U {f8E @sdZddlmZddlZddlZddlZddlZddlmZdZ dZ dZ e d Z e d jd d d dddZe djddddZe d e d e d e de de de de ddZe dZe dZGdddejZd@dddddd Zddd!d"d#Zd$dd%d&d'd(Zdd)d)d*d+d,d-Zddd.d/d0Zddd1d2d3ZdAddd)d5d6d7ZdBdddd5d8d9ZdCdddd5d:d;Zdd?ZdS)Da An implementation of `urlparse` that provides URL validation and normalization as described by RFC3986. We rely on this implementation rather than the one in Python's stdlib, because: * It provides more complete URL validation. * It properly differentiates between an empty querystring and an absent querystring, to distinguish URLs with a trailing '?'. * It handles scheme, hostname, port, and path normalization. * It supports IDNA hostnames, normalizing them to their encoded form. * The API supports passing individual components, as well as the complete URL string. Previously we relied on the excellent `rfc3986` package to handle URL parsing and validation, but this module provides a simpler alternative, with less indirection required. ) annotationsN) InvalidURLizBABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~z !$&'()*+,;=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^\[.*\]$c@seZdZUded<ded<ded<ded<ded<ded <ded <edd d d Zedd ddZdddddZdd ddZdS) ParseResultstrrr r int | Noner r str | Noner r )returncCsRd|jr|jdndd|jkr0d|jdn|j|jdk rJd|jndgS)N@:[])joinr r r selfrN/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/httpx/_urlparse.pyris zParseResult.authoritycCs>dd|jkrd|jdn|j|jdk r6d|jndgS)Nrrrr)rr r rrrrnetlocss zParseResult.netloc)kwargsrcKs6|s|S|j|j|j|j|jd}||td|S)Nrr)r)rrrr r updateurlparse)rrdefaultsrrr copy_with|s zParseResult.copy_withcCsh|j}d|jr|jdnd|r,d|nd|j|jdk rHd|jnd|jdk r`d|jndgS)Nrr//?#)rrrrr r )rrrrr__str__szParseResult.__str__N) __name__ __module__ __qualname____annotations__propertyrrr"r&rrrrr`s  rrrr)urlrrcKst|tkrtdtdd|Dr.tdd|krX|d}t|trPt|n||d<d|kr|dpld}|d\|d <}|d<d |ksd |krt |d dpd}t |d dpd}|r|d|n||d <d |kr|d pd}|d\|d<}|d<|sd|d<d |krb| d p.d} d| krb| drR| dsbd| d|d <| D]v\} } | dk rjt| tkrtd| dtdd| Drtd| dt| | sjtd| dqjt|} | dk st| } | d| dpd}| d| dp,d}| d| dpBd}| d| d}| d| d}t|}|dk s|t|}| d |d pd}| d |d pd} | d|d}|}t |tdd}t| }t||}|dk}|dkp |dkp |dk }t|||d|r*t|}t |tdd}|dkrHdnt |tdd}|dkrfdnt |td d}t|||||||S)!Nz URL too longcss |]}|o| VqdSNisascii isprintable.0charrrr szurlparse..z,Invalid non-printable ASCII character in URLr rrrr usernamepasswordr raw_pathr$rr rrzURL component 'z ' too longcss |]}|o| VqdSr-r.r1rrrr4sz8Invalid 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_REGEXmatchAssertionError groupdictAUTHORITY_REGEXlower SUB_DELIMS encode_hostnormalize_port validate_pathnormalize_pathr)r,rr r_r5r6r7Z seperatorr keyvalueZ url_matchZurl_dictrrrr r Zauthority_matchZauthority_dictr Z parsed_schemeZparsed_userinfo parsed_host parsed_portr;r<Z parsed_pathZ parsed_queryZparsed_fragmentrrrr s   "     r )r rcCs|sdSt|rJzt|Wn$tjk rDtd|YnX|St|rzt|ddWn$tjk rtd|YnX|ddS|rt | t dSzt | dWSt jk rtd|YnXdS) NrzInvalid IPv4 address: rzInvalid IPv6 address: r9asciizInvalid IDNA hostname: )IPv4_STYLE_HOSTNAMErL ipaddress IPv4AddressAddressValueErrorrIPv6_STYLE_HOSTNAME IPv6Addressr/rDrPrQidnaencodedecode IDNAError)r rrrrRs(   rRzstr | int | Noner)r rrcCsj|dks|dkrdSz t|}Wn"tk rBtd|YnXdddddd|}||krfdS|S)NrzInvalid port: Pi)ftphttphttpswswss)rA ValueErrorrrE)r rZ port_as_int default_portrrrrSLs  rSboolNone)rr;r<rcCsH|r|rD|dsDtdn(|dr.td|drD|sDtddS)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)rFr)rr;r<rrrrTgs  rT)rrcCsV|d}g}|D]8}|dkr q|dkr@|rJ|dgkrJ|q||qd|S)z Drop "." and ".." segments from a URL path. For example: normalize_path("/path/./to/somewhere/..") == "/path/to" rr.z..r)splitrBappendr)r componentsoutput componentrrrrUs   rU)r3rcCsddd|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)r2byterrr sz"percent_encode..zutf-8)rrdupper)r3rrrpercent_encodes r~rr)stringr:rcCs(t|d}|D]}||krdSqdS)z< Determine if a given string is already quote-safe. ryFT)UNRESERVED_CHARACTERS)rr:NON_ESCAPED_CHARSr3rrris_safes  rcs0t||dr|St|dfdd|DS)z1 Use percent-encoding to quote a string. r9rcs g|]}|kr|nt|qSr)r~r1rrrr|sz#percent_encoded..)rrr)rr:rrrpercent_encodeds  rc Csg}d}tt|D]T}||}}|d}||krZ|||}|t||d|||}q|t|kr||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 rr9Nr) refinditerPERCENT_ENCODED_REGEXstartendgrouprurr=r) rr:partscurrent_positionrLZstart_positionZ end_positionZ matched_textZ leading_textZ trailing_textrrrrDs      rDzlist[tuple[str, str]])rHrcCsddd|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)rr9=)r)r2kvrrrr|szurlencode..)r)rHrrr urlencodes r)r)rr)rr)rr) __doc__ __future__rr^rtypingrc _exceptionsrr>rrQcompilerformatrKrOrIr]ra NamedTuplerr rRrSrTrUr~rrrDrrrrrsh     7. !