Z/*A .@fفjMzkg @TvZH3Zxu6Ra'%O?/dQ5xYkU]Rֽkق@DaS^RSּ5|BeHNN͘p HvcYcC5:y #`οb;z2.!kr}gUWkyZn=f Pvsn3p~;4p˚=ē~NmI] ¾ 0lH[_L hsh_ғߤc_њec)g7VIZ5yrgk̞W#IjӪv>՞y睝M8[|]\շ8M6%|@PZڨI-m>=k='aiRo-x?>Q.}`Ȏ:Wsmu u > .@,&;+!!˱tﭧDQwRW\vF\~Q7>spYw$%A~;~}6¾ g&if_=j,v+UL1(tWake:@Ș>j$Gq2t7S?vL|]u/ .(0E6Mk6hiۺzښOrifޱxm/Gx> Lal%%~{lBsR4*}{0Z/tNIɚpV^#Lf:u@k#RSu =S^ZyuR/.@n&΃z~B=0eg뺆#,Þ[B/?H uUf7y Wy}Bwegל`Wh(||`l`.;Ws?V@"c:iɍL֯PGv6zctM̠':wuW;d=;EveD}9J@B(0iհ bvP1{\P&G7D޴Iy_$-Qjm~Yrr&]CDv%bh|Yzni_ˆR;kg}nJOIIwyuL}{ЌNj}:+3Y?:WJ/N+Rzd=hb;dj͒suݔ@NKMԄ jqzC5@y°hL m;*5ezᕏ=ep XL n?מ:r`۵tŤZ|1v`V뽧_csج'ߤ%oTuumk%%%h)uy]Nk[n 'b2 l.=͜E%gf$[c;s:V-͞WߤWh-j7]4=F-X]>ZLSi[Y*We;Zan(ӇW|e(HNNP5[= r4tP &0<pc#`vTNV GFqvTi*Tyam$ߏWyE*VJKMTfFw>'$-ؽ.Ho.8c"@DADADADADADADADADA~j*֘,N;Pi3599h=goضLgiJ5փy~}&Zd9p֚ e:|hL``b/d9p? fgg+%%hMgXosج, ΩOl0Zh=xdjLmhݻoO[g_l,8a]٭+ӧ0$I]c]:粹:Teꢢ"5a^Kgh,&= =՟^߶“ߢE ܹS J}I%:8 IDAT~,9/ʃPW'Mo}zNƍ쨓zPbNZ~^z=4mswg;5 Y~SVMRXUյڱRf?s:w ;6H:ºi5-maM&O3;1IKeamZh͛7+##v+c ~u~ca]GnF'ټL~PPPbn voC4R,ӟgg %hq}@#M4IÇ Oy^xMZx ) yOw@HkN˖-Sǎmb]X@n+i͖!++K3gd\$mt$^YfJ\8PRF)77Wא!Cl$i:@@_oG I{$# 8磌ŋ91A (Im7֭>}ߴJq7ޗt^ -[ԩSj*}%]&' -ɓ'ꫯVzzvB#;a 7@GxI{j޼ƌ.LÇWBB7`O"I$/@R @eee@۷>}0,ɒ2$53Xs|cS~rpTYYY} kHc %&k.], @ADADADADADADADADA@lT<%''*Lo^={رc5h %$+CnܸQ3fҥK}vUVVs9G R,_{xˇ3o߾;TTTd}馛]uuuG~iԩ@4bnvmvfϞ /Peeeq}}za I~,誫{UWW뮻}_~YƍSMMMYχ֝waw\ďcxꩧtEƍկ_?۷5@u?1kNׯWzz/wy>}zj3 k(ٺuq_Zvf̘:~ ABQ&r|!%KҥKgԞ={<_X-z !CyFUUz~ ABQIIIjݺW$UXXDٳZ~ ABQƍecW$<(~<RSSvZujjjԧOZQu@4 8m&&&jԩg$ď1h ͟?_{768@g =@`)))5o6m3)ѣƌJ;wҿUTT /KZR{~a=@0o<*狔iFɶ[ˎ;T]]OX@?K.ۈxN pppppppppppppppppPfl߾] ,{ァk۶mڿo5BTӦMӴiӴ|r DB2e|An!Dy'tkΝ[A $***t5' "!駟oaDnΝ:t֭[gDШQ06qD;@ x M6v(PiizmZ4ew"@̴ixf [~-Fٱc&IZ2|n!?$@{[HTɏ#@hȎI# _m(F /6Z3z'\r,r!;w2Z3j=~GY7"I$iI.p_"?pN`y DD?: _  Gÿab7J !Bx@0 Bo cG@`1C[@0G @`0C_u V1 aCX>W ` | `!<S `"<. `#c`?cAC4 ?c p#~@0?:08&_MQ1J h#?/`7;I  q 7a wQ A 1 Hp !#<8/#@1Ul7=S=K.4Z?E_$i@!1!E4?`P_  @Bă10#: "aU,xbFY1 [n|n #'vEH:`xb #vD4Y hi.i&EΖv#O H4IŶ}:Ikh @tZRF#(tXҙzZ ?I3l7q@õ|ۍ1,GpuY Ꮿ@hJv#xxk$ v#9 5 }_$c S#=+"K{F*m7`#%H:NRSp6I?sIՖ{Ap$I$I:QRv2$Z @UJ*$]<FO4IENDB`