now has + both span tags closed. +- Various HTMLPurifier_Config convenience functions now accept another parameter + $schema which defines what HTMLPurifier_ConfigSchema to use besides the + global default. +- Fix bug with trusted script handling in libxml versions later than 2.6.28. +- Fix bug in ExtractStyleBlocks with comments in style tags +- Fix bug in comment parsing for DirectLex +- Flush output now displayed when in command line mode for unit tester +- Fix bug with rgb(0, 1, 2) color syntax with spaces inside shorthand syntax +- HTMLPurifier_HTMLDefinition->addAttribute can now be called multiple times + on the same element without emitting errors. +- Fixed fatal error in PH5P lexer with invalid tag names +. Plugins now get their own changelogs according to project conventions. +. Convert tokens to use instanceof, reducing memory footprint and + improving comparison speed. +. Dry runs now supported in SimpleTest; testing facilities improved +. Bootstrap class added for handling autoloading functionality +. Implemented recursive glob at FSTools->globr +. ConfigSchema now has instance methods for all corresponding define* + static methods. +. A couple of new historical maintenance scripts were added. +. HTMLPurifier/HTMLModule/Tidy/XHTMLAndHTML4.php split into two files +. tests/index.php can now be run from any directory. +. HTMLPurifier_Token subclasses split into seperate files +. HTMLPURIFIER_PREFIX now is defined in Bootstrap.php, NOT HTMLPurifier.php +. HTMLPURIFIER_PREFIX can now be defined outside of HTML Purifier +. New --php=php flag added, allows PHP executable to be specified (command + line only!) +. htmlpurifier_add_test() preferred method to translate test files in to + classes, because it handles PHPT files too. +. Debugger class is deprecated and will be removed soon. +. Command line argument parsing for testing scripts revamped, now --opt value + format is supported. +. Smoketests now cleanup after magic quotes +. Generator now can output comments (however, comments are still stripped + from HTML Purifier output) +. HTMLPurifier_ConfigSchema->validate() deprecated in favor of + HTMLPurifier_VarParser->parse() +. Integers auto-cast into float type by VarParser. +. HTMLPURIFIER_STRICT removed; no validation is performed on runtime, only + during cache generation +. Reordered script calls in maintenance/flush.php +. Command line scripts now honor exit codes +. When --flush fails in unit testers, abort tests and print message +. Improved documentation in docs/dev-flush.html about the maintenance scripts +. copy() methods removed in favor of clone keyword + +3.0.0, released 2008-01-06 +# HTML Purifier is PHP 5 only! The 2.1.x branch will be maintained + until PHP 4 is completely deprecated, but no new features will be added + to it. + + Visibility declarations added + + Constructor methods renamed to __construct() + + PHP4 reference cruft removed (in progress) +! CSS properties are now case-insensitive +! DefinitionCacheFactory now can register new implementations +! New HTMLPurifier_Filter_ExtractStyleBlocks for extracting Some text'; + + $config = HTMLPurifier_Config::createDefault(); + $config->set('Filter', 'ExtractStyleBlocks', true); + $purifier = new HTMLPurifier($config); + + $html = $purifier->purify($dirty); + + // This implementation writes the stylesheets to the styles/ directory. + // You can also echo the styles inside the document, but it's a bit + // more difficult to make sure they get interpreted properly by + // browsers; try the usual CSS armoring techniques. + $styles = $purifier->context->get('StyleBlocks'); + $dir = 'styles/'; + if (!is_dir($dir)) mkdir($dir); + $hash = sha1($_GET['html']); + foreach ($styles as $i => $style) { + file_put_contents($name = $dir . $hash . "_$i"); + echo ''; + } +?> + + +

+ +

+ + +]]> +

+ Warning: It is possible for a user to mount an + imagecrash attack using this CSS. Counter-measures are difficult; + it is not simply enough to limit the range of CSS lengths (using + relative lengths with many nesting levels allows for large values + to be attained without actually specifying them in the stylesheet), + and the flexible nature of selectors makes it difficult to selectively + disable lengths on image tags (HTML Purifier, however, does disable + CSS width and height in inline styling). There are probably two effective + counter measures: an explicit width and height set to auto in all + images in your document (unlikely) or the disabling of width and + height (somewhat reasonable). Whether or not these measures should be + used is left to the reader. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt new file mode 100644 index 0000000000..321eaa2d80 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Filter.YouTube.txt @@ -0,0 +1,16 @@ +Filter.YouTube +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ Warning: Deprecated in favor of %HTML.SafeObject and + %Output.FlashCompat (turn both on to allow YouTube videos and other + Flash content). +

+ This directive enables YouTube video embedding in HTML Purifier. Check + this document + on embedding videos for more information on what this filter does. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt new file mode 100644 index 0000000000..0b2c106da5 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt @@ -0,0 +1,25 @@ +HTML.Allowed +TYPE: itext/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ This is a preferred convenience directive that combines + %HTML.AllowedElements and %HTML.AllowedAttributes. + Specify elements and attributes that are allowed using: + element1[attr1|attr2],element2.... For example, + if you would like to only allow paragraphs and links, specify + a[href],p. You can specify attributes that apply + to all elements using an asterisk, e.g. *[lang]. + You can also use newlines instead of commas to separate elements. +

+ Warning: + All of the constraints on the component directives are still enforced. + The syntax is a subset of TinyMCE's valid_elements + whitelist: directly copy-pasting it here will probably result in + broken whitelists. If %HTML.AllowedElements or %HTML.AllowedAttributes + are set, this directive has no effect. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt new file mode 100644 index 0000000000..fcf093f17d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt @@ -0,0 +1,19 @@ +HTML.AllowedAttributes +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ If HTML Purifier's attribute set is unsatisfactory, overload it! + The syntax is "tag.attr" or "*.attr" for the global attributes + (style, id, class, dir, lang, xml:lang). +

+ Warning: If another directive conflicts with the + elements here, that directive will win and override. For + example, %HTML.EnableAttrID will take precedence over *.id in this + directive. You must set that directive to true before you can use + IDs at all. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt new file mode 100644 index 0000000000..140e21423e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedComments.txt @@ -0,0 +1,10 @@ +HTML.AllowedComments +TYPE: lookup +VERSION: 4.4.0 +DEFAULT: array() +--DESCRIPTION-- +A whitelist which indicates what explicit comment bodies should be +allowed, modulo leading and trailing whitespace. See also %HTML.AllowedCommentsRegexp +(these directives are union'ed together, so a comment is considered +valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt new file mode 100644 index 0000000000..f22e977d43 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedCommentsRegexp.txt @@ -0,0 +1,15 @@ +HTML.AllowedCommentsRegexp +TYPE: string/null +VERSION: 4.4.0 +DEFAULT: NULL +--DESCRIPTION-- +A regexp, which if it matches the body of a comment, indicates that +it should be allowed. Trailing and leading spaces are removed prior +to running this regular expression. +Warning: Make sure you specify +correct anchor metacharacters ^regex$, otherwise you may accept +comments that you did not mean to! In particular, the regex /foo|bar/ +is probably not sufficiently strict, since it also allows foobar. +See also %HTML.AllowedComments (these directives are union'ed together, +so a comment is considered valid if any directive deems it valid.) +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt new file mode 100644 index 0000000000..1d3fa7907d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt @@ -0,0 +1,23 @@ +HTML.AllowedElements +TYPE: lookup/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- +

+ If HTML Purifier's tag set is unsatisfactory for your needs, you can + overload it with your own list of tags to allow. If you change + this, you probably also want to change %HTML.AllowedAttributes; see + also %HTML.Allowed which lets you set allowed elements and + attributes at the same time. +

+ If you attempt to allow an element that HTML Purifier does not know + about, HTML Purifier will raise an error. You will need to manually + tell HTML Purifier about this element by using the + advanced customization features. +

+ Warning: If another directive conflicts with the + elements here, that directive will win and override. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt new file mode 100644 index 0000000000..5a59a55c08 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt @@ -0,0 +1,20 @@ +HTML.AllowedModules +TYPE: lookup/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ A doctype comes with a set of usual modules to use. Without having + to mucking about with the doctypes, you can quickly activate or + disable these modules by specifying which modules you wish to allow + with this directive. This is most useful for unit testing specific + modules, although end users may find it useful for their own ends. +

+ If you specify a module that does not exist, the manager will silently + fail to use it, so be careful! User-defined modules are not affected + by this directive. Modules defined in %HTML.CoreModules are not + affected by this directive. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt new file mode 100644 index 0000000000..151fb7b826 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Attr.Name.UseCDATA.txt @@ -0,0 +1,11 @@ +HTML.Attr.Name.UseCDATA +TYPE: bool +DEFAULT: false +VERSION: 4.0.0 +--DESCRIPTION-- +The W3C specification DTD defines the name attribute to be CDATA, not ID, due +to limitations of DTD. In certain documents, this relaxed behavior is desired, +whether it is to specify duplicate names, or to specify names that would be +illegal IDs (for example, names that begin with a digit.) Set this configuration +directive to true to use the relaxed parsing rules. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt new file mode 100644 index 0000000000..45ae469ec9 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt @@ -0,0 +1,18 @@ +HTML.BlockWrapper +TYPE: string +VERSION: 1.3.0 +DEFAULT: 'p' +--DESCRIPTION-- + +

+ String name of element to wrap inline elements that are inside a block + context. This only occurs in the children of blockquote in strict mode. +

+ Example: by default value, + <blockquote>Foo</blockquote> would become + <blockquote><p>Foo</p></blockquote>. + The <p> tags can be replaced with whatever you desire, + as long as it is a block level element. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt new file mode 100644 index 0000000000..5246188795 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt @@ -0,0 +1,23 @@ +HTML.CoreModules +TYPE: lookup +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'Structure' => true, + 'Text' => true, + 'Hypertext' => true, + 'List' => true, + 'NonXMLCommonAttributes' => true, + 'XMLCommonAttributes' => true, + 'CommonAttributes' => true, +) +--DESCRIPTION-- + +

+ Certain modularized doctypes (XHTML, namely), have certain modules + that must be included for the doctype to be an conforming document + type: put those modules here. By default, XHTML's core modules + are used. You can set this to a blank array to disable core module + protection, but this is not recommended. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt new file mode 100644 index 0000000000..6ed70b599f --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt @@ -0,0 +1,9 @@ +HTML.CustomDoctype +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +A custom doctype for power-users who defined their own document +type. This directive only applies when %HTML.Doctype is blank. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt new file mode 100644 index 0000000000..103db754a2 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt @@ -0,0 +1,33 @@ +HTML.DefinitionID +TYPE: string/null +DEFAULT: NULL +VERSION: 2.0.0 +--DESCRIPTION-- + +

+ Unique identifier for a custom-built HTML definition. If you edit + the raw version of the HTMLDefinition, introducing changes that the + configuration object does not reflect, you must specify this variable. + If you change your custom edits, you should change this directive, or + clear your cache. Example: +

+$config = HTMLPurifier_Config::createDefault();
+$config->set('HTML', 'DefinitionID', '1');
+$def = $config->getHTMLDefinition();
+$def->addAttribute('a', 'tabindex', 'Number');
+

+ In the above example, the configuration is still at the defaults, but + using the advanced API, an extra attribute has been added. The + configuration object normally has no way of knowing that this change + has taken place, so it needs an extra directive: %HTML.DefinitionID. + If someone else attempts to use the default configuration, these two + pieces of code will not clobber each other in the cache, since one has + an extra directive attached to it. +

+ You must specify a value to this directive to use the + advanced API features. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt new file mode 100644 index 0000000000..229ae0267a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt @@ -0,0 +1,16 @@ +HTML.DefinitionRev +TYPE: int +VERSION: 2.0.0 +DEFAULT: 1 +--DESCRIPTION-- + +

+ Revision identifier for your custom definition specified in + %HTML.DefinitionID. This serves the same purpose: uniquely identifying + your custom definition, but this one does so in a chronological + context: revision 3 is more up-to-date then revision 2. Thus, when + this gets incremented, the cache handling is smart enough to clean + up any older revisions of your definition as well as flush the + cache. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt new file mode 100644 index 0000000000..9dab497f2f --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt @@ -0,0 +1,11 @@ +HTML.Doctype +TYPE: string/null +DEFAULT: NULL +--DESCRIPTION-- +Doctype to use during filtering. Technically speaking this is not actually +a doctype (as it does not identify a corresponding DTD), but we are using +this name for sake of simplicity. When non-blank, this will override any +older directives like %HTML.XHTML or %HTML.Strict. +--ALLOWED-- +'HTML 4.01 Transitional', 'HTML 4.01 Strict', 'XHTML 1.0 Transitional', 'XHTML 1.0 Strict', 'XHTML 1.1' +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt new file mode 100644 index 0000000000..7878dc0bf6 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.FlashAllowFullScreen.txt @@ -0,0 +1,11 @@ +HTML.FlashAllowFullScreen +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit embedded Flash content from + %HTML.SafeObject to expand to the full screen. Corresponds to + the allowFullScreen parameter. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt new file mode 100644 index 0000000000..57358f9bad --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenAttributes.txt @@ -0,0 +1,21 @@ +HTML.ForbiddenAttributes +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ While this directive is similar to %HTML.AllowedAttributes, for + forwards-compatibility with XML, this attribute has a different syntax. Instead of + tag.attr, use tag@attr. To disallow href + attributes in a tags, set this directive to + a@href. You can also disallow an attribute globally with + attr or *@attr (either syntax is fine; the latter + is provided for consistency with %HTML.AllowedAttributes). +

+ Warning: This directive complements %HTML.ForbiddenElements, + accordingly, check + out that directive for a discussion of why you + should think twice before using this directive. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt new file mode 100644 index 0000000000..93a53e14fb --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.ForbiddenElements.txt @@ -0,0 +1,20 @@ +HTML.ForbiddenElements +TYPE: lookup +VERSION: 3.1.0 +DEFAULT: array() +--DESCRIPTION-- +

+ This was, perhaps, the most requested feature ever in HTML + Purifier. Please don't abuse it! This is the logical inverse of + %HTML.AllowedElements, and it will override that directive, or any + other directive. +

+ If possible, %HTML.Allowed is recommended over this directive, because it + can sometimes be difficult to tell whether or not you've forbidden all of + the behavior you would like to disallow. If you forbid img + with the expectation of preventing images on your site, you'll be in for + a nasty surprise when people start using the background-image + CSS property. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt new file mode 100644 index 0000000000..e424c386ec --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.MaxImgLength.txt @@ -0,0 +1,14 @@ +HTML.MaxImgLength +TYPE: int/null +DEFAULT: 1200 +VERSION: 3.1.1 +--DESCRIPTION-- +

+ This directive controls the maximum number of pixels in the width and + height attributes in img tags. This is + in place to prevent imagecrash attacks, disable with null at your own risk. + This directive is similar to %CSS.MaxImgLength, and both should be + concurrently edited, although there are + subtle differences in the input format (the HTML max is an integer). +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt new file mode 100644 index 0000000000..700b30924a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Nofollow.txt @@ -0,0 +1,7 @@ +HTML.Nofollow +TYPE: bool +VERSION: 4.3.0 +DEFAULT: FALSE +--DESCRIPTION-- +If enabled, nofollow rel attributes are added to all outgoing links. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt new file mode 100644 index 0000000000..62e8e160c7 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt @@ -0,0 +1,12 @@ +HTML.Parent +TYPE: string +VERSION: 1.3.0 +DEFAULT: 'div' +--DESCRIPTION-- + +

+ String name of element that HTML fragment passed to library will be + inserted in. An interesting variation would be using span as the + parent element, meaning that only inline tags would be allowed. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt new file mode 100644 index 0000000000..dfb720496d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Proprietary.txt @@ -0,0 +1,12 @@ +HTML.Proprietary +TYPE: bool +VERSION: 3.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to allow proprietary elements and attributes in your + documents, as per HTMLPurifier_HTMLModule_Proprietary. + Warning: This can cause your documents to stop + validating! +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt new file mode 100644 index 0000000000..cdda09a4c5 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeEmbed.txt @@ -0,0 +1,13 @@ +HTML.SafeEmbed +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit embed tags in documents, with a number of extra + security features added to prevent script execution. This is similar to + what websites like MySpace do to embed tags. Embed is a proprietary + element and will cause your website to stop validating; you should + see if you can use %Output.FlashCompat with %HTML.SafeObject instead + first.

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt new file mode 100644 index 0000000000..5eb6ec2b5a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeIframe.txt @@ -0,0 +1,13 @@ +HTML.SafeIframe +TYPE: bool +VERSION: 4.4.0 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit iframe tags in untrusted documents. This + directive must be accompanied by a whitelist of permitted iframes, + such as %URI.SafeIframeRegexp, otherwise it will fatally error. + This directive has no effect on strict doctypes, as iframes are not + valid. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt new file mode 100644 index 0000000000..ceb342e22b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeObject.txt @@ -0,0 +1,13 @@ +HTML.SafeObject +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ Whether or not to permit object tags in documents, with a number of extra + security features added to prevent script execution. This is similar to + what websites like MySpace do to object tags. You should also enable + %Output.FlashCompat in order to generate Internet Explorer + compatibility code for your object tags. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt new file mode 100644 index 0000000000..5ebc7a19d5 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.SafeScripting.txt @@ -0,0 +1,10 @@ +HTML.SafeScripting +TYPE: lookup +VERSION: 4.5.0 +DEFAULT: array() +--DESCRIPTION-- +

+ Whether or not to permit script tags to external scripts in documents. + Inline scripting is not allowed, and the script must match an explicit whitelist. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt new file mode 100644 index 0000000000..a8b1de56be --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt @@ -0,0 +1,9 @@ +HTML.Strict +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +DEPRECATED-VERSION: 1.7.0 +DEPRECATED-USE: HTML.Doctype +--DESCRIPTION-- +Determines whether or not to use Transitional (loose) or Strict rulesets. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt new file mode 100644 index 0000000000..587a16778b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TargetBlank.txt @@ -0,0 +1,8 @@ +HTML.TargetBlank +TYPE: bool +VERSION: 4.4.0 +DEFAULT: FALSE +--DESCRIPTION-- +If enabled, target=blank attributes are added to all outgoing links. +(This includes links from an HTTPS version of a page to an HTTP version.) +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt new file mode 100644 index 0000000000..b4c271b7fa --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt @@ -0,0 +1,8 @@ +HTML.TidyAdd +TYPE: lookup +VERSION: 2.0.0 +DEFAULT: array() +--DESCRIPTION-- + +Fixes to add to the default set of Tidy fixes as per your level. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt new file mode 100644 index 0000000000..4186ccd0d1 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt @@ -0,0 +1,24 @@ +HTML.TidyLevel +TYPE: string +VERSION: 2.0.0 +DEFAULT: 'medium' +--DESCRIPTION-- + +

General level of cleanliness the Tidy module should enforce. +There are four allowed values:

none: No extra tidying should be done
light: Only fix elements that would be discarded otherwise due to + lack of support in doctype
medium: Enforce best practices
heavy: Transform all deprecated elements and attributes to standards + compliant equivalents

+ +--ALLOWED-- +'none', 'light', 'medium', 'heavy' +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt new file mode 100644 index 0000000000..996762bd1d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt @@ -0,0 +1,8 @@ +HTML.TidyRemove +TYPE: lookup +VERSION: 2.0.0 +DEFAULT: array() +--DESCRIPTION-- + +Fixes to remove from the default set of Tidy fixes as per your level. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt new file mode 100644 index 0000000000..1db9237e9e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt @@ -0,0 +1,9 @@ +HTML.Trusted +TYPE: bool +VERSION: 2.0.0 +DEFAULT: false +--DESCRIPTION-- +Indicates whether or not the user input is trusted or not. If the input is +trusted, a more expansive set of allowed tags and attributes will be used. +See also %CSS.Trusted. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt new file mode 100644 index 0000000000..2a47e384f4 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt @@ -0,0 +1,11 @@ +HTML.XHTML +TYPE: bool +DEFAULT: true +VERSION: 1.1.0 +DEPRECATED-VERSION: 1.7.0 +DEPRECATED-USE: HTML.Doctype +--DESCRIPTION-- +Determines whether or not output is XHTML 1.0 or HTML 4.01 flavor. +--ALIASES-- +Core.XHTML +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt new file mode 100644 index 0000000000..08921fde70 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt @@ -0,0 +1,10 @@ +Output.CommentScriptContents +TYPE: bool +VERSION: 2.0.0 +DEFAULT: true +--DESCRIPTION-- +Determines whether or not HTML Purifier should attempt to fix up the +contents of script tags for legacy browsers with comments. +--ALIASES-- +Core.CommentScriptContents +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt new file mode 100644 index 0000000000..d6f0d9f295 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FixInnerHTML.txt @@ -0,0 +1,15 @@ +Output.FixInnerHTML +TYPE: bool +VERSION: 4.3.0 +DEFAULT: true +--DESCRIPTION-- +

+ If true, HTML Purifier will protect against Internet Explorer's + mishandling of the innerHTML attribute by appending + a space to any attribute that does not contain angled brackets, spaces + or quotes, but contains a backtick. This slightly changes the + semantics of any given attribute, so if this is unacceptable and + you do not use innerHTML on any of your pages, you can + turn this directive off. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt new file mode 100644 index 0000000000..93398e8598 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.FlashCompat.txt @@ -0,0 +1,11 @@ +Output.FlashCompat +TYPE: bool +VERSION: 4.1.0 +DEFAULT: false +--DESCRIPTION-- +

+ If true, HTML Purifier will generate Internet Explorer compatibility + code for all object code. This is highly recommended if you enable + %HTML.SafeObject. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt new file mode 100644 index 0000000000..79f8ad82cf --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt @@ -0,0 +1,13 @@ +Output.Newline +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Newline string to format final output with. If left null, HTML Purifier + will auto-detect the default newline type of the system and use that; + you can manually override it here. Remember, \r\n is Windows, \r + is Mac, and \n is Unix. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt new file mode 100644 index 0000000000..232b02362a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.SortAttr.txt @@ -0,0 +1,14 @@ +Output.SortAttr +TYPE: bool +VERSION: 3.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ If true, HTML Purifier will sort attributes by name before writing them back + to the document, converting a tag like: <el b="" a="" c="" /> + to <el a="" b="" c="" />. This is a workaround for + a bug in FCKeditor which causes it to swap attributes order, adding noise + to text diffs. If you're not seeing this bug, chances are, you don't need + this directive. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt new file mode 100644 index 0000000000..06bab00a0a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt @@ -0,0 +1,25 @@ +Output.TidyFormat +TYPE: bool +VERSION: 1.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ Determines whether or not to run Tidy on the final output for pretty + formatting reasons, such as indentation and wrap. +

+ This can greatly improve readability for editors who are hand-editing + the HTML, but is by no means necessary as HTML Purifier has already + fixed all major errors the HTML may have had. Tidy is a non-default + extension, and this directive will silently fail if Tidy is not + available. +

+ If you are looking to make the overall look of your page's source + better, I recommend running Tidy on the entire page rather than just + user-content (after all, the indentation relative to the containing + blocks will be incorrect). +

+--ALIASES-- +Core.TidyFormat +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt new file mode 100644 index 0000000000..071bc0295d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt @@ -0,0 +1,7 @@ +Test.ForceNoIconv +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When set to true, HTMLPurifier_Encoder will act as if iconv does not exist +and use only pure PHP implementations. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt new file mode 100644 index 0000000000..666635a5ff --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt @@ -0,0 +1,17 @@ +URI.AllowedSchemes +TYPE: lookup +--DEFAULT-- +array ( + 'http' => true, + 'https' => true, + 'mailto' => true, + 'ftp' => true, + 'nntp' => true, + 'news' => true, +) +--DESCRIPTION-- +Whitelist that defines the schemes that a URI is allowed to have. This +prevents XSS attacks from using pseudo-schemes like javascript or mocha. +There is also support for the data and file +URI schemes, but they are not enabled by default. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt new file mode 100644 index 0000000000..876f0680cf --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt @@ -0,0 +1,17 @@ +URI.Base +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ The base URI is the URI of the document this purified HTML will be + inserted into. This information is important if HTML Purifier needs + to calculate absolute URIs from relative URIs, such as when %URI.MakeAbsolute + is on. You may use a non-absolute URI for this value, but behavior + may vary (%URI.MakeAbsolute deals nicely with both absolute and + relative paths, but forwards-compatibility is not guaranteed). + Warning: If set, the scheme on this URI + overrides the one specified by %URI.DefaultScheme. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt new file mode 100644 index 0000000000..728e378cbe --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt @@ -0,0 +1,10 @@ +URI.DefaultScheme +TYPE: string +DEFAULT: 'http' +--DESCRIPTION-- + +

+ Defines through what scheme the output will be served, in order to + select the proper object validator when no scheme information is present. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt new file mode 100644 index 0000000000..f05312ba86 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt @@ -0,0 +1,11 @@ +URI.DefinitionID +TYPE: string/null +VERSION: 2.1.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Unique identifier for a custom-built URI definition. If you want + to add custom URIFilters, you must specify this value. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt new file mode 100644 index 0000000000..80cfea93f7 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt @@ -0,0 +1,11 @@ +URI.DefinitionRev +TYPE: int +VERSION: 2.1.0 +DEFAULT: 1 +--DESCRIPTION-- + +

+ Revision identifier for your custom definition. See + %HTML.DefinitionRev for details. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt new file mode 100644 index 0000000000..71ce025a2d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt @@ -0,0 +1,14 @@ +URI.Disable +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Disables all URIs in all forms. Not sure why you'd want to do that + (after all, the Internet's founded on the notion of a hyperlink). +

+ +--ALIASES-- +Attr.DisableURI +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt new file mode 100644 index 0000000000..13c122c8ce --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt @@ -0,0 +1,11 @@ +URI.DisableExternal +TYPE: bool +VERSION: 1.2.0 +DEFAULT: false +--DESCRIPTION-- +Disables links to external websites. This is a highly effective anti-spam +and anti-pagerank-leech measure, but comes at a hefty price: nolinks or +images outside of your domain will be allowed. Non-linkified URIs will +still be preserved. If you want to be able to link to subdomains or use +absolute URIs, specify %URI.Host for your website. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt new file mode 100644 index 0000000000..abcc1efd61 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt @@ -0,0 +1,13 @@ +URI.DisableExternalResources +TYPE: bool +VERSION: 1.3.0 +DEFAULT: false +--DESCRIPTION-- +Disables the embedding of external resources, preventing users from +embedding things like images from other hosts. This prevents access +tracking (good for email viewers), bandwidth leeching, cross-site request +forging, goatse.cx posting, and other nasties, but also results in a loss +of end-user functionality (they can't directly post a pic they posted from +Flickr anymore). Use it if you don't have a robust user-content moderation +team. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt new file mode 100644 index 0000000000..f891de4996 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt @@ -0,0 +1,15 @@ +URI.DisableResources +TYPE: bool +VERSION: 4.2.0 +DEFAULT: false +--DESCRIPTION-- +

+ Disables embedding resources, essentially meaning no pictures. You can + still link to them though. See %URI.DisableExternalResources for why + this might be a good idea. +

+ Note: While this directive has been available since 1.3.0, + it didn't actually start doing anything until 4.2.0. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt new file mode 100644 index 0000000000..ee83b121de --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt @@ -0,0 +1,19 @@ +URI.Host +TYPE: string/null +VERSION: 1.2.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Defines the domain name of the server, so we can determine whether or + an absolute URI is from your website or not. Not strictly necessary, + as users should be using relative URIs to reference resources on your + website. It will, however, let you use absolute URIs to link to + subdomains of the domain you post here: i.e. example.com will allow + sub.example.com. However, higher up domains will still be excluded: + if you set %URI.Host to sub.example.com, example.com will be blocked. + Note: This directive overrides %URI.Base because + a given page may be on a sub-domain, but you wish HTML Purifier to be + more relaxed and allow some of the parent domains too. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt new file mode 100644 index 0000000000..0b6df7625d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt @@ -0,0 +1,9 @@ +URI.HostBlacklist +TYPE: list +VERSION: 1.3.0 +DEFAULT: array() +--DESCRIPTION-- +List of strings that are forbidden in the host of any URI. Use it to kill +domain names of spam, etc. Note that it will catch anything in the domain, +so moo.com will catch moo.com.example.com. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt new file mode 100644 index 0000000000..4214900a59 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt @@ -0,0 +1,13 @@ +URI.MakeAbsolute +TYPE: bool +VERSION: 2.1.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Converts all URIs into absolute forms. This is useful when the HTML + being filtered assumes a specific base path, but will actually be + viewed in a different context (and setting an alternate base URI is + not possible). %URI.Base must be set for this directive to work. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt new file mode 100644 index 0000000000..58c81dcc44 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt @@ -0,0 +1,83 @@ +URI.Munge +TYPE: string/null +VERSION: 1.3.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Munges all browsable (usually http, https and ftp) + absolute URIs into another URI, usually a URI redirection service. + This directive accepts a URI, formatted with a %s where + the url-encoded original URI should be inserted (sample: + http://www.google.com/url?q=%s). +

+ Uses for this directive: +

+ Prevent PageRank leaks, while being fairly transparent + to users (you may also want to add some client side JavaScript to + override the text in the statusbar). Notice: + Many security experts believe that this form of protection does not deter spam-bots. +
+ Redirect users to a splash page telling them they are leaving your + website. While this is poor usability practice, it is often mandated + in corporate environments. +

+ Prior to HTML Purifier 3.1.1, this directive also enabled the munging + of browsable external resources, which could break things if your redirection + script was a splash page or used meta tags. To revert to + previous behavior, please use %URI.MungeResources. +

+ You may want to also use %URI.MungeSecretKey along with this directive + in order to enforce what URIs your redirector script allows. Open + redirector scripts can be a security risk and negatively affect the + reputation of your domain name. +

+ Starting with HTML Purifier 3.1.1, there is also these substitutions: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +

Key	Description	Example `<a href="">`
%r	1 - The URI embeds a resource (blank) - The URI is merely a link
%n	The name of the tag this URI came from	a
%m	The name of the attribute this URI came from	href
%p	The name of the CSS property this URI came from, or blank if irrelevant

+ Admittedly, these letters are somewhat arbitrary; the only stipulation + was that they couldn't be a through f. r is for resource (I would have preferred + e, but you take what you can get), n is for name, m + was picked because it came after n (and I couldn't use a), p is for + property. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt new file mode 100644 index 0000000000..6fce0fdc37 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeResources.txt @@ -0,0 +1,17 @@ +URI.MungeResources +TYPE: bool +VERSION: 3.1.1 +DEFAULT: false +--DESCRIPTION-- +

+ If true, any URI munging directives like %URI.Munge + will also apply to embedded resources, such as <img src="">. + Be careful enabling this directive if you have a redirector script + that does not use the Location HTTP header; all of your images + and other embedded resources will break. +

+ Warning: It is strongly advised you use this in conjunction + %URI.MungeSecretKey to mitigate the security risk of an open redirector. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt new file mode 100644 index 0000000000..1e17c1d461 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.MungeSecretKey.txt @@ -0,0 +1,30 @@ +URI.MungeSecretKey +TYPE: string/null +VERSION: 3.1.1 +DEFAULT: NULL +--DESCRIPTION-- +

+ This directive enables secure checksum generation along with %URI.Munge. + It should be set to a secure key that is not shared with anyone else. + The checksum can be placed in the URI using %t. Use of this checksum + affords an additional level of protection by allowing a redirector + to check if a URI has passed through HTML Purifier with this line: +

+ +

$checksum === hash_hmac("sha256", $url, $secret_key)

+ +

+ If the output is TRUE, the redirector script should accept the URI. +

+ +

+ Please note that it would still be possible for an attacker to procure + secure hashes en-mass by abusing your website's Preview feature or the + like, but this service affords an additional level of protection + that should be combined with website blacklisting. +

+ +

+ Remember this has no effect if %URI.Munge is not on. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt new file mode 100644 index 0000000000..23331a4e79 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt @@ -0,0 +1,9 @@ +URI.OverrideAllowedSchemes +TYPE: bool +DEFAULT: true +--DESCRIPTION-- +If this is set to true (which it is by default), you can override +%URI.AllowedSchemes by simply registering a HTMLPurifier_URIScheme to the +registry. If false, you will also have to update that directive in order +to add more schemes. +--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt new file mode 100644 index 0000000000..79084832be --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/URI.SafeIframeRegexp.txt @@ -0,0 +1,22 @@ +URI.SafeIframeRegexp +TYPE: string/null +VERSION: 4.4.0 +DEFAULT: NULL +--DESCRIPTION-- +

+ A PCRE regular expression that will be matched against an iframe URI. This is + a relatively inflexible scheme, but works well enough for the most common + use-case of iframes: embedded video. This directive only has an effect if + %HTML.SafeIframe is enabled. Here are some example values: +

%^http://www.youtube.com/embed/% - Allow YouTube videos
%^http://player.vimeo.com/video/% - Allow Vimeo videos
%^http://(www.youtube.com/embed/|player.vimeo.com/video/)% - Allow both

+ Note that this directive does not give you enough granularity to, say, disable + all autoplay videos. Pipe up on the HTML Purifier forums if this + is a capability you want. +

+--# vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/info.ini b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/info.ini new file mode 100644 index 0000000000..5de4505e1b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ConfigSchema/schema/info.ini @@ -0,0 +1,3 @@ +name = "HTML Purifier" + +; vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ContentSets.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ContentSets.php new file mode 100644 index 0000000000..543e3f8f11 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ContentSets.php @@ -0,0 +1,170 @@ + true) indexed by name. + * @type array + * @note This is in HTMLPurifier_HTMLDefinition->info_content_sets + */ + public $lookup = array(); + + /** + * Synchronized list of defined content sets (keys of info). + * @type array + */ + protected $keys = array(); + /** + * Synchronized list of defined content values (values of info). + * @type array + */ + protected $values = array(); + + /** + * Merges in module's content sets, expands identifiers in the content + * sets and populates the keys, values and lookup member variables. + * @param HTMLPurifier_HTMLModule[] $modules List of HTMLPurifier_HTMLModule + */ + public function __construct($modules) + { + if (!is_array($modules)) { + $modules = array($modules); + } + // populate content_sets based on module hints + // sorry, no way of overloading + foreach ($modules as $module) { + foreach ($module->content_sets as $key => $value) { + $temp = $this->convertToLookup($value); + if (isset($this->lookup[$key])) { + // add it into the existing content set + $this->lookup[$key] = array_merge($this->lookup[$key], $temp); + } else { + $this->lookup[$key] = $temp; + } + } + } + $old_lookup = false; + while ($old_lookup !== $this->lookup) { + $old_lookup = $this->lookup; + foreach ($this->lookup as $i => $set) { + $add = array(); + foreach ($set as $element => $x) { + if (isset($this->lookup[$element])) { + $add += $this->lookup[$element]; + unset($this->lookup[$i][$element]); + } + } + $this->lookup[$i] += $add; + } + } + + foreach ($this->lookup as $key => $lookup) { + $this->info[$key] = implode(' | ', array_keys($lookup)); + } + $this->keys = array_keys($this->info); + $this->values = array_values($this->info); + } + + /** + * Accepts a definition; generates and assigns a ChildDef for it + * @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef reference + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef + */ + public function generateChildDef(&$def, $module) + { + if (!empty($def->child)) { // already done! + return; + } + $content_model = $def->content_model; + if (is_string($content_model)) { + // Assume that $this->keys is alphanumeric + $def->content_model = preg_replace_callback( + '/\b(' . implode('|', $this->keys) . ')\b/', + array($this, 'generateChildDefCallback'), + $content_model + ); + //$def->content_model = str_replace( + // $this->keys, $this->values, $content_model); + } + $def->child = $this->getChildDef($def, $module); + } + + public function generateChildDefCallback($matches) + { + return $this->info[$matches[0]]; + } + + /** + * Instantiates a ChildDef based on content_model and content_model_type + * member variables in HTMLPurifier_ElementDef + * @note This will also defer to modules for custom HTMLPurifier_ChildDef + * subclasses that need content set expansion + * @param HTMLPurifier_ElementDef $def HTMLPurifier_ElementDef to have ChildDef extracted + * @param HTMLPurifier_HTMLModule $module Module that defined the ElementDef + * @return HTMLPurifier_ChildDef corresponding to ElementDef + */ + public function getChildDef($def, $module) + { + $value = $def->content_model; + if (is_object($value)) { + trigger_error( + 'Literal object child definitions should be stored in '. + 'ElementDef->child not ElementDef->content_model', + E_USER_NOTICE + ); + return $value; + } + switch ($def->content_model_type) { + case 'required': + return new HTMLPurifier_ChildDef_Required($value); + case 'optional': + return new HTMLPurifier_ChildDef_Optional($value); + case 'empty': + return new HTMLPurifier_ChildDef_Empty(); + case 'custom': + return new HTMLPurifier_ChildDef_Custom($value); + } + // defer to its module + $return = false; + if ($module->defines_child_def) { // save a func call + $return = $module->getChildDef($def); + } + if ($return !== false) { + return $return; + } + // error-out + trigger_error( + 'Could not determine which ChildDef class to instantiate', + E_USER_ERROR + ); + return false; + } + + /** + * Converts a string list of elements separated by pipes into + * a lookup array. + * @param string $string List of elements + * @return array Lookup array of elements + */ + protected function convertToLookup($string) + { + $array = explode('|', str_replace(' ', '', $string)); + $ret = array(); + foreach ($array as $k) { + $ret[$k] = true; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Context.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Context.php new file mode 100644 index 0000000000..00e509c85c --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Context.php @@ -0,0 +1,95 @@ +_storage)) { + trigger_error( + "Name $name produces collision, cannot re-register", + E_USER_ERROR + ); + return; + } + $this->_storage[$name] =& $ref; + } + + /** + * Retrieves a variable reference from the context. + * @param string $name String name + * @param bool $ignore_error Boolean whether or not to ignore error + * @return mixed + */ + public function &get($name, $ignore_error = false) + { + if (!array_key_exists($name, $this->_storage)) { + if (!$ignore_error) { + trigger_error( + "Attempted to retrieve non-existent variable $name", + E_USER_ERROR + ); + } + $var = null; // so we can return by reference + return $var; + } + return $this->_storage[$name]; + } + + /** + * Destroys a variable in the context. + * @param string $name String name + */ + public function destroy($name) + { + if (!array_key_exists($name, $this->_storage)) { + trigger_error( + "Attempted to destroy non-existent variable $name", + E_USER_ERROR + ); + return; + } + unset($this->_storage[$name]); + } + + /** + * Checks whether or not the variable exists. + * @param string $name String name + * @return bool + */ + public function exists($name) + { + return array_key_exists($name, $this->_storage); + } + + /** + * Loads a series of variables from an associative array + * @param array $context_array Assoc array of variables to load + */ + public function loadArray($context_array) + { + foreach ($context_array as $key => $discard) { + $this->register($key, $context_array[$key]); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Definition.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Definition.php new file mode 100644 index 0000000000..bc6d433647 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Definition.php @@ -0,0 +1,55 @@ +setup) { + return; + } + $this->setup = true; + $this->doSetup($config); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache.php new file mode 100644 index 0000000000..67bb5b1e69 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache.php @@ -0,0 +1,129 @@ +type = $type; + } + + /** + * Generates a unique identifier for a particular configuration + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config + * @return string + */ + public function generateKey($config) + { + return $config->version . ',' . // possibly replace with function calls + $config->getBatchSerial($this->type) . ',' . + $config->get($this->type . '.DefinitionRev'); + } + + /** + * Tests whether or not a key is old with respect to the configuration's + * version and revision number. + * @param string $key Key to test + * @param HTMLPurifier_Config $config Instance of HTMLPurifier_Config to test against + * @return bool + */ + public function isOld($key, $config) + { + if (substr_count($key, ',') < 2) { + return true; + } + list($version, $hash, $revision) = explode(',', $key, 3); + $compare = version_compare($version, $config->version); + // version mismatch, is always old + if ($compare != 0) { + return true; + } + // versions match, ids match, check revision number + if ($hash == $config->getBatchSerial($this->type) && + $revision < $config->get($this->type . '.DefinitionRev')) { + return true; + } + return false; + } + + /** + * Checks if a definition's type jives with the cache's type + * @note Throws an error on failure + * @param HTMLPurifier_Definition $def Definition object to check + * @return bool true if good, false if not + */ + public function checkDefType($def) + { + if ($def->type !== $this->type) { + trigger_error("Cannot use definition of type {$def->type} in cache for {$this->type}"); + return false; + } + return true; + } + + /** + * Adds a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function add($def, $config); + + /** + * Unconditionally saves a definition object to the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function set($def, $config); + + /** + * Replace an object in the cache + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + */ + abstract public function replace($def, $config); + + /** + * Retrieves a definition object from the cache + * @param HTMLPurifier_Config $config + */ + abstract public function get($config); + + /** + * Removes a definition object to the cache + * @param HTMLPurifier_Config $config + */ + abstract public function remove($config); + + /** + * Clears all objects from cache + * @param HTMLPurifier_Config $config + */ + abstract public function flush($config); + + /** + * Clears all expired (older version or revision) objects from cache + * @note Be carefuly implementing this method as flush. Flush must + * not interfere with other Definition types, and cleanup() + * should not be repeatedly called by userland code. + * @param HTMLPurifier_Config $config + */ + abstract public function cleanup($config); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator.php new file mode 100644 index 0000000000..b57a51b6cb --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator.php @@ -0,0 +1,112 @@ +copy(); + // reference is necessary for mocks in PHP 4 + $decorator->cache =& $cache; + $decorator->type = $cache->type; + return $decorator; + } + + /** + * Cross-compatible clone substitute + * @return HTMLPurifier_DefinitionCache_Decorator + */ + public function copy() + { + return new HTMLPurifier_DefinitionCache_Decorator(); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function add($def, $config) + { + return $this->cache->add($def, $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { + return $this->cache->set($def, $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { + return $this->cache->replace($def, $config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { + return $this->cache->get($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function remove($config) + { + return $this->cache->remove($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function flush($config) + { + return $this->cache->flush($config); + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function cleanup($config) + { + return $this->cache->cleanup($config); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php new file mode 100644 index 0000000000..4991777ce1 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Cleanup.php @@ -0,0 +1,78 @@ +definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function set($def, $config) + { + $status = parent::set($def, $config); + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function replace($def, $config) + { + $status = parent::replace($def, $config); + if ($status) { + $this->definitions[$this->generateKey($config)] = $def; + } + return $status; + } + + /** + * @param HTMLPurifier_Config $config + * @return mixed + */ + public function get($config) + { + $key = $this->generateKey($config); + if (isset($this->definitions[$key])) { + return $this->definitions[$key]; + } + $this->definitions[$key] = parent::get($config); + return $this->definitions[$key]; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in new file mode 100644 index 0000000000..b1fec8d367 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in @@ -0,0 +1,82 @@ +checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function set($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Definition $def + * @param HTMLPurifier_Config $config + * @return int|bool + */ + public function replace($def, $config) + { + if (!$this->checkDefType($def)) { + return; + } + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + if (!$this->_prepareDir($config)) { + return false; + } + return $this->_write($file, serialize($def), $config); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool|HTMLPurifier_Config + */ + public function get($config) + { + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + return unserialize(file_get_contents($file)); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function remove($config) + { + $file = $this->generateFilePath($config); + if (!file_exists($file)) { + return false; + } + return unlink($file); + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function flush($config) + { + if (!$this->_prepareDir($config)) { + return false; + } + $dir = $this->generateDirectoryPath($config); + $dh = opendir($dir); + while (false !== ($filename = readdir($dh))) { + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } + unlink($dir . '/' . $filename); + } + } + + /** + * @param HTMLPurifier_Config $config + * @return bool + */ + public function cleanup($config) + { + if (!$this->_prepareDir($config)) { + return false; + } + $dir = $this->generateDirectoryPath($config); + $dh = opendir($dir); + while (false !== ($filename = readdir($dh))) { + if (empty($filename)) { + continue; + } + if ($filename[0] === '.') { + continue; + } + $key = substr($filename, 0, strlen($filename) - 4); + if ($this->isOld($key, $config)) { + unlink($dir . '/' . $filename); + } + } + } + + /** + * Generates the file path to the serial file corresponding to + * the configuration and definition name + * @param HTMLPurifier_Config $config + * @return string + * @todo Make protected + */ + public function generateFilePath($config) + { + $key = $this->generateKey($config); + return $this->generateDirectoryPath($config) . '/' . $key . '.ser'; + } + + /** + * Generates the path to the directory contain this cache's serial files + * @param HTMLPurifier_Config $config + * @return string + * @note No trailing slash + * @todo Make protected + */ + public function generateDirectoryPath($config) + { + $base = $this->generateBaseDirectoryPath($config); + return $base . '/' . $this->type; + } + + /** + * Generates path to base directory that contains all definition type + * serials + * @param HTMLPurifier_Config $config + * @return mixed|string + * @todo Make protected + */ + public function generateBaseDirectoryPath($config) + { + $base = $config->get('Cache.SerializerPath'); + $base = is_null($base) ? HTMLPURIFIER_PREFIX . '/HTMLPurifier/DefinitionCache/Serializer' : $base; + return $base; + } + + /** + * Convenience wrapper function for file_put_contents + * @param string $file File name to write to + * @param string $data Data to write into file + * @param HTMLPurifier_Config $config + * @return int|bool Number of bytes written if success, or false if failure. + */ + private function _write($file, $data, $config) + { + $result = file_put_contents($file, $data); + if ($result !== false) { + // set permissions of the new file (no execute) + $chmod = $config->get('Cache.SerializerPermissions'); + if (!$chmod) { + $chmod = 0644; // invalid config or simpletest + } + $chmod = $chmod & 0666; + chmod($file, $chmod); + } + return $result; + } + + /** + * Prepares the directory that this type stores the serials in + * @param HTMLPurifier_Config $config + * @return bool True if successful + */ + private function _prepareDir($config) + { + $directory = $this->generateDirectoryPath($config); + $chmod = $config->get('Cache.SerializerPermissions'); + if (!$chmod) { + $chmod = 0755; // invalid config or simpletest + } + if (!is_dir($directory)) { + $base = $this->generateBaseDirectoryPath($config); + if (!is_dir($base)) { + trigger_error( + 'Base directory ' . $base . ' does not exist, + please create or change using %Cache.SerializerPath', + E_USER_WARNING + ); + return false; + } elseif (!$this->_testPermissions($base, $chmod)) { + return false; + } + mkdir($directory, $chmod); + if (!$this->_testPermissions($directory, $chmod)) { + trigger_error( + 'Base directory ' . $base . ' does not exist, + please create or change using %Cache.SerializerPath', + E_USER_WARNING + ); + return false; + } + } elseif (!$this->_testPermissions($directory, $chmod)) { + return false; + } + return true; + } + + /** + * Tests permissions on a directory and throws out friendly + * error messages and attempts to chmod it itself if possible + * @param string $dir Directory path + * @param int $chmod Permissions + * @return bool True if directory is writable + */ + private function _testPermissions($dir, $chmod) + { + // early abort, if it is writable, everything is hunky-dory + if (is_writable($dir)) { + return true; + } + if (!is_dir($dir)) { + // generally, you'll want to handle this beforehand + // so a more specific error message can be given + trigger_error( + 'Directory ' . $dir . ' does not exist', + E_USER_WARNING + ); + return false; + } + if (function_exists('posix_getuid')) { + // POSIX system, we can give more specific advice + if (fileowner($dir) === posix_getuid()) { + // we can chmod it ourselves + $chmod = $chmod | 0700; + if (chmod($dir, $chmod)) { + return true; + } + } elseif (filegroup($dir) === posix_getgid()) { + $chmod = $chmod | 0070; + } else { + // PHP's probably running as nobody, so we'll + // need to give global permissions + $chmod = $chmod | 0777; + } + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please chmod to ' . decoct($chmod), + E_USER_WARNING + ); + } else { + // generic error message + trigger_error( + 'Directory ' . $dir . ' not writable, ' . + 'please alter file permissions', + E_USER_WARNING + ); + } + return false; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer/README b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer/README new file mode 100644 index 0000000000..2e35c1c3d0 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCache/Serializer/README @@ -0,0 +1,3 @@ +This is a dummy file to prevent Git from ignoring this empty directory. + + vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCacheFactory.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCacheFactory.php new file mode 100644 index 0000000000..fd1cc9be46 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DefinitionCacheFactory.php @@ -0,0 +1,106 @@ + array()); + + /** + * @type array + */ + protected $implementations = array(); + + /** + * @type HTMLPurifier_DefinitionCache_Decorator[] + */ + protected $decorators = array(); + + /** + * Initialize default decorators + */ + public function setup() + { + $this->addDecorator('Cleanup'); + } + + /** + * Retrieves an instance of global definition cache factory. + * @param HTMLPurifier_DefinitionCacheFactory $prototype + * @return HTMLPurifier_DefinitionCacheFactory + */ + public static function instance($prototype = null) + { + static $instance; + if ($prototype !== null) { + $instance = $prototype; + } elseif ($instance === null || $prototype === true) { + $instance = new HTMLPurifier_DefinitionCacheFactory(); + $instance->setup(); + } + return $instance; + } + + /** + * Registers a new definition cache object + * @param string $short Short name of cache object, for reference + * @param string $long Full class name of cache object, for construction + */ + public function register($short, $long) + { + $this->implementations[$short] = $long; + } + + /** + * Factory method that creates a cache object based on configuration + * @param string $type Name of definitions handled by cache + * @param HTMLPurifier_Config $config Config instance + * @return mixed + */ + public function create($type, $config) + { + $method = $config->get('Cache.DefinitionImpl'); + if ($method === null) { + return new HTMLPurifier_DefinitionCache_Null($type); + } + if (!empty($this->caches[$method][$type])) { + return $this->caches[$method][$type]; + } + if (isset($this->implementations[$method]) && + class_exists($class = $this->implementations[$method], false)) { + $cache = new $class($type); + } else { + if ($method != 'Serializer') { + trigger_error("Unrecognized DefinitionCache $method, using Serializer instead", E_USER_WARNING); + } + $cache = new HTMLPurifier_DefinitionCache_Serializer($type); + } + foreach ($this->decorators as $decorator) { + $new_cache = $decorator->decorate($cache); + // prevent infinite recursion in PHP 4 + unset($cache); + $cache = $new_cache; + } + $this->caches[$method][$type] = $cache; + return $this->caches[$method][$type]; + } + + /** + * Registers a decorator to add to all new cache objects + * @param HTMLPurifier_DefinitionCache_Decorator|string $decorator An instance or the name of a decorator + */ + public function addDecorator($decorator) + { + if (is_string($decorator)) { + $class = "HTMLPurifier_DefinitionCache_Decorator_$decorator"; + $decorator = new $class; + } + $this->decorators[$decorator->name] = $decorator; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Doctype.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Doctype.php new file mode 100644 index 0000000000..4acd06e5bd --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Doctype.php @@ -0,0 +1,73 @@ +renderDoctype. + * If structure changes, please update that function. + */ +class HTMLPurifier_Doctype +{ + /** + * Full name of doctype + * @type string + */ + public $name; + + /** + * List of standard modules (string identifiers or literal objects) + * that this doctype uses + * @type array + */ + public $modules = array(); + + /** + * List of modules to use for tidying up code + * @type array + */ + public $tidyModules = array(); + + /** + * Is the language derived from XML (i.e. XHTML)? + * @type bool + */ + public $xml = true; + + /** + * List of aliases for this doctype + * @type array + */ + public $aliases = array(); + + /** + * Public DTD identifier + * @type string + */ + public $dtdPublic; + + /** + * System DTD identifier + * @type string + */ + public $dtdSystem; + + public function __construct( + $name = null, + $xml = true, + $modules = array(), + $tidyModules = array(), + $aliases = array(), + $dtd_public = null, + $dtd_system = null + ) { + $this->name = $name; + $this->xml = $xml; + $this->modules = $modules; + $this->tidyModules = $tidyModules; + $this->aliases = $aliases; + $this->dtdPublic = $dtd_public; + $this->dtdSystem = $dtd_system; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DoctypeRegistry.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DoctypeRegistry.php new file mode 100644 index 0000000000..acc1d64a62 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/DoctypeRegistry.php @@ -0,0 +1,142 @@ +doctypes[$doctype->name] = $doctype; + $name = $doctype->name; + // hookup aliases + foreach ($doctype->aliases as $alias) { + if (isset($this->doctypes[$alias])) { + continue; + } + $this->aliases[$alias] = $name; + } + // remove old aliases + if (isset($this->aliases[$name])) { + unset($this->aliases[$name]); + } + return $doctype; + } + + /** + * Retrieves reference to a doctype of a certain name + * @note This function resolves aliases + * @note When possible, use the more fully-featured make() + * @param string $doctype Name of doctype + * @return HTMLPurifier_Doctype Editable doctype object + */ + public function get($doctype) + { + if (isset($this->aliases[$doctype])) { + $doctype = $this->aliases[$doctype]; + } + if (!isset($this->doctypes[$doctype])) { + trigger_error('Doctype ' . htmlspecialchars($doctype) . ' does not exist', E_USER_ERROR); + $anon = new HTMLPurifier_Doctype($doctype); + return $anon; + } + return $this->doctypes[$doctype]; + } + + /** + * Creates a doctype based on a configuration object, + * will perform initialization on the doctype + * @note Use this function to get a copy of doctype that config + * can hold on to (this is necessary in order to tell + * Generator whether or not the current document is XML + * based or not). + * @param HTMLPurifier_Config $config + * @return HTMLPurifier_Doctype + */ + public function make($config) + { + return clone $this->get($this->getDoctypeFromConfig($config)); + } + + /** + * Retrieves the doctype from the configuration object + * @param HTMLPurifier_Config $config + * @return string + */ + public function getDoctypeFromConfig($config) + { + // recommended test + $doctype = $config->get('HTML.Doctype'); + if (!empty($doctype)) { + return $doctype; + } + $doctype = $config->get('HTML.CustomDoctype'); + if (!empty($doctype)) { + return $doctype; + } + // backwards-compatibility + if ($config->get('HTML.XHTML')) { + $doctype = 'XHTML 1.0'; + } else { + $doctype = 'HTML 4.01'; + } + if ($config->get('HTML.Strict')) { + $doctype .= ' Strict'; + } else { + $doctype .= ' Transitional'; + } + return $doctype; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ElementDef.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ElementDef.php new file mode 100644 index 0000000000..d5311cedcf --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ElementDef.php @@ -0,0 +1,216 @@ +setup(), this array may also + * contain an array at index 0 that indicates which attribute + * collections to load into the full array. It may also + * contain string indentifiers in lieu of HTMLPurifier_AttrDef, + * see HTMLPurifier_AttrTypes on how they are expanded during + * HTMLPurifier_HTMLDefinition->setup() processing. + */ + public $attr = array(); + + // XXX: Design note: currently, it's not possible to override + // previously defined AttrTransforms without messing around with + // the final generated config. This is by design; a previous version + // used an associated list of attr_transform, but it was extremely + // easy to accidentally override other attribute transforms by + // forgetting to specify an index (and just using 0.) While we + // could check this by checking the index number and complaining, + // there is a second problem which is that it is not at all easy to + // tell when something is getting overridden. Combine this with a + // codebase where this isn't really being used, and it's perfect for + // nuking. + + /** + * List of tags HTMLPurifier_AttrTransform to be done before validation. + * @type array + */ + public $attr_transform_pre = array(); + + /** + * List of tags HTMLPurifier_AttrTransform to be done after validation. + * @type array + */ + public $attr_transform_post = array(); + + /** + * HTMLPurifier_ChildDef of this tag. + * @type HTMLPurifier_ChildDef + */ + public $child; + + /** + * Abstract string representation of internal ChildDef rules. + * @see HTMLPurifier_ContentSets for how this is parsed and then transformed + * into an HTMLPurifier_ChildDef. + * @warning This is a temporary variable that is not available after + * being processed by HTMLDefinition + * @type string + */ + public $content_model; + + /** + * Value of $child->type, used to determine which ChildDef to use, + * used in combination with $content_model. + * @warning This must be lowercase + * @warning This is a temporary variable that is not available after + * being processed by HTMLDefinition + * @type string + */ + public $content_model_type; + + /** + * Does the element have a content model (#PCDATA | Inline)*? This + * is important for chameleon ins and del processing in + * HTMLPurifier_ChildDef_Chameleon. Dynamically set: modules don't + * have to worry about this one. + * @type bool + */ + public $descendants_are_inline = false; + + /** + * List of the names of required attributes this element has. + * Dynamically populated by HTMLPurifier_HTMLDefinition::getElement() + * @type array + */ + public $required_attr = array(); + + /** + * Lookup table of tags excluded from all descendants of this tag. + * @type array + * @note SGML permits exclusions for all descendants, but this is + * not possible with DTDs or XML Schemas. W3C has elected to + * use complicated compositions of content_models to simulate + * exclusion for children, but we go the simpler, SGML-style + * route of flat-out exclusions, which correctly apply to + * all descendants and not just children. Note that the XHTML + * Modularization Abstract Modules are blithely unaware of such + * distinctions. + */ + public $excludes = array(); + + /** + * This tag is explicitly auto-closed by the following tags. + * @type array + */ + public $autoclose = array(); + + /** + * If a foreign element is found in this element, test if it is + * allowed by this sub-element; if it is, instead of closing the + * current element, place it inside this element. + * @type string + */ + public $wrap; + + /** + * Whether or not this is a formatting element affected by the + * "Active Formatting Elements" algorithm. + * @type bool + */ + public $formatting; + + /** + * Low-level factory constructor for creating new standalone element defs + */ + public static function create($content_model, $content_model_type, $attr) + { + $def = new HTMLPurifier_ElementDef(); + $def->content_model = $content_model; + $def->content_model_type = $content_model_type; + $def->attr = $attr; + return $def; + } + + /** + * Merges the values of another element definition into this one. + * Values from the new element def take precedence if a value is + * not mergeable. + * @param HTMLPurifier_ElementDef $def + */ + public function mergeIn($def) + { + // later keys takes precedence + foreach ($def->attr as $k => $v) { + if ($k === 0) { + // merge in the includes + // sorry, no way to override an include + foreach ($v as $v2) { + $this->attr[0][] = $v2; + } + continue; + } + if ($v === false) { + if (isset($this->attr[$k])) { + unset($this->attr[$k]); + } + continue; + } + $this->attr[$k] = $v; + } + $this->_mergeAssocArray($this->excludes, $def->excludes); + $this->attr_transform_pre = array_merge($this->attr_transform_pre, $def->attr_transform_pre); + $this->attr_transform_post = array_merge($this->attr_transform_post, $def->attr_transform_post); + + if (!empty($def->content_model)) { + $this->content_model = + str_replace("#SUPER", $this->content_model, $def->content_model); + $this->child = false; + } + if (!empty($def->content_model_type)) { + $this->content_model_type = $def->content_model_type; + $this->child = false; + } + if (!is_null($def->child)) { + $this->child = $def->child; + } + if (!is_null($def->formatting)) { + $this->formatting = $def->formatting; + } + if ($def->descendants_are_inline) { + $this->descendants_are_inline = $def->descendants_are_inline; + } + } + + /** + * Merges one array into another, removes values which equal false + * @param $a1 Array by reference that is merged into + * @param $a2 Array that merges into $a1 + */ + private function _mergeAssocArray(&$a1, $a2) + { + foreach ($a2 as $k => $v) { + if ($v === false) { + if (isset($a1[$k])) { + unset($a1[$k]); + } + continue; + } + $a1[$k] = $v; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Encoder.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Encoder.php new file mode 100644 index 0000000000..fef9b58906 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Encoder.php @@ -0,0 +1,611 @@ += $c) { + $r .= self::unsafeIconv($in, $out, substr($text, $i)); + break; + } + // wibble the boundary + if (0x80 != (0xC0 & ord($text[$i + $max_chunk_size]))) { + $chunk_size = $max_chunk_size; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 1]))) { + $chunk_size = $max_chunk_size - 1; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 2]))) { + $chunk_size = $max_chunk_size - 2; + } elseif (0x80 != (0xC0 & ord($text[$i + $max_chunk_size - 3]))) { + $chunk_size = $max_chunk_size - 3; + } else { + return false; // rather confusing UTF-8... + } + $chunk = substr($text, $i, $chunk_size); // substr doesn't mind overlong lengths + $r .= self::unsafeIconv($in, $out, $chunk); + $i += $chunk_size; + } + return $r; + } else { + return false; + } + } else { + return false; + } + } + + /** + * Cleans a UTF-8 string for well-formedness and SGML validity + * + * It will parse according to UTF-8 and return a valid UTF8 string, with + * non-SGML codepoints excluded. + * + * @param string $str The string to clean + * @param bool $force_php + * @return string + * + * @note Just for reference, the non-SGML code points are 0 to 31 and + * 127 to 159, inclusive. However, we allow code points 9, 10 + * and 13, which are the tab, line feed and carriage return + * respectively. 128 and above the code points map to multibyte + * UTF-8 representations. + * + * @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and + * hsivonen@iki.fi at under the + * LGPL license. Notes on what changed are inside, but in general, + * the original code transformed UTF-8 text into an array of integer + * Unicode codepoints. Understandably, transforming that back to + * a string would be somewhat expensive, so the function was modded to + * directly operate on the string. However, this discourages code + * reuse, and the logic enumerated here would be useful for any + * function that needs to be able to understand UTF-8 characters. + * As of right now, only smart lossless character encoding converters + * would need that, and I'm probably not going to implement them. + * Once again, PHP 6 should solve all our problems. + */ + public static function cleanUTF8($str, $force_php = false) + { + // UTF-8 validity is checked since PHP 4.3.5 + // This is an optimization: if the string is already valid UTF-8, no + // need to do PHP stuff. 99% of the time, this will be the case. + // The regexp matches the XML char production, as well as well as excluding + // non-SGML codepoints U+007F to U+009F + if (preg_match( + '/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', + $str + )) { + return $str; + } + + $mState = 0; // cached expected number of octets after the current octet + // until the beginning of the next UTF8 character sequence + $mUcs4 = 0; // cached Unicode character + $mBytes = 1; // cached expected number of octets in the current sequence + + // original code involved an $out that was an array of Unicode + // codepoints. Instead of having to convert back into UTF-8, we've + // decided to directly append valid UTF-8 characters onto a string + // $out once they're done. $char accumulates raw bytes, while $mUcs4 + // turns into the Unicode code point, so there's some redundancy. + + $out = ''; + $char = ''; + + $len = strlen($str); + for ($i = 0; $i < $len; $i++) { + $in = ord($str{$i}); + $char .= $str[$i]; // append byte to char + if (0 == $mState) { + // When mState is zero we expect either a US-ASCII character + // or a multi-octet sequence. + if (0 == (0x80 & ($in))) { + // US-ASCII, pass straight through. + if (($in <= 31 || $in == 127) && + !($in == 9 || $in == 13 || $in == 10) // save \r\t\n + ) { + // control characters, remove + } else { + $out .= $char; + } + // reset + $char = ''; + $mBytes = 1; + } elseif (0xC0 == (0xE0 & ($in))) { + // First octet of 2 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x1F) << 6; + $mState = 1; + $mBytes = 2; + } elseif (0xE0 == (0xF0 & ($in))) { + // First octet of 3 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x0F) << 12; + $mState = 2; + $mBytes = 3; + } elseif (0xF0 == (0xF8 & ($in))) { + // First octet of 4 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x07) << 18; + $mState = 3; + $mBytes = 4; + } elseif (0xF8 == (0xFC & ($in))) { + // First octet of 5 octet sequence. + // + // This is illegal because the encoded codepoint must be + // either: + // (a) not the shortest form or + // (b) outside the Unicode range of 0-0x10FFFF. + // Rather than trying to resynchronize, we will carry on + // until the end of the sequence and let the later error + // handling code catch it. + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x03) << 24; + $mState = 4; + $mBytes = 5; + } elseif (0xFC == (0xFE & ($in))) { + // First octet of 6 octet sequence, see comments for 5 + // octet sequence. + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 1) << 30; + $mState = 5; + $mBytes = 6; + } else { + // Current octet is neither in the US-ASCII range nor a + // legal first octet of a multi-octet sequence. + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + $char = ''; + } + } else { + // When mState is non-zero, we expect a continuation of the + // multi-octet sequence + if (0x80 == (0xC0 & ($in))) { + // Legal continuation. + $shift = ($mState - 1) * 6; + $tmp = $in; + $tmp = ($tmp & 0x0000003F) << $shift; + $mUcs4 |= $tmp; + + if (0 == --$mState) { + // End of the multi-octet sequence. mUcs4 now contains + // the final Unicode codepoint to be output + + // Check for illegal sequences and codepoints. + + // From Unicode 3.1, non-shortest form is illegal + if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || + ((3 == $mBytes) && ($mUcs4 < 0x0800)) || + ((4 == $mBytes) && ($mUcs4 < 0x10000)) || + (4 < $mBytes) || + // From Unicode 3.2, surrogate characters = illegal + (($mUcs4 & 0xFFFFF800) == 0xD800) || + // Codepoints outside the Unicode range are illegal + ($mUcs4 > 0x10FFFF) + ) { + + } elseif (0xFEFF != $mUcs4 && // omit BOM + // check for valid Char unicode codepoints + ( + 0x9 == $mUcs4 || + 0xA == $mUcs4 || + 0xD == $mUcs4 || + (0x20 <= $mUcs4 && 0x7E >= $mUcs4) || + // 7F-9F is not strictly prohibited by XML, + // but it is non-SGML, and thus we don't allow it + (0xA0 <= $mUcs4 && 0xD7FF >= $mUcs4) || + (0x10000 <= $mUcs4 && 0x10FFFF >= $mUcs4) + ) + ) { + $out .= $char; + } + // initialize UTF8 cache (reset) + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + $char = ''; + } + } else { + // ((0xC0 & (*in) != 0x80) && (mState != 0)) + // Incomplete multi-octet sequence. + // used to result in complete fail, but we'll reset + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + $char =''; + } + } + } + return $out; + } + + /** + * Translates a Unicode codepoint into its corresponding UTF-8 character. + * @note Based on Feyd's function at + * , + * which is in public domain. + * @note While we're going to do code point parsing anyway, a good + * optimization would be to refuse to translate code points that + * are non-SGML characters. However, this could lead to duplication. + * @note This is very similar to the unichr function in + * maintenance/generate-entity-file.php (although this is superior, + * due to its sanity checks). + */ + + // +----------+----------+----------+----------+ + // | 33222222 | 22221111 | 111111 | | + // | 10987654 | 32109876 | 54321098 | 76543210 | bit + // +----------+----------+----------+----------+ + // | | | | 0xxxxxxx | 1 byte 0x00000000..0x0000007F + // | | | 110yyyyy | 10xxxxxx | 2 byte 0x00000080..0x000007FF + // | | 1110zzzz | 10yyyyyy | 10xxxxxx | 3 byte 0x00000800..0x0000FFFF + // | 11110www | 10wwzzzz | 10yyyyyy | 10xxxxxx | 4 byte 0x00010000..0x0010FFFF + // +----------+----------+----------+----------+ + // | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF) + // | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes + // +----------+----------+----------+----------+ + + public static function unichr($code) + { + if ($code > 1114111 or $code < 0 or + ($code >= 55296 and $code <= 57343) ) { + // bits are set outside the "valid" range as defined + // by UNICODE 4.1.0 + return ''; + } + + $x = $y = $z = $w = 0; + if ($code < 128) { + // regular ASCII character + $x = $code; + } else { + // set up bits for UTF-8 + $x = ($code & 63) | 128; + if ($code < 2048) { + $y = (($code & 2047) >> 6) | 192; + } else { + $y = (($code & 4032) >> 6) | 128; + if ($code < 65536) { + $z = (($code >> 12) & 15) | 224; + } else { + $z = (($code >> 12) & 63) | 128; + $w = (($code >> 18) & 7) | 240; + } + } + } + // set up the actual character + $ret = ''; + if ($w) { + $ret .= chr($w); + } + if ($z) { + $ret .= chr($z); + } + if ($y) { + $ret .= chr($y); + } + $ret .= chr($x); + + return $ret; + } + + /** + * @return bool + */ + public static function iconvAvailable() + { + static $iconv = null; + if ($iconv === null) { + $iconv = function_exists('iconv') && self::testIconvTruncateBug() != self::ICONV_UNUSABLE; + } + return $iconv; + } + + /** + * Convert a string to UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public static function convertToUTF8($str, $config, $context) + { + $encoding = $config->get('Core.Encoding'); + if ($encoding === 'utf-8') { + return $str; + } + static $iconv = null; + if ($iconv === null) { + $iconv = self::iconvAvailable(); + } + if ($iconv && !$config->get('Test.ForceNoIconv')) { + // unaffected by bugs, since UTF-8 support all characters + $str = self::unsafeIconv($encoding, 'utf-8//IGNORE', $str); + if ($str === false) { + // $encoding is not a valid encoding + trigger_error('Invalid encoding ' . $encoding, E_USER_ERROR); + return ''; + } + // If the string is bjorked by Shift_JIS or a similar encoding + // that doesn't support all of ASCII, convert the naughty + // characters to their true byte-wise ASCII/UTF-8 equivalents. + $str = strtr($str, self::testEncodingSupportsASCII($encoding)); + return $str; + } elseif ($encoding === 'iso-8859-1') { + $str = utf8_encode($str); + return $str; + } + $bug = HTMLPurifier_Encoder::testIconvTruncateBug(); + if ($bug == self::ICONV_OK) { + trigger_error('Encoding not supported, please install iconv', E_USER_ERROR); + } else { + trigger_error( + 'You have a buggy version of iconv, see https://bugs.php.net/bug.php?id=48147 ' . + 'and http://sourceware.org/bugzilla/show_bug.cgi?id=13541', + E_USER_ERROR + ); + } + } + + /** + * Converts a string from UTF-8 based on configuration. + * @param string $str The string to convert + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + * @note Currently, this is a lossy conversion, with unexpressable + * characters being omitted. + */ + public static function convertFromUTF8($str, $config, $context) + { + $encoding = $config->get('Core.Encoding'); + if ($escape = $config->get('Core.EscapeNonASCIICharacters')) { + $str = self::convertToASCIIDumbLossless($str); + } + if ($encoding === 'utf-8') { + return $str; + } + static $iconv = null; + if ($iconv === null) { + $iconv = self::iconvAvailable(); + } + if ($iconv && !$config->get('Test.ForceNoIconv')) { + // Undo our previous fix in convertToUTF8, otherwise iconv will barf + $ascii_fix = self::testEncodingSupportsASCII($encoding); + if (!$escape && !empty($ascii_fix)) { + $clear_fix = array(); + foreach ($ascii_fix as $utf8 => $native) { + $clear_fix[$utf8] = ''; + } + $str = strtr($str, $clear_fix); + } + $str = strtr($str, array_flip($ascii_fix)); + // Normal stuff + $str = self::iconv('utf-8', $encoding . '//IGNORE', $str); + return $str; + } elseif ($encoding === 'iso-8859-1') { + $str = utf8_decode($str); + return $str; + } + trigger_error('Encoding not supported', E_USER_ERROR); + // You might be tempted to assume that the ASCII representation + // might be OK, however, this is *not* universally true over all + // encodings. So we take the conservative route here, rather + // than forcibly turn on %Core.EscapeNonASCIICharacters + } + + /** + * Lossless (character-wise) conversion of HTML to ASCII + * @param string $str UTF-8 string to be converted to ASCII + * @return string ASCII encoded string with non-ASCII character entity-ized + * @warning Adapted from MediaWiki, claiming fair use: this is a common + * algorithm. If you disagree with this license fudgery, + * implement it yourself. + * @note Uses decimal numeric entities since they are best supported. + * @note This is a DUMB function: it has no concept of keeping + * character entities that the projected character encoding + * can allow. We could possibly implement a smart version + * but that would require it to also know which Unicode + * codepoints the charset supported (not an easy task). + * @note Sort of with cleanUTF8() but it assumes that $str is + * well-formed UTF-8 + */ + public static function convertToASCIIDumbLossless($str) + { + $bytesleft = 0; + $result = ''; + $working = 0; + $len = strlen($str); + for ($i = 0; $i < $len; $i++) { + $bytevalue = ord($str[$i]); + if ($bytevalue <= 0x7F) { //0xxx xxxx + $result .= chr($bytevalue); + $bytesleft = 0; + } elseif ($bytevalue <= 0xBF) { //10xx xxxx + $working = $working << 6; + $working += ($bytevalue & 0x3F); + $bytesleft--; + if ($bytesleft <= 0) { + $result .= "&#" . $working . ";"; + } + } elseif ($bytevalue <= 0xDF) { //110x xxxx + $working = $bytevalue & 0x1F; + $bytesleft = 1; + } elseif ($bytevalue <= 0xEF) { //1110 xxxx + $working = $bytevalue & 0x0F; + $bytesleft = 2; + } else { //1111 0xxx + $working = $bytevalue & 0x07; + $bytesleft = 3; + } + } + return $result; + } + + /** No bugs detected in iconv. */ + const ICONV_OK = 0; + + /** Iconv truncates output if converting from UTF-8 to another + * character set with //IGNORE, and a non-encodable character is found */ + const ICONV_TRUNCATES = 1; + + /** Iconv does not support //IGNORE, making it unusable for + * transcoding purposes */ + const ICONV_UNUSABLE = 2; + + /** + * glibc iconv has a known bug where it doesn't handle the magic + * //IGNORE stanza correctly. In particular, rather than ignore + * characters, it will return an EILSEQ after consuming some number + * of characters, and expect you to restart iconv as if it were + * an E2BIG. Old versions of PHP did not respect the errno, and + * returned the fragment, so as a result you would see iconv + * mysteriously truncating output. We can work around this by + * manually chopping our input into segments of about 8000 + * characters, as long as PHP ignores the error code. If PHP starts + * paying attention to the error code, iconv becomes unusable. + * + * @return int Error code indicating severity of bug. + */ + public static function testIconvTruncateBug() + { + static $code = null; + if ($code === null) { + // better not use iconv, otherwise infinite loop! + $r = self::unsafeIconv('utf-8', 'ascii//IGNORE', "\xCE\xB1" . str_repeat('a', 9000)); + if ($r === false) { + $code = self::ICONV_UNUSABLE; + } elseif (($c = strlen($r)) < 9000) { + $code = self::ICONV_TRUNCATES; + } elseif ($c > 9000) { + trigger_error( + 'Your copy of iconv is extremely buggy. Please notify HTML Purifier maintainers: ' . + 'include your iconv version as per phpversion()', + E_USER_ERROR + ); + } else { + $code = self::ICONV_OK; + } + } + return $code; + } + + /** + * This expensive function tests whether or not a given character + * encoding supports ASCII. 7/8-bit encodings like Shift_JIS will + * fail this test, and require special processing. Variable width + * encodings shouldn't ever fail. + * + * @param string $encoding Encoding name to test, as per iconv format + * @param bool $bypass Whether or not to bypass the precompiled arrays. + * @return Array of UTF-8 characters to their corresponding ASCII, + * which can be used to "undo" any overzealous iconv action. + */ + public static function testEncodingSupportsASCII($encoding, $bypass = false) + { + // All calls to iconv here are unsafe, proof by case analysis: + // If ICONV_OK, no difference. + // If ICONV_TRUNCATE, all calls involve one character inputs, + // so bug is not triggered. + // If ICONV_UNUSABLE, this call is irrelevant + static $encodings = array(); + if (!$bypass) { + if (isset($encodings[$encoding])) { + return $encodings[$encoding]; + } + $lenc = strtolower($encoding); + switch ($lenc) { + case 'shift_jis': + return array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~'); + case 'johab': + return array("\xE2\x82\xA9" => '\\'); + } + if (strpos($lenc, 'iso-8859-') === 0) { + return array(); + } + } + $ret = array(); + if (self::unsafeIconv('UTF-8', $encoding, 'a') === false) { + return false; + } + for ($i = 0x20; $i <= 0x7E; $i++) { // all printable ASCII chars + $c = chr($i); // UTF-8 char + $r = self::unsafeIconv('UTF-8', "$encoding//IGNORE", $c); // initial conversion + if ($r === '' || + // This line is needed for iconv implementations that do not + // omit characters that do not exist in the target character set + ($r === $c && self::unsafeIconv($encoding, 'UTF-8//IGNORE', $r) !== $c) + ) { + // Reverse engineer: what's the UTF-8 equiv of this byte + // sequence? This assumes that there's no variable width + // encoding that doesn't support ASCII. + $ret[self::unsafeIconv($encoding, 'UTF-8//IGNORE', $c)] = $c; + } + } + $encodings[$encoding] = $ret; + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityLookup.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityLookup.php new file mode 100644 index 0000000000..f12ff13a35 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityLookup.php @@ -0,0 +1,48 @@ +table = unserialize(file_get_contents($file)); + } + + /** + * Retrieves sole instance of the object. + * @param bool|HTMLPurifier_EntityLookup $prototype Optional prototype of custom lookup table to overload with. + * @return HTMLPurifier_EntityLookup + */ + public static function instance($prototype = false) + { + // no references, since PHP doesn't copy unless modified + static $instance = null; + if ($prototype) { + $instance = $prototype; + } elseif (!$instance) { + $instance = new HTMLPurifier_EntityLookup(); + $instance->setup(); + } + return $instance; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityLookup/entities.ser b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityLookup/entities.ser new file mode 100644 index 0000000000..e8b08128be --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityLookup/entities.ser @@ -0,0 +1 @@ +a:253:{s:4:"fnof";s:2:"Æ";s:5:"Alpha";s:2:"Î";s:4:"Beta";s:2:"Î";s:5:"Gamma";s:2:"Î";s:5:"Delta";s:2:"Î";s:7:"Epsilon";s:2:"Î";s:4:"Zeta";s:2:"Î";s:3:"Eta";s:2:"Î";s:5:"Theta";s:2:"Î";s:4:"Iota";s:2:"Î";s:5:"Kappa";s:2:"Î";s:6:"Lambda";s:2:"Î";s:2:"Mu";s:2:"Î";s:2:"Nu";s:2:"Î";s:2:"Xi";s:2:"Î";s:7:"Omicron";s:2:"Î";s:2:"Pi";s:2:"Î ";s:3:"Rho";s:2:"Î¡";s:5:"Sigma";s:2:"Î£";s:3:"Tau";s:2:"Î¤";s:7:"Upsilon";s:2:"Î¥";s:3:"Phi";s:2:"Î¦";s:3:"Chi";s:2:"Î§";s:3:"Psi";s:2:"Î¨";s:5:"Omega";s:2:"Î©";s:5:"alpha";s:2:"Î±";s:4:"beta";s:2:"Î²";s:5:"gamma";s:2:"Î³";s:5:"delta";s:2:"Î´";s:7:"epsilon";s:2:"Îµ";s:4:"zeta";s:2:"Î¶";s:3:"eta";s:2:"Î·";s:5:"theta";s:2:"Î¸";s:4:"iota";s:2:"Î¹";s:5:"kappa";s:2:"Îº";s:6:"lambda";s:2:"Î»";s:2:"mu";s:2:"Î¼";s:2:"nu";s:2:"Î½";s:2:"xi";s:2:"Î¾";s:7:"omicron";s:2:"Î¿";s:2:"pi";s:2:"Ï";s:3:"rho";s:2:"Ï";s:6:"sigmaf";s:2:"Ï";s:5:"sigma";s:2:"Ï";s:3:"tau";s:2:"Ï";s:7:"upsilon";s:2:"Ï";s:3:"phi";s:2:"Ï";s:3:"chi";s:2:"Ï";s:3:"psi";s:2:"Ï";s:5:"omega";s:2:"Ï";s:8:"thetasym";s:2:"Ï";s:5:"upsih";s:2:"Ï";s:3:"piv";s:2:"Ï";s:4:"bull";s:3:"â¢";s:6:"hellip";s:3:"â¦";s:5:"prime";s:3:"â²";s:5:"Prime";s:3:"â³";s:5:"oline";s:3:"â¾";s:5:"frasl";s:3:"â";s:6:"weierp";s:3:"â";s:5:"image";s:3:"â";s:4:"real";s:3:"â";s:5:"trade";s:3:"â¢";s:7:"alefsym";s:3:"âµ";s:4:"larr";s:3:"â";s:4:"uarr";s:3:"â";s:4:"rarr";s:3:"â";s:4:"darr";s:3:"â";s:4:"harr";s:3:"â";s:5:"crarr";s:3:"âµ";s:4:"lArr";s:3:"â";s:4:"uArr";s:3:"â";s:4:"rArr";s:3:"â";s:4:"dArr";s:3:"â";s:4:"hArr";s:3:"â";s:6:"forall";s:3:"â";s:4:"part";s:3:"â";s:5:"exist";s:3:"â";s:5:"empty";s:3:"â";s:5:"nabla";s:3:"â";s:4:"isin";s:3:"â";s:5:"notin";s:3:"â";s:2:"ni";s:3:"â";s:4:"prod";s:3:"â";s:3:"sum";s:3:"â";s:5:"minus";s:3:"â";s:6:"lowast";s:3:"â";s:5:"radic";s:3:"â";s:4:"prop";s:3:"â";s:5:"infin";s:3:"â";s:3:"ang";s:3:"â ";s:3:"and";s:3:"â§";s:2:"or";s:3:"â¨";s:3:"cap";s:3:"â©";s:3:"cup";s:3:"âª";s:3:"int";s:3:"â«";s:6:"there4";s:3:"â´";s:3:"sim";s:3:"â¼";s:4:"cong";s:3:"â";s:5:"asymp";s:3:"â";s:2:"ne";s:3:"â ";s:5:"equiv";s:3:"â¡";s:2:"le";s:3:"â¤";s:2:"ge";s:3:"â¥";s:3:"sub";s:3:"â";s:3:"sup";s:3:"â";s:4:"nsub";s:3:"â";s:4:"sube";s:3:"â";s:4:"supe";s:3:"â";s:5:"oplus";s:3:"â";s:6:"otimes";s:3:"â";s:4:"perp";s:3:"â¥";s:4:"sdot";s:3:"â";s:5:"lceil";s:3:"â";s:5:"rceil";s:3:"â";s:6:"lfloor";s:3:"â";s:6:"rfloor";s:3:"â";s:4:"lang";s:3:"â©";s:4:"rang";s:3:"âª";s:3:"loz";s:3:"â";s:6:"spades";s:3:"â ";s:5:"clubs";s:3:"â£";s:6:"hearts";s:3:"â¥";s:5:"diams";s:3:"â¦";s:4:"quot";s:1:""";s:3:"amp";s:1:"&";s:2:"lt";s:1:"<";s:2:"gt";s:1:">";s:4:"apos";s:1:"'";s:5:"OElig";s:2:"Å";s:5:"oelig";s:2:"Å";s:6:"Scaron";s:2:"Å ";s:6:"scaron";s:2:"Å¡";s:4:"Yuml";s:2:"Å¸";s:4:"circ";s:2:"Ë";s:5:"tilde";s:2:"Ë";s:4:"ensp";s:3:"â";s:4:"emsp";s:3:"â";s:6:"thinsp";s:3:"â";s:4:"zwnj";s:3:"â";s:3:"zwj";s:3:"â";s:3:"lrm";s:3:"â";s:3:"rlm";s:3:"â";s:5:"ndash";s:3:"â";s:5:"mdash";s:3:"â";s:5:"lsquo";s:3:"â";s:5:"rsquo";s:3:"â";s:5:"sbquo";s:3:"â";s:5:"ldquo";s:3:"â";s:5:"rdquo";s:3:"â";s:5:"bdquo";s:3:"â";s:6:"dagger";s:3:"â ";s:6:"Dagger";s:3:"â¡";s:6:"permil";s:3:"â°";s:6:"lsaquo";s:3:"â¹";s:6:"rsaquo";s:3:"âº";s:4:"euro";s:3:"â¬";s:4:"nbsp";s:2:"Â ";s:5:"iexcl";s:2:"Â¡";s:4:"cent";s:2:"Â¢";s:5:"pound";s:2:"Â£";s:6:"curren";s:2:"Â¤";s:3:"yen";s:2:"Â¥";s:6:"brvbar";s:2:"Â¦";s:4:"sect";s:2:"Â§";s:3:"uml";s:2:"Â¨";s:4:"copy";s:2:"Â©";s:4:"ordf";s:2:"Âª";s:5:"laquo";s:2:"Â«";s:3:"not";s:2:"Â¬";s:3:"shy";s:2:"Â";s:3:"reg";s:2:"Â®";s:4:"macr";s:2:"Â¯";s:3:"deg";s:2:"Â°";s:6:"plusmn";s:2:"Â±";s:4:"sup2";s:2:"Â²";s:4:"sup3";s:2:"Â³";s:5:"acute";s:2:"Â´";s:5:"micro";s:2:"Âµ";s:4:"para";s:2:"Â¶";s:6:"middot";s:2:"Â·";s:5:"cedil";s:2:"Â¸";s:4:"sup1";s:2:"Â¹";s:4:"ordm";s:2:"Âº";s:5:"raquo";s:2:"Â»";s:6:"frac14";s:2:"Â¼";s:6:"frac12";s:2:"Â½";s:6:"frac34";s:2:"Â¾";s:6:"iquest";s:2:"Â¿";s:6:"Agrave";s:2:"Ã";s:6:"Aacute";s:2:"Ã";s:5:"Acirc";s:2:"Ã";s:6:"Atilde";s:2:"Ã";s:4:"Auml";s:2:"Ã";s:5:"Aring";s:2:"Ã";s:5:"AElig";s:2:"Ã";s:6:"Ccedil";s:2:"Ã";s:6:"Egrave";s:2:"Ã";s:6:"Eacute";s:2:"Ã";s:5:"Ecirc";s:2:"Ã";s:4:"Euml";s:2:"Ã";s:6:"Igrave";s:2:"Ã";s:6:"Iacute";s:2:"Ã";s:5:"Icirc";s:2:"Ã";s:4:"Iuml";s:2:"Ã";s:3:"ETH";s:2:"Ã";s:6:"Ntilde";s:2:"Ã";s:6:"Ograve";s:2:"Ã";s:6:"Oacute";s:2:"Ã";s:5:"Ocirc";s:2:"Ã";s:6:"Otilde";s:2:"Ã";s:4:"Ouml";s:2:"Ã";s:5:"times";s:2:"Ã";s:6:"Oslash";s:2:"Ã";s:6:"Ugrave";s:2:"Ã";s:6:"Uacute";s:2:"Ã";s:5:"Ucirc";s:2:"Ã";s:4:"Uuml";s:2:"Ã";s:6:"Yacute";s:2:"Ã";s:5:"THORN";s:2:"Ã";s:5:"szlig";s:2:"Ã";s:6:"agrave";s:2:"Ã ";s:6:"aacute";s:2:"Ã¡";s:5:"acirc";s:2:"Ã¢";s:6:"atilde";s:2:"Ã£";s:4:"auml";s:2:"Ã¤";s:5:"aring";s:2:"Ã¥";s:5:"aelig";s:2:"Ã¦";s:6:"ccedil";s:2:"Ã§";s:6:"egrave";s:2:"Ã¨";s:6:"eacute";s:2:"Ã©";s:5:"ecirc";s:2:"Ãª";s:4:"euml";s:2:"Ã«";s:6:"igrave";s:2:"Ã¬";s:6:"iacute";s:2:"Ã";s:5:"icirc";s:2:"Ã®";s:4:"iuml";s:2:"Ã¯";s:3:"eth";s:2:"Ã°";s:6:"ntilde";s:2:"Ã±";s:6:"ograve";s:2:"Ã²";s:6:"oacute";s:2:"Ã³";s:5:"ocirc";s:2:"Ã´";s:6:"otilde";s:2:"Ãµ";s:4:"ouml";s:2:"Ã¶";s:6:"divide";s:2:"Ã·";s:6:"oslash";s:2:"Ã¸";s:6:"ugrave";s:2:"Ã¹";s:6:"uacute";s:2:"Ãº";s:5:"ucirc";s:2:"Ã»";s:4:"uuml";s:2:"Ã¼";s:6:"yacute";s:2:"Ã½";s:5:"thorn";s:2:"Ã¾";s:4:"yuml";s:2:"Ã¿";} \ No newline at end of file diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php new file mode 100644 index 0000000000..61529dcd9d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/EntityParser.php @@ -0,0 +1,153 @@ + '"', + 38 => '&', + 39 => "'", + 60 => '<', + 62 => '>' + ); + + /** + * Stripped entity names to decimal conversion table for special entities. + * @type array + */ + protected $_special_ent2dec = + array( + 'quot' => 34, + 'amp' => 38, + 'lt' => 60, + 'gt' => 62 + ); + + /** + * Substitutes non-special entities with their parsed equivalents. Since + * running this whenever you have parsed character is t3h 5uck, we run + * it before everything else. + * + * @param string $string String to have non-special entities parsed. + * @return string Parsed string. + */ + public function substituteNonSpecialEntities($string) + { + // it will try to detect missing semicolons, but don't rely on it + return preg_replace_callback( + $this->_substituteEntitiesRegex, + array($this, 'nonSpecialEntityCallback'), + $string + ); + } + + /** + * Callback function for substituteNonSpecialEntities() that does the work. + * + * @param array $matches PCRE matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + + protected function nonSpecialEntityCallback($matches) + { + // replaces all but big five + $entity = $matches[0]; + $is_num = (@$matches[0][1] === '#'); + if ($is_num) { + $is_hex = (@$entity[2] === 'x'); + $code = $is_hex ? hexdec($matches[1]) : (int) $matches[2]; + // abort for special characters + if (isset($this->_special_dec2str[$code])) { + return $entity; + } + return HTMLPurifier_Encoder::unichr($code); + } else { + if (isset($this->_special_ent2dec[$matches[3]])) { + return $entity; + } + if (!$this->_entity_lookup) { + $this->_entity_lookup = HTMLPurifier_EntityLookup::instance(); + } + if (isset($this->_entity_lookup->table[$matches[3]])) { + return $this->_entity_lookup->table[$matches[3]]; + } else { + return $entity; + } + } + } + + /** + * Substitutes only special entities with their parsed equivalents. + * + * @notice We try to avoid calling this function because otherwise, it + * would have to be called a lot (for every parsed section). + * + * @param string $string String to have non-special entities parsed. + * @return string Parsed string. + */ + public function substituteSpecialEntities($string) + { + return preg_replace_callback( + $this->_substituteEntitiesRegex, + array($this, 'specialEntityCallback'), + $string + ); + } + + /** + * Callback function for substituteSpecialEntities() that does the work. + * + * This callback has same syntax as nonSpecialEntityCallback(). + * + * @param array $matches PCRE-style matches array, with 0 the entire match, and + * either index 1, 2 or 3 set with a hex value, dec value, + * or string (respectively). + * @return string Replacement string. + */ + protected function specialEntityCallback($matches) + { + $entity = $matches[0]; + $is_num = (@$matches[0][1] === '#'); + if ($is_num) { + $is_hex = (@$entity[2] === 'x'); + $int = $is_hex ? hexdec($matches[1]) : (int) $matches[2]; + return isset($this->_special_dec2str[$int]) ? + $this->_special_dec2str[$int] : + $entity; + } else { + return isset($this->_special_ent2dec[$matches[3]]) ? + $this->_special_ent2dec[$matches[3]] : + $entity; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ErrorCollector.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ErrorCollector.php new file mode 100644 index 0000000000..d47e3f2e24 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ErrorCollector.php @@ -0,0 +1,244 @@ +locale =& $context->get('Locale'); + $this->context = $context; + $this->_current =& $this->_stacks[0]; + $this->errors =& $this->_stacks[0]; + } + + /** + * Sends an error message to the collector for later use + * @param int $severity Error severity, PHP error style (don't use E_USER_) + * @param string $msg Error message text + */ + public function send($severity, $msg) + { + $args = array(); + if (func_num_args() > 2) { + $args = func_get_args(); + array_shift($args); + unset($args[0]); + } + + $token = $this->context->get('CurrentToken', true); + $line = $token ? $token->line : $this->context->get('CurrentLine', true); + $col = $token ? $token->col : $this->context->get('CurrentCol', true); + $attr = $this->context->get('CurrentAttr', true); + + // perform special substitutions, also add custom parameters + $subst = array(); + if (!is_null($token)) { + $args['CurrentToken'] = $token; + } + if (!is_null($attr)) { + $subst['$CurrentAttr.Name'] = $attr; + if (isset($token->attr[$attr])) { + $subst['$CurrentAttr.Value'] = $token->attr[$attr]; + } + } + + if (empty($args)) { + $msg = $this->locale->getMessage($msg); + } else { + $msg = $this->locale->formatMessage($msg, $args); + } + + if (!empty($subst)) { + $msg = strtr($msg, $subst); + } + + // (numerically indexed) + $error = array( + self::LINENO => $line, + self::SEVERITY => $severity, + self::MESSAGE => $msg, + self::CHILDREN => array() + ); + $this->_current[] = $error; + + // NEW CODE BELOW ... + // Top-level errors are either: + // TOKEN type, if $value is set appropriately, or + // "syntax" type, if $value is null + $new_struct = new HTMLPurifier_ErrorStruct(); + $new_struct->type = HTMLPurifier_ErrorStruct::TOKEN; + if ($token) { + $new_struct->value = clone $token; + } + if (is_int($line) && is_int($col)) { + if (isset($this->lines[$line][$col])) { + $struct = $this->lines[$line][$col]; + } else { + $struct = $this->lines[$line][$col] = $new_struct; + } + // These ksorts may present a performance problem + ksort($this->lines[$line], SORT_NUMERIC); + } else { + if (isset($this->lines[-1])) { + $struct = $this->lines[-1]; + } else { + $struct = $this->lines[-1] = $new_struct; + } + } + ksort($this->lines, SORT_NUMERIC); + + // Now, check if we need to operate on a lower structure + if (!empty($attr)) { + $struct = $struct->getChild(HTMLPurifier_ErrorStruct::ATTR, $attr); + if (!$struct->value) { + $struct->value = array($attr, 'PUT VALUE HERE'); + } + } + if (!empty($cssprop)) { + $struct = $struct->getChild(HTMLPurifier_ErrorStruct::CSSPROP, $cssprop); + if (!$struct->value) { + // if we tokenize CSS this might be a little more difficult to do + $struct->value = array($cssprop, 'PUT VALUE HERE'); + } + } + + // Ok, structs are all setup, now time to register the error + $struct->addError($severity, $msg); + } + + /** + * Retrieves raw error data for custom formatter to use + */ + public function getRaw() + { + return $this->errors; + } + + /** + * Default HTML formatting implementation for error messages + * @param HTMLPurifier_Config $config Configuration, vital for HTML output nature + * @param array $errors Errors array to display; used for recursion. + * @return string + */ + public function getHTMLFormatted($config, $errors = null) + { + $ret = array(); + + $this->generator = new HTMLPurifier_Generator($config, $this->context); + if ($errors === null) { + $errors = $this->errors; + } + + // 'At line' message needs to be removed + + // generation code for new structure goes here. It needs to be recursive. + foreach ($this->lines as $line => $col_array) { + if ($line == -1) { + continue; + } + foreach ($col_array as $col => $struct) { + $this->_renderStruct($ret, $struct, $line, $col); + } + } + if (isset($this->lines[-1])) { + $this->_renderStruct($ret, $this->lines[-1]); + } + + if (empty($errors)) { + return '

' . $this->locale->getMessage('ErrorCollector: No errors') . '

'; + } else { + return '

' . implode('
', $ret) . '

'; + } + + } + + private function _renderStruct(&$ret, $struct, $line = null, $col = null) + { + $stack = array($struct); + $context_stack = array(array()); + while ($current = array_pop($stack)) { + $context = array_pop($context_stack); + foreach ($current->errors as $error) { + list($severity, $msg) = $error; + $string = ''; + $string .= '

'; + // W3C uses an icon to indicate the severity of the error. + $error = $this->locale->getErrorName($severity); + $string .= "$error "; + if (!is_null($line) && !is_null($col)) { + $string .= "Line $line, Column $col: "; + } else { + $string .= 'End of Document: '; + } + $string .= '' . $this->generator->escape($msg) . ' '; + $string .= '

'; + // Here, have a marker for the character on the column appropriate. + // Be sure to clip extremely long lines. + //$string .= '

';
+                //$string .= '';
+                //$string .= '

'; + $ret[] = $string; + } + foreach ($current->children as $array) { + $context[] = $current; + $stack = array_merge($stack, array_reverse($array, true)); + for ($i = count($array); $i > 0; $i--) { + $context_stack[] = $context; + } + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ErrorStruct.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ErrorStruct.php new file mode 100644 index 0000000000..cf869d3212 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/ErrorStruct.php @@ -0,0 +1,74 @@ +children[$type][$id])) { + $this->children[$type][$id] = new HTMLPurifier_ErrorStruct(); + $this->children[$type][$id]->type = $type; + } + return $this->children[$type][$id]; + } + + /** + * @param int $severity + * @param string $message + */ + public function addError($severity, $message) + { + $this->errors[] = array($severity, $message); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Exception.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Exception.php new file mode 100644 index 0000000000..be85b4c560 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Exception.php @@ -0,0 +1,12 @@ +preFilter, + * 2->preFilter, 3->preFilter, purify, 3->postFilter, 2->postFilter, + * 1->postFilter. + * + * @note Methods are not declared abstract as it is perfectly legitimate + * for an implementation not to want anything to happen on a step + */ + +class HTMLPurifier_Filter +{ + + /** + * Name of the filter for identification purposes. + * @type string + */ + public $name; + + /** + * Pre-processor function, handles HTML before HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function preFilter($html, $config, $context) + { + return $html; + } + + /** + * Post-processor function, handles HTML after HTML Purifier + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + return $html; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Filter/ExtractStyleBlocks.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Filter/ExtractStyleBlocks.php new file mode 100644 index 0000000000..08e62c16bf --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Filter/ExtractStyleBlocks.php @@ -0,0 +1,338 @@ + blocks from input HTML, cleans them up + * using CSSTidy, and then places them in $purifier->context->get('StyleBlocks') + * so they can be used elsewhere in the document. + * + * @note + * See tests/HTMLPurifier/Filter/ExtractStyleBlocksTest.php for + * sample usage. + * + * @note + * This filter can also be used on stylesheets not included in the + * document--something purists would probably prefer. Just directly + * call HTMLPurifier_Filter_ExtractStyleBlocks->cleanCSS() + */ +class HTMLPurifier_Filter_ExtractStyleBlocks extends HTMLPurifier_Filter +{ + /** + * @type string + */ + public $name = 'ExtractStyleBlocks'; + + /** + * @type array + */ + private $_styleMatches = array(); + + /** + * @type csstidy + */ + private $_tidy; + + /** + * @type HTMLPurifier_AttrDef_HTML_ID + */ + private $_id_attrdef; + + /** + * @type HTMLPurifier_AttrDef_CSS_Ident + */ + private $_class_attrdef; + + /** + * @type HTMLPurifier_AttrDef_Enum + */ + private $_enum_attrdef; + + public function __construct() + { + $this->_tidy = new csstidy(); + $this->_tidy->set_cfg('lowercase_s', false); + $this->_id_attrdef = new HTMLPurifier_AttrDef_HTML_ID(true); + $this->_class_attrdef = new HTMLPurifier_AttrDef_CSS_Ident(); + $this->_enum_attrdef = new HTMLPurifier_AttrDef_Enum( + array( + 'first-child', + 'link', + 'visited', + 'active', + 'hover', + 'focus' + ) + ); + } + + /** + * Save the contents of CSS blocks to style matches + * @param array $matches preg_replace style $matches array + */ + protected function styleCallback($matches) + { + $this->_styleMatches[] = $matches[1]; + } + + /** + * Removes inline #isU', array($this, 'styleCallback'), $html); + $style_blocks = $this->_styleMatches; + $this->_styleMatches = array(); // reset + $context->register('StyleBlocks', $style_blocks); // $context must not be reused + if ($this->_tidy) { + foreach ($style_blocks as &$style) { + $style = $this->cleanCSS($style, $config, $context); + } + } + return $html; + } + + /** + * Takes CSS (the stuff found in in a font-family prop). + if ($config->get('Filter.ExtractStyleBlocks.Escaping')) { + $css = str_replace( + array('<', '>', '&'), + array('\3C ', '\3E ', '\26 '), + $css + ); + } + return $css; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Filter/YouTube.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Filter/YouTube.php new file mode 100644 index 0000000000..276d8362fa --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Filter/YouTube.php @@ -0,0 +1,65 @@ +]+>.+?' . + '(?:http:)?//www.youtube.com/((?:v|cp)/[A-Za-z0-9\-_=]+).+?#s'; + $pre_replace = '\1'; + return preg_replace($pre_regex, $pre_replace, $html); + } + + /** + * @param string $html + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function postFilter($html, $config, $context) + { + $post_regex = '#((?:v|cp)/[A-Za-z0-9\-_=]+)#'; + return preg_replace_callback($post_regex, array($this, 'postFilterCallback'), $html); + } + + /** + * @param $url + * @return string + */ + protected function armorUrl($url) + { + return str_replace('--', '--', $url); + } + + /** + * @param array $matches + * @return string + */ + protected function postFilterCallback($matches) + { + $url = $this->armorUrl($matches[1]); + return '

'; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Generator.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Generator.php new file mode 100644 index 0000000000..6fb5687146 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Generator.php @@ -0,0 +1,286 @@ + tags. + * @type bool + */ + private $_scriptFix = false; + + /** + * Cache of HTMLDefinition during HTML output to determine whether or + * not attributes should be minimized. + * @type HTMLPurifier_HTMLDefinition + */ + private $_def; + + /** + * Cache of %Output.SortAttr. + * @type bool + */ + private $_sortAttr; + + /** + * Cache of %Output.FlashCompat. + * @type bool + */ + private $_flashCompat; + + /** + * Cache of %Output.FixInnerHTML. + * @type bool + */ + private $_innerHTMLFix; + + /** + * Stack for keeping track of object information when outputting IE + * compatibility code. + * @type array + */ + private $_flashStack = array(); + + /** + * Configuration for the generator + * @type HTMLPurifier_Config + */ + protected $config; + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + public function __construct($config, $context) + { + $this->config = $config; + $this->_scriptFix = $config->get('Output.CommentScriptContents'); + $this->_innerHTMLFix = $config->get('Output.FixInnerHTML'); + $this->_sortAttr = $config->get('Output.SortAttr'); + $this->_flashCompat = $config->get('Output.FlashCompat'); + $this->_def = $config->getHTMLDefinition(); + $this->_xhtml = $this->_def->doctype->xml; + } + + /** + * Generates HTML from an array of tokens. + * @param HTMLPurifier_Token[] $tokens Array of HTMLPurifier_Token + * @return string Generated HTML + */ + public function generateFromTokens($tokens) + { + if (!$tokens) { + return ''; + } + + // Basic algorithm + $html = ''; + for ($i = 0, $size = count($tokens); $i < $size; $i++) { + if ($this->_scriptFix && $tokens[$i]->name === 'script' + && $i + 2 < $size && $tokens[$i+2] instanceof HTMLPurifier_Token_End) { + // script special case + // the contents of the script block must be ONE token + // for this to work. + $html .= $this->generateFromToken($tokens[$i++]); + $html .= $this->generateScriptFromToken($tokens[$i++]); + } + $html .= $this->generateFromToken($tokens[$i]); + } + + // Tidy cleanup + if (extension_loaded('tidy') && $this->config->get('Output.TidyFormat')) { + $tidy = new Tidy; + $tidy->parseString( + $html, + array( + 'indent'=> true, + 'output-xhtml' => $this->_xhtml, + 'show-body-only' => true, + 'indent-spaces' => 2, + 'wrap' => 68, + ), + 'utf8' + ); + $tidy->cleanRepair(); + $html = (string) $tidy; // explicit cast necessary + } + + // Normalize newlines to system defined value + if ($this->config->get('Core.NormalizeNewlines')) { + $nl = $this->config->get('Output.Newline'); + if ($nl === null) { + $nl = PHP_EOL; + } + if ($nl !== "\n") { + $html = str_replace("\n", $nl, $html); + } + } + return $html; + } + + /** + * Generates HTML from a single token. + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string Generated HTML + */ + public function generateFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token) { + trigger_error('Cannot generate HTML from non-HTMLPurifier_Token object', E_USER_WARNING); + return ''; + + } elseif ($token instanceof HTMLPurifier_Token_Start) { + $attr = $this->generateAttributes($token->attr, $token->name); + if ($this->_flashCompat) { + if ($token->name == "object") { + $flash = new stdclass(); + $flash->attr = $token->attr; + $flash->param = array(); + $this->_flashStack[] = $flash; + } + } + return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_End) { + $_extra = ''; + if ($this->_flashCompat) { + if ($token->name == "object" && !empty($this->_flashStack)) { + // doesn't do anything for now + } + } + return $_extra . 'name . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + if ($this->_flashCompat && $token->name == "param" && !empty($this->_flashStack)) { + $this->_flashStack[count($this->_flashStack)-1]->param[$token->attr['name']] = $token->attr['value']; + } + $attr = $this->generateAttributes($token->attr, $token->name); + return '<' . $token->name . ($attr ? ' ' : '') . $attr . + ( $this->_xhtml ? ' /': '' ) //
v.
+ . '>'; + + } elseif ($token instanceof HTMLPurifier_Token_Text) { + return $this->escape($token->data, ENT_NOQUOTES); + + } elseif ($token instanceof HTMLPurifier_Token_Comment) { + return ''; + } else { + return ''; + + } + } + + /** + * Special case processor for the contents of script tags + * @param HTMLPurifier_Token $token HTMLPurifier_Token object. + * @return string + * @warning This runs into problems if there's already a literal + * --> somewhere inside the script contents. + */ + public function generateScriptFromToken($token) + { + if (!$token instanceof HTMLPurifier_Token_Text) { + return $this->generateFromToken($token); + } + // Thanks + $data = preg_replace('#//\s*$#', '', $token->data); + return ''; + } + + /** + * Generates attribute declarations from attribute array. + * @note This does not include the leading or trailing space. + * @param array $assoc_array_of_attributes Attribute array + * @param string $element Name of element attributes are for, used to check + * attribute minimization. + * @return string Generated HTML fragment for insertion. + */ + public function generateAttributes($assoc_array_of_attributes, $element = '') + { + $html = ''; + if ($this->_sortAttr) { + ksort($assoc_array_of_attributes); + } + foreach ($assoc_array_of_attributes as $key => $value) { + if (!$this->_xhtml) { + // Remove namespaced attributes + if (strpos($key, ':') !== false) { + continue; + } + // Check if we should minimize the attribute: val="val" -> val + if ($element && !empty($this->_def->info[$element]->attr[$key]->minimized)) { + $html .= $key . ' '; + continue; + } + } + // Workaround for Internet Explorer innerHTML bug. + // Essentially, Internet Explorer, when calculating + // innerHTML, omits quotes if there are no instances of + // angled brackets, quotes or spaces. However, when parsing + // HTML (for example, when you assign to innerHTML), it + // treats backticks as quotes. Thus, + //

+ // becomes + //

+ // becomes + // + // Fortunately, all we need to do is trigger an appropriate + // quoting style, which we do by adding an extra space. + // This also is consistent with the W3C spec, which states + // that user agents may ignore leading or trailing + // whitespace (in fact, most don't, at least for attributes + // like alt, but an extra space at the end is barely + // noticeable). Still, we have a configuration knob for + // this, since this transformation is not necesary if you + // don't process user input with innerHTML or you don't plan + // on supporting Internet Explorer. + if ($this->_innerHTMLFix) { + if (strpos($value, '`') !== false) { + // check if correct quoting style would not already be + // triggered + if (strcspn($value, '"\' <>') === strlen($value)) { + // protect! + $value .= ' '; + } + } + } + $html .= $key.'="'.$this->escape($value).'" '; + } + return rtrim($html); + } + + /** + * Escapes raw text data. + * @todo This really ought to be protected, but until we have a facility + * for properly generating HTML here w/o using tokens, it stays + * public. + * @param string $string String data to escape for HTML. + * @param int $quote Quoting style, like htmlspecialchars. ENT_NOQUOTES is + * permissible for non-attribute output. + * @return string escaped data. + */ + public function escape($string, $quote = null) + { + // Workaround for APC bug on Mac Leopard reported by sidepodcast + // http://htmlpurifier.org/phorum/read.php?3,4823,4846 + if ($quote === null) { + $quote = ENT_COMPAT; + } + return htmlspecialchars($string, $quote, 'UTF-8'); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLDefinition.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLDefinition.php new file mode 100644 index 0000000000..9b7b334dd9 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLDefinition.php @@ -0,0 +1,493 @@ +getAnonymousModule(); + if (!isset($module->info[$element_name])) { + $element = $module->addBlankElement($element_name); + } else { + $element = $module->info[$element_name]; + } + $element->attr[$attr_name] = $def; + } + + /** + * Adds a custom element to your HTML definition + * @see HTMLPurifier_HTMLModule::addElement() for detailed + * parameter and return value descriptions. + */ + public function addElement($element_name, $type, $contents, $attr_collections, $attributes = array()) + { + $module = $this->getAnonymousModule(); + // assume that if the user is calling this, the element + // is safe. This may not be a good idea + $element = $module->addElement($element_name, $type, $contents, $attr_collections, $attributes); + return $element; + } + + /** + * Adds a blank element to your HTML definition, for overriding + * existing behavior + * @param string $element_name + * @return HTMLPurifier_ElementDef + * @see HTMLPurifier_HTMLModule::addBlankElement() for detailed + * parameter and return value descriptions. + */ + public function addBlankElement($element_name) + { + $module = $this->getAnonymousModule(); + $element = $module->addBlankElement($element_name); + return $element; + } + + /** + * Retrieves a reference to the anonymous module, so you can + * bust out advanced features without having to make your own + * module. + * @return HTMLPurifier_HTMLModule + */ + public function getAnonymousModule() + { + if (!$this->_anonModule) { + $this->_anonModule = new HTMLPurifier_HTMLModule(); + $this->_anonModule->name = 'Anonymous'; + } + return $this->_anonModule; + } + + private $_anonModule = null; + + // PUBLIC BUT INTERNAL VARIABLES -------------------------------------- + + /** + * @type string + */ + public $type = 'HTML'; + + /** + * @type HTMLPurifier_HTMLModuleManager + */ + public $manager; + + /** + * Performs low-cost, preliminary initialization. + */ + public function __construct() + { + $this->manager = new HTMLPurifier_HTMLModuleManager(); + } + + /** + * @param HTMLPurifier_Config $config + */ + protected function doSetup($config) + { + $this->processModules($config); + $this->setupConfigStuff($config); + unset($this->manager); + + // cleanup some of the element definitions + foreach ($this->info as $k => $v) { + unset($this->info[$k]->content_model); + unset($this->info[$k]->content_model_type); + } + } + + /** + * Extract out the information from the manager + * @param HTMLPurifier_Config $config + */ + protected function processModules($config) + { + if ($this->_anonModule) { + // for user specific changes + // this is late-loaded so we don't have to deal with PHP4 + // reference wonky-ness + $this->manager->addModule($this->_anonModule); + unset($this->_anonModule); + } + + $this->manager->setup($config); + $this->doctype = $this->manager->doctype; + + foreach ($this->manager->modules as $module) { + foreach ($module->info_tag_transform as $k => $v) { + if ($v === false) { + unset($this->info_tag_transform[$k]); + } else { + $this->info_tag_transform[$k] = $v; + } + } + foreach ($module->info_attr_transform_pre as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_pre[$k]); + } else { + $this->info_attr_transform_pre[$k] = $v; + } + } + foreach ($module->info_attr_transform_post as $k => $v) { + if ($v === false) { + unset($this->info_attr_transform_post[$k]); + } else { + $this->info_attr_transform_post[$k] = $v; + } + } + foreach ($module->info_injector as $k => $v) { + if ($v === false) { + unset($this->info_injector[$k]); + } else { + $this->info_injector[$k] = $v; + } + } + } + $this->info = $this->manager->getElements(); + $this->info_content_sets = $this->manager->contentSets->lookup; + } + + /** + * Sets up stuff based on config. We need a better way of doing this. + * @param HTMLPurifier_Config $config + */ + protected function setupConfigStuff($config) + { + $block_wrapper = $config->get('HTML.BlockWrapper'); + if (isset($this->info_content_sets['Block'][$block_wrapper])) { + $this->info_block_wrapper = $block_wrapper; + } else { + trigger_error( + 'Cannot use non-block element as block wrapper', + E_USER_ERROR + ); + } + + $parent = $config->get('HTML.Parent'); + $def = $this->manager->getElement($parent, true); + if ($def) { + $this->info_parent = $parent; + $this->info_parent_def = $def; + } else { + trigger_error( + 'Cannot use unrecognized element as parent', + E_USER_ERROR + ); + $this->info_parent_def = $this->manager->getElement($this->info_parent, true); + } + + // support template text + $support = "(for information on implementing this, see the support forums) "; + + // setup allowed elements ----------------------------------------- + + $allowed_elements = $config->get('HTML.AllowedElements'); + $allowed_attributes = $config->get('HTML.AllowedAttributes'); // retrieve early + + if (!is_array($allowed_elements) && !is_array($allowed_attributes)) { + $allowed = $config->get('HTML.Allowed'); + if (is_string($allowed)) { + list($allowed_elements, $allowed_attributes) = $this->parseTinyMCEAllowedList($allowed); + } + } + + if (is_array($allowed_elements)) { + foreach ($this->info as $name => $d) { + if (!isset($allowed_elements[$name])) { + unset($this->info[$name]); + } + unset($allowed_elements[$name]); + } + // emit errors + foreach ($allowed_elements as $element => $d) { + $element = htmlspecialchars($element); // PHP doesn't escape errors, be careful! + trigger_error("Element '$element' is not supported $support", E_USER_WARNING); + } + } + + // setup allowed attributes --------------------------------------- + + $allowed_attributes_mutable = $allowed_attributes; // by copy! + if (is_array($allowed_attributes)) { + // This actually doesn't do anything, since we went away from + // global attributes. It's possible that userland code uses + // it, but HTMLModuleManager doesn't! + foreach ($this->info_global_attr as $attr => $x) { + $keys = array($attr, "*@$attr", "*.$attr"); + $delete = true; + foreach ($keys as $key) { + if ($delete && isset($allowed_attributes[$key])) { + $delete = false; + } + if (isset($allowed_attributes_mutable[$key])) { + unset($allowed_attributes_mutable[$key]); + } + } + if ($delete) { + unset($this->info_global_attr[$attr]); + } + } + + foreach ($this->info as $tag => $info) { + foreach ($info->attr as $attr => $x) { + $keys = array("$tag@$attr", $attr, "*@$attr", "$tag.$attr", "*.$attr"); + $delete = true; + foreach ($keys as $key) { + if ($delete && isset($allowed_attributes[$key])) { + $delete = false; + } + if (isset($allowed_attributes_mutable[$key])) { + unset($allowed_attributes_mutable[$key]); + } + } + if ($delete) { + if ($this->info[$tag]->attr[$attr]->required) { + trigger_error( + "Required attribute '$attr' in element '$tag' " . + "was not allowed, which means '$tag' will not be allowed either", + E_USER_WARNING + ); + } + unset($this->info[$tag]->attr[$attr]); + } + } + } + // emit errors + foreach ($allowed_attributes_mutable as $elattr => $d) { + $bits = preg_split('/[.@]/', $elattr, 2); + $c = count($bits); + switch ($c) { + case 2: + if ($bits[0] !== '*') { + $element = htmlspecialchars($bits[0]); + $attribute = htmlspecialchars($bits[1]); + if (!isset($this->info[$element])) { + trigger_error( + "Cannot allow attribute '$attribute' if element " . + "'$element' is not allowed/supported $support" + ); + } else { + trigger_error( + "Attribute '$attribute' in element '$element' not supported $support", + E_USER_WARNING + ); + } + break; + } + // otherwise fall through + case 1: + $attribute = htmlspecialchars($bits[0]); + trigger_error( + "Global attribute '$attribute' is not ". + "supported in any elements $support", + E_USER_WARNING + ); + break; + } + } + } + + // setup forbidden elements --------------------------------------- + + $forbidden_elements = $config->get('HTML.ForbiddenElements'); + $forbidden_attributes = $config->get('HTML.ForbiddenAttributes'); + + foreach ($this->info as $tag => $info) { + if (isset($forbidden_elements[$tag])) { + unset($this->info[$tag]); + continue; + } + foreach ($info->attr as $attr => $x) { + if (isset($forbidden_attributes["$tag@$attr"]) || + isset($forbidden_attributes["*@$attr"]) || + isset($forbidden_attributes[$attr]) + ) { + unset($this->info[$tag]->attr[$attr]); + continue; + } elseif (isset($forbidden_attributes["$tag.$attr"])) { // this segment might get removed eventually + // $tag.$attr are not user supplied, so no worries! + trigger_error( + "Error with $tag.$attr: tag.attr syntax not supported for " . + "HTML.ForbiddenAttributes; use tag@attr instead", + E_USER_WARNING + ); + } + } + } + foreach ($forbidden_attributes as $key => $v) { + if (strlen($key) < 2) { + continue; + } + if ($key[0] != '*') { + continue; + } + if ($key[1] == '.') { + trigger_error( + "Error with $key: *.attr syntax not supported for HTML.ForbiddenAttributes; use attr instead", + E_USER_WARNING + ); + } + } + + // setup injectors ----------------------------------------------------- + foreach ($this->info_injector as $i => $injector) { + if ($injector->checkNeeded($config) !== false) { + // remove injector that does not have it's required + // elements/attributes present, and is thus not needed. + unset($this->info_injector[$i]); + } + } + } + + /** + * Parses a TinyMCE-flavored Allowed Elements and Attributes list into + * separate lists for processing. Format is element[attr1|attr2],element2... + * @warning Although it's largely drawn from TinyMCE's implementation, + * it is different, and you'll probably have to modify your lists + * @param array $list String list to parse + * @return array + * @todo Give this its own class, probably static interface + */ + public function parseTinyMCEAllowedList($list) + { + $list = str_replace(array(' ', "\t"), '', $list); + + $elements = array(); + $attributes = array(); + + $chunks = preg_split('/(,|[\n\r]+)/', $list); + foreach ($chunks as $chunk) { + if (empty($chunk)) { + continue; + } + // remove TinyMCE element control characters + if (!strpos($chunk, '[')) { + $element = $chunk; + $attr = false; + } else { + list($element, $attr) = explode('[', $chunk); + } + if ($element !== '*') { + $elements[$element] = true; + } + if (!$attr) { + continue; + } + $attr = substr($attr, 0, strlen($attr) - 1); // remove trailing ] + $attr = explode('|', $attr); + foreach ($attr as $key) { + $attributes["$element.$key"] = true; + } + } + return array($elements, $attributes); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule.php new file mode 100644 index 0000000000..bb3a9230b1 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule.php @@ -0,0 +1,284 @@ +info, since the object's data is only info, + * with extra behavior associated with it. + * @type array + */ + public $attr_collections = array(); + + /** + * Associative array of deprecated tag name to HTMLPurifier_TagTransform. + * @type array + */ + public $info_tag_transform = array(); + + /** + * List of HTMLPurifier_AttrTransform to be performed before validation. + * @type array + */ + public $info_attr_transform_pre = array(); + + /** + * List of HTMLPurifier_AttrTransform to be performed after validation. + * @type array + */ + public $info_attr_transform_post = array(); + + /** + * List of HTMLPurifier_Injector to be performed during well-formedness fixing. + * An injector will only be invoked if all of it's pre-requisites are met; + * if an injector fails setup, there will be no error; it will simply be + * silently disabled. + * @type array + */ + public $info_injector = array(); + + /** + * Boolean flag that indicates whether or not getChildDef is implemented. + * For optimization reasons: may save a call to a function. Be sure + * to set it if you do implement getChildDef(), otherwise it will have + * no effect! + * @type bool + */ + public $defines_child_def = false; + + /** + * Boolean flag whether or not this module is safe. If it is not safe, all + * of its members are unsafe. Modules are safe by default (this might be + * slightly dangerous, but it doesn't make much sense to force HTML Purifier, + * which is based off of safe HTML, to explicitly say, "This is safe," even + * though there are modules which are "unsafe") + * + * @type bool + * @note Previously, safety could be applied at an element level granularity. + * We've removed this ability, so in order to add "unsafe" elements + * or attributes, a dedicated module with this property set to false + * must be used. + */ + public $safe = true; + + /** + * Retrieves a proper HTMLPurifier_ChildDef subclass based on + * content_model and content_model_type member variables of + * the HTMLPurifier_ElementDef class. There is a similar function + * in HTMLPurifier_HTMLDefinition. + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef subclass + */ + public function getChildDef($def) + { + return false; + } + + // -- Convenience ----------------------------------------------------- + + /** + * Convenience function that sets up a new element + * @param string $element Name of element to add + * @param string|bool $type What content set should element be registered to? + * Set as false to skip this step. + * @param string $contents Allowed children in form of: + * "$content_model_type: $content_model" + * @param array $attr_includes What attribute collections to register to + * element? + * @param array $attr What unique attributes does the element define? + * @see HTMLPurifier_ElementDef:: for in-depth descriptions of these parameters. + * @return HTMLPurifier_ElementDef Created element definition object, so you + * can set advanced parameters + */ + public function addElement($element, $type, $contents, $attr_includes = array(), $attr = array()) + { + $this->elements[] = $element; + // parse content_model + list($content_model_type, $content_model) = $this->parseContents($contents); + // merge in attribute inclusions + $this->mergeInAttrIncludes($attr, $attr_includes); + // add element to content sets + if ($type) { + $this->addElementToContentSet($element, $type); + } + // create element + $this->info[$element] = HTMLPurifier_ElementDef::create( + $content_model, + $content_model_type, + $attr + ); + // literal object $contents means direct child manipulation + if (!is_string($contents)) { + $this->info[$element]->child = $contents; + } + return $this->info[$element]; + } + + /** + * Convenience function that creates a totally blank, non-standalone + * element. + * @param string $element Name of element to create + * @return HTMLPurifier_ElementDef Created element + */ + public function addBlankElement($element) + { + if (!isset($this->info[$element])) { + $this->elements[] = $element; + $this->info[$element] = new HTMLPurifier_ElementDef(); + $this->info[$element]->standalone = false; + } else { + trigger_error("Definition for $element already exists in module, cannot redefine"); + } + return $this->info[$element]; + } + + /** + * Convenience function that registers an element to a content set + * @param string $element Element to register + * @param string $type Name content set (warning: case sensitive, usually upper-case + * first letter) + */ + public function addElementToContentSet($element, $type) + { + if (!isset($this->content_sets[$type])) { + $this->content_sets[$type] = ''; + } else { + $this->content_sets[$type] .= ' | '; + } + $this->content_sets[$type] .= $element; + } + + /** + * Convenience function that transforms single-string contents + * into separate content model and content model type + * @param string $contents Allowed children in form of: + * "$content_model_type: $content_model" + * @return array + * @note If contents is an object, an array of two nulls will be + * returned, and the callee needs to take the original $contents + * and use it directly. + */ + public function parseContents($contents) + { + if (!is_string($contents)) { + return array(null, null); + } // defer + switch ($contents) { + // check for shorthand content model forms + case 'Empty': + return array('empty', ''); + case 'Inline': + return array('optional', 'Inline | #PCDATA'); + case 'Flow': + return array('optional', 'Flow | #PCDATA'); + } + list($content_model_type, $content_model) = explode(':', $contents); + $content_model_type = strtolower(trim($content_model_type)); + $content_model = trim($content_model); + return array($content_model_type, $content_model); + } + + /** + * Convenience function that merges a list of attribute includes into + * an attribute array. + * @param array $attr Reference to attr array to modify + * @param array $attr_includes Array of includes / string include to merge in + */ + public function mergeInAttrIncludes(&$attr, $attr_includes) + { + if (!is_array($attr_includes)) { + if (empty($attr_includes)) { + $attr_includes = array(); + } else { + $attr_includes = array($attr_includes); + } + } + $attr[0] = $attr_includes; + } + + /** + * Convenience function that generates a lookup table with boolean + * true as value. + * @param string $list List of values to turn into a lookup + * @note You can also pass an arbitrary number of arguments in + * place of the regular argument + * @return array array equivalent of list + */ + public function makeLookup($list) + { + if (is_string($list)) { + $list = func_get_args(); + } + $ret = array(); + foreach ($list as $value) { + if (is_null($value)) { + continue; + } + $ret[$value] = true; + } + return $ret; + } + + /** + * Lazy load construction of the module after determining whether + * or not it's needed, and also when a finalized configuration object + * is available. + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Bdo.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Bdo.php new file mode 100644 index 0000000000..1e67c790d0 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Bdo.php @@ -0,0 +1,44 @@ + array('dir' => false) + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $bdo = $this->addElement( + 'bdo', + 'Inline', + 'Inline', + array('Core', 'Lang'), + array( + 'dir' => 'Enum#ltr,rtl', // required + // The Abstract Module specification has the attribute + // inclusions wrong for bdo: bdo allows Lang + ) + ); + $bdo->attr_transform_post[] = new HTMLPurifier_AttrTransform_BdoDir(); + + $this->attr_collections['I18N']['dir'] = 'Enum#ltr,rtl'; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/CommonAttributes.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/CommonAttributes.php new file mode 100644 index 0000000000..a96ab1bef1 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/CommonAttributes.php @@ -0,0 +1,31 @@ + array( + 0 => array('Style'), + // 'xml:space' => false, + 'class' => 'Class', + 'id' => 'ID', + 'title' => 'CDATA', + ), + 'Lang' => array(), + 'I18N' => array( + 0 => array('Lang'), // proprietary, for xml:lang/lang + ), + 'Common' => array( + 0 => array('Core', 'I18N') + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Edit.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Edit.php new file mode 100644 index 0000000000..a9042a3577 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Edit.php @@ -0,0 +1,55 @@ + 'URI', + // 'datetime' => 'Datetime', // not implemented + ); + $this->addElement('del', 'Inline', $contents, 'Common', $attr); + $this->addElement('ins', 'Inline', $contents, 'Common', $attr); + } + + // HTML 4.01 specifies that ins/del must not contain block + // elements when used in an inline context, chameleon is + // a complicated workaround to acheive this effect + + // Inline context ! Block context (exclamation mark is + // separator, see getChildDef for parsing) + + /** + * @type bool + */ + public $defines_child_def = true; + + /** + * @param HTMLPurifier_ElementDef $def + * @return HTMLPurifier_ChildDef_Chameleon + */ + public function getChildDef($def) + { + if ($def->content_model_type != 'chameleon') { + return false; + } + $value = explode('!', $def->content_model); + return new HTMLPurifier_ChildDef_Chameleon($value[0], $value[1]); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Forms.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Forms.php new file mode 100644 index 0000000000..6f7ddbc05b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Forms.php @@ -0,0 +1,190 @@ + 'Form', + 'Inline' => 'Formctrl', + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $form = $this->addElement( + 'form', + 'Form', + 'Required: Heading | List | Block | fieldset', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accept-charset' => 'Charsets', + 'action*' => 'URI', + 'method' => 'Enum#get,post', + // really ContentType, but these two are the only ones used today + 'enctype' => 'Enum#application/x-www-form-urlencoded,multipart/form-data', + ) + ); + $form->excludes = array('form' => true); + + $input = $this->addElement( + 'input', + 'Formctrl', + 'Empty', + 'Common', + array( + 'accept' => 'ContentTypes', + 'accesskey' => 'Character', + 'alt' => 'Text', + 'checked' => 'Bool#checked', + 'disabled' => 'Bool#disabled', + 'maxlength' => 'Number', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'size' => 'Number', + 'src' => 'URI#embedded', + 'tabindex' => 'Number', + 'type' => 'Enum#text,password,checkbox,button,radio,submit,reset,file,hidden,image', + 'value' => 'CDATA', + ) + ); + $input->attr_transform_post[] = new HTMLPurifier_AttrTransform_Input(); + + $this->addElement( + 'select', + 'Formctrl', + 'Required: optgroup | option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'multiple' => 'Bool#multiple', + 'name' => 'CDATA', + 'size' => 'Number', + 'tabindex' => 'Number', + ) + ); + + $this->addElement( + 'option', + false, + 'Optional: #PCDATA', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label' => 'Text', + 'selected' => 'Bool#selected', + 'value' => 'CDATA', + ) + ); + // It's illegal for there to be more than one selected, but not + // be multiple. Also, no selected means undefined behavior. This might + // be difficult to implement; perhaps an injector, or a context variable. + + $textarea = $this->addElement( + 'textarea', + 'Formctrl', + 'Optional: #PCDATA', + 'Common', + array( + 'accesskey' => 'Character', + 'cols*' => 'Number', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'readonly' => 'Bool#readonly', + 'rows*' => 'Number', + 'tabindex' => 'Number', + ) + ); + $textarea->attr_transform_pre[] = new HTMLPurifier_AttrTransform_Textarea(); + + $button = $this->addElement( + 'button', + 'Formctrl', + 'Optional: #PCDATA | Heading | List | Block | Inline', + 'Common', + array( + 'accesskey' => 'Character', + 'disabled' => 'Bool#disabled', + 'name' => 'CDATA', + 'tabindex' => 'Number', + 'type' => 'Enum#button,submit,reset', + 'value' => 'CDATA', + ) + ); + + // For exclusions, ideally we'd specify content sets, not literal elements + $button->excludes = $this->makeLookup( + 'form', + 'fieldset', // Form + 'input', + 'select', + 'textarea', + 'label', + 'button', // Formctrl + 'a', // as per HTML 4.01 spec, this is omitted by modularization + 'isindex', + 'iframe' // legacy items + ); + + // Extra exclusion: img usemap="" is not permitted within this element. + // We'll omit this for now, since we don't have any good way of + // indicating it yet. + + // This is HIGHLY user-unfriendly; we need a custom child-def for this + $this->addElement('fieldset', 'Form', 'Custom: (#WS?,legend,(Flow|#PCDATA)*)', 'Common'); + + $label = $this->addElement( + 'label', + 'Formctrl', + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + // 'for' => 'IDREF', // IDREF not implemented, cannot allow + ) + ); + $label->excludes = array('label' => true); + + $this->addElement( + 'legend', + false, + 'Optional: #PCDATA | Inline', + 'Common', + array( + 'accesskey' => 'Character', + ) + ); + + $this->addElement( + 'optgroup', + false, + 'Required: option', + 'Common', + array( + 'disabled' => 'Bool#disabled', + 'label*' => 'Text', + ) + ); + // Don't forget an injector for . This one's a little complex + // because it maps to multiple elements. + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Hypertext.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Hypertext.php new file mode 100644 index 0000000000..72d7a31e68 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Hypertext.php @@ -0,0 +1,40 @@ +addElement( + 'a', + 'Inline', + 'Inline', + 'Common', + array( + // 'accesskey' => 'Character', + // 'charset' => 'Charset', + 'href' => 'URI', + // 'hreflang' => 'LanguageCode', + 'rel' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rel'), + 'rev' => new HTMLPurifier_AttrDef_HTML_LinkTypes('rev'), + // 'tabindex' => 'Number', + // 'type' => 'ContentType', + ) + ); + $a->formatting = true; + $a->excludes = array('a' => true); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Iframe.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Iframe.php new file mode 100644 index 0000000000..f7e7c91c02 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Iframe.php @@ -0,0 +1,51 @@ +get('HTML.SafeIframe')) { + $this->safe = true; + } + $this->addElement( + 'iframe', + 'Inline', + 'Flow', + 'Common', + array( + 'src' => 'URI#embedded', + 'width' => 'Length', + 'height' => 'Length', + 'name' => 'ID', + 'scrolling' => 'Enum#yes,no,auto', + 'frameborder' => 'Enum#0,1', + 'longdesc' => 'URI', + 'marginheight' => 'Pixels', + 'marginwidth' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Image.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Image.php new file mode 100644 index 0000000000..0f5fdb3baf --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Image.php @@ -0,0 +1,49 @@ +get('HTML.MaxImgLength'); + $img = $this->addElement( + 'img', + 'Inline', + 'Empty', + 'Common', + array( + 'alt*' => 'Text', + // According to the spec, it's Length, but percents can + // be abused, so we allow only Pixels. + 'height' => 'Pixels#' . $max, + 'width' => 'Pixels#' . $max, + 'longdesc' => 'URI', + 'src*' => new HTMLPurifier_AttrDef_URI(true), // embedded + ) + ); + if ($max === null || $config->get('HTML.Trusted')) { + $img->attr['height'] = + $img->attr['width'] = 'Length'; + } + + // kind of strange, but splitting things up would be inefficient + $img->attr_transform_pre[] = + $img->attr_transform_post[] = + new HTMLPurifier_AttrTransform_ImgRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Legacy.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Legacy.php new file mode 100644 index 0000000000..86b5299579 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Legacy.php @@ -0,0 +1,186 @@ +addElement( + 'basefont', + 'Inline', + 'Empty', + null, + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + 'id' => 'ID' + ) + ); + $this->addElement('center', 'Block', 'Flow', 'Common'); + $this->addElement( + 'dir', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + $this->addElement( + 'font', + 'Inline', + 'Inline', + array('Core', 'I18N'), + array( + 'color' => 'Color', + 'face' => 'Text', // extremely broad, we should + 'size' => 'Text', // tighten it + ) + ); + $this->addElement( + 'menu', + 'Block', + 'Required: li', + 'Common', + array( + 'compact' => 'Bool#compact' + ) + ); + + $s = $this->addElement('s', 'Inline', 'Inline', 'Common'); + $s->formatting = true; + + $strike = $this->addElement('strike', 'Inline', 'Inline', 'Common'); + $strike->formatting = true; + + $u = $this->addElement('u', 'Inline', 'Inline', 'Common'); + $u->formatting = true; + + // setup modifications to old elements + + $align = 'Enum#left,right,center,justify'; + + $address = $this->addBlankElement('address'); + $address->content_model = 'Inline | #PCDATA | p'; + $address->content_model_type = 'optional'; + $address->child = false; + + $blockquote = $this->addBlankElement('blockquote'); + $blockquote->content_model = 'Flow | #PCDATA'; + $blockquote->content_model_type = 'optional'; + $blockquote->child = false; + + $br = $this->addBlankElement('br'); + $br->attr['clear'] = 'Enum#left,all,right,none'; + + $caption = $this->addBlankElement('caption'); + $caption->attr['align'] = 'Enum#top,bottom,left,right'; + + $div = $this->addBlankElement('div'); + $div->attr['align'] = $align; + + $dl = $this->addBlankElement('dl'); + $dl->attr['compact'] = 'Bool#compact'; + + for ($i = 1; $i <= 6; $i++) { + $h = $this->addBlankElement("h$i"); + $h->attr['align'] = $align; + } + + $hr = $this->addBlankElement('hr'); + $hr->attr['align'] = $align; + $hr->attr['noshade'] = 'Bool#noshade'; + $hr->attr['size'] = 'Pixels'; + $hr->attr['width'] = 'Length'; + + $img = $this->addBlankElement('img'); + $img->attr['align'] = 'IAlign'; + $img->attr['border'] = 'Pixels'; + $img->attr['hspace'] = 'Pixels'; + $img->attr['vspace'] = 'Pixels'; + + // figure out this integer business + + $li = $this->addBlankElement('li'); + $li->attr['value'] = new HTMLPurifier_AttrDef_Integer(); + $li->attr['type'] = 'Enum#s:1,i,I,a,A,disc,square,circle'; + + $ol = $this->addBlankElement('ol'); + $ol->attr['compact'] = 'Bool#compact'; + $ol->attr['start'] = new HTMLPurifier_AttrDef_Integer(); + $ol->attr['type'] = 'Enum#s:1,i,I,a,A'; + + $p = $this->addBlankElement('p'); + $p->attr['align'] = $align; + + $pre = $this->addBlankElement('pre'); + $pre->attr['width'] = 'Number'; + + // script omitted + + $table = $this->addBlankElement('table'); + $table->attr['align'] = 'Enum#left,center,right'; + $table->attr['bgcolor'] = 'Color'; + + $tr = $this->addBlankElement('tr'); + $tr->attr['bgcolor'] = 'Color'; + + $th = $this->addBlankElement('th'); + $th->attr['bgcolor'] = 'Color'; + $th->attr['height'] = 'Length'; + $th->attr['nowrap'] = 'Bool#nowrap'; + $th->attr['width'] = 'Length'; + + $td = $this->addBlankElement('td'); + $td->attr['bgcolor'] = 'Color'; + $td->attr['height'] = 'Length'; + $td->attr['nowrap'] = 'Bool#nowrap'; + $td->attr['width'] = 'Length'; + + $ul = $this->addBlankElement('ul'); + $ul->attr['compact'] = 'Bool#compact'; + $ul->attr['type'] = 'Enum#square,disc,circle'; + + // "safe" modifications to "unsafe" elements + // WARNING: If you want to add support for an unsafe, legacy + // attribute, make a new TrustedLegacy module with the trusted + // bit set appropriately + + $form = $this->addBlankElement('form'); + $form->content_model = 'Flow | #PCDATA'; + $form->content_model_type = 'optional'; + $form->attr['target'] = 'FrameTarget'; + + $input = $this->addBlankElement('input'); + $input->attr['align'] = 'IAlign'; + + $legend = $this->addBlankElement('legend'); + $legend->attr['align'] = 'LAlign'; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/List.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/List.php new file mode 100644 index 0000000000..7a20ff701c --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/List.php @@ -0,0 +1,51 @@ + 'List'); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $ol = $this->addElement('ol', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + $ul = $this->addElement('ul', 'List', new HTMLPurifier_ChildDef_List(), 'Common'); + // XXX The wrap attribute is handled by MakeWellFormed. This is all + // quite unsatisfactory, because we generated this + // *specifically* for lists, and now a big chunk of the handling + // is done properly by the List ChildDef. So actually, we just + // want enough information to make autoclosing work properly, + // and then hand off the tricky stuff to the ChildDef. + $ol->wrap = 'li'; + $ul->wrap = 'li'; + $this->addElement('dl', 'List', 'Required: dt | dd', 'Common'); + + $this->addElement('li', false, 'Flow', 'Common'); + + $this->addElement('dd', false, 'Flow', 'Common'); + $this->addElement('dt', false, 'Inline', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Name.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Name.php new file mode 100644 index 0000000000..60c0545154 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Name.php @@ -0,0 +1,26 @@ +addBlankElement($name); + $element->attr['name'] = 'CDATA'; + if (!$config->get('HTML.Attr.Name.UseCDATA')) { + $element->attr_transform_post[] = new HTMLPurifier_AttrTransform_NameSync(); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Nofollow.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Nofollow.php new file mode 100644 index 0000000000..dc9410a895 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Nofollow.php @@ -0,0 +1,25 @@ +addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_Nofollow(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php new file mode 100644 index 0000000000..da722253ac --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/NonXMLCommonAttributes.php @@ -0,0 +1,20 @@ + array( + 'lang' => 'LanguageCode', + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Object.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Object.php new file mode 100644 index 0000000000..2f9efc5c88 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Object.php @@ -0,0 +1,62 @@ + to cater to legacy browsers: this + * module does not allow this sort of behavior + */ +class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule +{ + /** + * @type string + */ + public $name = 'Object'; + + /** + * @type bool + */ + public $safe = false; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->addElement( + 'object', + 'Inline', + 'Optional: #PCDATA | Flow | param', + 'Common', + array( + 'archive' => 'URI', + 'classid' => 'URI', + 'codebase' => 'URI', + 'codetype' => 'Text', + 'data' => 'URI', + 'declare' => 'Bool#declare', + 'height' => 'Length', + 'name' => 'CDATA', + 'standby' => 'Text', + 'tabindex' => 'Number', + 'type' => 'ContentType', + 'width' => 'Length' + ) + ); + + $this->addElement( + 'param', + false, + 'Empty', + null, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'type' => 'Text', + 'value' => 'Text', + 'valuetype' => 'Enum#data,ref,object' + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Presentation.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Presentation.php new file mode 100644 index 0000000000..6458ce9d88 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Presentation.php @@ -0,0 +1,42 @@ +addElement('hr', 'Block', 'Empty', 'Common'); + $this->addElement('sub', 'Inline', 'Inline', 'Common'); + $this->addElement('sup', 'Inline', 'Inline', 'Common'); + $b = $this->addElement('b', 'Inline', 'Inline', 'Common'); + $b->formatting = true; + $big = $this->addElement('big', 'Inline', 'Inline', 'Common'); + $big->formatting = true; + $i = $this->addElement('i', 'Inline', 'Inline', 'Common'); + $i->formatting = true; + $small = $this->addElement('small', 'Inline', 'Inline', 'Common'); + $small->formatting = true; + $tt = $this->addElement('tt', 'Inline', 'Inline', 'Common'); + $tt->formatting = true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Proprietary.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Proprietary.php new file mode 100644 index 0000000000..5ee3c8e67f --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Proprietary.php @@ -0,0 +1,40 @@ +addElement( + 'marquee', + 'Inline', + 'Flow', + 'Common', + array( + 'direction' => 'Enum#left,right,up,down', + 'behavior' => 'Enum#alternate', + 'width' => 'Length', + 'height' => 'Length', + 'scrolldelay' => 'Number', + 'scrollamount' => 'Number', + 'loop' => 'Number', + 'bgcolor' => 'Color', + 'hspace' => 'Pixels', + 'vspace' => 'Pixels', + ) + ); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Ruby.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Ruby.php new file mode 100644 index 0000000000..a0d48924da --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Ruby.php @@ -0,0 +1,36 @@ +addElement( + 'ruby', + 'Inline', + 'Custom: ((rb, (rt | (rp, rt, rp))) | (rbc, rtc, rtc?))', + 'Common' + ); + $this->addElement('rbc', false, 'Required: rb', 'Common'); + $this->addElement('rtc', false, 'Required: rt', 'Common'); + $rb = $this->addElement('rb', false, 'Inline', 'Common'); + $rb->excludes = array('ruby' => true); + $rt = $this->addElement('rt', false, 'Inline', 'Common', array('rbspan' => 'Number')); + $rt->excludes = array('ruby' => true); + $this->addElement('rp', false, 'Optional: #PCDATA', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeEmbed.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeEmbed.php new file mode 100644 index 0000000000..04e6689ea6 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeEmbed.php @@ -0,0 +1,40 @@ +get('HTML.MaxImgLength'); + $embed = $this->addElement( + 'embed', + 'Inline', + 'Empty', + 'Common', + array( + 'src*' => 'URI#embedded', + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, + 'height' => 'Pixels#' . $max, + 'allowscriptaccess' => 'Enum#never', + 'allownetworking' => 'Enum#internal', + 'flashvars' => 'Text', + 'wmode' => 'Enum#window,transparent,opaque', + 'name' => 'ID', + ) + ); + $embed->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeEmbed(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeObject.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeObject.php new file mode 100644 index 0000000000..1297f80a39 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeObject.php @@ -0,0 +1,62 @@ +get('HTML.MaxImgLength'); + $object = $this->addElement( + 'object', + 'Inline', + 'Optional: param | Flow | #PCDATA', + 'Common', + array( + // While technically not required by the spec, we're forcing + // it to this value. + 'type' => 'Enum#application/x-shockwave-flash', + 'width' => 'Pixels#' . $max, + 'height' => 'Pixels#' . $max, + 'data' => 'URI#embedded', + 'codebase' => new HTMLPurifier_AttrDef_Enum( + array( + 'http://download.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,40,0' + ) + ), + ) + ); + $object->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeObject(); + + $param = $this->addElement( + 'param', + false, + 'Empty', + false, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'value' => 'Text' + ) + ); + $param->attr_transform_post[] = new HTMLPurifier_AttrTransform_SafeParam(); + $this->info_injector[] = 'SafeObject'; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeScripting.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeScripting.php new file mode 100644 index 0000000000..0330cd97f8 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/SafeScripting.php @@ -0,0 +1,40 @@ +get('HTML.SafeScripting'); + $script = $this->addElement( + 'script', + 'Inline', + 'Empty', + null, + array( + // While technically not required by the spec, we're forcing + // it to this value. + 'type' => 'Enum#text/javascript', + 'src*' => new HTMLPurifier_AttrDef_Enum(array_keys($allowed)) + ) + ); + $script->attr_transform_pre[] = + $script->attr_transform_post[] = new HTMLPurifier_AttrTransform_ScriptRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Scripting.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Scripting.php new file mode 100644 index 0000000000..8b28a7b7ea --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Scripting.php @@ -0,0 +1,73 @@ + 'script | noscript', 'Inline' => 'script | noscript'); + + /** + * @type bool + */ + public $safe = false; + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + // TODO: create custom child-definition for noscript that + // auto-wraps stray #PCDATA in a similar manner to + // blockquote's custom definition (we would use it but + // blockquote's contents are optional while noscript's contents + // are required) + + // TODO: convert this to new syntax, main problem is getting + // both content sets working + + // In theory, this could be safe, but I don't see any reason to + // allow it. + $this->info['noscript'] = new HTMLPurifier_ElementDef(); + $this->info['noscript']->attr = array(0 => array('Common')); + $this->info['noscript']->content_model = 'Heading | List | Block'; + $this->info['noscript']->content_model_type = 'required'; + + $this->info['script'] = new HTMLPurifier_ElementDef(); + $this->info['script']->attr = array( + 'defer' => new HTMLPurifier_AttrDef_Enum(array('defer')), + 'src' => new HTMLPurifier_AttrDef_URI(true), + 'type' => new HTMLPurifier_AttrDef_Enum(array('text/javascript')) + ); + $this->info['script']->content_model = '#PCDATA'; + $this->info['script']->content_model_type = 'optional'; + $this->info['script']->attr_transform_pre[] = + $this->info['script']->attr_transform_post[] = + new HTMLPurifier_AttrTransform_ScriptRequired(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/StyleAttribute.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/StyleAttribute.php new file mode 100644 index 0000000000..497b832ae2 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/StyleAttribute.php @@ -0,0 +1,33 @@ + array('style' => false), // see constructor + 'Core' => array(0 => array('Style')) + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->attr_collections['Style']['style'] = new HTMLPurifier_AttrDef_CSS(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tables.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tables.php new file mode 100644 index 0000000000..8a0b3b4616 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tables.php @@ -0,0 +1,75 @@ +addElement('caption', false, 'Inline', 'Common'); + + $this->addElement( + 'table', + 'Block', + new HTMLPurifier_ChildDef_Table(), + 'Common', + array( + 'border' => 'Pixels', + 'cellpadding' => 'Length', + 'cellspacing' => 'Length', + 'frame' => 'Enum#void,above,below,hsides,lhs,rhs,vsides,box,border', + 'rules' => 'Enum#none,groups,rows,cols,all', + 'summary' => 'Text', + 'width' => 'Length' + ) + ); + + // common attributes + $cell_align = array( + 'align' => 'Enum#left,center,right,justify,char', + 'charoff' => 'Length', + 'valign' => 'Enum#top,middle,bottom,baseline', + ); + + $cell_t = array_merge( + array( + 'abbr' => 'Text', + 'colspan' => 'Number', + 'rowspan' => 'Number', + // Apparently, as of HTML5 this attribute only applies + // to 'th' elements. + 'scope' => 'Enum#row,col,rowgroup,colgroup', + ), + $cell_align + ); + $this->addElement('td', false, 'Flow', 'Common', $cell_t); + $this->addElement('th', false, 'Flow', 'Common', $cell_t); + + $this->addElement('tr', false, 'Required: td | th', 'Common', $cell_align); + + $cell_col = array_merge( + array( + 'span' => 'Number', + 'width' => 'MultiLength', + ), + $cell_align + ); + $this->addElement('col', false, 'Empty', 'Common', $cell_col); + $this->addElement('colgroup', false, 'Optional: col', 'Common', $cell_col); + + $this->addElement('tbody', false, 'Required: tr', 'Common', $cell_align); + $this->addElement('thead', false, 'Required: tr', 'Common', $cell_align); + $this->addElement('tfoot', false, 'Required: tr', 'Common', $cell_align); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Target.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Target.php new file mode 100644 index 0000000000..b188ac9369 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Target.php @@ -0,0 +1,28 @@ +addBlankElement($name); + $e->attr = array( + 'target' => new HTMLPurifier_AttrDef_HTML_FrameTarget() + ); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/TargetBlank.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/TargetBlank.php new file mode 100644 index 0000000000..58ccc68941 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/TargetBlank.php @@ -0,0 +1,24 @@ +addBlankElement('a'); + $a->attr_transform_post[] = new HTMLPurifier_AttrTransform_TargetBlank(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Text.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Text.php new file mode 100644 index 0000000000..7a65e0048f --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Text.php @@ -0,0 +1,87 @@ + 'Heading | Block | Inline' + ); + + /** + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + // Inline Phrasal ------------------------------------------------- + $this->addElement('abbr', 'Inline', 'Inline', 'Common'); + $this->addElement('acronym', 'Inline', 'Inline', 'Common'); + $this->addElement('cite', 'Inline', 'Inline', 'Common'); + $this->addElement('dfn', 'Inline', 'Inline', 'Common'); + $this->addElement('kbd', 'Inline', 'Inline', 'Common'); + $this->addElement('q', 'Inline', 'Inline', 'Common', array('cite' => 'URI')); + $this->addElement('samp', 'Inline', 'Inline', 'Common'); + $this->addElement('var', 'Inline', 'Inline', 'Common'); + + $em = $this->addElement('em', 'Inline', 'Inline', 'Common'); + $em->formatting = true; + + $strong = $this->addElement('strong', 'Inline', 'Inline', 'Common'); + $strong->formatting = true; + + $code = $this->addElement('code', 'Inline', 'Inline', 'Common'); + $code->formatting = true; + + // Inline Structural ---------------------------------------------- + $this->addElement('span', 'Inline', 'Inline', 'Common'); + $this->addElement('br', 'Inline', 'Empty', 'Core'); + + // Block Phrasal -------------------------------------------------- + $this->addElement('address', 'Block', 'Inline', 'Common'); + $this->addElement('blockquote', 'Block', 'Optional: Heading | Block | List', 'Common', array('cite' => 'URI')); + $pre = $this->addElement('pre', 'Block', 'Inline', 'Common'); + $pre->excludes = $this->makeLookup( + 'img', + 'big', + 'small', + 'object', + 'applet', + 'font', + 'basefont' + ); + $this->addElement('h1', 'Heading', 'Inline', 'Common'); + $this->addElement('h2', 'Heading', 'Inline', 'Common'); + $this->addElement('h3', 'Heading', 'Inline', 'Common'); + $this->addElement('h4', 'Heading', 'Inline', 'Common'); + $this->addElement('h5', 'Heading', 'Inline', 'Common'); + $this->addElement('h6', 'Heading', 'Inline', 'Common'); + + // Block Structural ----------------------------------------------- + $p = $this->addElement('p', 'Block', 'Inline', 'Common'); + $p->autoclose = array_flip( + array("address", "blockquote", "center", "dir", "div", "dl", "fieldset", "ol", "p", "ul") + ); + + $this->addElement('div', 'Block', 'Flow', 'Common'); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy.php new file mode 100644 index 0000000000..08aa232470 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy.php @@ -0,0 +1,230 @@ + 'none', 'light', 'medium', 'heavy'); + + /** + * Default level to place all fixes in. + * Disabled by default. + * @type string + */ + public $defaultLevel = null; + + /** + * Lists of fixes used by getFixesForLevel(). + * Format is: + * HTMLModule_Tidy->fixesForLevel[$level] = array('fix-1', 'fix-2'); + * @type array + */ + public $fixesForLevel = array( + 'light' => array(), + 'medium' => array(), + 'heavy' => array() + ); + + /** + * Lazy load constructs the module by determining the necessary + * fixes to create and then delegating to the populate() function. + * @param HTMLPurifier_Config $config + * @todo Wildcard matching and error reporting when an added or + * subtracted fix has no effect. + */ + public function setup($config) + { + // create fixes, initialize fixesForLevel + $fixes = $this->makeFixes(); + $this->makeFixesForLevel($fixes); + + // figure out which fixes to use + $level = $config->get('HTML.TidyLevel'); + $fixes_lookup = $this->getFixesForLevel($level); + + // get custom fix declarations: these need namespace processing + $add_fixes = $config->get('HTML.TidyAdd'); + $remove_fixes = $config->get('HTML.TidyRemove'); + + foreach ($fixes as $name => $fix) { + // needs to be refactored a little to implement globbing + if (isset($remove_fixes[$name]) || + (!isset($add_fixes[$name]) && !isset($fixes_lookup[$name]))) { + unset($fixes[$name]); + } + } + + // populate this module with necessary fixes + $this->populate($fixes); + } + + /** + * Retrieves all fixes per a level, returning fixes for that specific + * level as well as all levels below it. + * @param string $level level identifier, see $levels for valid values + * @return array Lookup up table of fixes + */ + public function getFixesForLevel($level) + { + if ($level == $this->levels[0]) { + return array(); + } + $activated_levels = array(); + for ($i = 1, $c = count($this->levels); $i < $c; $i++) { + $activated_levels[] = $this->levels[$i]; + if ($this->levels[$i] == $level) { + break; + } + } + if ($i == $c) { + trigger_error( + 'Tidy level ' . htmlspecialchars($level) . ' not recognized', + E_USER_WARNING + ); + return array(); + } + $ret = array(); + foreach ($activated_levels as $level) { + foreach ($this->fixesForLevel[$level] as $fix) { + $ret[$fix] = true; + } + } + return $ret; + } + + /** + * Dynamically populates the $fixesForLevel member variable using + * the fixes array. It may be custom overloaded, used in conjunction + * with $defaultLevel, or not used at all. + * @param array $fixes + */ + public function makeFixesForLevel($fixes) + { + if (!isset($this->defaultLevel)) { + return; + } + if (!isset($this->fixesForLevel[$this->defaultLevel])) { + trigger_error( + 'Default level ' . $this->defaultLevel . ' does not exist', + E_USER_ERROR + ); + return; + } + $this->fixesForLevel[$this->defaultLevel] = array_keys($fixes); + } + + /** + * Populates the module with transforms and other special-case code + * based on a list of fixes passed to it + * @param array $fixes Lookup table of fixes to activate + */ + public function populate($fixes) + { + foreach ($fixes as $name => $fix) { + // determine what the fix is for + list($type, $params) = $this->getFixType($name); + switch ($type) { + case 'attr_transform_pre': + case 'attr_transform_post': + $attr = $params['attr']; + if (isset($params['element'])) { + $element = $params['element']; + if (empty($this->info[$element])) { + $e = $this->addBlankElement($element); + } else { + $e = $this->info[$element]; + } + } else { + $type = "info_$type"; + $e = $this; + } + // PHP does some weird parsing when I do + // $e->$type[$attr], so I have to assign a ref. + $f =& $e->$type; + $f[$attr] = $fix; + break; + case 'tag_transform': + $this->info_tag_transform[$params['element']] = $fix; + break; + case 'child': + case 'content_model_type': + $element = $params['element']; + if (empty($this->info[$element])) { + $e = $this->addBlankElement($element); + } else { + $e = $this->info[$element]; + } + $e->$type = $fix; + break; + default: + trigger_error("Fix type $type not supported", E_USER_ERROR); + break; + } + } + } + + /** + * Parses a fix name and determines what kind of fix it is, as well + * as other information defined by the fix + * @param $name String name of fix + * @return array(string $fix_type, array $fix_parameters) + * @note $fix_parameters is type dependant, see populate() for usage + * of these parameters + */ + public function getFixType($name) + { + // parse it + $property = $attr = null; + if (strpos($name, '#') !== false) { + list($name, $property) = explode('#', $name); + } + if (strpos($name, '@') !== false) { + list($name, $attr) = explode('@', $name); + } + + // figure out the parameters + $params = array(); + if ($name !== '') { + $params['element'] = $name; + } + if (!is_null($attr)) { + $params['attr'] = $attr; + } + + // special case: attribute transform + if (!is_null($attr)) { + if (is_null($property)) { + $property = 'pre'; + } + $type = 'attr_transform_' . $property; + return array($type, $params); + } + + // special case: tag transform + if (is_null($property)) { + return array('tag_transform', $params); + } + + return array($property, $params); + + } + + /** + * Defines all fixes the module will perform in a compact + * associative array of fix name to fix implementation. + * @return array + */ + public function makeFixes() + { + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Name.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Name.php new file mode 100644 index 0000000000..a995161b28 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Name.php @@ -0,0 +1,33 @@ +content_model_type != 'strictblockquote') { + return parent::getChildDef($def); + } + return new HTMLPurifier_ChildDef_StrictBlockquote($def->content_model); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php new file mode 100644 index 0000000000..c095ad9745 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/Tidy/Transitional.php @@ -0,0 +1,16 @@ + 'text-align:left;', + 'right' => 'text-align:right;', + 'top' => 'caption-side:top;', + 'bottom' => 'caption-side:bottom;' // not supported by IE + ) + ); + + // @align for img ------------------------------------------------- + $r['img@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + 'left' => 'float:left;', + 'right' => 'float:right;', + 'top' => 'vertical-align:top;', + 'middle' => 'vertical-align:middle;', + 'bottom' => 'vertical-align:baseline;', + ) + ); + + // @align for table ----------------------------------------------- + $r['table@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + 'left' => 'float:left;', + 'center' => 'margin-left:auto;margin-right:auto;', + 'right' => 'float:right;' + ) + ); + + // @align for hr ----------------------------------------------- + $r['hr@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'align', + array( + // we use both text-align and margin because these work + // for different browsers (IE and Firefox, respectively) + // and the melange makes for a pretty cross-compatible + // solution + 'left' => 'margin-left:0;margin-right:auto;text-align:left;', + 'center' => 'margin-left:auto;margin-right:auto;text-align:center;', + 'right' => 'margin-left:auto;margin-right:0;text-align:right;' + ) + ); + + // @align for h1, h2, h3, h4, h5, h6, p, div ---------------------- + // {{{ + $align_lookup = array(); + $align_values = array('left', 'right', 'center', 'justify'); + foreach ($align_values as $v) { + $align_lookup[$v] = "text-align:$v;"; + } + // }}} + $r['h1@align'] = + $r['h2@align'] = + $r['h3@align'] = + $r['h4@align'] = + $r['h5@align'] = + $r['h6@align'] = + $r['p@align'] = + $r['div@align'] = + new HTMLPurifier_AttrTransform_EnumToCSS('align', $align_lookup); + + // @bgcolor for table, tr, td, th --------------------------------- + $r['table@bgcolor'] = + $r['td@bgcolor'] = + $r['th@bgcolor'] = + new HTMLPurifier_AttrTransform_BgColor(); + + // @border for img ------------------------------------------------ + $r['img@border'] = new HTMLPurifier_AttrTransform_Border(); + + // @clear for br -------------------------------------------------- + $r['br@clear'] = + new HTMLPurifier_AttrTransform_EnumToCSS( + 'clear', + array( + 'left' => 'clear:left;', + 'right' => 'clear:right;', + 'all' => 'clear:both;', + 'none' => 'clear:none;', + ) + ); + + // @height for td, th --------------------------------------------- + $r['td@height'] = + $r['th@height'] = + new HTMLPurifier_AttrTransform_Length('height'); + + // @hspace for img ------------------------------------------------ + $r['img@hspace'] = new HTMLPurifier_AttrTransform_ImgSpace('hspace'); + + // @noshade for hr ------------------------------------------------ + // this transformation is not precise but often good enough. + // different browsers use different styles to designate noshade + $r['hr@noshade'] = + new HTMLPurifier_AttrTransform_BoolToCSS( + 'noshade', + 'color:#808080;background-color:#808080;border:0;' + ); + + // @nowrap for td, th --------------------------------------------- + $r['td@nowrap'] = + $r['th@nowrap'] = + new HTMLPurifier_AttrTransform_BoolToCSS( + 'nowrap', + 'white-space:nowrap;' + ); + + // @size for hr -------------------------------------------------- + $r['hr@size'] = new HTMLPurifier_AttrTransform_Length('size', 'height'); + + // @type for li, ol, ul ------------------------------------------- + // {{{ + $ul_types = array( + 'disc' => 'list-style-type:disc;', + 'square' => 'list-style-type:square;', + 'circle' => 'list-style-type:circle;' + ); + $ol_types = array( + '1' => 'list-style-type:decimal;', + 'i' => 'list-style-type:lower-roman;', + 'I' => 'list-style-type:upper-roman;', + 'a' => 'list-style-type:lower-alpha;', + 'A' => 'list-style-type:upper-alpha;' + ); + $li_types = $ul_types + $ol_types; + // }}} + + $r['ul@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ul_types); + $r['ol@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $ol_types, true); + $r['li@type'] = new HTMLPurifier_AttrTransform_EnumToCSS('type', $li_types, true); + + // @vspace for img ------------------------------------------------ + $r['img@vspace'] = new HTMLPurifier_AttrTransform_ImgSpace('vspace'); + + // @width for hr, td, th ------------------------------------------ + $r['td@width'] = + $r['th@width'] = + $r['hr@width'] = new HTMLPurifier_AttrTransform_Length('width'); + + return $r; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php new file mode 100644 index 0000000000..01dbe9deb6 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModule/XMLCommonAttributes.php @@ -0,0 +1,20 @@ + array( + 'xml:lang' => 'LanguageCode', + ) + ); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModuleManager.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModuleManager.php new file mode 100644 index 0000000000..f3a17cb03b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/HTMLModuleManager.php @@ -0,0 +1,459 @@ +attrTypes = new HTMLPurifier_AttrTypes(); + $this->doctypes = new HTMLPurifier_DoctypeRegistry(); + + // setup basic modules + $common = array( + 'CommonAttributes', 'Text', 'Hypertext', 'List', + 'Presentation', 'Edit', 'Bdo', 'Tables', 'Image', + 'StyleAttribute', + // Unsafe: + 'Scripting', 'Object', 'Forms', + // Sorta legacy, but present in strict: + 'Name', + ); + $transitional = array('Legacy', 'Target', 'Iframe'); + $xml = array('XMLCommonAttributes'); + $non_xml = array('NonXMLCommonAttributes'); + + // setup basic doctypes + $this->doctypes->register( + 'HTML 4.01 Transitional', + false, + array_merge($common, $transitional, $non_xml), + array('Tidy_Transitional', 'Tidy_Proprietary'), + array(), + '-//W3C//DTD HTML 4.01 Transitional//EN', + 'http://www.w3.org/TR/html4/loose.dtd' + ); + + $this->doctypes->register( + 'HTML 4.01 Strict', + false, + array_merge($common, $non_xml), + array('Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'), + array(), + '-//W3C//DTD HTML 4.01//EN', + 'http://www.w3.org/TR/html4/strict.dtd' + ); + + $this->doctypes->register( + 'XHTML 1.0 Transitional', + true, + array_merge($common, $transitional, $xml, $non_xml), + array('Tidy_Transitional', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Name'), + array(), + '-//W3C//DTD XHTML 1.0 Transitional//EN', + 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd' + ); + + $this->doctypes->register( + 'XHTML 1.0 Strict', + true, + array_merge($common, $xml, $non_xml), + array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Strict', 'Tidy_Proprietary', 'Tidy_Name'), + array(), + '-//W3C//DTD XHTML 1.0 Strict//EN', + 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd' + ); + + $this->doctypes->register( + 'XHTML 1.1', + true, + // Iframe is a real XHTML 1.1 module, despite being + // "transitional"! + array_merge($common, $xml, array('Ruby', 'Iframe')), + array('Tidy_Strict', 'Tidy_XHTML', 'Tidy_Proprietary', 'Tidy_Strict', 'Tidy_Name'), // Tidy_XHTML1_1 + array(), + '-//W3C//DTD XHTML 1.1//EN', + 'http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd' + ); + + } + + /** + * Registers a module to the recognized module list, useful for + * overloading pre-existing modules. + * @param $module Mixed: string module name, with or without + * HTMLPurifier_HTMLModule prefix, or instance of + * subclass of HTMLPurifier_HTMLModule. + * @param $overload Boolean whether or not to overload previous modules. + * If this is not set, and you do overload a module, + * HTML Purifier will complain with a warning. + * @note This function will not call autoload, you must instantiate + * (and thus invoke) autoload outside the method. + * @note If a string is passed as a module name, different variants + * will be tested in this order: + * - Check for HTMLPurifier_HTMLModule_$name + * - Check all prefixes with $name in order they were added + * - Check for literal object name + * - Throw fatal error + * If your object name collides with an internal class, specify + * your module manually. All modules must have been included + * externally: registerModule will not perform inclusions for you! + */ + public function registerModule($module, $overload = false) + { + if (is_string($module)) { + // attempt to load the module + $original_module = $module; + $ok = false; + foreach ($this->prefixes as $prefix) { + $module = $prefix . $original_module; + if (class_exists($module)) { + $ok = true; + break; + } + } + if (!$ok) { + $module = $original_module; + if (!class_exists($module)) { + trigger_error( + $original_module . ' module does not exist', + E_USER_ERROR + ); + return; + } + } + $module = new $module(); + } + if (empty($module->name)) { + trigger_error('Module instance of ' . get_class($module) . ' must have name'); + return; + } + if (!$overload && isset($this->registeredModules[$module->name])) { + trigger_error('Overloading ' . $module->name . ' without explicit overload parameter', E_USER_WARNING); + } + $this->registeredModules[$module->name] = $module; + } + + /** + * Adds a module to the current doctype by first registering it, + * and then tacking it on to the active doctype + */ + public function addModule($module) + { + $this->registerModule($module); + if (is_object($module)) { + $module = $module->name; + } + $this->userModules[] = $module; + } + + /** + * Adds a class prefix that registerModule() will use to resolve a + * string name to a concrete class + */ + public function addPrefix($prefix) + { + $this->prefixes[] = $prefix; + } + + /** + * Performs processing on modules, after being called you may + * use getElement() and getElements() + * @param HTMLPurifier_Config $config + */ + public function setup($config) + { + $this->trusted = $config->get('HTML.Trusted'); + + // generate + $this->doctype = $this->doctypes->make($config); + $modules = $this->doctype->modules; + + // take out the default modules that aren't allowed + $lookup = $config->get('HTML.AllowedModules'); + $special_cases = $config->get('HTML.CoreModules'); + + if (is_array($lookup)) { + foreach ($modules as $k => $m) { + if (isset($special_cases[$m])) { + continue; + } + if (!isset($lookup[$m])) { + unset($modules[$k]); + } + } + } + + // custom modules + if ($config->get('HTML.Proprietary')) { + $modules[] = 'Proprietary'; + } + if ($config->get('HTML.SafeObject')) { + $modules[] = 'SafeObject'; + } + if ($config->get('HTML.SafeEmbed')) { + $modules[] = 'SafeEmbed'; + } + if ($config->get('HTML.SafeScripting') !== array()) { + $modules[] = 'SafeScripting'; + } + if ($config->get('HTML.Nofollow')) { + $modules[] = 'Nofollow'; + } + if ($config->get('HTML.TargetBlank')) { + $modules[] = 'TargetBlank'; + } + + // merge in custom modules + $modules = array_merge($modules, $this->userModules); + + foreach ($modules as $module) { + $this->processModule($module); + $this->modules[$module]->setup($config); + } + + foreach ($this->doctype->tidyModules as $module) { + $this->processModule($module); + $this->modules[$module]->setup($config); + } + + // prepare any injectors + foreach ($this->modules as $module) { + $n = array(); + foreach ($module->info_injector as $injector) { + if (!is_object($injector)) { + $class = "HTMLPurifier_Injector_$injector"; + $injector = new $class; + } + $n[$injector->name] = $injector; + } + $module->info_injector = $n; + } + + // setup lookup table based on all valid modules + foreach ($this->modules as $module) { + foreach ($module->info as $name => $def) { + if (!isset($this->elementLookup[$name])) { + $this->elementLookup[$name] = array(); + } + $this->elementLookup[$name][] = $module->name; + } + } + + // note the different choice + $this->contentSets = new HTMLPurifier_ContentSets( + // content set assembly deals with all possible modules, + // not just ones deemed to be "safe" + $this->modules + ); + $this->attrCollections = new HTMLPurifier_AttrCollections( + $this->attrTypes, + // there is no way to directly disable a global attribute, + // but using AllowedAttributes or simply not including + // the module in your custom doctype should be sufficient + $this->modules + ); + } + + /** + * Takes a module and adds it to the active module collection, + * registering it if necessary. + */ + public function processModule($module) + { + if (!isset($this->registeredModules[$module]) || is_object($module)) { + $this->registerModule($module); + } + $this->modules[$module] = $this->registeredModules[$module]; + } + + /** + * Retrieves merged element definitions. + * @return Array of HTMLPurifier_ElementDef + */ + public function getElements() + { + $elements = array(); + foreach ($this->modules as $module) { + if (!$this->trusted && !$module->safe) { + continue; + } + foreach ($module->info as $name => $v) { + if (isset($elements[$name])) { + continue; + } + $elements[$name] = $this->getElement($name); + } + } + + // remove dud elements, this happens when an element that + // appeared to be safe actually wasn't + foreach ($elements as $n => $v) { + if ($v === false) { + unset($elements[$n]); + } + } + + return $elements; + + } + + /** + * Retrieves a single merged element definition + * @param string $name Name of element + * @param bool $trusted Boolean trusted overriding parameter: set to true + * if you want the full version of an element + * @return HTMLPurifier_ElementDef Merged HTMLPurifier_ElementDef + * @note You may notice that modules are getting iterated over twice (once + * in getElements() and once here). This + * is because + */ + public function getElement($name, $trusted = null) + { + if (!isset($this->elementLookup[$name])) { + return false; + } + + // setup global state variables + $def = false; + if ($trusted === null) { + $trusted = $this->trusted; + } + + // iterate through each module that has registered itself to this + // element + foreach ($this->elementLookup[$name] as $module_name) { + $module = $this->modules[$module_name]; + + // refuse to create/merge from a module that is deemed unsafe-- + // pretend the module doesn't exist--when trusted mode is not on. + if (!$trusted && !$module->safe) { + continue; + } + + // clone is used because, ideally speaking, the original + // definition should not be modified. Usually, this will + // make no difference, but for consistency's sake + $new_def = clone $module->info[$name]; + + if (!$def && $new_def->standalone) { + $def = $new_def; + } elseif ($def) { + // This will occur even if $new_def is standalone. In practice, + // this will usually result in a full replacement. + $def->mergeIn($new_def); + } else { + // :TODO: + // non-standalone definitions that don't have a standalone + // to merge into could be deferred to the end + // HOWEVER, it is perfectly valid for a non-standalone + // definition to lack a standalone definition, even + // after all processing: this allows us to safely + // specify extra attributes for elements that may not be + // enabled all in one place. In particular, this might + // be the case for trusted elements. WARNING: care must + // be taken that the /extra/ definitions are all safe. + continue; + } + + // attribute value expansions + $this->attrCollections->performInclusions($def->attr); + $this->attrCollections->expandIdentifiers($def->attr, $this->attrTypes); + + // descendants_are_inline, for ChildDef_Chameleon + if (is_string($def->content_model) && + strpos($def->content_model, 'Inline') !== false) { + if ($name != 'del' && $name != 'ins') { + // this is for you, ins/del + $def->descendants_are_inline = true; + } + } + + $this->contentSets->generateChildDef($def, $module); + } + + // This can occur if there is a blank definition, but no base to + // mix it in with + if (!$def) { + return false; + } + + // add information on required attributes + foreach ($def->attr as $attr_name => $attr_def) { + if ($attr_def->required) { + $def->required_attr[] = $attr_name; + } + } + return $def; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/IDAccumulator.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/IDAccumulator.php new file mode 100644 index 0000000000..65c902c076 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/IDAccumulator.php @@ -0,0 +1,57 @@ +load($config->get('Attr.IDBlacklist')); + return $id_accumulator; + } + + /** + * Add an ID to the lookup table. + * @param string $id ID to be added. + * @return bool status, true if success, false if there's a dupe + */ + public function add($id) + { + if (isset($this->ids[$id])) { + return false; + } + return $this->ids[$id] = true; + } + + /** + * Load a list of IDs into the lookup table + * @param $array_of_ids Array of IDs to load + * @note This function doesn't care about duplicates + */ + public function load($array_of_ids) + { + foreach ($array_of_ids as $id) { + $this->ids[$id] = true; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector.php new file mode 100644 index 0000000000..5060eef9e2 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector.php @@ -0,0 +1,281 @@ +processToken() + * documentation. + * + * @todo Allow injectors to request a re-run on their output. This + * would help if an operation is recursive. + */ +abstract class HTMLPurifier_Injector +{ + + /** + * Advisory name of injector, this is for friendly error messages. + * @type string + */ + public $name; + + /** + * @type HTMLPurifier_HTMLDefinition + */ + protected $htmlDefinition; + + /** + * Reference to CurrentNesting variable in Context. This is an array + * list of tokens that we are currently "inside" + * @type array + */ + protected $currentNesting; + + /** + * Reference to current token. + * @type HTMLPurifier_Token + */ + protected $currentToken; + + /** + * Reference to InputZipper variable in Context. + * @type HTMLPurifier_Zipper + */ + protected $inputZipper; + + /** + * Array of elements and attributes this injector creates and therefore + * need to be allowed by the definition. Takes form of + * array('element' => array('attr', 'attr2'), 'element2') + * @type array + */ + public $needed = array(); + + /** + * Number of elements to rewind backwards (relative). + * @type bool|int + */ + protected $rewindOffset = false; + + /** + * Rewind to a spot to re-perform processing. This is useful if you + * deleted a node, and now need to see if this change affected any + * earlier nodes. Rewinding does not affect other injectors, and can + * result in infinite loops if not used carefully. + * @param bool|int $offset + * @warning HTML Purifier will prevent you from fast-forwarding with this + * function. + */ + public function rewindOffset($offset) + { + $this->rewindOffset = $offset; + } + + /** + * Retrieves rewind offset, and then unsets it. + * @return bool|int + */ + public function getRewindOffset() + { + $r = $this->rewindOffset; + $this->rewindOffset = false; + return $r; + } + + /** + * Prepares the injector by giving it the config and context objects: + * this allows references to important variables to be made within + * the injector. This function also checks if the HTML environment + * will work with the Injector (see checkNeeded()). + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool|string Boolean false if success, string of missing needed element/attribute if failure + */ + public function prepare($config, $context) + { + $this->htmlDefinition = $config->getHTMLDefinition(); + // Even though this might fail, some unit tests ignore this and + // still test checkNeeded, so be careful. Maybe get rid of that + // dependency. + $result = $this->checkNeeded($config); + if ($result !== false) { + return $result; + } + $this->currentNesting =& $context->get('CurrentNesting'); + $this->currentToken =& $context->get('CurrentToken'); + $this->inputZipper =& $context->get('InputZipper'); + return false; + } + + /** + * This function checks if the HTML environment + * will work with the Injector: if p tags are not allowed, the + * Auto-Paragraphing injector should not be enabled. + * @param HTMLPurifier_Config $config + * @return bool|string Boolean false if success, string of missing needed element/attribute if failure + */ + public function checkNeeded($config) + { + $def = $config->getHTMLDefinition(); + foreach ($this->needed as $element => $attributes) { + if (is_int($element)) { + $element = $attributes; + } + if (!isset($def->info[$element])) { + return $element; + } + if (!is_array($attributes)) { + continue; + } + foreach ($attributes as $name) { + if (!isset($def->info[$element]->attr[$name])) { + return "$element.$name"; + } + } + } + return false; + } + + /** + * Tests if the context node allows a certain element + * @param string $name Name of element to test for + * @return bool True if element is allowed, false if it is not + */ + public function allowsElement($name) + { + if (!empty($this->currentNesting)) { + $parent_token = array_pop($this->currentNesting); + $this->currentNesting[] = $parent_token; + $parent = $this->htmlDefinition->info[$parent_token->name]; + } else { + $parent = $this->htmlDefinition->info_parent_def; + } + if (!isset($parent->child->elements[$name]) || isset($parent->excludes[$name])) { + return false; + } + // check for exclusion + for ($i = count($this->currentNesting) - 2; $i >= 0; $i--) { + $node = $this->currentNesting[$i]; + $def = $this->htmlDefinition->info[$node->name]; + if (isset($def->excludes[$name])) { + return false; + } + } + return true; + } + + /** + * Iterator function, which starts with the next token and continues until + * you reach the end of the input tokens. + * @warning Please prevent previous references from interfering with this + * functions by setting $i = null beforehand! + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @return bool + */ + protected function forward(&$i, &$current) + { + if ($i === null) { + $i = count($this->inputZipper->back) - 1; + } else { + $i--; + } + if ($i < 0) { + return false; + } + $current = $this->inputZipper->back[$i]; + return true; + } + + /** + * Similar to _forward, but accepts a third parameter $nesting (which + * should be initialized at 0) and stops when we hit the end tag + * for the node $this->inputIndex starts in. + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @param int $nesting + * @return bool + */ + protected function forwardUntilEndToken(&$i, &$current, &$nesting) + { + $result = $this->forward($i, $current); + if (!$result) { + return false; + } + if ($nesting === null) { + $nesting = 0; + } + if ($current instanceof HTMLPurifier_Token_Start) { + $nesting++; + } elseif ($current instanceof HTMLPurifier_Token_End) { + if ($nesting <= 0) { + return false; + } + $nesting--; + } + return true; + } + + /** + * Iterator function, starts with the previous token and continues until + * you reach the beginning of input tokens. + * @warning Please prevent previous references from interfering with this + * functions by setting $i = null beforehand! + * @param int $i Current integer index variable for inputTokens + * @param HTMLPurifier_Token $current Current token variable. + * Do NOT use $token, as that variable is also a reference + * @return bool + */ + protected function backward(&$i, &$current) + { + if ($i === null) { + $i = count($this->inputZipper->front) - 1; + } else { + $i--; + } + if ($i < 0) { + return false; + } + $current = $this->inputZipper->front[$i]; + return true; + } + + /** + * Handler that is called when a text token is processed + */ + public function handleText(&$token) + { + } + + /** + * Handler that is called when a start or empty token is processed + */ + public function handleElement(&$token) + { + } + + /** + * Handler that is called when an end token is processed + */ + public function handleEnd(&$token) + { + $this->notifyEnd($token); + } + + /** + * Notifier that is called when an end token is processed + * @param HTMLPurifier_Token $token Current token variable. + * @note This differs from handlers in that the token is read-only + * @deprecated + */ + public function notifyEnd($token) + { + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/AutoParagraph.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/AutoParagraph.php new file mode 100644 index 0000000000..4afdd128d5 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/AutoParagraph.php @@ -0,0 +1,356 @@ +armor['MakeWellFormed_TagClosedError'] = true; + return $par; + } + + /** + * @param HTMLPurifier_Token_Text $token + */ + public function handleText(&$token) + { + $text = $token->data; + // Does the current parent allow

tags? + if ($this->allowsElement('p')) { + if (empty($this->currentNesting) || strpos($text, "\n\n") !== false) { + // Note that we have differing behavior when dealing with text + // in the anonymous root node, or a node inside the document. + // If the text as a double-newline, the treatment is the same; + // if it doesn't, see the next if-block if you're in the document. + + $i = $nesting = null; + if (!$this->forwardUntilEndToken($i, $current, $nesting) && $token->is_whitespace) { + // State 1.1: ... ^ (whitespace, then document end) + // ---- + // This is a degenerate case + } else { + if (!$token->is_whitespace || $this->_isInline($current)) { + // State 1.2: PAR1 + // ---- + + // State 1.3: PAR1\n\nPAR2 + // ------------ + + // State 1.4:

PAR1\n\nPAR2 (see State 2) + // ------------ + $token = array($this->_pStart()); + $this->_splitText($text, $token); + } else { + // State 1.5: \n

+ // -- + } + } + } else { + // State 2:

PAR1... (similar to 1.4) + // ---- + + // We're in an element that allows paragraph tags, but we're not + // sure if we're going to need them. + if ($this->_pLookAhead()) { + // State 2.1:

PAR1PAR1\n\nPAR2 + // ---- + // Note: This will always be the first child, since any + // previous inline element would have triggered this very + // same routine, and found the double newline. One possible + // exception would be a comment. + $token = array($this->_pStart(), $token); + } else { + // State 2.2.1:
PAR1
+ // ---- + + // State 2.2.2:
PAR1PAR1
+ // ---- + } + } + // Is the current parent a
tag? + } elseif (!empty($this->currentNesting) && + $this->currentNesting[count($this->currentNesting) - 1]->name == 'p') { + // State 3.1: ...
PAR1 + // ---- + + // State 3.2: ...
PAR1\n\nPAR2 + // ------------ + $token = array(); + $this->_splitText($text, $token); + // Abort! + } else { + // State 4.1: ...PAR1 + // ---- + + // State 4.2: ...PAR1\n\nPAR2 + // ------------ + } + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + // We don't have to check if we're already in a
tag for block + // tokens, because the tag would have been autoclosed by MakeWellFormed. + if ($this->allowsElement('p')) { + if (!empty($this->currentNesting)) { + if ($this->_isInline($token)) { + // State 1:
... + // --- + // Check if this token is adjacent to the parent token + // (seek backwards until token isn't whitespace) + $i = null; + $this->backward($i, $prev); + + if (!$prev instanceof HTMLPurifier_Token_Start) { + // Token wasn't adjacent + if ($prev instanceof HTMLPurifier_Token_Text && + substr($prev->data, -2) === "\n\n" + ) { + // State 1.1.4:
PAR1
\n\n + // --- + // Quite frankly, this should be handled by splitText + $token = array($this->_pStart(), $token); + } else { + // State 1.1.1:
PAR1
+ // --- + // State 1.1.2:

+ // --- + // State 1.1.3:
PAR + // --- + } + } else { + // State 1.2.1:
+ // --- + // Lookahead to see if
is needed. + if ($this->_pLookAhead()) { + // State 1.3.1:
PAR1\n\nPAR2 + // --- + $token = array($this->_pStart(), $token); + } else { + // State 1.3.2:
PAR1
+ // --- + + // State 1.3.3:
PAR1
\n\n
+ // --- + } + } + } else { + // State 2.3: ...
+ // ----- + } + } else { + if ($this->_isInline($token)) { + // State 3.1: + // --- + // This is where the {p} tag is inserted, not reflected in + // inputTokens yet, however. + $token = array($this->_pStart(), $token); + } else { + // State 3.2:
+ // ----- + } + + $i = null; + if ($this->backward($i, $prev)) { + if (!$prev instanceof HTMLPurifier_Token_Text) { + // State 3.1.1: ...
{p} + // --- + // State 3.2.1: ...
+ // ----- + if (!is_array($token)) { + $token = array($token); + } + array_unshift($token, new HTMLPurifier_Token_Text("\n\n")); + } else { + // State 3.1.2: ...
\n\n{p} + // --- + // State 3.2.2: ...
\n\n
+ // ----- + // Note: PAR cannot occur because PAR would have been + // wrapped in
tags. + } + } + } + } else { + // State 2.2:
+ // ---- + // State 2.4:
+ // --- + } + } + + /** + * Splits up a text in paragraph tokens and appends them + * to the result stream that will replace the original + * @param string $data String text data that will be processed + * into paragraphs + * @param HTMLPurifier_Token[] $result Reference to array of tokens that the + * tags will be appended onto + */ + private function _splitText($data, &$result) + { + $raw_paragraphs = explode("\n\n", $data); + $paragraphs = array(); // without empty paragraphs + $needs_start = false; + $needs_end = false; + + $c = count($raw_paragraphs); + if ($c == 1) { + // There were no double-newlines, abort quickly. In theory this + // should never happen. + $result[] = new HTMLPurifier_Token_Text($data); + return; + } + for ($i = 0; $i < $c; $i++) { + $par = $raw_paragraphs[$i]; + if (trim($par) !== '') { + $paragraphs[] = $par; + } else { + if ($i == 0) { + // Double newline at the front + if (empty($result)) { + // The empty result indicates that the AutoParagraph + // injector did not add any start paragraph tokens. + // This means that we have been in a paragraph for + // a while, and the newline means we should start a new one. + $result[] = new HTMLPurifier_Token_End('p'); + $result[] = new HTMLPurifier_Token_Text("\n\n"); + // However, the start token should only be added if + // there is more processing to be done (i.e. there are + // real paragraphs in here). If there are none, the + // next start paragraph tag will be handled by the + // next call to the injector + $needs_start = true; + } else { + // We just started a new paragraph! + // Reinstate a double-newline for presentation's sake, since + // it was in the source code. + array_unshift($result, new HTMLPurifier_Token_Text("\n\n")); + } + } elseif ($i + 1 == $c) { + // Double newline at the end + // There should be a trailing
when we're finally done. + $needs_end = true; + } + } + } + + // Check if this was just a giant blob of whitespace. Move this earlier, + // perhaps? + if (empty($paragraphs)) { + return; + } + + // Add the start tag indicated by \n\n at the beginning of $data + if ($needs_start) { + $result[] = $this->_pStart(); + } + + // Append the paragraphs onto the result + foreach ($paragraphs as $par) { + $result[] = new HTMLPurifier_Token_Text($par); + $result[] = new HTMLPurifier_Token_End('p'); + $result[] = new HTMLPurifier_Token_Text("\n\n"); + $result[] = $this->_pStart(); + } + + // Remove trailing start token; Injector will handle this later if + // it was indeed needed. This prevents from needing to do a lookahead, + // at the cost of a lookbehind later. + array_pop($result); + + // If there is no need for an end tag, remove all of it and let + // MakeWellFormed close it later. + if (!$needs_end) { + array_pop($result); // removes \n\n + array_pop($result); // removes
+ } + } + + /** + * Returns true if passed token is inline (and, ergo, allowed in + * paragraph tags) + * @param HTMLPurifier_Token $token + * @return bool + */ + private function _isInline($token) + { + return isset($this->htmlDefinition->info['p']->child->elements[$token->name]); + } + + /** + * Looks ahead in the token list and determines whether or not we need + * to insert a
tag. + * @return bool + */ + private function _pLookAhead() + { + if ($this->currentToken instanceof HTMLPurifier_Token_Start) { + $nesting = 1; + } else { + $nesting = 0; + } + $ok = false; + $i = null; + while ($this->forwardUntilEndToken($i, $current, $nesting)) { + $result = $this->_checkNeedsP($current); + if ($result !== null) { + $ok = $result; + break; + } + } + return $ok; + } + + /** + * Determines if a particular token requires an earlier inline token + * to get a paragraph. This should be used with _forwardUntilEndToken + * @param HTMLPurifier_Token $current + * @return bool + */ + private function _checkNeedsP($current) + { + if ($current instanceof HTMLPurifier_Token_Start) { + if (!$this->_isInline($current)) { + //
PAR1
+ // ---- + // Terminate early, since we hit a block element + return false; + } + } elseif ($current instanceof HTMLPurifier_Token_Text) { + if (strpos($current->data, "\n\n") !== false) { + //
PAR1PAR1\n\nPAR2 + // ---- + return true; + } else { + //
PAR1PAR1... + // ---- + } + } + return null; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/DisplayLinkURI.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/DisplayLinkURI.php new file mode 100644 index 0000000000..c19b1bc271 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/DisplayLinkURI.php @@ -0,0 +1,40 @@ +start->attr['href'])) { + $url = $token->start->attr['href']; + unset($token->start->attr['href']); + $token = array($token, new HTMLPurifier_Token_Text(" ($url)")); + } else { + // nothing to display + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/Linkify.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/Linkify.php new file mode 100644 index 0000000000..069708c250 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/Linkify.php @@ -0,0 +1,59 @@ + array('href')); + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + + if (strpos($token->data, '://') === false) { + // our really quick heuristic failed, abort + // this may not work so well if we want to match things like + // "google.com", but then again, most people don't + return; + } + + // there is/are URL(s). Let's split the string: + // Note: this regex is extremely permissive + $bits = preg_split('#((?:https?|ftp)://[^\s\'",<>()]+)#Su', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + + + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start('a', array('href' => $bits[$i])); + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/PurifierLinkify.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/PurifierLinkify.php new file mode 100644 index 0000000000..cb9046f334 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/PurifierLinkify.php @@ -0,0 +1,71 @@ + array('href')); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function prepare($config, $context) + { + $this->docURL = $config->get('AutoFormat.PurifierLinkify.DocURL'); + return parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleText(&$token) + { + if (!$this->allowsElement('a')) { + return; + } + if (strpos($token->data, '%') === false) { + return; + } + + $bits = preg_split('#%([a-z0-9]+\.[a-z0-9]+)#Si', $token->data, -1, PREG_SPLIT_DELIM_CAPTURE); + $token = array(); + + // $i = index + // $c = count + // $l = is link + for ($i = 0, $c = count($bits), $l = false; $i < $c; $i++, $l = !$l) { + if (!$l) { + if ($bits[$i] === '') { + continue; + } + $token[] = new HTMLPurifier_Token_Text($bits[$i]); + } else { + $token[] = new HTMLPurifier_Token_Start( + 'a', + array('href' => str_replace('%s', $bits[$i], $this->docURL)) + ); + $token[] = new HTMLPurifier_Token_Text('%' . $bits[$i]); + $token[] = new HTMLPurifier_Token_End('a'); + } + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/RemoveEmpty.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/RemoveEmpty.php new file mode 100644 index 0000000000..01353ff1d5 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/RemoveEmpty.php @@ -0,0 +1,106 @@ +config = $config; + $this->context = $context; + $this->removeNbsp = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp'); + $this->removeNbspExceptions = $config->get('AutoFormat.RemoveEmpty.RemoveNbsp.Exceptions'); + $this->exclude = $config->get('AutoFormat.RemoveEmpty.Predicate'); + $this->attrValidator = new HTMLPurifier_AttrValidator(); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if (!$token instanceof HTMLPurifier_Token_Start) { + return; + } + $next = false; + $deleted = 1; // the current tag + for ($i = count($this->inputZipper->back) - 1; $i >= 0; $i--, $deleted++) { + $next = $this->inputZipper->back[$i]; + if ($next instanceof HTMLPurifier_Token_Text) { + if ($next->is_whitespace) { + continue; + } + if ($this->removeNbsp && !isset($this->removeNbspExceptions[$token->name])) { + $plain = str_replace("\xC2\xA0", "", $next->data); + $isWsOrNbsp = $plain === '' || ctype_space($plain); + if ($isWsOrNbsp) { + continue; + } + } + } + break; + } + if (!$next || ($next instanceof HTMLPurifier_Token_End && $next->name == $token->name)) { + $this->attrValidator->validateToken($token, $this->config, $this->context); + $token->armor['ValidateAttributes'] = true; + if (isset($this->exclude[$token->name])) { + $r = true; + foreach ($this->exclude[$token->name] as $elem) { + if (!isset($token->attr[$elem])) $r = false; + } + if ($r) return; + } + if (isset($token->attr['id']) || isset($token->attr['name'])) { + return; + } + $token = $deleted + 1; + for ($b = 0, $c = count($this->inputZipper->front); $b < $c; $b++) { + $prev = $this->inputZipper->front[$b]; + if ($prev instanceof HTMLPurifier_Token_Text && $prev->is_whitespace) { + continue; + } + break; + } + // This is safe because we removed the token that triggered this. + $this->rewindOffset($b+$deleted); + return; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php new file mode 100644 index 0000000000..9ee7aa84d7 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/RemoveSpansWithoutAttributes.php @@ -0,0 +1,84 @@ +attrValidator = new HTMLPurifier_AttrValidator(); + $this->config = $config; + $this->context = $context; + return parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if ($token->name !== 'span' || !$token instanceof HTMLPurifier_Token_Start) { + return; + } + + // We need to validate the attributes now since this doesn't normally + // happen until after MakeWellFormed. If all the attributes are removed + // the span needs to be removed too. + $this->attrValidator->validateToken($token, $this->config, $this->context); + $token->armor['ValidateAttributes'] = true; + + if (!empty($token->attr)) { + return; + } + + $nesting = 0; + while ($this->forwardUntilEndToken($i, $current, $nesting)) { + } + + if ($current instanceof HTMLPurifier_Token_End && $current->name === 'span') { + // Mark closing span tag for deletion + $current->markForDeletion = true; + // Delete open span tag + $token = false; + } + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleEnd(&$token) + { + if ($token->markForDeletion) { + $token = false; + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/SafeObject.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/SafeObject.php new file mode 100644 index 0000000000..3d17e07af2 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Injector/SafeObject.php @@ -0,0 +1,121 @@ + 'never', + 'allowNetworking' => 'internal', + ); + + /** + * @type array + */ + protected $allowedParam = array( + 'wmode' => true, + 'movie' => true, + 'flashvars' => true, + 'src' => true, + 'allowFullScreen' => true, // if omitted, assume to be 'false' + ); + + /** + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return void + */ + public function prepare($config, $context) + { + parent::prepare($config, $context); + } + + /** + * @param HTMLPurifier_Token $token + */ + public function handleElement(&$token) + { + if ($token->name == 'object') { + $this->objectStack[] = $token; + $this->paramStack[] = array(); + $new = array($token); + foreach ($this->addParam as $name => $value) { + $new[] = new HTMLPurifier_Token_Empty('param', array('name' => $name, 'value' => $value)); + } + $token = $new; + } elseif ($token->name == 'param') { + $nest = count($this->currentNesting) - 1; + if ($nest >= 0 && $this->currentNesting[$nest]->name === 'object') { + $i = count($this->objectStack) - 1; + if (!isset($token->attr['name'])) { + $token = false; + return; + } + $n = $token->attr['name']; + // We need this fix because YouTube doesn't supply a data + // attribute, which we need if a type is specified. This is + // *very* Flash specific. + if (!isset($this->objectStack[$i]->attr['data']) && + ($token->attr['name'] == 'movie' || $token->attr['name'] == 'src') + ) { + $this->objectStack[$i]->attr['data'] = $token->attr['value']; + } + // Check if the parameter is the correct value but has not + // already been added + if (!isset($this->paramStack[$i][$n]) && + isset($this->addParam[$n]) && + $token->attr['name'] === $this->addParam[$n]) { + // keep token, and add to param stack + $this->paramStack[$i][$n] = true; + } elseif (isset($this->allowedParam[$n])) { + // keep token, don't do anything to it + // (could possibly check for duplicates here) + } else { + $token = false; + } + } else { + // not directly inside an object, DENY! + $token = false; + } + } + } + + public function handleEnd(&$token) + { + // This is the WRONG way of handling the object and param stacks; + // we should be inserting them directly on the relevant object tokens + // so that the global stack handling handles it. + if ($token->name == 'object') { + array_pop($this->objectStack); + array_pop($this->paramStack); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language.php new file mode 100644 index 0000000000..65277dd43c --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language.php @@ -0,0 +1,204 @@ +config = $config; + $this->context = $context; + } + + /** + * Loads language object with necessary info from factory cache + * @note This is a lazy loader + */ + public function load() + { + if ($this->_loaded) { + return; + } + $factory = HTMLPurifier_LanguageFactory::instance(); + $factory->loadLanguage($this->code); + foreach ($factory->keys as $key) { + $this->$key = $factory->cache[$this->code][$key]; + } + $this->_loaded = true; + } + + /** + * Retrieves a localised message. + * @param string $key string identifier of message + * @return string localised message + */ + public function getMessage($key) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } + return $this->messages[$key]; + } + + /** + * Retrieves a localised error name. + * @param int $int error number, corresponding to PHP's error reporting + * @return string localised message + */ + public function getErrorName($int) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->errorNames[$int])) { + return "[Error: $int]"; + } + return $this->errorNames[$int]; + } + + /** + * Converts an array list into a string readable representation + * @param array $array + * @return string + */ + public function listify($array) + { + $sep = $this->getMessage('Item separator'); + $sep_last = $this->getMessage('Item separator last'); + $ret = ''; + for ($i = 0, $c = count($array); $i < $c; $i++) { + if ($i == 0) { + } elseif ($i + 1 < $c) { + $ret .= $sep; + } else { + $ret .= $sep_last; + } + $ret .= $array[$i]; + } + return $ret; + } + + /** + * Formats a localised message with passed parameters + * @param string $key string identifier of message + * @param array $args Parameters to substitute in + * @return string localised message + * @todo Implement conditionals? Right now, some messages make + * reference to line numbers, but those aren't always available + */ + public function formatMessage($key, $args = array()) + { + if (!$this->_loaded) { + $this->load(); + } + if (!isset($this->messages[$key])) { + return "[$key]"; + } + $raw = $this->messages[$key]; + $subst = array(); + $generator = false; + foreach ($args as $i => $value) { + if (is_object($value)) { + if ($value instanceof HTMLPurifier_Token) { + // factor this out some time + if (!$generator) { + $generator = $this->context->get('Generator'); + } + if (isset($value->name)) { + $subst['$'.$i.'.Name'] = $value->name; + } + if (isset($value->data)) { + $subst['$'.$i.'.Data'] = $value->data; + } + $subst['$'.$i.'.Compact'] = + $subst['$'.$i.'.Serialized'] = $generator->generateFromToken($value); + // a more complex algorithm for compact representation + // could be introduced for all types of tokens. This + // may need to be factored out into a dedicated class + if (!empty($value->attr)) { + $stripped_token = clone $value; + $stripped_token->attr = array(); + $subst['$'.$i.'.Compact'] = $generator->generateFromToken($stripped_token); + } + $subst['$'.$i.'.Line'] = $value->line ? $value->line : 'unknown'; + } + continue; + } elseif (is_array($value)) { + $keys = array_keys($value); + if (array_keys($keys) === $keys) { + // list + $subst['$'.$i] = $this->listify($value); + } else { + // associative array + // no $i implementation yet, sorry + $subst['$'.$i.'.Keys'] = $this->listify($keys); + $subst['$'.$i.'.Values'] = $this->listify(array_values($value)); + } + continue; + } + $subst['$' . $i] = $value; + } + return strtr($raw, $subst); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/classes/en-x-test.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/classes/en-x-test.php new file mode 100644 index 0000000000..8828f5cded --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/classes/en-x-test.php @@ -0,0 +1,9 @@ + 'HTML Purifier X' +); + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/messages/en-x-testmini.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/messages/en-x-testmini.php new file mode 100644 index 0000000000..806c83fbf7 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/messages/en-x-testmini.php @@ -0,0 +1,12 @@ + 'HTML Purifier XNone' +); + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/messages/en.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/messages/en.php new file mode 100644 index 0000000000..c7f197e1e1 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Language/messages/en.php @@ -0,0 +1,55 @@ + 'HTML Purifier', +// for unit testing purposes + 'LanguageFactoryTest: Pizza' => 'Pizza', + 'LanguageTest: List' => '$1', + 'LanguageTest: Hash' => '$1.Keys; $1.Values', + 'Item separator' => ', ', + 'Item separator last' => ' and ', // non-Harvard style + + 'ErrorCollector: No errors' => 'No errors detected. However, because error reporting is still incomplete, there may have been errors that the error collector was not notified of; please inspect the output HTML carefully.', + 'ErrorCollector: At line' => ' at line $line', + 'ErrorCollector: Incidental errors' => 'Incidental errors', + 'Lexer: Unclosed comment' => 'Unclosed comment', + 'Lexer: Unescaped lt' => 'Unescaped less-than sign (<) should be <', + 'Lexer: Missing gt' => 'Missing greater-than sign (>), previous less-than sign (<) should be escaped', + 'Lexer: Missing attribute key' => 'Attribute declaration has no key', + 'Lexer: Missing end quote' => 'Attribute declaration has no end quote', + 'Lexer: Extracted body' => 'Removed document metadata tags', + 'Strategy_RemoveForeignElements: Tag transform' => '<$1> element transformed into $CurrentToken.Serialized', + 'Strategy_RemoveForeignElements: Missing required attribute' => '$CurrentToken.Compact element missing required attribute $1', + 'Strategy_RemoveForeignElements: Foreign element to text' => 'Unrecognized $CurrentToken.Serialized tag converted to text', + 'Strategy_RemoveForeignElements: Foreign element removed' => 'Unrecognized $CurrentToken.Serialized tag removed', + 'Strategy_RemoveForeignElements: Comment removed' => 'Comment containing "$CurrentToken.Data" removed', + 'Strategy_RemoveForeignElements: Foreign meta element removed' => 'Unrecognized $CurrentToken.Serialized meta tag and all descendants removed', + 'Strategy_RemoveForeignElements: Token removed to end' => 'Tags and text starting from $1 element where removed to end', + 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' => 'Trailing hyphen(s) in comment removed', + 'Strategy_RemoveForeignElements: Hyphens in comment collapsed' => 'Double hyphens in comments are not allowed, and were collapsed into single hyphens', + 'Strategy_MakeWellFormed: Unnecessary end tag removed' => 'Unnecessary $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Unnecessary end tag to text' => 'Unnecessary $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag auto closed' => '$1.Compact started on line $1.Line auto-closed by $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Tag carryover' => '$1.Compact started on line $1.Line auto-continued into $CurrentToken.Compact', + 'Strategy_MakeWellFormed: Stray end tag removed' => 'Stray $CurrentToken.Serialized tag removed', + 'Strategy_MakeWellFormed: Stray end tag to text' => 'Stray $CurrentToken.Serialized tag converted to text', + 'Strategy_MakeWellFormed: Tag closed by element end' => '$1.Compact tag started on line $1.Line closed by end of $CurrentToken.Serialized', + 'Strategy_MakeWellFormed: Tag closed by document end' => '$1.Compact tag started on line $1.Line closed by end of document', + 'Strategy_FixNesting: Node removed' => '$CurrentToken.Compact node removed', + 'Strategy_FixNesting: Node excluded' => '$CurrentToken.Compact node removed due to descendant exclusion by ancestor element', + 'Strategy_FixNesting: Node reorganized' => 'Contents of $CurrentToken.Compact node reorganized to enforce its content model', + 'Strategy_FixNesting: Node contents removed' => 'Contents of $CurrentToken.Compact node removed', + 'AttrValidator: Attributes transformed' => 'Attributes on $CurrentToken.Compact transformed from $1.Keys to $2.Keys', + 'AttrValidator: Attribute removed' => '$CurrentAttr.Name attribute on $CurrentToken.Compact removed', +); + +$errorNames = array( + E_ERROR => 'Error', + E_WARNING => 'Warning', + E_NOTICE => 'Notice' +); + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/LanguageFactory.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/LanguageFactory.php new file mode 100644 index 0000000000..4e35272d87 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/LanguageFactory.php @@ -0,0 +1,209 @@ +cache[$language_code][$key] = $value + * @type array + */ + public $cache; + + /** + * Valid keys in the HTMLPurifier_Language object. Designates which + * variables to slurp out of a message file. + * @type array + */ + public $keys = array('fallback', 'messages', 'errorNames'); + + /** + * Instance to validate language codes. + * @type HTMLPurifier_AttrDef_Lang + * + */ + protected $validator; + + /** + * Cached copy of dirname(__FILE__), directory of current file without + * trailing slash. + * @type string + */ + protected $dir; + + /** + * Keys whose contents are a hash map and can be merged. + * @type array + */ + protected $mergeable_keys_map = array('messages' => true, 'errorNames' => true); + + /** + * Keys whose contents are a list and can be merged. + * @value array lookup + */ + protected $mergeable_keys_list = array(); + + /** + * Retrieve sole instance of the factory. + * @param HTMLPurifier_LanguageFactory $prototype Optional prototype to overload sole instance with, + * or bool true to reset to default factory. + * @return HTMLPurifier_LanguageFactory + */ + public static function instance($prototype = null) + { + static $instance = null; + if ($prototype !== null) { + $instance = $prototype; + } elseif ($instance === null || $prototype == true) { + $instance = new HTMLPurifier_LanguageFactory(); + $instance->setup(); + } + return $instance; + } + + /** + * Sets up the singleton, much like a constructor + * @note Prevents people from getting this outside of the singleton + */ + public function setup() + { + $this->validator = new HTMLPurifier_AttrDef_Lang(); + $this->dir = HTMLPURIFIER_PREFIX . '/HTMLPurifier'; + } + + /** + * Creates a language object, handles class fallbacks + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @param bool|string $code Code to override configuration with. Private parameter. + * @return HTMLPurifier_Language + */ + public function create($config, $context, $code = false) + { + // validate language code + if ($code === false) { + $code = $this->validator->validate( + $config->get('Core.Language'), + $config, + $context + ); + } else { + $code = $this->validator->validate($code, $config, $context); + } + if ($code === false) { + $code = 'en'; // malformed code becomes English + } + + $pcode = str_replace('-', '_', $code); // make valid PHP classname + static $depth = 0; // recursion protection + + if ($code == 'en') { + $lang = new HTMLPurifier_Language($config, $context); + } else { + $class = 'HTMLPurifier_Language_' . $pcode; + $file = $this->dir . '/Language/classes/' . $code . '.php'; + if (file_exists($file) || class_exists($class, false)) { + $lang = new $class($config, $context); + } else { + // Go fallback + $raw_fallback = $this->getFallbackFor($code); + $fallback = $raw_fallback ? $raw_fallback : 'en'; + $depth++; + $lang = $this->create($config, $context, $fallback); + if (!$raw_fallback) { + $lang->error = true; + } + $depth--; + } + } + $lang->code = $code; + return $lang; + } + + /** + * Returns the fallback language for language + * @note Loads the original language into cache + * @param string $code language code + * @return string|bool + */ + public function getFallbackFor($code) + { + $this->loadLanguage($code); + return $this->cache[$code]['fallback']; + } + + /** + * Loads language into the cache, handles message file and fallbacks + * @param string $code language code + */ + public function loadLanguage($code) + { + static $languages_seen = array(); // recursion guard + + // abort if we've already loaded it + if (isset($this->cache[$code])) { + return; + } + + // generate filename + $filename = $this->dir . '/Language/messages/' . $code . '.php'; + + // default fallback : may be overwritten by the ensuing include + $fallback = ($code != 'en') ? 'en' : false; + + // load primary localisation + if (!file_exists($filename)) { + // skip the include: will rely solely on fallback + $filename = $this->dir . '/Language/messages/en.php'; + $cache = array(); + } else { + include $filename; + $cache = compact($this->keys); + } + + // load fallback localisation + if (!empty($fallback)) { + + // infinite recursion guard + if (isset($languages_seen[$code])) { + trigger_error( + 'Circular fallback reference in language ' . + $code, + E_USER_ERROR + ); + $fallback = 'en'; + } + $language_seen[$code] = true; + + // load the fallback recursively + $this->loadLanguage($fallback); + $fallback_cache = $this->cache[$fallback]; + + // merge fallback with current language + foreach ($this->keys as $key) { + if (isset($cache[$key]) && isset($fallback_cache[$key])) { + if (isset($this->mergeable_keys_map[$key])) { + $cache[$key] = $cache[$key] + $fallback_cache[$key]; + } elseif (isset($this->mergeable_keys_list[$key])) { + $cache[$key] = array_merge($fallback_cache[$key], $cache[$key]); + } + } else { + $cache[$key] = $fallback_cache[$key]; + } + } + } + + // save to cache for later retrieval + $this->cache[$code] = $cache; + return; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Length.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Length.php new file mode 100644 index 0000000000..bbfbe6624d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Length.php @@ -0,0 +1,160 @@ + true, 'ex' => true, 'px' => true, 'in' => true, + 'cm' => true, 'mm' => true, 'pt' => true, 'pc' => true + ); + + /** + * @param string $n Magnitude + * @param bool|string $u Unit + */ + public function __construct($n = '0', $u = false) + { + $this->n = (string) $n; + $this->unit = $u !== false ? (string) $u : false; + } + + /** + * @param string $s Unit string, like '2em' or '3.4in' + * @return HTMLPurifier_Length + * @warning Does not perform validation. + */ + public static function make($s) + { + if ($s instanceof HTMLPurifier_Length) { + return $s; + } + $n_length = strspn($s, '1234567890.+-'); + $n = substr($s, 0, $n_length); + $unit = substr($s, $n_length); + if ($unit === '') { + $unit = false; + } + return new HTMLPurifier_Length($n, $unit); + } + + /** + * Validates the number and unit. + * @return bool + */ + protected function validate() + { + // Special case: + if ($this->n === '+0' || $this->n === '-0') { + $this->n = '0'; + } + if ($this->n === '0' && $this->unit === false) { + return true; + } + if (!ctype_lower($this->unit)) { + $this->unit = strtolower($this->unit); + } + if (!isset(HTMLPurifier_Length::$allowedUnits[$this->unit])) { + return false; + } + // Hack: + $def = new HTMLPurifier_AttrDef_CSS_Number(); + $result = $def->validate($this->n, false, false); + if ($result === false) { + return false; + } + $this->n = $result; + return true; + } + + /** + * Returns string representation of number. + * @return string + */ + public function toString() + { + if (!$this->isValid()) { + return false; + } + return $this->n . $this->unit; + } + + /** + * Retrieves string numeric magnitude. + * @return string + */ + public function getN() + { + return $this->n; + } + + /** + * Retrieves string unit. + * @return string + */ + public function getUnit() + { + return $this->unit; + } + + /** + * Returns true if this length unit is valid. + * @return bool + */ + public function isValid() + { + if ($this->isValid === null) { + $this->isValid = $this->validate(); + } + return $this->isValid; + } + + /** + * Compares two lengths, and returns 1 if greater, -1 if less and 0 if equal. + * @param HTMLPurifier_Length $l + * @return int + * @warning If both values are too large or small, this calculation will + * not work properly + */ + public function compareTo($l) + { + if ($l === false) { + return false; + } + if ($l->unit !== $this->unit) { + $converter = new HTMLPurifier_UnitConverter(); + $l = $converter->convert($l, $this->unit); + if ($l === false) { + return false; + } + } + return $this->n - $l->n; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Lexer.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Lexer.php new file mode 100644 index 0000000000..43732621dc --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Lexer.php @@ -0,0 +1,357 @@ +get('Core.LexerImpl'); + } + + $needs_tracking = + $config->get('Core.MaintainLineNumbers') || + $config->get('Core.CollectErrors'); + + $inst = null; + if (is_object($lexer)) { + $inst = $lexer; + } else { + if (is_null($lexer)) { + do { + // auto-detection algorithm + if ($needs_tracking) { + $lexer = 'DirectLex'; + break; + } + + if (class_exists('DOMDocument') && + method_exists('DOMDocument', 'loadHTML') && + !extension_loaded('domxml') + ) { + // check for DOM support, because while it's part of the + // core, it can be disabled compile time. Also, the PECL + // domxml extension overrides the default DOM, and is evil + // and nasty and we shan't bother to support it + $lexer = 'DOMLex'; + } else { + $lexer = 'DirectLex'; + } + } while (0); + } // do..while so we can break + + // instantiate recognized string names + switch ($lexer) { + case 'DOMLex': + $inst = new HTMLPurifier_Lexer_DOMLex(); + break; + case 'DirectLex': + $inst = new HTMLPurifier_Lexer_DirectLex(); + break; + case 'PH5P': + $inst = new HTMLPurifier_Lexer_PH5P(); + break; + default: + throw new HTMLPurifier_Exception( + "Cannot instantiate unrecognized Lexer type " . + htmlspecialchars($lexer) + ); + } + } + + if (!$inst) { + throw new HTMLPurifier_Exception('No lexer was instantiated'); + } + + // once PHP DOM implements native line numbers, or we + // hack out something using XSLT, remove this stipulation + if ($needs_tracking && !$inst->tracksLineNumbers) { + throw new HTMLPurifier_Exception( + 'Cannot use lexer that does not support line numbers with ' . + 'Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)' + ); + } + + return $inst; + + } + + // -- CONVENIENCE MEMBERS --------------------------------------------- + + public function __construct() + { + $this->_entity_parser = new HTMLPurifier_EntityParser(); + } + + /** + * Most common entity to raw value conversion table for special entities. + * @type array + */ + protected $_special_entity2str = + array( + '"' => '"', + '&' => '&', + '<' => '<', + '>' => '>', + ''' => "'", + ''' => "'", + ''' => "'" + ); + + /** + * Parses special entities into the proper characters. + * + * This string will translate escaped versions of the special characters + * into the correct ones. + * + * @warning + * You should be able to treat the output of this function as + * completely parsed, but that's only because all other entities should + * have been handled previously in substituteNonSpecialEntities() + * + * @param string $string String character data to be parsed. + * @return string Parsed character data. + */ + public function parseData($string) + { + // following functions require at least one character + if ($string === '') { + return ''; + } + + // subtracts amps that cannot possibly be escaped + $num_amp = substr_count($string, '&') - substr_count($string, '& ') - + ($string[strlen($string) - 1] === '&' ? 1 : 0); + + if (!$num_amp) { + return $string; + } // abort if no entities + $num_esc_amp = substr_count($string, '&'); + $string = strtr($string, $this->_special_entity2str); + + // code duplication for sake of optimization, see above + $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') - + ($string[strlen($string) - 1] === '&' ? 1 : 0); + + if ($num_amp_2 <= $num_esc_amp) { + return $string; + } + + // hmm... now we have some uncommon entities. Use the callback. + $string = $this->_entity_parser->substituteSpecialEntities($string); + return $string; + } + + /** + * Lexes an HTML string into tokens. + * @param $string String HTML. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token[] array representation of HTML. + */ + public function tokenizeHTML($string, $config, $context) + { + trigger_error('Call to abstract class', E_USER_ERROR); + } + + /** + * Translates CDATA sections into regular sections (through escaping). + * @param string $string HTML string to process. + * @return string HTML with CDATA sections escaped. + */ + protected static function escapeCDATA($string) + { + return preg_replace_callback( + '//s', + array('HTMLPurifier_Lexer', 'CDATACallback'), + $string + ); + } + + /** + * Special CDATA case that is especially convoluted for )#si', + array($this, 'scriptCallback'), + $html + ); + } + + $html = $this->normalize($html, $config, $context); + + $cursor = 0; // our location in the text + $inside_tag = false; // whether or not we're parsing the inside of a tag + $array = array(); // result array + + // This is also treated to mean maintain *column* numbers too + $maintain_line_numbers = $config->get('Core.MaintainLineNumbers'); + + if ($maintain_line_numbers === null) { + // automatically determine line numbering by checking + // if error collection is on + $maintain_line_numbers = $config->get('Core.CollectErrors'); + } + + if ($maintain_line_numbers) { + $current_line = 1; + $current_col = 0; + $length = strlen($html); + } else { + $current_line = false; + $current_col = false; + $length = false; + } + $context->register('CurrentLine', $current_line); + $context->register('CurrentCol', $current_col); + $nl = "\n"; + // how often to manually recalculate. This will ALWAYS be right, + // but it's pretty wasteful. Set to 0 to turn off + $synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval'); + + $e = false; + if ($config->get('Core.CollectErrors')) { + $e =& $context->get('ErrorCollector'); + } + + // for testing synchronization + $loops = 0; + + while (++$loops) { + // $cursor is either at the start of a token, or inside of + // a tag (i.e. there was a < immediately before it), as indicated + // by $inside_tag + + if ($maintain_line_numbers) { + // $rcursor, however, is always at the start of a token. + $rcursor = $cursor - (int)$inside_tag; + + // Column number is cheap, so we calculate it every round. + // We're interested at the *end* of the newline string, so + // we need to add strlen($nl) == 1 to $nl_pos before subtracting it + // from our "rcursor" position. + $nl_pos = strrpos($html, $nl, $rcursor - $length); + $current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1); + + // recalculate lines + if ($synchronize_interval && // synchronization is on + $cursor > 0 && // cursor is further than zero + $loops % $synchronize_interval === 0) { // time to synchronize! + $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor); + } + } + + $position_next_lt = strpos($html, '<', $cursor); + $position_next_gt = strpos($html, '>', $cursor); + + // triggers on "asdf" but not "asdf " + // special case to set up context + if ($position_next_lt === $cursor) { + $inside_tag = true; + $cursor++; + } + + if (!$inside_tag && $position_next_lt !== false) { + // We are not inside tag and there still is another tag to parse + $token = new + HTMLPurifier_Token_Text( + $this->parseData( + substr( + $html, + $cursor, + $position_next_lt - $cursor + ) + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor); + } + $array[] = $token; + $cursor = $position_next_lt + 1; + $inside_tag = true; + continue; + } elseif (!$inside_tag) { + // We are not inside tag but there are no more tags + // If we're already at the end, break + if ($cursor === strlen($html)) { + break; + } + // Create Text of rest of string + $token = new + HTMLPurifier_Token_Text( + $this->parseData( + substr( + $html, + $cursor + ) + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } + $array[] = $token; + break; + } elseif ($inside_tag && $position_next_gt !== false) { + // We are in tag and it is well formed + // Grab the internals of the tag + $strlen_segment = $position_next_gt - $cursor; + + if ($strlen_segment < 1) { + // there's nothing to process! + $token = new HTMLPurifier_Token_Text('<'); + $cursor++; + continue; + } + + $segment = substr($html, $cursor, $strlen_segment); + + if ($segment === false) { + // somehow, we attempted to access beyond the end of + // the string, defense-in-depth, reported by Nate Abele + break; + } + + // Check if it's a comment + if (substr($segment, 0, 3) === '!--') { + // re-determine segment length, looking for --> + $position_comment_end = strpos($html, '-->', $cursor); + if ($position_comment_end === false) { + // uh oh, we have a comment that extends to + // infinity. Can't be helped: set comment + // end position to end of string + if ($e) { + $e->send(E_WARNING, 'Lexer: Unclosed comment'); + } + $position_comment_end = strlen($html); + $end = true; + } else { + $end = false; + } + $strlen_segment = $position_comment_end - $cursor; + $segment = substr($html, $cursor, $strlen_segment); + $token = new + HTMLPurifier_Token_Comment( + substr( + $segment, + 3, + $strlen_segment - 3 + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment); + } + $array[] = $token; + $cursor = $end ? $position_comment_end : $position_comment_end + 3; + $inside_tag = false; + continue; + } + + // Check if it's an end tag + $is_end_tag = (strpos($segment, '/') === 0); + if ($is_end_tag) { + $type = substr($segment, 1); + $token = new HTMLPurifier_Token_End($type); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + $cursor = $position_next_gt + 1; + continue; + } + + // Check leading character is alnum, if not, we may + // have accidently grabbed an emoticon. Translate into + // text and go our merry way + if (!ctype_alpha($segment[0])) { + // XML: $segment[0] !== '_' && $segment[0] !== ':' + if ($e) { + $e->send(E_NOTICE, 'Lexer: Unescaped lt'); + } + $token = new HTMLPurifier_Token_Text('<'); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + continue; + } + + // Check if it is explicitly self closing, if so, remove + // trailing slash. Remember, we could have a tag like
, so + // any later token processing scripts must convert improperly + // classified EmptyTags from StartTags. + $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1); + if ($is_self_closing) { + $strlen_segment--; + $segment = substr($segment, 0, $strlen_segment); + } + + // Check if there are any attributes + $position_first_space = strcspn($segment, $this->_whitespace); + + if ($position_first_space >= $strlen_segment) { + if ($is_self_closing) { + $token = new HTMLPurifier_Token_Empty($segment); + } else { + $token = new HTMLPurifier_Token_Start($segment); + } + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $inside_tag = false; + $cursor = $position_next_gt + 1; + continue; + } + + // Grab out all the data + $type = substr($segment, 0, $position_first_space); + $attribute_string = + trim( + substr( + $segment, + $position_first_space + ) + ); + if ($attribute_string) { + $attr = $this->parseAttributeString( + $attribute_string, + $config, + $context + ); + } else { + $attr = array(); + } + + if ($is_self_closing) { + $token = new HTMLPurifier_Token_Empty($type, $attr); + } else { + $token = new HTMLPurifier_Token_Start($type, $attr); + } + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor); + } + $array[] = $token; + $cursor = $position_next_gt + 1; + $inside_tag = false; + continue; + } else { + // inside tag, but there's no ending > sign + if ($e) { + $e->send(E_WARNING, 'Lexer: Missing gt'); + } + $token = new + HTMLPurifier_Token_Text( + '<' . + $this->parseData( + substr($html, $cursor) + ) + ); + if ($maintain_line_numbers) { + $token->rawPosition($current_line, $current_col); + } + // no cursor scroll? Hmm... + $array[] = $token; + break; + } + break; + } + + $context->destroy('CurrentLine'); + $context->destroy('CurrentCol'); + return $array; + } + + /** + * PHP 5.0.x compatible substr_count that implements offset and length + * @param string $haystack + * @param string $needle + * @param int $offset + * @param int $length + * @return int + */ + protected function substrCount($haystack, $needle, $offset, $length) + { + static $oldVersion; + if ($oldVersion === null) { + $oldVersion = version_compare(PHP_VERSION, '5.1', '<'); + } + if ($oldVersion) { + $haystack = substr($haystack, $offset, $length); + return substr_count($haystack, $needle); + } else { + return substr_count($haystack, $needle, $offset, $length); + } + } + + /** + * Takes the inside of an HTML tag and makes an assoc array of attributes. + * + * @param string $string Inside of tag excluding name. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return array Assoc array of attributes. + */ + public function parseAttributeString($string, $config, $context) + { + $string = (string)$string; // quick typecast + + if ($string == '') { + return array(); + } // no attributes + + $e = false; + if ($config->get('Core.CollectErrors')) { + $e =& $context->get('ErrorCollector'); + } + + // let's see if we can abort as quickly as possible + // one equal sign, no spaces => one attribute + $num_equal = substr_count($string, '='); + $has_space = strpos($string, ' '); + if ($num_equal === 0 && !$has_space) { + // bool attribute + return array($string => $string); + } elseif ($num_equal === 1 && !$has_space) { + // only one attribute + list($key, $quoted_value) = explode('=', $string); + $quoted_value = trim($quoted_value); + if (!$key) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + return array(); + } + if (!$quoted_value) { + return array($key => ''); + } + $first_char = @$quoted_value[0]; + $last_char = @$quoted_value[strlen($quoted_value) - 1]; + + $same_quote = ($first_char == $last_char); + $open_quote = ($first_char == '"' || $first_char == "'"); + + if ($same_quote && $open_quote) { + // well behaved + $value = substr($quoted_value, 1, strlen($quoted_value) - 2); + } else { + // not well behaved + if ($open_quote) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing end quote'); + } + $value = substr($quoted_value, 1); + } else { + $value = $quoted_value; + } + } + if ($value === false) { + $value = ''; + } + return array($key => $this->parseData($value)); + } + + // setup loop environment + $array = array(); // return assoc array of attributes + $cursor = 0; // current position in string (moves forward) + $size = strlen($string); // size of the string (stays the same) + + // if we have unquoted attributes, the parser expects a terminating + // space, so let's guarantee that there's always a terminating space. + $string .= ' '; + + $old_cursor = -1; + while ($cursor < $size) { + if ($old_cursor >= $cursor) { + throw new Exception("Infinite loop detected"); + } + $old_cursor = $cursor; + + $cursor += ($value = strspn($string, $this->_whitespace, $cursor)); + // grab the key + + $key_begin = $cursor; //we're currently at the start of the key + + // scroll past all characters that are the key (not whitespace or =) + $cursor += strcspn($string, $this->_whitespace . '=', $cursor); + + $key_end = $cursor; // now at the end of the key + + $key = substr($string, $key_begin, $key_end - $key_begin); + + if (!$key) { + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + $cursor += 1 + strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop + continue; // empty key + } + + // scroll past all whitespace + $cursor += strspn($string, $this->_whitespace, $cursor); + + if ($cursor >= $size) { + $array[$key] = $key; + break; + } + + // if the next character is an equal sign, we've got a regular + // pair, otherwise, it's a bool attribute + $first_char = @$string[$cursor]; + + if ($first_char == '=') { + // key="value" + + $cursor++; + $cursor += strspn($string, $this->_whitespace, $cursor); + + if ($cursor === false) { + $array[$key] = ''; + break; + } + + // we might be in front of a quote right now + + $char = @$string[$cursor]; + + if ($char == '"' || $char == "'") { + // it's quoted, end bound is $char + $cursor++; + $value_begin = $cursor; + $cursor = strpos($string, $char, $cursor); + $value_end = $cursor; + } else { + // it's not quoted, end bound is whitespace + $value_begin = $cursor; + $cursor += strcspn($string, $this->_whitespace, $cursor); + $value_end = $cursor; + } + + // we reached a premature end + if ($cursor === false) { + $cursor = $size; + $value_end = $cursor; + } + + $value = substr($string, $value_begin, $value_end - $value_begin); + if ($value === false) { + $value = ''; + } + $array[$key] = $this->parseData($value); + $cursor++; + } else { + // boolattr + if ($key !== '') { + $array[$key] = $key; + } else { + // purely theoretical + if ($e) { + $e->send(E_ERROR, 'Lexer: Missing attribute key'); + } + } + } + } + return $array; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/PH5P.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/PH5P.php new file mode 100644 index 0000000000..ff4fa218fb --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Lexer/PH5P.php @@ -0,0 +1,4787 @@ +normalize($html, $config, $context); + $new_html = $this->wrapHTML($new_html, $config, $context); + try { + $parser = new HTML5($new_html); + $doc = $parser->save(); + } catch (DOMException $e) { + // Uh oh, it failed. Punt to DirectLex. + $lexer = new HTMLPurifier_Lexer_DirectLex(); + $context->register('PH5PError', $e); // save the error, so we can detect it + return $lexer->tokenizeHTML($html, $config, $context); // use original HTML + } + $tokens = array(); + $this->tokenizeDOM( + $doc->getElementsByTagName('html')->item(0)-> // + getElementsByTagName('body')->item(0) // + , + $tokens + ); + return $tokens; + } +} + +/* + +Copyright 2007 Jeroen van der Meer + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +*/ + +class HTML5 +{ + private $data; + private $char; + private $EOF; + private $state; + private $tree; + private $token; + private $content_model; + private $escape = false; + private $entities = array( + 'AElig;', + 'AElig', + 'AMP;', + 'AMP', + 'Aacute;', + 'Aacute', + 'Acirc;', + 'Acirc', + 'Agrave;', + 'Agrave', + 'Alpha;', + 'Aring;', + 'Aring', + 'Atilde;', + 'Atilde', + 'Auml;', + 'Auml', + 'Beta;', + 'COPY;', + 'COPY', + 'Ccedil;', + 'Ccedil', + 'Chi;', + 'Dagger;', + 'Delta;', + 'ETH;', + 'ETH', + 'Eacute;', + 'Eacute', + 'Ecirc;', + 'Ecirc', + 'Egrave;', + 'Egrave', + 'Epsilon;', + 'Eta;', + 'Euml;', + 'Euml', + 'GT;', + 'GT', + 'Gamma;', + 'Iacute;', + 'Iacute', + 'Icirc;', + 'Icirc', + 'Igrave;', + 'Igrave', + 'Iota;', + 'Iuml;', + 'Iuml', + 'Kappa;', + 'LT;', + 'LT', + 'Lambda;', + 'Mu;', + 'Ntilde;', + 'Ntilde', + 'Nu;', + 'OElig;', + 'Oacute;', + 'Oacute', + 'Ocirc;', + 'Ocirc', + 'Ograve;', + 'Ograve', + 'Omega;', + 'Omicron;', + 'Oslash;', + 'Oslash', + 'Otilde;', + 'Otilde', + 'Ouml;', + 'Ouml', + 'Phi;', + 'Pi;', + 'Prime;', + 'Psi;', + 'QUOT;', + 'QUOT', + 'REG;', + 'REG', + 'Rho;', + 'Scaron;', + 'Sigma;', + 'THORN;', + 'THORN', + 'TRADE;', + 'Tau;', + 'Theta;', + 'Uacute;', + 'Uacute', + 'Ucirc;', + 'Ucirc', + 'Ugrave;', + 'Ugrave', + 'Upsilon;', + 'Uuml;', + 'Uuml', + 'Xi;', + 'Yacute;', + 'Yacute', + 'Yuml;', + 'Zeta;', + 'aacute;', + 'aacute', + 'acirc;', + 'acirc', + 'acute;', + 'acute', + 'aelig;', + 'aelig', + 'agrave;', + 'agrave', + 'alefsym;', + 'alpha;', + 'amp;', + 'amp', + 'and;', + 'ang;', + 'apos;', + 'aring;', + 'aring', + 'asymp;', + 'atilde;', + 'atilde', + 'auml;', + 'auml', + 'bdquo;', + 'beta;', + 'brvbar;', + 'brvbar', + 'bull;', + 'cap;', + 'ccedil;', + 'ccedil', + 'cedil;', + 'cedil', + 'cent;', + 'cent', + 'chi;', + 'circ;', + 'clubs;', + 'cong;', + 'copy;', + 'copy', + 'crarr;', + 'cup;', + 'curren;', + 'curren', + 'dArr;', + 'dagger;', + 'darr;', + 'deg;', + 'deg', + 'delta;', + 'diams;', + 'divide;', + 'divide', + 'eacute;', + 'eacute', + 'ecirc;', + 'ecirc', + 'egrave;', + 'egrave', + 'empty;', + 'emsp;', + 'ensp;', + 'epsilon;', + 'equiv;', + 'eta;', + 'eth;', + 'eth', + 'euml;', + 'euml', + 'euro;', + 'exist;', + 'fnof;', + 'forall;', + 'frac12;', + 'frac12', + 'frac14;', + 'frac14', + 'frac34;', + 'frac34', + 'frasl;', + 'gamma;', + 'ge;', + 'gt;', + 'gt', + 'hArr;', + 'harr;', + 'hearts;', + 'hellip;', + 'iacute;', + 'iacute', + 'icirc;', + 'icirc', + 'iexcl;', + 'iexcl', + 'igrave;', + 'igrave', + 'image;', + 'infin;', + 'int;', + 'iota;', + 'iquest;', + 'iquest', + 'isin;', + 'iuml;', + 'iuml', + 'kappa;', + 'lArr;', + 'lambda;', + 'lang;', + 'laquo;', + 'laquo', + 'larr;', + 'lceil;', + 'ldquo;', + 'le;', + 'lfloor;', + 'lowast;', + 'loz;', + 'lrm;', + 'lsaquo;', + 'lsquo;', + 'lt;', + 'lt', + 'macr;', + 'macr', + 'mdash;', + 'micro;', + 'micro', + 'middot;', + 'middot', + 'minus;', + 'mu;', + 'nabla;', + 'nbsp;', + 'nbsp', + 'ndash;', + 'ne;', + 'ni;', + 'not;', + 'not', + 'notin;', + 'nsub;', + 'ntilde;', + 'ntilde', + 'nu;', + 'oacute;', + 'oacute', + 'ocirc;', + 'ocirc', + 'oelig;', + 'ograve;', + 'ograve', + 'oline;', + 'omega;', + 'omicron;', + 'oplus;', + 'or;', + 'ordf;', + 'ordf', + 'ordm;', + 'ordm', + 'oslash;', + 'oslash', + 'otilde;', + 'otilde', + 'otimes;', + 'ouml;', + 'ouml', + 'para;', + 'para', + 'part;', + 'permil;', + 'perp;', + 'phi;', + 'pi;', + 'piv;', + 'plusmn;', + 'plusmn', + 'pound;', + 'pound', + 'prime;', + 'prod;', + 'prop;', + 'psi;', + 'quot;', + 'quot', + 'rArr;', + 'radic;', + 'rang;', + 'raquo;', + 'raquo', + 'rarr;', + 'rceil;', + 'rdquo;', + 'real;', + 'reg;', + 'reg', + 'rfloor;', + 'rho;', + 'rlm;', + 'rsaquo;', + 'rsquo;', + 'sbquo;', + 'scaron;', + 'sdot;', + 'sect;', + 'sect', + 'shy;', + 'shy', + 'sigma;', + 'sigmaf;', + 'sim;', + 'spades;', + 'sub;', + 'sube;', + 'sum;', + 'sup1;', + 'sup1', + 'sup2;', + 'sup2', + 'sup3;', + 'sup3', + 'sup;', + 'supe;', + 'szlig;', + 'szlig', + 'tau;', + 'there4;', + 'theta;', + 'thetasym;', + 'thinsp;', + 'thorn;', + 'thorn', + 'tilde;', + 'times;', + 'times', + 'trade;', + 'uArr;', + 'uacute;', + 'uacute', + 'uarr;', + 'ucirc;', + 'ucirc', + 'ugrave;', + 'ugrave', + 'uml;', + 'uml', + 'upsih;', + 'upsilon;', + 'uuml;', + 'uuml', + 'weierp;', + 'xi;', + 'yacute;', + 'yacute', + 'yen;', + 'yen', + 'yuml;', + 'yuml', + 'zeta;', + 'zwj;', + 'zwnj;' + ); + + const PCDATA = 0; + const RCDATA = 1; + const CDATA = 2; + const PLAINTEXT = 3; + + const DOCTYPE = 0; + const STARTTAG = 1; + const ENDTAG = 2; + const COMMENT = 3; + const CHARACTR = 4; + const EOF = 5; + + public function __construct($data) + { + $this->data = $data; + $this->char = -1; + $this->EOF = strlen($data); + $this->tree = new HTML5TreeConstructer; + $this->content_model = self::PCDATA; + + $this->state = 'data'; + + while ($this->state !== null) { + $this->{$this->state . 'State'}(); + } + } + + public function save() + { + return $this->tree->save(); + } + + private function char() + { + return ($this->char < $this->EOF) + ? $this->data[$this->char] + : false; + } + + private function character($s, $l = 0) + { + if ($s + $l < $this->EOF) { + if ($l === 0) { + return $this->data[$s]; + } else { + return substr($this->data, $s, $l); + } + } + } + + private function characters($char_class, $start) + { + return preg_replace('#^([' . $char_class . ']+).*#s', '\\1', substr($this->data, $start)); + } + + private function dataState() + { + // Consume the next input character + $this->char++; + $char = $this->char(); + + if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) { + /* U+0026 AMPERSAND (&) + When the content model flag is set to one of the PCDATA or RCDATA + states: switch to the entity data state. Otherwise: treat it as per + the "anything else" entry below. */ + $this->state = 'entityData'; + + } elseif ($char === '-') { + /* If the content model flag is set to either the RCDATA state or + the CDATA state, and the escape flag is false, and there are at + least three characters before this one in the input stream, and the + last four characters in the input stream, including this one, are + U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS, + and U+002D HYPHEN-MINUS (""), + set the escape flag to false. */ + if (($this->content_model === self::RCDATA || + $this->content_model === self::CDATA) && $this->escape === true && + $this->character($this->char, 3) === '-->' + ) { + $this->escape = false; + } + + /* In any case, emit the input character as a character token. + Stay in the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); + + } elseif ($this->char === $this->EOF) { + /* EOF + Emit an end-of-file token. */ + $this->EOF(); + + } elseif ($this->content_model === self::PLAINTEXT) { + /* When the content model flag is set to the PLAINTEXT state + THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of + the text and emit it as a character token. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => substr($this->data, $this->char) + ) + ); + + $this->EOF(); + + } else { + /* Anything else + THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that + otherwise would also be treated as a character token and emit it + as a single character token. Stay in the data state. */ + $len = strcspn($this->data, '<&', $this->char); + $char = substr($this->data, $this->char, $len); + $this->char += $len - 1; + + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); + + $this->state = 'data'; + } + } + + private function entityDataState() + { + // Attempt to consume an entity. + $entity = $this->entity(); + + // If nothing is returned, emit a U+0026 AMPERSAND character token. + // Otherwise, emit the character token that was returned. + $char = (!$entity) ? '&' : $entity; + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => $char + ) + ); + + // Finally, switch to the data state. + $this->state = 'data'; + } + + private function tagOpenState() + { + switch ($this->content_model) { + case self::RCDATA: + case self::CDATA: + /* If the next input character is a U+002F SOLIDUS (/) character, + consume it and switch to the close tag open state. If the next + input character is not a U+002F SOLIDUS (/) character, emit a + U+003C LESS-THAN SIGN character token and switch to the data + state to process the next input character. */ + if ($this->character($this->char + 1) === '/') { + $this->char++; + $this->state = 'closeTagOpen'; + + } else { + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<' + ) + ); + + $this->state = 'data'; + } + break; + + case self::PCDATA: + // If the content model flag is set to the PCDATA state + // Consume the next input character: + $this->char++; + $char = $this->char(); + + if ($char === '!') { + /* U+0021 EXCLAMATION MARK (!) + Switch to the markup declaration open state. */ + $this->state = 'markupDeclarationOpen'; + + } elseif ($char === '/') { + /* U+002F SOLIDUS (/) + Switch to the close tag open state. */ + $this->state = 'closeTagOpen'; + + } elseif (preg_match('/^[A-Za-z]$/', $char)) { + /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z + Create a new start tag token, set its tag name to the lowercase + version of the input character (add 0x0020 to the character's code + point), then switch to the tag name state. (Don't emit the token + yet; further details will be filled in before it is emitted.) */ + $this->token = array( + 'name' => strtolower($char), + 'type' => self::STARTTAG, + 'attr' => array() + ); + + $this->state = 'tagName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Parse error. Emit a U+003C LESS-THAN SIGN character token and a + U+003E GREATER-THAN SIGN character token. Switch to the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<>' + ) + ); + + $this->state = 'data'; + + } elseif ($char === '?') { + /* U+003F QUESTION MARK (?) + Parse error. Switch to the bogus comment state. */ + $this->state = 'bogusComment'; + + } else { + /* Anything else + Parse error. Emit a U+003C LESS-THAN SIGN character token and + reconsume the current input character in the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => '<' + ) + ); + + $this->char--; + $this->state = 'data'; + } + break; + } + } + + private function closeTagOpenState() + { + $next_node = strtolower($this->characters('A-Za-z', $this->char + 1)); + $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName; + + if (($this->content_model === self::RCDATA || $this->content_model === self::CDATA) && + (!$the_same || ($the_same && (!preg_match( + '/[\t\n\x0b\x0c >\/]/', + $this->character($this->char + 1 + strlen($next_node)) + ) || $this->EOF === $this->char))) + ) { + /* If the content model flag is set to the RCDATA or CDATA states then + examine the next few characters. If they do not match the tag name of + the last start tag token emitted (case insensitively), or if they do but + they are not immediately followed by one of the following characters: + * U+0009 CHARACTER TABULATION + * U+000A LINE FEED (LF) + * U+000B LINE TABULATION + * U+000C FORM FEED (FF) + * U+0020 SPACE + * U+003E GREATER-THAN SIGN (>) + * U+002F SOLIDUS (/) + * EOF + ...then there is a parse error. Emit a U+003C LESS-THAN SIGN character + token, a U+002F SOLIDUS character token, and switch to the data state + to process the next input character. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => 'state = 'data'; + + } else { + /* Otherwise, if the content model flag is set to the PCDATA state, + or if the next few characters do match that tag name, consume the + next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[A-Za-z]$/', $char)) { + /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z + Create a new end tag token, set its tag name to the lowercase version + of the input character (add 0x0020 to the character's code point), then + switch to the tag name state. (Don't emit the token yet; further details + will be filled in before it is emitted.) */ + $this->token = array( + 'name' => strtolower($char), + 'type' => self::ENDTAG + ); + + $this->state = 'tagName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Parse error. Switch to the data state. */ + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F + SOLIDUS character token. Reconsume the EOF character in the data state. */ + $this->emitToken( + array( + 'type' => self::CHARACTR, + 'data' => 'char--; + $this->state = 'data'; + + } else { + /* Parse error. Switch to the bogus comment state. */ + $this->state = 'bogusComment'; + } + } + } + + private function tagNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } elseif ($char === '/') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Switch to the before + attribute name state. */ + $this->state = 'beforeAttributeName'; + + } else { + /* Anything else + Append the current input character to the current tag token's tag name. + Stay in the tag name state. */ + $this->token['name'] .= strtolower($char); + $this->state = 'tagName'; + } + } + + private function beforeAttributeNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '/') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Stay in the before + attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Start a new attribute in the current tag token. Set that attribute's + name to the current input character, and its value to the empty string. + Switch to the attribute name state. */ + $this->token['attr'][] = array( + 'name' => strtolower($char), + 'value' => null + ); + + $this->state = 'attributeName'; + } + } + + private function attributeNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the before attribute name state. */ + $this->state = 'afterAttributeName'; + + } elseif ($char === '=') { + /* U+003D EQUALS SIGN (=) + Switch to the before attribute value state. */ + $this->state = 'beforeAttributeValue'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '/' && $this->character($this->char + 1) !== '>') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Switch to the before + attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's name. + Stay in the attribute name state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['name'] .= strtolower($char); + + $this->state = 'attributeName'; + } + } + + private function afterAttributeNameState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the after attribute name state. */ + $this->state = 'afterAttributeName'; + + } elseif ($char === '=') { + /* U+003D EQUALS SIGN (=) + Switch to the before attribute value state. */ + $this->state = 'beforeAttributeValue'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '/' && $this->character($this->char + 1) !== '>') { + /* U+002F SOLIDUS (/) + Parse error unless this is a permitted slash. Switch to the + before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the EOF + character in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Start a new attribute in the current tag token. Set that attribute's + name to the current input character, and its value to the empty string. + Switch to the attribute name state. */ + $this->token['attr'][] = array( + 'name' => strtolower($char), + 'value' => null + ); + + $this->state = 'attributeName'; + } + } + + private function beforeAttributeValueState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Stay in the before attribute value state. */ + $this->state = 'beforeAttributeValue'; + + } elseif ($char === '"') { + /* U+0022 QUOTATION MARK (") + Switch to the attribute value (double-quoted) state. */ + $this->state = 'attributeValueDoubleQuoted'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the attribute value (unquoted) state and reconsume + this input character. */ + $this->char--; + $this->state = 'attributeValueUnquoted'; + + } elseif ($char === '\'') { + /* U+0027 APOSTROPHE (') + Switch to the attribute value (single-quoted) state. */ + $this->state = 'attributeValueSingleQuoted'; + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Switch to the attribute value (unquoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueUnquoted'; + } + } + + private function attributeValueDoubleQuotedState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if ($char === '"') { + /* U+0022 QUOTATION MARK (") + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ + $this->entityInAttributeValueState('double'); + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the character + in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Stay in the attribute value (double-quoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueDoubleQuoted'; + } + } + + private function attributeValueSingleQuotedState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if ($char === '\'') { + /* U+0022 QUOTATION MARK (') + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ + $this->entityInAttributeValueState('single'); + + } elseif ($this->char === $this->EOF) { + /* EOF + Parse error. Emit the current tag token. Reconsume the character + in the data state. */ + $this->emitToken($this->token); + + $this->char--; + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Stay in the attribute value (single-quoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueSingleQuoted'; + } + } + + private function attributeValueUnquotedState() + { + // Consume the next input character: + $this->char++; + $char = $this->character($this->char); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + /* U+0009 CHARACTER TABULATION + U+000A LINE FEED (LF) + U+000B LINE TABULATION + U+000C FORM FEED (FF) + U+0020 SPACE + Switch to the before attribute name state. */ + $this->state = 'beforeAttributeName'; + + } elseif ($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ + $this->entityInAttributeValueState(); + + } elseif ($char === '>') { + /* U+003E GREATER-THAN SIGN (>) + Emit the current tag token. Switch to the data state. */ + $this->emitToken($this->token); + $this->state = 'data'; + + } else { + /* Anything else + Append the current input character to the current attribute's value. + Stay in the attribute value (unquoted) state. */ + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + + $this->state = 'attributeValueUnquoted'; + } + } + + private function entityInAttributeValueState() + { + // Attempt to consume an entity. + $entity = $this->entity(); + + // If nothing is returned, append a U+0026 AMPERSAND character to the + // current attribute's value. Otherwise, emit the character token that + // was returned. + $char = (!$entity) + ? '&' + : $entity; + + $last = count($this->token['attr']) - 1; + $this->token['attr'][$last]['value'] .= $char; + } + + private function bogusCommentState() + { + /* Consume every character up to the first U+003E GREATER-THAN SIGN + character (>) or the end of the file (EOF), whichever comes first. Emit + a comment token whose data is the concatenation of all the characters + starting from and including the character that caused the state machine + to switch into the bogus comment state, up to and including the last + consumed character before the U+003E character, if any, or up to the + end of the file otherwise. (If the comment was started by the end of + the file (EOF), the token is empty.) */ + $data = $this->characters('^>', $this->char); + $this->emitToken( + array( + 'data' => $data, + 'type' => self::COMMENT + ) + ); + + $this->char += strlen($data); + + /* Switch to the data state. */ + $this->state = 'data'; + + /* If the end of the file was reached, reconsume the EOF character. */ + if ($this->char === $this->EOF) { + $this->char = $this->EOF - 1; + } + } + + private function markupDeclarationOpenState() + { + /* If the next two characters are both U+002D HYPHEN-MINUS (-) + characters, consume those two characters, create a comment token whose + data is the empty string, and switch to the comment state. */ + if ($this->character($this->char + 1, 2) === '--') { + $this->char += 2; + $this->state = 'comment'; + $this->token = array( + 'data' => null, + 'type' => self::COMMENT + ); + + /* Otherwise if the next seven chacacters are a case-insensitive match + for the word "DOCTYPE", then consume those characters and switch to the + DOCTYPE state. */ + } elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') { + $this->char += 7; + $this->state = 'doctype'; + + /* Otherwise, is is a parse error. Switch to the bogus comment state. + The next character that is consumed, if any, is the first character + that will be in the comment. */ + } else { + $this->char++; + $this->state = 'bogusComment'; + } + } + + private function commentState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + /* U+002D HYPHEN-MINUS (-) */ + if ($char === '-') { + /* Switch to the comment dash state */ + $this->state = 'commentDash'; + + /* EOF */ + } elseif ($this->char === $this->EOF) { + /* Parse error. Emit the comment token. Reconsume the EOF character + in the data state. */ + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + /* Anything else */ + } else { + /* Append the input character to the comment token's data. Stay in + the comment state. */ + $this->token['data'] .= $char; + } + } + + private function commentDashState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + /* U+002D HYPHEN-MINUS (-) */ + if ($char === '-') { + /* Switch to the comment end state */ + $this->state = 'commentEnd'; + + /* EOF */ + } elseif ($this->char === $this->EOF) { + /* Parse error. Emit the comment token. Reconsume the EOF character + in the data state. */ + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + /* Anything else */ + } else { + /* Append a U+002D HYPHEN-MINUS (-) character and the input + character to the comment token's data. Switch to the comment state. */ + $this->token['data'] .= '-' . $char; + $this->state = 'comment'; + } + } + + private function commentEndState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($char === '-') { + $this->token['data'] .= '-'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + $this->token['data'] .= '--' . $char; + $this->state = 'comment'; + } + } + + private function doctypeState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + $this->state = 'beforeDoctypeName'; + + } else { + $this->char--; + $this->state = 'beforeDoctypeName'; + } + } + + private function beforeDoctypeNameState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + // Stay in the before DOCTYPE name state. + + } elseif (preg_match('/^[a-z]$/', $char)) { + $this->token = array( + 'name' => strtoupper($char), + 'type' => self::DOCTYPE, + 'error' => true + ); + + $this->state = 'doctypeName'; + + } elseif ($char === '>') { + $this->emitToken( + array( + 'name' => null, + 'type' => self::DOCTYPE, + 'error' => true + ) + ); + + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken( + array( + 'name' => null, + 'type' => self::DOCTYPE, + 'error' => true + ) + ); + + $this->char--; + $this->state = 'data'; + + } else { + $this->token = array( + 'name' => $char, + 'type' => self::DOCTYPE, + 'error' => true + ); + + $this->state = 'doctypeName'; + } + } + + private function doctypeNameState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + $this->state = 'AfterDoctypeName'; + + } elseif ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif (preg_match('/^[a-z]$/', $char)) { + $this->token['name'] .= strtoupper($char); + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + $this->token['name'] .= $char; + } + + $this->token['error'] = ($this->token['name'] === 'HTML') + ? false + : true; + } + + private function afterDoctypeNameState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) { + // Stay in the DOCTYPE name state. + + } elseif ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + $this->token['error'] = true; + $this->state = 'bogusDoctype'; + } + } + + private function bogusDoctypeState() + { + /* Consume the next input character: */ + $this->char++; + $char = $this->char(); + + if ($char === '>') { + $this->emitToken($this->token); + $this->state = 'data'; + + } elseif ($this->char === $this->EOF) { + $this->emitToken($this->token); + $this->char--; + $this->state = 'data'; + + } else { + // Stay in the bogus DOCTYPE state. + } + } + + private function entity() + { + $start = $this->char; + + // This section defines how to consume an entity. This definition is + // used when parsing entities in text and in attributes. + + // The behaviour depends on the identity of the next character (the + // one immediately after the U+0026 AMPERSAND character): + + switch ($this->character($this->char + 1)) { + // U+0023 NUMBER SIGN (#) + case '#': + + // The behaviour further depends on the character after the + // U+0023 NUMBER SIGN: + switch ($this->character($this->char + 1)) { + // U+0078 LATIN SMALL LETTER X + // U+0058 LATIN CAPITAL LETTER X + case 'x': + case 'X': + // Follow the steps below, but using the range of + // characters U+0030 DIGIT ZERO through to U+0039 DIGIT + // NINE, U+0061 LATIN SMALL LETTER A through to U+0066 + // LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER + // A, through to U+0046 LATIN CAPITAL LETTER F (in other + // words, 0-9, A-F, a-f). + $char = 1; + $char_class = '0-9A-Fa-f'; + break; + + // Anything else + default: + // Follow the steps below, but using the range of + // characters U+0030 DIGIT ZERO through to U+0039 DIGIT + // NINE (i.e. just 0-9). + $char = 0; + $char_class = '0-9'; + break; + } + + // Consume as many characters as match the range of characters + // given above. + $this->char++; + $e_name = $this->characters($char_class, $this->char + $char + 1); + $entity = $this->character($start, $this->char); + $cond = strlen($e_name) > 0; + + // The rest of the parsing happens bellow. + break; + + // Anything else + default: + // Consume the maximum number of characters possible, with the + // consumed characters case-sensitively matching one of the + // identifiers in the first column of the entities table. + $e_name = $this->characters('0-9A-Za-z;', $this->char + 1); + $len = strlen($e_name); + + for ($c = 1; $c <= $len; $c++) { + $id = substr($e_name, 0, $c); + $this->char++; + + if (in_array($id, $this->entities)) { + if ($e_name[$c - 1] !== ';') { + if ($c < $len && $e_name[$c] == ';') { + $this->char++; // consume extra semicolon + } + } + $entity = $id; + break; + } + } + + $cond = isset($entity); + // The rest of the parsing happens bellow. + break; + } + + if (!$cond) { + // If no match can be made, then this is a parse error. No + // characters are consumed, and nothing is returned. + $this->char = $start; + return false; + } + + // Return a character token for the character corresponding to the + // entity name (as given by the second column of the entities table). + return html_entity_decode('&' . $entity . ';', ENT_QUOTES, 'UTF-8'); + } + + private function emitToken($token) + { + $emit = $this->tree->emitToken($token); + + if (is_int($emit)) { + $this->content_model = $emit; + + } elseif ($token['type'] === self::ENDTAG) { + $this->content_model = self::PCDATA; + } + } + + private function EOF() + { + $this->state = null; + $this->tree->emitToken( + array( + 'type' => self::EOF + ) + ); + } +} + +class HTML5TreeConstructer +{ + public $stack = array(); + + private $phase; + private $mode; + private $dom; + private $foster_parent = null; + private $a_formatting = array(); + + private $head_pointer = null; + private $form_pointer = null; + + private $scoping = array('button', 'caption', 'html', 'marquee', 'object', 'table', 'td', 'th'); + private $formatting = array( + 'a', + 'b', + 'big', + 'em', + 'font', + 'i', + 'nobr', + 's', + 'small', + 'strike', + 'strong', + 'tt', + 'u' + ); + private $special = array( + 'address', + 'area', + 'base', + 'basefont', + 'bgsound', + 'blockquote', + 'body', + 'br', + 'center', + 'col', + 'colgroup', + 'dd', + 'dir', + 'div', + 'dl', + 'dt', + 'embed', + 'fieldset', + 'form', + 'frame', + 'frameset', + 'h1', + 'h2', + 'h3', + 'h4', + 'h5', + 'h6', + 'head', + 'hr', + 'iframe', + 'image', + 'img', + 'input', + 'isindex', + 'li', + 'link', + 'listing', + 'menu', + 'meta', + 'noembed', + 'noframes', + 'noscript', + 'ol', + 'optgroup', + 'option', + 'p', + 'param', + 'plaintext', + 'pre', + 'script', + 'select', + 'spacer', + 'style', + 'tbody', + 'textarea', + 'tfoot', + 'thead', + 'title', + 'tr', + 'ul', + 'wbr' + ); + + // The different phases. + const INIT_PHASE = 0; + const ROOT_PHASE = 1; + const MAIN_PHASE = 2; + const END_PHASE = 3; + + // The different insertion modes for the main phase. + const BEFOR_HEAD = 0; + const IN_HEAD = 1; + const AFTER_HEAD = 2; + const IN_BODY = 3; + const IN_TABLE = 4; + const IN_CAPTION = 5; + const IN_CGROUP = 6; + const IN_TBODY = 7; + const IN_ROW = 8; + const IN_CELL = 9; + const IN_SELECT = 10; + const AFTER_BODY = 11; + const IN_FRAME = 12; + const AFTR_FRAME = 13; + + // The different types of elements. + const SPECIAL = 0; + const SCOPING = 1; + const FORMATTING = 2; + const PHRASING = 3; + + const MARKER = 0; + + public function __construct() + { + $this->phase = self::INIT_PHASE; + $this->mode = self::BEFOR_HEAD; + $this->dom = new DOMDocument; + + $this->dom->encoding = 'UTF-8'; + $this->dom->preserveWhiteSpace = true; + $this->dom->substituteEntities = true; + $this->dom->strictErrorChecking = false; + } + + // Process tag tokens + public function emitToken($token) + { + switch ($this->phase) { + case self::INIT_PHASE: + return $this->initPhase($token); + break; + case self::ROOT_PHASE: + return $this->rootElementPhase($token); + break; + case self::MAIN_PHASE: + return $this->mainPhase($token); + break; + case self::END_PHASE : + return $this->trailingEndPhase($token); + break; + } + } + + private function initPhase($token) + { + /* Initially, the tree construction stage must handle each token + emitted from the tokenisation stage as follows: */ + + /* A DOCTYPE token that is marked as being in error + A comment token + A start tag token + An end tag token + A character token that is not one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE + An end-of-file token */ + if ((isset($token['error']) && $token['error']) || + $token['type'] === HTML5::COMMENT || + $token['type'] === HTML5::STARTTAG || + $token['type'] === HTML5::ENDTAG || + $token['type'] === HTML5::EOF || + ($token['type'] === HTML5::CHARACTR && isset($token['data']) && + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) + ) { + /* This specification does not define how to handle this case. In + particular, user agents may ignore the entirety of this specification + altogether for such documents, and instead invoke special parse modes + with a greater emphasis on backwards compatibility. */ + + $this->phase = self::ROOT_PHASE; + return $this->rootElementPhase($token); + + /* A DOCTYPE token marked as being correct */ + } elseif (isset($token['error']) && !$token['error']) { + /* Append a DocumentType node to the Document node, with the name + attribute set to the name given in the DOCTYPE token (which will be + "HTML"), and the other attributes specific to DocumentType objects + set to null, empty lists, or the empty string as appropriate. */ + $doctype = new DOMDocumentType(null, null, 'HTML'); + + /* Then, switch to the root element phase of the tree construction + stage. */ + $this->phase = self::ROOT_PHASE; + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif (isset($token['data']) && preg_match( + '/^[\t\n\x0b\x0c ]+$/', + $token['data'] + ) + ) { + /* Append that character to the Document node. */ + $text = $this->dom->createTextNode($token['data']); + $this->dom->appendChild($text); + } + } + + private function rootElementPhase($token) + { + /* After the initial phase, as each token is emitted from the tokenisation + stage, it must be processed as described in this section. */ + + /* A DOCTYPE token */ + if ($token['type'] === HTML5::DOCTYPE) { + // Parse error. Ignore the token. + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the Document object with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + $this->dom->appendChild($comment); + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append that character to the Document node. */ + $text = $this->dom->createTextNode($token['data']); + $this->dom->appendChild($text); + + /* A character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED + (FF), or U+0020 SPACE + A start tag token + An end tag token + An end-of-file token */ + } elseif (($token['type'] === HTML5::CHARACTR && + !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || + $token['type'] === HTML5::STARTTAG || + $token['type'] === HTML5::ENDTAG || + $token['type'] === HTML5::EOF + ) { + /* Create an HTMLElement node with the tag name html, in the HTML + namespace. Append it to the Document object. Switch to the main + phase and reprocess the current token. */ + $html = $this->dom->createElement('html'); + $this->dom->appendChild($html); + $this->stack[] = $html; + + $this->phase = self::MAIN_PHASE; + return $this->mainPhase($token); + } + } + + private function mainPhase($token) + { + /* Tokens in the main phase must be handled as follows: */ + + /* A DOCTYPE token */ + if ($token['type'] === HTML5::DOCTYPE) { + // Parse error. Ignore the token. + + /* A start tag token with the tag name "html" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') { + /* If this start tag token was not the first start tag token, then + it is a parse error. */ + + /* For each attribute on the token, check to see if the attribute + is already present on the top element of the stack of open elements. + If it is not, add the attribute and its corresponding value to that + element. */ + foreach ($token['attr'] as $attr) { + if (!$this->stack[0]->hasAttribute($attr['name'])) { + $this->stack[0]->setAttribute($attr['name'], $attr['value']); + } + } + + /* An end-of-file token */ + } elseif ($token['type'] === HTML5::EOF) { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* Anything else. */ + } else { + /* Depends on the insertion mode: */ + switch ($this->mode) { + case self::BEFOR_HEAD: + return $this->beforeHead($token); + break; + case self::IN_HEAD: + return $this->inHead($token); + break; + case self::AFTER_HEAD: + return $this->afterHead($token); + break; + case self::IN_BODY: + return $this->inBody($token); + break; + case self::IN_TABLE: + return $this->inTable($token); + break; + case self::IN_CAPTION: + return $this->inCaption($token); + break; + case self::IN_CGROUP: + return $this->inColumnGroup($token); + break; + case self::IN_TBODY: + return $this->inTableBody($token); + break; + case self::IN_ROW: + return $this->inRow($token); + break; + case self::IN_CELL: + return $this->inCell($token); + break; + case self::IN_SELECT: + return $this->inSelect($token); + break; + case self::AFTER_BODY: + return $this->afterBody($token); + break; + case self::IN_FRAME: + return $this->inFrameset($token); + break; + case self::AFTR_FRAME: + return $this->afterFrameset($token); + break; + case self::END_PHASE: + return $this->trailingEndPhase($token); + break; + } + } + } + + private function beforeHead($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data attribute + set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag token with the tag name "head" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') { + /* Create an element for the token, append the new element to the + current node and push it onto the stack of open elements. */ + $element = $this->insertElement($token); + + /* Set the head element pointer to this new element node. */ + $this->head_pointer = $element; + + /* Change the insertion mode to "in head". */ + $this->mode = self::IN_HEAD; + + /* A start tag token whose tag name is one of: "base", "link", "meta", + "script", "style", "title". Or an end tag with the tag name "html". + Or a character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. Or any other start tag token */ + } elseif ($token['type'] === HTML5::STARTTAG || + ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') || + ($token['type'] === HTML5::CHARACTR && !preg_match( + '/^[\t\n\x0b\x0c ]$/', + $token['data'] + )) + ) { + /* Act as if a start tag token with the tag name "head" and no + attributes had been seen, then reprocess the current token. */ + $this->beforeHead( + array( + 'name' => 'head', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inHead($token); + + /* Any other end tag */ + } elseif ($token['type'] === HTML5::ENDTAG) { + /* Parse error. Ignore the token. */ + } + } + + private function inHead($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. + + THIS DIFFERS FROM THE SPEC: If the current node is either a title, style + or script element, append the character to the current node regardless + of its content. */ + if (($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || ( + $token['type'] === HTML5::CHARACTR && in_array( + end($this->stack)->nodeName, + array('title', 'style', 'script') + )) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data attribute + set to the data given in the comment token. */ + $this->insertComment($token['data']); + + } elseif ($token['type'] === HTML5::ENDTAG && + in_array($token['name'], array('title', 'style', 'script')) + ) { + array_pop($this->stack); + return HTML5::PCDATA; + + /* A start tag with the tag name "title" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') { + /* Create an element for the token and append the new element to the + node pointed to by the head element pointer, or, if that is null + (innerHTML case), to the current node. */ + if ($this->head_pointer !== null) { + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + + } else { + $element = $this->insertElement($token); + } + + /* Switch the tokeniser's content model flag to the RCDATA state. */ + return HTML5::RCDATA; + + /* A start tag with the tag name "style" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') { + /* Create an element for the token and append the new element to the + node pointed to by the head element pointer, or, if that is null + (innerHTML case), to the current node. */ + if ($this->head_pointer !== null) { + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + + } else { + $this->insertElement($token); + } + + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + + /* A start tag with the tag name "script" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') { + /* Create an element for the token. */ + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + + /* A start tag with the tag name "base", "link", or "meta" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('base', 'link', 'meta') + ) + ) { + /* Create an element for the token and append the new element to the + node pointed to by the head element pointer, or, if that is null + (innerHTML case), to the current node. */ + if ($this->head_pointer !== null) { + $element = $this->insertElement($token, false); + $this->head_pointer->appendChild($element); + array_pop($this->stack); + + } else { + $this->insertElement($token); + } + + /* An end tag with the tag name "head" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') { + /* If the current node is a head element, pop the current node off + the stack of open elements. */ + if ($this->head_pointer->isSameNode(end($this->stack))) { + array_pop($this->stack); + + /* Otherwise, this is a parse error. */ + } else { + // k + } + + /* Change the insertion mode to "after head". */ + $this->mode = self::AFTER_HEAD; + + /* A start tag with the tag name "head" or an end tag except "html". */ + } elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') || + ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html') + ) { + // Parse error. Ignore the token. + + /* Anything else */ + } else { + /* If the current node is a head element, act as if an end tag + token with the tag name "head" had been seen. */ + if ($this->head_pointer->isSameNode(end($this->stack))) { + $this->inHead( + array( + 'name' => 'head', + 'type' => HTML5::ENDTAG + ) + ); + + /* Otherwise, change the insertion mode to "after head". */ + } else { + $this->mode = self::AFTER_HEAD; + } + + /* Then, reprocess the current token. */ + return $this->afterHead($token); + } + } + + private function afterHead($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data attribute + set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag token with the tag name "body" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') { + /* Insert a body element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in body". */ + $this->mode = self::IN_BODY; + + /* A start tag token with the tag name "frameset" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') { + /* Insert a frameset element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in frameset". */ + $this->mode = self::IN_FRAME; + + /* A start tag token whose tag name is one of: "base", "link", "meta", + "script", "style", "title" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('base', 'link', 'meta', 'script', 'style', 'title') + ) + ) { + /* Parse error. Switch the insertion mode back to "in head" and + reprocess the token. */ + $this->mode = self::IN_HEAD; + return $this->inHead($token); + + /* Anything else */ + } else { + /* Act as if a start tag token with the tag name "body" and no + attributes had been seen, and then reprocess the current token. */ + $this->afterHead( + array( + 'name' => 'body', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inBody($token); + } + } + + private function inBody($token) + { + /* Handle the token as follows: */ + + switch ($token['type']) { + /* A character token */ + case HTML5::CHARACTR: + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Append the token's character to the current node. */ + $this->insertText($token['data']); + break; + + /* A comment token */ + case HTML5::COMMENT: + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + break; + + case HTML5::STARTTAG: + switch ($token['name']) { + /* A start tag token whose tag name is one of: "script", + "style" */ + case 'script': + case 'style': + /* Process the token as if the insertion mode had been "in + head". */ + return $this->inHead($token); + break; + + /* A start tag token whose tag name is one of: "base", "link", + "meta", "title" */ + case 'base': + case 'link': + case 'meta': + case 'title': + /* Parse error. Process the token as if the insertion mode + had been "in head". */ + return $this->inHead($token); + break; + + /* A start tag token with the tag name "body" */ + case 'body': + /* Parse error. If the second element on the stack of open + elements is not a body element, or, if the stack of open + elements has only one node on it, then ignore the token. + (innerHTML case) */ + if (count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') { + // Ignore + + /* Otherwise, for each attribute on the token, check to see + if the attribute is already present on the body element (the + second element) on the stack of open elements. If it is not, + add the attribute and its corresponding value to that + element. */ + } else { + foreach ($token['attr'] as $attr) { + if (!$this->stack[1]->hasAttribute($attr['name'])) { + $this->stack[1]->setAttribute($attr['name'], $attr['value']); + } + } + } + break; + + /* A start tag whose tag name is one of: "address", + "blockquote", "center", "dir", "div", "dl", "fieldset", + "listing", "menu", "ol", "p", "ul" */ + case 'address': + case 'blockquote': + case 'center': + case 'dir': + case 'div': + case 'dl': + case 'fieldset': + case 'listing': + case 'menu': + case 'ol': + case 'p': + case 'ul': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + break; + + /* A start tag whose tag name is "form" */ + case 'form': + /* If the form element pointer is not null, ignore the + token with a parse error. */ + if ($this->form_pointer !== null) { + // Ignore. + + /* Otherwise: */ + } else { + /* If the stack of open elements has a p element in + scope, then act as if an end tag with the tag name p + had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token, and set the + form element pointer to point to the element created. */ + $element = $this->insertElement($token); + $this->form_pointer = $element; + } + break; + + /* A start tag whose tag name is "li", "dd" or "dt" */ + case 'li': + case 'dd': + case 'dt': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + $stack_length = count($this->stack) - 1; + + for ($n = $stack_length; 0 <= $n; $n--) { + /* 1. Initialise node to be the current node (the + bottommost node of the stack). */ + $stop = false; + $node = $this->stack[$n]; + $cat = $this->getElementCategory($node->tagName); + + /* 2. If node is an li, dd or dt element, then pop all + the nodes from the current node up to node, including + node, then stop this algorithm. */ + if ($token['name'] === $node->tagName || ($token['name'] !== 'li' + && ($node->tagName === 'dd' || $node->tagName === 'dt')) + ) { + for ($x = $stack_length; $x >= $n; $x--) { + array_pop($this->stack); + } + + break; + } + + /* 3. If node is not in the formatting category, and is + not in the phrasing category, and is not an address or + div element, then stop this algorithm. */ + if ($cat !== self::FORMATTING && $cat !== self::PHRASING && + $node->tagName !== 'address' && $node->tagName !== 'div' + ) { + break; + } + } + + /* Finally, insert an HTML element with the same tag + name as the token's. */ + $this->insertElement($token); + break; + + /* A start tag token whose tag name is "plaintext" */ + case 'plaintext': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been + seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + return HTML5::PLAINTEXT; + break; + + /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4", + "h5", "h6" */ + case 'h1': + case 'h2': + case 'h3': + case 'h4': + case 'h5': + case 'h6': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* If the stack of open elements has in scope an element whose + tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then + this is a parse error; pop elements from the stack until an + element with one of those tag names has been popped from the + stack. */ + while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) { + array_pop($this->stack); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + break; + + /* A start tag whose tag name is "a" */ + case 'a': + /* If the list of active formatting elements contains + an element whose tag name is "a" between the end of the + list and the last marker on the list (or the start of + the list if there is no marker on the list), then this + is a parse error; act as if an end tag with the tag name + "a" had been seen, then remove that element from the list + of active formatting elements and the stack of open + elements if the end tag didn't already remove it (it + might not have if the element is not in table scope). */ + $leng = count($this->a_formatting); + + for ($n = $leng - 1; $n >= 0; $n--) { + if ($this->a_formatting[$n] === self::MARKER) { + break; + + } elseif ($this->a_formatting[$n]->nodeName === 'a') { + $this->emitToken( + array( + 'name' => 'a', + 'type' => HTML5::ENDTAG + ) + ); + break; + } + } + + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $el = $this->insertElement($token); + + /* Add that element to the list of active formatting + elements. */ + $this->a_formatting[] = $el; + break; + + /* A start tag whose tag name is one of: "b", "big", "em", "font", + "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ + case 'b': + case 'big': + case 'em': + case 'font': + case 'i': + case 'nobr': + case 's': + case 'small': + case 'strike': + case 'strong': + case 'tt': + case 'u': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $el = $this->insertElement($token); + + /* Add that element to the list of active formatting + elements. */ + $this->a_formatting[] = $el; + break; + + /* A start tag token whose tag name is "button" */ + case 'button': + /* If the stack of open elements has a button element in scope, + then this is a parse error; act as if an end tag with the tag + name "button" had been seen, then reprocess the token. (We don't + do that. Unnecessary.) */ + if ($this->elementInScope('button')) { + $this->inBody( + array( + 'name' => 'button', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Insert a marker at the end of the list of active + formatting elements. */ + $this->a_formatting[] = self::MARKER; + break; + + /* A start tag token whose tag name is one of: "marquee", "object" */ + case 'marquee': + case 'object': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Insert a marker at the end of the list of active + formatting elements. */ + $this->a_formatting[] = self::MARKER; + break; + + /* A start tag token whose tag name is "xmp" */ + case 'xmp': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Switch the content model flag to the CDATA state. */ + return HTML5::CDATA; + break; + + /* A start tag whose tag name is "table" */ + case 'table': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in table". */ + $this->mode = self::IN_TABLE; + break; + + /* A start tag whose tag name is one of: "area", "basefont", + "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */ + case 'area': + case 'basefont': + case 'bgsound': + case 'br': + case 'embed': + case 'img': + case 'param': + case 'spacer': + case 'wbr': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Immediately pop the current node off the stack of open elements. */ + array_pop($this->stack); + break; + + /* A start tag whose tag name is "hr" */ + case 'hr': + /* If the stack of open elements has a p element in scope, + then act as if an end tag with the tag name p had been seen. */ + if ($this->elementInScope('p')) { + $this->emitToken( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Immediately pop the current node off the stack of open elements. */ + array_pop($this->stack); + break; + + /* A start tag whose tag name is "image" */ + case 'image': + /* Parse error. Change the token's tag name to "img" and + reprocess it. (Don't ask.) */ + $token['name'] = 'img'; + return $this->inBody($token); + break; + + /* A start tag whose tag name is "input" */ + case 'input': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an input element for the token. */ + $element = $this->insertElement($token, false); + + /* If the form element pointer is not null, then associate the + input element with the form element pointed to by the form + element pointer. */ + $this->form_pointer !== null + ? $this->form_pointer->appendChild($element) + : end($this->stack)->appendChild($element); + + /* Pop that input element off the stack of open elements. */ + array_pop($this->stack); + break; + + /* A start tag whose tag name is "isindex" */ + case 'isindex': + /* Parse error. */ + // w/e + + /* If the form element pointer is not null, + then ignore the token. */ + if ($this->form_pointer === null) { + /* Act as if a start tag token with the tag name "form" had + been seen. */ + $this->inBody( + array( + 'name' => 'body', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a start tag token with the tag name "hr" had + been seen. */ + $this->inBody( + array( + 'name' => 'hr', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a start tag token with the tag name "p" had + been seen. */ + $this->inBody( + array( + 'name' => 'p', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a start tag token with the tag name "label" + had been seen. */ + $this->inBody( + array( + 'name' => 'label', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + /* Act as if a stream of character tokens had been seen. */ + $this->insertText( + 'This is a searchable index. ' . + 'Insert your search keywords here: ' + ); + + /* Act as if a start tag token with the tag name "input" + had been seen, with all the attributes from the "isindex" + token, except with the "name" attribute set to the value + "isindex" (ignoring any explicit "name" attribute). */ + $attr = $token['attr']; + $attr[] = array('name' => 'name', 'value' => 'isindex'); + + $this->inBody( + array( + 'name' => 'input', + 'type' => HTML5::STARTTAG, + 'attr' => $attr + ) + ); + + /* Act as if a stream of character tokens had been seen + (see below for what they should say). */ + $this->insertText( + 'This is a searchable index. ' . + 'Insert your search keywords here: ' + ); + + /* Act as if an end tag token with the tag name "label" + had been seen. */ + $this->inBody( + array( + 'name' => 'label', + 'type' => HTML5::ENDTAG + ) + ); + + /* Act as if an end tag token with the tag name "p" had + been seen. */ + $this->inBody( + array( + 'name' => 'p', + 'type' => HTML5::ENDTAG + ) + ); + + /* Act as if a start tag token with the tag name "hr" had + been seen. */ + $this->inBody( + array( + 'name' => 'hr', + 'type' => HTML5::ENDTAG + ) + ); + + /* Act as if an end tag token with the tag name "form" had + been seen. */ + $this->inBody( + array( + 'name' => 'form', + 'type' => HTML5::ENDTAG + ) + ); + } + break; + + /* A start tag whose tag name is "textarea" */ + case 'textarea': + $this->insertElement($token); + + /* Switch the tokeniser's content model flag to the + RCDATA state. */ + return HTML5::RCDATA; + break; + + /* A start tag whose tag name is one of: "iframe", "noembed", + "noframes" */ + case 'iframe': + case 'noembed': + case 'noframes': + $this->insertElement($token); + + /* Switch the tokeniser's content model flag to the CDATA state. */ + return HTML5::CDATA; + break; + + /* A start tag whose tag name is "select" */ + case 'select': + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Change the insertion mode to "in select". */ + $this->mode = self::IN_SELECT; + break; + + /* A start or end tag whose tag name is one of: "caption", "col", + "colgroup", "frame", "frameset", "head", "option", "optgroup", + "tbody", "td", "tfoot", "th", "thead", "tr". */ + case 'caption': + case 'col': + case 'colgroup': + case 'frame': + case 'frameset': + case 'head': + case 'option': + case 'optgroup': + case 'tbody': + case 'td': + case 'tfoot': + case 'th': + case 'thead': + case 'tr': + // Parse error. Ignore the token. + break; + + /* A start or end tag whose tag name is one of: "event-source", + "section", "nav", "article", "aside", "header", "footer", + "datagrid", "command" */ + case 'event-source': + case 'section': + case 'nav': + case 'article': + case 'aside': + case 'header': + case 'footer': + case 'datagrid': + case 'command': + // Work in progress! + break; + + /* A start tag token not covered by the previous entries */ + default: + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + + $this->insertElement($token, true, true); + break; + } + break; + + case HTML5::ENDTAG: + switch ($token['name']) { + /* An end tag with the tag name "body" */ + case 'body': + /* If the second element in the stack of open elements is + not a body element, this is a parse error. Ignore the token. + (innerHTML case) */ + if (count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') { + // Ignore. + + /* If the current node is not the body element, then this + is a parse error. */ + } elseif (end($this->stack)->nodeName !== 'body') { + // Parse error. + } + + /* Change the insertion mode to "after body". */ + $this->mode = self::AFTER_BODY; + break; + + /* An end tag with the tag name "html" */ + case 'html': + /* Act as if an end tag with tag name "body" had been seen, + then, if that token wasn't ignored, reprocess the current + token. */ + $this->inBody( + array( + 'name' => 'body', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->afterBody($token); + break; + + /* An end tag whose tag name is one of: "address", "blockquote", + "center", "dir", "div", "dl", "fieldset", "listing", "menu", + "ol", "pre", "ul" */ + case 'address': + case 'blockquote': + case 'center': + case 'dir': + case 'div': + case 'dl': + case 'fieldset': + case 'listing': + case 'menu': + case 'ol': + case 'pre': + case 'ul': + /* If the stack of open elements has an element in scope + with the same tag name as that of the token, then generate + implied end tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); + + /* Now, if the current node is not an element with + the same tag name as that of the token, then this + is a parse error. */ + // w/e + + /* If the stack of open elements has an element in + scope with the same tag name as that of the token, + then pop elements from this stack until an element + with that tag name has been popped from the stack. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === $token['name']) { + $n = -1; + } + + array_pop($this->stack); + } + } + break; + + /* An end tag whose tag name is "form" */ + case 'form': + /* If the stack of open elements has an element in scope + with the same tag name as that of the token, then generate + implied end tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); + + } + + if (end($this->stack)->nodeName !== $token['name']) { + /* Now, if the current node is not an element with the + same tag name as that of the token, then this is a parse + error. */ + // w/e + + } else { + /* Otherwise, if the current node is an element with + the same tag name as that of the token pop that element + from the stack. */ + array_pop($this->stack); + } + + /* In any case, set the form element pointer to null. */ + $this->form_pointer = null; + break; + + /* An end tag whose tag name is "p" */ + case 'p': + /* If the stack of open elements has a p element in scope, + then generate implied end tags, except for p elements. */ + if ($this->elementInScope('p')) { + $this->generateImpliedEndTags(array('p')); + + /* If the current node is not a p element, then this is + a parse error. */ + // k + + /* If the stack of open elements has a p element in + scope, then pop elements from this stack until the stack + no longer has a p element in scope. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->elementInScope('p')) { + array_pop($this->stack); + + } else { + break; + } + } + } + break; + + /* An end tag whose tag name is "dd", "dt", or "li" */ + case 'dd': + case 'dt': + case 'li': + /* If the stack of open elements has an element in scope + whose tag name matches the tag name of the token, then + generate implied end tags, except for elements with the + same tag name as the token. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(array($token['name'])); + + /* If the current node is not an element with the same + tag name as the token, then this is a parse error. */ + // w/e + + /* If the stack of open elements has an element in scope + whose tag name matches the tag name of the token, then + pop elements from this stack until an element with that + tag name has been popped from the stack. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === $token['name']) { + $n = -1; + } + + array_pop($this->stack); + } + } + break; + + /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4", + "h5", "h6" */ + case 'h1': + case 'h2': + case 'h3': + case 'h4': + case 'h5': + case 'h6': + $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'); + + /* If the stack of open elements has in scope an element whose + tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then + generate implied end tags. */ + if ($this->elementInScope($elements)) { + $this->generateImpliedEndTags(); + + /* Now, if the current node is not an element with the same + tag name as that of the token, then this is a parse error. */ + // w/e + + /* If the stack of open elements has in scope an element + whose tag name is one of "h1", "h2", "h3", "h4", "h5", or + "h6", then pop elements from the stack until an element + with one of those tag names has been popped from the stack. */ + while ($this->elementInScope($elements)) { + array_pop($this->stack); + } + } + break; + + /* An end tag whose tag name is one of: "a", "b", "big", "em", + "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */ + case 'a': + case 'b': + case 'big': + case 'em': + case 'font': + case 'i': + case 'nobr': + case 's': + case 'small': + case 'strike': + case 'strong': + case 'tt': + case 'u': + /* 1. Let the formatting element be the last element in + the list of active formatting elements that: + * is between the end of the list and the last scope + marker in the list, if any, or the start of the list + otherwise, and + * has the same tag name as the token. + */ + while (true) { + for ($a = count($this->a_formatting) - 1; $a >= 0; $a--) { + if ($this->a_formatting[$a] === self::MARKER) { + break; + + } elseif ($this->a_formatting[$a]->tagName === $token['name']) { + $formatting_element = $this->a_formatting[$a]; + $in_stack = in_array($formatting_element, $this->stack, true); + $fe_af_pos = $a; + break; + } + } + + /* If there is no such node, or, if that node is + also in the stack of open elements but the element + is not in scope, then this is a parse error. Abort + these steps. The token is ignored. */ + if (!isset($formatting_element) || ($in_stack && + !$this->elementInScope($token['name'])) + ) { + break; + + /* Otherwise, if there is such a node, but that node + is not in the stack of open elements, then this is a + parse error; remove the element from the list, and + abort these steps. */ + } elseif (isset($formatting_element) && !$in_stack) { + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); + break; + } + + /* 2. Let the furthest block be the topmost node in the + stack of open elements that is lower in the stack + than the formatting element, and is not an element in + the phrasing or formatting categories. There might + not be one. */ + $fe_s_pos = array_search($formatting_element, $this->stack, true); + $length = count($this->stack); + + for ($s = $fe_s_pos + 1; $s < $length; $s++) { + $category = $this->getElementCategory($this->stack[$s]->nodeName); + + if ($category !== self::PHRASING && $category !== self::FORMATTING) { + $furthest_block = $this->stack[$s]; + } + } + + /* 3. If there is no furthest block, then the UA must + skip the subsequent steps and instead just pop all + the nodes from the bottom of the stack of open + elements, from the current node up to the formatting + element, and remove the formatting element from the + list of active formatting elements. */ + if (!isset($furthest_block)) { + for ($n = $length - 1; $n >= $fe_s_pos; $n--) { + array_pop($this->stack); + } + + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); + break; + } + + /* 4. Let the common ancestor be the element + immediately above the formatting element in the stack + of open elements. */ + $common_ancestor = $this->stack[$fe_s_pos - 1]; + + /* 5. If the furthest block has a parent node, then + remove the furthest block from its parent node. */ + if ($furthest_block->parentNode !== null) { + $furthest_block->parentNode->removeChild($furthest_block); + } + + /* 6. Let a bookmark note the position of the + formatting element in the list of active formatting + elements relative to the elements on either side + of it in the list. */ + $bookmark = $fe_af_pos; + + /* 7. Let node and last node be the furthest block. + Follow these steps: */ + $node = $furthest_block; + $last_node = $furthest_block; + + while (true) { + for ($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) { + /* 7.1 Let node be the element immediately + prior to node in the stack of open elements. */ + $node = $this->stack[$n]; + + /* 7.2 If node is not in the list of active + formatting elements, then remove node from + the stack of open elements and then go back + to step 1. */ + if (!in_array($node, $this->a_formatting, true)) { + unset($this->stack[$n]); + $this->stack = array_merge($this->stack); + + } else { + break; + } + } + + /* 7.3 Otherwise, if node is the formatting + element, then go to the next step in the overall + algorithm. */ + if ($node === $formatting_element) { + break; + + /* 7.4 Otherwise, if last node is the furthest + block, then move the aforementioned bookmark to + be immediately after the node in the list of + active formatting elements. */ + } elseif ($last_node === $furthest_block) { + $bookmark = array_search($node, $this->a_formatting, true) + 1; + } + + /* 7.5 If node has any children, perform a + shallow clone of node, replace the entry for + node in the list of active formatting elements + with an entry for the clone, replace the entry + for node in the stack of open elements with an + entry for the clone, and let node be the clone. */ + if ($node->hasChildNodes()) { + $clone = $node->cloneNode(); + $s_pos = array_search($node, $this->stack, true); + $a_pos = array_search($node, $this->a_formatting, true); + + $this->stack[$s_pos] = $clone; + $this->a_formatting[$a_pos] = $clone; + $node = $clone; + } + + /* 7.6 Insert last node into node, first removing + it from its previous parent node if any. */ + if ($last_node->parentNode !== null) { + $last_node->parentNode->removeChild($last_node); + } + + $node->appendChild($last_node); + + /* 7.7 Let last node be node. */ + $last_node = $node; + } + + /* 8. Insert whatever last node ended up being in + the previous step into the common ancestor node, + first removing it from its previous parent node if + any. */ + if ($last_node->parentNode !== null) { + $last_node->parentNode->removeChild($last_node); + } + + $common_ancestor->appendChild($last_node); + + /* 9. Perform a shallow clone of the formatting + element. */ + $clone = $formatting_element->cloneNode(); + + /* 10. Take all of the child nodes of the furthest + block and append them to the clone created in the + last step. */ + while ($furthest_block->hasChildNodes()) { + $child = $furthest_block->firstChild; + $furthest_block->removeChild($child); + $clone->appendChild($child); + } + + /* 11. Append that clone to the furthest block. */ + $furthest_block->appendChild($clone); + + /* 12. Remove the formatting element from the list + of active formatting elements, and insert the clone + into the list of active formatting elements at the + position of the aforementioned bookmark. */ + $fe_af_pos = array_search($formatting_element, $this->a_formatting, true); + unset($this->a_formatting[$fe_af_pos]); + $this->a_formatting = array_merge($this->a_formatting); + + $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1); + $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting)); + $this->a_formatting = array_merge($af_part1, array($clone), $af_part2); + + /* 13. Remove the formatting element from the stack + of open elements, and insert the clone into the stack + of open elements immediately after (i.e. in a more + deeply nested position than) the position of the + furthest block in that stack. */ + $fe_s_pos = array_search($formatting_element, $this->stack, true); + $fb_s_pos = array_search($furthest_block, $this->stack, true); + unset($this->stack[$fe_s_pos]); + + $s_part1 = array_slice($this->stack, 0, $fb_s_pos); + $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack)); + $this->stack = array_merge($s_part1, array($clone), $s_part2); + + /* 14. Jump back to step 1 in this series of steps. */ + unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block); + } + break; + + /* An end tag token whose tag name is one of: "button", + "marquee", "object" */ + case 'button': + case 'marquee': + case 'object': + /* If the stack of open elements has an element in scope whose + tag name matches the tag name of the token, then generate implied + tags. */ + if ($this->elementInScope($token['name'])) { + $this->generateImpliedEndTags(); + + /* Now, if the current node is not an element with the same + tag name as the token, then this is a parse error. */ + // k + + /* Now, if the stack of open elements has an element in scope + whose tag name matches the tag name of the token, then pop + elements from the stack until that element has been popped from + the stack, and clear the list of active formatting elements up + to the last marker. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === $token['name']) { + $n = -1; + } + + array_pop($this->stack); + } + + $marker = end(array_keys($this->a_formatting, self::MARKER, true)); + + for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) { + array_pop($this->a_formatting); + } + } + break; + + /* Or an end tag whose tag name is one of: "area", "basefont", + "bgsound", "br", "embed", "hr", "iframe", "image", "img", + "input", "isindex", "noembed", "noframes", "param", "select", + "spacer", "table", "textarea", "wbr" */ + case 'area': + case 'basefont': + case 'bgsound': + case 'br': + case 'embed': + case 'hr': + case 'iframe': + case 'image': + case 'img': + case 'input': + case 'isindex': + case 'noembed': + case 'noframes': + case 'param': + case 'select': + case 'spacer': + case 'table': + case 'textarea': + case 'wbr': + // Parse error. Ignore the token. + break; + + /* An end tag token not covered by the previous entries */ + default: + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + /* Initialise node to be the current node (the bottommost + node of the stack). */ + $node = end($this->stack); + + /* If node has the same tag name as the end tag token, + then: */ + if ($token['name'] === $node->nodeName) { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* If the tag name of the end tag token does not + match the tag name of the current node, this is a + parse error. */ + // k + + /* Pop all the nodes from the current node up to + node, including node, then stop this algorithm. */ + for ($x = count($this->stack) - $n; $x >= $n; $x--) { + array_pop($this->stack); + } + + } else { + $category = $this->getElementCategory($node); + + if ($category !== self::SPECIAL && $category !== self::SCOPING) { + /* Otherwise, if node is in neither the formatting + category nor the phrasing category, then this is a + parse error. Stop this algorithm. The end tag token + is ignored. */ + return false; + } + } + } + break; + } + break; + } + } + + private function inTable($token) + { + $clear = array('html', 'table'); + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $text = $this->dom->createTextNode($token['data']); + end($this->stack)->appendChild($text); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + end($this->stack)->appendChild($comment); + + /* A start tag whose tag name is "caption" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'caption' + ) { + /* Clear the stack back to a table context. */ + $this->clearStackToTableContext($clear); + + /* Insert a marker at the end of the list of active + formatting elements. */ + $this->a_formatting[] = self::MARKER; + + /* Insert an HTML element for the token, then switch the + insertion mode to "in caption". */ + $this->insertElement($token); + $this->mode = self::IN_CAPTION; + + /* A start tag whose tag name is "colgroup" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'colgroup' + ) { + /* Clear the stack back to a table context. */ + $this->clearStackToTableContext($clear); + + /* Insert an HTML element for the token, then switch the + insertion mode to "in column group". */ + $this->insertElement($token); + $this->mode = self::IN_CGROUP; + + /* A start tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'col' + ) { + $this->inTable( + array( + 'name' => 'colgroup', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + $this->inColumnGroup($token); + + /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('tbody', 'tfoot', 'thead') + ) + ) { + /* Clear the stack back to a table context. */ + $this->clearStackToTableContext($clear); + + /* Insert an HTML element for the token, then switch the insertion + mode to "in table body". */ + $this->insertElement($token); + $this->mode = self::IN_TBODY; + + /* A start tag whose tag name is one of: "td", "th", "tr" */ + } elseif ($token['type'] === HTML5::STARTTAG && + in_array($token['name'], array('td', 'th', 'tr')) + ) { + /* Act as if a start tag token with the tag name "tbody" had been + seen, then reprocess the current token. */ + $this->inTable( + array( + 'name' => 'tbody', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inTableBody($token); + + /* A start tag whose tag name is "table" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'table' + ) { + /* Parse error. Act as if an end tag token with the tag name "table" + had been seen, then, if that token wasn't ignored, reprocess the + current token. */ + $this->inTable( + array( + 'name' => 'table', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->mainPhase($token); + + /* An end tag whose tag name is "table" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'table' + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + return false; + + /* Otherwise: */ + } else { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* Now, if the current node is not a table element, then this + is a parse error. */ + // w/e + + /* Pop elements from this stack until a table element has been + popped from the stack. */ + while (true) { + $current = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($current === 'table') { + break; + } + } + + /* Reset the insertion mode appropriately. */ + $this->resetInsertionMode(); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array( + 'body', + 'caption', + 'col', + 'colgroup', + 'html', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + // Parse error. Ignore the token. + + /* Anything else */ + } else { + /* Parse error. Process the token as if the insertion mode was "in + body", with the following exception: */ + + /* If the current node is a table, tbody, tfoot, thead, or tr + element, then, whenever a node would be inserted into the current + node, it must instead be inserted into the foster parent element. */ + if (in_array( + end($this->stack)->nodeName, + array('table', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { + /* The foster parent element is the parent element of the last + table element in the stack of open elements, if there is a + table element and it has such a parent element. If there is no + table element in the stack of open elements (innerHTML case), + then the foster parent element is the first element in the + stack of open elements (the html element). Otherwise, if there + is a table element in the stack of open elements, but the last + table element in the stack of open elements has no parent, or + its parent node is not an element, then the foster parent + element is the element before the last table element in the + stack of open elements. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === 'table') { + $table = $this->stack[$n]; + break; + } + } + + if (isset($table) && $table->parentNode !== null) { + $this->foster_parent = $table->parentNode; + + } elseif (!isset($table)) { + $this->foster_parent = $this->stack[0]; + + } elseif (isset($table) && ($table->parentNode === null || + $table->parentNode->nodeType !== XML_ELEMENT_NODE) + ) { + $this->foster_parent = $this->stack[$n - 1]; + } + } + + $this->inBody($token); + } + } + + private function inCaption($token) + { + /* An end tag whose tag name is "caption" */ + if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore + + /* Otherwise: */ + } else { + /* Generate implied end tags. */ + $this->generateImpliedEndTags(); + + /* Now, if the current node is not a caption element, then this + is a parse error. */ + // w/e + + /* Pop elements from this stack until a caption element has + been popped from the stack. */ + while (true) { + $node = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($node === 'caption') { + break; + } + } + + /* Clear the list of active formatting elements up to the last + marker. */ + $this->clearTheActiveFormattingElementsUpToTheLastMarker(); + + /* Switch the insertion mode to "in table". */ + $this->mode = self::IN_TABLE; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag + name is "table" */ + } elseif (($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array( + 'caption', + 'col', + 'colgroup', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + )) || ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'table') + ) { + /* Parse error. Act as if an end tag with the tag name "caption" + had been seen, then, if that token wasn't ignored, reprocess the + current token. */ + $this->inCaption( + array( + 'name' => 'caption', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inTable($token); + + /* An end tag whose tag name is one of: "body", "col", "colgroup", + "html", "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array( + 'body', + 'col', + 'colgroup', + 'html', + 'tbody', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + // Parse error. Ignore the token. + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in body". */ + $this->inBody($token); + } + } + + private function inColumnGroup($token) + { + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $text = $this->dom->createTextNode($token['data']); + end($this->stack)->appendChild($text); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + end($this->stack)->appendChild($comment); + + /* A start tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') { + /* Insert a col element for the token. Immediately pop the current + node off the stack of open elements. */ + $this->insertElement($token); + array_pop($this->stack); + + /* An end tag whose tag name is "colgroup" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'colgroup' + ) { + /* If the current node is the root html element, then this is a + parse error, ignore the token. (innerHTML case) */ + if (end($this->stack)->nodeName === 'html') { + // Ignore + + /* Otherwise, pop the current node (which will be a colgroup + element) from the stack of open elements. Switch the insertion + mode to "in table". */ + } else { + array_pop($this->stack); + $this->mode = self::IN_TABLE; + } + + /* An end tag whose tag name is "col" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') { + /* Parse error. Ignore the token. */ + + /* Anything else */ + } else { + /* Act as if an end tag with the tag name "colgroup" had been seen, + and then, if that token wasn't ignored, reprocess the current token. */ + $this->inColumnGroup( + array( + 'name' => 'colgroup', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inTable($token); + } + } + + private function inTableBody($token) + { + $clear = array('tbody', 'tfoot', 'thead', 'html'); + + /* A start tag whose tag name is "tr" */ + if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') { + /* Clear the stack back to a table body context. */ + $this->clearStackToTableContext($clear); + + /* Insert a tr element for the token, then switch the insertion + mode to "in row". */ + $this->insertElement($token); + $this->mode = self::IN_ROW; + + /* A start tag whose tag name is one of: "th", "td" */ + } elseif ($token['type'] === HTML5::STARTTAG && + ($token['name'] === 'th' || $token['name'] === 'td') + ) { + /* Parse error. Act as if a start tag with the tag name "tr" had + been seen, then reprocess the current token. */ + $this->inTableBody( + array( + 'name' => 'tr', + 'type' => HTML5::STARTTAG, + 'attr' => array() + ) + ); + + return $this->inRow($token); + + /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ + } elseif ($token['type'] === HTML5::ENDTAG && + in_array($token['name'], array('tbody', 'tfoot', 'thead')) + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore + + /* Otherwise: */ + } else { + /* Clear the stack back to a table body context. */ + $this->clearStackToTableContext($clear); + + /* Pop the current node from the stack of open elements. Switch + the insertion mode to "in table". */ + array_pop($this->stack); + $this->mode = self::IN_TABLE; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */ + } elseif (($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead') + )) || + ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table') + ) { + /* If the stack of open elements does not have a tbody, thead, or + tfoot element in table scope, this is a parse error. Ignore the + token. (innerHTML case) */ + if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Clear the stack back to a table body context. */ + $this->clearStackToTableContext($clear); + + /* Act as if an end tag with the same tag name as the current + node ("tbody", "tfoot", or "thead") had been seen, then + reprocess the current token. */ + $this->inTableBody( + array( + 'name' => end($this->stack)->nodeName, + 'type' => HTML5::ENDTAG + ) + ); + + return $this->mainPhase($token); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "td", "th", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr') + ) + ) { + /* Parse error. Ignore the token. */ + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in table". */ + $this->inTable($token); + } + } + + private function inRow($token) + { + $clear = array('tr', 'html'); + + /* A start tag whose tag name is one of: "th", "td" */ + if ($token['type'] === HTML5::STARTTAG && + ($token['name'] === 'th' || $token['name'] === 'td') + ) { + /* Clear the stack back to a table row context. */ + $this->clearStackToTableContext($clear); + + /* Insert an HTML element for the token, then switch the insertion + mode to "in cell". */ + $this->insertElement($token); + $this->mode = self::IN_CELL; + + /* Insert a marker at the end of the list of active formatting + elements. */ + $this->a_formatting[] = self::MARKER; + + /* An end tag whose tag name is "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Clear the stack back to a table row context. */ + $this->clearStackToTableContext($clear); + + /* Pop the current node (which will be a tr element) from the + stack of open elements. Switch the insertion mode to "in table + body". */ + array_pop($this->stack); + $this->mode = self::IN_TBODY; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { + /* Act as if an end tag with the tag name "tr" had been seen, then, + if that token wasn't ignored, reprocess the current token. */ + $this->inRow( + array( + 'name' => 'tr', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inCell($token); + + /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */ + } elseif ($token['type'] === HTML5::ENDTAG && + in_array($token['name'], array('tbody', 'tfoot', 'thead')) + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Otherwise, act as if an end tag with the tag name "tr" had + been seen, then reprocess the current token. */ + $this->inRow( + array( + 'name' => 'tr', + 'type' => HTML5::ENDTAG + ) + ); + + return $this->inCell($token); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html", "td", "th" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr') + ) + ) { + /* Parse error. Ignore the token. */ + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in table". */ + $this->inTable($token); + } + } + + private function inCell($token) + { + /* An end tag whose tag name is one of: "td", "th" */ + if ($token['type'] === HTML5::ENDTAG && + ($token['name'] === 'td' || $token['name'] === 'th') + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as that of the token, then this is a + parse error and the token must be ignored. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise: */ + } else { + /* Generate implied end tags, except for elements with the same + tag name as the token. */ + $this->generateImpliedEndTags(array($token['name'])); + + /* Now, if the current node is not an element with the same tag + name as the token, then this is a parse error. */ + // k + + /* Pop elements from this stack until an element with the same + tag name as the token has been popped from the stack. */ + while (true) { + $node = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($node === $token['name']) { + break; + } + } + + /* Clear the list of active formatting elements up to the last + marker. */ + $this->clearTheActiveFormattingElementsUpToTheLastMarker(); + + /* Switch the insertion mode to "in row". (The current node + will be a tr element at this point.) */ + $this->mode = self::IN_ROW; + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array( + 'caption', + 'col', + 'colgroup', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + /* If the stack of open elements does not have a td or th element + in table scope, then this is a parse error; ignore the token. + (innerHTML case) */ + if (!$this->elementInScope(array('td', 'th'), true)) { + // Ignore. + + /* Otherwise, close the cell (see below) and reprocess the current + token. */ + } else { + $this->closeCell(); + return $this->inRow($token); + } + + /* A start tag whose tag name is one of: "caption", "col", "colgroup", + "tbody", "td", "tfoot", "th", "thead", "tr" */ + } elseif ($token['type'] === HTML5::STARTTAG && in_array( + $token['name'], + array( + 'caption', + 'col', + 'colgroup', + 'tbody', + 'td', + 'tfoot', + 'th', + 'thead', + 'tr' + ) + ) + ) { + /* If the stack of open elements does not have a td or th element + in table scope, then this is a parse error; ignore the token. + (innerHTML case) */ + if (!$this->elementInScope(array('td', 'th'), true)) { + // Ignore. + + /* Otherwise, close the cell (see below) and reprocess the current + token. */ + } else { + $this->closeCell(); + return $this->inRow($token); + } + + /* An end tag whose tag name is one of: "body", "caption", "col", + "colgroup", "html" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('body', 'caption', 'col', 'colgroup', 'html') + ) + ) { + /* Parse error. Ignore the token. */ + + /* An end tag whose tag name is one of: "table", "tbody", "tfoot", + "thead", "tr" */ + } elseif ($token['type'] === HTML5::ENDTAG && in_array( + $token['name'], + array('table', 'tbody', 'tfoot', 'thead', 'tr') + ) + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as that of the token (which can only + happen for "tbody", "tfoot" and "thead", or, in the innerHTML case), + then this is a parse error and the token must be ignored. */ + if (!$this->elementInScope($token['name'], true)) { + // Ignore. + + /* Otherwise, close the cell (see below) and reprocess the current + token. */ + } else { + $this->closeCell(); + return $this->inRow($token); + } + + /* Anything else */ + } else { + /* Process the token as if the insertion mode was "in body". */ + $this->inBody($token); + } + } + + private function inSelect($token) + { + /* Handle the token as follows: */ + + /* A character token */ + if ($token['type'] === HTML5::CHARACTR) { + /* Append the token's character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag token whose tag name is "option" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'option' + ) { + /* If the current node is an option element, act as if an end tag + with the tag name "option" had been seen. */ + if (end($this->stack)->nodeName === 'option') { + $this->inSelect( + array( + 'name' => 'option', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* A start tag token whose tag name is "optgroup" */ + } elseif ($token['type'] === HTML5::STARTTAG && + $token['name'] === 'optgroup' + ) { + /* If the current node is an option element, act as if an end tag + with the tag name "option" had been seen. */ + if (end($this->stack)->nodeName === 'option') { + $this->inSelect( + array( + 'name' => 'option', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* If the current node is an optgroup element, act as if an end tag + with the tag name "optgroup" had been seen. */ + if (end($this->stack)->nodeName === 'optgroup') { + $this->inSelect( + array( + 'name' => 'optgroup', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* An end tag token whose tag name is "optgroup" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'optgroup' + ) { + /* First, if the current node is an option element, and the node + immediately before it in the stack of open elements is an optgroup + element, then act as if an end tag with the tag name "option" had + been seen. */ + $elements_in_stack = count($this->stack); + + if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' && + $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup' + ) { + $this->inSelect( + array( + 'name' => 'option', + 'type' => HTML5::ENDTAG + ) + ); + } + + /* If the current node is an optgroup element, then pop that node + from the stack of open elements. Otherwise, this is a parse error, + ignore the token. */ + if ($this->stack[$elements_in_stack - 1] === 'optgroup') { + array_pop($this->stack); + } + + /* An end tag token whose tag name is "option" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'option' + ) { + /* If the current node is an option element, then pop that node + from the stack of open elements. Otherwise, this is a parse error, + ignore the token. */ + if (end($this->stack)->nodeName === 'option') { + array_pop($this->stack); + } + + /* An end tag whose tag name is "select" */ + } elseif ($token['type'] === HTML5::ENDTAG && + $token['name'] === 'select' + ) { + /* If the stack of open elements does not have an element in table + scope with the same tag name as the token, this is a parse error. + Ignore the token. (innerHTML case) */ + if (!$this->elementInScope($token['name'], true)) { + // w/e + + /* Otherwise: */ + } else { + /* Pop elements from the stack of open elements until a select + element has been popped from the stack. */ + while (true) { + $current = end($this->stack)->nodeName; + array_pop($this->stack); + + if ($current === 'select') { + break; + } + } + + /* Reset the insertion mode appropriately. */ + $this->resetInsertionMode(); + } + + /* A start tag whose tag name is "select" */ + } elseif ($token['name'] === 'select' && + $token['type'] === HTML5::STARTTAG + ) { + /* Parse error. Act as if the token had been an end tag with the + tag name "select" instead. */ + $this->inSelect( + array( + 'name' => 'select', + 'type' => HTML5::ENDTAG + ) + ); + + /* An end tag whose tag name is one of: "caption", "table", "tbody", + "tfoot", "thead", "tr", "td", "th" */ + } elseif (in_array( + $token['name'], + array( + 'caption', + 'table', + 'tbody', + 'tfoot', + 'thead', + 'tr', + 'td', + 'th' + ) + ) && $token['type'] === HTML5::ENDTAG + ) { + /* Parse error. */ + // w/e + + /* If the stack of open elements has an element in table scope with + the same tag name as that of the token, then act as if an end tag + with the tag name "select" had been seen, and reprocess the token. + Otherwise, ignore the token. */ + if ($this->elementInScope($token['name'], true)) { + $this->inSelect( + array( + 'name' => 'select', + 'type' => HTML5::ENDTAG + ) + ); + + $this->mainPhase($token); + } + + /* Anything else */ + } else { + /* Parse error. Ignore the token. */ + } + } + + private function afterBody($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Process the token as it would be processed if the insertion mode + was "in body". */ + $this->inBody($token); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the first element in the stack of open + elements (the html element), with the data attribute set to the + data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + $this->stack[0]->appendChild($comment); + + /* An end tag with the tag name "html" */ + } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') { + /* If the parser was originally created in order to handle the + setting of an element's innerHTML attribute, this is a parse error; + ignore the token. (The element will be an html element in this + case.) (innerHTML case) */ + + /* Otherwise, switch to the trailing end phase. */ + $this->phase = self::END_PHASE; + + /* Anything else */ + } else { + /* Parse error. Set the insertion mode to "in body" and reprocess + the token. */ + $this->mode = self::IN_BODY; + return $this->inBody($token); + } + } + + private function inFrameset($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* A start tag with the tag name "frameset" */ + } elseif ($token['name'] === 'frameset' && + $token['type'] === HTML5::STARTTAG + ) { + $this->insertElement($token); + + /* An end tag with the tag name "frameset" */ + } elseif ($token['name'] === 'frameset' && + $token['type'] === HTML5::ENDTAG + ) { + /* If the current node is the root html element, then this is a + parse error; ignore the token. (innerHTML case) */ + if (end($this->stack)->nodeName === 'html') { + // Ignore + + } else { + /* Otherwise, pop the current node from the stack of open + elements. */ + array_pop($this->stack); + + /* If the parser was not originally created in order to handle + the setting of an element's innerHTML attribute (innerHTML case), + and the current node is no longer a frameset element, then change + the insertion mode to "after frameset". */ + $this->mode = self::AFTR_FRAME; + } + + /* A start tag with the tag name "frame" */ + } elseif ($token['name'] === 'frame' && + $token['type'] === HTML5::STARTTAG + ) { + /* Insert an HTML element for the token. */ + $this->insertElement($token); + + /* Immediately pop the current node off the stack of open elements. */ + array_pop($this->stack); + + /* A start tag with the tag name "noframes" */ + } elseif ($token['name'] === 'noframes' && + $token['type'] === HTML5::STARTTAG + ) { + /* Process the token as if the insertion mode had been "in body". */ + $this->inBody($token); + + /* Anything else */ + } else { + /* Parse error. Ignore the token. */ + } + } + + private function afterFrameset($token) + { + /* Handle the token as follows: */ + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */ + if ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Append the character to the current node. */ + $this->insertText($token['data']); + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the current node with the data + attribute set to the data given in the comment token. */ + $this->insertComment($token['data']); + + /* An end tag with the tag name "html" */ + } elseif ($token['name'] === 'html' && + $token['type'] === HTML5::ENDTAG + ) { + /* Switch to the trailing end phase. */ + $this->phase = self::END_PHASE; + + /* A start tag with the tag name "noframes" */ + } elseif ($token['name'] === 'noframes' && + $token['type'] === HTML5::STARTTAG + ) { + /* Process the token as if the insertion mode had been "in body". */ + $this->inBody($token); + + /* Anything else */ + } else { + /* Parse error. Ignore the token. */ + } + } + + private function trailingEndPhase($token) + { + /* After the main phase, as each token is emitted from the tokenisation + stage, it must be processed as described in this section. */ + + /* A DOCTYPE token */ + if ($token['type'] === HTML5::DOCTYPE) { + // Parse error. Ignore the token. + + /* A comment token */ + } elseif ($token['type'] === HTML5::COMMENT) { + /* Append a Comment node to the Document object with the data + attribute set to the data given in the comment token. */ + $comment = $this->dom->createComment($token['data']); + $this->dom->appendChild($comment); + + /* A character token that is one of one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE */ + } elseif ($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']) + ) { + /* Process the token as it would be processed in the main phase. */ + $this->mainPhase($token); + + /* A character token that is not one of U+0009 CHARACTER TABULATION, + U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF), + or U+0020 SPACE. Or a start tag token. Or an end tag token. */ + } elseif (($token['type'] === HTML5::CHARACTR && + preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || + $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG + ) { + /* Parse error. Switch back to the main phase and reprocess the + token. */ + $this->phase = self::MAIN_PHASE; + return $this->mainPhase($token); + + /* An end-of-file token */ + } elseif ($token['type'] === HTML5::EOF) { + /* OMG DONE!! */ + } + } + + private function insertElement($token, $append = true, $check = false) + { + // Proprietary workaround for libxml2's limitations with tag names + if ($check) { + // Slightly modified HTML5 tag-name modification, + // removing anything that's not an ASCII letter, digit, or hyphen + $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']); + // Remove leading hyphens and numbers + $token['name'] = ltrim($token['name'], '-0..9'); + // In theory, this should ever be needed, but just in case + if ($token['name'] === '') { + $token['name'] = 'span'; + } // arbitrary generic choice + } + + $el = $this->dom->createElement($token['name']); + + foreach ($token['attr'] as $attr) { + if (!$el->hasAttribute($attr['name'])) { + $el->setAttribute($attr['name'], $attr['value']); + } + } + + $this->appendToRealParent($el); + $this->stack[] = $el; + + return $el; + } + + private function insertText($data) + { + $text = $this->dom->createTextNode($data); + $this->appendToRealParent($text); + } + + private function insertComment($data) + { + $comment = $this->dom->createComment($data); + $this->appendToRealParent($comment); + } + + private function appendToRealParent($node) + { + if ($this->foster_parent === null) { + end($this->stack)->appendChild($node); + + } elseif ($this->foster_parent !== null) { + /* If the foster parent element is the parent element of the + last table element in the stack of open elements, then the new + node must be inserted immediately before the last table element + in the stack of open elements in the foster parent element; + otherwise, the new node must be appended to the foster parent + element. */ + for ($n = count($this->stack) - 1; $n >= 0; $n--) { + if ($this->stack[$n]->nodeName === 'table' && + $this->stack[$n]->parentNode !== null + ) { + $table = $this->stack[$n]; + break; + } + } + + if (isset($table) && $this->foster_parent->isSameNode($table->parentNode)) { + $this->foster_parent->insertBefore($node, $table); + } else { + $this->foster_parent->appendChild($node); + } + + $this->foster_parent = null; + } + } + + private function elementInScope($el, $table = false) + { + if (is_array($el)) { + foreach ($el as $element) { + if ($this->elementInScope($element, $table)) { + return true; + } + } + + return false; + } + + $leng = count($this->stack); + + for ($n = 0; $n < $leng; $n++) { + /* 1. Initialise node to be the current node (the bottommost node of + the stack). */ + $node = $this->stack[$leng - 1 - $n]; + + if ($node->tagName === $el) { + /* 2. If node is the target node, terminate in a match state. */ + return true; + + } elseif ($node->tagName === 'table') { + /* 3. Otherwise, if node is a table element, terminate in a failure + state. */ + return false; + + } elseif ($table === true && in_array( + $node->tagName, + array( + 'caption', + 'td', + 'th', + 'button', + 'marquee', + 'object' + ) + ) + ) { + /* 4. Otherwise, if the algorithm is the "has an element in scope" + variant (rather than the "has an element in table scope" variant), + and node is one of the following, terminate in a failure state. */ + return false; + + } elseif ($node === $node->ownerDocument->documentElement) { + /* 5. Otherwise, if node is an html element (root element), terminate + in a failure state. (This can only happen if the node is the topmost + node of the stack of open elements, and prevents the next step from + being invoked if there are no more elements in the stack.) */ + return false; + } + + /* Otherwise, set node to the previous entry in the stack of open + elements and return to step 2. (This will never fail, since the loop + will always terminate in the previous step if the top of the stack + is reached.) */ + } + } + + private function reconstructActiveFormattingElements() + { + /* 1. If there are no entries in the list of active formatting elements, + then there is nothing to reconstruct; stop this algorithm. */ + $formatting_elements = count($this->a_formatting); + + if ($formatting_elements === 0) { + return false; + } + + /* 3. Let entry be the last (most recently added) element in the list + of active formatting elements. */ + $entry = end($this->a_formatting); + + /* 2. If the last (most recently added) entry in the list of active + formatting elements is a marker, or if it is an element that is in the + stack of open elements, then there is nothing to reconstruct; stop this + algorithm. */ + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { + return false; + } + + for ($a = $formatting_elements - 1; $a >= 0; true) { + /* 4. If there are no entries before entry in the list of active + formatting elements, then jump to step 8. */ + if ($a === 0) { + $step_seven = false; + break; + } + + /* 5. Let entry be the entry one earlier than entry in the list of + active formatting elements. */ + $a--; + $entry = $this->a_formatting[$a]; + + /* 6. If entry is neither a marker nor an element that is also in + thetack of open elements, go to step 4. */ + if ($entry === self::MARKER || in_array($entry, $this->stack, true)) { + break; + } + } + + while (true) { + /* 7. Let entry be the element one later than entry in the list of + active formatting elements. */ + if (isset($step_seven) && $step_seven === true) { + $a++; + $entry = $this->a_formatting[$a]; + } + + /* 8. Perform a shallow clone of the element entry to obtain clone. */ + $clone = $entry->cloneNode(); + + /* 9. Append clone to the current node and push it onto the stack + of open elements so that it is the new current node. */ + end($this->stack)->appendChild($clone); + $this->stack[] = $clone; + + /* 10. Replace the entry for entry in the list with an entry for + clone. */ + $this->a_formatting[$a] = $clone; + + /* 11. If the entry for clone in the list of active formatting + elements is not the last entry in the list, return to step 7. */ + if (end($this->a_formatting) !== $clone) { + $step_seven = true; + } else { + break; + } + } + } + + private function clearTheActiveFormattingElementsUpToTheLastMarker() + { + /* When the steps below require the UA to clear the list of active + formatting elements up to the last marker, the UA must perform the + following steps: */ + + while (true) { + /* 1. Let entry be the last (most recently added) entry in the list + of active formatting elements. */ + $entry = end($this->a_formatting); + + /* 2. Remove entry from the list of active formatting elements. */ + array_pop($this->a_formatting); + + /* 3. If entry was a marker, then stop the algorithm at this point. + The list has been cleared up to the last marker. */ + if ($entry === self::MARKER) { + break; + } + } + } + + private function generateImpliedEndTags($exclude = array()) + { + /* When the steps below require the UA to generate implied end tags, + then, if the current node is a dd element, a dt element, an li element, + a p element, a td element, a th element, or a tr element, the UA must + act as if an end tag with the respective tag name had been seen and + then generate implied end tags again. */ + $node = end($this->stack); + $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude); + + while (in_array(end($this->stack)->nodeName, $elements)) { + array_pop($this->stack); + } + } + + private function getElementCategory($node) + { + $name = $node->tagName; + if (in_array($name, $this->special)) { + return self::SPECIAL; + } elseif (in_array($name, $this->scoping)) { + return self::SCOPING; + } elseif (in_array($name, $this->formatting)) { + return self::FORMATTING; + } else { + return self::PHRASING; + } + } + + private function clearStackToTableContext($elements) + { + /* When the steps above require the UA to clear the stack back to a + table context, it means that the UA must, while the current node is not + a table element or an html element, pop elements from the stack of open + elements. If this causes any elements to be popped from the stack, then + this is a parse error. */ + while (true) { + $node = end($this->stack)->nodeName; + + if (in_array($node, $elements)) { + break; + } else { + array_pop($this->stack); + } + } + } + + private function resetInsertionMode() + { + /* 1. Let last be false. */ + $last = false; + $leng = count($this->stack); + + for ($n = $leng - 1; $n >= 0; $n--) { + /* 2. Let node be the last node in the stack of open elements. */ + $node = $this->stack[$n]; + + /* 3. If node is the first node in the stack of open elements, then + set last to true. If the element whose innerHTML attribute is being + set is neither a td element nor a th element, then set node to the + element whose innerHTML attribute is being set. (innerHTML case) */ + if ($this->stack[0]->isSameNode($node)) { + $last = true; + } + + /* 4. If node is a select element, then switch the insertion mode to + "in select" and abort these steps. (innerHTML case) */ + if ($node->nodeName === 'select') { + $this->mode = self::IN_SELECT; + break; + + /* 5. If node is a td or th element, then switch the insertion mode + to "in cell" and abort these steps. */ + } elseif ($node->nodeName === 'td' || $node->nodeName === 'th') { + $this->mode = self::IN_CELL; + break; + + /* 6. If node is a tr element, then switch the insertion mode to + "in row" and abort these steps. */ + } elseif ($node->nodeName === 'tr') { + $this->mode = self::IN_ROW; + break; + + /* 7. If node is a tbody, thead, or tfoot element, then switch the + insertion mode to "in table body" and abort these steps. */ + } elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) { + $this->mode = self::IN_TBODY; + break; + + /* 8. If node is a caption element, then switch the insertion mode + to "in caption" and abort these steps. */ + } elseif ($node->nodeName === 'caption') { + $this->mode = self::IN_CAPTION; + break; + + /* 9. If node is a colgroup element, then switch the insertion mode + to "in column group" and abort these steps. (innerHTML case) */ + } elseif ($node->nodeName === 'colgroup') { + $this->mode = self::IN_CGROUP; + break; + + /* 10. If node is a table element, then switch the insertion mode + to "in table" and abort these steps. */ + } elseif ($node->nodeName === 'table') { + $this->mode = self::IN_TABLE; + break; + + /* 11. If node is a head element, then switch the insertion mode + to "in body" ("in body"! not "in head"!) and abort these steps. + (innerHTML case) */ + } elseif ($node->nodeName === 'head') { + $this->mode = self::IN_BODY; + break; + + /* 12. If node is a body element, then switch the insertion mode to + "in body" and abort these steps. */ + } elseif ($node->nodeName === 'body') { + $this->mode = self::IN_BODY; + break; + + /* 13. If node is a frameset element, then switch the insertion + mode to "in frameset" and abort these steps. (innerHTML case) */ + } elseif ($node->nodeName === 'frameset') { + $this->mode = self::IN_FRAME; + break; + + /* 14. If node is an html element, then: if the head element + pointer is null, switch the insertion mode to "before head", + otherwise, switch the insertion mode to "after head". In either + case, abort these steps. (innerHTML case) */ + } elseif ($node->nodeName === 'html') { + $this->mode = ($this->head_pointer === null) + ? self::BEFOR_HEAD + : self::AFTER_HEAD; + + break; + + /* 15. If last is true, then set the insertion mode to "in body" + and abort these steps. (innerHTML case) */ + } elseif ($last) { + $this->mode = self::IN_BODY; + break; + } + } + } + + private function closeCell() + { + /* If the stack of open elements has a td or th element in table scope, + then act as if an end tag token with that tag name had been seen. */ + foreach (array('td', 'th') as $cell) { + if ($this->elementInScope($cell, true)) { + $this->inCell( + array( + 'name' => $cell, + 'type' => HTML5::ENDTAG + ) + ); + + break; + } + } + } + + public function save() + { + return $this->dom; + } +} diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node.php new file mode 100644 index 0000000000..3995fec9fe --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node.php @@ -0,0 +1,49 @@ +data = $data; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Comment($this->data, $this->line, $this->col), null); + } +} diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node/Element.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node/Element.php new file mode 100644 index 0000000000..6cbf56dada --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node/Element.php @@ -0,0 +1,59 @@ + form or the form, i.e. + * is it a pair of start/end tokens or an empty token. + * @bool + */ + public $empty = false; + + public $endCol = null, $endLine = null, $endArmor = array(); + + public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) { + $this->name = $name; + $this->attr = $attr; + $this->line = $line; + $this->col = $col; + $this->armor = $armor; + } + + public function toTokenPair() { + // XXX inefficiency here, normalization is not necessary + if ($this->empty) { + return array(new HTMLPurifier_Token_Empty($this->name, $this->attr, $this->line, $this->col, $this->armor), null); + } else { + $start = new HTMLPurifier_Token_Start($this->name, $this->attr, $this->line, $this->col, $this->armor); + $end = new HTMLPurifier_Token_End($this->name, array(), $this->endLine, $this->endCol, $this->endArmor); + //$end->start = $start; + return array($start, $end); + } + } +} + diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node/Text.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node/Text.php new file mode 100644 index 0000000000..aec9166473 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Node/Text.php @@ -0,0 +1,54 @@ +data = $data; + $this->is_whitespace = $is_whitespace; + $this->line = $line; + $this->col = $col; + } + + public function toTokenPair() { + return array(new HTMLPurifier_Token_Text($this->data, $this->line, $this->col), null); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PercentEncoder.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PercentEncoder.php new file mode 100644 index 0000000000..18c8bbb00a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PercentEncoder.php @@ -0,0 +1,111 @@ +preserve[$i] = true; + } + for ($i = 65; $i <= 90; $i++) { // upper-case + $this->preserve[$i] = true; + } + for ($i = 97; $i <= 122; $i++) { // lower-case + $this->preserve[$i] = true; + } + $this->preserve[45] = true; // Dash - + $this->preserve[46] = true; // Period . + $this->preserve[95] = true; // Underscore _ + $this->preserve[126]= true; // Tilde ~ + + // extra letters not to escape + if ($preserve !== false) { + for ($i = 0, $c = strlen($preserve); $i < $c; $i++) { + $this->preserve[ord($preserve[$i])] = true; + } + } + } + + /** + * Our replacement for urlencode, it encodes all non-reserved characters, + * as well as any extra characters that were instructed to be preserved. + * @note + * Assumes that the string has already been normalized, making any + * and all percent escape sequences valid. Percents will not be + * re-escaped, regardless of their status in $preserve + * @param string $string String to be encoded + * @return string Encoded string. + */ + public function encode($string) + { + $ret = ''; + for ($i = 0, $c = strlen($string); $i < $c; $i++) { + if ($string[$i] !== '%' && !isset($this->preserve[$int = ord($string[$i])])) { + $ret .= '%' . sprintf('%02X', $int); + } else { + $ret .= $string[$i]; + } + } + return $ret; + } + + /** + * Fix up percent-encoding by decoding unreserved characters and normalizing. + * @warning This function is affected by $preserve, even though the + * usual desired behavior is for this not to preserve those + * characters. Be careful when reusing instances of PercentEncoder! + * @param string $string String to normalize + * @return string + */ + public function normalize($string) + { + if ($string == '') { + return ''; + } + $parts = explode('%', $string); + $ret = array_shift($parts); + foreach ($parts as $part) { + $length = strlen($part); + if ($length < 2) { + $ret .= '%25' . $part; + continue; + } + $encoding = substr($part, 0, 2); + $text = substr($part, 2); + if (!ctype_xdigit($encoding)) { + $ret .= '%25' . $part; + continue; + } + $int = hexdec($encoding); + if (isset($this->preserve[$int])) { + $ret .= chr($int) . $text; + continue; + } + $encoding = strtoupper($encoding); + $ret .= '%' . $encoding . $text; + } + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer.php new file mode 100644 index 0000000000..549e4cea1e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer.php @@ -0,0 +1,218 @@ +getAll(); + $context = new HTMLPurifier_Context(); + $this->generator = new HTMLPurifier_Generator($config, $context); + } + + /** + * Main function that renders object or aspect of that object + * @note Parameters vary depending on printer + */ + // function render() {} + + /** + * Returns a start tag + * @param string $tag Tag name + * @param array $attr Attribute array + * @return string + */ + protected function start($tag, $attr = array()) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Start($tag, $attr ? $attr : array()) + ); + } + + /** + * Returns an end tag + * @param string $tag Tag name + * @return string + */ + protected function end($tag) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_End($tag) + ); + } + + /** + * Prints a complete element with content inside + * @param string $tag Tag name + * @param string $contents Element contents + * @param array $attr Tag attributes + * @param bool $escape whether or not to escape contents + * @return string + */ + protected function element($tag, $contents, $attr = array(), $escape = true) + { + return $this->start($tag, $attr) . + ($escape ? $this->escape($contents) : $contents) . + $this->end($tag); + } + + /** + * @param string $tag + * @param array $attr + * @return string + */ + protected function elementEmpty($tag, $attr = array()) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Empty($tag, $attr) + ); + } + + /** + * @param string $text + * @return string + */ + protected function text($text) + { + return $this->generator->generateFromToken( + new HTMLPurifier_Token_Text($text) + ); + } + + /** + * Prints a simple key/value row in a table. + * @param string $name Key + * @param mixed $value Value + * @return string + */ + protected function row($name, $value) + { + if (is_bool($value)) { + $value = $value ? 'On' : 'Off'; + } + return + $this->start('tr') . "\n" . + $this->element('th', $name) . "\n" . + $this->element('td', $value) . "\n" . + $this->end('tr'); + } + + /** + * Escapes a string for HTML output. + * @param string $string String to escape + * @return string + */ + protected function escape($string) + { + $string = HTMLPurifier_Encoder::cleanUTF8($string); + $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8'); + return $string; + } + + /** + * Takes a list of strings and turns them into a single list + * @param string[] $array List of strings + * @param bool $polite Bool whether or not to add an end before the last + * @return string + */ + protected function listify($array, $polite = false) + { + if (empty($array)) { + return 'None'; + } + $ret = ''; + $i = count($array); + foreach ($array as $value) { + $i--; + $ret .= $value; + if ($i > 0 && !($polite && $i == 1)) { + $ret .= ', '; + } + if ($polite && $i == 1) { + $ret .= 'and '; + } + } + return $ret; + } + + /** + * Retrieves the class of an object without prefixes, as well as metadata + * @param object $obj Object to determine class of + * @param string $sec_prefix Further prefix to remove + * @return string + */ + protected function getClass($obj, $sec_prefix = '') + { + static $five = null; + if ($five === null) { + $five = version_compare(PHP_VERSION, '5', '>='); + } + $prefix = 'HTMLPurifier_' . $sec_prefix; + if (!$five) { + $prefix = strtolower($prefix); + } + $class = str_replace($prefix, '', get_class($obj)); + $lclass = strtolower($class); + $class .= '('; + switch ($lclass) { + case 'enum': + $values = array(); + foreach ($obj->valid_values as $value => $bool) { + $values[] = $value; + } + $class .= implode(', ', $values); + break; + case 'css_composite': + $values = array(); + foreach ($obj->defs as $def) { + $values[] = $this->getClass($def, $sec_prefix); + } + $class .= implode(', ', $values); + break; + case 'css_multiple': + $class .= $this->getClass($obj->single, $sec_prefix) . ', '; + $class .= $obj->max; + break; + case 'css_denyelementdecorator': + $class .= $this->getClass($obj->def, $sec_prefix) . ', '; + $class .= $obj->element; + break; + case 'css_importantdecorator': + $class .= $this->getClass($obj->def, $sec_prefix); + if ($obj->allow) { + $class .= ', !important'; + } + break; + } + $class .= ')'; + return $class; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/CSSDefinition.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/CSSDefinition.php new file mode 100644 index 0000000000..29505fe12d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/CSSDefinition.php @@ -0,0 +1,44 @@ +def = $config->getCSSDefinition(); + $ret = ''; + + $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer')); + $ret .= $this->start('table'); + + $ret .= $this->element('caption', 'Properties ($info)'); + + $ret .= $this->start('thead'); + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Property', array('class' => 'heavy')); + $ret .= $this->element('th', 'Definition', array('class' => 'heavy', 'style' => 'width:auto;')); + $ret .= $this->end('tr'); + $ret .= $this->end('thead'); + + ksort($this->def->info); + foreach ($this->def->info as $property => $obj) { + $name = $this->getClass($obj, 'AttrDef_'); + $ret .= $this->row($property, $name); + } + + $ret .= $this->end('table'); + $ret .= $this->end('div'); + + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.css b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.css new file mode 100644 index 0000000000..3ff1a88aa4 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.css @@ -0,0 +1,10 @@ + +.hp-config {} + +.hp-config tbody th {text-align:right; padding-right:0.5em;} +.hp-config thead, .hp-config .namespace {background:#3C578C; color:#FFF;} +.hp-config .namespace th {text-align:center;} +.hp-config .verbose {display:none;} +.hp-config .controls {text-align:center;} + +/* vim: et sw=4 sts=4 */ diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.js b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.js new file mode 100644 index 0000000000..cba00c9b80 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.js @@ -0,0 +1,5 @@ +function toggleWriteability(id_of_patient, checked) { + document.getElementById(id_of_patient).disabled = checked; +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.php new file mode 100644 index 0000000000..36100ce738 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/ConfigForm.php @@ -0,0 +1,447 @@ +docURL = $doc_url; + $this->name = $name; + $this->compress = $compress; + // initialize sub-printers + $this->fields[0] = new HTMLPurifier_Printer_ConfigForm_default(); + $this->fields[HTMLPurifier_VarParser::BOOL] = new HTMLPurifier_Printer_ConfigForm_bool(); + } + + /** + * Sets default column and row size for textareas in sub-printers + * @param $cols Integer columns of textarea, null to use default + * @param $rows Integer rows of textarea, null to use default + */ + public function setTextareaDimensions($cols = null, $rows = null) + { + if ($cols) { + $this->fields['default']->cols = $cols; + } + if ($rows) { + $this->fields['default']->rows = $rows; + } + } + + /** + * Retrieves styling, in case it is not accessible by webserver + */ + public static function getCSS() + { + return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.css'); + } + + /** + * Retrieves JavaScript, in case it is not accessible by webserver + */ + public static function getJavaScript() + { + return file_get_contents(HTMLPURIFIER_PREFIX . '/HTMLPurifier/Printer/ConfigForm.js'); + } + + /** + * Returns HTML output for a configuration form + * @param HTMLPurifier_Config|array $config Configuration object of current form state, or an array + * where [0] has an HTML namespace and [1] is being rendered. + * @param array|bool $allowed Optional namespace(s) and directives to restrict form to. + * @param bool $render_controls + * @return string + */ + public function render($config, $allowed = true, $render_controls = true) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + + $this->config = $config; + $this->genConfig = $gen_config; + $this->prepareGenerator($gen_config); + + $allowed = HTMLPurifier_Config::getAllowedDirectivesForForm($allowed, $config->def); + $all = array(); + foreach ($allowed as $key) { + list($ns, $directive) = $key; + $all[$ns][$directive] = $config->get($ns . '.' . $directive); + } + + $ret = ''; + $ret .= $this->start('table', array('class' => 'hp-config')); + $ret .= $this->start('thead'); + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Directive', array('class' => 'hp-directive')); + $ret .= $this->element('th', 'Value', array('class' => 'hp-value')); + $ret .= $this->end('tr'); + $ret .= $this->end('thead'); + foreach ($all as $ns => $directives) { + $ret .= $this->renderNamespace($ns, $directives); + } + if ($render_controls) { + $ret .= $this->start('tbody'); + $ret .= $this->start('tr'); + $ret .= $this->start('td', array('colspan' => 2, 'class' => 'controls')); + $ret .= $this->elementEmpty('input', array('type' => 'submit', 'value' => 'Submit')); + $ret .= '[Reset]'; + $ret .= $this->end('td'); + $ret .= $this->end('tr'); + $ret .= $this->end('tbody'); + } + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders a single namespace + * @param $ns String namespace name + * @param array $directives array of directives to values + * @return string + */ + protected function renderNamespace($ns, $directives) + { + $ret = ''; + $ret .= $this->start('tbody', array('class' => 'namespace')); + $ret .= $this->start('tr'); + $ret .= $this->element('th', $ns, array('colspan' => 2)); + $ret .= $this->end('tr'); + $ret .= $this->end('tbody'); + $ret .= $this->start('tbody'); + foreach ($directives as $directive => $value) { + $ret .= $this->start('tr'); + $ret .= $this->start('th'); + if ($this->docURL) { + $url = str_replace('%s', urlencode("$ns.$directive"), $this->docURL); + $ret .= $this->start('a', array('href' => $url)); + } + $attr = array('for' => "{$this->name}:$ns.$directive"); + + // crop directive name if it's too long + if (!$this->compress || (strlen($directive) < $this->compress)) { + $directive_disp = $directive; + } else { + $directive_disp = substr($directive, 0, $this->compress - 2) . '...'; + $attr['title'] = $directive; + } + + $ret .= $this->element( + 'label', + $directive_disp, + // component printers must create an element with this id + $attr + ); + if ($this->docURL) { + $ret .= $this->end('a'); + } + $ret .= $this->end('th'); + + $ret .= $this->start('td'); + $def = $this->config->def->info["$ns.$directive"]; + if (is_int($def)) { + $allow_null = $def < 0; + $type = abs($def); + } else { + $type = $def->type; + $allow_null = isset($def->allow_null); + } + if (!isset($this->fields[$type])) { + $type = 0; + } // default + $type_obj = $this->fields[$type]; + if ($allow_null) { + $type_obj = new HTMLPurifier_Printer_ConfigForm_NullDecorator($type_obj); + } + $ret .= $type_obj->render($ns, $directive, $value, $this->name, array($this->genConfig, $this->config)); + $ret .= $this->end('td'); + $ret .= $this->end('tr'); + } + $ret .= $this->end('tbody'); + return $ret; + } + +} + +/** + * Printer decorator for directives that accept null + */ +class HTMLPurifier_Printer_ConfigForm_NullDecorator extends HTMLPurifier_Printer +{ + /** + * Printer being decorated + * @type HTMLPurifier_Printer + */ + protected $obj; + + /** + * @param HTMLPurifier_Printer $obj Printer to decorate + */ + public function __construct($obj) + { + parent::__construct(); + $this->obj = $obj; + } + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + $this->prepareGenerator($gen_config); + + $ret = ''; + $ret .= $this->start('label', array('for' => "$name:Null_$ns.$directive")); + $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose')); + $ret .= $this->text(' Null/Disabled'); + $ret .= $this->end('label'); + $attr = array( + 'type' => 'checkbox', + 'value' => '1', + 'class' => 'null-toggle', + 'name' => "$name" . "[Null_$ns.$directive]", + 'id' => "$name:Null_$ns.$directive", + 'onclick' => "toggleWriteability('$name:$ns.$directive',checked)" // INLINE JAVASCRIPT!!!! + ); + if ($this->obj instanceof HTMLPurifier_Printer_ConfigForm_bool) { + // modify inline javascript slightly + $attr['onclick'] = + "toggleWriteability('$name:Yes_$ns.$directive',checked);" . + "toggleWriteability('$name:No_$ns.$directive',checked)"; + } + if ($value === null) { + $attr['checked'] = 'checked'; + } + $ret .= $this->elementEmpty('input', $attr); + $ret .= $this->text(' or '); + $ret .= $this->elementEmpty('br'); + $ret .= $this->obj->render($ns, $directive, $value, $name, array($gen_config, $config)); + return $ret; + } +} + +/** + * Swiss-army knife configuration form field printer + */ +class HTMLPurifier_Printer_ConfigForm_default extends HTMLPurifier_Printer +{ + /** + * @type int + */ + public $cols = 18; + + /** + * @type int + */ + public $rows = 5; + + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + $this->prepareGenerator($gen_config); + // this should probably be split up a little + $ret = ''; + $def = $config->def->info["$ns.$directive"]; + if (is_int($def)) { + $type = abs($def); + } else { + $type = $def->type; + } + if (is_array($value)) { + switch ($type) { + case HTMLPurifier_VarParser::LOOKUP: + $array = $value; + $value = array(); + foreach ($array as $val => $b) { + $value[] = $val; + } + //TODO does this need a break? + case HTMLPurifier_VarParser::ALIST: + $value = implode(PHP_EOL, $value); + break; + case HTMLPurifier_VarParser::HASH: + $nvalue = ''; + foreach ($value as $i => $v) { + $nvalue .= "$i:$v" . PHP_EOL; + } + $value = $nvalue; + break; + default: + $value = ''; + } + } + if ($type === HTMLPurifier_VarParser::MIXED) { + return 'Not supported'; + $value = serialize($value); + } + $attr = array( + 'name' => "$name" . "[$ns.$directive]", + 'id' => "$name:$ns.$directive" + ); + if ($value === null) { + $attr['disabled'] = 'disabled'; + } + if (isset($def->allowed)) { + $ret .= $this->start('select', $attr); + foreach ($def->allowed as $val => $b) { + $attr = array(); + if ($value == $val) { + $attr['selected'] = 'selected'; + } + $ret .= $this->element('option', $val, $attr); + } + $ret .= $this->end('select'); + } elseif ($type === HTMLPurifier_VarParser::TEXT || + $type === HTMLPurifier_VarParser::ITEXT || + $type === HTMLPurifier_VarParser::ALIST || + $type === HTMLPurifier_VarParser::HASH || + $type === HTMLPurifier_VarParser::LOOKUP) { + $attr['cols'] = $this->cols; + $attr['rows'] = $this->rows; + $ret .= $this->start('textarea', $attr); + $ret .= $this->text($value); + $ret .= $this->end('textarea'); + } else { + $attr['value'] = $value; + $attr['type'] = 'text'; + $ret .= $this->elementEmpty('input', $attr); + } + return $ret; + } +} + +/** + * Bool form field printer + */ +class HTMLPurifier_Printer_ConfigForm_bool extends HTMLPurifier_Printer +{ + /** + * @param string $ns + * @param string $directive + * @param string $value + * @param string $name + * @param HTMLPurifier_Config|array $config + * @return string + */ + public function render($ns, $directive, $value, $name, $config) + { + if (is_array($config) && isset($config[0])) { + $gen_config = $config[0]; + $config = $config[1]; + } else { + $gen_config = $config; + } + $this->prepareGenerator($gen_config); + $ret = ''; + $ret .= $this->start('div', array('id' => "$name:$ns.$directive")); + + $ret .= $this->start('label', array('for' => "$name:Yes_$ns.$directive")); + $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose')); + $ret .= $this->text(' Yes'); + $ret .= $this->end('label'); + + $attr = array( + 'type' => 'radio', + 'name' => "$name" . "[$ns.$directive]", + 'id' => "$name:Yes_$ns.$directive", + 'value' => '1' + ); + if ($value === true) { + $attr['checked'] = 'checked'; + } + if ($value === null) { + $attr['disabled'] = 'disabled'; + } + $ret .= $this->elementEmpty('input', $attr); + + $ret .= $this->start('label', array('for' => "$name:No_$ns.$directive")); + $ret .= $this->element('span', "$ns.$directive:", array('class' => 'verbose')); + $ret .= $this->text(' No'); + $ret .= $this->end('label'); + + $attr = array( + 'type' => 'radio', + 'name' => "$name" . "[$ns.$directive]", + 'id' => "$name:No_$ns.$directive", + 'value' => '0' + ); + if ($value === false) { + $attr['checked'] = 'checked'; + } + if ($value === null) { + $attr['disabled'] = 'disabled'; + } + $ret .= $this->elementEmpty('input', $attr); + + $ret .= $this->end('div'); + + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/HTMLDefinition.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/HTMLDefinition.php new file mode 100644 index 0000000000..5f2f2f8a7c --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Printer/HTMLDefinition.php @@ -0,0 +1,324 @@ +config =& $config; + + $this->def = $config->getHTMLDefinition(); + + $ret .= $this->start('div', array('class' => 'HTMLPurifier_Printer')); + + $ret .= $this->renderDoctype(); + $ret .= $this->renderEnvironment(); + $ret .= $this->renderContentSets(); + $ret .= $this->renderInfo(); + + $ret .= $this->end('div'); + + return $ret; + } + + /** + * Renders the Doctype table + * @return string + */ + protected function renderDoctype() + { + $doctype = $this->def->doctype; + $ret = ''; + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Doctype'); + $ret .= $this->row('Name', $doctype->name); + $ret .= $this->row('XML', $doctype->xml ? 'Yes' : 'No'); + $ret .= $this->row('Default Modules', implode($doctype->modules, ', ')); + $ret .= $this->row('Default Tidy Modules', implode($doctype->tidyModules, ', ')); + $ret .= $this->end('table'); + return $ret; + } + + + /** + * Renders environment table, which is miscellaneous info + * @return string + */ + protected function renderEnvironment() + { + $def = $this->def; + + $ret = ''; + + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Environment'); + + $ret .= $this->row('Parent of fragment', $def->info_parent); + $ret .= $this->renderChildren($def->info_parent_def->child); + $ret .= $this->row('Block wrap name', $def->info_block_wrapper); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Global attributes'); + $ret .= $this->element('td', $this->listifyAttr($def->info_global_attr), null, 0); + $ret .= $this->end('tr'); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Tag transforms'); + $list = array(); + foreach ($def->info_tag_transform as $old => $new) { + $new = $this->getClass($new, 'TagTransform_'); + $list[] = "<$old> with $new"; + } + $ret .= $this->element('td', $this->listify($list)); + $ret .= $this->end('tr'); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Pre-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_pre)); + $ret .= $this->end('tr'); + + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Post-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->info_attr_transform_post)); + $ret .= $this->end('tr'); + + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders the Content Sets table + * @return string + */ + protected function renderContentSets() + { + $ret = ''; + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Content Sets'); + foreach ($this->def->info_content_sets as $name => $lookup) { + $ret .= $this->heavyHeader($name); + $ret .= $this->start('tr'); + $ret .= $this->element('td', $this->listifyTagLookup($lookup)); + $ret .= $this->end('tr'); + } + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders the Elements ($info) table + * @return string + */ + protected function renderInfo() + { + $ret = ''; + $ret .= $this->start('table'); + $ret .= $this->element('caption', 'Elements ($info)'); + ksort($this->def->info); + $ret .= $this->heavyHeader('Allowed tags', 2); + $ret .= $this->start('tr'); + $ret .= $this->element('td', $this->listifyTagLookup($this->def->info), array('colspan' => 2)); + $ret .= $this->end('tr'); + foreach ($this->def->info as $name => $def) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', "<$name>", array('class' => 'heavy', 'colspan' => 2)); + $ret .= $this->end('tr'); + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Inline content'); + $ret .= $this->element('td', $def->descendants_are_inline ? 'Yes' : 'No'); + $ret .= $this->end('tr'); + if (!empty($def->excludes)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Excludes'); + $ret .= $this->element('td', $this->listifyTagLookup($def->excludes)); + $ret .= $this->end('tr'); + } + if (!empty($def->attr_transform_pre)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Pre-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_pre)); + $ret .= $this->end('tr'); + } + if (!empty($def->attr_transform_post)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Post-AttrTransform'); + $ret .= $this->element('td', $this->listifyObjectList($def->attr_transform_post)); + $ret .= $this->end('tr'); + } + if (!empty($def->auto_close)) { + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Auto closed by'); + $ret .= $this->element('td', $this->listifyTagLookup($def->auto_close)); + $ret .= $this->end('tr'); + } + $ret .= $this->start('tr'); + $ret .= $this->element('th', 'Allowed attributes'); + $ret .= $this->element('td', $this->listifyAttr($def->attr), array(), 0); + $ret .= $this->end('tr'); + + if (!empty($def->required_attr)) { + $ret .= $this->row('Required attributes', $this->listify($def->required_attr)); + } + + $ret .= $this->renderChildren($def->child); + } + $ret .= $this->end('table'); + return $ret; + } + + /** + * Renders a row describing the allowed children of an element + * @param HTMLPurifier_ChildDef $def HTMLPurifier_ChildDef of pertinent element + * @return string + */ + protected function renderChildren($def) + { + $context = new HTMLPurifier_Context(); + $ret = ''; + $ret .= $this->start('tr'); + $elements = array(); + $attr = array(); + if (isset($def->elements)) { + if ($def->type == 'strictblockquote') { + $def->validateChildren(array(), $this->config, $context); + } + $elements = $def->elements; + } + if ($def->type == 'chameleon') { + $attr['rowspan'] = 2; + } elseif ($def->type == 'empty') { + $elements = array(); + } elseif ($def->type == 'table') { + $elements = array_flip( + array( + 'col', + 'caption', + 'colgroup', + 'thead', + 'tfoot', + 'tbody', + 'tr' + ) + ); + } + $ret .= $this->element('th', 'Allowed children', $attr); + + if ($def->type == 'chameleon') { + + $ret .= $this->element( + 'td', + 'Block: ' . + $this->escape($this->listifyTagLookup($def->block->elements)), + null, + 0 + ); + $ret .= $this->end('tr'); + $ret .= $this->start('tr'); + $ret .= $this->element( + 'td', + 'Inline: ' . + $this->escape($this->listifyTagLookup($def->inline->elements)), + null, + 0 + ); + + } elseif ($def->type == 'custom') { + + $ret .= $this->element( + 'td', + '' . ucfirst($def->type) . ': ' . + $def->dtd_regex + ); + + } else { + $ret .= $this->element( + 'td', + '' . ucfirst($def->type) . ': ' . + $this->escape($this->listifyTagLookup($elements)), + null, + 0 + ); + } + $ret .= $this->end('tr'); + return $ret; + } + + /** + * Listifies a tag lookup table. + * @param array $array Tag lookup array in form of array('tagname' => true) + * @return string + */ + protected function listifyTagLookup($array) + { + ksort($array); + $list = array(); + foreach ($array as $name => $discard) { + if ($name !== '#PCDATA' && !isset($this->def->info[$name])) { + continue; + } + $list[] = $name; + } + return $this->listify($list); + } + + /** + * Listifies a list of objects by retrieving class names and internal state + * @param array $array List of objects + * @return string + * @todo Also add information about internal state + */ + protected function listifyObjectList($array) + { + ksort($array); + $list = array(); + foreach ($array as $obj) { + $list[] = $this->getClass($obj, 'AttrTransform_'); + } + return $this->listify($list); + } + + /** + * Listifies a hash of attributes to AttrDef classes + * @param array $array Array hash in form of array('attrname' => HTMLPurifier_AttrDef) + * @return string + */ + protected function listifyAttr($array) + { + ksort($array); + $list = array(); + foreach ($array as $name => $obj) { + if ($obj === false) { + continue; + } + $list[] = "$name = " . $this->getClass($obj, 'AttrDef_') . ''; + } + return $this->listify($list); + } + + /** + * Creates a heavy header row + * @param string $text + * @param int $num + * @return string + */ + protected function heavyHeader($text, $num = 1) + { + $ret = ''; + $ret .= $this->start('tr'); + $ret .= $this->element('th', $text, array('colspan' => $num, 'class' => 'heavy')); + $ret .= $this->end('tr'); + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PropertyList.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PropertyList.php new file mode 100644 index 0000000000..189348fd9e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PropertyList.php @@ -0,0 +1,122 @@ +parent = $parent; + } + + /** + * Recursively retrieves the value for a key + * @param string $name + * @throws HTMLPurifier_Exception + */ + public function get($name) + { + if ($this->has($name)) { + return $this->data[$name]; + } + // possible performance bottleneck, convert to iterative if necessary + if ($this->parent) { + return $this->parent->get($name); + } + throw new HTMLPurifier_Exception("Key '$name' not found"); + } + + /** + * Sets the value of a key, for this plist + * @param string $name + * @param mixed $value + */ + public function set($name, $value) + { + $this->data[$name] = $value; + } + + /** + * Returns true if a given key exists + * @param string $name + * @return bool + */ + public function has($name) + { + return array_key_exists($name, $this->data); + } + + /** + * Resets a value to the value of it's parent, usually the default. If + * no value is specified, the entire plist is reset. + * @param string $name + */ + public function reset($name = null) + { + if ($name == null) { + $this->data = array(); + } else { + unset($this->data[$name]); + } + } + + /** + * Squashes this property list and all of its property lists into a single + * array, and returns the array. This value is cached by default. + * @param bool $force If true, ignores the cache and regenerates the array. + * @return array + */ + public function squash($force = false) + { + if ($this->cache !== null && !$force) { + return $this->cache; + } + if ($this->parent) { + return $this->cache = array_merge($this->parent->squash($force), $this->data); + } else { + return $this->cache = $this->data; + } + } + + /** + * Returns the parent plist. + * @return HTMLPurifier_PropertyList + */ + public function getParent() + { + return $this->parent; + } + + /** + * Sets the parent plist. + * @param HTMLPurifier_PropertyList $plist Parent plist + */ + public function setParent($plist) + { + $this->parent = $plist; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PropertyListIterator.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PropertyListIterator.php new file mode 100644 index 0000000000..15b330ea30 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/PropertyListIterator.php @@ -0,0 +1,42 @@ +l = strlen($filter); + $this->filter = $filter; + } + + /** + * @return bool + */ + public function accept() + { + $key = $this->getInnerIterator()->key(); + if (strncmp($key, $this->filter, $this->l) !== 0) { + return false; + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Queue.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Queue.php new file mode 100644 index 0000000000..f58db9042a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Queue.php @@ -0,0 +1,56 @@ +input = $input; + $this->output = array(); + } + + /** + * Shifts an element off the front of the queue. + */ + public function shift() { + if (empty($this->output)) { + $this->output = array_reverse($this->input); + $this->input = array(); + } + if (empty($this->output)) { + return NULL; + } + return array_pop($this->output); + } + + /** + * Pushes an element onto the front of the queue. + */ + public function push($x) { + array_push($this->input, $x); + } + + /** + * Checks if it's empty. + */ + public function isEmpty() { + return empty($this->input) && empty($this->output); + } +} diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy.php new file mode 100644 index 0000000000..e1ff3b72df --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy.php @@ -0,0 +1,26 @@ +strategies as $strategy) { + $tokens = $strategy->execute($tokens, $config, $context); + } + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/Core.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/Core.php new file mode 100644 index 0000000000..4414c17d6e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/Core.php @@ -0,0 +1,17 @@ +strategies[] = new HTMLPurifier_Strategy_RemoveForeignElements(); + $this->strategies[] = new HTMLPurifier_Strategy_MakeWellFormed(); + $this->strategies[] = new HTMLPurifier_Strategy_FixNesting(); + $this->strategies[] = new HTMLPurifier_Strategy_ValidateAttributes(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/FixNesting.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/FixNesting.php new file mode 100644 index 0000000000..6fa673db9a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/FixNesting.php @@ -0,0 +1,181 @@ +getHTMLDefinition(); + + $excludes_enabled = !$config->get('Core.DisableExcludes'); + + // setup the context variable 'IsInline', for chameleon processing + // is 'false' when we are not inline, 'true' when it must always + // be inline, and an integer when it is inline for a certain + // branch of the document tree + $is_inline = $definition->info_parent_def->descendants_are_inline; + $context->register('IsInline', $is_inline); + + // setup error collector + $e =& $context->get('ErrorCollector', true); + + //####################################################################// + // Loop initialization + + // stack that contains all elements that are excluded + // it is organized by parent elements, similar to $stack, + // but it is only populated when an element with exclusions is + // processed, i.e. there won't be empty exclusions. + $exclude_stack = array($definition->info_parent_def->excludes); + + // variable that contains the start token while we are processing + // nodes. This enables error reporting to do its job + $node = $top_node; + // dummy token + list($token, $d) = $node->toTokenPair(); + $context->register('CurrentNode', $node); + $context->register('CurrentToken', $token); + + //####################################################################// + // Loop + + // We need to implement a post-order traversal iteratively, to + // avoid running into stack space limits. This is pretty tricky + // to reason about, so we just manually stack-ify the recursive + // variant: + // + // function f($node) { + // foreach ($node->children as $child) { + // f($child); + // } + // validate($node); + // } + // + // Thus, we will represent a stack frame as array($node, + // $is_inline, stack of children) + // e.g. array_reverse($node->children) - already processed + // children. + + $parent_def = $definition->info_parent_def; + $stack = array( + array($top_node, + $parent_def->descendants_are_inline, + $parent_def->excludes, // exclusions + 0) + ); + + while (!empty($stack)) { + list($node, $is_inline, $excludes, $ix) = array_pop($stack); + // recursive call + $go = false; + $def = empty($stack) ? $definition->info_parent_def : $definition->info[$node->name]; + while (isset($node->children[$ix])) { + $child = $node->children[$ix++]; + if ($child instanceof HTMLPurifier_Node_Element) { + $go = true; + $stack[] = array($node, $is_inline, $excludes, $ix); + $stack[] = array($child, + // ToDo: I don't think it matters if it's def or + // child_def, but double check this... + $is_inline || $def->descendants_are_inline, + empty($def->excludes) ? $excludes + : array_merge($excludes, $def->excludes), + 0); + break; + } + }; + if ($go) continue; + list($token, $d) = $node->toTokenPair(); + // base case + if ($excludes_enabled && isset($excludes[$node->name])) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node excluded'); + } else { + // XXX I suppose it would be slightly more efficient to + // avoid the allocation here and have children + // strategies handle it + $children = array(); + foreach ($node->children as $child) { + if (!$child->dead) $children[] = $child; + } + $result = $def->child->validateChildren($children, $config, $context); + if ($result === true) { + // nop + $node->children = $children; + } elseif ($result === false) { + $node->dead = true; + if ($e) $e->send(E_ERROR, 'Strategy_FixNesting: Node removed'); + } else { + $node->children = $result; + if ($e) { + // XXX This will miss mutations of internal nodes. Perhaps defer to the child validators + if (empty($result) && !empty($children)) { + $e->send(E_ERROR, 'Strategy_FixNesting: Node contents removed'); + } else if ($result != $children) { + $e->send(E_WARNING, 'Strategy_FixNesting: Node reorganized'); + } + } + } + } + } + + //####################################################################// + // Post-processing + + // remove context variables + $context->destroy('IsInline'); + $context->destroy('CurrentNode'); + $context->destroy('CurrentToken'); + + //####################################################################// + // Return + + return HTMLPurifier_Arborize::flatten($node, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/MakeWellFormed.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/MakeWellFormed.php new file mode 100644 index 0000000000..e389e00116 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/MakeWellFormed.php @@ -0,0 +1,600 @@ +getHTMLDefinition(); + + // local variables + $generator = new HTMLPurifier_Generator($config, $context); + $escape_invalid_tags = $config->get('Core.EscapeInvalidTags'); + // used for autoclose early abortion + $global_parent_allowed_elements = $definition->info_parent_def->child->getAllowedElements($config); + $e = $context->get('ErrorCollector', true); + $i = false; // injector index + list($zipper, $token) = HTMLPurifier_Zipper::fromArray($tokens); + if ($token === NULL) { + return array(); + } + $reprocess = false; // whether or not to reprocess the same token + $stack = array(); + + // member variables + $this->stack =& $stack; + $this->tokens =& $tokens; + $this->token =& $token; + $this->zipper =& $zipper; + $this->config = $config; + $this->context = $context; + + // context variables + $context->register('CurrentNesting', $stack); + $context->register('InputZipper', $zipper); + $context->register('CurrentToken', $token); + + // -- begin INJECTOR -- + + $this->injectors = array(); + + $injectors = $config->getBatch('AutoFormat'); + $def_injectors = $definition->info_injector; + $custom_injectors = $injectors['Custom']; + unset($injectors['Custom']); // special case + foreach ($injectors as $injector => $b) { + // XXX: Fix with a legitimate lookup table of enabled filters + if (strpos($injector, '.') !== false) { + continue; + } + $injector = "HTMLPurifier_Injector_$injector"; + if (!$b) { + continue; + } + $this->injectors[] = new $injector; + } + foreach ($def_injectors as $injector) { + // assumed to be objects + $this->injectors[] = $injector; + } + foreach ($custom_injectors as $injector) { + if (!$injector) { + continue; + } + if (is_string($injector)) { + $injector = "HTMLPurifier_Injector_$injector"; + $injector = new $injector; + } + $this->injectors[] = $injector; + } + + // give the injectors references to the definition and context + // variables for performance reasons + foreach ($this->injectors as $ix => $injector) { + $error = $injector->prepare($config, $context); + if (!$error) { + continue; + } + array_splice($this->injectors, $ix, 1); // rm the injector + trigger_error("Cannot enable {$injector->name} injector because $error is not allowed", E_USER_WARNING); + } + + // -- end INJECTOR -- + + // a note on reprocessing: + // In order to reduce code duplication, whenever some code needs + // to make HTML changes in order to make things "correct", the + // new HTML gets sent through the purifier, regardless of its + // status. This means that if we add a start token, because it + // was totally necessary, we don't have to update nesting; we just + // punt ($reprocess = true; continue;) and it does that for us. + + // isset is in loop because $tokens size changes during loop exec + for (;; + // only increment if we don't need to reprocess + $reprocess ? $reprocess = false : $token = $zipper->next($token)) { + + // check for a rewind + if (is_int($i)) { + // possibility: disable rewinding if the current token has a + // rewind set on it already. This would offer protection from + // infinite loop, but might hinder some advanced rewinding. + $rewind_offset = $this->injectors[$i]->getRewindOffset(); + if (is_int($rewind_offset)) { + for ($j = 0; $j < $rewind_offset; $j++) { + if (empty($zipper->front)) break; + $token = $zipper->prev($token); + // indicate that other injectors should not process this token, + // but we need to reprocess it + unset($token->skip[$i]); + $token->rewind = $i; + if ($token instanceof HTMLPurifier_Token_Start) { + array_pop($this->stack); + } elseif ($token instanceof HTMLPurifier_Token_End) { + $this->stack[] = $token->start; + } + } + } + $i = false; + } + + // handle case of document end + if ($token === NULL) { + // kill processing if stack is empty + if (empty($this->stack)) { + break; + } + + // peek + $top_nesting = array_pop($this->stack); + $this->stack[] = $top_nesting; + + // send error [TagClosedSuppress] + if ($e && !isset($top_nesting->armor['MakeWellFormed_TagClosedError'])) { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by document end', $top_nesting); + } + + // append, don't splice, since this is the end + $token = new HTMLPurifier_Token_End($top_nesting->name); + + // punt! + $reprocess = true; + continue; + } + + //echo '
'; printZipper($zipper, $token);//printTokens($this->stack); + //flush(); + + // quick-check: if it's not a tag, no need to process + if (empty($token->is_tag)) { + if ($token instanceof HTMLPurifier_Token_Text) { + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + // XXX fuckup + $r = $token; + $injector->handleText($r); + $token = $this->processToken($r, $i); + $reprocess = true; + break; + } + } + // another possibility is a comment + continue; + } + + if (isset($definition->info[$token->name])) { + $type = $definition->info[$token->name]->child->type; + } else { + $type = false; // Type is unknown, treat accordingly + } + + // quick tag checks: anything that's *not* an end tag + $ok = false; + if ($type === 'empty' && $token instanceof HTMLPurifier_Token_Start) { + // claims to be a start tag but is empty + $token = new HTMLPurifier_Token_Empty( + $token->name, + $token->attr, + $token->line, + $token->col, + $token->armor + ); + $ok = true; + } elseif ($type && $type !== 'empty' && $token instanceof HTMLPurifier_Token_Empty) { + // claims to be empty but really is a start tag + // NB: this assignment is required + $old_token = $token; + $token = new HTMLPurifier_Token_End($token->name); + $token = $this->insertBefore( + new HTMLPurifier_Token_Start($old_token->name, $old_token->attr, $old_token->line, $old_token->col, $old_token->armor) + ); + // punt (since we had to modify the input stream in a non-trivial way) + $reprocess = true; + continue; + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + // real empty token + $ok = true; + } elseif ($token instanceof HTMLPurifier_Token_Start) { + // start tag + + // ...unless they also have to close their parent + if (!empty($this->stack)) { + + // Performance note: you might think that it's rather + // inefficient, recalculating the autoclose information + // for every tag that a token closes (since when we + // do an autoclose, we push a new token into the + // stream and then /process/ that, before + // re-processing this token.) But this is + // necessary, because an injector can make an + // arbitrary transformations to the autoclosing + // tokens we introduce, so things may have changed + // in the meantime. Also, doing the inefficient thing is + // "easy" to reason about (for certain perverse definitions + // of "easy") + + $parent = array_pop($this->stack); + $this->stack[] = $parent; + + $parent_def = null; + $parent_elements = null; + $autoclose = false; + if (isset($definition->info[$parent->name])) { + $parent_def = $definition->info[$parent->name]; + $parent_elements = $parent_def->child->getAllowedElements($config); + $autoclose = !isset($parent_elements[$token->name]); + } + + if ($autoclose && $definition->info[$token->name]->wrap) { + // Check if an element can be wrapped by another + // element to make it valid in a context (for + // example,
needs a
in between) + $wrapname = $definition->info[$token->name]->wrap; + $wrapdef = $definition->info[$wrapname]; + $elements = $wrapdef->child->getAllowedElements($config); + if (isset($elements[$token->name]) && isset($parent_elements[$wrapname])) { + $newtoken = new HTMLPurifier_Token_Start($wrapname); + $token = $this->insertBefore($newtoken); + $reprocess = true; + continue; + } + } + + $carryover = false; + if ($autoclose && $parent_def->formatting) { + $carryover = true; + } + + if ($autoclose) { + // check if this autoclose is doomed to fail + // (this rechecks $parent, which his harmless) + $autoclose_ok = isset($global_parent_allowed_elements[$token->name]); + if (!$autoclose_ok) { + foreach ($this->stack as $ancestor) { + $elements = $definition->info[$ancestor->name]->child->getAllowedElements($config); + if (isset($elements[$token->name])) { + $autoclose_ok = true; + break; + } + if ($definition->info[$token->name]->wrap) { + $wrapname = $definition->info[$token->name]->wrap; + $wrapdef = $definition->info[$wrapname]; + $wrap_elements = $wrapdef->child->getAllowedElements($config); + if (isset($wrap_elements[$token->name]) && isset($elements[$wrapname])) { + $autoclose_ok = true; + break; + } + } + } + } + if ($autoclose_ok) { + // errors need to be updated + $new_token = new HTMLPurifier_Token_End($parent->name); + $new_token->start = $parent; + // [TagClosedSuppress] + if ($e && !isset($parent->armor['MakeWellFormed_TagClosedError'])) { + if (!$carryover) { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag auto closed', $parent); + } else { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag carryover', $parent); + } + } + if ($carryover) { + $element = clone $parent; + // [TagClosedAuto] + $element->armor['MakeWellFormed_TagClosedError'] = true; + $element->carryover = true; + $token = $this->processToken(array($new_token, $token, $element)); + } else { + $token = $this->insertBefore($new_token); + } + } else { + $token = $this->remove(); + } + $reprocess = true; + continue; + } + + } + $ok = true; + } + + if ($ok) { + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + $r = $token; + $injector->handleElement($r); + $token = $this->processToken($r, $i); + $reprocess = true; + break; + } + if (!$reprocess) { + // ah, nothing interesting happened; do normal processing + if ($token instanceof HTMLPurifier_Token_Start) { + $this->stack[] = $token; + } elseif ($token instanceof HTMLPurifier_Token_End) { + throw new HTMLPurifier_Exception( + 'Improper handling of end tag in start code; possible error in MakeWellFormed' + ); + } + } + continue; + } + + // sanity check: we should be dealing with a closing tag + if (!$token instanceof HTMLPurifier_Token_End) { + throw new HTMLPurifier_Exception('Unaccounted for tag token in input stream, bug in HTML Purifier'); + } + + // make sure that we have something open + if (empty($this->stack)) { + if ($escape_invalid_tags) { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); + } else { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Unnecessary end tag removed'); + } + $token = $this->remove(); + } + $reprocess = true; + continue; + } + + // first, check for the simplest case: everything closes neatly. + // Eventually, everything passes through here; if there are problems + // we modify the input stream accordingly and then punt, so that + // the tokens get processed again. + $current_parent = array_pop($this->stack); + if ($current_parent->name == $token->name) { + $token->start = $current_parent; + foreach ($this->injectors as $i => $injector) { + if (isset($token->skip[$i])) { + continue; + } + if ($token->rewind !== null && $token->rewind !== $i) { + continue; + } + $r = $token; + $injector->handleEnd($r); + $token = $this->processToken($r, $i); + $this->stack[] = $current_parent; + $reprocess = true; + break; + } + continue; + } + + // okay, so we're trying to close the wrong tag + + // undo the pop previous pop + $this->stack[] = $current_parent; + + // scroll back the entire nest, trying to find our tag. + // (feature could be to specify how far you'd like to go) + $size = count($this->stack); + // -2 because -1 is the last element, but we already checked that + $skipped_tags = false; + for ($j = $size - 2; $j >= 0; $j--) { + if ($this->stack[$j]->name == $token->name) { + $skipped_tags = array_slice($this->stack, $j); + break; + } + } + + // we didn't find the tag, so remove + if ($skipped_tags === false) { + if ($escape_invalid_tags) { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag to text'); + } + $token = new HTMLPurifier_Token_Text($generator->generateFromToken($token)); + } else { + if ($e) { + $e->send(E_WARNING, 'Strategy_MakeWellFormed: Stray end tag removed'); + } + $token = $this->remove(); + } + $reprocess = true; + continue; + } + + // do errors, in REVERSE $j order: a,b,c with + $c = count($skipped_tags); + if ($e) { + for ($j = $c - 1; $j > 0; $j--) { + // notice we exclude $j == 0, i.e. the current ending tag, from + // the errors... [TagClosedSuppress] + if (!isset($skipped_tags[$j]->armor['MakeWellFormed_TagClosedError'])) { + $e->send(E_NOTICE, 'Strategy_MakeWellFormed: Tag closed by element end', $skipped_tags[$j]); + } + } + } + + // insert tags, in FORWARD $j order: c,b,a with + $replace = array($token); + for ($j = 1; $j < $c; $j++) { + // ...as well as from the insertions + $new_token = new HTMLPurifier_Token_End($skipped_tags[$j]->name); + $new_token->start = $skipped_tags[$j]; + array_unshift($replace, $new_token); + if (isset($definition->info[$new_token->name]) && $definition->info[$new_token->name]->formatting) { + // [TagClosedAuto] + $element = clone $skipped_tags[$j]; + $element->carryover = true; + $element->armor['MakeWellFormed_TagClosedError'] = true; + $replace[] = $element; + } + } + $token = $this->processToken($replace); + $reprocess = true; + continue; + } + + $context->destroy('CurrentToken'); + $context->destroy('CurrentNesting'); + $context->destroy('InputZipper'); + + unset($this->injectors, $this->stack, $this->tokens); + return $zipper->toArray($token); + } + + /** + * Processes arbitrary token values for complicated substitution patterns. + * In general: + * + * If $token is an array, it is a list of tokens to substitute for the + * current token. These tokens then get individually processed. If there + * is a leading integer in the list, that integer determines how many + * tokens from the stream should be removed. + * + * If $token is a regular token, it is swapped with the current token. + * + * If $token is false, the current token is deleted. + * + * If $token is an integer, that number of tokens (with the first token + * being the current one) will be deleted. + * + * @param HTMLPurifier_Token|array|int|bool $token Token substitution value + * @param HTMLPurifier_Injector|int $injector Injector that performed the substitution; default is if + * this is not an injector related operation. + * @throws HTMLPurifier_Exception + */ + protected function processToken($token, $injector = -1) + { + // normalize forms of token + if (is_object($token)) { + $token = array(1, $token); + } + if (is_int($token)) { + $token = array($token); + } + if ($token === false) { + $token = array(1); + } + if (!is_array($token)) { + throw new HTMLPurifier_Exception('Invalid token type from injector'); + } + if (!is_int($token[0])) { + array_unshift($token, 1); + } + if ($token[0] === 0) { + throw new HTMLPurifier_Exception('Deleting zero tokens is not valid'); + } + + // $token is now an array with the following form: + // array(number nodes to delete, new node 1, new node 2, ...) + + $delete = array_shift($token); + list($old, $r) = $this->zipper->splice($this->token, $delete, $token); + + if ($injector > -1) { + // determine appropriate skips + $oldskip = isset($old[0]) ? $old[0]->skip : array(); + foreach ($token as $object) { + $object->skip = $oldskip; + $object->skip[$injector] = true; + } + } + + return $r; + + } + + /** + * Inserts a token before the current token. Cursor now points to + * this token. You must reprocess after this. + * @param HTMLPurifier_Token $token + */ + private function insertBefore($token) + { + // NB not $this->zipper->insertBefore(), due to positioning + // differences + $splice = $this->zipper->splice($this->token, 0, array($token)); + + return $splice[1]; + } + + /** + * Removes current token. Cursor now points to new token occupying previously + * occupied space. You must reprocess after this. + */ + private function remove() + { + return $this->zipper->delete(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/RemoveForeignElements.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/RemoveForeignElements.php new file mode 100644 index 0000000000..1a8149eccb --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/RemoveForeignElements.php @@ -0,0 +1,207 @@ +getHTMLDefinition(); + $generator = new HTMLPurifier_Generator($config, $context); + $result = array(); + + $escape_invalid_tags = $config->get('Core.EscapeInvalidTags'); + $remove_invalid_img = $config->get('Core.RemoveInvalidImg'); + + // currently only used to determine if comments should be kept + $trusted = $config->get('HTML.Trusted'); + $comment_lookup = $config->get('HTML.AllowedComments'); + $comment_regexp = $config->get('HTML.AllowedCommentsRegexp'); + $check_comments = $comment_lookup !== array() || $comment_regexp !== null; + + $remove_script_contents = $config->get('Core.RemoveScriptContents'); + $hidden_elements = $config->get('Core.HiddenElements'); + + // remove script contents compatibility + if ($remove_script_contents === true) { + $hidden_elements['script'] = true; + } elseif ($remove_script_contents === false && isset($hidden_elements['script'])) { + unset($hidden_elements['script']); + } + + $attr_validator = new HTMLPurifier_AttrValidator(); + + // removes tokens until it reaches a closing tag with its value + $remove_until = false; + + // converts comments into text tokens when this is equal to a tag name + $textify_comments = false; + + $token = false; + $context->register('CurrentToken', $token); + + $e = false; + if ($config->get('Core.CollectErrors')) { + $e =& $context->get('ErrorCollector'); + } + + foreach ($tokens as $token) { + if ($remove_until) { + if (empty($token->is_tag) || $token->name !== $remove_until) { + continue; + } + } + if (!empty($token->is_tag)) { + // DEFINITION CALL + + // before any processing, try to transform the element + if (isset($definition->info_tag_transform[$token->name])) { + $original_name = $token->name; + // there is a transformation for this tag + // DEFINITION CALL + $token = $definition-> + info_tag_transform[$token->name]->transform($token, $config, $context); + if ($e) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Tag transform', $original_name); + } + } + + if (isset($definition->info[$token->name])) { + // mostly everything's good, but + // we need to make sure required attributes are in order + if (($token instanceof HTMLPurifier_Token_Start || $token instanceof HTMLPurifier_Token_Empty) && + $definition->info[$token->name]->required_attr && + ($token->name != 'img' || $remove_invalid_img) // ensure config option still works + ) { + $attr_validator->validateToken($token, $config, $context); + $ok = true; + foreach ($definition->info[$token->name]->required_attr as $name) { + if (!isset($token->attr[$name])) { + $ok = false; + break; + } + } + if (!$ok) { + if ($e) { + $e->send( + E_ERROR, + 'Strategy_RemoveForeignElements: Missing required attribute', + $name + ); + } + continue; + } + $token->armor['ValidateAttributes'] = true; + } + + if (isset($hidden_elements[$token->name]) && $token instanceof HTMLPurifier_Token_Start) { + $textify_comments = $token->name; + } elseif ($token->name === $textify_comments && $token instanceof HTMLPurifier_Token_End) { + $textify_comments = false; + } + + } elseif ($escape_invalid_tags) { + // invalid tag, generate HTML representation and insert in + if ($e) { + $e->send(E_WARNING, 'Strategy_RemoveForeignElements: Foreign element to text'); + } + $token = new HTMLPurifier_Token_Text( + $generator->generateFromToken($token) + ); + } else { + // check if we need to destroy all of the tag's children + // CAN BE GENERICIZED + if (isset($hidden_elements[$token->name])) { + if ($token instanceof HTMLPurifier_Token_Start) { + $remove_until = $token->name; + } elseif ($token instanceof HTMLPurifier_Token_Empty) { + // do nothing: we're still looking + } else { + $remove_until = false; + } + if ($e) { + $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign meta element removed'); + } + } else { + if ($e) { + $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Foreign element removed'); + } + } + continue; + } + } elseif ($token instanceof HTMLPurifier_Token_Comment) { + // textify comments in script tags when they are allowed + if ($textify_comments !== false) { + $data = $token->data; + $token = new HTMLPurifier_Token_Text($data); + } elseif ($trusted || $check_comments) { + // always cleanup comments + $trailing_hyphen = false; + if ($e) { + // perform check whether or not there's a trailing hyphen + if (substr($token->data, -1) == '-') { + $trailing_hyphen = true; + } + } + $token->data = rtrim($token->data, '-'); + $found_double_hyphen = false; + while (strpos($token->data, '--') !== false) { + $found_double_hyphen = true; + $token->data = str_replace('--', '-', $token->data); + } + if ($trusted || !empty($comment_lookup[trim($token->data)]) || + ($comment_regexp !== null && preg_match($comment_regexp, trim($token->data)))) { + // OK good + if ($e) { + if ($trailing_hyphen) { + $e->send( + E_NOTICE, + 'Strategy_RemoveForeignElements: Trailing hyphen in comment removed' + ); + } + if ($found_double_hyphen) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Hyphens in comment collapsed'); + } + } + } else { + if ($e) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed'); + } + continue; + } + } else { + // strip comments + if ($e) { + $e->send(E_NOTICE, 'Strategy_RemoveForeignElements: Comment removed'); + } + continue; + } + } elseif ($token instanceof HTMLPurifier_Token_Text) { + } else { + continue; + } + $result[] = $token; + } + if ($remove_until && $e) { + // we removed tokens until the end, throw error + $e->send(E_ERROR, 'Strategy_RemoveForeignElements: Token removed to end', $remove_until); + } + $context->destroy('CurrentToken'); + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/ValidateAttributes.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/ValidateAttributes.php new file mode 100644 index 0000000000..fbb3d27c81 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Strategy/ValidateAttributes.php @@ -0,0 +1,45 @@ +register('CurrentToken', $token); + + foreach ($tokens as $key => $token) { + + // only process tokens that have attributes, + // namely start and empty tags + if (!$token instanceof HTMLPurifier_Token_Start && !$token instanceof HTMLPurifier_Token_Empty) { + continue; + } + + // skip tokens that are armored + if (!empty($token->armor['ValidateAttributes'])) { + continue; + } + + // note that we have no facilities here for removing tokens + $validator->validateToken($token, $config, $context); + } + $context->destroy('CurrentToken'); + return $tokens; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/StringHash.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/StringHash.php new file mode 100644 index 0000000000..c07370197a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/StringHash.php @@ -0,0 +1,47 @@ +accessed[$index] = true; + return parent::offsetGet($index); + } + + /** + * Returns a lookup array of all array indexes that have been accessed. + * @return array in form array($index => true). + */ + public function getAccessed() + { + return $this->accessed; + } + + /** + * Resets the access array. + */ + public function resetAccessed() + { + $this->accessed = array(); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/StringHashParser.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/StringHashParser.php new file mode 100644 index 0000000000..7c73f80835 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/StringHashParser.php @@ -0,0 +1,136 @@ + 'DefaultKeyValue', + * 'KEY' => 'Value', + * 'KEY2' => 'Value2', + * 'MULTILINE-KEY' => "Multiline\nvalue.\n", + * ) + * + * We use this as an easy to use file-format for configuration schema + * files, but the class itself is usage agnostic. + * + * You can use ---- to forcibly terminate parsing of a single string-hash; + * this marker is used in multi string-hashes to delimit boundaries. + */ +class HTMLPurifier_StringHashParser +{ + + /** + * @type string + */ + public $default = 'ID'; + + /** + * Parses a file that contains a single string-hash. + * @param string $file + * @return array + */ + public function parseFile($file) + { + if (!file_exists($file)) { + return false; + } + $fh = fopen($file, 'r'); + if (!$fh) { + return false; + } + $ret = $this->parseHandle($fh); + fclose($fh); + return $ret; + } + + /** + * Parses a file that contains multiple string-hashes delimited by '----' + * @param string $file + * @return array + */ + public function parseMultiFile($file) + { + if (!file_exists($file)) { + return false; + } + $ret = array(); + $fh = fopen($file, 'r'); + if (!$fh) { + return false; + } + while (!feof($fh)) { + $ret[] = $this->parseHandle($fh); + } + fclose($fh); + return $ret; + } + + /** + * Internal parser that acepts a file handle. + * @note While it's possible to simulate in-memory parsing by using + * custom stream wrappers, if such a use-case arises we should + * factor out the file handle into its own class. + * @param resource $fh File handle with pointer at start of valid string-hash + * block. + * @return array + */ + protected function parseHandle($fh) + { + $state = false; + $single = false; + $ret = array(); + do { + $line = fgets($fh); + if ($line === false) { + break; + } + $line = rtrim($line, "\n\r"); + if (!$state && $line === '') { + continue; + } + if ($line === '----') { + break; + } + if (strncmp('--#', $line, 3) === 0) { + // Comment + continue; + } elseif (strncmp('--', $line, 2) === 0) { + // Multiline declaration + $state = trim($line, '- '); + if (!isset($ret[$state])) { + $ret[$state] = ''; + } + continue; + } elseif (!$state) { + $single = true; + if (strpos($line, ':') !== false) { + // Single-line declaration + list($state, $line) = explode(':', $line, 2); + $line = trim($line); + } else { + // Use default declaration + $state = $this->default; + } + } + if ($single) { + $ret[$state] = $line; + $single = false; + $state = false; + } else { + $ret[$state] .= "$line\n"; + } + } while (!feof($fh)); + return $ret; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TagTransform.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TagTransform.php new file mode 100644 index 0000000000..7b8d833433 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TagTransform.php @@ -0,0 +1,37 @@ + 'xx-small', + '1' => 'xx-small', + '2' => 'small', + '3' => 'medium', + '4' => 'large', + '5' => 'x-large', + '6' => 'xx-large', + '7' => '300%', + '-1' => 'smaller', + '-2' => '60%', + '+1' => 'larger', + '+2' => '150%', + '+3' => '200%', + '+4' => '300%' + ); + + /** + * @param HTMLPurifier_Token_Tag $tag + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_Token_End|string + */ + public function transform($tag, $config, $context) + { + if ($tag instanceof HTMLPurifier_Token_End) { + $new_tag = clone $tag; + $new_tag->name = $this->transform_to; + return $new_tag; + } + + $attr = $tag->attr; + $prepend_style = ''; + + // handle color transform + if (isset($attr['color'])) { + $prepend_style .= 'color:' . $attr['color'] . ';'; + unset($attr['color']); + } + + // handle face transform + if (isset($attr['face'])) { + $prepend_style .= 'font-family:' . $attr['face'] . ';'; + unset($attr['face']); + } + + // handle size transform + if (isset($attr['size'])) { + // normalize large numbers + if ($attr['size'] !== '') { + if ($attr['size']{0} == '+' || $attr['size']{0} == '-') { + $size = (int)$attr['size']; + if ($size < -2) { + $attr['size'] = '-2'; + } + if ($size > 4) { + $attr['size'] = '+4'; + } + } else { + $size = (int)$attr['size']; + if ($size > 7) { + $attr['size'] = '7'; + } + } + } + if (isset($this->_size_lookup[$attr['size']])) { + $prepend_style .= 'font-size:' . + $this->_size_lookup[$attr['size']] . ';'; + } + unset($attr['size']); + } + + if ($prepend_style) { + $attr['style'] = isset($attr['style']) ? + $prepend_style . $attr['style'] : + $prepend_style; + } + + $new_tag = clone $tag; + $new_tag->name = $this->transform_to; + $new_tag->attr = $attr; + + return $new_tag; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TagTransform/Simple.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TagTransform/Simple.php new file mode 100644 index 0000000000..71bf10b91f --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TagTransform/Simple.php @@ -0,0 +1,44 @@ +transform_to = $transform_to; + $this->style = $style; + } + + /** + * @param HTMLPurifier_Token_Tag $tag + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return string + */ + public function transform($tag, $config, $context) + { + $new_tag = clone $tag; + $new_tag->name = $this->transform_to; + if (!is_null($this->style) && + ($new_tag instanceof HTMLPurifier_Token_Start || $new_tag instanceof HTMLPurifier_Token_Empty) + ) { + $this->prependCSS($new_tag->attr, $this->style); + } + return $new_tag; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token.php new file mode 100644 index 0000000000..85b85e072d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token.php @@ -0,0 +1,100 @@ +line = $l; + $this->col = $c; + } + + /** + * Convenience function for DirectLex settings line/col position. + * @param int $l + * @param int $c + */ + public function rawPosition($l, $c) + { + if ($c === -1) { + $l++; + } + $this->line = $l; + $this->col = $c; + } + + /** + * Converts a token into its corresponding node. + */ + abstract public function toNode(); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Comment.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Comment.php new file mode 100644 index 0000000000..23453c7052 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Comment.php @@ -0,0 +1,38 @@ +data = $data; + $this->line = $line; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Comment($this->data, $this->line, $this->col); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Empty.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Empty.php new file mode 100644 index 0000000000..78a95f5555 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Empty.php @@ -0,0 +1,15 @@ +empty = true; + return $n; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/End.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/End.php new file mode 100644 index 0000000000..59b38fdc57 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/End.php @@ -0,0 +1,24 @@ +toNode not supported!"); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Start.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Start.php new file mode 100644 index 0000000000..019f317ada --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Start.php @@ -0,0 +1,10 @@ +!empty($obj->is_tag) + * without having to use a function call is_a(). + * @type bool + */ + public $is_tag = true; + + /** + * The lower-case name of the tag, like 'a', 'b' or 'blockquote'. + * + * @note Strictly speaking, XML tags are case sensitive, so we shouldn't + * be lower-casing them, but these tokens cater to HTML tags, which are + * insensitive. + * @type string + */ + public $name; + + /** + * Associative array of the tag's attributes. + * @type array + */ + public $attr = array(); + + /** + * Non-overloaded constructor, which lower-cases passed tag name. + * + * @param string $name String name. + * @param array $attr Associative array of attributes. + * @param int $line + * @param int $col + * @param array $armor + */ + public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) + { + $this->name = ctype_lower($name) ? $name : strtolower($name); + foreach ($attr as $key => $value) { + // normalization only necessary when key is not lowercase + if (!ctype_lower($key)) { + $new_key = strtolower($key); + if (!isset($attr[$new_key])) { + $attr[$new_key] = $attr[$key]; + } + if ($new_key !== $key) { + unset($attr[$key]); + } + } + } + $this->attr = $attr; + $this->line = $line; + $this->col = $col; + $this->armor = $armor; + } + + public function toNode() { + return new HTMLPurifier_Node_Element($this->name, $this->attr, $this->line, $this->col, $this->armor); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Text.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Text.php new file mode 100644 index 0000000000..f26a1c211b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/Token/Text.php @@ -0,0 +1,53 @@ +data = $data; + $this->is_whitespace = ctype_space($data); + $this->line = $line; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Text($this->data, $this->is_whitespace, $this->line, $this->col); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TokenFactory.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TokenFactory.php new file mode 100644 index 0000000000..dea2446b93 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/TokenFactory.php @@ -0,0 +1,118 @@ +p_start = new HTMLPurifier_Token_Start('', array()); + $this->p_end = new HTMLPurifier_Token_End(''); + $this->p_empty = new HTMLPurifier_Token_Empty('', array()); + $this->p_text = new HTMLPurifier_Token_Text(''); + $this->p_comment = new HTMLPurifier_Token_Comment(''); + } + + /** + * Creates a HTMLPurifier_Token_Start. + * @param string $name Tag name + * @param array $attr Associative array of attributes + * @return HTMLPurifier_Token_Start Generated HTMLPurifier_Token_Start + */ + public function createStart($name, $attr = array()) + { + $p = clone $this->p_start; + $p->__construct($name, $attr); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_End. + * @param string $name Tag name + * @return HTMLPurifier_Token_End Generated HTMLPurifier_Token_End + */ + public function createEnd($name) + { + $p = clone $this->p_end; + $p->__construct($name); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Empty. + * @param string $name Tag name + * @param array $attr Associative array of attributes + * @return HTMLPurifier_Token_Empty Generated HTMLPurifier_Token_Empty + */ + public function createEmpty($name, $attr = array()) + { + $p = clone $this->p_empty; + $p->__construct($name, $attr); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Text. + * @param string $data Data of text token + * @return HTMLPurifier_Token_Text Generated HTMLPurifier_Token_Text + */ + public function createText($data) + { + $p = clone $this->p_text; + $p->__construct($data); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Comment. + * @param string $data Data of comment token + * @return HTMLPurifier_Token_Comment Generated HTMLPurifier_Token_Comment + */ + public function createComment($data) + { + $p = clone $this->p_comment; + $p->__construct($data); + return $p; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URI.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URI.php new file mode 100644 index 0000000000..a5e7ae2984 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URI.php @@ -0,0 +1,314 @@ +scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme); + $this->userinfo = $userinfo; + $this->host = $host; + $this->port = is_null($port) ? $port : (int)$port; + $this->path = $path; + $this->query = $query; + $this->fragment = $fragment; + } + + /** + * Retrieves a scheme object corresponding to the URI's scheme/default + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return HTMLPurifier_URIScheme Scheme object appropriate for validating this URI + */ + public function getSchemeObj($config, $context) + { + $registry = HTMLPurifier_URISchemeRegistry::instance(); + if ($this->scheme !== null) { + $scheme_obj = $registry->getScheme($this->scheme, $config, $context); + if (!$scheme_obj) { + return false; + } // invalid scheme, clean it out + } else { + // no scheme: retrieve the default one + $def = $config->getDefinition('URI'); + $scheme_obj = $def->getDefaultScheme($config, $context); + if (!$scheme_obj) { + // something funky happened to the default scheme object + trigger_error( + 'Default scheme object "' . $def->defaultScheme . '" was not readable', + E_USER_WARNING + ); + return false; + } + } + return $scheme_obj; + } + + /** + * Generic validation method applicable for all schemes. May modify + * this URI in order to get it into a compliant form. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool True if validation/filtering succeeds, false if failure + */ + public function validate($config, $context) + { + // ABNF definitions from RFC 3986 + $chars_sub_delims = '!$&\'()*+,;='; + $chars_gen_delims = ':/?#[]@'; + $chars_pchar = $chars_sub_delims . ':@'; + + // validate host + if (!is_null($this->host)) { + $host_def = new HTMLPurifier_AttrDef_URI_Host(); + $this->host = $host_def->validate($this->host, $config, $context); + if ($this->host === false) { + $this->host = null; + } + } + + // validate scheme + // NOTE: It's not appropriate to check whether or not this + // scheme is in our registry, since a URIFilter may convert a + // URI that we don't allow into one we do. So instead, we just + // check if the scheme can be dropped because there is no host + // and it is our default scheme. + if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') { + // support for relative paths is pretty abysmal when the + // scheme is present, so axe it when possible + $def = $config->getDefinition('URI'); + if ($def->defaultScheme === $this->scheme) { + $this->scheme = null; + } + } + + // validate username + if (!is_null($this->userinfo)) { + $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':'); + $this->userinfo = $encoder->encode($this->userinfo); + } + + // validate port + if (!is_null($this->port)) { + if ($this->port < 1 || $this->port > 65535) { + $this->port = null; + } + } + + // validate path + $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/'); + if (!is_null($this->host)) { // this catches $this->host === '' + // path-abempty (hier and relative) + // http://www.example.com/my/path + // //www.example.com/my/path (looks odd, but works, and + // recognized by most browsers) + // (this set is valid or invalid on a scheme by scheme + // basis, so we'll deal with it later) + // file:///my/path + // ///my/path + $this->path = $segments_encoder->encode($this->path); + } elseif ($this->path !== '') { + if ($this->path[0] === '/') { + // path-absolute (hier and relative) + // http:/my/path + // /my/path + if (strlen($this->path) >= 2 && $this->path[1] === '/') { + // This could happen if both the host gets stripped + // out + // http://my/path + // //my/path + $this->path = ''; + } else { + $this->path = $segments_encoder->encode($this->path); + } + } elseif (!is_null($this->scheme)) { + // path-rootless (hier) + // http:my/path + // Short circuit evaluation means we don't need to check nz + $this->path = $segments_encoder->encode($this->path); + } else { + // path-noscheme (relative) + // my/path + // (once again, not checking nz) + $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@'); + $c = strpos($this->path, '/'); + if ($c !== false) { + $this->path = + $segment_nc_encoder->encode(substr($this->path, 0, $c)) . + $segments_encoder->encode(substr($this->path, $c)); + } else { + $this->path = $segment_nc_encoder->encode($this->path); + } + } + } else { + // path-empty (hier and relative) + $this->path = ''; // just to be safe + } + + // qf = query and fragment + $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?'); + + if (!is_null($this->query)) { + $this->query = $qf_encoder->encode($this->query); + } + + if (!is_null($this->fragment)) { + $this->fragment = $qf_encoder->encode($this->fragment); + } + return true; + } + + /** + * Convert URI back to string + * @return string URI appropriate for output + */ + public function toString() + { + // reconstruct authority + $authority = null; + // there is a rendering difference between a null authority + // (http:foo-bar) and an empty string authority + // (http:///foo-bar). + if (!is_null($this->host)) { + $authority = ''; + if (!is_null($this->userinfo)) { + $authority .= $this->userinfo . '@'; + } + $authority .= $this->host; + if (!is_null($this->port)) { + $authority .= ':' . $this->port; + } + } + + // Reconstruct the result + // One might wonder about parsing quirks from browsers after + // this reconstruction. Unfortunately, parsing behavior depends + // on what *scheme* was employed (file:///foo is handled *very* + // differently than http:///foo), so unfortunately we have to + // defer to the schemes to do the right thing. + $result = ''; + if (!is_null($this->scheme)) { + $result .= $this->scheme . ':'; + } + if (!is_null($authority)) { + $result .= '//' . $authority; + } + $result .= $this->path; + if (!is_null($this->query)) { + $result .= '?' . $this->query; + } + if (!is_null($this->fragment)) { + $result .= '#' . $this->fragment; + } + + return $result; + } + + /** + * Returns true if this URL might be considered a 'local' URL given + * the current context. This is true when the host is null, or + * when it matches the host supplied to the configuration. + * + * Note that this does not do any scheme checking, so it is mostly + * only appropriate for metadata that doesn't care about protocol + * security. isBenign is probably what you actually want. + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function isLocal($config, $context) + { + if ($this->host === null) { + return true; + } + $uri_def = $config->getDefinition('URI'); + if ($uri_def->host === $this->host) { + return true; + } + return false; + } + + /** + * Returns true if this URL should be considered a 'benign' URL, + * that is: + * + * - It is a local URL (isLocal), and + * - It has a equal or better level of security + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function isBenign($config, $context) + { + if (!$this->isLocal($config, $context)) { + return false; + } + + $scheme_obj = $this->getSchemeObj($config, $context); + if (!$scheme_obj) { + return false; + } // conservative approach + + $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context); + if ($current_scheme_obj->secure) { + if (!$scheme_obj->secure) { + return false; + } + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIDefinition.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIDefinition.php new file mode 100644 index 0000000000..e0bd8bcca8 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIDefinition.php @@ -0,0 +1,112 @@ +registerFilter(new HTMLPurifier_URIFilter_DisableExternal()); + $this->registerFilter(new HTMLPurifier_URIFilter_DisableExternalResources()); + $this->registerFilter(new HTMLPurifier_URIFilter_DisableResources()); + $this->registerFilter(new HTMLPurifier_URIFilter_HostBlacklist()); + $this->registerFilter(new HTMLPurifier_URIFilter_SafeIframe()); + $this->registerFilter(new HTMLPurifier_URIFilter_MakeAbsolute()); + $this->registerFilter(new HTMLPurifier_URIFilter_Munge()); + } + + public function registerFilter($filter) + { + $this->registeredFilters[$filter->name] = $filter; + } + + public function addFilter($filter, $config) + { + $r = $filter->prepare($config); + if ($r === false) return; // null is ok, for backwards compat + if ($filter->post) { + $this->postFilters[$filter->name] = $filter; + } else { + $this->filters[$filter->name] = $filter; + } + } + + protected function doSetup($config) + { + $this->setupMemberVariables($config); + $this->setupFilters($config); + } + + protected function setupFilters($config) + { + foreach ($this->registeredFilters as $name => $filter) { + if ($filter->always_load) { + $this->addFilter($filter, $config); + } else { + $conf = $config->get('URI.' . $name); + if ($conf !== false && $conf !== null) { + $this->addFilter($filter, $config); + } + } + } + unset($this->registeredFilters); + } + + protected function setupMemberVariables($config) + { + $this->host = $config->get('URI.Host'); + $base_uri = $config->get('URI.Base'); + if (!is_null($base_uri)) { + $parser = new HTMLPurifier_URIParser(); + $this->base = $parser->parse($base_uri); + $this->defaultScheme = $this->base->scheme; + if (is_null($this->host)) $this->host = $this->base->host; + } + if (is_null($this->defaultScheme)) $this->defaultScheme = $config->get('URI.DefaultScheme'); + } + + public function getDefaultScheme($config, $context) + { + return HTMLPurifier_URISchemeRegistry::instance()->getScheme($this->defaultScheme, $config, $context); + } + + public function filter(&$uri, $config, $context) + { + foreach ($this->filters as $name => $f) { + $result = $f->filter($uri, $config, $context); + if (!$result) return false; + } + return true; + } + + public function postFilter(&$uri, $config, $context) + { + foreach ($this->postFilters as $name => $f) { + $result = $f->filter($uri, $config, $context); + if (!$result) return false; + } + return true; + } + +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter.php new file mode 100644 index 0000000000..09724e9f41 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter.php @@ -0,0 +1,74 @@ +getDefinition('URI')->host; + if ($our_host !== null) { + $this->ourHostParts = array_reverse(explode('.', $our_host)); + } + } + + /** + * @param HTMLPurifier_URI $uri Reference + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if (is_null($uri->host)) { + return true; + } + if ($this->ourHostParts === false) { + return false; + } + $host_parts = array_reverse(explode('.', $uri->host)); + foreach ($this->ourHostParts as $i => $x) { + if (!isset($host_parts[$i])) { + return false; + } + if ($host_parts[$i] != $this->ourHostParts[$i]) { + return false; + } + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternalResources.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternalResources.php new file mode 100644 index 0000000000..c6562169e0 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/DisableExternalResources.php @@ -0,0 +1,25 @@ +get('EmbeddedURI', true)) { + return true; + } + return parent::filter($uri, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/DisableResources.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/DisableResources.php new file mode 100644 index 0000000000..d5c412c444 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/DisableResources.php @@ -0,0 +1,22 @@ +get('EmbeddedURI', true); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/HostBlacklist.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/HostBlacklist.php new file mode 100644 index 0000000000..a6645c17ee --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/HostBlacklist.php @@ -0,0 +1,46 @@ +blacklist = $config->get('URI.HostBlacklist'); + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + foreach ($this->blacklist as $blacklisted_host_fragment) { + if (strpos($uri->host, $blacklisted_host_fragment) !== false) { + return false; + } + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/MakeAbsolute.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/MakeAbsolute.php new file mode 100644 index 0000000000..c507bbff8e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/MakeAbsolute.php @@ -0,0 +1,158 @@ +getDefinition('URI'); + $this->base = $def->base; + if (is_null($this->base)) { + trigger_error( + 'URI.MakeAbsolute is being ignored due to lack of ' . + 'value for URI.Base configuration', + E_USER_WARNING + ); + return false; + } + $this->base->fragment = null; // fragment is invalid for base URI + $stack = explode('/', $this->base->path); + array_pop($stack); // discard last segment + $stack = $this->_collapseStack($stack); // do pre-parsing + $this->basePathStack = $stack; + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if (is_null($this->base)) { + return true; + } // abort early + if ($uri->path === '' && is_null($uri->scheme) && + is_null($uri->host) && is_null($uri->query) && is_null($uri->fragment)) { + // reference to current document + $uri = clone $this->base; + return true; + } + if (!is_null($uri->scheme)) { + // absolute URI already: don't change + if (!is_null($uri->host)) { + return true; + } + $scheme_obj = $uri->getSchemeObj($config, $context); + if (!$scheme_obj) { + // scheme not recognized + return false; + } + if (!$scheme_obj->hierarchical) { + // non-hierarchal URI with explicit scheme, don't change + return true; + } + // special case: had a scheme but always is hierarchical and had no authority + } + if (!is_null($uri->host)) { + // network path, don't bother + return true; + } + if ($uri->path === '') { + $uri->path = $this->base->path; + } elseif ($uri->path[0] !== '/') { + // relative path, needs more complicated processing + $stack = explode('/', $uri->path); + $new_stack = array_merge($this->basePathStack, $stack); + if ($new_stack[0] !== '' && !is_null($this->base->host)) { + array_unshift($new_stack, ''); + } + $new_stack = $this->_collapseStack($new_stack); + $uri->path = implode('/', $new_stack); + } else { + // absolute path, but still we should collapse + $uri->path = implode('/', $this->_collapseStack(explode('/', $uri->path))); + } + // re-combine + $uri->scheme = $this->base->scheme; + if (is_null($uri->userinfo)) { + $uri->userinfo = $this->base->userinfo; + } + if (is_null($uri->host)) { + $uri->host = $this->base->host; + } + if (is_null($uri->port)) { + $uri->port = $this->base->port; + } + return true; + } + + /** + * Resolve dots and double-dots in a path stack + * @param array $stack + * @return array + */ + private function _collapseStack($stack) + { + $result = array(); + $is_folder = false; + for ($i = 0; isset($stack[$i]); $i++) { + $is_folder = false; + // absorb an internally duplicated slash + if ($stack[$i] == '' && $i && isset($stack[$i + 1])) { + continue; + } + if ($stack[$i] == '..') { + if (!empty($result)) { + $segment = array_pop($result); + if ($segment === '' && empty($result)) { + // error case: attempted to back out too far: + // restore the leading slash + $result[] = ''; + } elseif ($segment === '..') { + $result[] = '..'; // cannot remove .. with .. + } + } else { + // relative path, preserve the double-dots + $result[] = '..'; + } + $is_folder = true; + continue; + } + if ($stack[$i] == '.') { + // silently absorb + $is_folder = true; + continue; + } + $result[] = $stack[$i]; + } + if ($is_folder) { + $result[] = ''; + } + return $result; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/Munge.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/Munge.php new file mode 100644 index 0000000000..6e03315a17 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/Munge.php @@ -0,0 +1,115 @@ +target = $config->get('URI.' . $this->name); + $this->parser = new HTMLPurifier_URIParser(); + $this->doEmbed = $config->get('URI.MungeResources'); + $this->secretKey = $config->get('URI.MungeSecretKey'); + if ($this->secretKey && !function_exists('hash_hmac')) { + throw new Exception("Cannot use %URI.MungeSecretKey without hash_hmac support."); + } + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + if ($context->get('EmbeddedURI', true) && !$this->doEmbed) { + return true; + } + + $scheme_obj = $uri->getSchemeObj($config, $context); + if (!$scheme_obj) { + return true; + } // ignore unknown schemes, maybe another postfilter did it + if (!$scheme_obj->browsable) { + return true; + } // ignore non-browseable schemes, since we can't munge those in a reasonable way + if ($uri->isBenign($config, $context)) { + return true; + } // don't redirect if a benign URL + + $this->makeReplace($uri, $config, $context); + $this->replace = array_map('rawurlencode', $this->replace); + + $new_uri = strtr($this->target, $this->replace); + $new_uri = $this->parser->parse($new_uri); + // don't redirect if the target host is the same as the + // starting host + if ($uri->host === $new_uri->host) { + return true; + } + $uri = $new_uri; // overwrite + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + */ + protected function makeReplace($uri, $config, $context) + { + $string = $uri->toString(); + // always available + $this->replace['%s'] = $string; + $this->replace['%r'] = $context->get('EmbeddedURI', true); + $token = $context->get('CurrentToken', true); + $this->replace['%n'] = $token ? $token->name : null; + $this->replace['%m'] = $context->get('CurrentAttr', true); + $this->replace['%p'] = $context->get('CurrentCSSProperty', true); + // not always available + if ($this->secretKey) { + $this->replace['%t'] = hash_hmac("sha256", $string, $this->secretKey); + } + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/SafeIframe.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/SafeIframe.php new file mode 100644 index 0000000000..f609c47a34 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIFilter/SafeIframe.php @@ -0,0 +1,68 @@ +regexp = $config->get('URI.SafeIframeRegexp'); + return true; + } + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function filter(&$uri, $config, $context) + { + // check if filter not applicable + if (!$config->get('HTML.SafeIframe')) { + return true; + } + // check if the filter should actually trigger + if (!$context->get('EmbeddedURI', true)) { + return true; + } + $token = $context->get('CurrentToken', true); + if (!($token && $token->name == 'iframe')) { + return true; + } + // check if we actually have some whitelists enabled + if ($this->regexp === null) { + return false; + } + // actually check the whitelists + return preg_match($this->regexp, $uri->toString()); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIParser.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIParser.php new file mode 100644 index 0000000000..0e7381a07b --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIParser.php @@ -0,0 +1,71 @@ +percentEncoder = new HTMLPurifier_PercentEncoder(); + } + + /** + * Parses a URI. + * @param $uri string URI to parse + * @return HTMLPurifier_URI representation of URI. This representation has + * not been validated yet and may not conform to RFC. + */ + public function parse($uri) + { + $uri = $this->percentEncoder->normalize($uri); + + // Regexp is as per Appendix B. + // Note that ["<>] are an addition to the RFC's recommended + // characters, because they represent external delimeters. + $r_URI = '!'. + '(([a-zA-Z0-9\.\+\-]+):)?'. // 2. Scheme + '(//([^/?#"<>]*))?'. // 4. Authority + '([^?#"<>]*)'. // 5. Path + '(\?([^#"<>]*))?'. // 7. Query + '(#([^"<>]*))?'. // 8. Fragment + '!'; + + $matches = array(); + $result = preg_match($r_URI, $uri, $matches); + + if (!$result) return false; // *really* invalid URI + + // seperate out parts + $scheme = !empty($matches[1]) ? $matches[2] : null; + $authority = !empty($matches[3]) ? $matches[4] : null; + $path = $matches[5]; // always present, can be empty + $query = !empty($matches[6]) ? $matches[7] : null; + $fragment = !empty($matches[8]) ? $matches[9] : null; + + // further parse authority + if ($authority !== null) { + $r_authority = "/^((.+?)@)?(\[[^\]]+\]|[^:]*)(:(\d*))?/"; + $matches = array(); + preg_match($r_authority, $authority, $matches); + $userinfo = !empty($matches[1]) ? $matches[2] : null; + $host = !empty($matches[3]) ? $matches[3] : ''; + $port = !empty($matches[4]) ? (int) $matches[5] : null; + } else { + $port = $host = $userinfo = null; + } + + return new HTMLPurifier_URI( + $scheme, $userinfo, $host, $port, $path, $query, $fragment); + } + +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme.php new file mode 100644 index 0000000000..fe9e82cf26 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme.php @@ -0,0 +1,102 @@ +, resolves edge cases + * with making relative URIs absolute + * @type bool + */ + public $hierarchical = false; + + /** + * Whether or not the URI may omit a hostname when the scheme is + * explicitly specified, ala file:///path/to/file. As of writing, + * 'file' is the only scheme that browsers support his properly. + * @type bool + */ + public $may_omit_host = false; + + /** + * Validates the components of a URI for a specific scheme. + * @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool success or failure + */ + abstract public function doValidate(&$uri, $config, $context); + + /** + * Public interface for validating components of a URI. Performs a + * bunch of default actions. Don't overload this method. + * @param HTMLPurifier_URI $uri Reference to a HTMLPurifier_URI object + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool success or failure + */ + public function validate(&$uri, $config, $context) + { + if ($this->default_port == $uri->port) { + $uri->port = null; + } + // kludge: browsers do funny things when the scheme but not the + // authority is set + if (!$this->may_omit_host && + // if the scheme is present, a missing host is always in error + (!is_null($uri->scheme) && ($uri->host === '' || is_null($uri->host))) || + // if the scheme is not present, a *blank* host is in error, + // since this translates into '///path' which most browsers + // interpret as being 'http://path'. + (is_null($uri->scheme) && $uri->host === '') + ) { + do { + if (is_null($uri->scheme)) { + if (substr($uri->path, 0, 2) != '//') { + $uri->host = null; + break; + } + // URI is '////path', so we cannot nullify the + // host to preserve semantics. Try expanding the + // hostname instead (fall through) + } + // first see if we can manually insert a hostname + $host = $config->get('URI.Host'); + if (!is_null($host)) { + $uri->host = $host; + } else { + // we can't do anything sensible, reject the URL. + return false; + } + } while (false); + } + return $this->doValidate($uri, $config, $context); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/data.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/data.php new file mode 100644 index 0000000000..6ebca49848 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/data.php @@ -0,0 +1,127 @@ + true, + 'image/gif' => true, + 'image/png' => true, + ); + // this is actually irrelevant since we only write out the path + // component + /** + * @type bool + */ + public $may_omit_host = true; + + /** + * @param HTMLPurifier_URI $uri + * @param HTMLPurifier_Config $config + * @param HTMLPurifier_Context $context + * @return bool + */ + public function doValidate(&$uri, $config, $context) + { + $result = explode(',', $uri->path, 2); + $is_base64 = false; + $charset = null; + $content_type = null; + if (count($result) == 2) { + list($metadata, $data) = $result; + // do some legwork on the metadata + $metas = explode(';', $metadata); + while (!empty($metas)) { + $cur = array_shift($metas); + if ($cur == 'base64') { + $is_base64 = true; + break; + } + if (substr($cur, 0, 8) == 'charset=') { + // doesn't match if there are arbitrary spaces, but + // whatever dude + if ($charset !== null) { + continue; + } // garbage + $charset = substr($cur, 8); // not used + } else { + if ($content_type !== null) { + continue; + } // garbage + $content_type = $cur; + } + } + } else { + $data = $result[0]; + } + if ($content_type !== null && empty($this->allowed_types[$content_type])) { + return false; + } + if ($charset !== null) { + // error; we don't allow plaintext stuff + $charset = null; + } + $data = rawurldecode($data); + if ($is_base64) { + $raw_data = base64_decode($data); + } else { + $raw_data = $data; + } + // XXX probably want to refactor this into a general mechanism + // for filtering arbitrary content types + $file = tempnam("/tmp", ""); + file_put_contents($file, $raw_data); + if (function_exists('exif_imagetype')) { + $image_code = exif_imagetype($file); + unlink($file); + } elseif (function_exists('getimagesize')) { + set_error_handler(array($this, 'muteErrorHandler')); + $info = getimagesize($file); + restore_error_handler(); + unlink($file); + if ($info == false) { + return false; + } + $image_code = $info[2]; + } else { + trigger_error("could not find exif_imagetype or getimagesize functions", E_USER_ERROR); + } + $real_content_type = image_type_to_mime_type($image_code); + if ($real_content_type != $content_type) { + // we're nice guys; if the content type is something else we + // support, change it over + if (empty($this->allowed_types[$real_content_type])) { + return false; + } + $content_type = $real_content_type; + } + // ok, it's kosher, rewrite what we need + $uri->userinfo = null; + $uri->host = null; + $uri->port = null; + $uri->fragment = null; + $uri->query = null; + $uri->path = "$content_type;base64," . base64_encode($raw_data); + return true; + } + + /** + * @param int $errno + * @param string $errstr + */ + public function muteErrorHandler($errno, $errstr) + { + } +} diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/file.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/file.php new file mode 100644 index 0000000000..215be4ba80 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/file.php @@ -0,0 +1,44 @@ +userinfo = null; + // file:// makes no provisions for accessing the resource + $uri->port = null; + // While it seems to work on Firefox, the querystring has + // no possible effect and is thus stripped. + $uri->query = null; + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/ftp.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/ftp.php new file mode 100644 index 0000000000..1eb43ee5c4 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/ftp.php @@ -0,0 +1,58 @@ +query = null; + + // typecode check + $semicolon_pos = strrpos($uri->path, ';'); // reverse + if ($semicolon_pos !== false) { + $type = substr($uri->path, $semicolon_pos + 1); // no semicolon + $uri->path = substr($uri->path, 0, $semicolon_pos); + $type_ret = ''; + if (strpos($type, '=') !== false) { + // figure out whether or not the declaration is correct + list($key, $typecode) = explode('=', $type, 2); + if ($key !== 'type') { + // invalid key, tack it back on encoded + $uri->path .= '%3B' . $type; + } elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') { + $type_ret = ";type=$typecode"; + } + } else { + $uri->path .= '%3B' . $type; + } + $uri->path = str_replace(';', '%3B', $uri->path); + $uri->path .= $type_ret; + } + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/http.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/http.php new file mode 100644 index 0000000000..ce69ec438a --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/http.php @@ -0,0 +1,36 @@ +userinfo = null; + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/https.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/https.php new file mode 100644 index 0000000000..0e96882db9 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/https.php @@ -0,0 +1,18 @@ +userinfo = null; + $uri->host = null; + $uri->port = null; + // we need to validate path against RFC 2368's addr-spec + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/news.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/news.php new file mode 100644 index 0000000000..7490927d63 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/news.php @@ -0,0 +1,35 @@ +userinfo = null; + $uri->host = null; + $uri->port = null; + $uri->query = null; + // typecode check needed on path + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/nntp.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/nntp.php new file mode 100644 index 0000000000..f211d715e9 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URIScheme/nntp.php @@ -0,0 +1,32 @@ +userinfo = null; + $uri->query = null; + return true; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URISchemeRegistry.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URISchemeRegistry.php new file mode 100644 index 0000000000..4ac8a0b76e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/URISchemeRegistry.php @@ -0,0 +1,81 @@ +get('URI.AllowedSchemes'); + if (!$config->get('URI.OverrideAllowedSchemes') && + !isset($allowed_schemes[$scheme]) + ) { + return; + } + + if (isset($this->schemes[$scheme])) { + return $this->schemes[$scheme]; + } + if (!isset($allowed_schemes[$scheme])) { + return; + } + + $class = 'HTMLPurifier_URIScheme_' . $scheme; + if (!class_exists($class)) { + return; + } + $this->schemes[$scheme] = new $class(); + return $this->schemes[$scheme]; + } + + /** + * Registers a custom scheme to the cache, bypassing reflection. + * @param string $scheme Scheme name + * @param HTMLPurifier_URIScheme $scheme_obj + */ + public function register($scheme, $scheme_obj) + { + $this->schemes[$scheme] = $scheme_obj; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/UnitConverter.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/UnitConverter.php new file mode 100644 index 0000000000..166f3bf306 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/UnitConverter.php @@ -0,0 +1,307 @@ + array( + 'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary + 'pt' => 4, + 'pc' => 48, + 'in' => 288, + self::METRIC => array('pt', '0.352777778', 'mm'), + ), + self::METRIC => array( + 'mm' => 1, + 'cm' => 10, + self::ENGLISH => array('mm', '2.83464567', 'pt'), + ), + ); + + /** + * Minimum bcmath precision for output. + * @type int + */ + protected $outputPrecision; + + /** + * Bcmath precision for internal calculations. + * @type int + */ + protected $internalPrecision; + + /** + * Whether or not BCMath is available. + * @type bool + */ + private $bcmath; + + public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) + { + $this->outputPrecision = $output_precision; + $this->internalPrecision = $internal_precision; + $this->bcmath = !$force_no_bcmath && function_exists('bcmul'); + } + + /** + * Converts a length object of one unit into another unit. + * @param HTMLPurifier_Length $length + * Instance of HTMLPurifier_Length to convert. You must validate() + * it before passing it here! + * @param string $to_unit + * Unit to convert to. + * @return HTMLPurifier_Length|bool + * @note + * About precision: This conversion function pays very special + * attention to the incoming precision of values and attempts + * to maintain a number of significant figure. Results are + * fairly accurate up to nine digits. Some caveats: + * - If a number is zero-padded as a result of this significant + * figure tracking, the zeroes will be eliminated. + * - If a number contains less than four sigfigs ($outputPrecision) + * and this causes some decimals to be excluded, those + * decimals will be added on. + */ + public function convert($length, $to_unit) + { + if (!$length->isValid()) { + return false; + } + + $n = $length->getN(); + $unit = $length->getUnit(); + + if ($n === '0' || $unit === false) { + return new HTMLPurifier_Length('0', false); + } + + $state = $dest_state = false; + foreach (self::$units as $k => $x) { + if (isset($x[$unit])) { + $state = $k; + } + if (isset($x[$to_unit])) { + $dest_state = $k; + } + } + if (!$state || !$dest_state) { + return false; + } + + // Some calculations about the initial precision of the number; + // this will be useful when we need to do final rounding. + $sigfigs = $this->getSigFigs($n); + if ($sigfigs < $this->outputPrecision) { + $sigfigs = $this->outputPrecision; + } + + // BCMath's internal precision deals only with decimals. Use + // our default if the initial number has no decimals, or increase + // it by how ever many decimals, thus, the number of guard digits + // will always be greater than or equal to internalPrecision. + $log = (int)floor(log(abs($n), 10)); + $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision + + for ($i = 0; $i < 2; $i++) { + + // Determine what unit IN THIS SYSTEM we need to convert to + if ($dest_state === $state) { + // Simple conversion + $dest_unit = $to_unit; + } else { + // Convert to the smallest unit, pending a system shift + $dest_unit = self::$units[$state][$dest_state][0]; + } + + // Do the conversion if necessary + if ($dest_unit !== $unit) { + $factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp); + $n = $this->mul($n, $factor, $cp); + $unit = $dest_unit; + } + + // Output was zero, so bail out early. Shouldn't ever happen. + if ($n === '') { + $n = '0'; + $unit = $to_unit; + break; + } + + // It was a simple conversion, so bail out + if ($dest_state === $state) { + break; + } + + if ($i !== 0) { + // Conversion failed! Apparently, the system we forwarded + // to didn't have this unit. This should never happen! + return false; + } + + // Pre-condition: $i == 0 + + // Perform conversion to next system of units + $n = $this->mul($n, self::$units[$state][$dest_state][1], $cp); + $unit = self::$units[$state][$dest_state][2]; + $state = $dest_state; + + // One more loop around to convert the unit in the new system. + + } + + // Post-condition: $unit == $to_unit + if ($unit !== $to_unit) { + return false; + } + + // Useful for debugging: + //echo "
n"; + //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n
\n"; + + $n = $this->round($n, $sigfigs); + if (strpos($n, '.') !== false) { + $n = rtrim($n, '0'); + } + $n = rtrim($n, '.'); + + return new HTMLPurifier_Length($n, $unit); + } + + /** + * Returns the number of significant figures in a string number. + * @param string $n Decimal number + * @return int number of sigfigs + */ + public function getSigFigs($n) + { + $n = ltrim($n, '0+-'); + $dp = strpos($n, '.'); // decimal position + if ($dp === false) { + $sigfigs = strlen(rtrim($n, '0')); + } else { + $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character + if ($dp !== 0) { + $sigfigs--; + } + } + return $sigfigs; + } + + /** + * Adds two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function add($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcadd($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 + (float)$s2, $scale); + } + } + + /** + * Multiples two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function mul($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcmul($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 * (float)$s2, $scale); + } + } + + /** + * Divides two numbers, using arbitrary precision when available. + * @param string $s1 + * @param string $s2 + * @param int $scale + * @return string + */ + private function div($s1, $s2, $scale) + { + if ($this->bcmath) { + return bcdiv($s1, $s2, $scale); + } else { + return $this->scale((float)$s1 / (float)$s2, $scale); + } + } + + /** + * Rounds a number according to the number of sigfigs it should have, + * using arbitrary precision when available. + * @param float $n + * @param int $sigfigs + * @return string + */ + private function round($n, $sigfigs) + { + $new_log = (int)floor(log(abs($n), 10)); // Number of digits left of decimal - 1 + $rp = $sigfigs - $new_log - 1; // Number of decimal places needed + $neg = $n < 0 ? '-' : ''; // Negative sign + if ($this->bcmath) { + if ($rp >= 0) { + $n = bcadd($n, $neg . '0.' . str_repeat('0', $rp) . '5', $rp + 1); + $n = bcdiv($n, '1', $rp); + } else { + // This algorithm partially depends on the standardized + // form of numbers that comes out of bcmath. + $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0); + $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1); + } + return $n; + } else { + return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1); + } + } + + /** + * Scales a float to $scale digits right of decimal point, like BCMath. + * @param float $r + * @param int $scale + * @return string + */ + private function scale($r, $scale) + { + if ($scale < 0) { + // The f sprintf type doesn't support negative numbers, so we + // need to cludge things manually. First get the string. + $r = sprintf('%.0f', (float)$r); + // Due to floating point precision loss, $r will more than likely + // look something like 4652999999999.9234. We grab one more digit + // than we need to precise from $r and then use that to round + // appropriately. + $precise = (string)round(substr($r, 0, strlen($r) + $scale), -1); + // Now we return it, truncating the zero that was rounded off. + return substr($precise, 0, -1) . str_repeat('0', -$scale + 1); + } + return sprintf('%.' . $scale . 'f', (float)$r); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser.php new file mode 100644 index 0000000000..50cba6910d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser.php @@ -0,0 +1,198 @@ + self::STRING, + 'istring' => self::ISTRING, + 'text' => self::TEXT, + 'itext' => self::ITEXT, + 'int' => self::INT, + 'float' => self::FLOAT, + 'bool' => self::BOOL, + 'lookup' => self::LOOKUP, + 'list' => self::ALIST, + 'hash' => self::HASH, + 'mixed' => self::MIXED + ); + + /** + * Lookup table of types that are string, and can have aliases or + * allowed value lists. + */ + public static $stringTypes = array( + self::STRING => true, + self::ISTRING => true, + self::TEXT => true, + self::ITEXT => true, + ); + + /** + * Validate a variable according to type. + * It may return NULL as a valid type if $allow_null is true. + * + * @param mixed $var Variable to validate + * @param int $type Type of variable, see HTMLPurifier_VarParser->types + * @param bool $allow_null Whether or not to permit null as a value + * @return string Validated and type-coerced variable + * @throws HTMLPurifier_VarParserException + */ + final public function parse($var, $type, $allow_null = false) + { + if (is_string($type)) { + if (!isset(HTMLPurifier_VarParser::$types[$type])) { + throw new HTMLPurifier_VarParserException("Invalid type '$type'"); + } else { + $type = HTMLPurifier_VarParser::$types[$type]; + } + } + $var = $this->parseImplementation($var, $type, $allow_null); + if ($allow_null && $var === null) { + return null; + } + // These are basic checks, to make sure nothing horribly wrong + // happened in our implementations. + switch ($type) { + case (self::STRING): + case (self::ISTRING): + case (self::TEXT): + case (self::ITEXT): + if (!is_string($var)) { + break; + } + if ($type == self::ISTRING || $type == self::ITEXT) { + $var = strtolower($var); + } + return $var; + case (self::INT): + if (!is_int($var)) { + break; + } + return $var; + case (self::FLOAT): + if (!is_float($var)) { + break; + } + return $var; + case (self::BOOL): + if (!is_bool($var)) { + break; + } + return $var; + case (self::LOOKUP): + case (self::ALIST): + case (self::HASH): + if (!is_array($var)) { + break; + } + if ($type === self::LOOKUP) { + foreach ($var as $k) { + if ($k !== true) { + $this->error('Lookup table contains value other than true'); + } + } + } elseif ($type === self::ALIST) { + $keys = array_keys($var); + if (array_keys($keys) !== $keys) { + $this->error('Indices for list are not uniform'); + } + } + return $var; + case (self::MIXED): + return $var; + default: + $this->errorInconsistent(get_class($this), $type); + } + $this->errorGeneric($var, $type); + } + + /** + * Actually implements the parsing. Base implementation does not + * do anything to $var. Subclasses should overload this! + * @param mixed $var + * @param int $type + * @param bool $allow_null + * @return string + */ + protected function parseImplementation($var, $type, $allow_null) + { + return $var; + } + + /** + * Throws an exception. + * @throws HTMLPurifier_VarParserException + */ + protected function error($msg) + { + throw new HTMLPurifier_VarParserException($msg); + } + + /** + * Throws an inconsistency exception. + * @note This should not ever be called. It would be called if we + * extend the allowed values of HTMLPurifier_VarParser without + * updating subclasses. + * @param string $class + * @param int $type + * @throws HTMLPurifier_Exception + */ + protected function errorInconsistent($class, $type) + { + throw new HTMLPurifier_Exception( + "Inconsistency in $class: " . HTMLPurifier_VarParser::getTypeName($type) . + " not implemented" + ); + } + + /** + * Generic error for if a type didn't work. + * @param mixed $var + * @param int $type + */ + protected function errorGeneric($var, $type) + { + $vtype = gettype($var); + $this->error("Expected type " . HTMLPurifier_VarParser::getTypeName($type) . ", got $vtype"); + } + + /** + * @param int $type + * @return string + */ + public static function getTypeName($type) + { + static $lookup; + if (!$lookup) { + // Lazy load the alternative lookup table + $lookup = array_flip(HTMLPurifier_VarParser::$types); + } + if (!isset($lookup[$type])) { + return 'unknown'; + } + return $lookup[$type]; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Flexible.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Flexible.php new file mode 100644 index 0000000000..b15016c5b2 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Flexible.php @@ -0,0 +1,130 @@ + $j) { + $var[$i] = trim($j); + } + if ($type === self::HASH) { + // key:value,key2:value2 + $nvar = array(); + foreach ($var as $keypair) { + $c = explode(':', $keypair, 2); + if (!isset($c[1])) { + continue; + } + $nvar[trim($c[0])] = trim($c[1]); + } + $var = $nvar; + } + } + if (!is_array($var)) { + break; + } + $keys = array_keys($var); + if ($keys === array_keys($keys)) { + if ($type == self::ALIST) { + return $var; + } elseif ($type == self::LOOKUP) { + $new = array(); + foreach ($var as $key) { + $new[$key] = true; + } + return $new; + } else { + break; + } + } + if ($type === self::ALIST) { + trigger_error("Array list did not have consecutive integer indexes", E_USER_WARNING); + return array_values($var); + } + if ($type === self::LOOKUP) { + foreach ($var as $key => $value) { + if ($value !== true) { + trigger_error( + "Lookup array has non-true value at key '$key'; " . + "maybe your input array was not indexed numerically", + E_USER_WARNING + ); + } + $var[$key] = true; + } + } + return $var; + default: + $this->errorInconsistent(__CLASS__, $type); + } + $this->errorGeneric($var, $type); + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Native.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Native.php new file mode 100644 index 0000000000..f11c318efb --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParser/Native.php @@ -0,0 +1,38 @@ +evalExpression($var); + } + + /** + * @param string $expr + * @return mixed + * @throws HTMLPurifier_VarParserException + */ + protected function evalExpression($expr) + { + $var = null; + $result = eval("\$var = $expr;"); + if ($result === false) { + throw new HTMLPurifier_VarParserException("Fatal error in evaluated code"); + } + return $var; + } +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParserException.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParserException.php new file mode 100644 index 0000000000..5df3414959 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/library/HTMLPurifier/VarParserException.php @@ -0,0 +1,11 @@ +front = $front; + $this->back = $back; + } + + /** + * Creates a zipper from an array, with a hole in the + * 0-index position. + * @param Array to zipper-ify. + * @return Tuple of zipper and element of first position. + */ + static public function fromArray($array) { + $z = new self(array(), array_reverse($array)); + $t = $z->delete(); // delete the "dummy hole" + return array($z, $t); + } + + /** + * Convert zipper back into a normal array, optionally filling in + * the hole with a value. (Usually you should supply a $t, unless you + * are at the end of the array.) + */ + public function toArray($t = NULL) { + $a = $this->front; + if ($t !== NULL) $a[] = $t; + for ($i = count($this->back)-1; $i >= 0; $i--) { + $a[] = $this->back[$i]; + } + return $a; + } + + /** + * Move hole to the next element. + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function next($t) { + if ($t !== NULL) array_push($this->front, $t); + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Iterated hole advancement. + * @param $t Element to fill hole with + * @param $i How many forward to advance hole + * @return Original contents of new hole, i away + */ + public function advance($t, $n) { + for ($i = 0; $i < $n; $i++) { + $t = $this->next($t); + } + return $t; + } + + /** + * Move hole to the previous element + * @param $t Element to fill hole with + * @return Original contents of new hole. + */ + public function prev($t) { + if ($t !== NULL) array_push($this->back, $t); + return empty($this->front) ? NULL : array_pop($this->front); + } + + /** + * Delete contents of current hole, shifting hole to + * next element. + * @return Original contents of new hole. + */ + public function delete() { + return empty($this->back) ? NULL : array_pop($this->back); + } + + /** + * Returns true if we are at the end of the list. + * @return bool + */ + public function done() { + return empty($this->back); + } + + /** + * Insert element before hole. + * @param Element to insert + */ + public function insertBefore($t) { + if ($t !== NULL) array_push($this->front, $t); + } + + /** + * Insert element after hole. + * @param Element to insert + */ + public function insertAfter($t) { + if ($t !== NULL) array_push($this->back, $t); + } + + /** + * Splice in multiple elements at hole. Functional specification + * in terms of array_splice: + * + * $arr1 = $arr; + * $old1 = array_splice($arr1, $i, $delete, $replacement); + * + * list($z, $t) = HTMLPurifier_Zipper::fromArray($arr); + * $t = $z->advance($t, $i); + * list($old2, $t) = $z->splice($t, $delete, $replacement); + * $arr2 = $z->toArray($t); + * + * assert($old1 === $old2); + * assert($arr1 === $arr2); + * + * NB: the absolute index location after this operation is + * *unchanged!* + * + * @param Current contents of hole. + */ + public function splice($t, $delete, $replacement) { + // delete + $old = array(); + $r = $t; + for ($i = $delete; $i > 0; $i--) { + $old[] = $r; + $r = $this->delete(); + } + // insert + for ($i = count($replacement)-1; $i >= 0; $i--) { + $this->insertAfter($r); + $r = $replacement[$i]; + } + return array($old, $r); + } +} diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/package.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/package.php new file mode 100644 index 0000000000..bfef93622d --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/package.php @@ -0,0 +1,61 @@ +setOptions( + array( + 'baseinstalldir' => '/', + 'packagefile' => 'package.xml', + 'packagedirectory' => realpath(dirname(__FILE__) . '/library'), + 'filelistgenerator' => 'file', + 'include' => array('*'), + 'dir_roles' => array('/' => 'php'), // hack to put *.ser files in the right place + 'ignore' => array( + 'HTMLPurifier.standalone.php', + 'HTMLPurifier.path.php', + '*.tar.gz', + '*.tgz', + 'standalone/' + ), + ) +); + +$pkg->setPackage('HTMLPurifier'); +$pkg->setLicense('LGPL', 'http://www.gnu.org/licenses/lgpl.html'); +$pkg->setSummary('Standards-compliant HTML filter'); +$pkg->setDescription( + 'HTML Purifier is an HTML filter that will remove all malicious code + (better known as XSS) with a thoroughly audited, secure yet permissive + whitelist and will also make sure your documents are standards + compliant.' +); + +$pkg->addMaintainer('lead', 'ezyang', 'Edward Z. Yang', 'admin@htmlpurifier.org', 'yes'); + +$version = trim(file_get_contents('VERSION')); +$api_version = substr($version, 0, strrpos($version, '.')); + +$pkg->setChannel('htmlpurifier.org'); +$pkg->setAPIVersion($api_version); +$pkg->setAPIStability('stable'); +$pkg->setReleaseVersion($version); +$pkg->setReleaseStability('stable'); + +$pkg->addRelease(); + +$pkg->setNotes(file_get_contents('WHATSNEW')); +$pkg->setPackageType('php'); + +$pkg->setPhpDep('5.0.0'); +$pkg->setPearinstallerDep('1.4.3'); + +$pkg->generateContents(); + +$pkg->writePackageFile(); + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/phpdoc.ini b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/phpdoc.ini new file mode 100644 index 0000000000..c4c3723538 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/phpdoc.ini @@ -0,0 +1,102 @@ +;; phpDocumentor parse configuration file +;; +;; This file is designed to cut down on repetitive typing on the command-line or web interface +;; You can copy this file to create a number of configuration files that can be used with the +;; command-line switch -c, as in phpdoc -c default.ini or phpdoc -c myini.ini. The web +;; interface will automatically generate a list of .ini files that can be used. +;; +;; default.ini is used to generate the online manual at http://www.phpdoc.org/docs +;; +;; ALL .ini files must be in the user subdirectory of phpDocumentor with an extension of .ini +;; +;; Copyright 2002, Greg Beaver +;; +;; WARNING: do not change the name of any command-line parameters, phpDocumentor will ignore them + +[Parse Data] +;; title of all the documentation +;; legal values: any string +title = HTML Purifier API Documentation + +;; parse files that start with a . like .bash_profile +;; legal values: true, false +hidden = false + +;; show elements marked @access private in documentation by setting this to on +;; legal values: on, off +parseprivate = off + +;; parse with javadoc-like description (first sentence is always the short description) +;; legal values: on, off +javadocdesc = on + +;; add any custom @tags separated by commas here +;; legal values: any legal tagname separated by commas. +;customtags = mytag1,mytag2 + +;; This is only used by the XML:DocBook/peardoc2 converter +defaultcategoryname = Documentation + +;; what is the main package? +;; legal values: alphanumeric string plus - and _ +defaultpackagename = HTMLPurifier + +;; output any parsing information? set to on for cron jobs +;; legal values: on +;quiet = on + +;; parse a PEAR-style repository. Do not turn this on if your project does +;; not have a parent directory named "pear" +;; legal values: on/off +;pear = on + +;; where should the documentation be written? +;; legal values: a legal path +target = docs/phpdoc + +;; Which files should be parsed out as special documentation files, such as README, +;; INSTALL and CHANGELOG? This overrides the default files found in +;; phpDocumentor.ini (this file is not a user .ini file, but the global file) +readmeinstallchangelog = README, INSTALL, NEWS, WYSIWYG, SLOW, LICENSE, CREDITS + +;; limit output to the specified packages, even if others are parsed +;; legal values: package names separated by commas +;packageoutput = package1,package2 + +;; comma-separated list of files to parse +;; legal values: paths separated by commas +;filename = /path/to/file1,/path/to/file2,fileincurrentdirectory + +;; comma-separated list of directories to parse +;; legal values: directory paths separated by commas +;directory = /path1,/path2,.,..,subdirectory +;directory = /home/jeichorn/cvs/pear +directory = . + +;; template base directory (the equivalent directory of /phpDocumentor) +;templatebase = /path/to/my/templates + +;; directory to find any example files in through @example and {@example} tags +;examplesdir = /path/to/my/templates + +;; comma-separated list of files, directories or wildcards ? and * (any wildcard) to ignore +;; legal values: any wildcard strings separated by commas +;ignore = /path/to/ignore*,*list.php,myfile.php,subdirectory/ +ignore = *tests*,*benchmarks*,*docs*,*test-settings.php,*configdoc*,*maintenance*,*smoketests*,*standalone*,*.svn*,*conf* + +sourcecode = on + +;; comma-separated list of Converters to use in outputformat:Convertername:templatedirectory format +;; legal values: HTML:frames:default,HTML:frames:l0l33t,HTML:frames:phpdoc.de,HTML:frames:phphtmllib, +;; HTML:frames:earthli, +;; HTML:frames:DOM/default,HTML:frames:DOM/l0l33t,HTML:frames:DOM/phpdoc.de, +;; HTML:frames:DOM/phphtmllib,HTML:frames:DOM/earthli +;; HTML:Smarty:default,HTML:Smarty:PHP,HTML:Smarty:HandS +;; PDF:default:default,CHM:default:default,XML:DocBook/peardoc2:default +output=HTML:frames:default + +;; turn this option on if you want highlighted source code for every file +;; legal values: on/off +sourcecode = on + +; vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/modx.txt b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/modx.txt new file mode 100644 index 0000000000..0763821b50 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/modx.txt @@ -0,0 +1,112 @@ + +MODx Plugin + +MODx is an open source PHP application framework. +I first came across them in my referrer logs when tillda asked if anyone +could implement an HTML Purifier plugin. This forum thread + eventually resulted +in the fruition of this plugin that davidm says, "is on top of my favorite +list." HTML Purifier goes great with WYSIWYG editors! + + + +1. Credits + +PaulGregory wrote the overall structure of the code. I added the +slashes hack. + + + +2. Install + +First, you need to place HTML Purifier library somewhere. The code here +assumes that you've placed in MODx's assets/plugins/htmlpurifier (no version +number). + +Log into the manager, and navigate: + +Resources > Manage Resources > Plugins tab > New Plugin + +Type in a name (probably HTML Purifier), and copy paste this code into the +textarea: + +-------------------------------------------------------------------------------- +$e = &$modx->Event; +if ($e->name == 'OnBeforeDocFormSave') { + global $content; + + include_once '../assets/plugins/htmlpurifier/library/HTMLPurifier.auto.php'; + $purifier = new HTMLPurifier(); + + static $magic_quotes = null; + if ($magic_quotes === null) { + // this is an ugly hack because this hook hasn't + // had the backslashes removed yet when magic_quotes_gpc is on, + // but HTMLPurifier must not have the quotes slashed. + $magic_quotes = get_magic_quotes_gpc(); + } + + if ($magic_quotes) $content = stripslashes($content); + $content = $purifier->purify($content); + if ($magic_quotes) $content = addslashes($content); +} +-------------------------------------------------------------------------------- + +Then navigate to the System Events tab and check "OnBeforeDocFormSave". +Save the plugin. HTML Purifier now is integrated! + + + +3. Making sure it works + +You can test HTML Purifier by deliberately putting in crappy HTML and seeing +whether or not it gets fixed. A better way is to put in something like this: + +
Il est bon
+ +...and seeing whether or not the content comes out as: + +
Il est bon
+ +(lang to xml:lang synchronization is one of the many features HTML Purifier +has). + + + +4. Caveat Emptor + +This code does not intercept save requests from the QuickEdit plugin, this may +be added in a later version. It also modifies things on save, so there's a +slight chance that HTML Purifier may make a boo-boo and accidently mess things +up (the original version is not saved). + +Finally, make sure that MODx is using UTF-8. If you are using, say, a French +localisation, you may be using Latin-1, if that's the case, configure +HTML Purifier properly like this: + +$config = HTMLPurifier_Config::createDefault(); +$config->set('Core', 'Encoding', 'ISO-8859-1'); // or whatever encoding +$purifier = new HTMLPurifier($config); + + + +5. Known Bugs + +'rn' characters sometimes mysteriously appear after purification. We are +currently investigating this issue. See: + + + +6. See Also + +A modified version of Jot 1.1.3 is available, which integrates with HTML +Purifier. You can check it out here: + + +X. Changelog + +2008-06-16 +- Updated code to work with 3.1.0 and later +- Add Known Bugs and See Also section + + vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/.gitignore b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/.gitignore new file mode 100644 index 0000000000..8325e09020 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/.gitignore @@ -0,0 +1,2 @@ +migrate.php +htmlpurifier/* diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/Changelog b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/Changelog new file mode 100644 index 0000000000..9f939e54ae --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/Changelog @@ -0,0 +1,27 @@ +Changelog HTMLPurifier : Phorum Mod +||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||| + += KEY ==================== + # Breaks back-compat + ! Feature + - Bugfix + + Sub-comment + . Internal change +========================== + +Version 4.0.0 for Phorum 5.2, released July 9, 2009 +# Works only with HTML Purifier 4.0.0 +! Better installation documentation +- Fixed double encoded quotes +- Fixed fatal error when migrate.php is blank + +Version 3.0.0 for Phorum 5.2, released January 12, 2008 +# WYSIWYG and suppress_message options are now configurable via web + interface. +- Module now compatible with Phorum 5.2, primary bugs were in migration + code as well as signature and edit message handling. This module is NOT + compatible with Phorum 5.1. +- Buggy WYSIWYG mode refined +. AutoFormatParam added to list of default configuration namespaces + + vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/INSTALL b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/INSTALL new file mode 100644 index 0000000000..23c76fc5c6 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/INSTALL @@ -0,0 +1,84 @@ + +Install + How to install the Phorum HTML Purifier plugin + +0. PREREQUISITES +---------------- +This Phorum module only works on PHP5 and with HTML Purifier 4.0.0 +or later. + +1. UNZIP +-------- +Unzip phorum-htmlpurifier-x.y.z, producing an htmlpurifier folder. +You've already done this step if you're reading this! + +2. MOVE +------- +Move the htmlpurifier folder to the mods/ folder of your Phorum +installation, so the directory structure looks like: + +phorum/ + mods/ + htmlpurifier/ + INSTALL - this install file + info.txt, ... - the module files + htmlpurifier/ + +3. INSTALL HTML PURIFIER +------------------------ +Download and unzip HTML Purifier . Place the contents of +the library/ folder in the htmlpurifier/htmlpurifier folder. Your directory +structure will look like: + +phorum/ + mods/ + htmlpurifier/ + htmlpurifier/ + HTMLPurifier.auto.php + ... - other files + HTMLPurifier/ + +Advanced users: + If you have HTML Purifier installed elsewhere on your server, + all you need is an HTMLPurifier.auto.php file in the library folder which + includes the HTMLPurifier.auto.php file in your install. + +4. MIGRATE +---------- +If you're setting up a new Phorum installation, all you need to do is create +a blank migrate.php file in the htmlpurifier module folder (NOT the library +folder. + +If you have an old Phorum installation and was using BBCode, +copy migrate.bbcode.php to migrate.php. If you were using a different input +format, follow the instructions in migrate.bbcode.php to create your own custom +migrate.php file. + +Your directory structure should now look like this: + +phorum/ + mods/ + htmlpurifier/ + migrate.php + +5. ENABLE +--------- +Navigate to your Phorum admin panel at http://example.com/phorum/admin.php, +click on Global Settings > Modules, scroll to "HTML Purifier Phorum Mod" and +turn it On. + +6. MIGRATE SIGNATURES +--------------------- +If you're setting up a new Phorum installation, skip this step. + +If you allowed your users to make signatures, navigate to the module settings +page of HTML Purifier (Global Settings > Modules > HTML Purifier Phorum Mod > +Configure), type in "yes" in the "Confirm" box, and press "Migrate." + +ONLY DO THIS ONCE! BE SURE TO BACK UP YOUR DATABASE! + +7. CONFIGURE +------------ +Configure using Edit settings. See that page for more information. + + vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/README b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/README new file mode 100644 index 0000000000..0524ed39db --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/README @@ -0,0 +1,45 @@ + +HTML Purifier Phorum Mod - Filter your HTML the Standards-Compliant Way! + +This Phorum mod enables HTML posting on Phorum. Under normal circumstances, +this would cause a huge security risk, but because we are running +HTML through HTML Purifier, output is guaranteed to be XSS free and +standards-compliant. + +This mod requires HTML input, and previous markup languages need to be +converted accordingly. Thus, it is vital that you create a 'migrate.php' +file that works with your installation. If you're using the built-in +BBCode formatting, simply move migrate.bbcode.php to that place; for +other markup languages, consult said file for instructions on how +to adapt it to your needs. + + -- NOTE ------------------------------------------------- + You can also run this module in parallel with another + formatting module; this module attempts to place itself + at the end of the filtering chain. However, if any + previous modules produce insecure HTML (for instance, + a JavaScript email obfuscator) they will get cleaned. + +This module will not work if 'migrate.php' is not created, and an improperly +made migration file may *CORRUPT* Phorum, so please take your time to +do this correctly. It should go without saying to *BACKUP YOUR DATABASE* +before attempting anything here. If no migration is necessary, you can +simply create a blank migrate.php file. HTML Purifier is smart and will +not re-migrate already processed messages. However, the original code +is irretrievably lost (we may change this in the future.) + +This module will not automatically migrate user signatures, because this +process may take a long time. After installing the HTML Purifier module and +then configuring 'migrate.php', navigate to Settings and click 'Migrate +Signatures' to migrate all user signatures to HTML. + +All of HTML Purifier's usual functions are configurable via the mod settings +page. If you require custom configuration, create config.php file in +the mod directory that edits a $config variable. Be sure, also, to +set $PHORUM['mod_htmlpurifier']['wysiwyg'] to TRUE if you are using a +WYSIWYG editor (you can do this through a common hook or the web +configuration form). + +Visit HTML Purifier at . + + vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/config.default.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/config.default.php new file mode 100644 index 0000000000..e047c0b423 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/config.default.php @@ -0,0 +1,57 @@ +set('HTML.Allowed', + // alphabetically sorted +'a[href|title] +abbr[title] +acronym[title] +b +blockquote[cite] +br +caption +cite +code +dd +del +dfn +div +dl +dt +em +i +img[src|alt|title|class] +ins +kbd +li +ol +p +pre +s +strike +strong +sub +sup +table +tbody +td +tfoot +th +thead +tr +tt +u +ul +var'); +$config->set('AutoFormat.AutoParagraph', true); +$config->set('AutoFormat.Linkify', true); +$config->set('HTML.Doctype', 'XHTML 1.0 Transitional'); +$config->set('Core.AggressivelyFixLt', true); +$config->set('Core.Encoding', $GLOBALS['PHORUM']['DATA']['CHARSET']); // we'll change this eventually +if (strtolower($GLOBALS['PHORUM']['DATA']['CHARSET']) !== 'utf-8') { + $config->set('Core.EscapeNonASCIICharacters', true); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/htmlpurifier.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/htmlpurifier.php new file mode 100644 index 0000000000..f66d8c36cd --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/htmlpurifier.php @@ -0,0 +1,316 @@ + $message){ + if(isset($message['body'])) { + + if ($message_id) { + // we're dealing with a real message, not a fake, so + // there a number of shortcuts that can be taken + + if (isset($message['meta']['htmlpurifier_light'])) { + // format hook was called outside of Phorum's normal + // functions, do the abridged purification + $data[$message_id]['body'] = $purifier->purify($message['body']); + continue; + } + + if (!empty($PHORUM['args']['purge'])) { + // purge the cache, must be below the following if + unset($message['meta']['body_cache']); + } + + if ( + isset($message['meta']['body_cache']) && + isset($message['meta']['body_cache_serial']) && + $message['meta']['body_cache_serial'] == $cache_serial + ) { + // cached version is present, bail out early + $data[$message_id]['body'] = base64_decode($message['meta']['body_cache']); + continue; + } + } + + // migration might edit this array, that's why it's defined + // so early + $updated_message = array(); + + // create the $body variable + if ( + $message_id && // message must be real to migrate + !isset($message['meta']['body_cache_serial']) + ) { + // perform migration + $fake_data = array(); + list($signature, $edit_message) = phorum_htmlpurifier_remove_sig_and_editmessage($message); + $fake_data[$message_id] = $message; + $fake_data = phorum_htmlpurifier_migrate($fake_data); + $body = $fake_data[$message_id]['body']; + $body = str_replace("\n", "\n", $body); + $updated_message['body'] = $body; // save it in + $body .= $signature . $edit_message; // add it back in + } else { + // reverse Phorum's pre-processing + $body = $message['body']; + // order is important + $body = str_replace("\n", "\n", $body); + $body = str_replace(array('<','>','&', '"'), array('<','>','&','"'), $body); + if (!$message_id && defined('PHORUM_CONTROL_CENTER')) { + // we're in control.php, so it was double-escaped + $body = str_replace(array('<','>','&', '"'), array('<','>','&','"'), $body); + } + } + + $body = $purifier->purify($body); + + // dynamically update the cache (MUST BE DONE HERE!) + // this is inefficient because it's one db call per + // cache miss, but once the cache is in place things are + // a lot zippier. + + if ($message_id) { // make sure it's not a fake id + $updated_message['meta'] = $message['meta']; + $updated_message['meta']['body_cache'] = base64_encode($body); + $updated_message['meta']['body_cache_serial'] = $cache_serial; + phorum_db_update_message($message_id, $updated_message); + } + + // must not get overloaded until after we cache it, otherwise + // we'll inadvertently change the original text + $data[$message_id]['body'] = $body; + + } + } + + return $data; +} + +// ----------------------------------------------------------------------- +// This is fragile code, copied from read.php:596 (Phorum 5.2.6). Please +// keep this code in-sync with Phorum + +/** + * Generates a signature based on a message array + */ +function phorum_htmlpurifier_generate_sig($row) +{ + $phorum_sig = ''; + if(isset($row["user"]["signature"]) + && isset($row['meta']['show_signature']) && $row['meta']['show_signature']==1){ + $phorum_sig=trim($row["user"]["signature"]); + if(!empty($phorum_sig)){ + $phorum_sig="\n\n$phorum_sig"; + } + } + return $phorum_sig; +} + +/** + * Generates an edit message based on a message array + */ +function phorum_htmlpurifier_generate_editmessage($row) +{ + $PHORUM = $GLOBALS['PHORUM']; + $editmessage = ''; + if(isset($row['meta']['edit_count']) && $row['meta']['edit_count'] > 0) { + $editmessage = str_replace ("%count%", $row['meta']['edit_count'], $PHORUM["DATA"]["LANG"]["EditedMessage"]); + $editmessage = str_replace ("%lastedit%", phorum_date($PHORUM["short_date_time"],$row['meta']['edit_date']), $editmessage); + $editmessage = str_replace ("%lastuser%", $row['meta']['edit_username'], $editmessage); + $editmessage = "\n\n\n\n$editmessage"; + } + return $editmessage; +} + +// End fragile code +// ----------------------------------------------------------------------- + +/** + * Removes the signature and edit message from a message + * @param $row Message passed by reference + */ +function phorum_htmlpurifier_remove_sig_and_editmessage(&$row) +{ + $signature = phorum_htmlpurifier_generate_sig($row); + $editmessage = phorum_htmlpurifier_generate_editmessage($row); + $replacements = array(); + // we need to remove add as that is the form these + // extra bits are in. + if ($signature) $replacements[str_replace("\n", "\n", $signature)] = ''; + if ($editmessage) $replacements[str_replace("\n", "\n", $editmessage)] = ''; + $row['body'] = strtr($row['body'], $replacements); + return array($signature, $editmessage); +} + +/** + * Indicate that data is fully HTML and not from migration, invalidate + * previous caches + * @note This function could generate the actual cache entries, but + * since there's data missing that must be deferred to the first read + */ +function phorum_htmlpurifier_posting($message) +{ + $PHORUM = $GLOBALS["PHORUM"]; + unset($message['meta']['body_cache']); // invalidate the cache + $message['meta']['body_cache_serial'] = $PHORUM['mod_htmlpurifier']['body_cache_serial']; + return $message; +} + +/** + * Overload quoting mechanism to prevent default, mail-style quote from happening + */ +function phorum_htmlpurifier_quote($array) +{ + $PHORUM = $GLOBALS["PHORUM"]; + $purifier =& HTMLPurifier::getInstance(); + $text = $purifier->purify($array[1]); + $source = htmlspecialchars($array[0]); + return "
\n$text\n
"; +} + +/** + * Ensure that our format hook is processed last. Also, loads the library. + * @credits + */ +function phorum_htmlpurifier_common() +{ + require_once(dirname(__FILE__).'/htmlpurifier/HTMLPurifier.auto.php'); + require(dirname(__FILE__).'/init-config.php'); + + $config = phorum_htmlpurifier_get_config(); + HTMLPurifier::getInstance($config); + + // increment revision.txt if you want to invalidate the cache + $GLOBALS['PHORUM']['mod_htmlpurifier']['body_cache_serial'] = $config->getSerial(); + + // load migration + if (file_exists(dirname(__FILE__) . '/migrate.php')) { + include(dirname(__FILE__) . '/migrate.php'); + } else { + echo 'Error: No migration path specified for HTML Purifier, please check + modes/htmlpurifier/migrate.bbcode.php for instructions on + how to migrate from your previous markup language.'; + exit; + } + + if (!function_exists('phorum_htmlpurifier_migrate')) { + // Dummy function + function phorum_htmlpurifier_migrate($data) {return $data;} + } + +} + +/** + * Pre-emptively performs purification if it looks like a WYSIWYG editor + * is being used + */ +function phorum_htmlpurifier_before_editor($message) +{ + if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'])) { + if (!empty($message['body'])) { + $body = $message['body']; + // de-entity-ize contents + $body = str_replace(array('<','>','&'), array('<','>','&'), $body); + $purifier =& HTMLPurifier::getInstance(); + $body = $purifier->purify($body); + // re-entity-ize contents + $body = htmlspecialchars($body, ENT_QUOTES, $GLOBALS['PHORUM']['DATA']['CHARSET']); + $message['body'] = $body; + } + } + return $message; +} + +function phorum_htmlpurifier_editor_after_subject() +{ + // don't show this message if it's a WYSIWYG editor, since it will + // then be handled automatically + if (!empty($GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'])) { + $i = $GLOBALS['PHORUM']['DATA']['MODE']; + if ($i == 'quote' || $i == 'edit' || $i == 'moderation') { + ?> +
+
+ Notice: HTML has been scrubbed for your safety. + If you would like to see the original, turn off WYSIWYG mode + (consult your administrator for details.) +
+
+
+
+ HTML input is enabled. Make sure you escape all HTML and + angled brackets with < and >. +
config; + if ($config->get('AutoFormat.AutoParagraph')) { + ?>
+ Auto-paragraphing is enabled. Double + newlines will be converted to paragraphs; for single + newlines, use the pre tag. +
getDefinition('HTML'); + $allowed = array(); + foreach ($html_definition->info as $name => $x) $allowed[] = "$name"; + sort($allowed); + $allowed_text = implode(', ', $allowed); + ?>
Allowed tags: .
+
+
+ For inputting literal code such as HTML and PHP for display, use + CDATA tags to auto-escape your angled brackets, and pre + to preserve newlines: +
+
<pre><![CDATA[ +Place code here +]]></pre>
+
+ Power users, you can hide this notice with: +
.htmlpurifier-help {display:none;}
+
+
'; +phorum_htmlpurifier_show_form(); + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/form.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/form.php new file mode 100644 index 0000000000..9b6ad5f39e --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/form.php @@ -0,0 +1,95 @@ +hidden("module", "modsettings"); + $frm->hidden("mod", "htmlpurifier"); // this is the directory name that the Settings file lives in + + if (!empty($error)){ + echo "$error
"; + } + + $frm->addbreak("Edit settings for the HTML Purifier module"); + + $frm->addMessage('
The box below sets $PHORUM[\'mod_htmlpurifier\'][\'wysiwyg\']. + When checked, contents sent for edit are now purified and the + informative message is disabled. If your WYSIWYG editor is disabled for + admin edits, you can safely keep this unchecked.
'); + $frm->addRow('Use WYSIWYG?', $frm->checkbox('wysiwyg', '1', '', $PHORUM['mod_htmlpurifier']['wysiwyg'])); + + $frm->addMessage('
The box below sets $PHORUM[\'mod_htmlpurifier\'][\'suppress_message\'], + which removes the big how-to use + HTML Purifier message.
'); + $frm->addRow('Suppress information?', $frm->checkbox('suppress_message', '1', '', $PHORUM['mod_htmlpurifier']['suppress_message'])); + + $frm->addMessage('
Click on directive links to read what each option does + (links do not open in new windows).
+
For more flexibility (for instance, you want to edit the full + range of configuration directives), you can create a config.php + file in your mods/htmlpurifier/ directory. Doing so will, + however, make the web configuration interface unavailable.
'); + + require_once 'HTMLPurifier/Printer/ConfigForm.php'; + $htmlpurifier_form = new HTMLPurifier_Printer_ConfigForm('config', 'http://htmlpurifier.org/live/configdoc/plain.html#%s'); + $htmlpurifier_form->setTextareaDimensions(23, 7); // widen a little, since we have space + + $frm->addMessage($htmlpurifier_form->render( + $config, $PHORUM['mod_htmlpurifier']['directives'], false)); + + $frm->addMessage("Warning: Changing HTML Purifier's configuration will invalidate + the cache. Expect to see a flurry of database activity after you change + any of these settings."); + + $frm->addrow('Reset to defaults:', $frm->checkbox("reset", "1", "", false)); + + // hack to include extra styling + echo ''; + $js = $htmlpurifier_form->getJavaScript(); + echo ''; + + $frm->show(); +} + +function phorum_htmlpurifier_show_config_info() +{ + global $PHORUM; + + // update mod_htmlpurifier for housekeeping + phorum_htmlpurifier_commit_settings(); + + // politely tell user how to edit settings manually +?> +
How to edit settings for HTML Purifier module
+
+ A config.php file exists in your mods/htmlpurifier/ + directory. This file contains your custom configuration: in order to + change it, please navigate to that file and edit it accordingly. + You can also set $GLOBALS['PHORUM']['mod_htmlpurifier']['wysiwyg'] + or $GLOBALS['PHORUM']['mod_htmlpurifier']['suppress_message'] +
+
+ To use the web interface, delete config.php (or rename it to + config.php.bak). +
+
+ Warning: Changing HTML Purifier's configuration will invalidate + the cache. Expect to see a flurry of database activity after you change + any of these settings. +
+hidden("module", "modsettings"); + $frm->hidden("mod", "htmlpurifier"); + $frm->hidden("migrate-sigs", "1"); + $frm->addbreak("Migrate user signatures to HTML"); + $frm->addMessage('This operation will migrate your users signatures + to HTML. This process is irreversible and must only be performed once. + Type in yes in the confirmation field to migrate.'); + if (!file_exists(dirname(__FILE__) . '/../migrate.php')) { + $frm->addMessage('Migration file does not exist, cannot migrate signatures. + Please check migrate.bbcode.php on how to create an appropriate file.'); + } else { + $frm->addrow('Confirm:', $frm->text_box("confirmation", "")); + } + $frm->show(); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/migrate-sigs.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/migrate-sigs.php new file mode 100644 index 0000000000..5ea9cd0b81 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/migrate-sigs.php @@ -0,0 +1,79 @@ +$PHORUM["mod_htmlpurifier"])); + $offset = 1; + } elseif (!empty($_GET['migrate-sigs']) && $PHORUM['mod_htmlpurifier']['migrate-sigs']) { + $offset = (int) $_GET['migrate-sigs']; + } + return $offset; +} + +function phorum_htmlpurifier_migrate_sigs($offset) +{ + global $PHORUM; + + if(!$offset) return; // bail out quick if $offset == 0 + + // theoretically, we could get rid of this multi-request + // doo-hickery if safe mode is off + @set_time_limit(0); // attempt to let this run + $increment = $PHORUM['mod_htmlpurifier']['migrate-sigs-increment']; + + require_once(dirname(__FILE__) . '/../migrate.php'); + // migrate signatures + // do this in batches so we don't run out of time/space + $end = $offset + $increment; + $user_ids = array(); + for ($i = $offset; $i < $end; $i++) { + $user_ids[] = $i; + } + $userinfos = phorum_db_user_get_fields($user_ids, 'signature'); + foreach ($userinfos as $i => $user) { + if (empty($user['signature'])) continue; + $sig = $user['signature']; + // perform standard Phorum processing on the sig + $sig = str_replace(array("&","<",">"), array("&","<",">"), $sig); + $sig = preg_replace("/<((http|https|ftp):\/\/[a-z0-9;\/\?:@=\&\$\-_\.\+!*',~%]+?)>/i", "$1", $sig); + // prepare fake data to pass to migration function + $fake_data = array(array("author"=>"", "email"=>"", "subject"=>"", 'body' => $sig)); + list($fake_message) = phorum_htmlpurifier_migrate($fake_data); + $user['signature'] = $fake_message['body']; + if (!phorum_api_user_save($user)) { + exit('Error while saving user data'); + } + } + unset($userinfos); // free up memory + + // query for highest ID in database + $type = $PHORUM['DBCONFIG']['type']; + $sql = "select MAX(user_id) from {$PHORUM['user_table']}"; + $row = phorum_db_interact(DB_RETURN_ROW, $sql); + $top_id = (int) $row[0]; + + $offset += $increment; + if ($offset > $top_id) { // test for end condition + echo 'Migration finished'; + $PHORUM['mod_htmlpurifier']['migrate-sigs'] = false; + phorum_htmlpurifier_commit_settings(); + return true; + } + $host = $_SERVER['HTTP_HOST']; + $uri = rtrim(dirname($_SERVER['PHP_SELF']), '/\\'); + $extra = 'admin.php?module=modsettings&mod=htmlpurifier&migrate-sigs=' . $offset; + // relies on output buffering to work + header("Location: http://$host$uri/$extra"); + exit; + +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/save.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/save.php new file mode 100644 index 0000000000..2aefaf83a0 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/plugins/phorum/settings/save.php @@ -0,0 +1,29 @@ +mods/htmlpurifier/config.php already exists. To change + settings, edit that file. To use the web form, delete that file.
"; + } else { + $config = phorum_htmlpurifier_get_config(true); + if (!isset($_POST['reset'])) $config->mergeArrayFromForm($_POST, 'config', $PHORUM['mod_htmlpurifier']['directives']); + $PHORUM['mod_htmlpurifier']['config'] = $config->getAll(); + } + $PHORUM['mod_htmlpurifier']['wysiwyg'] = !empty($_POST['wysiwyg']); + $PHORUM['mod_htmlpurifier']['suppress_message'] = !empty($_POST['suppress_message']); + if(!phorum_htmlpurifier_commit_settings()){ + $error="Database error while updating settings."; + } else { + echo "Settings Updated
"; + } +} + +function phorum_htmlpurifier_commit_settings() +{ + global $PHORUM; + return phorum_db_update_settings(array("mod_htmlpurifier"=>$PHORUM["mod_htmlpurifier"])); +} + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/release1-update.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/release1-update.php new file mode 100644 index 0000000000..834d385676 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/release1-update.php @@ -0,0 +1,110 @@ + 1) { + echo 'More than one release declaration in NEWS replaced' . PHP_EOL; + exit; + } + file_put_contents('NEWS', $news_c); +} + +// ...in Doxyfile +$doxyfile_c = preg_replace( + '/(?<=PROJECT_NUMBER {9}= )[^\s]+/m', // brittle + $version, + file_get_contents('Doxyfile'), + 1, $c +); +if (!$c) { + echo 'Could not update Doxyfile, missing PROJECT_NUMBER.' . PHP_EOL; + exit; +} +file_put_contents('Doxyfile', $doxyfile_c); + +// ...in HTMLPurifier.php +$htmlpurifier_c = file_get_contents('library/HTMLPurifier.php'); +$htmlpurifier_c = preg_replace( + '/HTML Purifier .+? - /', + "HTML Purifier $version - ", + $htmlpurifier_c, + 1, $c +); +if (!$c) { + echo 'Could not update HTMLPurifier.php, missing HTML Purifier [version] header.' . PHP_EOL; + exit; +} +$htmlpurifier_c = preg_replace( + '/public \$version = \'.+?\';/', + "public \$version = '$version';", + $htmlpurifier_c, + 1, $c +); +if (!$c) { + echo 'Could not update HTMLPurifier.php, missing public $version.' . PHP_EOL; + exit; +} +$htmlpurifier_c = preg_replace( + '/const VERSION = \'.+?\';/', + "const VERSION = '$version';", + $htmlpurifier_c, + 1, $c +); +if (!$c) { + echo 'Could not update HTMLPurifier.php, missing const $version.' . PHP_EOL; + exit; +} +file_put_contents('library/HTMLPurifier.php', $htmlpurifier_c); + +$config_c = file_get_contents('library/HTMLPurifier/Config.php'); +$config_c = preg_replace( + '/public \$version = \'.+?\';/', + "public \$version = '$version';", + $config_c, + 1, $c +); +if (!$c) { + echo 'Could not update Config.php, missing public $version.' . PHP_EOL; + exit; +} +file_put_contents('library/HTMLPurifier/Config.php', $config_c); + +passthru('php maintenance/flush.php'); + +if ($is_dev) echo "Review changes, write something in WHATSNEW and FOCUS, and then commit with log 'Release $version.'" . PHP_EOL; +else echo "Numbers updated to dev, no other modifications necessary!"; + +// vim: et sw=4 sts=4 diff --git a/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/release2-tag.php b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/release2-tag.php new file mode 100644 index 0000000000..25e5300d81 --- /dev/null +++ b/wcfsetup/install/files/lib/system/api/ezyang/htmlpurifier/release2-tag.php @@ -0,0 +1,22 @@ +getHtmlInputFilter()->apply($html); + + } + + public function setHtmlInputFilter(IHtmlInputFilter $htmlInputFilter) { + $this->htmlInputFilter = $htmlInputFilter; + } + + /** + * @return IHtmlInputFilter + */ + public function getHtmlInputFilter() { + if ($this->htmlInputFilter === null) { + $this->htmlInputFilter = WCF::getDIContainer()->make(MessageHtmlInputFilter::class); + } + + return $this->htmlInputFilter; + } +} diff --git a/wcfsetup/install/files/lib/system/html/input/filter/IHtmlInputFilter.class.php b/wcfsetup/install/files/lib/system/html/input/filter/IHtmlInputFilter.class.php new file mode 100644 index 0000000000..f30d84fe4e --- /dev/null +++ b/wcfsetup/install/files/lib/system/html/input/filter/IHtmlInputFilter.class.php @@ -0,0 +1,12 @@ +getPurifier()->purify($html); + } + + /** + * @return \HTMLPurifier + */ + protected function getPurifier() { + if (self::$purifier === null) { + $config = \HTMLPurifier_Config::createDefault(); + $this->setAttributeDefinitions($config); + self::$purifier = new \HTMLPurifier($config); + } + + return self::$purifier; + } + + protected function setAttributeDefinitions(\HTMLPurifier_Config $config) { + $definition = $config->getHTMLDefinition(true); + $definition->addAttribute('blockquote', 'data-quote-title', 'Text'); + $definition->addAttribute('blockquote', 'data-quote-url', 'URI'); + } +} \ No newline at end of file diff --git a/wcfsetup/install/files/lib/system/html/output/HtmlOutputNodeProcessor.class.php b/wcfsetup/install/files/lib/system/html/output/HtmlOutputNodeProcessor.class.php new file mode 100644 index 0000000000..3412314840 --- /dev/null +++ b/wcfsetup/install/files/lib/system/html/output/HtmlOutputNodeProcessor.class.php @@ -0,0 +1,78 @@ +document = new \DOMDocument(); + $this->document->loadHTML($html); + $this->nodeData = []; + } + + public function process() { + $quoteNode = WCF::getDIContainer()->get(QuoteHtmlOutputNode::class); + $quoteNode->process($this); + + $html = $this->document->saveHTML(); + + // remove nuisance added by PHP + $html = preg_replace('~^]+>\s~', '', $html); + $html = preg_replace('~$~', '', $html); + + /** @var IHtmlOutputNode $obj */ + foreach ($this->nodeData as $data) { + $obj = $data['object']; + $string = $obj->replaceTag($data['data']); + $html = preg_replace_callback('~(?P.*)~', function($matches) use ($string) { + $string = str_replace('', $matches['content'], $string); + + return $string; + }, $html); + + } + + return $html; + } + + public function getDocument() { + return $this->document; + } + + public function addNodeData(IHtmlOutputNode $htmlOutputNode, $nodeIdentifier, array $data) { + $this->nodeData[] = [ + 'data' => $data, + 'identifier' => $nodeIdentifier, + 'object' => $htmlOutputNode + ]; + } + + public function renameTag(\DOMElement $element, $tagName) { + $newElement = $this->document->createElement($tagName); + $element->parentNode->insertBefore($newElement, $element); + while ($element->hasChildNodes()) { + $newElement->appendChild($element->firstChild); + } + + $element->parentNode->removeChild($element); + + return $newElement; + } + + public function unwrapContent(\DOMElement $element) { + while ($element->hasChildNodes()) { + $element->parentNode->insertBefore($element->firstChild, $element); + } + + $element->parentNode->removeChild($element); + } +} diff --git a/wcfsetup/install/files/lib/system/html/output/HtmlOutputProcessor.class.php b/wcfsetup/install/files/lib/system/html/output/HtmlOutputProcessor.class.php new file mode 100644 index 0000000000..b483afabb0 --- /dev/null +++ b/wcfsetup/install/files/lib/system/html/output/HtmlOutputProcessor.class.php @@ -0,0 +1,22 @@ +htmlOutputNodeProcessor = $htmlOutputNodeProcessor; + } + + public function process($html) { + $this->htmlOutputNodeProcessor->load($html); + $html = $this->htmlOutputNodeProcessor->process(); + + return $html; + } +} diff --git a/wcfsetup/install/files/lib/system/html/output/node/IHtmlOutputNode.class.php b/wcfsetup/install/files/lib/system/html/output/node/IHtmlOutputNode.class.php new file mode 100644 index 0000000000..841f68e39c --- /dev/null +++ b/wcfsetup/install/files/lib/system/html/output/node/IHtmlOutputNode.class.php @@ -0,0 +1,10 @@ +applicationHandler = $applicationHandler; + } + + public function process(HtmlOutputNodeProcessor $htmlOutputNodeProcessor) { + $elements = $htmlOutputNodeProcessor->getDocument()->getElementsByTagName('blockquote'); + while ($elements->length) { + /** @var \DOMElement $blockquote */ + $blockquote = $elements->item(0); + + if ($blockquote->getAttribute('class') === 'quoteBox') { + $nodeIdentifier = StringUtil::getRandomID(); + $htmlOutputNodeProcessor->addNodeData($this, $nodeIdentifier, [ + 'title' => ($blockquote->hasAttribute('data-quote-title')) ? $blockquote->getAttribute('data-quote-title') : '', + 'url' => ($blockquote->hasAttribute('data-quote-url')) ? $blockquote->getAttribute('data-quote-url') : '' + ]); + + $htmlOutputNodeProcessor->renameTag($blockquote, 'wcfNode-' . $nodeIdentifier); + } + else { + $htmlOutputNodeProcessor->unwrapContent($blockquote); + } + } + } + + public function replaceTag(array $data) { + $externalQuoteLink = (!empty($data['url'])) ? !$this->applicationHandler->isInternalURL($data['url']) : false; + if (!$externalQuoteLink) { + $data['url'] = preg_replace('~^https://~', RouteHandler::getProtocol(), $data['url']); + } + + $quoteAuthorObject = null; + /* + * TODO: how should the author object be resolved? + * + if ($quoteAuthor && !$externalQuoteLink) { + $quoteAuthorLC = mb_strtolower(StringUtil::decodeHTML($quoteAuthor)); + foreach (MessageEmbeddedObjectManager::getInstance()->getObjects('com.woltlab.wcf.quote') as $user) { + if (mb_strtolower($user->username) == $quoteAuthorLC) { + $quoteAuthorObject = $user; + break; + } + } + } + */ + + WCF::getTPL()->assign(array( + 'quoteLink' => $data['url'], + 'quoteAuthor' => $data['title'], + 'quoteAuthorObject' => $quoteAuthorObject, + 'isExternalQuoteLink' => $externalQuoteLink + )); + return WCF::getTPL()->fetch('quoteMetaCode'); + } +} \ No newline at end of file