U mu fU @sddlmZddlZddlZddlmZddlmZddlmZe dZ ddgdgdgd Z e d Z d d d eeddeddeddDZededejZdZGdddeZGdddZddZGdddejZdS))chainN)unescape) html5lib_shim) parse_shim) aabbracronymb blockquotecodeemiliolstrongulhreftitle)rrr)httphttpsmailtocCsg|] }t|qS)chr).0crr4/tmp/pip-unpacked-wheel-0vx3v32x/bleach/sanitizer.py *sr  []?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||_||_||_||_||_|p$g|_||_tj|j|jddd|_ t d|_ tj ddddddd|_ |dkrg}t|tr|}n4t|trg}|D]} t| ttfr|| qd|krtjd td dS) 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)tagsstripZconsume_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_sanitizerrZBleachHTMLParserparser getTreeWalkerwalkerZBleachHTMLSerializer serializer isinstancelistdictvaluestupleextendwarningswarnr&) selfr+r8r9r,r:r;r<Zattributes_valuesrDrrr__init__VsH&       zCleaner.__init__c Cst|ts&d|jjdd}t||s.dS|j|}t|||j |j |j |j |j |jd}|jD]}||d}qh|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_tagsr8strip_disallowed_tagsstrip_html_commentsr<allowed_protocols)rK)rAstr __class__r' TypeErrorr= parseFragmentBleachSanitizerFilterr?r+r8r,r:r<r9r;r@render)rItextmessagedomfilteredZ filter_classrrrcleans*    z Cleaner.clean) r'r(r)__doc__ ALLOWED_TAGSALLOWED_ATTRIBUTESALLOWED_PROTOCOLSrJrZrrrrr*9s Ur*csLtr Sttr&fdd}|Sttr@fdd}|StddS)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`|kr0|}t|r$||||S||kr0dSdkr\d}t|rT||||S||kSdS)NT*F)callable)tagattrvalueZattr_valr8rr _attr_filters  z.attribute_filter_factory.._attr_filtercs|kSNr)rarbrcrdrrresz3attributes needs to be a callable, a list or a dictN)r`rArCrB ValueError)r8rerrdrattribute_filter_factorys    rhc @sreZdZdZeeeejej ej dddf ddZ ddZ d d Z d d Zd dZddZddZddZddZdS)rTzmhtml5lib 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)rFilterrJ frozensetrLrOrh attr_filterrMrNattr_val_is_urisvg_attr_val_allows_refr<svg_allow_local_href) rIrKrLr8rOrlrmrnrMrNr<rrrrJs0   zBleachSanitizerFilter.__init__ccs:|D]0}||}|sqt|tr.|EdHq|VqdSrf)sanitize_tokenrArB)rItoken_iteratortokenretrrrsanitize_streamAs   z%BleachSanitizerFilter.sanitize_streamccsg}|D]f}|rP|ddkr*||qqhddd|Ddd}g}|Vn|ddkrh||q|Vqddd|Ddd}|VdS) z/Merge consecutive Characters tokens in a streamtype CharactersrcSsg|] }|dqSdatarrZ char_tokenrrrr[sz:BleachSanitizerFilter.merge_characters..)rwrtcSsg|] }|dqSrvrrxrrrrisN)appendjoin)rIrpZcharacters_bufferrq new_tokenrrrmerge_charactersMs*     z&BleachSanitizerFilter.merge_characterscCs||tj|Srf)r|rsrri__iter__)rIrrrr}nszBleachSanitizerFilter.__iter__cCs|d}|dkr>|d|jkr(||S|jr2dS||SnJ|dkrr|jsltj|dddd d |d<|SdSn|d kr||S|SdS) 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 rt)StartTagEndTagEmptyTagnameNCommentrwz"z')"')entitiesru)rL allow_tokenrMdisallowed_tokenrNrescapesanitize_characters)rIrq token_typerrrross$    z$BleachSanitizerFilter.sanitize_tokencCs|dd}|s|Stt|}||d<d|kr4|Sg}t|D]}|sLqB|drt|}|dk r|dkr|dddn|d|d |t |d d}|rB|d|dqB|d|dqB|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 rwr&Nampru)rtrwEntity)rtr) getINVISIBLE_CHARACTERS_REsubINVISIBLE_REPLACEMENT_CHARrZnext_possible_entity startswithZ match_entityrylen)rIrqrwZ new_tokenspartentity remainderrrrrs.    z)BleachSanitizerFilter.sanitize_characterscCst|}tdd|}|dd}|}zt|}Wntk rPYdSX|j rh|j |kr|Sn@| drv|Sd|kr| dd|kr|Sd|ksd |kr|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) rZconvert_entitiesrerreplacelowerrurlparsergschemersplit)rIrcrOZnormalized_uriparsedrrrsanitize_uri_values*    z(BleachSanitizerFilter.sanitize_uri_valuec Csd|kri}|dD]\}}|\}}||d||s     z!BleachSanitizerFilter.allow_tokencCs|d}|dkr&d|dd|d<n|dr|dks:tg}|dD]b\\}}}|rh|sh||}}|dksz|tjkr|}ntj|d|}|d |d |d qJd |dd |d|d<nd |dd|d<|dr|dddd|d<d|d<|d=|S)Nrtrzrw)r~rrrz="rru)AssertionErrorrrprefixesryrzr)rIrqrrnsrvrrrrrZs(    z&BleachSanitizerFilter.disallowed_token)r'r(r)r[r\r]r^rrlrmrnrJrsr|r}rorrrrrrrrrTs&  > !+=:ErT) itertoolsrrrGxml.sax.saxutilsrZbleachrrrjr\r]r^rzrangeZINVISIBLE_CHARACTERScompileUNICODErr UserWarningr&r*rhZSanitizerFilterrTrrrrs.    &+