o Zh0h&@sldZddlZddlZddlZddlZddlZddlZddlZddl m Z ddl m Z ddl mZmZmZmZddlmZmZmZddlmZdd lmZed Zed ZeZz eej d kred ZWn e!yqd ZYnwdedddZ"Gddde Z#ddZ$ddZ%ddZ&d*ddZ'ddZ(dd Z)d!d"Z*d+d$d%Z+Gd&d'd'e,Z-ej.d(d)Z/dS),z9Various utility functions and classes for URL management.N)GzipFile)Path)quoteunquoteurljoinurlsplit)Request pathname2urlurlopen) __version__)LOGGERz^([a-zA-Z][a-zA-Z0-9.+-]+):s^([a-zA-Z][a-zA-Z0-9.+-]+):asciiutf-8z WeasyPrint z*/*z gzip, deflate)z User-AgentAcceptzAccept-Encodingc@s$eZdZddZddZddZdS)StreamingGzipFilecCstj||d||_dS)Nfileobj)r__init__fileobj_to_close)selfrrE/var/www/html/rh/venv/lib/python3.10/site-packages/weasyprint/urls.pyr(s zStreamingGzipFile.__init__cCst||jdS)N)rcloserrrrrr,s zStreamingGzipFile.closecCsdS)NFrrrrrseekable0szStreamingGzipFile.seekableN)__name__ __module__ __qualname__rrrrrrrr's rcCs2|dr|S||drtnd}t|ddS)zDTurn a Unicode IRI into an ASCII-only URI that conforms to RFC 3986.zdata:file:rs/:?#[]@!$&'()*+,;=~%)safe) startswithencodeFILESYSTEM_ENCODINGr)urlrrr iri_to_uri4s  r%cCst|tr t|}n t|tr|t}|tjj p|d}tj |}|s.tj |r6|tjj 7}d}t |}|rE|dsE|d7}| drOd|Sd|S)zVReturn file URL of `path`. Accepts 'str', 'bytes' or 'Path', returns 'str'. /Tz///rfile://) isinstancerstrbytesdecoder#endswithospathsepabspathisdirr r!)r.wants_trailing_slashrrrpath2urlEs         r3cCs t|trtnt}t||S)z4Return whether an URL (bytes or string) is absolute.)r(r)UNICODE_SCHEME_REBYTES_SCHEME_REboolmatch)r$schemerrrurl_is_absolutedsr9FcCs4||d}|rt|pd||d|j||fSdS)a'Get the URI corresponding to the ``attr_name`` attribute. Return ``None`` if: * the attribute is empty or missing or, * the value is a relative URI but the document has no base URI and ``allow_relative`` is ``False``. Otherwise return an URI, absolute if possible. z <%s %s="%s">N)getstripurl_jointag)element attr_namebase_urlallow_relativevaluerrrget_url_attributejs   rDcCsJt|rt|S|rtt||S|rt|Stjd|g|RdS)zBLike urllib.urljoin, but warn if base_url is required but missing.z+Relative URI reference without a base URI: N)r9r%rr error)rAr$rBcontext context_argsrrrr=}sr=cCs||d}|drt|dkrddt|ddffSt|||dd}|ru|rozt|}Wnty@t d |Yn/wzt|}WntyVt d |Ynw|j ro|dd |dd kroddt|j ffSdd |ffSdS) zGet the URL value of an element attribute. Return ``('external', absolute_uri)``, or ``('internal', unquoted_fragment_id)``, or ``None``. r:#r r$internalNT)rBzMalformed URL: %szMalformed base URL: %sexternal) r;r<r!lenrrDr ValueErrorr warningfragment)r?r@rA attr_valueuriparsed parsed_baserrrget_link_attributes(     rTcCst|r|St|S)zGet a ``scheme://path`` URL from ``string``. If ``string`` looks like an URL, return it unchanged. Otherwise assume a filename and convert it to a ``file://`` URL. )r9r3)stringrrr ensure_urlsrV cCst|rr|dr|dd}t|}tt|td||d}|}| | | d| d}| d}|d krFt|d |d <|S|d krl|}z t||d <W|Stjykt|d|d <Y|Sw||d <|Std|)uFetch an external resource such as an image or stylesheet. Another callable with the same signature can be given as the ``url_fetcher`` argument to :class:`HTML` or :class:`CSS`. (See :ref:`URL Fetchers`.) :param str url: The URL of the resource to fetch. :param int timeout: The number of seconds before HTTP requests are dropped. :param ssl.SSLContext ssl_context: An SSL context used for HTTP requests. :raises: An exception indicating failure, e.g. :obj:`ValueError` on syntactically invalid URL. :returns: A :obj:`dict` with the following keys: * One of ``string`` (a :obj:`bytestring `) or ``file_obj`` (a :term:`file object`). * Optionally: ``mime_type``, a MIME type extracted e.g. from a *Content-Type* header. If not provided, the type is guessed from the file extension in the URL. * Optionally: ``encoding``, a character encoding extracted e.g. from a *charset* parameter in a *Content-Type* header * Optionally: ``redirected_url``, the actual URL of the resource if there were e.g. HTTP redirects. * Optionally: ``filename``, the filename of the resource. Usually derived from the *filename* parameter in a *Content-Disposition* header If a ``file_obj`` key is given, it is the caller’s responsibility to call ``file_obj.close()``. The default function used internally to fetch data in WeasyPrint tries to close the file object after retreiving; but if this URL fetcher is used elsewhere, the file object has to be closed manually. r'?r)headers)timeoutrFcharset)redirected_url mime_typeencodingfilenamezContent-Encodinggziprfile_objdeflaterUizNot an absolute URI: %r)r4r7r!splitr%r r HTTP_HEADERSinfogeturlget_content_type get_param get_filenamer;rreadzlib decompressrErM)r$rZ ssl_contextresponse response_inforesultcontent_encodingdatarrrdefault_url_fetchers< %     rsc@seZdZdZdS)URLFetchingErrorz)Some error happened when fetching an URL.N)rrr__doc__rrrrrtsrtccsz||}Wnty}z tt|jd|d}~ww|d||ddd|vrmz!|VWz |dWdStyQtd|t YdSwz|dWwtyltd|t Yww|VdS)z9Call an url_fetcher, fill in optional data, and clean up.z: Nr\r]raz$Error when closing stream for %s: %s) Exceptionrttyper setdefaultrr rN traceback format_exc) url_fetcherr$rp exceptionrrrfetchs:       r})F)rWN)0rucodecs contextlibos.pathr-resysryrkr`rpathlibr urllib.parserrrrurllib.requestrr r r:r loggerr compiler4r5getfilesystemencodingr#lookupname LookupErrorrdrr%r3r9rDr=rTrVrsIOErrorrtcontextmanagerr}rrrrsP          F