o eU @sddlmZddlZddlZddlmZddlmZddlmZe dZ ddgdgdgd Z e d Z d d d eeddeddeddDZededejZdZGdddeZGdddZddZGdddejZdS))chainN)unescape) html5lib_shim) parse_shim) aabbracronymb blockquotecodeemiliolstrongulhreftitle)rrr)httphttpsmailtocCsg|]}t|qS)chr).0crrC/var/www/html/venv/lib/python3.10/site-packages/bleach/sanitizer.py *r  []?c@s eZdZdS)NoCssSanitizerWarningN)__name__ __module__ __qualname__rrrrr'5sr'c@s0eZdZdZeeeddddfddZddZdS) CleaneraCleaner for cleaning HTML fragments of malicious content This cleaner is a security-focused function whose sole purpose is to remove malicious content from a string such that it can be displayed as content in a web page. To use:: from bleach.sanitizer import Cleaner cleaner = Cleaner() for text in all_the_yucky_things: sanitized = cleaner.clean(text) .. Note:: This cleaner is not designed to use to transform content to be used in non-web-page contexts. .. Warning:: This cleaner is not thread-safe--the html parser has internal state. Create a separate cleaner per thread! FTNc Cs||_||_||_||_||_|pg|_||_tj|j|jddd|_ t d|_ tj ddddddd|_ |durjg}t|trC|}nt|tr]g}|D]} t| ttfr\|| qNd|vrltjd td dSdSdS) a:Initializes a Cleaner :arg set tags: set of allowed tags; defaults to ``bleach.sanitizer.ALLOWED_TAGS`` :arg dict attributes: allowed attributes; can be a callable, list or dict; defaults to ``bleach.sanitizer.ALLOWED_ATTRIBUTES`` :arg list protocols: allowed list of protocols for links; defaults to ``bleach.sanitizer.ALLOWED_PROTOCOLS`` :arg bool strip: whether or not to strip disallowed elements :arg bool strip_comments: whether or not to strip HTML comments :arg list filters: list of html5lib Filter classes to pass streamed content through .. seealso:: http://html5lib.readthedocs.io/en/latest/movingparts.html#filters .. Warning:: Using filters changes the output of ``bleach.Cleaner.clean``. Make sure the way the filters change the output are secure. :arg CSSSanitizer css_sanitizer: instance with a "sanitize_css" method for sanitizing style attribute values and style text; defaults to None F)tagsstripconsume_entitiesnamespaceHTMLElementsetreealwaysT)quote_attr_valuesomit_optional_tagsescape_lt_in_attrsresolve_entitiessanitizealphabetical_attributesNstylez7'style' attribute specified, but css_sanitizer not set.)category)r, attributes protocolsr-strip_commentsfilters css_sanitizerrBleachHTMLParserparser getTreeWalkerwalkerBleachHTMLSerializer serializer isinstancelistdictvaluestupleextendwarningswarnr') selfr,r:r;r-r<r=r>attributes_valuesrHrrr__init__VsN&         zCleaner.__init__c Cst|tsd|jjdd}t||sdS|j|}t|||j |j |j |j |j |jd}|jD]}||d}q4|j|S)zCleans text and returns sanitized result as unicode :arg str text: text to be cleaned :returns: sanitized text as unicode :raises TypeError: if ``text`` is not a text type zargument cannot be of z type, zmust be of text typer)source allowed_tagsr:strip_disallowed_tagsstrip_html_commentsr>allowed_protocols)rP)rEstr __class__r( TypeErrorr@ parseFragmentBleachSanitizerFilterrBr,r:r-r<r>r;r=rDrender)rMtextmessagedomfiltered filter_classrrrcleans*    z Cleaner.clean) r(r)r*__doc__ ALLOWED_TAGSALLOWED_ATTRIBUTESALLOWED_PROTOCOLSrOr`rrrrr+9s Ur+csHtrSttrfdd}|Sttr fdd}|Std)a0Generates attribute filter function for the given attributes value The attributes value can take one of several shapes. This returns a filter function appropriate to the attributes value. One nice thing about this is that there's less if/then shenanigans in the ``allow_token`` method. cs`|vr|}t|r||||S||vrdSdvr.d}t|r*||||S||vSdS)NT*F)callable)tagattrvalueattr_valr:rr _attr_filters  z.attribute_filter_factory.._attr_filtercs|vSNr)rgrhrirkrrrlsz3attributes needs to be a callable, a list or a dict)rfrErGrF ValueError)r:rlrrkrattribute_filter_factorys    roc @sreZdZdZeeeejej ej dddf ddZ ddZ d d Z d d Zd dZddZddZddZddZdS)rYzmhtml5lib Filter that sanitizes text This filter can be used anywhere html5lib filters can be used. FTNc CsTtj||t||_t||_t||_||_| |_ ||_ ||_ | |_ ||_ dS)a_Creates a BleachSanitizerFilter instance :arg source: html5lib TreeWalker stream as an html5lib TreeWalker :arg set allowed_tags: set of allowed tags; defaults to ``bleach.sanitizer.ALLOWED_TAGS`` :arg dict attributes: allowed attributes; can be a callable, list or dict; defaults to ``bleach.sanitizer.ALLOWED_ATTRIBUTES`` :arg list allowed_protocols: allowed list of protocols for links; defaults to ``bleach.sanitizer.ALLOWED_PROTOCOLS`` :arg attr_val_is_uri: set of attributes that have URI values :arg svg_attr_val_allows_ref: set of SVG attributes that can have references :arg svg_allow_local_href: set of SVG elements that can have local hrefs :arg bool strip_disallowed_tags: whether or not to strip disallowed tags :arg bool strip_html_comments: whether or not to strip HTML comments :arg CSSSanitizer css_sanitizer: instance with a "sanitize_css" method for sanitizing style attribute values and style text; defaults to None N)rFilterrO frozensetrQrTro attr_filterrRrSattr_val_is_urisvg_attr_val_allows_refr>svg_allow_local_href) rMrPrQr:rTrsrtrurRrSr>rrrrOs0    zBleachSanitizerFilter.__init__ccs<|D]}||}|s qt|tr|EdHq|VqdSrm)sanitize_tokenrErF)rMtoken_iteratortokenretrrrsanitize_streamAs   z%BleachSanitizerFilter.sanitize_streamccsg}|D]2}|r(|ddkr||qddd|Ddd}g}|Vn |ddkr4||q|Vqddd|Ddd}|VdS) z/Merge consecutive Characters tokens in a streamtype CharactersrcSg|]}|dqSdatarr char_tokenrrrr[rz:BleachSanitizerFilter.merge_characters..)rr{cSr}r~rrrrrrirN)appendjoin)rMrwcharacters_bufferrx new_tokenrrrmerge_charactersMs,      z&BleachSanitizerFilter.merge_characterscCs||tj|Srm)rrzrrp__iter__)rMrrrrnszBleachSanitizerFilter.__iter__cCs|d}|dvr|d|jvr||S|jrdS||S|dkr7|js5tj|dddd d |d<|SdS|d kr@||S|S) aSanitize a token either by HTML-encoding or dropping. Unlike sanitizer.Filter, allowed_attributes can be a dict of {'tag': ['attribute', 'pairs'], 'tag': callable}. Here callable is a function with two arguments of attribute name and value. It should return true of false. Also gives the option to strip tags instead of encoding. :arg dict token: token to sanitize :returns: token or list of tokens r{)StartTagEndTagEmptyTagnameNCommentrz"z')"')entitiesr|)rQ allow_tokenrRdisallowed_tokenrSrescapesanitize_characters)rMrx token_typerrrrvss"    z$BleachSanitizerFilter.sanitize_tokencCs|dd}|s |Stt|}||d<d|vr|Sg}t|D]E}|s&q!|dr^t|}|dur^|dkrA|dddn|d|d |t |d d}|r]|d|dq!|d|dq!|S) aHandles Characters tokens Our overridden tokenizer doesn't do anything with entities. However, that means that the serializer will convert all ``&`` in Characters tokens to ``&``. Since we don't want that, we extract entities here and convert them to Entity tokens so the serializer will let them be. :arg token: the Characters token to work on :returns: a list of tokens rr&Nampr|)r{rEntity)r{r) getINVISIBLE_CHARACTERS_REsubINVISIBLE_REPLACEMENT_CHARrnext_possible_entity startswith match_entityrlen)rMrxr new_tokenspartentity remainderrrrrs.    z)BleachSanitizerFilter.sanitize_characterscCst|}tdd|}|dd}|}zt|}Wn ty'YdSw|j r4|j |vr2|SdS| dr;|Sd|vrJ| dd|vrJ|Sd|vsRd |vrT|SdS) zChecks a uri value to see if it's allowed :arg value: the uri value to sanitize :arg allowed_protocols: list of allowed protocols :returns: allowed value or None z[`\000-\040\177-\240\s]+ru�N#:rrr) rconvert_entitiesrerreplacelowerrurlparsernschemersplit)rMrirTnormalized_uriparsedrrrsanitize_uri_values*     z(BleachSanitizerFilter.sanitize_uri_valuec Csd|vr|i}|dD]k\}}|\}}||d||sq ||jvr1|||j}|dur/q |}||jvrHtddt|}| }|sFq |}d|df|j vrc|dt j ddffvrct d |rcq |d krs|jrq|j|}nd }|||<q ||d<|S) z-Handles the case where we're allowing the tagrrNzurl\s*\(\s*[^#\s][^)]+?\) )Nrxlinkrz ^\s*[^#\s])Nr8r)itemsrrrsrrTrtrrrr-rur namespacessearchr> sanitize_css) rMrxattrsnamespaced_nameval namespacer new_valuenew_valrrrrs>     z!BleachSanitizerFilter.allow_tokencCs|d}|dkrd|dd|d<n^|drg|dvsJg}|dD]1\\}}}|r4|s4||}}|dus=|tjvr@|}n tj|d|}|d |d |d q%d |dd |d|d<n d |dd|d<|dr|dddd|d<d|d<|d=|S)Nr{rzr)rrrrz="rr|)rrprefixesrrr)rMrxrrnsrvrrrrrZs(    z&BleachSanitizerFilter.disallowed_token)r(r)r*rarbrcrdrrsrtrurOrzrrrvrrrrrrrrrYs(  > !+=: ErY) itertoolsrrrKxml.sax.saxutilsrbleachrrrqrbrcrdrrangeINVISIBLE_CHARACTERScompileUNICODErr UserWarningr'r+roSanitizerFilterrYrrrrs0    &+