o )if8E @s^dZddlmZddlZddlZddlZddlZddlmZdZ dZ dZ e d Z e d jd d d dddZe djddddZe d e d e d e de de de de ddZe dZe dZGdddejZdEdFd!d"ZdGd$d%ZdHd*d+ZdId1d2ZdJd3d4ZdKd6d7ZdLdMd;d<ZdLdNd=d>ZdLdNd?d@ZdOdCdDZdS)Pa An implementation of `urlparse` that provides URL validation and normalization as described by RFC3986. We rely on this implementation rather than the one in Python's stdlib, because: * It provides more complete URL validation. * It properly differentiates between an empty querystring and an absent querystring, to distinguish URLs with a trailing '?'. * It handles scheme, hostname, port, and path normalization. * It supports IDNA hostnames, normalizing them to their encoded form. * The API supports passing individual components, as well as the complete URL string. Previously we relied on the excellent `rfc3986` package to handle URL parsing and validation, but this module provides a simpler alternative, with less indirection required. ) annotationsN) InvalidURLizBABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~z !$&'()*+,;=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(\[.*\]|[^:]*))rrrr r r r r z ^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$z^\[.*\]$c@sveZdZUded<ded<ded<ded<ded<ded <ded <edd d ZedddZdddZdddZdS) ParseResultstrrr r int | Noner r str | Noner r returncCsVd|jr |jdndd|jvrd|jdn|j|jdur'd|jgSdgS)N@:[])joinr r r selfrH/var/www/html/corbot_env/lib/python3.10/site-packages/httpx/_urlparse.pyriszParseResult.authoritycCsBdd|jvrd|jdn|j|jdurd|jgSdgS)Nrrrr)rr r rrrrnetlocsszParseResult.netlockwargscKs:|s|S|j|j|j|j|jd}||tdi|S)Nrrr)rrrr r updateurlparse)rrdefaultsrrr copy_with|s zParseResult.copy_withcCsl|j}d|jr|jdnd|rd|nd|j|jdur$d|jnd|jdur2d|jgSdgS)Nrr//?#)rrrrr r )rrrrr__str__szParseResult.__str__N)rr)rrrr) __name__ __module__ __qualname____annotations__propertyrrr#r'rrrrr`s    rrurlrrrrcKsnt|tkr tdtdd|Drtdd|vr,|d}t|tr(t|n||d<d|vrC|dp6d}|d\|d <}|d<d |vsKd |vrlt |d dpSd}t |d dp]d}|rh|d|n||d <d |vr|d pvd}|d\|d<}|d<|sd|d<d |vr| d pd} d| vr| dr| dsd| d|d <| D]6\} } | durt| tkrtd| dtdd| Drtd| dt| | std| dqt|} | dusJ| } | d| dpd}| d| dpd}| d| dpd}| d| d}| d| d}t|}|dus0J|}| d |d p>d}| d |d pId} | d|d}|}t |tdd}t| }t||}|dk}|dkpx|dkpx|du}t|||d|rt|}t |tdd}|durdnt |tdd}|durdnt |td d}t|||||||S)!Nz URL too longcs"|] }|o | VqdSNisascii isprintable.0charrrr  zurlparse..z,Invalid non-printable ASCII character in URLr rrrr usernamepasswordr raw_pathr%rr rrzURL component 'z ' too longcsr.r/r0r3rrrr6r7z8Invalid non-printable ASCII character in URL component ''zInvalid URL component 'rrr safe) has_scheme has_authorityz:/[]@z:/?[]@z:/?#[]@)lenMAX_URL_LENGTHrany isinstanceintrpop partitionquoteget startswithendswithitemsCOMPONENT_REGEX fullmatch URL_REGEXmatch groupdictAUTHORITY_REGEXlower SUB_DELIMS encode_hostnormalize_port validate_pathnormalize_pathr)r-rr r_r8r9r: seperatorr keyvalue url_matchurl_dictrrrr r authority_matchauthority_dictr parsed_schemeparsed_userinfo parsed_host parsed_portr>r? parsed_path parsed_queryparsed_fragmentrrrr!s       r!r cCs|sdSt|r!zt|W|Stjy td|wt|rGz t|ddWntjy@td|w|ddS|rSt | t dSz t | dWSt jymtd|w) NrzInvalid IPv4 address: rzInvalid IPv6 address: r<asciizInvalid IDNA hostname: )IPv4_STYLE_HOSTNAMErO ipaddress IPv4AddressAddressValueErrorrIPv6_STYLE_HOSTNAME IPv6Addressr1rGrRrSidnaencodedecode IDNAError)r rrrrTs.     rTr str | int | NonerrcCsd|dus|dkr dSzt|}Wntytd|wdddddd|}||kr0dS|S)NrzInvalid port: Pi)ftphttphttpswswss)rD ValueErrorrrH)r r port_as_int default_portrrrrULs   rUrr>boolr?NonecCsR|r|r |dstddSdS|drtd|dr%|s'tddSdS)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$zFURLs with no authority component cannot have a path starting with '//'rzBURLs with no scheme component cannot have a path starting with ':'N)rIr)rr>r?rrrrVgs rVcCsV|d}g}|D]}|dkrq |dkr |r|dgkr|q ||q d|S)z Drop "." and ".." segments from a URL path. For example: normalize_path("/path/./to/somewhere/..") == "/path/to" r.z..r)splitrEappendr)r componentsoutput componentrrrrWs   rWr5cCsddd|dDS)a  Replace a single character with the percent-encoded representation. Characters outside the ASCII range are represented with their a percent-encoded representation of their UTF-8 byte sequence. For example: percent_encode(" ") == "%20" rcSsg|]}d|dqS)%02xr)r4byterrr sz"percent_encode..zutf-8)rrpupper)r5rrrpercent_encodes rrstringr=cCs(t|d}|D] }||vrdSqdS)z< Determine if a given string is already quote-safe. rFT)UNRESERVED_CHARACTERS)rr=NON_ESCAPED_CHARSr5rrris_safes rcs0t||dr|St|dfdd|DS)z1 Use percent-encoding to quote a string. r<rcs g|] }|vr |nt|qSr)rr3rrrrs z#percent_encoded..)rrr)rr=rrrpercent_encodeds rc Csg}d}tt|D]*}||}}|d}||kr-|||}|t||d|||}q |t|krJ||d} |t| |dd |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 rr<Nr) refinditerPERCENT_ENCODED_REGEXstartendgrouprrr@r) rr=partscurrent_positionrOstart_position end_position matched_text leading_text trailing_textrrrrGs       rGrKlist[tuple[str, str]]cCsddd|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 &cSs,g|]\}}t|dddt|ddqS)rr<=)r)r4kvrrrrszurlencode..)r)rKrrr urlencodes rr)r-rrrrr)r rrr)r rsrrrr)rrr>r~r?r~rr)rrrr)r5rrr)r)rrr=rrr~)rrr=rrr)rKrrr) __doc__ __future__rrjrtypingro _exceptionsrrArrScompilerformatrNrQrLrirm NamedTuplerr!rTrUrVrWrrrrGrrrrrsj      7  .      !