U grH @sdZddlmZddlZddlZddlZddlZddlmZdZ dZ dZ e d Z d d d ed dDZd dd ed dDZd dd ed dDZd dd ed dDZd dd ed dDZd dd ed dDZe djddddddZe djddddZe de de de de de de de dd Ze d!Ze d"ZGd#d$d$ejZdBd%d&d$d'd(d)Zd%d%d*d+d,Zd-d%d.d/d0d1Z d%d2d2d3d4d5d6Z!d%d%d7d8d9Z"d%d%d:d;d<Z#d%d%d%d=d>d?Z$d%d%d%d=d@dAZ%dS)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}cCsg|]}|dkrt|qS)) "<>`chr.0ir3/tmp/pip-unpacked-wheel-ql4n0x43/httpx/_urlparse.py ,srrcCsg|]}|dkrt|qS))rr#rr r r rrrr2scCsg|]}|dkrt|qS)) rrrrr ?r {}r r rrrr8scCsg|]}|dkrt|qS)rrrrr rr rr/:;=@[\]^|r r rrrrCs cCsg|]}|dkrt|qSrr r rrrrMs cCsg|]}|dkrt|qS))rrrrr rr rrrrrrrrr r!r"r r rrrrZs 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(\[.*\]|[^:]*))r$r%r&r'r(r)r*r+z ^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$z^\[.*\]$c@seZdZUded<ded<ded<ded<ded<ded <ded <edd d d Zedd ddZdddddZdd ddZdS) ParseResultstrr$r)r* int | Noner+r& str | Noner'r()returncCsRd|jr|jdndd|jkr0d|jdn|j|jdk rJd|jndgS)Nr@:[])joinr)r*r+selfrrrr%s zParseResult.authoritycCs>dd|jkrd|jdn|j|jdk r6d|jndgS)Nrr2r3r4)r5r*r+r6rrrnetlocs zParseResult.netloc)kwargsr0cKs6|s|S|j|j|j|j|jd}||td|S)Nr#r)r)r$r%r&r'r(updateurlparse)r7r9defaultsrrr copy_withs zParseResult.copy_withcCsh|j}d|jr|jdnd|r,d|nd|j|jdk rHd|jnd|jdk r`d|jndgS)Nrr2//?#)r%r5r$r&r'r()r7r%rrr__str__szParseResult.__str__N) __name__ __module__ __qualname____annotations__propertyr%r8r=rArrrrr,s  r,r-r/)urlr9r0c"Kst|tkrtdtdd|Dr\tdd|D}||}d|d|d}t|d|kr|d}t|tr~t|n||d<d |kr| d pd }| d \|d <}|d<d |ksd|krt | d d pd t d}t | dd pd t d} | r |d | n||d<d|krR| dp*d } | d\|d<} |d<| sRd|d<d |kr|d pjd } d | kr| dr| dsd| d|d <|D]\} }|dk rt|tkrtd| dtdd|Dr&tdd|D}||}d| d|d|d}t|t| |std| dqt|}|dk sbt|}|d|dp~d }|d |d pd }|d|dpd }|d|d}|d!|d!}t|}|dk st|}|d|dpd }|d |d pd } |d|d}|}t |td}t| }t||}|d k}|d kpp|d kpp|dk }t|||d"|s|rt|}t |td}|dkrdn t |t d} |dkrdn t |t!d}!t"|||||| |!S)#Nz URL too longcss |]}|o| VqdSNisascii isprintablercharrrr szurlparse..css"|]}|r|s|VqdSrHrIrLrrrrNsz.Invalid non-printable ASCII character in URL, z at position .r+r8rr2r*usernamepasswordsafer)raw_pathr?r&r'r3r4zURL component 'z ' too longcss |]}|o| VqdSrHrIrLrrrrNscss"|]}|r|s|VqdSrHrIrLrrrrNsz-Invalid non-printable ASCII character in URL z component, zInvalid URL component ''r$r%r() has_scheme has_authority)#lenMAX_URL_LENGTHranynextfind isinstanceintr-pop partitionquote USERNAME_SAFE PASSWORD_SAFEget startswithendswithitemsCOMPONENT_REGEX fullmatch URL_REGEXmatchAssertionError groupdictAUTHORITY_REGEXlower USERINFO_SAFE encode_hostnormalize_port validate_pathnormalize_path PATH_SAFE QUERY_SAFE FRAG_SAFEr,)"rGr9rMidxerrorr+r8_rPrQrTZ seperatorr*keyvalueZ url_matchZurl_dictr$r%r&r'fragZauthority_matchZauthority_dictr)Z parsed_schemeZparsed_userinfoZ parsed_hostZ parsed_portrVrWZ parsed_pathZ parsed_queryZ parsed_fragrrrr;s    "        r;)r*r0cCs|sdSt|rJzt|Wn$tjk rDtd|YnX|St|rzt|ddWn$tjk rtd|YnX|ddS|rd}t | t |dSzt | dWSt jk rtd |YnXdS) NrzInvalid IPv4 address: rzInvalid IPv6 address: z"`{}%|\rRasciizInvalid IDNA hostname: )IPv4_STYLE_HOSTNAMErk ipaddress IPv4AddressAddressValueErrorrIPv6_STYLE_HOSTNAME IPv6AddressrJraro SUB_DELIMSidnaencodedecode IDNAError)r*Z WHATWG_SAFErrrrq\s*   rqzstr | int | Noner.)r+r$r0cCsj|dks|dkrdSz t|}Wn"tk rBtd|YnXdddddd|}||krfdS|S)NrzInvalid port: Pi)ftphttphttpswswss)r^ ValueErrorrrd)r+r$Z port_as_int default_portrrrrrs  rrboolNone)r&rVrWr0cCsJ|r|r|dstd|sF|sF|dr4td|drFtddS)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 '//'r2z2Relative URLs cannot have a path starting with ':'N)rer)r&rVrWrrrrss  rs)r&r0cCsvd|kr |S|d}d|kr*d|kr*|Sg}|D]8}|dkr@q2|dkr`|rj|dgkrj|q2||q2d|S)z Drop "." and ".." segments from a URL path. For example: normalize_path("/path/./to/somewhere/..") == "/path/to" rOrz..r)splitr_appendr5)r& componentsoutput componentrrrrts    rt)stringr0cCsddd|dDS)NrcSsg|]}d|dqS)%Z02Xr)rbyterrrrszPERCENT..zutf-8)r5r)rrrrPERCENTsr)rrSr0cs.t||s|Sdfdd|DS)z1 Use percent-encoding to quote a string. rcs g|]}|kr|nt|qSr)rrLZNON_ESCAPED_CHARSrrrsz#percent_encoded..)UNRESERVED_CHARACTERSrstripr5)rrSrrrpercent_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 rrRNr) refinditerPERCENT_ENCODED_REGEXstartendgrouprrrXr5) rrSpartscurrent_positionrkZstart_positionZ end_positionZ matched_textZ leading_textZ trailing_textrrrras      ra)r)&__doc__ __future__rrrtypingr _exceptionsrrYrrcompilerr5rangerwrvrurbrcrpformatrjrnrhrr NamedTupler,r;rqrrrsrtrrrarrrrs        7/