ZL jOZ ddlZddlZddlZddlZddlmZmZddlmZddl m Z dZ dZ ej dZed d hZehd Zehd Zehd ZeddhZehdZeddhZeededhZeed edhZGddeZGddeZGddeZGddeZdedefdZ de!de!de"fdZ#d e!de$fd!Z%d ede!fd"Z&d#ee$e!fde"fd$Z'd%ee$e!fd&e"de"fd'Z(d=d#e!d)e"de"fd*Z)d#e!de"fd+Z*d#e!de"fd,Z+d#e!ddfd-Z,d#e!d.ede"fd/Z-d=d#e!d.ed0e"de"fd1Z.d#ee!e$e/fddfd2Z0d#e!de$fd3Z1d#ee!e$e/fde!fd4Z2d>d%e!d6e"d7e"de!fd8Z3 d?d ee!e$e/fd9e"d:e"d6e"d7e"de$f d;Z4 d@d ee!e$e/fd9e"d:e"d6e"de!f d<Z5dS)AN)OptionalUnion)idnadata)intranges_contain sxn--u [.。．｡]RAL>r r AN> r r r BNCSENESETONNSM>r r r rr r>Lr r rrrrrrDceZdZdZdS) IDNAErrorz5Base exception for all IDNA-encoding related problemsN__name__ __module__ __qualname____doc__O/home/kuhnn/.hermes/hermes-agent/venv/lib/python3.11/site-packages/idna/core.pyrrs??DrrceZdZdZdS) IDNABidiErrorz;Exception when bidirectional requirements are not satisfiedNrrrrr r !sEEDrr ceZdZdZdS)InvalidCodepointz ? ??rsc,|dS)Npunycode)encoder4s r _punycoder9>s 88J  rcd|dS)NzU+04Xrr8s r_unotr<Bs <<<rlabelc(t|dkS)uCheck that a label does not exceed the maximum permitted length. Per :rfc:`1035` (and :rfc:`5891` §4.2.4) a DNS label must not exceed 63 octets. The argument may be either a :class:`str` (a U-label, where length is measured in characters) or :class:`bytes` (an A-label, where length is measured in octets). :param label: The label to check. :returns: ``True`` if the label is within the length limit, otherwise ``False``. ?lenr=s rvalid_label_lengthrCFs u:: rdomain trailing_dotc0t||rdndkS)aCheck that a full domain name does not exceed the maximum length. Per :rfc:`1035`, a domain name is limited to 253 octets when no trailing dot is present, or 254 octets when one is included. :param domain: The full (possibly multi-label) domain name. :param trailing_dot: ``True`` if ``domain`` includes a trailing ``.``. :returns: ``True`` if the domain is within the length limit, otherwise ``False``. r@)rDrEs rvalid_string_lengthrIUs v;;,733C 88rF check_ltrcd}t|dD]L\}}tj|}|dkr"tdt |d||t vrd}M|s|sdStj|d}|t vrd}n)|dkrd}n td t |d d}d }t|dD]\}}tj|}|rT|tvrtd |d |tvrd}n|dkrd}|tvr|s|}Y||krtdo|tvrtd |d|tvrd}|dkrd}|stddS)a!Validate the Bidi Rule from :rfc:`5893` for a single label. The Bidi Rule constrains how bidirectional characters (Hebrew, Arabic, etc.) may appear within a label. By default the check is only applied when the label contains at least one right-to-left character (Unicode bidirectional categories ``R``, ``AL``, or ``AN``); set ``check_ltr`` to ``True`` to apply it to LTR-only labels as well. :param label: The label to validate, as a Unicode string. :param check_ltr: If ``True``, apply the rules even when the label contains no RTL characters. :returns: ``True`` if the label satisfies the Bidi Rule. :raises IDNABidiError: If any of Bidi Rule conditions 1-6 are violated, or if the directional category of a codepoint cannot be determined. Frz Unknown directionality in label at position TrrzFirst codepoint in label z" must be directionality L, R or ALNz,Invalid direction for codepoint at position z in a right-to-left labelrz2Can not mix numeral types in a right-to-left labelz in a left-to-right labelz0Label ends with illegal codepoint directionality) enumerater( bidirectionalr repr_bidi_rtl_categories_bidi_rtl_first_bidi_rtl_allowed_bidi_rtl_valid_ending_bidi_rtl_numeric_bidi_ltr_allowed_bidi_ltr_valid_ending) r=rJ bidi_labelidxr% directionrtl valid_ending number_types r check_bidir^cs"JUA&&R-b11 ?? b4;; b b]` b bcc c , , ,J it)%(33IO## c  gU ggghhhL!%KUA&&%%R-b11  % 111#$qSV$q$q$qrrr222# e##$ ---"b"+KK"i//+,`aaa 111#$qSV$q$q$qrrr222# e##$ PNOOO 4rcltj|dddkrtddS)u^Reject labels that begin with a combining mark. Per :rfc:`5891` §4.2.3.2 a label must not start with a character of Unicode general category ``M`` (Mark). :param label: The label to check. :returns: ``True`` if the first character is not a combining mark. :raises IDNAError: If the label begins with a combining character. rMz0Label begins with an illegal combining characterT)r(categoryrrBs rcheck_initial_combinerrbs7E!H%%a(C//JKKK 4rc|dddkrtd|ddks |ddkrtdd S) uValidate the hyphen restrictions for a label. Per :rfc:`5891` §4.2.3.1 a label must not start or end with a hyphen (``U+002D``), and must not have hyphens in both the third and fourth positions (the prefix reserved for A-labels). :param label: The label to check. :returns: ``True`` if the hyphen restrictions are satisfied. :raises IDNAError: If any of the hyphen restrictions are violated. z--z4Label has disallowed hyphens in 3rd and 4th positionr-z)Label must not start or end with a hyphenT)rrBs rcheck_hyphen_okrhsU QqSzTNOOO Qx3%)s**CDDD 4rcVtjd||krtddS)zRequire that a label is in Unicode Normalization Form C. :param label: The label to check. :raises IDNAError: If ``label`` differs from its NFC normalisation. NFCz%Label must be in Normalization Form CN)r( normalizerrBs r check_nfcrls3 UE**e33?@@@43rposct||}|dkr.|dkr0tt||dz tkrdSd}t|dz ddD]\}t jt||}|tdkrO|tvrd}n|sdSd}t|dzt|D]\}t jt||}|tdkrO|tvrd}n|S|dkr4|dko-tt||dz tkSdS) aValidate the CONTEXTJ rules from :rfc:`5892` Appendix A. These rules govern the contextual use of the joiner codepoints ``U+200C`` (ZERO WIDTH NON-JOINER, Appendix A.1) and ``U+200D`` (ZERO WIDTH JOINER, Appendix A.2) within a label. :param label: The label containing the codepoint. :param pos: Index of the joiner codepoint within ``label``. :returns: ``True`` if the codepoint at ``pos`` satisfies its CONTEXTJ rule, ``False`` otherwise (including when the codepoint at ``pos`` is not a recognised joiner). :raises ValueError: If an adjacent codepoint has no Unicode name when determining its combining class. i rrTFrgTi ) r1r._virama_combining_classranger joining_typesget_bidi_joiner_l_or_drA_bidi_joiner_r_or_d)r=rmcp_valueoki joining_types rvalid_contextjrzs5:H6 77'E#'N(;(;<<@WWW4 sQwB''  A#13377E!H FFLs3xx''!444 5 sQwE ++  A#13377E!H FFLs3xx''!444 6Qw[+CcAg,?,?@@D[[[ur exceptionct||}|dkrXd|cxkot|dz knco7t||dz dkot||dzdkS|dkrD|t|dz kr,t|dkrt||dzdSdS|dks|d kr!|dkrt||dz d SdS|d krA|D]<}|d kr t|d s t|dst|drdS=dSd|cxkrdkrnntd|D Sd|cxkrdkrnntd|D SdS)aValidate the CONTEXTO rules from :rfc:`5892` Appendix A. Covers the contextual rules for codepoints such as MIDDLE DOT (``U+00B7``), Greek lower numeral sign, Hebrew punctuation, Katakana middle dot, and the Arabic-Indic / Extended Arabic-Indic digit ranges. :param label: The label containing the codepoint. :param pos: Index of the codepoint within ``label``. :param exception: Reserved for forward compatibility; currently unused. :returns: ``True`` if the codepoint at ``pos`` satisfies its CONTEXTO rule, ``False`` otherwise (including when the codepoint is not a recognised CONTEXTO codepoint). rrliuGreekFiiHebrewi0u・HiraganaKatakanaHanT`ic3PK|]!}dt|cxkodkncV"dS)Nr1.0r%s r z!valid_contexto..4DBBbuB111161111BBBBBBrrrc3PK|]!}dt|cxkodkncV"dS)rrNrrs rrz!valid_contexto..7rr)r1rAr3any)r=rmr{rvr%s rvalid_contextors5:H63''''Ua''''kCcAg,?,?6,IkcRWX[^_X_R`NaNaekNkk V   Ua  CJJNNeC!Gng66 6u V  x611 77eC!Gnh77 7u V    BX~~"j)) ZJ-G-G :VXZ_K`K` tt u ( # # # #e # # # # #BBEBBBBBBB ( # # # #e # # # # #BBEBBBBBBB 5rc t|ttfr|d}t |dkrt dt |dst dt|t|t|t|D]\}}t|}t|tjdr6t|tjdr t||s5t!d t#|d |d zd t%|#t&$r;}t d t#|d|d zd t%||d}~wwxYwt|tjdrGt)||s5t!dt#|d |d zd t%|Lt+dt#|d|d zdt%|dt-|dS)a8Run the full set of IDNA 2008 validity checks on a single label. Applies, in order: NFC normalisation (:func:`check_nfc`), hyphen restrictions (:func:`check_hyphen_ok`), the no-leading-combiner rule (:func:`check_initial_combiner`), per-codepoint validity (PVALID, CONTEXTJ, CONTEXTO classes from :rfc:`5892`), and the Bidi Rule (:func:`check_bidi`). :param label: The label to validate. ``bytes`` or ``bytearray`` input is decoded as UTF-8 first. :raises IDNAError: If the label is empty or fails a structural rule. :raises InvalidCodepoint: If the label contains a DISALLOWED or UNASSIGNED codepoint. :raises InvalidCodepointContext: If a CONTEXTJ or CONTEXTO codepoint is not valid in its context. :raises IDNABidiError: If the Bidi Rule is violated. zutf-8rz Empty LabelTrELabel too longPVALIDCONTEXTJzJoiner  not allowed at position r in z%Unknown codepoint adjacent to joiner rMNCONTEXTO Codepoint z of z not allowed) isinstancebytes bytearraydecoderArrIrlrhrbrNr1rrcodepoint_classesrzr$r<rPr,rr"r^)r=rmr%rverrs r check_labelr<s$%%+,,& W%% 5zzQ &&& u4 8 8 8*())) eE5!!!U##vvRr77 Xx'A('K L L v  x)CJ)O P P v %eS111f%//ffCRSGffY]^cYdYdff   tE(OOttZ]`aZattgklqgrgrtt x)CJ)O P P v!%-- -exee3QR7eeX\]bXcXcee  ##th#t#tcTUg#t#t[_`e[f[f#t#t#tuu uusAE  F6F  Fc8 |d}t|t|std|S#t$rYnwxYwt |t t|z}t|std|S)uConvert a single U-label into its A-label form. The result is the ASCII-Compatible Encoding (ACE) form per :rfc:`5891` §4: the label is validated, Punycode-encoded, and prefixed with ``xn--``. Pure ASCII labels that are already valid IDNA labels are returned unchanged (as :class:`bytes`). :param label: The label to convert, as a Unicode string. :returns: The A-label as ASCII-encoded :class:`bytes`. :raises IDNAError: If the label is invalid or the resulting A-label exceeds 63 octets. asciir)r7ulabelrCrUnicodeEncodeErrorr_alabel_prefixr9)r= label_bytess ralabelrus ll7++ {!+.. .,-- -       9U#3#33K k * **())) sAA AAct|ttfs8 |d}n0#t$rt ||cYSwxYwt|}|}|trR|ttd}|std| drtdn$t || dS | d}n"#t$r}td|d}~wwxYwt ||S)aConvert a single A-label into its U-label form. Performs the inverse of :func:`alabel`: an ``xn--``-prefixed label is Punycode-decoded and validated. Labels that are already Unicode (or plain ASCII without the ACE prefix) are validated and returned as a Unicode string. :param label: The label to convert. ``bytes`` or ``bytearray`` input is treated as ASCII. :returns: The U-label as a Unicode string. :raises IDNAError: If the label is malformed or fails validation. rNz5Malformed A-label, no Punycode eligible content found-z"A-label must not end with a hyphenr6zInvalid A-label)rrrr7rrlower startswithrrArendswithr UnicodeError)r=rrs rrrsv eeY/ 0 0# ,,w//KK!       LLL Ell ##%%Kn--+!#n"5"5"7"78  USTT T    % % B@AA A B K   !!'***4"":.. 444)**34 Ls'4AA D D>)D99D>T std3_rules transitionalc *ddlm}d}t|D]\}}t|}||dkr|ntj||dfdz }|d} d} t |dkr|d} | d kp| d kr| p | d ko| o| du} | duo| d kp| d kr| p| d ko|} | r||z }| r | J|| z }| d krt dt|d|dzdt|tj d|S)uApply the UTS #46 character mapping to a domain string. Implements the mapping table from `UTS #46 §4 `_: each character is kept, replaced, or rejected based on its status (``V``, ``M``, ``D``, ``3``, ``I``). The result is returned in Normalisation Form C. :param domain: The full domain name to remap. :param std3_rules: If ``True``, apply the stricter STD3 ASCII rules (status ``3`` codepoints raise instead of being kept or mapped). :param transitional: If ``True``, use transitional processing (status ``D`` codepoints are mapped instead of kept). Transitional processing has been removed from UTS #46 and this option is retained only for backwards compatibility. :returns: The remapped domain, in Normalisation Form C. :raises InvalidCodepoint: If the domain contains a disallowed codepoint under the chosen rules. r) uts46datarLZNrdVr3r`Irrrrj) rrNr1bisect bisect_leftrAr"r<rPr(rk) rDrrroutputrmchar code_pointuts46rowstatus replacement keep_as_isuse_replacements r uts46_remaprs&%$$$$$ Fv&&yy TYY :+;+;ZZAST]`jlo_pAqAqtuAuv!%) x==A  "1+K cM fm@L0@ fPSmF~\fXfF~kvz~k~  &T1 cM cfm>J cFcMDbVb   y dNFF  y*** k !FF s]] "#wj0A0A#w#w\_bc\c#w#wimntiuiu#w#wxx x   / //rstrictuts46c|rtjdtdt|ts; t |d}n)#t t f$r}td|d}~wwxYw|rt|||}t|dstd d }g}|r| d nt |}|r|d gkrtd |dd kr|d=d}|D]7} t| }|r| |)td|r| dd|}t||std |S)aAEncode a Unicode domain name into its ASCII (A-label) form. Splits the input on label separators (only ``U+002E`` if ``strict`` is set; otherwise also IDEOGRAPHIC FULL STOP ``U+3002``, FULLWIDTH FULL STOP ``U+FF0E``, and HALFWIDTH IDEOGRAPHIC FULL STOP ``U+FF61``), encodes each label with :func:`alabel`, and rejoins them with ``.``. Optionally pre-processes the input through :func:`uts46_remap`. :param s: The domain name to encode. :param strict: If ``True``, only ``U+002E`` is recognised as a label separator. :param uts46: If ``True``, apply UTS #46 mapping before encoding. :param std3_rules: Forwarded to :func:`uts46_remap` when ``uts46`` is ``True``. :param transitional: Forwarded to :func:`uts46_remap` when ``uts46`` is ``True``. Deprecated: emits a :class:`DeprecationWarning` and will be removed in a future version. :returns: The encoded domain as ASCII :class:`bytes`. :raises IDNAError: If the domain is empty, contains an invalid label, or exceeds the maximum domain length. zuTransitional processing has been removed from UTS #46. The transitional argument will be removed in a future version.rd) stacklevelrzGshould pass a unicode string to the function rather than a byte string.NTrDomain too longF.rL Empty domainrg Empty labelr.)warningswarnDeprecationWarningrstrUnicodeDecodeError TypeErrorrrrIsplit_unicode_dots_rerappendjoin) r4rrrrrrEresultlabelsr=s rr7r7s8   M      a  p pAwAA"I. p p pefflo o p 5 :| 4 4 qt 4 4 4+)***L F# BQWWS\\\)9)?)?)B)BF (Vt^^''' bzR 2J ++ 5MM  + MM!    M** * c &A q, / /+)*** HsAA,A''A,ct|ts; t|d}n)#ttf$r}t d|d}~wwxYw|rt ||d}t |dst dd}g}|r|dnt|}|r|d gkrt d |d s|d =d}|D]7}t|}|r| |)t d |r| d d |S) aDecode an A-label-encoded domain name back to Unicode. Splits the input on label separators (see :func:`encode` for the rules), decodes each label with :func:`ulabel`, and rejoins them with ``.``. Optionally pre-processes the input through :func:`uts46_remap`. :param s: The domain name to decode. :param strict: If ``True``, only ``U+002E`` is recognised as a label separator. :param uts46: If ``True``, apply UTS #46 mapping before decoding. :param std3_rules: Forwarded to :func:`uts46_remap` when ``uts46`` is ``True``. :returns: The decoded domain as a Unicode string. :raises IDNAError: If the input is not valid ASCII, contains an invalid label, or is empty. rzInvalid ASCII in A-labelNFTrrrrLrrgr) rrrrrrrIrrrrr) r4rrrrrErrr=s rrr:s~. a  A AAwAA"I. A A A677S @ A . :u - - qt 4 4 4+)***L F# BQWWS\\\)9)?)?)B)BF (Vt^^''' ": 2J ++ 5MM  + MM!    M** * b 88F  s(AA  A)F)TF)FFFF)FFF)6rrer(rtypingrrrLr intrangesrrprcompiler frozensetrRrQrSrTrUrVrWr1rtrurrr r"r$intr.rboolr3rr9r<rCrIr^rbrhrlrzrrrrrrr7rrrrrs """"""""((((((2::;;)S$K(( y!2!2!233IZZZ[["#:#:#:;;ItTl++INNNOO"C;//iS33s88 455iS33s88 455             I        y        i         @3@@@@@@      SS eE3J/ D     9eSj 1 9 9$ 9 9 9 9GGcGdGtGGGGT # $    34$ASATAAAA3#3C3D3333l++#+C+D+T++++\6uS%2366666r#%>&%UI-.&3&&&&R40404040D40UX40404040r C C  S% "#C C  C  C  C  C C C C P 22 S% "#2 2 2 2  222222r