From 6bb8c1fcacda0f4f1d555058b52e9374269ab924 Mon Sep 17 00:00:00 2001 From: "Edward Z. Yang" Date: Tue, 24 Jun 2008 21:10:51 -0400 Subject: [PATCH] Handle CRLF discrepancies Signed-off-by: Edward Z. Yang --- docs/specimens/LICENSE | 16 +- library/HTMLPurifier.safe-includes.php | 378 +- .../schema/Attr.AllowedFrameTargets.txt | 22 +- .../ConfigSchema/schema/Attr.AllowedRel.txt | 16 +- .../ConfigSchema/schema/Attr.AllowedRev.txt | 16 +- .../schema/Attr.DefaultInvalidImage.txt | 16 +- .../schema/Attr.DefaultInvalidImageAlt.txt | 14 +- .../ConfigSchema/schema/Attr.DefaultTextDir.txt | 18 +- .../ConfigSchema/schema/Attr.EnableID.txt | 30 +- .../ConfigSchema/schema/Attr.IDBlacklist.txt | 8 +- .../ConfigSchema/schema/Attr.IDBlacklistRegexp.txt | 16 +- .../ConfigSchema/schema/Attr.IDPrefix.txt | 22 +- .../ConfigSchema/schema/Attr.IDPrefixLocal.txt | 26 +- library/HTMLPurifier/ConfigSchema/schema/Attr.txt | 4 +- .../schema/AutoFormat.AutoParagraph.txt | 60 +- .../ConfigSchema/schema/AutoFormat.Custom.txt | 24 +- .../ConfigSchema/schema/AutoFormat.Linkify.txt | 24 +- .../schema/AutoFormat.PurifierLinkify.txt | 24 +- .../ConfigSchema/schema/AutoFormat.txt | 4 +- .../AutoFormatParam.PurifierLinkifyDocURL.txt | 24 +- .../ConfigSchema/schema/AutoFormatParam.txt | 4 +- .../ConfigSchema/schema/CSS.DefinitionRev.txt | 22 +- .../ConfigSchema/schema/CSS.Proprietary.txt | 20 +- library/HTMLPurifier/ConfigSchema/schema/CSS.txt | 4 +- .../ConfigSchema/schema/Cache.DefinitionImpl.txt | 26 +- .../ConfigSchema/schema/Cache.SerializerPath.txt | 26 +- library/HTMLPurifier/ConfigSchema/schema/Cache.txt | 4 +- .../ConfigSchema/schema/Core.AggressivelyFixLt.txt | 26 +- .../ConfigSchema/schema/Core.CollectErrors.txt | 22 +- .../ConfigSchema/schema/Core.ColorKeywords.txt | 58 +- .../schema/Core.ConvertDocumentToFragment.txt | 26 +- .../Core.DirectLexLineNumberSyncInterval.txt | 34 +- .../ConfigSchema/schema/Core.Encoding.txt | 28 +- .../schema/Core.EscapeInvalidChildren.txt | 18 +- .../ConfigSchema/schema/Core.EscapeInvalidTags.txt | 12 +- .../schema/Core.EscapeNonASCIICharacters.txt | 24 +- .../ConfigSchema/schema/Core.HiddenElements.txt | 38 +- .../ConfigSchema/schema/Core.Language.txt | 22 +- .../ConfigSchema/schema/Core.LexerImpl.txt | 66 +- .../schema/Core.MaintainLineNumbers.txt | 32 +- .../ConfigSchema/schema/Core.RemoveInvalidImg.txt | 24 +- .../schema/Core.RemoveScriptContents.txt | 22 +- library/HTMLPurifier/ConfigSchema/schema/Core.txt | 4 +- .../HTMLPurifier/ConfigSchema/schema/Filter.txt | 4 +- .../FilterParam.ExtractStyleBlocksEscaping.txt | 28 +- .../schema/FilterParam.ExtractStyleBlocksScope.txt | 56 +- .../ConfigSchema/schema/HTML.Allowed.txt | 44 +- .../ConfigSchema/schema/HTML.AllowedAttributes.txt | 38 +- .../ConfigSchema/schema/HTML.AllowedElements.txt | 36 +- .../ConfigSchema/schema/HTML.AllowedModules.txt | 40 +- .../ConfigSchema/schema/HTML.BlockWrapper.txt | 36 +- .../ConfigSchema/schema/HTML.CoreModules.txt | 46 +- .../ConfigSchema/schema/HTML.CustomDoctype.txt | 20 +- .../ConfigSchema/schema/HTML.DefinitionID.txt | 66 +- .../ConfigSchema/schema/HTML.DefinitionRev.txt | 32 +- .../ConfigSchema/schema/HTML.Doctype.txt | 20 +- .../ConfigSchema/schema/HTML.Parent.txt | 24 +- .../ConfigSchema/schema/HTML.Strict.txt | 16 +- .../ConfigSchema/schema/HTML.TidyAdd.txt | 16 +- .../ConfigSchema/schema/HTML.TidyLevel.txt | 46 +- .../ConfigSchema/schema/HTML.TidyRemove.txt | 16 +- .../ConfigSchema/schema/HTML.Trusted.txt | 14 +- .../ConfigSchema/schema/HTML.XHTML.txt | 20 +- library/HTMLPurifier/ConfigSchema/schema/HTML.txt | 4 +- .../schema/Output.CommentScriptContents.txt | 18 +- .../ConfigSchema/schema/Output.Newline.txt | 26 +- .../ConfigSchema/schema/Output.TidyFormat.txt | 48 +- .../HTMLPurifier/ConfigSchema/schema/Output.txt | 4 +- .../ConfigSchema/schema/Test.ForceNoIconv.txt | 12 +- library/HTMLPurifier/ConfigSchema/schema/Test.txt | 4 +- .../ConfigSchema/schema/URI.AllowedSchemes.txt | 28 +- .../HTMLPurifier/ConfigSchema/schema/URI.Base.txt | 34 +- .../ConfigSchema/schema/URI.DefaultScheme.txt | 20 +- .../ConfigSchema/schema/URI.DefinitionID.txt | 22 +- .../ConfigSchema/schema/URI.DefinitionRev.txt | 22 +- .../ConfigSchema/schema/URI.Disable.txt | 26 +- .../ConfigSchema/schema/URI.DisableExternal.txt | 20 +- .../schema/URI.DisableExternalResources.txt | 24 +- .../ConfigSchema/schema/URI.DisableResources.txt | 24 +- .../HTMLPurifier/ConfigSchema/schema/URI.Host.txt | 38 +- .../ConfigSchema/schema/URI.HostBlacklist.txt | 16 +- .../ConfigSchema/schema/URI.MakeAbsolute.txt | 24 +- .../HTMLPurifier/ConfigSchema/schema/URI.Munge.txt | 164 +- .../schema/URI.OverrideAllowedSchemes.txt | 16 +- library/HTMLPurifier/ConfigSchema/schema/URI.txt | 4 +- .../DefinitionCache/Decorator/Template.php.in | 92 +- library/HTMLPurifier/HTMLModule/Object.php | 92 +- library/HTMLPurifier/Lexer/PH5P.php | 7812 ++++++++++---------- maintenance/PH5P.patch | 182 +- maintenance/phpt-modifications.patch | 208 +- plugins/phorum/Changelog | 48 +- tests/HTMLPurifier/HTMLModule/ObjectTest.php | 74 +- tests/HTMLPurifier/PHPT/loading/safe-includes.phpt | 24 +- .../Strategy/MakeWellFormed_InjectorTest.php | 190 +- .../Strategy/RemoveForeignElements_TidyTest.php | 86 +- .../Strategy/ValidateAttributes_IDTest.php | 124 +- .../Strategy/ValidateAttributes_TidyTest.php | 700 +- tests/PHPT/Controller/SimpleTest.php | 44 +- tests/PHPT/Reporter/SimpleTest.php | 150 +- 99 files changed, 6183 insertions(+), 6183 deletions(-) diff --git a/docs/specimens/LICENSE b/docs/specimens/LICENSE index 8b94b0d4..8a491ac9 100644 --- a/docs/specimens/LICENSE +++ b/docs/specimens/LICENSE @@ -1,8 +1,8 @@ -Licensing of Specimens - -Some files in this directory have different licenses: - -windows-live-mail-desktop-beta.html - donated by laacz, public domain -img.png - LGPL, from - -All other files are by me, and are licensed under LGPL. \ No newline at end of file +Licensing of Specimens + +Some files in this directory have different licenses: + +windows-live-mail-desktop-beta.html - donated by laacz, public domain +img.png - LGPL, from + +All other files are by me, and are licensed under LGPL. diff --git a/library/HTMLPurifier.safe-includes.php b/library/HTMLPurifier.safe-includes.php index 42acd76b..97db35ca 100644 --- a/library/HTMLPurifier.safe-includes.php +++ b/library/HTMLPurifier.safe-includes.php @@ -1,189 +1,189 @@ - - This directive turns on auto-paragraphing, where double newlines are - converted in to paragraphs whenever possible. Auto-paragraphing: -

-
    -
  • Always applies to inline elements or text in the root node,
    • -
  • Applies to inline elements or text with double newlines in nodes - that allow paragraph tags,
    • -
  • Applies to double newlines in paragraph tags
    • -
-

- p tags must be allowed for this directive to take effect. - We do not use br tags for paragraphing, as that is - semantically incorrect. -

-

- To prevent auto-paragraphing as a content-producer, refrain from using - double-newlines except to specify a new paragraph or in contexts where - it has special meaning (whitespace usually has no meaning except in - tags like pre, so this should not be difficult.) To prevent - the paragraphing of inline text adjacent to block elements, wrap them - in div tags (the behavior is slightly different outside of - the root node.) -

+AutoFormat.AutoParagraph +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ This directive turns on auto-paragraphing, where double newlines are + converted in to paragraphs whenever possible. Auto-paragraphing: +

+
    +
  • Always applies to inline elements or text in the root node,
    • +
  • Applies to inline elements or text with double newlines in nodes + that allow paragraph tags,
    • +
  • Applies to double newlines in paragraph tags
    • +
+

+ p tags must be allowed for this directive to take effect. + We do not use br tags for paragraphing, as that is + semantically incorrect. +

+

+ To prevent auto-paragraphing as a content-producer, refrain from using + double-newlines except to specify a new paragraph or in contexts where + it has special meaning (whitespace usually has no meaning except in + tags like pre, so this should not be difficult.) To prevent + the paragraphing of inline text adjacent to block elements, wrap them + in div tags (the behavior is slightly different outside of + the root node.) +

diff --git a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt index c5a363b3..a8bd4eb1 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Custom.txt @@ -1,12 +1,12 @@ -AutoFormat.Custom -TYPE: list -VERSION: 2.0.1 -DEFAULT: array() ---DESCRIPTION-- - -

- This directive can be used to add custom auto-format injectors. - Specify an array of injector names (class name minus the prefix) - or concrete implementations. Injector class must exist. -

- +AutoFormat.Custom +TYPE: list +VERSION: 2.0.1 +DEFAULT: array() +--DESCRIPTION-- + +

+ This directive can be used to add custom auto-format injectors. + Specify an array of injector names (class name minus the prefix) + or concrete implementations. Injector class must exist. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt index 554086f3..6c1cd7b6 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.Linkify.txt @@ -1,12 +1,12 @@ -AutoFormat.Linkify -TYPE: bool -VERSION: 2.0.1 -DEFAULT: false ---DESCRIPTION-- - -

- This directive turns on linkification, auto-linking http, ftp and - https URLs. a tags with the href attribute - must be allowed. -

- +AutoFormat.Linkify +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ This directive turns on linkification, auto-linking http, ftp and + https URLs. a tags with the href attribute + must be allowed. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt index c7bcaf28..cd7f0b8e 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.PurifierLinkify.txt @@ -1,12 +1,12 @@ -AutoFormat.PurifierLinkify -TYPE: bool -VERSION: 2.0.1 -DEFAULT: false ---DESCRIPTION-- - -

- Internal auto-formatter that converts configuration directives in - syntax %Namespace.Directive to links. a tags - with the href attribute must be allowed. -

- +AutoFormat.PurifierLinkify +TYPE: bool +VERSION: 2.0.1 +DEFAULT: false +--DESCRIPTION-- + +

+ Internal auto-formatter that converts configuration directives in + syntax %Namespace.Directive to links. a tags + with the href attribute must be allowed. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.txt b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.txt index 4a7b5521..c63fb699 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/AutoFormat.txt @@ -1,2 +1,2 @@ -AutoFormat -DESCRIPTION: Configuration for activating auto-formatting functionality (also known as Injectors) +AutoFormat +DESCRIPTION: Configuration for activating auto-formatting functionality (also known as Injectors) diff --git a/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.PurifierLinkifyDocURL.txt b/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.PurifierLinkifyDocURL.txt index 79d33580..11d3b4e1 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.PurifierLinkifyDocURL.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.PurifierLinkifyDocURL.txt @@ -1,12 +1,12 @@ -AutoFormatParam.PurifierLinkifyDocURL -TYPE: string -VERSION: 2.0.1 -DEFAULT: '#%s' ---DESCRIPTION-- - -

- Location of configuration documentation to link to, let %s substitute - into the configuration's namespace and directive names sans the percent - sign. -

- +AutoFormatParam.PurifierLinkifyDocURL +TYPE: string +VERSION: 2.0.1 +DEFAULT: '#%s' +--DESCRIPTION-- + +

+ Location of configuration documentation to link to, let %s substitute + into the configuration's namespace and directive names sans the percent + sign. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.txt b/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.txt index 0ed78846..95bffcd8 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/AutoFormatParam.txt @@ -1,2 +1,2 @@ -AutoFormatParam -DESCRIPTION: Configuration for customizing auto-formatting functionality +AutoFormatParam +DESCRIPTION: Configuration for customizing auto-formatting functionality diff --git a/library/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt b/library/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt index e1e59926..5b40de2a 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/CSS.DefinitionRev.txt @@ -1,11 +1,11 @@ -CSS.DefinitionRev -TYPE: int -VERSION: 2.0.0 -DEFAULT: 1 ---DESCRIPTION-- - -

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

- +CSS.DefinitionRev +TYPE: int +VERSION: 2.0.0 +DEFAULT: 1 +--DESCRIPTION-- + +

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

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt b/library/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt index c9c068fc..cc883dc5 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/CSS.Proprietary.txt @@ -1,10 +1,10 @@ -CSS.Proprietary -TYPE: bool -VERSION: 3.0.0 -DEFAULT: false ---DESCRIPTION-- - -

- Whether or not to allow safe, proprietary CSS values. -

- +CSS.Proprietary +TYPE: bool +VERSION: 3.0.0 +DEFAULT: false +--DESCRIPTION-- + +

+ Whether or not to allow safe, proprietary CSS values. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/CSS.txt b/library/HTMLPurifier/ConfigSchema/schema/CSS.txt index 060f5d37..8bafc4b3 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/CSS.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/CSS.txt @@ -1,2 +1,2 @@ -CSS -DESCRIPTION: Configuration regarding allowed CSS. +CSS +DESCRIPTION: Configuration regarding allowed CSS. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt b/library/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt index e9fa699a..192db1f9 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Cache.DefinitionImpl.txt @@ -1,13 +1,13 @@ -Cache.DefinitionImpl -TYPE: string/null -VERSION: 2.0.0 -DEFAULT: 'Serializer' ---DESCRIPTION-- - -This directive defines which method to use when caching definitions, -the complex data-type that makes HTML Purifier tick. Set to null -to disable caching (not recommended, as you will see a definite -performance degradation). - ---ALIASES-- -Core.DefinitionCache +Cache.DefinitionImpl +TYPE: string/null +VERSION: 2.0.0 +DEFAULT: 'Serializer' +--DESCRIPTION-- + +This directive defines which method to use when caching definitions, +the complex data-type that makes HTML Purifier tick. Set to null +to disable caching (not recommended, as you will see a definite +performance degradation). + +--ALIASES-- +Core.DefinitionCache diff --git a/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt b/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt index 3682cbb3..600c567e 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Cache.SerializerPath.txt @@ -1,13 +1,13 @@ -Cache.SerializerPath -TYPE: string/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -

- Absolute path with no trailing slash to store serialized definitions in. - Default is within the - HTML Purifier library inside DefinitionCache/Serializer. This - path must be writable by the webserver. -

- +Cache.SerializerPath +TYPE: string/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ Absolute path with no trailing slash to store serialized definitions in. + Default is within the + HTML Purifier library inside DefinitionCache/Serializer. This + path must be writable by the webserver. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/Cache.txt b/library/HTMLPurifier/ConfigSchema/schema/Cache.txt index 2f7aaa26..6edaae0c 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Cache.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Cache.txt @@ -1,2 +1,2 @@ -Cache -DESCRIPTION: Configuration for DefinitionCache and related subclasses. +Cache +DESCRIPTION: Configuration for DefinitionCache and related subclasses. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt index 0d60b89f..2f6d35b8 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.AggressivelyFixLt.txt @@ -1,13 +1,13 @@ -Core.AggressivelyFixLt -TYPE: bool -VERSION: 2.1.0 -DEFAULT: false ---DESCRIPTION-- - -This directive enables aggressive pre-filter fixes HTML Purifier can -perform in order to ensure that open angled-brackets do not get killed -during parsing stage. Enabling this will result in two preg_replace_callback -calls and one preg_replace call for every bit of HTML passed through here. -It is not necessary and will have no effect for PHP 4. - - +Core.AggressivelyFixLt +TYPE: bool +VERSION: 2.1.0 +DEFAULT: false +--DESCRIPTION-- + +This directive enables aggressive pre-filter fixes HTML Purifier can +perform in order to ensure that open angled-brackets do not get killed +during parsing stage. Enabling this will result in two preg_replace_callback +calls and one preg_replace call for every bit of HTML passed through here. +It is not necessary and will have no effect for PHP 4. + + diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt index dcf20563..ccaf2ae3 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.CollectErrors.txt @@ -1,11 +1,11 @@ -Core.CollectErrors -TYPE: bool -VERSION: 2.0.0 -DEFAULT: false ---DESCRIPTION-- - -Whether or not to collect errors found while filtering the document. This -is a useful way to give feedback to your users. Warning: -Currently this feature is very patchy and experimental, with lots of -possible error messages not yet implemented. It will not cause any -problems, but it may not help your users either. +Core.CollectErrors +TYPE: bool +VERSION: 2.0.0 +DEFAULT: false +--DESCRIPTION-- + +Whether or not to collect errors found while filtering the document. This +is a useful way to give feedback to your users. Warning: +Currently this feature is very patchy and experimental, with lots of +possible error messages not yet implemented. It will not cause any +problems, but it may not help your users either. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt index 28c96821..6ec36dbb 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.ColorKeywords.txt @@ -1,29 +1,29 @@ -Core.ColorKeywords -TYPE: hash -VERSION: 2.0.0 ---DEFAULT-- -array ( - 'maroon' => '#800000', - 'red' => '#FF0000', - 'orange' => '#FFA500', - 'yellow' => '#FFFF00', - 'olive' => '#808000', - 'purple' => '#800080', - 'fuchsia' => '#FF00FF', - 'white' => '#FFFFFF', - 'lime' => '#00FF00', - 'green' => '#008000', - 'navy' => '#000080', - 'blue' => '#0000FF', - 'aqua' => '#00FFFF', - 'teal' => '#008080', - 'black' => '#000000', - 'silver' => '#C0C0C0', - 'gray' => '#808080', -) ---DESCRIPTION-- - -Lookup array of color names to six digit hexadecimal number corresponding -to color, with preceding hash mark. Used when parsing colors. - - +Core.ColorKeywords +TYPE: hash +VERSION: 2.0.0 +--DEFAULT-- +array ( + 'maroon' => '#800000', + 'red' => '#FF0000', + 'orange' => '#FFA500', + 'yellow' => '#FFFF00', + 'olive' => '#808000', + 'purple' => '#800080', + 'fuchsia' => '#FF00FF', + 'white' => '#FFFFFF', + 'lime' => '#00FF00', + 'green' => '#008000', + 'navy' => '#000080', + 'blue' => '#0000FF', + 'aqua' => '#00FFFF', + 'teal' => '#008080', + 'black' => '#000000', + 'silver' => '#C0C0C0', + 'gray' => '#808080', +) +--DESCRIPTION-- + +Lookup array of color names to six digit hexadecimal number corresponding +to color, with preceding hash mark. Used when parsing colors. + + diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt index 0f03d3aa..3f832c10 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.ConvertDocumentToFragment.txt @@ -1,13 +1,13 @@ -Core.ConvertDocumentToFragment -TYPE: bool -DEFAULT: true ---DESCRIPTION-- - -This parameter determines whether or not the filter should convert -input that is a full document with html and body tags to a fragment -of just the contents of a body tag. This parameter is simply something -HTML Purifier can do during an edge-case: for most inputs, this -processing is not necessary. - ---ALIASES-- -Core.AcceptFullDocuments +Core.ConvertDocumentToFragment +TYPE: bool +DEFAULT: true +--DESCRIPTION-- + +This parameter determines whether or not the filter should convert +input that is a full document with html and body tags to a fragment +of just the contents of a body tag. This parameter is simply something +HTML Purifier can do during an edge-case: for most inputs, this +processing is not necessary. + +--ALIASES-- +Core.AcceptFullDocuments diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt index 392adb5a..1ecc6637 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.DirectLexLineNumberSyncInterval.txt @@ -1,17 +1,17 @@ -Core.DirectLexLineNumberSyncInterval -TYPE: int -VERSION: 2.0.0 -DEFAULT: 0 ---DESCRIPTION-- - -

- Specifies the number of tokens the DirectLex line number tracking - implementations should process before attempting to resyncronize the - current line count by manually counting all previous new-lines. When - at 0, this functionality is disabled. Lower values will decrease - performance, and this is only strictly necessary if the counting - algorithm is buggy (in which case you should report it as a bug). - This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is - not being used. -

- +Core.DirectLexLineNumberSyncInterval +TYPE: int +VERSION: 2.0.0 +DEFAULT: 0 +--DESCRIPTION-- + +

+ Specifies the number of tokens the DirectLex line number tracking + implementations should process before attempting to resyncronize the + current line count by manually counting all previous new-lines. When + at 0, this functionality is disabled. Lower values will decrease + performance, and this is only strictly necessary if the counting + algorithm is buggy (in which case you should report it as a bug). + This has no effect when %Core.MaintainLineNumbers is disabled or DirectLex is + not being used. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt index 9bca95c7..ab75dbd9 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.Encoding.txt @@ -1,14 +1,14 @@ -Core.Encoding -TYPE: istring -DEFAULT: 'utf-8' ---DESCRIPTION-- -If for some reason you are unable to convert all webpages to UTF-8, you can -use this directive as a stop-gap compatibility change to let HTML Purifier -deal with non UTF-8 input. This technique has notable deficiencies: -absolutely no characters outside of the selected character encoding will be -preserved, not even the ones that have been ampersand escaped (this is due -to a UTF-8 specific feature that automatically resolves all -entities), making it pretty useless for anything except the most I18N-blind -applications, although %Core.EscapeNonASCIICharacters offers fixes this -trouble with another tradeoff. This directive only accepts ISO-8859-1 if -iconv is not enabled. +Core.Encoding +TYPE: istring +DEFAULT: 'utf-8' +--DESCRIPTION-- +If for some reason you are unable to convert all webpages to UTF-8, you can +use this directive as a stop-gap compatibility change to let HTML Purifier +deal with non UTF-8 input. This technique has notable deficiencies: +absolutely no characters outside of the selected character encoding will be +preserved, not even the ones that have been ampersand escaped (this is due +to a UTF-8 specific feature that automatically resolves all +entities), making it pretty useless for anything except the most I18N-blind +applications, although %Core.EscapeNonASCIICharacters offers fixes this +trouble with another tradeoff. This directive only accepts ISO-8859-1 if +iconv is not enabled. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt index cca96c60..554d6a24 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidChildren.txt @@ -1,9 +1,9 @@ -Core.EscapeInvalidChildren -TYPE: bool -DEFAULT: false ---DESCRIPTION-- -When true, a child is found that is not allowed in the context of the -parent element will be transformed into text as if it were ASCII. When -false, that element and all internal tags will be dropped, though text will -be preserved. There is no option for dropping the element but preserving -child nodes. +Core.EscapeInvalidChildren +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When true, a child is found that is not allowed in the context of the +parent element will be transformed into text as if it were ASCII. When +false, that element and all internal tags will be dropped, though text will +be preserved. There is no option for dropping the element but preserving +child nodes. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt index 6e02a19b..779a573e 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeInvalidTags.txt @@ -1,6 +1,6 @@ -Core.EscapeInvalidTags -TYPE: bool -DEFAULT: false ---DESCRIPTION-- -When true, invalid tags will be written back to the document as plain text. -Otherwise, they are silently dropped. +Core.EscapeInvalidTags +TYPE: bool +DEFAULT: false +--DESCRIPTION-- +When true, invalid tags will be written back to the document as plain text. +Otherwise, they are silently dropped. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt index f8b7d38b..93b8a4b2 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.EscapeNonASCIICharacters.txt @@ -1,12 +1,12 @@ -Core.EscapeNonASCIICharacters -TYPE: bool -VERSION: 1.4.0 -DEFAULT: false ---DESCRIPTION-- -This directive overcomes a deficiency in %Core.Encoding by blindly -converting all non-ASCII characters into decimal numeric entities before -converting it to its native encoding. This means that even characters that -can be expressed in the non-UTF-8 encoding will be entity-ized, which can -be a real downer for encodings like Big5. It also assumes that the ASCII -repetoire is available, although this is the case for almost all encodings. -Anyway, use UTF-8! +Core.EscapeNonASCIICharacters +TYPE: bool +VERSION: 1.4.0 +DEFAULT: false +--DESCRIPTION-- +This directive overcomes a deficiency in %Core.Encoding by blindly +converting all non-ASCII characters into decimal numeric entities before +converting it to its native encoding. This means that even characters that +can be expressed in the non-UTF-8 encoding will be entity-ized, which can +be a real downer for encodings like Big5. It also assumes that the ASCII +repetoire is available, although this is the case for almost all encodings. +Anyway, use UTF-8! diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt index 0a86d96a..f317221c 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.HiddenElements.txt @@ -1,19 +1,19 @@ -Core.HiddenElements -TYPE: lookup ---DEFAULT-- -array ( - 'script' => true, - 'style' => true, -) ---DESCRIPTION-- - -

- This directive is a lookup array of elements which should have their - contents removed when they are not allowed by the HTML definition. - For example, the contents of a script tag are not - normally shown in a document, so if script tags are to be removed, - their contents should be removed to. This is opposed to a b - tag, which defines some presentational changes but does not hide its - contents. -

- +Core.HiddenElements +TYPE: lookup +--DEFAULT-- +array ( + 'script' => true, + 'style' => true, +) +--DESCRIPTION-- + +

+ This directive is a lookup array of elements which should have their + contents removed when they are not allowed by the HTML definition. + For example, the contents of a script tag are not + normally shown in a document, so if script tags are to be removed, + their contents should be removed to. This is opposed to a b + tag, which defines some presentational changes but does not hide its + contents. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.Language.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.Language.txt index 1be60037..38d7e661 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.Language.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.Language.txt @@ -1,11 +1,11 @@ -Core.Language -TYPE: string -VERSION: 2.0.0 -DEFAULT: 'en' ---DESCRIPTION-- - -ISO 639 language code for localizable things in HTML Purifier to use, -which is mainly error reporting. There is currently only an English (en) -translation, so this directive is currently useless. - - +Core.Language +TYPE: string +VERSION: 2.0.0 +DEFAULT: 'en' +--DESCRIPTION-- + +ISO 639 language code for localizable things in HTML Purifier to use, +which is mainly error reporting. There is currently only an English (en) +translation, so this directive is currently useless. + + diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt index 62125a47..c32a6f65 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.LexerImpl.txt @@ -1,33 +1,33 @@ -Core.LexerImpl -TYPE: mixed/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -

- This parameter determines what lexer implementation can be used. The - valid values are: -

-
-
null
-
- Recommended, the lexer implementation will be auto-detected based on - your PHP-version and configuration. -
-
string lexer identifier
-
- This is a slim way of manually overridding the implementation. - Currently recognized values are: DOMLex (the default PHP5 -implementation) - and DirectLex (the default PHP4 implementation). Only use this if - you know what you are doing: usually, the auto-detection will - manage things for cases you aren't even aware of. -
-
object lexer instance
-
- Super-advanced: you can specify your own, custom, implementation that - implements the interface defined by HTMLPurifier_Lexer. - I may remove this option simply because I don't expect anyone - to use it. -
-
+Core.LexerImpl +TYPE: mixed/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ This parameter determines what lexer implementation can be used. The + valid values are: +

+
+
null
+
+ Recommended, the lexer implementation will be auto-detected based on + your PHP-version and configuration. +
+
string lexer identifier
+
+ This is a slim way of manually overridding the implementation. + Currently recognized values are: DOMLex (the default PHP5 +implementation) + and DirectLex (the default PHP4 implementation). Only use this if + you know what you are doing: usually, the auto-detection will + manage things for cases you aren't even aware of. +
+
object lexer instance
+
+ Super-advanced: you can specify your own, custom, implementation that + implements the interface defined by HTMLPurifier_Lexer. + I may remove this option simply because I don't expect anyone + to use it. +
+
diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt index de10208f..00fa7550 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.MaintainLineNumbers.txt @@ -1,16 +1,16 @@ -Core.MaintainLineNumbers -TYPE: bool/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -

- If true, HTML Purifier will add line number information to all tokens. - This is useful when error reporting is turned on, but can result in - significant performance degradation and should not be used when - unnecessary. This directive must be used with the DirectLex lexer, - as the DOMLex lexer does not (yet) support this functionality. - If the value is null, an appropriate value will be selected based - on other configuration. -

- +Core.MaintainLineNumbers +TYPE: bool/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ If true, HTML Purifier will add line number information to all tokens. + This is useful when error reporting is turned on, but can result in + significant performance degradation and should not be used when + unnecessary. This directive must be used with the DirectLex lexer, + as the DOMLex lexer does not (yet) support this functionality. + If the value is null, an appropriate value will be selected based + on other configuration. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt index 7ac86b31..3b5c8fd0 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveInvalidImg.txt @@ -1,12 +1,12 @@ -Core.RemoveInvalidImg -TYPE: bool -DEFAULT: true -VERSION: 1.3.0 ---DESCRIPTION-- - -

- This directive enables pre-emptive URI checking in img - tags, as the attribute validation strategy is not authorized to - remove elements from the document. Revert to pre-1.3.0 behavior by setting to false. -

- +Core.RemoveInvalidImg +TYPE: bool +DEFAULT: true +VERSION: 1.3.0 +--DESCRIPTION-- + +

+ This directive enables pre-emptive URI checking in img + tags, as the attribute validation strategy is not authorized to + remove elements from the document. Revert to pre-1.3.0 behavior by setting to false. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt index 531718ba..1d0e9779 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.RemoveScriptContents.txt @@ -1,11 +1,11 @@ -Core.RemoveScriptContents -TYPE: bool/null -DEFAULT: NULL -VERSION: 2.0.0 -DEPRECATED-VERSION: 2.1.0 -DEPRECATED-USE: Core.HiddenElements ---DESCRIPTION-- -

- This directive enables HTML Purifier to remove not only script tags - but all of their contents. -

+Core.RemoveScriptContents +TYPE: bool/null +DEFAULT: NULL +VERSION: 2.0.0 +DEPRECATED-VERSION: 2.1.0 +DEPRECATED-USE: Core.HiddenElements +--DESCRIPTION-- +

+ This directive enables HTML Purifier to remove not only script tags + but all of their contents. +

diff --git a/library/HTMLPurifier/ConfigSchema/schema/Core.txt b/library/HTMLPurifier/ConfigSchema/schema/Core.txt index 3240014d..296982a5 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Core.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Core.txt @@ -1,2 +1,2 @@ -Core -DESCRIPTION: Core features that are always available. +Core +DESCRIPTION: Core features that are always available. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Filter.txt b/library/HTMLPurifier/ConfigSchema/schema/Filter.txt index 9fad43a8..cf5f89cd 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Filter.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Filter.txt @@ -1,2 +1,2 @@ -Filter -DESCRIPTION: Directives for turning filters on and off, or specifying custom filters. +Filter +DESCRIPTION: Directives for turning filters on and off, or specifying custom filters. diff --git a/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksEscaping.txt b/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksEscaping.txt index d20010c7..96ac5e5d 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksEscaping.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksEscaping.txt @@ -1,14 +1,14 @@ -FilterParam.ExtractStyleBlocksEscaping -TYPE: bool -VERSION: 3.0.0 -DEFAULT: true -ALIASES: Filter.ExtractStyleBlocksEscaping ---DESCRIPTION-- - -

- Whether or not to escape the dangerous characters <, > and & - as \3C, \3E and \26, respectively. This is can be safely set to false - if the contents of StyleBlocks will be placed in an external stylesheet, - where there is no risk of it being interpreted as HTML. -

- +FilterParam.ExtractStyleBlocksEscaping +TYPE: bool +VERSION: 3.0.0 +DEFAULT: true +ALIASES: Filter.ExtractStyleBlocksEscaping +--DESCRIPTION-- + +

+ Whether or not to escape the dangerous characters <, > and & + as \3C, \3E and \26, respectively. This is can be safely set to false + if the contents of StyleBlocks will be placed in an external stylesheet, + where there is no risk of it being interpreted as HTML. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksScope.txt b/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksScope.txt index ec29078d..366df445 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksScope.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/FilterParam.ExtractStyleBlocksScope.txt @@ -1,28 +1,28 @@ -FilterParam.ExtractStyleBlocksScope -TYPE: string/null -VERSION: 3.0.0 -DEFAULT: NULL -ALIASES: Filter.ExtractStyleBlocksScope ---DESCRIPTION-- - -

- If you would like users to be able to define external stylesheets, but - only allow them to specify CSS declarations for a specific node and - prevent them from fiddling with other elements, use this directive. - It accepts any valid CSS selector, and will prepend this to any - CSS declaration extracted from the document. For example, if this - directive is set to #user-content and a user uses the - selector a:hover, the final selector will be - #user-content a:hover. -

-

- The comma shorthand may be used; consider the above example, with - #user-content, #user-content2, the final selector will - be #user-content a:hover, #user-content2 a:hover. -

-

- Warning: It is possible for users to bypass this measure - using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML - Purifier, and I am working to get it fixed. Until then, HTML Purifier - performs a basic check to prevent this. -

+FilterParam.ExtractStyleBlocksScope +TYPE: string/null +VERSION: 3.0.0 +DEFAULT: NULL +ALIASES: Filter.ExtractStyleBlocksScope +--DESCRIPTION-- + +

+ If you would like users to be able to define external stylesheets, but + only allow them to specify CSS declarations for a specific node and + prevent them from fiddling with other elements, use this directive. + It accepts any valid CSS selector, and will prepend this to any + CSS declaration extracted from the document. For example, if this + directive is set to #user-content and a user uses the + selector a:hover, the final selector will be + #user-content a:hover. +

+

+ The comma shorthand may be used; consider the above example, with + #user-content, #user-content2, the final selector will + be #user-content a:hover, #user-content2 a:hover. +

+

+ Warning: It is possible for users to bypass this measure + using a naughty + selector. This is a bug in CSS Tidy 1.3, not HTML + Purifier, and I am working to get it fixed. Until then, HTML Purifier + performs a basic check to prevent this. +

diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt index 9329eb15..5fcd1244 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Allowed.txt @@ -1,22 +1,22 @@ -HTML.Allowed -TYPE: itext/null -VERSION: 2.0.0 -DEFAULT: NULL ---DESCRIPTION-- - -

- This is a convenience directive that rolls the functionality of - %HTML.AllowedElements and %HTML.AllowedAttributes into one directive. - Specify elements and attributes that are allowed using: - element1[attr1|attr2],element2.... 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. -

- +HTML.Allowed +TYPE: itext/null +VERSION: 2.0.0 +DEFAULT: NULL +--DESCRIPTION-- + +

+ This is a convenience directive that rolls the functionality of + %HTML.AllowedElements and %HTML.AllowedAttributes into one directive. + Specify elements and attributes that are allowed using: + element1[attr1|attr2],element2.... 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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt index 6ff12fc5..88e696e8 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedAttributes.txt @@ -1,19 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt index 031a3006..b667b3da 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedElements.txt @@ -1,18 +1,18 @@ -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. Note that this - method is subtractive: it does its job by taking away from HTML Purifier - usual feature set, so you cannot add a tag that HTML Purifier never - supported in the first place (like embed, form or head). If you - change this, you probably also want to change %HTML.AllowedAttributes. -

-

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

- +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. Note that this + method is subtractive: it does its job by taking away from HTML Purifier + usual feature set, so you cannot add a tag that HTML Purifier never + supported in the first place (like embed, form or head). If you + change this, you probably also want to change %HTML.AllowedAttributes. +

+

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

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt index 7b8367e1..85e39f76 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.AllowedModules.txt @@ -1,20 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt index 47fe1433..e12edb64 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.BlockWrapper.txt @@ -1,18 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt index 78bffdbe..c629f66b 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.CoreModules.txt @@ -1,23 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt index 4b6d39cf..ee410ff0 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.CustomDoctype.txt @@ -1,10 +1,10 @@ -HTML.CustomDoctype -TYPE: string/null -VERSION: 2.0.1 -DEFAULT: NULL ---DESCRIPTION-- - -A custom doctype for power-users who defined there own document -type. This directive only applies when %HTML.Doctype is blank. - - +HTML.CustomDoctype +TYPE: string/null +VERSION: 2.0.1 +DEFAULT: NULL +--DESCRIPTION-- + +A custom doctype for power-users who defined there own document +type. This directive only applies when %HTML.Doctype is blank. + + diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt index 07f6b67c..36a3e9da 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionID.txt @@ -1,33 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt index dfee8e77..bc084fa3 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.DefinitionRev.txt @@ -1,16 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt index 1c58e2a3..051cf20a 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Doctype.txt @@ -1,10 +1,10 @@ -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' +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' diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt index 0e680f62..ecc2f77b 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Parent.txt @@ -1,12 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt index 39f81796..c9697bde 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Strict.txt @@ -1,8 +1,8 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt index 7bf3c6d4..7fadf06c 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyAdd.txt @@ -1,8 +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. - +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. + diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt index 7b98bc7e..9383bbaa 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyLevel.txt @@ -1,23 +1,23 @@ -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' +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' diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt index 1e220695..4717f39f 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.TidyRemove.txt @@ -1,8 +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. - +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. + diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt index 9785137d..6a4015e7 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.Trusted.txt @@ -1,7 +1,7 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt index 7909203e..8cca4b05 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.XHTML.txt @@ -1,10 +1,10 @@ -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 +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 diff --git a/library/HTMLPurifier/ConfigSchema/schema/HTML.txt b/library/HTMLPurifier/ConfigSchema/schema/HTML.txt index 9b8b3a74..93500086 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/HTML.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/HTML.txt @@ -1,2 +1,2 @@ -HTML -DESCRIPTION: Configuration regarding allowed HTML. +HTML +DESCRIPTION: Configuration regarding allowed HTML. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt b/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt index 171b0fff..5a77edb4 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Output.CommentScriptContents.txt @@ -1,9 +1,9 @@ -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 +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 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt b/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt index 20215725..2dd17999 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Output.Newline.txt @@ -1,13 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt b/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt index 5d7f29d3..6d26c4de 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Output.TidyFormat.txt @@ -1,24 +1,24 @@ -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 +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 diff --git a/library/HTMLPurifier/ConfigSchema/schema/Output.txt b/library/HTMLPurifier/ConfigSchema/schema/Output.txt index 134e141f..abd4b1b3 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Output.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Output.txt @@ -1,2 +1,2 @@ -Output -DESCRIPTION: Configuration relating to the generation of (X)HTML. +Output +DESCRIPTION: Configuration relating to the generation of (X)HTML. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt b/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt index 99337628..2cd7067d 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Test.ForceNoIconv.txt @@ -1,6 +1,6 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/Test.txt b/library/HTMLPurifier/ConfigSchema/schema/Test.txt index fec6f8d8..a9928fec 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/Test.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/Test.txt @@ -1,2 +1,2 @@ -Test -DESCRIPTION: Developer testing configuration for our unit tests. +Test +DESCRIPTION: Developer testing configuration for our unit tests. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt index 2686bac4..cf1271c0 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.AllowedSchemes.txt @@ -1,14 +1,14 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt index a0f8d97b..f68b8259 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.Base.txt @@ -1,17 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt index 2f39c2fa..ba472eda 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DefaultScheme.txt @@ -1,10 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt index 20bfc1db..dd324a59 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionID.txt @@ -1,11 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt index 7dabdc6d..9049897b 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DefinitionRev.txt @@ -1,11 +1,11 @@ -URI.DefinitionRev -TYPE: int -VERSION: 2.1.0 -DEFAULT: 1 ---DESCRIPTION-- - -

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

- +URI.DefinitionRev +TYPE: int +VERSION: 2.1.0 +DEFAULT: 1 +--DESCRIPTION-- + +

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

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt index a97b2e29..85fe3df1 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.Disable.txt @@ -1,13 +1,13 @@ -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 +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 diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt index 6d3ceba8..5f9dc31f 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternal.txt @@ -1,10 +1,10 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt index 37f5d13f..af43b614 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableExternalResources.txt @@ -1,12 +1,12 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt index a4560514..2f4e5741 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.DisableResources.txt @@ -1,12 +1,12 @@ -URI.DisableResources -TYPE: bool -VERSION: 1.3.0 -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. -

- +URI.DisableResources +TYPE: bool +VERSION: 1.3.0 +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt index 15356ac2..48159407 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.Host.txt @@ -1,19 +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. -

- +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. +

+ diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt index 5f5cbc56..a62a3543 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.HostBlacklist.txt @@ -1,8 +1,8 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt index 2d2b40a5..0832b2cc 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.MakeAbsolute.txt @@ -1,12 +1,12 @@ -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. -

+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. +

diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt index 7743ac29..ed9e142d 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.Munge.txt @@ -1,82 +1,82 @@ -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: -

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
KeyDescriptionExample <a href="">
%r1 - The URI embeds a resource
(blank) - The URI is merely a link
%nThe name of the tag this URI came froma
%mThe name of the attribute this URI came fromhref
%pThe 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. -

+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: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
KeyDescriptionExample <a href="">
%r1 - The URI embeds a resource
(blank) - The URI is merely a link
%nThe name of the tag this URI came froma
%mThe name of the attribute this URI came fromhref
%pThe 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. +

diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt index c75b1331..e910ee54 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.OverrideAllowedSchemes.txt @@ -1,8 +1,8 @@ -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. +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. diff --git a/library/HTMLPurifier/ConfigSchema/schema/URI.txt b/library/HTMLPurifier/ConfigSchema/schema/URI.txt index 114ecb17..4bcdb95b 100644 --- a/library/HTMLPurifier/ConfigSchema/schema/URI.txt +++ b/library/HTMLPurifier/ConfigSchema/schema/URI.txt @@ -1,2 +1,2 @@ -URI -DESCRIPTION: Features regarding Uniform Resource Identifiers. +URI +DESCRIPTION: Features regarding Uniform Resource Identifiers. diff --git a/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in b/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in index 62235e22..d741764c 100644 --- a/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in +++ b/library/HTMLPurifier/DefinitionCache/Decorator/Template.php.in @@ -1,46 +1,46 @@ - to cater to legacy browsers: this - * module does not allow this sort of behavior - */ -class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule -{ - - public $name = 'Object'; - public $safe = false; - - public function setup($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', false, - array( - 'id' => 'ID', - 'name*' => 'Text', - 'type' => 'Text', - 'value' => 'Text', - 'valuetype' => 'Enum#data,ref,object' - ) - ); - - } - -} - + to cater to legacy browsers: this + * module does not allow this sort of behavior + */ +class HTMLPurifier_HTMLModule_Object extends HTMLPurifier_HTMLModule +{ + + public $name = 'Object'; + public $safe = false; + + public function setup($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' + ) + ); + + $this->addElement('param', false, 'Empty', false, + array( + 'id' => 'ID', + 'name*' => 'Text', + 'type' => 'Text', + 'value' => 'Text', + 'valuetype' => 'Enum#data,ref,object' + ) + ); + + } + +} + diff --git a/library/HTMLPurifier/Lexer/PH5P.php b/library/HTMLPurifier/Lexer/PH5P.php index 81659e50..fa1bf973 100644 --- a/library/HTMLPurifier/Lexer/PH5P.php +++ b/library/HTMLPurifier/Lexer/PH5P.php @@ -1,3906 +1,3906 @@ -normalize($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)-> // - getElementsByTagName('div')->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) { - $data = str_replace("\r\n", "\n", $data); - $data = str_replace("\r", null, $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 $this->dom; - } -} -?> +normalize($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)-> // + getElementsByTagName('div')->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) { + $data = str_replace("\r\n", "\n", $data); + $data = str_replace("\r", null, $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 $this->dom; + } +} +?> diff --git a/maintenance/PH5P.patch b/maintenance/PH5P.patch index bd9cd491..d9e489c1 100644 --- a/maintenance/PH5P.patch +++ b/maintenance/PH5P.patch @@ -1,102 +1,102 @@ --- C:\Users\Edward\Webs\htmlpurifier\maintenance\PH5P.php 2007-11-05 00:01:51.643585000 -0500 +++ C:\Users\Edward\Webs\htmlpurifier\maintenance/PH5P.new.php 2008-04-05 00:26:39.343160000 -0400 @@ -65,7 +65,7 @@ - - public function __construct($data) { - $data = str_replace("\r\n", "\n", $data); -- $date = str_replace("\r", null, $data); -+ $data = str_replace("\r", null, $data); - - $this->data = $data; - $this->char = -1; + + public function __construct($data) { + $data = str_replace("\r\n", "\n", $data); +- $date = str_replace("\r", null, $data); ++ $data = str_replace("\r", null, $data); + + $this->data = $data; + $this->char = -1; @@ -211,7 +211,10 @@ - // If nothing is returned, emit a U+0026 AMPERSAND character token. - // Otherwise, emit the character token that was returned. - $char = (!$entity) ? '&' : $entity; -- $this->emitToken($char); -+ $this->emitToken(array( -+ 'type' => self::CHARACTR, -+ 'data' => $char -+ )); - - // Finally, switch to the data state. - $this->state = 'data'; + // If nothing is returned, emit a U+0026 AMPERSAND character token. + // Otherwise, emit the character token that was returned. + $char = (!$entity) ? '&' : $entity; +- $this->emitToken($char); ++ $this->emitToken(array( ++ 'type' => self::CHARACTR, ++ 'data' => $char ++ )); + + // Finally, switch to the data state. + $this->state = 'data'; @@ -708,7 +711,7 @@ - } elseif($char === '&') { - /* U+0026 AMPERSAND (&) - Switch to the entity in attribute value state. */ -- $this->entityInAttributeValueState('non'); -+ $this->entityInAttributeValueState(); - - } elseif($char === '>') { - /* U+003E GREATER-THAN SIGN (>) + } elseif($char === '&') { + /* U+0026 AMPERSAND (&) + Switch to the entity in attribute value state. */ +- $this->entityInAttributeValueState('non'); ++ $this->entityInAttributeValueState(); + + } elseif($char === '>') { + /* U+003E GREATER-THAN SIGN (>) @@ -738,7 +741,8 @@ - ? '&' - : $entity; - -- $this->emitToken($char); -+ $last = count($this->token['attr']) - 1; -+ $this->token['attr'][$last]['value'] .= $char; - } - - private function bogusCommentState() { + ? '&' + : $entity; + +- $this->emitToken($char); ++ $last = count($this->token['attr']) - 1; ++ $this->token['attr'][$last]['value'] .= $char; + } + + private function bogusCommentState() { @@ -1066,6 +1070,11 @@ - $this->char++; - - if(in_array($id, $this->entities)) { -+ if ($e_name[$c-1] !== ';') { -+ if ($c < $len && $e_name[$c] == ';') { -+ $this->char++; // consume extra semicolon -+ } -+ } - $entity = $id; - break; - } + $this->char++; + + if(in_array($id, $this->entities)) { ++ if ($e_name[$c-1] !== ';') { ++ if ($c < $len && $e_name[$c] == ';') { ++ $this->char++; // consume extra semicolon ++ } ++ } + $entity = $id; + break; + } @@ -2084,7 +2093,7 @@ - /* Reconstruct the active formatting elements, if any. */ - $this->reconstructActiveFormattingElements(); - -- $this->insertElement($token); -+ $this->insertElement($token, true, true); - break; - } - break; + /* Reconstruct the active formatting elements, if any. */ + $this->reconstructActiveFormattingElements(); + +- $this->insertElement($token); ++ $this->insertElement($token, true, true); + break; + } + break; @@ -3465,7 +3474,18 @@ - } - } - -- private function insertElement($token, $append = true) { -+ private function insertElement($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 $attr) { + } + } + +- private function insertElement($token, $append = true) { ++ private function insertElement($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) { @@ -3659,7 +3679,7 @@ - } - } - -- private function generateImpliedEndTags(array $exclude = array()) { -+ private function generateImpliedEndTags($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 + } + } + +- private function generateImpliedEndTags(array $exclude = array()) { ++ private function generateImpliedEndTags($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 @@ -3673,7 +3693,8 @@ - } - } - -- private function getElementCategory($name) { -+ private function getElementCategory($node) { -+ $name = $node->tagName; - if(in_array($name, $this->special)) - return self::SPECIAL; - + } + } + +- private function getElementCategory($name) { ++ private function getElementCategory($node) { ++ $name = $node->tagName; + if(in_array($name, $this->special)) + return self::SPECIAL; + diff --git a/maintenance/phpt-modifications.patch b/maintenance/phpt-modifications.patch index df703ee1..4d135dc6 100644 --- a/maintenance/phpt-modifications.patch +++ b/maintenance/phpt-modifications.patch @@ -1,8 +1,8 @@ -Index: src/PHPT/Case.php -=================================================================== ---- src/PHPT/Case.php (revision 691) -+++ src/PHPT/Case.php (working copy) -@@ -28,17 +28,14 @@ +Index: src/PHPT/Case.php +=================================================================== +--- src/PHPT/Case.php (revision 691) ++++ src/PHPT/Case.php (working copy) +@@ -28,17 +28,14 @@ { $reporter->onCaseStart($this); try { @@ -26,7 +26,7 @@ Index: src/PHPT/Case.php } $reporter->onCasePass($this); } catch (PHPT_Case_VetoException $veto) { -@@ -46,7 +43,6 @@ +@@ -46,7 +43,6 @@ } catch (PHPT_Case_FailureException $failure) { $reporter->onCaseFail($this, $failure); } @@ -34,11 +34,11 @@ Index: src/PHPT/Case.php $reporter->onCaseEnd($this); } -Index: src/PHPT/Case/Validator/CgiRequired.php -=================================================================== ---- src/PHPT/Case/Validator/CgiRequired.php (revision 691) -+++ src/PHPT/Case/Validator/CgiRequired.php (working copy) -@@ -17,7 +17,6 @@ +Index: src/PHPT/Case/Validator/CgiRequired.php +=================================================================== +--- src/PHPT/Case/Validator/CgiRequired.php (revision 691) ++++ src/PHPT/Case/Validator/CgiRequired.php (working copy) +@@ -17,7 +17,6 @@ public function is(PHPT_Case $case) { $return = $case->sections->filterByInterface('CgiExecutable')->valid(); @@ -46,11 +46,11 @@ Index: src/PHPT/Case/Validator/CgiRequired.php return $return; } } -Index: src/PHPT/CodeRunner/CommandLine.php -=================================================================== ---- src/PHPT/CodeRunner/CommandLine.php (revision 691) -+++ src/PHPT/CodeRunner/CommandLine.php (working copy) -@@ -13,7 +13,7 @@ +Index: src/PHPT/CodeRunner/CommandLine.php +=================================================================== +--- src/PHPT/CodeRunner/CommandLine.php (revision 691) ++++ src/PHPT/CodeRunner/CommandLine.php (working copy) +@@ -13,7 +13,7 @@ $this->_filename = $runner->filename; $this->_ini = (string)$runner->ini; $this->_args = (string)$runner->args; @@ -59,45 +59,45 @@ Index: src/PHPT/CodeRunner/CommandLine.php $this->_post_filename = (string)$runner->post_filename; } -Index: src/PHPT/CodeRunner/Driver/WScriptShell.php -=================================================================== ---- src/PHPT/CodeRunner/Driver/WScriptShell.php (revision 691) -+++ src/PHPT/CodeRunner/Driver/WScriptShell.php (working copy) -@@ -23,9 +23,9 @@ - } - } - if ($found == false) { -- throw new PHPT_CodeRunner_InvalidExecutableException( -- 'unable to locate PHP executable: ' . $this->executable -- ); -+ //throw new PHPT_CodeRunner_InvalidExecutableException( -+ // 'unable to locate PHP executable: ' . $this->executable -+ //); - } - } - -@@ -69,7 +69,7 @@ - - $error = $this->_process->StdErr->ReadAll(); - if (!empty($error)) { -- throw new PHPT_CodeRunner_ExecutionException($error); -+ throw new PHPT_CodeRunner_ExecutionException($error, $this->_commandFactory()); - } - - return $this->_process->StdOut->ReadAll(); -@@ -93,6 +93,7 @@ - { - $return = ''; - foreach ($this->environment as $key => $value) { -+ $value = str_replace('&', '^&', $value); - $return .= "set {$key}={$value} & "; - } - return $return; -Index: src/PHPT/CodeRunner/Factory.php -=================================================================== ---- src/PHPT/CodeRunner/Factory.php (revision 691) -+++ src/PHPT/CodeRunner/Factory.php (working copy) -@@ -33,7 +33,13 @@ +Index: src/PHPT/CodeRunner/Driver/WScriptShell.php +=================================================================== +--- src/PHPT/CodeRunner/Driver/WScriptShell.php (revision 691) ++++ src/PHPT/CodeRunner/Driver/WScriptShell.php (working copy) +@@ -23,9 +23,9 @@ + } + } + if ($found == false) { +- throw new PHPT_CodeRunner_InvalidExecutableException( +- 'unable to locate PHP executable: ' . $this->executable +- ); ++ //throw new PHPT_CodeRunner_InvalidExecutableException( ++ // 'unable to locate PHP executable: ' . $this->executable ++ //); + } + } + +@@ -69,7 +69,7 @@ + + $error = $this->_process->StdErr->ReadAll(); + if (!empty($error)) { +- throw new PHPT_CodeRunner_ExecutionException($error); ++ throw new PHPT_CodeRunner_ExecutionException($error, $this->_commandFactory()); + } + + return $this->_process->StdOut->ReadAll(); +@@ -93,6 +93,7 @@ + { + $return = ''; + foreach ($this->environment as $key => $value) { ++ $value = str_replace('&', '^&', $value); + $return .= "set {$key}={$value} & "; + } + return $return; +Index: src/PHPT/CodeRunner/Factory.php +=================================================================== +--- src/PHPT/CodeRunner/Factory.php (revision 691) ++++ src/PHPT/CodeRunner/Factory.php (working copy) +@@ -33,7 +33,13 @@ 'php-cgi'; } @@ -112,11 +112,11 @@ Index: src/PHPT/CodeRunner/Factory.php $runner->executable = $runner->executable . '.exe'; } try { -Index: src/PHPT/Section/ModifiableAbstract.php -=================================================================== ---- src/PHPT/Section/ModifiableAbstract.php (revision 691) -+++ src/PHPT/Section/ModifiableAbstract.php (working copy) -@@ -15,12 +15,10 @@ +Index: src/PHPT/Section/ModifiableAbstract.php +=================================================================== +--- src/PHPT/Section/ModifiableAbstract.php (revision 691) ++++ src/PHPT/Section/ModifiableAbstract.php (working copy) +@@ -15,12 +15,10 @@ public function run(PHPT_Case $case) { @@ -133,11 +133,11 @@ Index: src/PHPT/Section/ModifiableAbstract.php } } -Index: src/PHPT/Section/SKIPIF.php -=================================================================== ---- src/PHPT/Section/SKIPIF.php (revision 691) -+++ src/PHPT/Section/SKIPIF.php (working copy) -@@ -3,10 +3,12 @@ +Index: src/PHPT/Section/SKIPIF.php +=================================================================== +--- src/PHPT/Section/SKIPIF.php (revision 691) ++++ src/PHPT/Section/SKIPIF.php (working copy) +@@ -3,10 +3,12 @@ class PHPT_Section_SKIPIF implements PHPT_Section_RunnableBefore { private $_data = null; @@ -150,7 +150,7 @@ Index: src/PHPT/Section/SKIPIF.php } public function run(PHPT_Case $case) -@@ -16,9 +18,7 @@ +@@ -16,9 +18,7 @@ // @todo refactor to PHPT_CodeRunner file_put_contents($filename, $this->_data); @@ -161,11 +161,11 @@ Index: src/PHPT/Section/SKIPIF.php unlink($filename); if (preg_match('/^skip( - (.*))?/', $response, $matches)) { -Index: src/PHPT/SectionList.php -=================================================================== ---- src/PHPT/SectionList.php (revision 691) -+++ src/PHPT/SectionList.php (working copy) -@@ -2,7 +2,6 @@ +Index: src/PHPT/SectionList.php +=================================================================== +--- src/PHPT/SectionList.php (revision 691) ++++ src/PHPT/SectionList.php (working copy) +@@ -2,7 +2,6 @@ class PHPT_SectionList implements Iterator { @@ -173,7 +173,7 @@ Index: src/PHPT/SectionList.php private $_sections = array(); private $_section_map = array(); private $_key_map = array(); -@@ -15,14 +14,12 @@ +@@ -15,14 +14,12 @@ } $name = strtoupper(str_replace('PHPT_Section_', '', get_class($section))); $key = $section instanceof PHPT_Section_Runnable ? $section->getPriority() . '.' . $name : $name; @@ -190,7 +190,7 @@ Index: src/PHPT/SectionList.php } public function current() -@@ -52,21 +49,23 @@ +@@ -52,21 +49,23 @@ public function filterByInterface($interface = null) { @@ -220,7 +220,7 @@ Index: src/PHPT/SectionList.php } public function has($name) -@@ -74,11 +73,11 @@ +@@ -74,11 +73,11 @@ if (!isset($this->_section_map[$name])) { return false; } @@ -234,11 +234,11 @@ Index: src/PHPT/SectionList.php + return $this->_sections[$this->_section_map[$key]]; } } -Index: tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt -=================================================================== ---- tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt (revision 691) -+++ tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt (working copy) -@@ -17,9 +17,9 @@ +Index: tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt +=================================================================== +--- tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt (revision 691) ++++ tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt (working copy) +@@ -17,9 +17,9 @@ // sanity check $obj = new FoobarIni(); @@ -250,11 +250,11 @@ Index: tests/CodeRunner/Driver/WScriptShell/injects-ini-settings.phpt unset($obj); -Index: tests/Section/File/restores-case-sections.phpt -=================================================================== ---- tests/Section/File/restores-case-sections.phpt (revision 691) -+++ tests/Section/File/restores-case-sections.phpt (working copy) -@@ -1,24 +0,0 @@ +Index: tests/Section/File/restores-case-sections.phpt +=================================================================== +--- tests/Section/File/restores-case-sections.phpt (revision 691) ++++ tests/Section/File/restores-case-sections.phpt (working copy) +@@ -1,24 +0,0 @@ ---TEST-- -After PHPT_Section_FILE::run(), the sections property of the provide $case object -is restored to its unfiltered state @@ -279,11 +279,11 @@ Index: tests/Section/File/restores-case-sections.phpt -===DONE=== ---EXPECT-- -===DONE=== -Index: tests/SectionList/filter-by-interface.phpt -=================================================================== ---- tests/SectionList/filter-by-interface.phpt (revision 691) -+++ tests/SectionList/filter-by-interface.phpt (working copy) -@@ -17,10 +17,10 @@ +Index: tests/SectionList/filter-by-interface.phpt +=================================================================== +--- tests/SectionList/filter-by-interface.phpt (revision 691) ++++ tests/SectionList/filter-by-interface.phpt (working copy) +@@ -17,10 +17,10 @@ $data = array_merge($runnable, $non_runnable); $list = new PHPT_SectionList($data); @@ -298,11 +298,11 @@ Index: tests/SectionList/filter-by-interface.phpt ?> ===DONE=== -Index: tests/SectionList/filter-resets-with-null.phpt -=================================================================== ---- tests/SectionList/filter-resets-with-null.phpt (revision 691) -+++ tests/SectionList/filter-resets-with-null.phpt (working copy) -@@ -1,36 +0,0 @@ +Index: tests/SectionList/filter-resets-with-null.phpt +=================================================================== +--- tests/SectionList/filter-resets-with-null.phpt (revision 691) ++++ tests/SectionList/filter-resets-with-null.phpt (working copy) +@@ -1,36 +0,0 @@ ---TEST-- -If you call filterByInterface() with null or no-value, the full dataset is restored ---FILE-- @@ -339,11 +339,11 @@ Index: tests/SectionList/filter-resets-with-null.phpt -===DONE=== ---EXPECT-- -===DONE=== -Index: tests/Util/Code/runAsFile-executes-in-file.phpt -=================================================================== ---- tests/Util/Code/runAsFile-executes-in-file.phpt (revision 691) -+++ tests/Util/Code/runAsFile-executes-in-file.phpt (working copy) -@@ -10,7 +10,7 @@ +Index: tests/Util/Code/runAsFile-executes-in-file.phpt +=================================================================== +--- tests/Util/Code/runAsFile-executes-in-file.phpt (revision 691) ++++ tests/Util/Code/runAsFile-executes-in-file.phpt (working copy) +@@ -10,7 +10,7 @@ $util = new PHPT_Util_Code($code); @@ -352,11 +352,11 @@ Index: tests/Util/Code/runAsFile-executes-in-file.phpt $result = $util->runAsFile($file); assert('$result == $file'); -Index: tests/Util/Code/runAsFile-returns-output-if-no-return.phpt -=================================================================== ---- tests/Util/Code/runAsFile-returns-output-if-no-return.phpt (revision 691) -+++ tests/Util/Code/runAsFile-returns-output-if-no-return.phpt (working copy) -@@ -9,7 +9,7 @@ +Index: tests/Util/Code/runAsFile-returns-output-if-no-return.phpt +=================================================================== +--- tests/Util/Code/runAsFile-returns-output-if-no-return.phpt (revision 691) ++++ tests/Util/Code/runAsFile-returns-output-if-no-return.phpt (working copy) +@@ -9,7 +9,7 @@ $util = new PHPT_Util_Code($code); diff --git a/plugins/phorum/Changelog b/plugins/phorum/Changelog index 4de9c636..998b967b 100644 --- a/plugins/phorum/Changelog +++ b/plugins/phorum/Changelog @@ -1,24 +1,24 @@ -Changelog HTMLPurifier : Phorum Mod -||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||| - -= KEY ==================== - # Breaks back-compat - ! Feature - - Bugfix - + Sub-comment - . Internal change -========================== - -Version 3.0.0.1 for Phorum 5.2, unknown release date -! 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 +Changelog HTMLPurifier : Phorum Mod +||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||| + += KEY ==================== + # Breaks back-compat + ! Feature + - Bugfix + + Sub-comment + . Internal change +========================== + +Version 3.0.0.1 for Phorum 5.2, unknown release date +! 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 diff --git a/tests/HTMLPurifier/HTMLModule/ObjectTest.php b/tests/HTMLPurifier/HTMLModule/ObjectTest.php index 12d9b0a4..81bbb50b 100644 --- a/tests/HTMLPurifier/HTMLModule/ObjectTest.php +++ b/tests/HTMLPurifier/HTMLModule/ObjectTest.php @@ -1,37 +1,37 @@ -config->set('HTML', 'Trusted', true); - } - - function testDefaultRemoval() { - $this->config->set('HTML', 'Trusted', false); - $this->assertResult( - '', '' - ); - } - - function testMinimal() { - $this->assertResult(''); - } - - function testStandardUseCase() { - $this->assertResult( -' - - - - -Windows Media player required -' - ); - } - - // more test-cases? - -} - +config->set('HTML', 'Trusted', true); + } + + function testDefaultRemoval() { + $this->config->set('HTML', 'Trusted', false); + $this->assertResult( + '', '' + ); + } + + function testMinimal() { + $this->assertResult(''); + } + + function testStandardUseCase() { + $this->assertResult( +' + + + + +Windows Media player required +' + ); + } + + // more test-cases? + +} + diff --git a/tests/HTMLPurifier/PHPT/loading/safe-includes.phpt b/tests/HTMLPurifier/PHPT/loading/safe-includes.phpt index 831a34f9..28b17e6e 100644 --- a/tests/HTMLPurifier/PHPT/loading/safe-includes.phpt +++ b/tests/HTMLPurifier/PHPT/loading/safe-includes.phpt @@ -1,12 +1,12 @@ ---TEST-- -HTMLPurifier.safe-includes.php loading test ---FILE-- -purify('Salsa!'); ---EXPECT-- -Salsa! +--TEST-- +HTMLPurifier.safe-includes.php loading test +--FILE-- +purify('Salsa!'); +--EXPECT-- +Salsa! diff --git a/tests/HTMLPurifier/Strategy/MakeWellFormed_InjectorTest.php b/tests/HTMLPurifier/Strategy/MakeWellFormed_InjectorTest.php index 3782c04a..039d00a6 100644 --- a/tests/HTMLPurifier/Strategy/MakeWellFormed_InjectorTest.php +++ b/tests/HTMLPurifier/Strategy/MakeWellFormed_InjectorTest.php @@ -1,95 +1,95 @@ -obj = new HTMLPurifier_Strategy_MakeWellFormed(); - $this->config->set('AutoFormat', 'AutoParagraph', true); - $this->config->set('AutoFormat', 'Linkify', true); - generate_mock_once('HTMLPurifier_Injector'); - } - - function testEndNotification() { - $mock = new HTMLPurifier_InjectorMock(); - $mock->skip = false; - $mock->expectAt(0, 'notifyEnd', array(new HTMLPurifier_Token_End('b'))); - $mock->expectAt(1, 'notifyEnd', array(new HTMLPurifier_Token_End('i'))); - $mock->expectCallCount('notifyEnd', 2); - $this->config->set('AutoFormat', 'AutoParagraph', false); - $this->config->set('AutoFormat', 'Linkify', false); - $this->config->set('AutoFormat', 'Custom', array($mock)); - $this->assertResult('asdf', 'asdf'); - } - - function testErrorRequiredElementNotAllowed() { - $this->config->set('HTML', 'Allowed', ''); - $this->expectError('Cannot enable AutoParagraph injector because p is not allowed'); - $this->expectError('Cannot enable Linkify injector because a is not allowed'); - $this->assertResult('Foobar'); - } - - function testErrorRequiredAttributeNotAllowed() { - $this->config->set('HTML', 'Allowed', 'a,p'); - $this->expectError('Cannot enable Linkify injector because a.href is not allowed'); - $this->assertResult('

http://example.com

'); - } - - function testOnlyAutoParagraph() { - $this->assertResult( - 'Foobar', - '

Foobar

' - ); - } - - function testParagraphWrappingOnlyLink() { - $this->assertResult( - 'http://example.com', - '

http://example.com

' - ); - } - - function testParagraphWrappingNodeContainingLink() { - $this->assertResult( - 'http://example.com', - '

http://example.com

' - ); - } - - function testParagraphWrappingPoorlyFormedNodeContainingLink() { - $this->assertResult( - 'http://example.com', - '

http://example.com

' - ); - } - - function testTwoParagraphsContainingOnlyOneLink() { - $this->assertResult( - "http://example.com\n\nhttp://dev.example.com", - '

http://example.com

http://dev.example.com

' - ); - } - - function testParagraphNextToDivWithLinks() { - $this->assertResult( - 'http://example.com
http://example.com
', - '

http://example.com

' - ); - } - - function testRealisticLinkInSentence() { - $this->assertResult( - 'This URL http://example.com is what you need', - '

This URL http://example.com is what you need

' - ); - } - - function testParagraphAfterLinkifiedURL() { - $this->assertResult( - "http://google.com\n\nb", - "

http://google.com

b

" - ); - } - -} +obj = new HTMLPurifier_Strategy_MakeWellFormed(); + $this->config->set('AutoFormat', 'AutoParagraph', true); + $this->config->set('AutoFormat', 'Linkify', true); + generate_mock_once('HTMLPurifier_Injector'); + } + + function testEndNotification() { + $mock = new HTMLPurifier_InjectorMock(); + $mock->skip = false; + $mock->expectAt(0, 'notifyEnd', array(new HTMLPurifier_Token_End('b'))); + $mock->expectAt(1, 'notifyEnd', array(new HTMLPurifier_Token_End('i'))); + $mock->expectCallCount('notifyEnd', 2); + $this->config->set('AutoFormat', 'AutoParagraph', false); + $this->config->set('AutoFormat', 'Linkify', false); + $this->config->set('AutoFormat', 'Custom', array($mock)); + $this->assertResult('asdf', 'asdf'); + } + + function testErrorRequiredElementNotAllowed() { + $this->config->set('HTML', 'Allowed', ''); + $this->expectError('Cannot enable AutoParagraph injector because p is not allowed'); + $this->expectError('Cannot enable Linkify injector because a is not allowed'); + $this->assertResult('Foobar'); + } + + function testErrorRequiredAttributeNotAllowed() { + $this->config->set('HTML', 'Allowed', 'a,p'); + $this->expectError('Cannot enable Linkify injector because a.href is not allowed'); + $this->assertResult('

http://example.com

'); + } + + function testOnlyAutoParagraph() { + $this->assertResult( + 'Foobar', + '

Foobar

' + ); + } + + function testParagraphWrappingOnlyLink() { + $this->assertResult( + 'http://example.com', + '

http://example.com

' + ); + } + + function testParagraphWrappingNodeContainingLink() { + $this->assertResult( + 'http://example.com', + '

http://example.com

' + ); + } + + function testParagraphWrappingPoorlyFormedNodeContainingLink() { + $this->assertResult( + 'http://example.com', + '

http://example.com

' + ); + } + + function testTwoParagraphsContainingOnlyOneLink() { + $this->assertResult( + "http://example.com\n\nhttp://dev.example.com", + '

http://example.com

http://dev.example.com

' + ); + } + + function testParagraphNextToDivWithLinks() { + $this->assertResult( + 'http://example.com
http://example.com
', + '

http://example.com

' + ); + } + + function testRealisticLinkInSentence() { + $this->assertResult( + 'This URL http://example.com is what you need', + '

This URL http://example.com is what you need

' + ); + } + + function testParagraphAfterLinkifiedURL() { + $this->assertResult( + "http://google.com\n\nb", + "

http://google.com

b

" + ); + } + +} diff --git a/tests/HTMLPurifier/Strategy/RemoveForeignElements_TidyTest.php b/tests/HTMLPurifier/Strategy/RemoveForeignElements_TidyTest.php index 57957080..24059114 100644 --- a/tests/HTMLPurifier/Strategy/RemoveForeignElements_TidyTest.php +++ b/tests/HTMLPurifier/Strategy/RemoveForeignElements_TidyTest.php @@ -1,43 +1,43 @@ -obj = new HTMLPurifier_Strategy_RemoveForeignElements(); - $this->config->set('HTML', 'TidyLevel', 'heavy'); - } - - function testCenterTransform() { - $this->assertResult( - '
Look I am Centered!
', - '
Look I am Centered!
' - ); - } - - function testFontTransform() { - $this->assertResult( - 'Big Warning!', - 'Big'. - ' Warning!' - ); - } - - function testTransformToForbiddenElement() { - $this->config->set('HTML', 'Allowed', 'div'); - $this->assertResult( - 'Big Warning!', - 'Big Warning!' - ); - } - - function testMenuTransform() { - $this->assertResult( - '
  • Item 1
    • ', - '
    • Item 1
    ' - ); - } - -} +obj = new HTMLPurifier_Strategy_RemoveForeignElements(); + $this->config->set('HTML', 'TidyLevel', 'heavy'); + } + + function testCenterTransform() { + $this->assertResult( + '
    Look I am Centered!
    ', + '
    Look I am Centered!
    ' + ); + } + + function testFontTransform() { + $this->assertResult( + 'Big Warning!', + 'Big'. + ' Warning!' + ); + } + + function testTransformToForbiddenElement() { + $this->config->set('HTML', 'Allowed', 'div'); + $this->assertResult( + 'Big Warning!', + 'Big Warning!' + ); + } + + function testMenuTransform() { + $this->assertResult( + '
  • Item 1
    • ', + '
    • Item 1
    ' + ); + } + +} diff --git a/tests/HTMLPurifier/Strategy/ValidateAttributes_IDTest.php b/tests/HTMLPurifier/Strategy/ValidateAttributes_IDTest.php index 5253705a..c9c28e21 100644 --- a/tests/HTMLPurifier/Strategy/ValidateAttributes_IDTest.php +++ b/tests/HTMLPurifier/Strategy/ValidateAttributes_IDTest.php @@ -1,62 +1,62 @@ -obj = new HTMLPurifier_Strategy_ValidateAttributes(); - $this->config->set('Attr', 'EnableID', true); - } - - - function testPreserveIDWhenEnabled() { - $this->assertResult('
    Preserve the ID.
    '); - } - - function testRemoveInvalidID() { - $this->assertResult( - '
    Kill the ID.
    ', - '
    Kill the ID.
    ' - ); - } - - function testRemoveDuplicateID() { - $this->assertResult( - '
    Valid
    Invalid
    ', - '
    Valid
    Invalid
    ' - ); - } - - function testAttributeKeyCaseInsensitivity() { - $this->assertResult( - '
    Convert ID to lowercase.
    ', - '
    Convert ID to lowercase.
    ' - ); - } - - function testTrimWhitespace() { - $this->assertResult( - '
    Trim whitespace.
    ', - '
    Trim whitespace.
    ' - ); - } - - function testIDBlacklist() { - $this->config->set('Attr', 'IDBlacklist', array('invalid')); - $this->assertResult( - '
    Invalid
    ', - '
    Invalid
    ' - ); - } - - function testNameConvertedToID() { - $this->config->set('HTML', 'TidyLevel', 'heavy'); - $this->assertResult( - '', - '' - ); - } - -} - +obj = new HTMLPurifier_Strategy_ValidateAttributes(); + $this->config->set('Attr', 'EnableID', true); + } + + + function testPreserveIDWhenEnabled() { + $this->assertResult('
    Preserve the ID.
    '); + } + + function testRemoveInvalidID() { + $this->assertResult( + '
    Kill the ID.
    ', + '
    Kill the ID.
    ' + ); + } + + function testRemoveDuplicateID() { + $this->assertResult( + '
    Valid
    Invalid
    ', + '
    Valid
    Invalid
    ' + ); + } + + function testAttributeKeyCaseInsensitivity() { + $this->assertResult( + '
    Convert ID to lowercase.
    ', + '
    Convert ID to lowercase.
    ' + ); + } + + function testTrimWhitespace() { + $this->assertResult( + '
    Trim whitespace.
    ', + '
    Trim whitespace.
    ' + ); + } + + function testIDBlacklist() { + $this->config->set('Attr', 'IDBlacklist', array('invalid')); + $this->assertResult( + '
    Invalid
    ', + '
    Invalid
    ' + ); + } + + function testNameConvertedToID() { + $this->config->set('HTML', 'TidyLevel', 'heavy'); + $this->assertResult( + '    ', + '' + ); + } + +} + diff --git a/tests/HTMLPurifier/Strategy/ValidateAttributes_TidyTest.php b/tests/HTMLPurifier/Strategy/ValidateAttributes_TidyTest.php index 928e093a..f4f4b2af 100644 --- a/tests/HTMLPurifier/Strategy/ValidateAttributes_TidyTest.php +++ b/tests/HTMLPurifier/Strategy/ValidateAttributes_TidyTest.php @@ -1,350 +1,350 @@ -obj = new HTMLPurifier_Strategy_ValidateAttributes(); - $this->config->set('HTML', 'TidyLevel', 'heavy'); - } - - function testConvertCenterAlign() { - $this->assertResult( - '

    Centered Headline

    ', - '

    Centered Headline

    ' - ); - } - - function testConvertRightAlign() { - $this->assertResult( - '

    Right-aligned Headline

    ', - '

    Right-aligned Headline

    ' - ); - } - - function testConvertLeftAlign() { - $this->assertResult( - '

    Left-aligned Headline

    ', - '

    Left-aligned Headline

    ' - ); - } - - function testConvertJustifyAlign() { - $this->assertResult( - '

    Justified Paragraph

    ', - '

    Justified Paragraph

    ' - ); - } - - function testRemoveInvalidAlign() { - $this->assertResult( - '

    Invalid Headline

    ', - '

    Invalid Headline

    ' - ); - } - - function testConvertTableLengths() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testTdConvertNowrap() { - $this->assertResult( - '', - '' - ); - } - - function testCaptionConvertAlignLeft() { - $this->assertResult( - '', - '' - ); - } - - function testCaptionConvertAlignRight() { - $this->assertResult( - '', - '' - ); - } - - function testCaptionConvertAlignTop() { - $this->assertResult( - '', - '' - ); - } - - function testCaptionConvertAlignBottom() { - $this->assertResult( - '', - '' - ); - } - - function testCaptionRemoveInvalidAlign() { - $this->assertResult( - '', - '' - ); - } - - function testTableConvertAlignLeft() { - $this->assertResult( - '', - '
    ' - ); - } - - function testTableConvertAlignCenter() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testTableConvertAlignRight() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testTableRemoveInvalidAlign() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testImgConvertAlignLeft() { - $this->assertResult( - 'foobar', - 'foobar' - ); - } - - function testImgConvertAlignRight() { - $this->assertResult( - 'foobar', - 'foobar' - ); - } - - function testImgConvertAlignBottom() { - $this->assertResult( - 'foobar', - 'foobar' - ); - } - - function testImgConvertAlignMiddle() { - $this->assertResult( - 'foobar', - 'foobar' - ); - } - - function testImgConvertAlignTop() { - $this->assertResult( - 'foobar', - 'foobar' - ); - } - - function testImgRemoveInvalidAlign() { - $this->assertResult( - 'foobar', - 'foobar' - ); - } - - function testBorderConvertHVSpace() { - $this->assertResult( - 'foo', - 'foo' - ); - } - - function testHrConvertSize() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testHrConvertNoshade() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testHrConvertAlignLeft() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testHrConvertAlignCenter() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testHrConvertAlignRight() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testHrRemoveInvalidAlign() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testBrConvertClearLeft() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testBrConvertClearRight() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testBrConvertClearAll() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testBrConvertClearNone() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testBrRemoveInvalidClear() { - $this->assertResult( - '
    ', - '
    ' - ); - } - - function testUlConvertTypeDisc() { - $this->assertResult( - '
      ', - '
        ' - ); - } - - function testUlConvertTypeSquare() { - $this->assertResult( - '
          ', - '
            ' - ); - } - - function testUlConvertTypeCircle() { - $this->assertResult( - '
              ', - '
                ' - ); - } - - function testUlConvertTypeCaseInsensitive() { - $this->assertResult( - '
                  ', - '
                    ' - ); - } - - function testUlRemoveInvalidType() { - $this->assertResult( - '
                      ', - '
                        ' - ); - } - - function testOlConvertType1() { - $this->assertResult( - '
                          ', - '
                            ' - ); - } - - function testOlConvertTypeLowerI() { - $this->assertResult( - '
                              ', - '
                                ' - ); - } - - function testOlConvertTypeUpperI() { - $this->assertResult( - '
                                  ', - '
                                    ' - ); - } - - function testOlConvertTypeLowerA() { - $this->assertResult( - '
                                      ', - '
                                        ' - ); - } - - function testOlConvertTypeUpperA() { - $this->assertResult( - '
                                          ', - '
                                            ' - ); - } - - function testOlRemoveInvalidType() { - $this->assertResult( - '
                                              ', - '
                                                ' - ); - } - - function testLiConvertTypeCircle() { - $this->assertResult( - '
                                              1. ', - '
                                              2. ' - ); - } - - function testLiConvertTypeA() { - $this->assertResult( - '
                                              3. ', - '
                                              4. ' - ); - } - - function testLiConvertTypeCaseSensitive() { - $this->assertResult( - '
                                              5. ', - '
                                              6. ' - ); - } - - -} - +obj = new HTMLPurifier_Strategy_ValidateAttributes(); + $this->config->set('HTML', 'TidyLevel', 'heavy'); + } + + function testConvertCenterAlign() { + $this->assertResult( + '

                                                Centered Headline

                                                ', + '

                                                Centered Headline

                                                ' + ); + } + + function testConvertRightAlign() { + $this->assertResult( + '

                                                Right-aligned Headline

                                                ', + '

                                                Right-aligned Headline

                                                ' + ); + } + + function testConvertLeftAlign() { + $this->assertResult( + '

                                                Left-aligned Headline

                                                ', + '

                                                Left-aligned Headline

                                                ' + ); + } + + function testConvertJustifyAlign() { + $this->assertResult( + '

                                                Justified Paragraph

                                                ', + '

                                                Justified Paragraph

                                                ' + ); + } + + function testRemoveInvalidAlign() { + $this->assertResult( + '

                                                Invalid Headline

                                                ', + '

                                                Invalid Headline

                                                ' + ); + } + + function testConvertTableLengths() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testTdConvertNowrap() { + $this->assertResult( + '    		', + '' + ); + } + + function testCaptionConvertAlignLeft() { + $this->assertResult( + '
    ', + '' + ); + } + + function testCaptionConvertAlignRight() { + $this->assertResult( + '', + '' + ); + } + + function testCaptionConvertAlignTop() { + $this->assertResult( + '', + '' + ); + } + + function testCaptionConvertAlignBottom() { + $this->assertResult( + '', + '' + ); + } + + function testCaptionRemoveInvalidAlign() { + $this->assertResult( + '', + '' + ); + } + + function testTableConvertAlignLeft() { + $this->assertResult( + '', + '
    ' + ); + } + + function testTableConvertAlignCenter() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testTableConvertAlignRight() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testTableRemoveInvalidAlign() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testImgConvertAlignLeft() { + $this->assertResult( + 'foobar', + 'foobar' + ); + } + + function testImgConvertAlignRight() { + $this->assertResult( + 'foobar', + 'foobar' + ); + } + + function testImgConvertAlignBottom() { + $this->assertResult( + 'foobar', + 'foobar' + ); + } + + function testImgConvertAlignMiddle() { + $this->assertResult( + 'foobar', + 'foobar' + ); + } + + function testImgConvertAlignTop() { + $this->assertResult( + 'foobar', + 'foobar' + ); + } + + function testImgRemoveInvalidAlign() { + $this->assertResult( + 'foobar', + 'foobar' + ); + } + + function testBorderConvertHVSpace() { + $this->assertResult( + 'foo', + 'foo' + ); + } + + function testHrConvertSize() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testHrConvertNoshade() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testHrConvertAlignLeft() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testHrConvertAlignCenter() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testHrConvertAlignRight() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testHrRemoveInvalidAlign() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testBrConvertClearLeft() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testBrConvertClearRight() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testBrConvertClearAll() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testBrConvertClearNone() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testBrRemoveInvalidClear() { + $this->assertResult( + '
    ', + '
    ' + ); + } + + function testUlConvertTypeDisc() { + $this->assertResult( + '
      ', + '
        ' + ); + } + + function testUlConvertTypeSquare() { + $this->assertResult( + '
          ', + '
            ' + ); + } + + function testUlConvertTypeCircle() { + $this->assertResult( + '
              ', + '
                ' + ); + } + + function testUlConvertTypeCaseInsensitive() { + $this->assertResult( + '
                  ', + '
                    ' + ); + } + + function testUlRemoveInvalidType() { + $this->assertResult( + '
                      ', + '
                        ' + ); + } + + function testOlConvertType1() { + $this->assertResult( + '
                          ', + '
                            ' + ); + } + + function testOlConvertTypeLowerI() { + $this->assertResult( + '
                              ', + '
                                ' + ); + } + + function testOlConvertTypeUpperI() { + $this->assertResult( + '
                                  ', + '
                                    ' + ); + } + + function testOlConvertTypeLowerA() { + $this->assertResult( + '
                                      ', + '
                                        ' + ); + } + + function testOlConvertTypeUpperA() { + $this->assertResult( + '
                                          ', + '
                                            ' + ); + } + + function testOlRemoveInvalidType() { + $this->assertResult( + '
                                              ', + '
                                                ' + ); + } + + function testLiConvertTypeCircle() { + $this->assertResult( + '
                                              1. ', + '
                                              2. ' + ); + } + + function testLiConvertTypeA() { + $this->assertResult( + '
                                              3. ', + '
                                              4. ' + ); + } + + function testLiConvertTypeCaseSensitive() { + $this->assertResult( + '
                                              5. ', + '
                                              6. ' + ); + } + + +} + diff --git a/tests/PHPT/Controller/SimpleTest.php b/tests/PHPT/Controller/SimpleTest.php index 91d63ad4..fb962bf6 100644 --- a/tests/PHPT/Controller/SimpleTest.php +++ b/tests/PHPT/Controller/SimpleTest.php @@ -1,22 +1,22 @@ -_path = $path; - parent::__construct($path); - } - - public function testPhpt() { - $suite = new PHPT_Suite(array($this->_path)); - $phpt_reporter = new PHPT_Reporter_SimpleTest($this->reporter); - $suite->run($phpt_reporter); - } - -} +_path = $path; + parent::__construct($path); + } + + public function testPhpt() { + $suite = new PHPT_Suite(array($this->_path)); + $phpt_reporter = new PHPT_Reporter_SimpleTest($this->reporter); + $suite->run($phpt_reporter); + } + +} diff --git a/tests/PHPT/Reporter/SimpleTest.php b/tests/PHPT/Reporter/SimpleTest.php index 86488b57..f3965ca2 100644 --- a/tests/PHPT/Reporter/SimpleTest.php +++ b/tests/PHPT/Reporter/SimpleTest.php @@ -1,75 +1,75 @@ -reporter = $reporter; - } - - // TODO: Figure out what the proper calls should be, since we've given - // each Suite its own UnitTestCase controller - - /** - * Called when the Reporter is started from a PHPT_Suite - * @todo Figure out if Suites can be named - */ - public function onSuiteStart(PHPT_Suite $suite) { - //$this->reporter->paintGroupStart('PHPT Suite', $suite->count()); - } - - /** - * Called when the Reporter is finished in a PHPT_Suite - */ - public function onSuiteEnd(PHPT_Suite $suite) { - //$this->reporter->paintGroupEnd('PHPT Suite'); - } - - /** - * Called when a Case is started - */ - public function onCaseStart(PHPT_Case $case) { - //$this->reporter->paintCaseStart($case->name); - } - - /** - * Called when a Case ends - */ - public function onCaseEnd(PHPT_Case $case) { - //$this->reporter->paintCaseEnd($case->name); - } - - /** - * Called when a Case runs without Exception - */ - public function onCasePass(PHPT_Case $case) { - $this->reporter->paintPass("{$case->name} in {$case->filename}"); - } - - /** - * Called when a PHPT_Case_VetoException is thrown during a Case's run() - */ - public function onCaseSkip(PHPT_Case $case, PHPT_Case_VetoException $veto) { - $this->reporter->paintSkip($veto->getMessage() . ' [' . $case->filename .']'); - } - - /** - * Called when any Exception other than a PHPT_Case_VetoException is encountered - * during a Case's run() - */ - public function onCaseFail(PHPT_Case $case, PHPT_Case_FailureException $failure) { - $this->reporter->paintFail($failure->getReason()); - } - - public function onParserError(Exception $exception) { - $this->reporter->paintException($exception); - } - -} +reporter = $reporter; + } + + // TODO: Figure out what the proper calls should be, since we've given + // each Suite its own UnitTestCase controller + + /** + * Called when the Reporter is started from a PHPT_Suite + * @todo Figure out if Suites can be named + */ + public function onSuiteStart(PHPT_Suite $suite) { + //$this->reporter->paintGroupStart('PHPT Suite', $suite->count()); + } + + /** + * Called when the Reporter is finished in a PHPT_Suite + */ + public function onSuiteEnd(PHPT_Suite $suite) { + //$this->reporter->paintGroupEnd('PHPT Suite'); + } + + /** + * Called when a Case is started + */ + public function onCaseStart(PHPT_Case $case) { + //$this->reporter->paintCaseStart($case->name); + } + + /** + * Called when a Case ends + */ + public function onCaseEnd(PHPT_Case $case) { + //$this->reporter->paintCaseEnd($case->name); + } + + /** + * Called when a Case runs without Exception + */ + public function onCasePass(PHPT_Case $case) { + $this->reporter->paintPass("{$case->name} in {$case->filename}"); + } + + /** + * Called when a PHPT_Case_VetoException is thrown during a Case's run() + */ + public function onCaseSkip(PHPT_Case $case, PHPT_Case_VetoException $veto) { + $this->reporter->paintSkip($veto->getMessage() . ' [' . $case->filename .']'); + } + + /** + * Called when any Exception other than a PHPT_Case_VetoException is encountered + * during a Case's run() + */ + public function onCaseFail(PHPT_Case $case, PHPT_Case_FailureException $failure) { + $this->reporter->paintFail($failure->getReason()); + } + + public function onParserError(Exception $exception) { + $this->reporter->paintException($exception); + } + +} -- 2.11.4.GIT