NgE dZddlmZddlZddlZddlZddlZddlmZdZ dZ dZ ej d Z ej d d d d ddZej ddddZej d ej d ej d ej dej dej dej dej ddZej dZej dZGddejZd9d:d!Zd;d#Zdd/Zd?d1Zd@dAd4Zd@dAd5ZdBd8ZdS)Ca An implementation of `urlparse` that provides URL validation and normalization as described by RFC3986. We rely on this implementation rather than the one in Python's stdlib, because: * It provides more complete URL validation. * It properly differentiates between an empty querystring and an absent querystring, to distinguish URLs with a trailing '?'. * It handles scheme, hostname, port, and path normalization. * It supports IDNA hostnames, normalizing them to their encoded form. * The API supports passing individual components, as well as the complete URL string. Previously we relied on the excellent `rfc3986` package to handle URL parsing and validation, but this module provides a simpler alternative, with less indirection required. ) annotationsN) InvalidURLizBABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~z !$&'()*+,;=z%[A-Fa-f0-9]{2}z(?:(?P{scheme}):)?(?://(?P{authority}))?(?P{path})(?:\?(?P{query}))?(?:#(?P{fragment}))?z([a-zA-Z][a-zA-Z0-9+.-]*)?z[^/?#]*z[^?#]*z[^#]*z.*scheme authoritypathqueryfragmentzA(?:(?P{userinfo})@)?(?P{host}):?(?P{port})?z(\[.*\]|[^:@]*))userinfohostportz[^@]*z(\[.*\]|[^:]*))rrr r r r r rz ^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$z^\[.*\]$ceZdZUded<ded<ded<ded<ded<ded <ded <edd Zedd ZddZddZdS) ParseResultstrrr r int | Nonerr str | Noner r returncd|jr |jdndd|jvr d|jdn|j|j d|jndgS)N@:[])joinr r rselfs K/var/www/html/ai-engine/env/lib/python3.11/site-packages/httpx/_urlparse.pyrzParseResult.authorityjsqww'+}<4=####"$'49$4$4 DI    $)#'9#8DIb    cdd|jvr d|jdn|j|j d|jndgS)Nrrrr)rr rrs rnetloczParseResult.netloctsWww$'49$4$4 DI    $)#'9#8DIb    rkwargsc |s|S|j|j|j|j|jd}||t di|S)Nrrr)rrr r r updateurlparse)rr"defaultss r copy_withzParseResult.copy_with}s^ KkIZ    ''h'''rc|j}d|jr |jdnd|rd|nd|j|j d|jnd|j d|jndgS)Nrr//?#)rrrr r r )rrs r__str__zParseResult.__str__sN ww%)[84;!!!!b$-5 Y   2 $(J$: DJ   '+}'@#DM###b     rN)rr)r"rrr) __name__ __module__ __qualname____annotations__propertyrr!r(r-rrrrasKKKMMM III III    X    X  ( ( ( (       rrrurlrr"rrc  t|tkrtdtd|DrFt d|D}||}d|d|d}t|d|vr1|d}t |trt|n||d<d|vr6| dpd }| d \|d <}|d<d |vsd |vrXt| d d pd }t| d d pd } | r|d | n||d<d|vr=| dpd } | d\|d<} |d<| sd|d<d |vrN| d pd } d | vr3| dr| ds d| d|d <|D]\} }|t|tkrtd| dtd|DrIt d|D}||}d| d|d|d}t|t | |std| dt$|}|J|}| d|dpd }| d|dpd }| d|dpd }| d|d}| d|d}t*|}|J|}| d|dpd }| d |d pd } | d|d}|}t|t.d z }t1| }t3||}|d k}|d kp |d kp|du}t5|||!|s|rt7|}d"}t|t.|zd#z } |dnt|t.|zd$z }!|dnt|t.|zd%z }"t9||||| |!|"S)&Nz URL too longc3hK|]-}|o| V.dSNisascii isprintable.0chars r zurlparse..s> E E4<<>> 4$"2"2"4"44 E E E E E Erc3jK|].}||*|V/dSr7r8r;s rr>zurlparse..s@VVTDLLNNV4CSCSCUCUVDVVVVVVrz.Invalid non-printable ASCII character in URL, z at position .rr!rrr usernamepasswordr raw_pathr+r r rrzURL component 'z ' too longc3hK|]-}|o| V.dSr7r8r;s rr>zurlparse..s>OO4<<>><$*:*:*<*<&<OOOOOOrc3jK|].}||*|V/dSr7r8r;s rr>zurlparse..sW!dllnnEIEUEUEWEWrz-Invalid non-printable ASCII character in URL z component, zInvalid URL component ''rrr safe) has_scheme has_authorityz`{}%|^\"z:/[]@z:/?[]@z:/?#[]@)lenMAX_URL_LENGTHranynextfind isinstanceintrpop partitionquoteget startswithendswithitemsCOMPONENT_REGEX fullmatch URL_REGEXmatch groupdictAUTHORITY_REGEXlower SUB_DELIMS encode_hostnormalize_port validate_pathnormalize_pathr)#r4r"r=idxerrorrr!_rArBrC seperatorr keyvalue url_matchurl_dictrrr r r authority_matchauthority_dictr parsed_schemeparsed_userinfo parsed_host parsed_portrIrJ WHATWG_SAFE parsed_path parsed_queryparsed_fragments# rr&r&s  3xx.  ((( E E E E EEE VVSVVVVVhhtnn XT X XRU X X X  f~&0s&;&;ETv6H%%+,2,<,VzV33J339r::J339r::9AO558555xzV::j))/R5=5G5G5L5L2v 6'? #"F7Ozz&!!'R $;; 4 4;s9K9K;([[[F6N llnnCC U  5zzN** !B3!B!B!BCCCOOOOOOO (%*jj&&3C3333,/333!'''#3'11%88 C !A3!A!A!ABBB$$I  ""$$HZZ(8"4 5 5 ;F ;(=>>D"I ::fhv. / / 52D JJw 1 2 2Ezz*hz&:;;H&++I66O  & & &$..00Nzz*nZ&@AAGRH ::fnV4 5 5 ;D ::fnV4 5 5D  M  S0@AAAO"4((K,T6::K"$J2M!2Mk6M$:]KKKK$]$d## KT [(@7(JKKKK =  5zK7(B C C C    8*{":Y"F G G G   rr c|sdSt|r= tj|n%#tj$rt d|wxYw|St |rM tj|ddn%#tj$rt d|wxYw|ddS|r-d}t| t|zS tj | dS#tj$rt d |wxYw) NrzInvalid IPv4 address: rzInvalid IPv6 address: z"`{}%|\rGasciizInvalid IDNA hostname: )IPv4_STYLE_HOSTNAMEr\ ipaddress IPv4AddressAddressValueErrorrIPv6_STYLE_HOSTNAME IPv6Addressr9rTr_r`idnaencodedecode IDNAError)r rss rrara/s %Br  " "4 ( ("B  @  !$ ' ' ' '* @ @ @>d>>?? ? @  " "4 ( (B @  !$qt* - - - -* @ @ @>d>>?? ? @AbDz B ! TZZ\\ [(@AAAA={4::<<((//888 >===;4;;<<<=s!5"A7B"B68D>>"E rstr | int | Nonerrc||dkrdS t|}n #t$rtd|wxYwdddddd|}||krdS|S)NrzInvalid port: Pi)ftphttphttpswswss)rQ ValueErrorrrU)rr port_as_int default_ports rrbrb^s |trzzt4$ii 4442$223334rCr#NNRRLl""t s9r rIboolrJNonec|r&|r$|dstd|sJ|sJ|drtd|drtddSdSdS)z Path validation rules that depend on if the URL contains a scheme or authority component. See https://datatracker.ietf.org/doc/html/rfc3986.html#section-3.3 /z7For absolute URLs, path must be empty or begin with '/'r*z3Relative URLs cannot have a path starting with '//'rz2Relative URLs cannot have a path starting with ':'N)rVr)r rIrJs rrcrcysX  X,, XVWW W  Sm S ??4  TRSS S ??3   SQRR R S S S S S Srcd|vr|S|d}d|vrd|vr|Sg}|D]B}|dkr |dkr|r|dgkr|-||Cd|S)z Drop "." and ".." segments from a URL path. For example: normalize_path("/path/./to/somewhere/..") == "/path/to" r@rz..r)splitrRappendr)r componentsoutput components rrdrds $ CJ *Z!7!7 F%%     $   &RD.. MM) $ $ $ $ 88F  rstringcfdd|dDS)Nrcg|]}d|d S)%02Xr3)r<bytes r zPERCENT..s FFFtNNNNFFFrzutf-8)rr)rs rPERCENTrs/ 77FFv}}W/E/EFFF G GGrrrHct|z|s|Sdfd|DS)z1 Use percent-encoding to quote a string. rc:g|]}|vr|nt|Sr3)r)r<r=NON_ESCAPED_CHARSs rrz#percent_encoded..s.QQQ$*** QQQr)UNRESERVED_CHARACTERSrstripr)rrHrs @rpercent_encodedrsY.4 ==* + + 77QQQQ&QQQ  rcg}d}tjt|D]}||}}|d}||kr.|||}|t|||||}|t|kr.||d} |t| |d |S)a Use percent-encoding to quote a string, omitting existing '%xx' escape sequences. See: https://www.rfc-editor.org/rfc/rfc3986#section-2.1 * `string`: The string to be percent-escaped. * `safe`: A string containing characters that may be treated as safe, and do not need to be escaped. Unreserved characters are always treated as safe. See: https://www.rfc-editor.org/rfc/rfc3986#section-2.3 rrGNr) refinditerPERCENT_ENCODED_REGEXstartendgrouprrrKr) rrHpartscurrent_positionr\start_position end_position matched_text leading_text trailing_texts rrTrTs E2F;; ( (',{{}}eiikk {{1~~ - - -!"2>"ABL LLDAAA B B B  \"""'3v;;&&/001  _]>>>??? 775>>rrXlist[tuple[str, str]]c@dd|DS)am We can use a much simpler version of the stdlib urlencode here because we don't need to handle a bunch of different typing cases, such as bytes vs str. https://github.com/python/cpython/blob/b2f7b2ef0b5421e01efb8c7bee2ef95d3bab77eb/Lib/urllib/parse.py#L926 Note that we use '%20' encoding for spaces. and '%2F for '/'. This is slightly different than `requests`, but is the behaviour that browsers use. See - https://github.com/encode/httpx/issues/2536 - https://github.com/encode/httpx/issues/2721 - https://docs.python.org/3/library/urllib.parse.html#urllib.parse.urlencode &c`g|]+\}}t|ddzt|dz,S)rrG=)r)r<kvs rrzurlencode..sP   1 AB ' ' '# -0K0K0K K   r)r)rXs r urlencoders6 88       rr$)r4rr"rrr)r rrr)rrrrrr)r rrIrrJrrr)r rrr)rrrr)r)rrrHrrr)rXrrr)__doc__ __future__rr{rtypingr _exceptionsrrLrr`compilerformatr[r^rYrzr~ NamedTuplerr&rarbrcrdrrrTrr3rrrs$#""""" ######I " #455 BJ *  f+      &"*T f      bj566I&& BJx RZ  4   7## BJ) * * BJt    !bj!DEE bj--4 4 4 4 4 &#4 4 4 nTTTTTn,=,=,=,=^6SSSS2>HHHH     Br