diff options
Diffstat (limited to '')
-rw-r--r-- | library/vendor/HTMLPurifier/Token.php | 100 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/Token/Comment.php | 38 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/Token/Empty.php | 15 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/Token/End.php | 24 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/Token/Start.php | 10 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/Token/Tag.php | 68 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/Token/Text.php | 53 | ||||
-rw-r--r-- | library/vendor/HTMLPurifier/TokenFactory.php | 118 |
8 files changed, 426 insertions, 0 deletions
diff --git a/library/vendor/HTMLPurifier/Token.php b/library/vendor/HTMLPurifier/Token.php new file mode 100644 index 0000000..84d3619 --- /dev/null +++ b/library/vendor/HTMLPurifier/Token.php @@ -0,0 +1,100 @@ +<?php + +/** + * Abstract base token class that all others inherit from. + */ +abstract class HTMLPurifier_Token +{ + /** + * Line number node was on in source document. Null if unknown. + * @type int + */ + public $line; + + /** + * Column of line node was on in source document. Null if unknown. + * @type int + */ + public $col; + + /** + * Lookup array of processing that this token is exempt from. + * Currently, valid values are "ValidateAttributes" and + * "MakeWellFormed_TagClosedError" + * @type array + */ + public $armor = array(); + + /** + * Used during MakeWellFormed. See Note [Injector skips] + * @type + */ + public $skip; + + /** + * @type + */ + public $rewind; + + /** + * @type + */ + public $carryover; + + /** + * @param string $n + * @return null|string + */ + public function __get($n) + { + if ($n === 'type') { + trigger_error('Deprecated type property called; use instanceof', E_USER_NOTICE); + switch (get_class($this)) { + case 'HTMLPurifier_Token_Start': + return 'start'; + case 'HTMLPurifier_Token_Empty': + return 'empty'; + case 'HTMLPurifier_Token_End': + return 'end'; + case 'HTMLPurifier_Token_Text': + return 'text'; + case 'HTMLPurifier_Token_Comment': + return 'comment'; + default: + return null; + } + } + } + + /** + * Sets the position of the token in the source document. + * @param int $l + * @param int $c + */ + public function position($l = null, $c = null) + { + $this->line = $l; + $this->col = $c; + } + + /** + * Convenience function for DirectLex settings line/col position. + * @param int $l + * @param int $c + */ + public function rawPosition($l, $c) + { + if ($c === -1) { + $l++; + } + $this->line = $l; + $this->col = $c; + } + + /** + * Converts a token into its corresponding node. + */ + abstract public function toNode(); +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/Token/Comment.php b/library/vendor/HTMLPurifier/Token/Comment.php new file mode 100644 index 0000000..23453c7 --- /dev/null +++ b/library/vendor/HTMLPurifier/Token/Comment.php @@ -0,0 +1,38 @@ +<?php + +/** + * Concrete comment token class. Generally will be ignored. + */ +class HTMLPurifier_Token_Comment extends HTMLPurifier_Token +{ + /** + * Character data within comment. + * @type string + */ + public $data; + + /** + * @type bool + */ + public $is_whitespace = true; + + /** + * Transparent constructor. + * + * @param string $data String comment data. + * @param int $line + * @param int $col + */ + public function __construct($data, $line = null, $col = null) + { + $this->data = $data; + $this->line = $line; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Comment($this->data, $this->line, $this->col); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/Token/Empty.php b/library/vendor/HTMLPurifier/Token/Empty.php new file mode 100644 index 0000000..78a95f5 --- /dev/null +++ b/library/vendor/HTMLPurifier/Token/Empty.php @@ -0,0 +1,15 @@ +<?php + +/** + * Concrete empty token class. + */ +class HTMLPurifier_Token_Empty extends HTMLPurifier_Token_Tag +{ + public function toNode() { + $n = parent::toNode(); + $n->empty = true; + return $n; + } +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/Token/End.php b/library/vendor/HTMLPurifier/Token/End.php new file mode 100644 index 0000000..59b38fd --- /dev/null +++ b/library/vendor/HTMLPurifier/Token/End.php @@ -0,0 +1,24 @@ +<?php + +/** + * Concrete end token class. + * + * @warning This class accepts attributes even though end tags cannot. This + * is for optimization reasons, as under normal circumstances, the Lexers + * do not pass attributes. + */ +class HTMLPurifier_Token_End extends HTMLPurifier_Token_Tag +{ + /** + * Token that started this node. + * Added by MakeWellFormed. Please do not edit this! + * @type HTMLPurifier_Token + */ + public $start; + + public function toNode() { + throw new Exception("HTMLPurifier_Token_End->toNode not supported!"); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/Token/Start.php b/library/vendor/HTMLPurifier/Token/Start.php new file mode 100644 index 0000000..019f317 --- /dev/null +++ b/library/vendor/HTMLPurifier/Token/Start.php @@ -0,0 +1,10 @@ +<?php + +/** + * Concrete start token class. + */ +class HTMLPurifier_Token_Start extends HTMLPurifier_Token_Tag +{ +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/Token/Tag.php b/library/vendor/HTMLPurifier/Token/Tag.php new file mode 100644 index 0000000..d643fa6 --- /dev/null +++ b/library/vendor/HTMLPurifier/Token/Tag.php @@ -0,0 +1,68 @@ +<?php + +/** + * Abstract class of a tag token (start, end or empty), and its behavior. + */ +abstract class HTMLPurifier_Token_Tag extends HTMLPurifier_Token +{ + /** + * Static bool marker that indicates the class is a tag. + * + * This allows us to check objects with <tt>!empty($obj->is_tag)</tt> + * without having to use a function call <tt>is_a()</tt>. + * @type bool + */ + public $is_tag = true; + + /** + * The lower-case name of the tag, like 'a', 'b' or 'blockquote'. + * + * @note Strictly speaking, XML tags are case sensitive, so we shouldn't + * be lower-casing them, but these tokens cater to HTML tags, which are + * insensitive. + * @type string + */ + public $name; + + /** + * Associative array of the tag's attributes. + * @type array + */ + public $attr = array(); + + /** + * Non-overloaded constructor, which lower-cases passed tag name. + * + * @param string $name String name. + * @param array $attr Associative array of attributes. + * @param int $line + * @param int $col + * @param array $armor + */ + public function __construct($name, $attr = array(), $line = null, $col = null, $armor = array()) + { + $this->name = ctype_lower($name) ? $name : strtolower($name); + foreach ($attr as $key => $value) { + // normalization only necessary when key is not lowercase + if (!ctype_lower($key)) { + $new_key = strtolower($key); + if (!isset($attr[$new_key])) { + $attr[$new_key] = $attr[$key]; + } + if ($new_key !== $key) { + unset($attr[$key]); + } + } + } + $this->attr = $attr; + $this->line = $line; + $this->col = $col; + $this->armor = $armor; + } + + public function toNode() { + return new HTMLPurifier_Node_Element($this->name, $this->attr, $this->line, $this->col, $this->armor); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/Token/Text.php b/library/vendor/HTMLPurifier/Token/Text.php new file mode 100644 index 0000000..f26a1c2 --- /dev/null +++ b/library/vendor/HTMLPurifier/Token/Text.php @@ -0,0 +1,53 @@ +<?php + +/** + * Concrete text token class. + * + * Text tokens comprise of regular parsed character data (PCDATA) and raw + * character data (from the CDATA sections). Internally, their + * data is parsed with all entities expanded. Surprisingly, the text token + * does have a "tag name" called #PCDATA, which is how the DTD represents it + * in permissible child nodes. + */ +class HTMLPurifier_Token_Text extends HTMLPurifier_Token +{ + + /** + * @type string + */ + public $name = '#PCDATA'; + /**< PCDATA tag name compatible with DTD. */ + + /** + * @type string + */ + public $data; + /**< Parsed character data of text. */ + + /** + * @type bool + */ + public $is_whitespace; + + /**< Bool indicating if node is whitespace. */ + + /** + * Constructor, accepts data and determines if it is whitespace. + * @param string $data String parsed character data. + * @param int $line + * @param int $col + */ + public function __construct($data, $line = null, $col = null) + { + $this->data = $data; + $this->is_whitespace = ctype_space($data); + $this->line = $line; + $this->col = $col; + } + + public function toNode() { + return new HTMLPurifier_Node_Text($this->data, $this->is_whitespace, $this->line, $this->col); + } +} + +// vim: et sw=4 sts=4 diff --git a/library/vendor/HTMLPurifier/TokenFactory.php b/library/vendor/HTMLPurifier/TokenFactory.php new file mode 100644 index 0000000..dea2446 --- /dev/null +++ b/library/vendor/HTMLPurifier/TokenFactory.php @@ -0,0 +1,118 @@ +<?php + +/** + * Factory for token generation. + * + * @note Doing some benchmarking indicates that the new operator is much + * slower than the clone operator (even discounting the cost of the + * constructor). This class is for that optimization. + * Other then that, there's not much point as we don't + * maintain parallel HTMLPurifier_Token hierarchies (the main reason why + * you'd want to use an abstract factory). + * @todo Port DirectLex to use this + */ +class HTMLPurifier_TokenFactory +{ + // p stands for prototype + + /** + * @type HTMLPurifier_Token_Start + */ + private $p_start; + + /** + * @type HTMLPurifier_Token_End + */ + private $p_end; + + /** + * @type HTMLPurifier_Token_Empty + */ + private $p_empty; + + /** + * @type HTMLPurifier_Token_Text + */ + private $p_text; + + /** + * @type HTMLPurifier_Token_Comment + */ + private $p_comment; + + /** + * Generates blank prototypes for cloning. + */ + public function __construct() + { + $this->p_start = new HTMLPurifier_Token_Start('', array()); + $this->p_end = new HTMLPurifier_Token_End(''); + $this->p_empty = new HTMLPurifier_Token_Empty('', array()); + $this->p_text = new HTMLPurifier_Token_Text(''); + $this->p_comment = new HTMLPurifier_Token_Comment(''); + } + + /** + * Creates a HTMLPurifier_Token_Start. + * @param string $name Tag name + * @param array $attr Associative array of attributes + * @return HTMLPurifier_Token_Start Generated HTMLPurifier_Token_Start + */ + public function createStart($name, $attr = array()) + { + $p = clone $this->p_start; + $p->__construct($name, $attr); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_End. + * @param string $name Tag name + * @return HTMLPurifier_Token_End Generated HTMLPurifier_Token_End + */ + public function createEnd($name) + { + $p = clone $this->p_end; + $p->__construct($name); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Empty. + * @param string $name Tag name + * @param array $attr Associative array of attributes + * @return HTMLPurifier_Token_Empty Generated HTMLPurifier_Token_Empty + */ + public function createEmpty($name, $attr = array()) + { + $p = clone $this->p_empty; + $p->__construct($name, $attr); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Text. + * @param string $data Data of text token + * @return HTMLPurifier_Token_Text Generated HTMLPurifier_Token_Text + */ + public function createText($data) + { + $p = clone $this->p_text; + $p->__construct($data); + return $p; + } + + /** + * Creates a HTMLPurifier_Token_Comment. + * @param string $data Data of comment token + * @return HTMLPurifier_Token_Comment Generated HTMLPurifier_Token_Comment + */ + public function createComment($data) + { + $p = clone $this->p_comment; + $p->__construct($data); + return $p; + } +} + +// vim: et sw=4 sts=4 |