j~ddlmZddlZddlZddlZddlZddlmZddlm Z ddl m Z dZ dZ d Zd \ZZZZej&d Zej&d Zed dhZehdZehdZehdZeddhZehdZeddhZeddhZed dhZd5dZ edZ!Gdde"Z#Gdde#Z$Gdde#Z%Gdd e#Z&d6d!Z'd7d"Z(d8d#Z)d9d$Z*d:d%Z+d;d&Z,dd(Z.d>d)Z/d?d*Z0d@d+Z1dr r AN> r r r BNCSENESETONNSM>r r r rr r>Lr r rrrrrrDcptjjD]\}}t||s|cSyN)r joining_typesitemsr)cpjtrangess r@rAcVt||||_||_||_||_yr)super__init__r=r>r@rA)selfr=r>r@rAargs __class__s rrEzIDNAError.__init__^s. $  "  r) rGobjectr=z_ErrorCode | Noner>r<r@r?rAr?returnNone)__name__ __module__ __qualname____doc____annotations__rE __classcell__)rHs@rr;r;Est&   #' $# ! !  ! !  !  !  ! !rr;ceZdZdZy) IDNABidiErrorz;Exception when bidirectional requirements are not satisfiedNrLrMrNrOrrrSrSmsErrSceZdZdZy)InvalidCodepointz ??rc$|jdS)Npunycode)encodess r _punycoderls 88J rcd|dS)NzU+04XrUrjs r_unotros #w<rct|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``. ?lenlabels rvalid_label_lengthrvs u: rc*t||rdkSdkS)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``. rr)domain trailing_dots rvalid_string_lengthr|s v;,3 88C 88rc t|tkDr tddd}t|dD]I\}}t j |}|dk(rt d|d|d |t|| |tvsHd }K|s|sy t j |d }|tvrd }n(|d k(rd}n t d|dd|t|d d d}d}d} t|dD]\}}t j |}|rh|tvrt d|dd|t|| |tvrd }|}n |dk7rd}|}|tvsa| s|} f| |k7slt dd|t|| |tvrt d|dd|t|| |tvrd }|}|dk7sd}|}|s#t d|rdnd|t||dz | y )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. Label too longrr=Frz Unknown directionality in label at position r2rBTrrzFirst codepoint in label z" must be directionality L, R or ALr,Nz,Invalid direction for codepoint at position z in a right-to-left labelr-rz2Can not mix numeral types in a right-to-left labelr/z in a left-to-right labelr0z0Label ends with illegal codepoint directionalityr.r1)rs_max_input_lengthr; enumerater[ bidirectionalrSrc_bidi_rtl_categories_bidi_rtl_first_bidi_rtl_allowed_bidi_rtl_valid_ending_bidi_rtl_numeric_bidi_ltr_allowed_bidi_ltr_valid_ending) ru check_ltr bidi_labelidxr directionrtl valid_ending ending_idx number_types r check_bidirsd  5z%%(/?@@JUA& R--b1 ?25)=N-b'   , ,J  i))%(3IO# c 'y0R S%(m   LJ"KUA&0!R--b1  11#B3%G`a&!"g 22#  e#$  --""+K I-'L*""%b'!$  11#B3%G`a&!"g 22#  e#$  a0!d  >"%=% Q/0    rc ||r:tj|dddk(rtdd|t|ddy)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 characterr'rrBT)r[categoryr;rcrts rcheck_initial_combinerrsK %%eAh/2c9 >#%(m    rc|dddk(r tdd|jds|jdr tdd y ) 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%r-z)Label must not start or end with a hyphenr&T)r; startswithendswithrts rcheck_hyphen_okr4sL QqzTNUabb s 3CJ\]] rct|tkDr tddtjd||k7r tddy)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. r~rrNFCz%Label must be in Normalization Form Cr$N)rsrr;r[ normalizerts r check_nfcrFsH  5z%%(/?@@UE*e3?iPP4rc2t|tkDr tddt||}|dk(r|dkDr"t t||dz t k(ryd}t |dz d d D],}tt||}|d k(r |tvrd}nn|syd}t |dzt|D].}tt||}|d k(r |tvrd}|S|S|S|d k(r(|dkDxr!t t||dz t k(Sy) 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. :raises IDNAError: If ``label`` exceeds the defensive input length limit. r~rri rrTFTi ) rsrr;rcra_virama_combining_classranger_bidi_joiner_l_or_d_bidi_joiner_r_or_d)ruposcp_valueoki joining_types rvalid_contextjrRsN  5z%%(/?@@5:H6 7'E#'N(;<@WW sQwB' A(U1X7Ls"22   sQwE + A(U1X7Ls"22     6Qw[+CcAg,?@D[[[ rct|tkDr tddt||}|dk(rHd|cxkxrt|dz kncxr*t||dz dk(xrt||dzdk(S|dk(r2|t|dz kr t|dkDrt ||dzd Sy |d vr|dkDrt ||dz d Sy |d k(r4|D].}|dk(r t |dst |ds t |ds.yy d|cxkrdkrnnt d|D Sd|cxkrdkrny t d|D Sy )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). :raises IDNAError: If ``label`` exceeds the defensive input length limit. r~rrrrliuGreekF>Hebrewi0u・HiraganaKatakanaHanT`ic3NK|]}dt|cxkxrdkncyw)Nrc.0rs r z!valid_contexto..!BbuB1611B#%rrc3NK|]}dt|cxkxrdkncyw)rrNrrs rrz!valid_contexto..rr)rsrr;rcrfany)rur exceptionrrs rvalid_contextorsv 5z%%(/?@@5:H63'Ua'kCcAg,?6,IkcRWX[^_X_R`NaekNkk6 Ua CJNeC!Gng6 6## 7eC!Gnh7 76 BX~"j)ZJ-G:VXZ_K`    !E!BEBBBB !E! BEBBBB rc t|tkDr tddt|tt fr |j d}t|dk(r td d t|d s tdd t|t|t|t|D]\}}t|}t|tj dr/t|tj dr8 t#||}|r\t)dt'|d|dzd|d|||dzt|tj dr5t+||rt)dt'|d|dzd|d|||dzt-dt'|d|dzd|dd|||dzt/|y#t$r}tdd|d}~wwxYw#t$$r.}tdt'|d|dzd|d|||dz|d}~wwxYw)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. r~rrzutf-8zInvalid UTF-8 in labelr6Nrz Empty Labelr"Tr{r PVALIDCONTEXTJz%Unknown codepoint adjacent to joiner rr in r+rBzJoiner  not allowed at position r)CONTEXTO Codepoint r*z of z not allowedr()rsrr; isinstancebytes bytearraydecodeUnicodeDecodeErrorr|rrrrrcrrcodepoint_classesrr_rorYrrWr)ruerrrrr contextj_oks r check_labelrsb$ 5z%%(/?@@%%+, TLL)E 5zQ M:: u4 8(/?@@ eE5!U#'Rr7 Xx'A'A('K L  Xx'A'A*'M N ,UC8 -eHo..GayPTUZT]^#& 1W x)C)CJ)O P!%-- x 11J3QR7)SWX]W`a#& 1W #U8_-]37)4yP\]+"q  C'Ruq" T4>JPS S T, ;E(O;LMZ]`aZaYbbfglfop,& 1W    s/F56 G5 G>G  G H )HH c:t|tkDr tdd |jd}t |t |s tdd|S#t $rYnwxYwt|tt|z}t |s tdd|S)uConvert a single U-label into its A-label form. The result is the ASCII-Compatible Encoding (ACE) form per :rfc:`5891` §4: the label is validated, Punycode-encoded, and prefixed with ``xn--``. Pure ASCII labels that are already valid IDNA labels are returned unchanged (as :class:`bytes`). :param label: The label to convert, as a Unicode string. :returns: The A-label as ASCII-encoded :class:`bytes`. :raises IDNAError: If the label is invalid or the resulting A-label exceeds 63 octets. r~rrasciir ) rsrr;riulabelrvUnicodeEncodeErrorr_alabel_prefixrl)ru label_bytess ralabelr s 5z%%(/?@@ll7+  {!+.,3CD D     9U#33K k *(/?@@ sA A#"A#ct|tkDr tddt|tt fs |j d}n(t |}|js tdd|j}|jtr?|ttd}|s tdd |jd r)td d t||jdS |jd }t!||k7r tddt||S#t$rt||cYSwxYw#t$r}td d |d}~wwxYw)ucConvert a single A-label into its U-label form. Performs the inverse of :func:`alabel`: an ``xn--``-prefixed label is Punycode-decoded and validated, and is rejected unless it is the canonical A-label for the decoded U-label (:rfc:`5891` §5.3). 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. r~rrrInvalid ASCII in A-labelr5Nz5Malformed A-label, no Punycode eligible content foundr3-z"A-label must not end with a hyphenrhzInvalid A-labelz=A-label is not the canonical Punycode encoding of its U-labelr4)rsrr;rrrrirrisasciilowerrrrr UnicodeErrorrl)rurrs rrr-s` 5z%%(/?@@ eeY/ 0 ,,w/K El ""$6_M M##%Kn-!#n"5"78 SZjk k    %@GWX XK !!'**K"":.;&W^tuu L?"   L * K)0@AsJKs)D+2E+EE E#EE#ctj|}|rQt|j}||j zdz}t dt |d|d|d|||y)zRaise if ``text``, a slice of ``domain`` starting at ``offset`` that UTS #46 mapping left unchanged, contains an ASCII character disallowed under ``UseSTD3ASCIIRules``.rrrrr8rBN)_std3_disallowed_researchrcgroupstartrWro)r>rzoffsetmatchr@rAs r _check_std3rbsy & &t ,E  & EKKM)A-y)**CH:TRXQ[ \    rc<tjdtdy)NzTransitional processing is deprecated in UTS #46 and has no effect. The transitional argument will be removed in a future version.) stacklevel)warningswarnDeprecationWarningrUrr_warn_transitionalrss MM I rc |r tt|tkDr tdd|j r!|j }|r t ||d|Sddlm}m }m }g}d}t|D]\} } t| } | dkr| ntj|| dz } || } | tk(rA| t k(r|| }n>| t"k(rZ| t$k(rd}n(t'd t)| d | dzd |d || | dz || kr%||| }|r t ||||j+||rP|r=t,j/|r(t'd t)| d | dzd |d|| | dz |j+|| dz}|dk(r%|r t ||dt1j2d|S||d}|r t ||||j+|t1j2ddj5|S)u3Apply 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``, ``I``, ``X``). The result is returned in Normalisation Form C. :param domain: The full domain name to remap. :param std3_rules: If ``True``, apply UTS #46's ``UseSTD3ASCIIRules``: after mapping, any ASCII character other than a lowercase letter, digit, hyphen or the label separator ``.`` is rejected, whether it appeared in the input or was produced by a mapping (e.g. U+FF01 FULLWIDTH EXCLAMATION MARK maps to ``!``). If ``False``, such characters are passed through. :param transitional: Deprecated and ignored. UTS #46 deprecated transitional processing in Unicode 15.1 and deviation (status ``D``) codepoints are now always kept, so this has no effect beyond emitting a :class:`DeprecationWarning`. It will be removed in a future version. :returns: The remapped domain, in Normalisation Form C. :raises InvalidCodepoint: If the domain contains a disallowed codepoint under the chosen rules. :raises IDNAError: If ``domain`` exceeds the defensive input length limit. Domain too longrrrr)uts46_replacements uts46_startsuts46_statusesNrrrr7rBr8rr)rrsrr;rrr uts46datarrrrrcbisect bisect_right _STATUS_VALID_STATUS_MAPPED_STATUS_DEVIATION_STATUS_IGNOREDrWroappendrrr[rjoin)rz std3_rules transitionalresultrrroutputrrchar code_pointrstatus replacementruntails r uts46_remapr|s72 6{&&)0@AA ~~   * KK F Ev&% TY $s*J0C0CLR\0]`a0a" ] "  ^ #,Q/K ( (   &K"U:.//Hq QUV\U_`'$q   3;s#CC/ MM#  188E& z!2 33LSSTWIUYZ`Ycd%( 1W  MM+ &aK%N z   *$$UF33 %&>DD&%( MM$   88rc|r tt|ts t|d}t |tkDr t dd|r t||}t|d s t dd d }g}|r|jd ntj|}|r|d gk(r t dd|dd k(r|d=d}|D]-} t| }|r|j|"t dd|r|jddj|}t||s t dd |S#ttf$r}t dd|d}~wwxYw)a*Encode 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: Deprecated and ignored (see :func:`uts46_remap`): 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. rzGshould pass a unicode string to the function rather than a byte string.r5rNrrTrr!F.r Empty domainr#r Empty labelr"r.)rrstrr TypeErrorr;rsrrr|split_unicode_dots_rerrr) rkstrictuts46rrrr{rlabelsrus rririsb8 a  AwA  1v!!)0@AA : & qt 4)0ABBL F#QWWS\)9)?)?)BF Vt^^<< bzR 2J ? 5M MM! M > > ?  c &A q, /)0ABB H?#I. Y`o  s D00E?E  Ect|ts t|d}t |t kDr t dd|r t||d}t|d s t dd d}g}|r|jd ntj|}|r|d gk(r t dd|ds|d=d }|D].} t| } | r|j| #t dd|r|jd d j|S#ttf$r}t dd|d}~wwxYw#t$r-|r'| ddjdk(r| j} nYwxYw)uDecode 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``. :param display: If ``True``, any ``xn--`` label that fails IDNA validation is passed through unchanged (lowercased) rather than aborting the whole call. Intended for "decode for display" consumers (e.g. URL libraries, HTTP clients) that want to show the user the label as it appears on the wire when it cannot be rendered as Unicode. Matches the per-label recovery prescribed by UTS #46 §4 and the WHATWG URL "domain to Unicode" algorithm. :returns: The decoded domain as a Unicode string. :raises IDNAError: If the input is not valid ASCII, contains an invalid label, or is empty. rrr5rNrrFTrr!rrrr#rrzxn--rr")rrrrr;rsrrr|rrrrrr) rkrrrdisplayrr{rrruus rrrsx> a  WAwA 1v!!)0@AA :u - qt 4)0ABBL F#QWWS\)9)?)?)BF Vt^^<< ": 2J  ? u A MM! M > > ? b 88F =#I. W6_MSV V W& 5!9??,6KKM s) D7 D-D*D%%D*-3E#"E#)rintrJr<)rr rJr )rrrerrJbool)rkrrJr)rkr rJr)ru bytes | strrJr!)rzr"r{r!rJr!)F)rurrr!rJr!)rurrJr!)rurrJrK)rurrr rJr!)rurrr rr!rJr!)rustr | bytes | bytearrayrJrK)rurrJr)rur#rJr)r>rrzrrr rJrK)rJrK)TF)rzrrr!rr!rJr)FFFF) rkr#rr!rr!rr!rr!rJr) rkr#rr!rr!rr!rr!rJr); __future__rrrer[rtypingrrr intrangesrrrrrrrrcompilerr frozensetrrrrrrrrrr _ErrorCoderr;rSrWrYrarfrlrorvr|rrrrrrrrrrrrrirrUrrr+s3" (DKA ~0/2:::; bjj!PQS$K( !23Z["#:;tTl+NO"C;/c +c + >%! %!PFIFGyGNiN @   9sl*$ Q3l.bOdD2j "\9B @ @ @  @  @  @  @ J @@ @ @ @  @  @r